~/f/openblas/RPMS.2017 ~/f/openblas ~/f/openblas RPMS.2017/libopenblas_openmp0-0.3.17-0.0.x86_64.rpm RPMS/libopenblas_openmp0-0.3.17-0.0.x86_64.rpm differ: byte 225, line 1 Comparing libopenblas_openmp0-0.3.17-0.0.x86_64.rpm to libopenblas_openmp0-0.3.17-0.0.x86_64.rpm comparing the rpm tags of libopenblas_openmp0 --- old-rpm-tags +++ new-rpm-tags @@ -146,7 +146,7 @@ /usr/lib64/libcblas.so.3 64 /usr/lib64/liblapack.so.3 64 /usr/lib64/libopenblas.so.0 64 -/usr/lib64/libopenblas_openmp.so.0 33124ffcecb599c6f0a92a404cd42a04ec2e7bafb8876717d169dadc88a82ff4 0 +/usr/lib64/libopenblas_openmp.so.0 6c46c90d6ba499d9c6fc348cf555e2c11406ef572bcbecc338c04ef405f08564 0 ___QF_CHECKSUM___ comparing rpmtags comparing RELEASE comparing PROVIDES comparing scripts comparing filelist comparing file checksum creating rename script RPM file checksum differs. Extracting packages /usr/lib64/libopenblas_openmp.so.0 differs in assembler output --- old /usr/lib64/libopenblas_openmp.so.0 (disasm) +++ new /usr/lib64/libopenblas_openmp.so.0 (disasm) @@ -107532,192 +107532,6 @@ data16 cs nopw offset(%rax,%rax,1) xchg %ax,%ax -trmv_kernel.lto_priv.23: - push %r15 - push %r14 - push %r13 - push %r12 - push %rbp - push %rbx - sub $something,%rsp - mov (%rdi),%rcx - mov offset(%rdi),%r13 - mov %rdi,offset(%rsp) - mov offset(%rdi),%rdx - mov %rcx,offset(%rsp) - mov offset(%rdi),%rcx - mov %r8,offset(%rsp) - mov %rcx,offset(%rsp) - mov offset(%rdi),%rcx - mov offset(%rdi),%rdi - mov %rcx,offset(%rsp) - test %rsi,%rsi - je - mov (%rsi),%r11 - mov offset(%rsi),%rbp - lea offset(,%r11,8),%rax - mov %rbp,offset(%rsp) - sub %r11,%rbp - lea offset(%r13,%rax,1),%r12 - cmp $something,%rdx - je - mov offset(%rsp),%rbx - mov offset(%rsp),%rsi - mov %r11,(%rsp) - sub %r11,%rdi - mov $something,%r8d - lea (%rbx,%rax,1),%rcx - mov %r11,%rax - imul %rdx,%rax - lea (%rsi,%rax,8),%rsi - mov offset(%rip),%rax # - mov (%rax),%r9 - mov %rax,offset(%rsp) - call *offset(%r9) - mov offset(%rsp),%rax - mov %rbx,offset(%rsp) - mov (%rsp),%r11 - mov offset(%rax),%rax - lea offset(,%rax,8),%rax - and $something,%rax - add %rbx,%rax - mov %rax,offset(%rsp) - mov %r11,(%rsp) - sub $something,%rsp - xor %r9d,%r9d - mov %r12,%rcx - mov offset(%rsp),%rbx - mov $something,%r8d - xor %edx,%edx - xor %esi,%esi - pxor %xmm0,%xmm0 - mov %rbp,%rdi - mov (%rbx),%rax - push $something - push $something - push $something - call *offset(%rax) - mov offset(%rsp),%r11 - add $something,%rsp - cmp offset(%rsp),%r11 - jge - mov (%rbx),%rax - mov offset(%rsp),%rcx - movslq (%rax),%rdx - lea offset(,%rcx,8),%r15 - mov %r15,%r10 - mov %r11,%r15 - nop - mov offset(%rsp),%rcx - sub %r15,%rcx - cmp %rdx,%rcx - cmovle %rcx,%rdx - lea (%rdx,%r15,1),%r9 - mov %rdx,offset(%rsp) - cmp %r15,%r9 - jle - mov offset(%rsp),%rdx - mov offset(%rsp),%rdi - mov %r15,offset(%rsp) - mov %r15,%rbx - mov offset(%rsp),%rsi - imul %r15,%rdx - lea (%r15,%rdx,1),%rcx - lea (%rdi,%rcx,8),%r12 - lea offset(%r15),%rcx - mov %r10,%r15 - add %rcx,%rdx - lea (%rsi,%rcx,8),%rbp - lea (%rdi,%rdx,8),%r14 - mov %r14,%rsi - mov %r9,%r14 - nopl offset(%rax) - movsd (%r12),%xmm0 - mulsd -offset(%rbp),%xmm0 - addsd offset(%r13,%rbx,8),%xmm0 - movsd %xmm0,offset(%r13,%rbx,8) - add $something,%rbx - cmp %r14,%rbx - jge - mov %r14,%rdi - mov %rsi,(%rsp) - mov %rbp,%rcx - mov $something,%r8d - sub %rbx,%rdi - mov $something,%edx - add %r15,%r12 - add $something,%rbp - call *offset(%rax) - mov offset(%rsp),%rax - mov (%rsp),%rsi - addsd -offset(%r13,%rbx,8),%xmm0 - mov (%rax),%rax - add %r15,%rsi - movsd %xmm0,-offset(%r13,%rbx,8) - jmp - cs nopw offset(%rax,%rax,1) - add %r15,%r12 - add %r15,%rsi - add $something,%rbp - cmp %r14,%rbx - jne - mov %r15,%r10 - mov offset(%rsp),%r15 - mov %r14,%r9 - mov offset(%rsp),%rcx - mov offset(%rcx),%rdx - cmp %r9,%rdx - jle - mov offset(%rsp),%r8 - mov offset(%rsp),%rsi - sub %r15,%rdx - mov %r10,(%rsp) - mov %r8,%rcx - imul %r15,%rcx - add %r9,%rcx - lea (%rsi,%rcx,8),%rcx - mov offset(%rsp),%rsi - push offset(%rsp) - push $something - sub %rsi,%rdx - mov %rdx,%rdi - lea offset(%r13,%r15,8),%rdx - push %rdx - push $something - mov offset(%rsp),%rdx - lea (%rdx,%r9,8),%r9 - mov offset(%rip),%rdx # <__PRETTY_FUNCTION__.0.lto_priv.0 + ofs> - movq %rdx,%xmm0 - xor %edx,%edx - call *offset(%rax) - mov offset(%rsp),%rax - mov offset(%rsp),%r10 - add $something,%rsp - mov (%rax),%rax - movslq (%rax),%rdx - add %rdx,%r15 - cmp %r15,offset(%rsp) - jg - add $something,%rsp - xor %eax,%eax - pop %rbx - pop %rbp - pop %r12 - pop %r13 - pop %r14 - pop %r15 - ret - mov offset(%rip),%rax # - mov %rax,offset(%rsp) - jmp - mov %rdi,offset(%rsp) - mov %rdi,%rbp - mov %r13,%r12 - xor %eax,%eax - xor %r11d,%r11d - jmp - cs nopw offset(%rax,%rax,1) - sgemv_thread_n: push %r15 push %r14 @@ -119091,7 +118905,7 @@ call <__stack_chk_fail@plt> nopw offset(%rax,%rax,1) -dtrmv_thread_TLN: /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .dynsym --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -3,103 +3,103 @@ Contents of section .dynsym: 2d8e0 00000000 00000000 00000000 00000000 ................ - 2d8f0 00000000 00000000 3caa0000 12000000 ........<....... + 2d8f0 00000000 00000000 28ab0000 12000000 ........(....... 2d900 00000000 00000000 00000000 00000000 ................ - 2d910 99990200 12000000 00000000 00000000 ................ - 2d920 00000000 00000000 24aa0000 12000000 ........$....... + 2d910 77990200 12000000 00000000 00000000 w............... + 2d920 00000000 00000000 10ab0000 12000000 ................ 2d930 00000000 00000000 00000000 00000000 ................ - 2d940 4eaa0000 12000000 00000000 00000000 N............... + 2d940 3aab0000 12000000 00000000 00000000 :............... 2d950 00000000 00000000 eaa10200 12000000 ................ 2d960 00000000 00000000 00000000 00000000 ................ - 2d970 79aa0000 12000000 00000000 00000000 y............... - 2d980 00000000 00000000 a5cb0200 12000000 ................ + 2d970 25ac0000 12000000 00000000 00000000 %............... + 2d980 00000000 00000000 2ccb0200 12000000 ........,....... 2d990 00000000 00000000 00000000 00000000 ................ - 2d9a0 87950200 12000000 00000000 00000000 ................ + 2d9a0 64950200 12000000 00000000 00000000 d............... 2d9b0 00000000 00000000 54690000 12000000 ........Ti...... 2d9c0 00000000 00000000 00000000 00000000 ................ 2d9d0 c7940200 12000000 00000000 00000000 ................ 2d9e0 00000000 00000000 46000000 22000000 ........F..."... 2d9f0 00000000 00000000 00000000 00000000 ................ - 2da00 fbc60200 12000000 00000000 00000000 ................ + 2da00 1ac80200 12000000 00000000 00000000 ................ 2da10 00000000 00000000 8c980200 12000000 ................ 2da20 00000000 00000000 00000000 00000000 ................ - 2da30 65950200 12000000 00000000 00000000 e............... - 2da40 00000000 00000000 43af0000 12000000 ........C....... + 2da30 42950200 12000000 00000000 00000000 B............... + 2da40 00000000 00000000 efb00000 12000000 ................ 2da50 00000000 00000000 00000000 00000000 ................ 2da60 2e6a0000 12000000 00000000 00000000 .j.............. - 2da70 00000000 00000000 1daa0000 12000000 ................ + 2da70 00000000 00000000 09ab0000 12000000 ................ 2da80 00000000 00000000 00000000 00000000 ................ 2da90 638b0200 12000000 00000000 00000000 c............... 2daa0 00000000 00000000 b7610000 12000000 .........a...... 2dab0 00000000 00000000 00000000 00000000 ................ - 2dac0 4baf0000 12000000 00000000 00000000 K............... - 2dad0 00000000 00000000 12af0000 12000000 ................ + 2dac0 f7b00000 12000000 00000000 00000000 ................ + 2dad0 00000000 00000000 beb00000 12000000 ................ 2dae0 00000000 00000000 00000000 00000000 ................ 2daf0 e3a10200 12000000 00000000 00000000 ................ - 2db00 00000000 00000000 a4cb0200 12000000 ................ + 2db00 00000000 00000000 2bcb0200 12000000 ........+....... 2db10 00000000 00000000 00000000 00000000 ................ - 2db20 9aaa0000 12000000 00000000 00000000 ................ + 2db20 46ac0000 12000000 00000000 00000000 F............... 2db30 00000000 00000000 60620000 12000000 ........`b...... 2db40 00000000 00000000 00000000 00000000 ................ 2db50 ca940200 12000000 00000000 00000000 ................ - 2db60 00000000 00000000 57ab0000 12000000 ........W....... + 2db60 00000000 00000000 03ad0000 12000000 ................ 2db70 00000000 00000000 00000000 00000000 ................ - 2db80 28b60200 12000000 00000000 00000000 (............... - 2db90 00000000 00000000 dd970200 12000000 ................ + 2db80 eab70200 12000000 00000000 00000000 ................ + 2db90 00000000 00000000 16980200 12000000 ................ 2dba0 00000000 00000000 00000000 00000000 ................ 2dbb0 b95e0000 12000000 00000000 00000000 .^.............. - 2dbc0 00000000 00000000 1bba0000 12000000 ................ + 2dbc0 00000000 00000000 c7bb0000 12000000 ................ 2dbd0 00000000 00000000 00000000 00000000 ................ - 2dbe0 35aa0000 12000000 00000000 00000000 5............... - 2dbf0 00000000 00000000 f5c90200 12000000 ................ + 2dbe0 21ab0000 12000000 00000000 00000000 !............... + 2dbf0 00000000 00000000 f6ca0200 12000000 ................ 2dc00 00000000 00000000 00000000 00000000 ................ - 2dc10 56aa0000 12000000 00000000 00000000 V............... - 2dc20 00000000 00000000 05af0000 12000000 ................ + 2dc10 02ac0000 12000000 00000000 00000000 ................ + 2dc20 00000000 00000000 b1b00000 12000000 ................ 2dc30 00000000 00000000 00000000 00000000 ................ 2dc40 a48b0200 12000000 00000000 00000000 ................ 2dc50 00000000 00000000 59ab0200 12000000 ........Y....... 2dc60 00000000 00000000 00000000 00000000 ................ 2dc70 d7610000 12000000 00000000 00000000 .a.............. - 2dc80 00000000 00000000 80af0000 12000000 ................ + 2dc80 00000000 00000000 2cb10000 12000000 ........,....... 2dc90 00000000 00000000 00000000 00000000 ................ - 2dca0 f4c90200 12000000 00000000 00000000 ................ - 2dcb0 00000000 00000000 85ac0000 12000000 ................ + 2dca0 f5ca0200 12000000 00000000 00000000 ................ + 2dcb0 00000000 00000000 31ae0000 12000000 ........1....... 2dcc0 00000000 00000000 00000000 00000000 ................ - 2dcd0 9eba0200 12000000 00000000 00000000 ................ - 2dce0 00000000 00000000 35c60200 12000000 ........5....... + 2dcd0 79ba0200 12000000 00000000 00000000 y............... + 2dce0 00000000 00000000 cbc70200 12000000 ................ 2dcf0 00000000 00000000 00000000 00000000 ................ - 2dd00 d8aa0000 12000000 00000000 00000000 ................ + 2dd00 84ac0000 12000000 00000000 00000000 ................ 2dd10 00000000 00000000 d9630000 12000000 .........c...... 2dd20 00000000 00000000 00000000 00000000 ................ - 2dd30 51ad0000 12000000 00000000 00000000 Q............... - 2dd40 00000000 00000000 37af0000 12000000 ........7....... + 2dd30 fdae0000 12000000 00000000 00000000 ................ + 2dd40 00000000 00000000 e3b00000 12000000 ................ 2dd50 00000000 00000000 00000000 00000000 ................ - 2dd60 f0c30200 12000000 00000000 00000000 ................ + 2dd60 18c50200 12000000 00000000 00000000 ................ 2dd70 00000000 00000000 d2630000 12000000 .........c...... 2dd80 00000000 00000000 00000000 00000000 ................ - 2dd90 27b60200 12000000 00000000 00000000 '............... + 2dd90 e9b70200 12000000 00000000 00000000 ................ 2dda0 00000000 00000000 4d690000 11000000 ........Mi...... 2ddb0 00000000 00000000 00000000 00000000 ................ 2ddc0 d18c0200 12000000 00000000 00000000 ................ 2ddd0 00000000 00000000 cf940200 12000000 ................ 2dde0 00000000 00000000 00000000 00000000 ................ 2ddf0 6d740000 12000000 00000000 00000000 mt.............. - 2de00 00000000 00000000 58ad0000 12000000 ........X....... + 2de00 00000000 00000000 04af0000 12000000 ................ 2de10 00000000 00000000 00000000 00000000 ................ - 2de20 8aaa0000 12000000 00000000 00000000 ................ - 2de30 00000000 00000000 72a70200 12000000 ........r....... + 2de20 36ac0000 12000000 00000000 00000000 6............... + 2de30 00000000 00000000 69a70200 12000000 ........i....... 2de40 00000000 00000000 00000000 00000000 ................ - 2de50 42900000 12000000 00000000 00000000 B............... - 2de60 00000000 00000000 44ab0000 12000000 ........D....... + 2de50 788f0000 12000000 00000000 00000000 x............... + 2de60 00000000 00000000 f0ac0000 12000000 ................ 2de70 00000000 00000000 00000000 00000000 ................ - 2de80 67aa0000 12000000 00000000 00000000 g............... - 2de90 00000000 00000000 d1af0000 12000000 ................ + 2de80 13ac0000 12000000 00000000 00000000 ................ + 2de90 00000000 00000000 7db10000 12000000 ........}....... 2dea0 00000000 00000000 00000000 00000000 ................ 2deb0 1da40200 12000000 00000000 00000000 ................ - 2dec0 00000000 00000000 86ac0000 12000000 ................ + 2dec0 00000000 00000000 32ae0000 12000000 ........2....... 2ded0 00000000 00000000 00000000 00000000 ................ 2dee0 c2940200 12000000 00000000 00000000 ................ - 2def0 00000000 00000000 2bb10000 12000000 ........+....... + 2def0 00000000 00000000 fbb20000 12000000 ................ 2df00 00000000 00000000 00000000 00000000 ................ 2df10 fd8e0200 12000000 00000000 00000000 ................ 2df20 00000000 00000000 63690000 12000000 ........ci...... @@ -111,19387 +111,19387 @@ 2df80 00000000 00000000 dfa10200 12000000 ................ 2df90 00000000 00000000 00000000 00000000 ................ 2dfa0 10000000 20000000 00000000 00000000 .... ........... - 2dfb0 00000000 00000000 49aa0000 12000000 ........I....... + 2dfb0 00000000 00000000 35ab0000 12000000 ........5....... 2dfc0 00000000 00000000 00000000 00000000 ................ - 2dfd0 9fba0200 12000000 00000000 00000000 ................ - 2dfe0 00000000 00000000 73a70200 12000000 ........s....... + 2dfd0 7aba0200 12000000 00000000 00000000 z............... + 2dfe0 00000000 00000000 6aa70200 12000000 ........j....... 2dff0 00000000 00000000 00000000 00000000 ................ 2e000 67b30200 12000000 00000000 00000000 g............... 2e010 00000000 00000000 e6a10200 12000000 ................ 2e020 00000000 00000000 00000000 00000000 ................ - 2e030 058b0200 12000000 00000000 00000000 ................ - 2e040 00000000 00000000 17b10000 12000000 ................ + 2e030 d48a0200 12000000 00000000 00000000 ................ + 2e040 00000000 00000000 e7b20000 12000000 ................ 2e050 00000000 00000000 00000000 00000000 ................ 2e060 01000000 20000000 00000000 00000000 .... ........... 2e070 00000000 00000000 2c000000 20000000 ........,... ... 2e080 00000000 00000000 00000000 00000000 ................ - 2e090 76c60000 12000000 00000000 00000000 v............... + 2e090 aec70000 12000000 00000000 00000000 ................ 2e0a0 00000000 00000000 cb080000 12000e00 ................ - 2e0b0 00866001 00000000 ca120000 00000000 ..`............. - 2e0c0 39f50200 12000e00 20193e01 00000000 9....... .>..... + 2e0b0 000a5e01 00000000 ca120000 00000000 ..^............. + 2e0c0 39f50200 12000e00 c0c23c01 00000000 9.........<..... 2e0d0 ae030000 00000000 80050100 12000e00 ................ - 2e0e0 c0ad4b00 00000000 93000000 00000000 ..K............. - 2e0f0 deac0200 12000e00 a06e0501 00000000 .........n...... + 2e0e0 10ad4b00 00000000 93000000 00000000 ..K............. + 2e0f0 deac0200 12000e00 10180401 00000000 ................ 2e100 79030000 00000000 09680000 12000e00 y........h...... 2e110 e06a1300 00000000 0b020000 00000000 .j.............. - 2e120 564c0300 12000e00 504f4b01 00000000 VL......POK..... + 2e120 564c0300 12000e00 f0f84901 00000000 VL........I..... 2e130 7a020000 00000000 4c1d0200 12000e00 z.......L....... - 2e140 a0db9900 00000000 46020000 00000000 ........F....... - 2e150 5b8b0200 12000e00 30e7cd00 00000000 [.......0....... + 2e140 00db9900 00000000 46020000 00000000 ........F....... + 2e150 5b8b0200 12000e00 7090cc00 00000000 [.......p....... 2e160 008d0000 00000000 ef290200 12000e00 .........)...... - 2e170 f0a0a200 00000000 ee140000 00000000 ................ - 2e180 0c430300 12000e00 909f4901 00000000 .C........I..... - 2e190 c7060000 00000000 fd7e0300 12000e00 .........~...... - 2e1a0 20145301 00000000 16000000 00000000 .S............. - 2e1b0 4f020200 12000e00 e0959000 00000000 O............... + 2e170 50a0a200 00000000 ee140000 00000000 P............... + 2e180 0c430300 12000e00 30494801 00000000 .C......0IH..... /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .dynstr --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -1926,89 +1926,89 @@ 81338 72656164 5f4e4c4e 00647472 6d765f74 read_NLN.dtrmv_t 81348 68726561 645f5455 55006474 726d765f hread_TUU.dtrmv_ 81358 74687265 61645f54 554e0064 74726d76 thread_TUN.dtrmv - 81368 5f746872 6561645f 544c5500 6474726d _thread_TLU.dtrm - 81378 765f7468 72656164 5f544c4e 00636762 v_thread_TLN.cgb - 81388 6d765f6e 00636762 6d765f74 00636762 mv_n.cgbmv_t.cgb - 81398 6d765f72 00636762 6d765f63 00636762 mv_r.cgbmv_c.cgb - 813a8 6d765f6f 00636762 6d765f75 00636762 mv_o.cgbmv_u.cgb - 813b8 6d765f73 00636762 6d765f64 00636862 mv_s.cgbmv_d.chb - 813c8 6d765f55 00636862 6d765f4c 00636862 mv_U.chbmv_L.chb - 813d8 6d765f56 00636862 6d765f4d 00636865 mv_V.chbmv_M.che - 813e8 725f5500 63686572 5f4c0063 6865725f r_U.cher_L.cher_ - 813f8 56006368 65725f4d 00636865 72325f55 V.cher_M.cher2_U - 81408 00636865 72325f4c 00636865 72325f56 .cher2_L.cher2_V - 81418 00636865 72325f4d 00636870 6d765f55 .cher2_M.chpmv_U - 81428 00636870 6d765f4c 00636870 6d765f56 .chpmv_L.chpmv_V - 81438 00636870 6d765f4d 00636870 725f5500 .chpmv_M.chpr_U. - 81448 63687072 5f4c0063 6870725f 56006368 chpr_L.chpr_V.ch - 81458 70725f4d 00636870 72325f55 00636870 pr_M.chpr2_U.chp - 81468 72325f4c 00636870 72325f56 00636870 r2_L.chpr2_V.chp - 81478 72325f4d 00637362 6d765f55 00637362 r2_M.csbmv_U.csb - 81488 6d765f4c 00637370 72325f55 00637370 mv_L.cspr2_U.csp - 81498 72325f4c 00637379 72325f55 00637379 r2_L.csyr2_U.csy - 814a8 72325f4c 00637462 6d765f4e 55550063 r2_L.ctbmv_NUU.c - 814b8 74626d76 5f4e554e 00637462 6d765f4e tbmv_NUN.ctbmv_N - 814c8 4c550063 74626d76 5f4e4c4e 00637462 LU.ctbmv_NLN.ctb - 814d8 6d765f54 55550063 74626d76 5f54554e mv_TUU.ctbmv_TUN - 814e8 00637462 6d765f54 4c550063 74626d76 .ctbmv_TLU.ctbmv - 814f8 5f544c4e 00637462 6d765f52 55550063 _TLN.ctbmv_RUU.c - 81508 74626d76 5f52554e 00637462 6d765f52 tbmv_RUN.ctbmv_R - 81518 4c550063 74626d76 5f524c4e 00637462 LU.ctbmv_RLN.ctb - 81528 6d765f43 55550063 74626d76 5f43554e mv_CUU.ctbmv_CUN - 81538 00637462 6d765f43 4c550063 74626d76 .ctbmv_CLU.ctbmv - 81548 5f434c4e 00637462 73765f4e 55550063 _CLN.ctbsv_NUU.c - 81558 74627376 5f4e554e 00637462 73765f4e tbsv_NUN.ctbsv_N - 81568 4c550063 74627376 5f4e4c4e 00637462 LU.ctbsv_NLN.ctb - 81578 73765f54 55550063 74627376 5f54554e sv_TUU.ctbsv_TUN - 81588 00637462 73765f54 4c550063 74627376 .ctbsv_TLU.ctbsv - 81598 5f544c4e 00637462 73765f52 55550063 _TLN.ctbsv_RUU.c - 815a8 74627376 5f52554e 00637462 73765f52 tbsv_RUN.ctbsv_R - 815b8 4c550063 74627376 5f524c4e 00637462 LU.ctbsv_RLN.ctb - 815c8 73765f43 55550063 74627376 5f43554e sv_CUU.ctbsv_CUN - 815d8 00637462 73765f43 4c550063 74627376 .ctbsv_CLU.ctbsv - 815e8 5f434c4e 00637470 6d765f4e 55550063 _CLN.ctpmv_NUU.c - 815f8 74706d76 5f4e554e 00637470 6d765f4e tpmv_NUN.ctpmv_N - 81608 4c550063 74706d76 5f4e4c4e 00637470 LU.ctpmv_NLN.ctp - 81618 6d765f54 55550063 74706d76 5f54554e mv_TUU.ctpmv_TUN - 81628 00637470 6d765f54 4c550063 74706d76 .ctpmv_TLU.ctpmv - 81638 5f544c4e 00637470 6d765f52 55550063 _TLN.ctpmv_RUU.c - 81648 74706d76 5f52554e 00637470 6d765f52 tpmv_RUN.ctpmv_R - 81658 4c550063 74706d76 5f524c4e 00637470 LU.ctpmv_RLN.ctp - 81668 6d765f43 55550063 74706d76 5f43554e mv_CUU.ctpmv_CUN - 81678 00637470 6d765f43 4c550063 74706d76 .ctpmv_CLU.ctpmv - 81688 5f434c4e 00637470 73765f4e 55550063 _CLN.ctpsv_NUU.c - 81698 74707376 5f4e554e 00637470 73765f4e tpsv_NUN.ctpsv_N - 816a8 4c550063 74707376 5f4e4c4e 00637470 LU.ctpsv_NLN.ctp - 816b8 73765f54 55550063 74707376 5f54554e sv_TUU.ctpsv_TUN - 816c8 00637470 73765f54 4c550063 74707376 .ctpsv_TLU.ctpsv - 816d8 5f544c4e 00637470 73765f52 55550063 _TLN.ctpsv_RUU.c - 816e8 74707376 5f52554e 00637470 73765f52 tpsv_RUN.ctpsv_R - 816f8 4c550063 74707376 5f524c4e 00637470 LU.ctpsv_RLN.ctp - 81708 73765f43 55550063 74707376 5f43554e sv_CUU.ctpsv_CUN - 81718 00637470 73765f43 4c550063 74707376 .ctpsv_CLU.ctpsv - 81728 5f434c4e 00637472 6d765f4e 55550063 _CLN.ctrmv_NUU.c - 81738 74726d76 5f4e554e 00637472 6d765f4e trmv_NUN.ctrmv_N - 81748 4c550063 74726d76 5f4e4c4e 00637472 LU.ctrmv_NLN.ctr - 81758 6d765f54 55550063 74726d76 5f54554e mv_TUU.ctrmv_TUN - 81768 00637472 6d765f54 4c550063 74726d76 .ctrmv_TLU.ctrmv - 81778 5f544c4e 00637472 6d765f52 55550063 _TLN.ctrmv_RUU.c - 81788 74726d76 5f52554e 00637472 6d765f52 trmv_RUN.ctrmv_R - 81798 4c550063 74726d76 5f524c4e 00637472 LU.ctrmv_RLN.ctr - 817a8 6d765f43 55550063 74726d76 5f43554e mv_CUU.ctrmv_CUN - 817b8 00637472 6d765f43 4c550063 74726d76 .ctrmv_CLU.ctrmv - 817c8 5f434c4e 00637472 73765f4e 55550063 _CLN.ctrsv_NUU.c - 817d8 74727376 5f4e554e 00637472 73765f4e trsv_NUN.ctrsv_N - 817e8 4c550063 74727376 5f4e4c4e 00637472 LU.ctrsv_NLN.ctr - 817f8 73765f54 55550063 74727376 5f54554e sv_TUU.ctrsv_TUN - 81808 00637472 73765f54 4c550063 74727376 .ctrsv_TLU.ctrsv - 81818 5f544c4e 00637472 73765f52 55550063 _TLN.ctrsv_RUU.c - 81828 74727376 5f52554e 00637472 73765f52 trsv_RUN.ctrsv_R - 81838 4c550063 74727376 5f524c4e 00637472 LU.ctrsv_RLN.ctr - 81848 73765f43 55550063 74727376 5f43554e sv_CUU.ctrsv_CUN - 81858 00637472 73765f43 4c550063 74727376 .ctrsv_CLU.ctrsv - 81868 5f434c4e 00637370 6d765f55 00637370 _CLN.cspmv_U.csp - 81878 6d765f4c 00637370 725f5500 63737072 mv_L.cspr_U.cspr - 81888 5f4c0063 7379725f 55006373 79725f4c _L.csyr_U.csyr_L + 81368 5f746872 6561645f 544c5500 6367626d _thread_TLU.cgbm + 81378 765f6e00 6367626d 765f7400 6367626d v_n.cgbmv_t.cgbm + 81388 765f7200 6367626d 765f6300 6367626d v_r.cgbmv_c.cgbm + 81398 765f6f00 6367626d 765f7500 6367626d v_o.cgbmv_u.cgbm + 813a8 765f7300 6367626d 765f6400 6368626d v_s.cgbmv_d.chbm + 813b8 765f5500 6368626d 765f4c00 6368626d v_U.chbmv_L.chbm + 813c8 765f5600 6368626d 765f4d00 63686572 v_V.chbmv_M.cher + 813d8 5f550063 6865725f 4c006368 65725f56 _U.cher_L.cher_V + 813e8 00636865 725f4d00 63686572 325f5500 .cher_M.cher2_U. + 813f8 63686572 325f4c00 63686572 325f5600 cher2_L.cher2_V. + 81408 63686572 325f4d00 6368706d 765f5500 cher2_M.chpmv_U. + 81418 6368706d 765f4c00 6368706d 765f5600 chpmv_L.chpmv_V. + 81428 6368706d 765f4d00 63687072 5f550063 chpmv_M.chpr_U.c + 81438 6870725f 4c006368 70725f56 00636870 hpr_L.chpr_V.chp + 81448 725f4d00 63687072 325f5500 63687072 r_M.chpr2_U.chpr + 81458 325f4c00 63687072 325f5600 63687072 2_L.chpr2_V.chpr + 81468 325f4d00 6373626d 765f5500 6373626d 2_M.csbmv_U.csbm + 81478 765f4c00 63737072 325f5500 63737072 v_L.cspr2_U.cspr + 81488 325f4c00 63737972 325f5500 63737972 2_L.csyr2_U.csyr + 81498 325f4c00 6374626d 765f4e55 55006374 2_L.ctbmv_NUU.ct + 814a8 626d765f 4e554e00 6374626d 765f4e4c bmv_NUN.ctbmv_NL + 814b8 55006374 626d765f 4e4c4e00 6374626d U.ctbmv_NLN.ctbm + 814c8 765f5455 55006374 626d765f 54554e00 v_TUU.ctbmv_TUN. + 814d8 6374626d 765f544c 55006374 626d765f ctbmv_TLU.ctbmv_ + 814e8 544c4e00 6374626d 765f5255 55006374 TLN.ctbmv_RUU.ct + 814f8 626d765f 52554e00 6374626d 765f524c bmv_RUN.ctbmv_RL + 81508 55006374 626d765f 524c4e00 6374626d U.ctbmv_RLN.ctbm + 81518 765f4355 55006374 626d765f 43554e00 v_CUU.ctbmv_CUN. + 81528 6374626d 765f434c 55006374 626d765f ctbmv_CLU.ctbmv_ + 81538 434c4e00 63746273 765f4e55 55006374 CLN.ctbsv_NUU.ct + 81548 6273765f 4e554e00 63746273 765f4e4c bsv_NUN.ctbsv_NL + 81558 55006374 6273765f 4e4c4e00 63746273 U.ctbsv_NLN.ctbs + 81568 765f5455 55006374 6273765f 54554e00 v_TUU.ctbsv_TUN. + 81578 63746273 765f544c 55006374 6273765f ctbsv_TLU.ctbsv_ + 81588 544c4e00 63746273 765f5255 55006374 TLN.ctbsv_RUU.ct + 81598 6273765f 52554e00 63746273 765f524c bsv_RUN.ctbsv_RL + 815a8 55006374 6273765f 524c4e00 63746273 U.ctbsv_RLN.ctbs + 815b8 765f4355 55006374 6273765f 43554e00 v_CUU.ctbsv_CUN. + 815c8 63746273 765f434c 55006374 6273765f ctbsv_CLU.ctbsv_ + 815d8 434c4e00 6374706d 765f4e55 55006374 CLN.ctpmv_NUU.ct + 815e8 706d765f 4e554e00 6374706d 765f4e4c pmv_NUN.ctpmv_NL + 815f8 55006374 706d765f 4e4c4e00 6374706d U.ctpmv_NLN.ctpm + 81608 765f5455 55006374 706d765f 54554e00 v_TUU.ctpmv_TUN. + 81618 6374706d 765f544c 55006374 706d765f ctpmv_TLU.ctpmv_ + 81628 544c4e00 6374706d 765f5255 55006374 TLN.ctpmv_RUU.ct + 81638 706d765f 52554e00 6374706d 765f524c pmv_RUN.ctpmv_RL + 81648 55006374 706d765f 524c4e00 6374706d U.ctpmv_RLN.ctpm + 81658 765f4355 55006374 706d765f 43554e00 v_CUU.ctpmv_CUN. + 81668 6374706d 765f434c 55006374 706d765f ctpmv_CLU.ctpmv_ + 81678 434c4e00 63747073 765f4e55 55006374 CLN.ctpsv_NUU.ct + 81688 7073765f 4e554e00 63747073 765f4e4c psv_NUN.ctpsv_NL + 81698 55006374 7073765f 4e4c4e00 63747073 U.ctpsv_NLN.ctps + 816a8 765f5455 55006374 7073765f 54554e00 v_TUU.ctpsv_TUN. + 816b8 63747073 765f544c 55006374 7073765f ctpsv_TLU.ctpsv_ + 816c8 544c4e00 63747073 765f5255 55006374 TLN.ctpsv_RUU.ct + 816d8 7073765f 52554e00 63747073 765f524c psv_RUN.ctpsv_RL + 816e8 55006374 7073765f 524c4e00 63747073 U.ctpsv_RLN.ctps + 816f8 765f4355 55006374 7073765f 43554e00 v_CUU.ctpsv_CUN. + 81708 63747073 765f434c 55006374 7073765f ctpsv_CLU.ctpsv_ + 81718 434c4e00 6374726d 765f4e55 55006374 CLN.ctrmv_NUU.ct + 81728 726d765f 4e554e00 6374726d 765f4e4c rmv_NUN.ctrmv_NL + 81738 55006374 726d765f 4e4c4e00 6374726d U.ctrmv_NLN.ctrm + 81748 765f5455 55006374 726d765f 54554e00 v_TUU.ctrmv_TUN. + 81758 6374726d 765f544c 55006374 726d765f ctrmv_TLU.ctrmv_ + 81768 544c4e00 6374726d 765f5255 55006374 TLN.ctrmv_RUU.ct + 81778 726d765f 52554e00 6374726d 765f524c rmv_RUN.ctrmv_RL + 81788 55006374 726d765f 524c4e00 6374726d U.ctrmv_RLN.ctrm + 81798 765f4355 55006374 726d765f 43554e00 v_CUU.ctrmv_CUN. + 817a8 6374726d 765f434c 55006374 726d765f ctrmv_CLU.ctrmv_ + 817b8 434c4e00 63747273 765f4e55 55006374 CLN.ctrsv_NUU.ct + 817c8 7273765f 4e554e00 63747273 765f4e4c rsv_NUN.ctrsv_NL + 817d8 55006374 7273765f 4e4c4e00 63747273 U.ctrsv_NLN.ctrs + 817e8 765f5455 55006374 7273765f 54554e00 v_TUU.ctrsv_TUN. + 817f8 63747273 765f544c 55006374 7273765f ctrsv_TLU.ctrsv_ + 81808 544c4e00 63747273 765f5255 55006374 TLN.ctrsv_RUU.ct + 81818 7273765f 52554e00 63747273 765f524c rsv_RUN.ctrsv_RL + 81828 55006374 7273765f 524c4e00 63747273 U.ctrsv_RLN.ctrs + 81838 765f4355 55006374 7273765f 43554e00 v_CUU.ctrsv_CUN. + 81848 63747273 765f434c 55006374 7273765f ctrsv_CLU.ctrsv_ + 81858 434c4e00 6373706d 765f5500 6373706d CLN.cspmv_U.cspm + 81868 765f4c00 63737072 5f550063 7370725f v_L.cspr_U.cspr_ + 81878 4c006373 79725f55 00637379 725f4c00 L.csyr_U.csyr_L. + 81888 6474726d 765f7468 72656164 5f544c4e dtrmv_thread_TLN 81898 00647370 6d765f74 68726561 645f5500 .dspmv_thread_U. 818a8 6473706d 765f7468 72656164 5f4c0064 dspmv_thread_L.d 818b8 74706d76 5f746872 6561645f 4e555500 tpmv_thread_NUU. @@ -2055,106 +2055,106 @@ 81b48 725f7468 72656164 5f560063 6865725f r_thread_V.cher_ 81b58 74687265 61645f4d 00637379 72325f74 thread_M.csyr2_t 81b68 68726561 645f5500 63737972 325f7468 hread_U.csyr2_th - 81b78 72656164 5f4c0063 68657232 5f746872 read_L.cher2_thr - 81b88 6561645f 55006368 6572325f 74687265 ead_U.cher2_thre - 81b98 61645f4c 007a6762 6d765f6e 007a6762 ad_L.zgbmv_n.zgb - 81ba8 6d765f74 007a6762 6d765f72 007a6762 mv_t.zgbmv_r.zgb - 81bb8 6d765f63 007a6762 6d765f6f 007a6762 mv_c.zgbmv_o.zgb - 81bc8 6d765f75 007a6762 6d765f73 007a6762 mv_u.zgbmv_s.zgb - 81bd8 6d765f64 007a6862 6d765f55 007a6862 mv_d.zhbmv_U.zhb - 81be8 6d765f4c 007a6862 6d765f56 007a6862 mv_L.zhbmv_V.zhb - 81bf8 6d765f4d 007a6865 725f5500 7a686572 mv_M.zher_U.zher - 81c08 5f4c007a 6865725f 56007a68 65725f4d _L.zher_V.zher_M - 81c18 007a6865 72325f55 007a6865 72325f4c .zher2_U.zher2_L - 81c28 007a6865 72325f56 007a6865 72325f4d .zher2_V.zher2_M - 81c38 007a6870 6d765f55 007a6870 6d765f4c .zhpmv_U.zhpmv_L - 81c48 007a6870 6d765f56 007a6870 6d765f4d .zhpmv_V.zhpmv_M - 81c58 007a6870 725f5500 7a687072 5f4c007a .zhpr_U.zhpr_L.z - 81c68 6870725f 56007a68 70725f4d 007a6870 hpr_V.zhpr_M.zhp - 81c78 72325f55 007a6870 72325f4c 007a6870 r2_U.zhpr2_L.zhp - 81c88 72325f56 00636865 72325f74 68726561 r2_V.cher2_threa - 81c98 645f5600 63686572 325f7468 72656164 d_V.cher2_thread - 81ca8 5f4d0063 7370725f 74687265 61645f55 _M.cspr_thread_U - 81cb8 00637370 725f7468 72656164 5f4c0063 .cspr_thread_L.c /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .rela.dyn --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,13343 +2,13343 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .rela.dyn: - b8458 400bd701 00000000 08000000 00000000 @............... - b8468 40811100 00000000 500bd701 00000000 @.......P....... + b8458 407bd401 00000000 08000000 00000000 @{.............. + b8468 40811100 00000000 507bd401 00000000 @.......P{...... b8478 08000000 00000000 00811100 00000000 ................ - b8488 600bd701 00000000 08000000 00000000 `............... - b8498 d1bbba01 00000000 680bd701 00000000 ........h....... - b84a8 08000000 00000000 2fbbba01 00000000 ......../....... - b84b8 700bd701 00000000 08000000 00000000 p............... - b84c8 36bbba01 00000000 780bd701 00000000 6.......x....... - b84d8 08000000 00000000 41bbba01 00000000 ........A....... - b84e8 800bd701 00000000 08000000 00000000 ................ - b84f8 4bbbba01 00000000 880bd701 00000000 K............... - b8508 08000000 00000000 54bbba01 00000000 ........T....... - b8518 900bd701 00000000 08000000 00000000 ................ - b8528 5abcba01 00000000 980bd701 00000000 Z............... - b8538 08000000 00000000 63bbba01 00000000 ........c....... - b8548 a00bd701 00000000 08000000 00000000 ................ - b8558 5fbcba01 00000000 a80bd701 00000000 _............... - b8568 08000000 00000000 66bcba01 00000000 ........f....... - b8578 b00bd701 00000000 08000000 00000000 ................ - b8588 5bbbba01 00000000 b80bd701 00000000 [............... - b8598 08000000 00000000 69bbba01 00000000 ........i....... - b85a8 c00bd701 00000000 08000000 00000000 ................ - b85b8 71bcba01 00000000 c80bd701 00000000 q............... - b85c8 08000000 00000000 79bcba01 00000000 ........y....... - b85d8 d00bd701 00000000 08000000 00000000 ................ - b85e8 70bbba01 00000000 d80bd701 00000000 p............... - b85f8 08000000 00000000 86bcba01 00000000 ................ - b8608 e00bd701 00000000 08000000 00000000 ................ - b8618 7abbba01 00000000 e80bd701 00000000 z............... - b8628 08000000 00000000 8bbcba01 00000000 ................ - b8638 f00bd701 00000000 08000000 00000000 ................ - b8648 86bbba01 00000000 f80bd701 00000000 ................ - b8658 08000000 00000000 90bbba01 00000000 ................ - b8668 000cd701 00000000 08000000 00000000 ................ - b8678 9bbbba01 00000000 080cd701 00000000 ................ - b8688 08000000 00000000 a3bbba01 00000000 ................ - b8698 100cd701 00000000 08000000 00000000 ................ - b86a8 afbbba01 00000000 180cd701 00000000 ................ - b86b8 08000000 00000000 b9bbba01 00000000 ................ - b86c8 200cd701 00000000 08000000 00000000 ............... - b86d8 bdbbba01 00000000 280cd701 00000000 ........(....... - b86e8 08000000 00000000 c6bbba01 00000000 ................ - b86f8 20b7d701 00000000 08000000 00000000 ............... - b8708 20b7d701 00000000 e0c8d701 00000000 ............... - b8718 08000000 00000000 c08dc000 00000000 ................ - b8728 40dbd701 00000000 08000000 00000000 @............... - b8738 f007ae00 00000000 a0edd701 00000000 ................ - b8748 08000000 00000000 405d9f00 00000000 ........@]...... - b8758 0000d801 00000000 08000000 00000000 ................ - b8768 a0578700 00000000 6012d801 00000000 .W......`....... - b8778 08000000 00000000 80377c00 00000000 .........7|..... - b8788 c024d801 00000000 08000000 00000000 .$.............. - b8798 20169000 00000000 2037d801 00000000 ....... 7...... - b87a8 08000000 00000000 909d7300 00000000 ..........s..... - b87b8 8049d801 00000000 08000000 00000000 .I.............. - b87c8 c0196900 00000000 e05bd801 00000000 ..i......[...... - b87d8 08000000 00000000 d0025d00 00000000 ..........]..... - b87e8 406ed801 00000000 08000000 00000000 @n.............. - b87f8 70785400 00000000 a080d801 00000000 pxT............. - b8808 08000000 00000000 10bf4100 00000000 ..........A..... - b8818 0093d801 00000000 08000000 00000000 ................ - b8828 b0644a00 00000000 60a5d801 00000000 .dJ.....`....... - b8838 08000000 00000000 10c63900 00000000 ..........9..... - b8848 48b7d801 00000000 08000000 00000000 H............... - b8858 10a3ba01 00000000 480bd701 00000000 ........H....... + b8488 607bd401 00000000 08000000 00000000 `{.............. + b8498 713cb801 00000000 687bd401 00000000 q<......h{...... + b84a8 08000000 00000000 cf3bb801 00000000 .........;...... + b84b8 707bd401 00000000 08000000 00000000 p{.............. + b84c8 d63bb801 00000000 787bd401 00000000 .;......x{...... + b84d8 08000000 00000000 e13bb801 00000000 .........;...... + b84e8 807bd401 00000000 08000000 00000000 .{.............. + b84f8 eb3bb801 00000000 887bd401 00000000 .;.......{...... + b8508 08000000 00000000 f43bb801 00000000 .........;...... + b8518 907bd401 00000000 08000000 00000000 .{.............. + b8528 fa3cb801 00000000 987bd401 00000000 .<.......{...... + b8538 08000000 00000000 033cb801 00000000 .........<...... + b8548 a07bd401 00000000 08000000 00000000 .{.............. + b8558 ff3cb801 00000000 a87bd401 00000000 .<.......{...... + b8568 08000000 00000000 063db801 00000000 .........=...... + b8578 b07bd401 00000000 08000000 00000000 .{.............. + b8588 fb3bb801 00000000 b87bd401 00000000 .;.......{...... + b8598 08000000 00000000 093cb801 00000000 .........<...... + b85a8 c07bd401 00000000 08000000 00000000 .{.............. + b85b8 113db801 00000000 c87bd401 00000000 .=.......{...... + b85c8 08000000 00000000 193db801 00000000 .........=...... + b85d8 d07bd401 00000000 08000000 00000000 .{.............. + b85e8 103cb801 00000000 d87bd401 00000000 .<.......{...... + b85f8 08000000 00000000 263db801 00000000 ........&=...... + b8608 e07bd401 00000000 08000000 00000000 .{.............. + b8618 1a3cb801 00000000 e87bd401 00000000 .<.......{...... + b8628 08000000 00000000 2b3db801 00000000 ........+=...... + b8638 f07bd401 00000000 08000000 00000000 .{.............. + b8648 263cb801 00000000 f87bd401 00000000 &<.......{...... + b8658 08000000 00000000 303cb801 00000000 ........0<...... + b8668 007cd401 00000000 08000000 00000000 .|.............. + b8678 3b3cb801 00000000 087cd401 00000000 ;<.......|...... + b8688 08000000 00000000 433cb801 00000000 ........C<...... + b8698 107cd401 00000000 08000000 00000000 .|.............. + b86a8 4f3cb801 00000000 187cd401 00000000 O<.......|...... + b86b8 08000000 00000000 593cb801 00000000 ........Y<...... + b86c8 207cd401 00000000 08000000 00000000 |.............. + b86d8 5d3cb801 00000000 287cd401 00000000 ]<......(|...... + b86e8 08000000 00000000 663cb801 00000000 ........f<...... + b86f8 2027d501 00000000 08000000 00000000 '.............. + b8708 2027d501 00000000 e038d501 00000000 '.......8...... + b8718 08000000 00000000 d0f7be00 00000000 ................ + b8728 404bd501 00000000 08000000 00000000 @K.............. + b8738 a0dead00 00000000 a05dd501 00000000 .........]...... + b8748 08000000 00000000 a05c9f00 00000000 .........\...... + b8758 0070d501 00000000 08000000 00000000 .p.............. + b8768 a0ae8500 00000000 6082d501 00000000 ........`....... + b8778 08000000 00000000 80257d00 00000000 .........%}..... + b8788 c094d501 00000000 08000000 00000000 ................ + b8798 70459000 00000000 20a7d501 00000000 pE...... ....... + b87a8 08000000 00000000 70c07200 00000000 ........p.r..... + b87b8 80b9d501 00000000 08000000 00000000 ................ + b87c8 d0296800 00000000 e0cbd501 00000000 .)h............. + b87d8 08000000 00000000 b06b5e00 00000000 .........k^..... + b87e8 40ded501 00000000 08000000 00000000 @............... + b87f8 c0295500 00000000 a0f0d501 00000000 .)U............. + b8808 08000000 00000000 30014200 00000000 ........0.B..... + b8818 0003d601 00000000 08000000 00000000 ................ + b8828 60244b00 00000000 6015d601 00000000 `$K.....`....... + b8838 08000000 00000000 d01a3a00 00000000 ..........:..... + b8848 4827d601 00000000 08000000 00000000 H'.............. + b8858 1023b801 00000000 487bd401 00000000 .#......H{...... b8868 01000000 062d0000 00000000 00000000 .....-.......... - b8878 580bd701 00000000 01000000 8b2a0000 X............*.. - b8888 00000000 00000000 400cd701 00000000 ........@....... + b8878 587bd401 00000000 01000000 8b2a0000 X{...........*.. + b8888 00000000 00000000 407cd401 00000000 ........@|...... b8898 01000000 0d020000 00000000 00000000 ................ - b88a8 480cd701 00000000 01000000 cc0d0000 H............... - b88b8 00000000 00000000 500cd701 00000000 ........P....... + b88a8 487cd401 00000000 01000000 cc0d0000 H|.............. + b88b8 00000000 00000000 507cd401 00000000 ........P|...... b88c8 01000000 65100000 00000000 00000000 ....e........... - b88d8 580cd701 00000000 01000000 a2280000 X............(.. - b88e8 00000000 00000000 600cd701 00000000 ........`....... + b88d8 587cd401 00000000 01000000 a2280000 X|...........(.. + b88e8 00000000 00000000 607cd401 00000000 ........`|...... b88f8 01000000 3f1a0000 00000000 00000000 ....?........... - b8908 680cd701 00000000 01000000 a6250000 h............%.. - b8918 00000000 00000000 700cd701 00000000 ........p....... + b8908 687cd401 00000000 01000000 a6250000 h|...........%.. + b8918 00000000 00000000 707cd401 00000000 ........p|...... b8928 01000000 83020000 00000000 00000000 ................ - b8938 780cd701 00000000 01000000 580e0000 x...........X... - b8948 00000000 00000000 800cd701 00000000 ................ + b8938 787cd401 00000000 01000000 580e0000 x|..........X... + b8948 00000000 00000000 807cd401 00000000 .........|...... b8958 01000000 75310000 00000000 00000000 ....u1.......... - b8968 880cd701 00000000 01000000 42010000 ............B... - b8978 00000000 00000000 900cd701 00000000 ................ + b8968 887cd401 00000000 01000000 42010000 .|..........B... + b8978 00000000 00000000 907cd401 00000000 .........|...... b8988 01000000 32080000 00000000 00000000 ....2........... - b8998 980cd701 00000000 01000000 9a170000 ................ - b89a8 00000000 00000000 a00cd701 00000000 ................ + b8998 987cd401 00000000 01000000 9a170000 .|.............. + b89a8 00000000 00000000 a07cd401 00000000 .........|...... b89b8 01000000 80150000 00000000 00000000 ................ - b89c8 a80cd701 00000000 01000000 c6170000 ................ - b89d8 00000000 00000000 b00cd701 00000000 ................ + b89c8 a87cd401 00000000 01000000 c6170000 .|.............. + b89d8 00000000 00000000 b07cd401 00000000 .........|...... b89e8 01000000 bc1e0000 00000000 00000000 ................ - b89f8 b80cd701 00000000 01000000 962d0000 .............-.. - b8a08 00000000 00000000 c00cd701 00000000 ................ + b89f8 b87cd401 00000000 01000000 962d0000 .|...........-.. + b8a08 00000000 00000000 c07cd401 00000000 .........|...... b8a18 01000000 e20f0000 00000000 00000000 ................ - b8a28 c80cd701 00000000 01000000 bb1b0000 ................ - b8a38 00000000 00000000 d00cd701 00000000 ................ + b8a28 c87cd401 00000000 01000000 bb1b0000 .|.............. + b8a38 00000000 00000000 d07cd401 00000000 .........|...... b8a48 01000000 812c0000 00000000 00000000 .....,.......... - b8a58 d80cd701 00000000 01000000 c0050000 ................ - b8a68 00000000 00000000 e00cd701 00000000 ................ + b8a58 d87cd401 00000000 01000000 c0050000 .|.............. + b8a68 00000000 00000000 e07cd401 00000000 .........|...... b8a78 01000000 290d0000 00000000 00000000 ....)........... - b8a88 e80cd701 00000000 01000000 b70f0000 ................ - b8a98 00000000 00000000 f00cd701 00000000 ................ + b8a88 e87cd401 00000000 01000000 b70f0000 .|.............. + b8a98 00000000 00000000 f07cd401 00000000 .........|...... b8aa8 01000000 2c2b0000 00000000 00000000 ....,+.......... - b8ab8 f80cd701 00000000 01000000 7f2d0000 .............-.. - b8ac8 00000000 00000000 000dd701 00000000 ................ + b8ab8 f87cd401 00000000 01000000 7f2d0000 .|...........-.. + b8ac8 00000000 00000000 007dd401 00000000 .........}...... /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .rela.plt --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,5712 +2,5712 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .rela.plt: - 0ec610 1840d701 00000000 07000000 f5090000 .@.............. - 0ec620 00000000 00000000 2040d701 00000000 ........ @...... + 0ec610 18b0d401 00000000 07000000 f5090000 ................ + 0ec620 00000000 00000000 20b0d401 00000000 ........ ....... 0ec630 07000000 ad140000 00000000 00000000 ................ - 0ec640 2840d701 00000000 07000000 fb0a0000 (@.............. - 0ec650 00000000 00000000 3040d701 00000000 ........0@...... + 0ec640 28b0d401 00000000 07000000 fb0a0000 (............... + 0ec650 00000000 00000000 30b0d401 00000000 ........0....... 0ec660 07000000 01000000 00000000 00000000 ................ - 0ec670 3840d701 00000000 07000000 0c280000 8@...........(.. - 0ec680 00000000 00000000 4040d701 00000000 ........@@...... + 0ec670 38b0d401 00000000 07000000 0c280000 8............(.. + 0ec680 00000000 00000000 40b0d401 00000000 ........@....... 0ec690 07000000 5f170000 00000000 00000000 ...._........... - 0ec6a0 4840d701 00000000 07000000 192f0000 H@.........../.. - 0ec6b0 00000000 00000000 5040d701 00000000 ........P@...... + 0ec6a0 48b0d401 00000000 07000000 192f0000 H............/.. + 0ec6b0 00000000 00000000 50b0d401 00000000 ........P....... 0ec6c0 07000000 412d0000 00000000 00000000 ....A-.......... - 0ec6d0 5840d701 00000000 07000000 5d1e0000 X@..........]... - 0ec6e0 00000000 00000000 6040d701 00000000 ........`@...... + 0ec6d0 58b0d401 00000000 07000000 5d1e0000 X...........]... + 0ec6e0 00000000 00000000 60b0d401 00000000 ........`....... 0ec6f0 07000000 6a210000 00000000 00000000 ....j!.......... - 0ec700 6840d701 00000000 07000000 fa1e0000 h@.............. - 0ec710 00000000 00000000 7040d701 00000000 ........p@...... + 0ec700 68b0d401 00000000 07000000 fa1e0000 h............... + 0ec710 00000000 00000000 70b0d401 00000000 ........p....... 0ec720 07000000 b9100000 00000000 00000000 ................ - 0ec730 7840d701 00000000 07000000 06270000 x@...........'.. - 0ec740 00000000 00000000 8040d701 00000000 .........@...... + 0ec730 78b0d401 00000000 07000000 06270000 x............'.. + 0ec740 00000000 00000000 80b0d401 00000000 ................ 0ec750 07000000 cb1d0000 00000000 00000000 ................ - 0ec760 8840d701 00000000 07000000 dc1d0000 .@.............. - 0ec770 00000000 00000000 9040d701 00000000 .........@...... + 0ec760 88b0d401 00000000 07000000 dc1d0000 ................ + 0ec770 00000000 00000000 90b0d401 00000000 ................ 0ec780 07000000 1a0a0000 00000000 00000000 ................ - 0ec790 9840d701 00000000 07000000 a22b0000 .@...........+.. - 0ec7a0 00000000 00000000 a040d701 00000000 .........@...... + 0ec790 98b0d401 00000000 07000000 a22b0000 .............+.. + 0ec7a0 00000000 00000000 a0b0d401 00000000 ................ 0ec7b0 07000000 5e070000 00000000 00000000 ....^........... - 0ec7c0 a840d701 00000000 07000000 09070000 .@.............. - 0ec7d0 00000000 00000000 b040d701 00000000 .........@...... + 0ec7c0 a8b0d401 00000000 07000000 09070000 ................ + 0ec7d0 00000000 00000000 b0b0d401 00000000 ................ 0ec7e0 07000000 531f0000 00000000 00000000 ....S........... - 0ec7f0 b840d701 00000000 07000000 60030000 .@..........`... - 0ec800 00000000 00000000 c040d701 00000000 .........@...... + 0ec7f0 b8b0d401 00000000 07000000 60030000 ............`... + 0ec800 00000000 00000000 c0b0d401 00000000 ................ 0ec810 07000000 91270000 00000000 00000000 .....'.......... - 0ec820 c840d701 00000000 07000000 ec260000 .@...........&.. - 0ec830 00000000 00000000 d040d701 00000000 .........@...... + 0ec820 c8b0d401 00000000 07000000 ec260000 .............&.. + 0ec830 00000000 00000000 d0b0d401 00000000 ................ 0ec840 07000000 63140000 00000000 00000000 ....c........... - 0ec850 d840d701 00000000 07000000 dc160000 .@.............. - 0ec860 00000000 00000000 e040d701 00000000 .........@...... + 0ec850 d8b0d401 00000000 07000000 dc160000 ................ + 0ec860 00000000 00000000 e0b0d401 00000000 ................ 0ec870 07000000 00210000 00000000 00000000 .....!.......... - 0ec880 e840d701 00000000 07000000 78200000 .@..........x .. - 0ec890 00000000 00000000 f040d701 00000000 .........@...... + 0ec880 e8b0d401 00000000 07000000 78200000 ............x .. + 0ec890 00000000 00000000 f0b0d401 00000000 ................ 0ec8a0 07000000 60300000 00000000 00000000 ....`0.......... - 0ec8b0 f840d701 00000000 07000000 a4310000 .@...........1.. - 0ec8c0 00000000 00000000 0041d701 00000000 .........A...... + 0ec8b0 f8b0d401 00000000 07000000 a4310000 .............1.. + 0ec8c0 00000000 00000000 00b1d401 00000000 ................ 0ec8d0 07000000 5a0b0000 00000000 00000000 ....Z........... - 0ec8e0 0841d701 00000000 07000000 e2070000 .A.............. - 0ec8f0 00000000 00000000 1041d701 00000000 .........A...... + 0ec8e0 08b1d401 00000000 07000000 e2070000 ................ + 0ec8f0 00000000 00000000 10b1d401 00000000 ................ 0ec900 07000000 2e0f0000 00000000 00000000 ................ - 0ec910 1841d701 00000000 07000000 e8060000 .A.............. - 0ec920 00000000 00000000 2041d701 00000000 ........ A...... + 0ec910 18b1d401 00000000 07000000 e8060000 ................ + 0ec920 00000000 00000000 20b1d401 00000000 ........ ....... 0ec930 07000000 a0160000 00000000 00000000 ................ - 0ec940 2841d701 00000000 07000000 1d2a0000 (A...........*.. - 0ec950 00000000 00000000 3041d701 00000000 ........0A...... + 0ec940 28b1d401 00000000 07000000 1d2a0000 (............*.. + 0ec950 00000000 00000000 30b1d401 00000000 ........0....... 0ec960 07000000 290f0000 00000000 00000000 ....)........... - 0ec970 3841d701 00000000 07000000 e52a0000 8A...........*.. - 0ec980 00000000 00000000 4041d701 00000000 ........@A...... + 0ec970 38b1d401 00000000 07000000 e52a0000 8............*.. + 0ec980 00000000 00000000 40b1d401 00000000 ........@....... 0ec990 07000000 2c0c0000 00000000 00000000 ....,........... - 0ec9a0 4841d701 00000000 07000000 130f0000 HA.............. - 0ec9b0 00000000 00000000 5041d701 00000000 ........PA...... + 0ec9a0 48b1d401 00000000 07000000 130f0000 H............... + 0ec9b0 00000000 00000000 50b1d401 00000000 ........P....... 0ec9c0 07000000 24290000 00000000 00000000 ....$).......... - 0ec9d0 5841d701 00000000 07000000 a3020000 XA.............. - 0ec9e0 00000000 00000000 6041d701 00000000 ........`A...... + 0ec9d0 58b1d401 00000000 07000000 a3020000 X............... + 0ec9e0 00000000 00000000 60b1d401 00000000 ........`....... 0ec9f0 07000000 0e110000 00000000 00000000 ................ - 0eca00 6841d701 00000000 07000000 ad190000 hA.............. - 0eca10 00000000 00000000 7041d701 00000000 ........pA...... + 0eca00 68b1d401 00000000 07000000 ad190000 h............... + 0eca10 00000000 00000000 70b1d401 00000000 ........p....... 0eca20 07000000 692d0000 00000000 00000000 ....i-.......... - 0eca30 7841d701 00000000 07000000 27100000 xA..........'... - 0eca40 00000000 00000000 8041d701 00000000 .........A...... + 0eca30 78b1d401 00000000 07000000 27100000 x...........'... + 0eca40 00000000 00000000 80b1d401 00000000 ................ 0eca50 07000000 02000000 00000000 00000000 ................ - 0eca60 8841d701 00000000 07000000 13110000 .A.............. - 0eca70 00000000 00000000 9041d701 00000000 .........A...... + 0eca60 88b1d401 00000000 07000000 13110000 ................ + 0eca70 00000000 00000000 90b1d401 00000000 ................ 0eca80 07000000 821c0000 00000000 00000000 ................ - 0eca90 9841d701 00000000 07000000 2c100000 .A..........,... - 0ecaa0 00000000 00000000 a041d701 00000000 .........A...... + 0eca90 98b1d401 00000000 07000000 2c100000 ............,... + 0ecaa0 00000000 00000000 a0b1d401 00000000 ................ 0ecab0 07000000 95180000 00000000 00000000 ................ - 0ecac0 a841d701 00000000 07000000 700a0000 .A..........p... - 0ecad0 00000000 00000000 b041d701 00000000 .........A...... + 0ecac0 a8b1d401 00000000 07000000 700a0000 ............p... + 0ecad0 00000000 00000000 b0b1d401 00000000 ................ 0ecae0 07000000 170e0000 00000000 00000000 ................ - 0ecaf0 b841d701 00000000 07000000 5e2e0000 .A..........^... - 0ecb00 00000000 00000000 c041d701 00000000 .........A...... + 0ecaf0 b8b1d401 00000000 07000000 5e2e0000 ............^... + 0ecb00 00000000 00000000 c0b1d401 00000000 ................ 0ecb10 07000000 70290000 00000000 00000000 ....p).......... - 0ecb20 c841d701 00000000 07000000 03000000 .A.............. - 0ecb30 00000000 00000000 d041d701 00000000 .........A...... + 0ecb20 c8b1d401 00000000 07000000 03000000 ................ + 0ecb30 00000000 00000000 d0b1d401 00000000 ................ 0ecb40 07000000 10170000 00000000 00000000 ................ - 0ecb50 d841d701 00000000 07000000 422f0000 .A..........B/.. - 0ecb60 00000000 00000000 e041d701 00000000 .........A...... + 0ecb50 d8b1d401 00000000 07000000 422f0000 ............B/.. + 0ecb60 00000000 00000000 e0b1d401 00000000 ................ 0ecb70 07000000 010c0000 00000000 00000000 ................ - 0ecb80 e841d701 00000000 07000000 b3060000 .A.............. - 0ecb90 00000000 00000000 f041d701 00000000 .........A...... + 0ecb80 e8b1d401 00000000 07000000 b3060000 ................ + 0ecb90 00000000 00000000 f0b1d401 00000000 ................ 0ecba0 07000000 00240000 00000000 00000000 .....$.......... - 0ecbb0 f841d701 00000000 07000000 e6080000 .A.............. - 0ecbc0 00000000 00000000 0042d701 00000000 .........B...... + 0ecbb0 f8b1d401 00000000 07000000 e6080000 ................ + 0ecbc0 00000000 00000000 00b2d401 00000000 ................ 0ecbd0 07000000 24010000 00000000 00000000 ....$........... - 0ecbe0 0842d701 00000000 07000000 f70d0000 .B.............. - 0ecbf0 00000000 00000000 1042d701 00000000 .........B...... + 0ecbe0 08b2d401 00000000 07000000 f70d0000 ................ + 0ecbf0 00000000 00000000 10b2d401 00000000 ................ 0ecc00 07000000 1b050000 00000000 00000000 ................ - 0ecc10 1842d701 00000000 07000000 3d150000 .B..........=... - 0ecc20 00000000 00000000 2042d701 00000000 ........ B...... + 0ecc10 18b2d401 00000000 07000000 3d150000 ............=... + 0ecc20 00000000 00000000 20b2d401 00000000 ........ ....... 0ecc30 07000000 a5220000 00000000 00000000 .....".......... - 0ecc40 2842d701 00000000 07000000 a10c0000 (B.............. - 0ecc50 00000000 00000000 3042d701 00000000 ........0B...... + 0ecc40 28b2d401 00000000 07000000 a10c0000 (............... + 0ecc50 00000000 00000000 30b2d401 00000000 ........0....... 0ecc60 07000000 d50c0000 00000000 00000000 ................ - 0ecc70 3842d701 00000000 07000000 f4110000 8B.............. - 0ecc80 00000000 00000000 4042d701 00000000 ........@B...... + 0ecc70 38b2d401 00000000 07000000 f4110000 8............... + 0ecc80 00000000 00000000 40b2d401 00000000 ........@....... 0ecc90 07000000 5a120000 00000000 00000000 ....Z........... - 0ecca0 4842d701 00000000 07000000 79030000 HB..........y... - 0eccb0 00000000 00000000 5042d701 00000000 ........PB...... + 0ecca0 48b2d401 00000000 07000000 79030000 H...........y... + 0eccb0 00000000 00000000 50b2d401 00000000 ........P....... 0eccc0 07000000 67150000 00000000 00000000 ....g........... - 0eccd0 5842d701 00000000 07000000 c0290000 XB...........).. - 0ecce0 00000000 00000000 6042d701 00000000 ........`B...... + 0eccd0 58b2d401 00000000 07000000 c0290000 X............).. + 0ecce0 00000000 00000000 60b2d401 00000000 ........`....... 0eccf0 07000000 a0130000 00000000 00000000 ................ - 0ecd00 6842d701 00000000 07000000 6f120000 hB..........o... - 0ecd10 00000000 00000000 7042d701 00000000 ........pB...... + 0ecd00 68b2d401 00000000 07000000 6f120000 h...........o... + 0ecd10 00000000 00000000 70b2d401 00000000 ........p....... 0ecd20 07000000 73280000 00000000 00000000 ....s(.......... - 0ecd30 7842d701 00000000 07000000 d8100000 xB.............. - 0ecd40 00000000 00000000 8042d701 00000000 .........B...... + 0ecd30 78b2d401 00000000 07000000 d8100000 x............... + 0ecd40 00000000 00000000 80b2d401 00000000 ................ /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .init --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,5 +2,5 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .init: - 103000 f30f1efa 4883ec08 488b05b9 0fc70148 ....H...H......H + 103000 f30f1efa 4883ec08 488b05b9 7fc40148 ....H...H......H 103010 85c07402 ffd04883 c408c3 ..t...H.... /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .plt --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,3810 +2,3810 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .plt: - 103020 ff35e20f c701ff25 e40fc701 0f1f4000 .5.....%......@. - 103030 ff25e20f c7016800 000000e9 e0ffffff .%....h......... - 103040 ff25da0f c7016801 000000e9 d0ffffff .%....h......... - 103050 ff25d20f c7016802 000000e9 c0ffffff .%....h......... - 103060 ff25ca0f c7016803 000000e9 b0ffffff .%....h......... - 103070 ff25c20f c7016804 000000e9 a0ffffff .%....h......... - 103080 ff25ba0f c7016805 000000e9 90ffffff .%....h......... - 103090 ff25b20f c7016806 000000e9 80ffffff .%....h......... - 1030a0 ff25aa0f c7016807 000000e9 70ffffff .%....h.....p... - 1030b0 ff25a20f c7016808 000000e9 60ffffff .%....h.....`... - 1030c0 ff259a0f c7016809 000000e9 50ffffff .%....h.....P... - 1030d0 ff25920f c701680a 000000e9 40ffffff .%....h.....@... - 1030e0 ff258a0f c701680b 000000e9 30ffffff .%....h.....0... - 1030f0 ff25820f c701680c 000000e9 20ffffff .%....h..... ... - 103100 ff257a0f c701680d 000000e9 10ffffff .%z...h......... - 103110 ff25720f c701680e 000000e9 00ffffff .%r...h......... - 103120 ff256a0f c701680f 000000e9 f0feffff .%j...h......... - 103130 ff25620f c7016810 000000e9 e0feffff .%b...h......... - 103140 ff255a0f c7016811 000000e9 d0feffff .%Z...h......... - 103150 ff25520f c7016812 000000e9 c0feffff .%R...h......... - 103160 ff254a0f c7016813 000000e9 b0feffff .%J...h......... - 103170 ff25420f c7016814 000000e9 a0feffff .%B...h......... - 103180 ff253a0f c7016815 000000e9 90feffff .%:...h......... - 103190 ff25320f c7016816 000000e9 80feffff .%2...h......... - 1031a0 ff252a0f c7016817 000000e9 70feffff .%*...h.....p... - 1031b0 ff25220f c7016818 000000e9 60feffff .%"...h.....`... - 1031c0 ff251a0f c7016819 000000e9 50feffff .%....h.....P... - 1031d0 ff25120f c701681a 000000e9 40feffff .%....h.....@... - 1031e0 ff250a0f c701681b 000000e9 30feffff .%....h.....0... - 1031f0 ff25020f c701681c 000000e9 20feffff .%....h..... ... - 103200 ff25fa0e c701681d 000000e9 10feffff .%....h......... - 103210 ff25f20e c701681e 000000e9 00feffff .%....h......... - 103220 ff25ea0e c701681f 000000e9 f0fdffff .%....h......... - 103230 ff25e20e c7016820 000000e9 e0fdffff .%....h ........ - 103240 ff25da0e c7016821 000000e9 d0fdffff .%....h!........ - 103250 ff25d20e c7016822 000000e9 c0fdffff .%....h"........ - 103260 ff25ca0e c7016823 000000e9 b0fdffff .%....h#........ - 103270 ff25c20e c7016824 000000e9 a0fdffff .%....h$........ - 103280 ff25ba0e c7016825 000000e9 90fdffff .%....h%........ - 103290 ff25b20e c7016826 000000e9 80fdffff .%....h&........ - 1032a0 ff25aa0e c7016827 000000e9 70fdffff .%....h'....p... - 1032b0 ff25a20e c7016828 000000e9 60fdffff .%....h(....`... - 1032c0 ff259a0e c7016829 000000e9 50fdffff .%....h)....P... - 1032d0 ff25920e c701682a 000000e9 40fdffff .%....h*....@... - 1032e0 ff258a0e c701682b 000000e9 30fdffff .%....h+....0... - 1032f0 ff25820e c701682c 000000e9 20fdffff .%....h,.... ... - 103300 ff257a0e c701682d 000000e9 10fdffff .%z...h-........ - 103310 ff25720e c701682e 000000e9 00fdffff .%r...h......... - 103320 ff256a0e c701682f 000000e9 f0fcffff .%j...h/........ - 103330 ff25620e c7016830 000000e9 e0fcffff .%b...h0........ - 103340 ff255a0e c7016831 000000e9 d0fcffff .%Z...h1........ - 103350 ff25520e c7016832 000000e9 c0fcffff .%R...h2........ - 103360 ff254a0e c7016833 000000e9 b0fcffff .%J...h3........ - 103370 ff25420e c7016834 000000e9 a0fcffff .%B...h4........ - 103380 ff253a0e c7016835 000000e9 90fcffff .%:...h5........ - 103390 ff25320e c7016836 000000e9 80fcffff .%2...h6........ - 1033a0 ff252a0e c7016837 000000e9 70fcffff .%*...h7....p... - 1033b0 ff25220e c7016838 000000e9 60fcffff .%"...h8....`... - 1033c0 ff251a0e c7016839 000000e9 50fcffff .%....h9....P... - 1033d0 ff25120e c701683a 000000e9 40fcffff .%....h:....@... - 1033e0 ff250a0e c701683b 000000e9 30fcffff .%....h;....0... - 1033f0 ff25020e c701683c 000000e9 20fcffff .%....h<.... ... - 103400 ff25fa0d c701683d 000000e9 10fcffff .%....h=........ - 103410 ff25f20d c701683e 000000e9 00fcffff .%....h>........ - 103420 ff25ea0d c701683f 000000e9 f0fbffff .%....h?........ - 103430 ff25e20d c7016840 000000e9 e0fbffff .%....h@........ - 103440 ff25da0d c7016841 000000e9 d0fbffff .%....hA........ - 103450 ff25d20d c7016842 000000e9 c0fbffff .%....hB........ - 103460 ff25ca0d c7016843 000000e9 b0fbffff .%....hC........ - 103470 ff25c20d c7016844 000000e9 a0fbffff .%....hD........ - 103480 ff25ba0d c7016845 000000e9 90fbffff .%....hE........ - 103490 ff25b20d c7016846 000000e9 80fbffff .%....hF........ - 1034a0 ff25aa0d c7016847 000000e9 70fbffff .%....hG....p... - 1034b0 ff25a20d c7016848 000000e9 60fbffff .%....hH....`... - 1034c0 ff259a0d c7016849 000000e9 50fbffff .%....hI....P... - 1034d0 ff25920d c701684a 000000e9 40fbffff .%....hJ....@... - 1034e0 ff258a0d c701684b 000000e9 30fbffff .%....hK....0... - 1034f0 ff25820d c701684c 000000e9 20fbffff .%....hL.... ... - 103500 ff257a0d c701684d 000000e9 10fbffff .%z...hM........ - 103510 ff25720d c701684e 000000e9 00fbffff .%r...hN........ - 103520 ff256a0d c701684f 000000e9 f0faffff .%j...hO........ - 103530 ff25620d c7016850 000000e9 e0faffff .%b...hP........ - 103540 ff255a0d c7016851 000000e9 d0faffff .%Z...hQ........ - 103550 ff25520d c7016852 000000e9 c0faffff .%R...hR........ - 103560 ff254a0d c7016853 000000e9 b0faffff .%J...hS........ - 103570 ff25420d c7016854 000000e9 a0faffff .%B...hT........ - 103580 ff253a0d c7016855 000000e9 90faffff .%:...hU........ - 103590 ff25320d c7016856 000000e9 80faffff .%2...hV........ - 1035a0 ff252a0d c7016857 000000e9 70faffff .%*...hW....p... - 1035b0 ff25220d c7016858 000000e9 60faffff .%"...hX....`... - 1035c0 ff251a0d c7016859 000000e9 50faffff .%....hY....P... - 1035d0 ff25120d c701685a 000000e9 40faffff .%....hZ....@... - 1035e0 ff250a0d c701685b 000000e9 30faffff .%....h[....0... - 1035f0 ff25020d c701685c 000000e9 20faffff .%....h\.... ... - 103600 ff25fa0c c701685d 000000e9 10faffff .%....h]........ - 103610 ff25f20c c701685e 000000e9 00faffff .%....h^........ - 103620 ff25ea0c c701685f 000000e9 f0f9ffff .%....h_........ - 103630 ff25e20c c7016860 000000e9 e0f9ffff .%....h`........ - 103640 ff25da0c c7016861 000000e9 d0f9ffff .%....ha........ - 103650 ff25d20c c7016862 000000e9 c0f9ffff .%....hb........ - 103660 ff25ca0c c7016863 000000e9 b0f9ffff .%....hc........ - 103670 ff25c20c c7016864 000000e9 a0f9ffff .%....hd........ - 103680 ff25ba0c c7016865 000000e9 90f9ffff .%....he........ - 103690 ff25b20c c7016866 000000e9 80f9ffff .%....hf........ - 1036a0 ff25aa0c c7016867 000000e9 70f9ffff .%....hg....p... - 1036b0 ff25a20c c7016868 000000e9 60f9ffff .%....hh....`... - 1036c0 ff259a0c c7016869 000000e9 50f9ffff .%....hi....P... - 1036d0 ff25920c c701686a 000000e9 40f9ffff .%....hj....@... - 1036e0 ff258a0c c701686b 000000e9 30f9ffff .%....hk....0... - 1036f0 ff25820c c701686c 000000e9 20f9ffff .%....hl.... ... - 103700 ff257a0c c701686d 000000e9 10f9ffff .%z...hm........ - 103710 ff25720c c701686e 000000e9 00f9ffff .%r...hn........ - 103720 ff256a0c c701686f 000000e9 f0f8ffff .%j...ho........ - 103730 ff25620c c7016870 000000e9 e0f8ffff .%b...hp........ - 103740 ff255a0c c7016871 000000e9 d0f8ffff .%Z...hq........ - 103750 ff25520c c7016872 000000e9 c0f8ffff .%R...hr........ - 103760 ff254a0c c7016873 000000e9 b0f8ffff .%J...hs........ - 103770 ff25420c c7016874 000000e9 a0f8ffff .%B...ht........ - 103780 ff253a0c c7016875 000000e9 90f8ffff .%:...hu........ - 103790 ff25320c c7016876 000000e9 80f8ffff .%2...hv........ - 1037a0 ff252a0c c7016877 000000e9 70f8ffff .%*...hw....p... - 1037b0 ff25220c c7016878 000000e9 60f8ffff .%"...hx....`... - 1037c0 ff251a0c c7016879 000000e9 50f8ffff .%....hy....P... - 1037d0 ff25120c c701687a 000000e9 40f8ffff .%....hz....@... - 1037e0 ff250a0c c701687b 000000e9 30f8ffff .%....h{....0... - 1037f0 ff25020c c701687c 000000e9 20f8ffff .%....h|.... ... - 103800 ff25fa0b c701687d 000000e9 10f8ffff .%....h}........ - 103810 ff25f20b c701687e 000000e9 00f8ffff .%....h~........ - 103820 ff25ea0b c701687f 000000e9 f0f7ffff .%....h......... - 103830 ff25e20b c7016880 000000e9 e0f7ffff .%....h......... - 103840 ff25da0b c7016881 000000e9 d0f7ffff .%....h......... - 103850 ff25d20b c7016882 000000e9 c0f7ffff .%....h......... - 103860 ff25ca0b c7016883 000000e9 b0f7ffff .%....h......... - 103870 ff25c20b c7016884 000000e9 a0f7ffff .%....h......... - 103880 ff25ba0b c7016885 000000e9 90f7ffff .%....h......... - 103890 ff25b20b c7016886 000000e9 80f7ffff .%....h......... - 1038a0 ff25aa0b c7016887 000000e9 70f7ffff .%....h.....p... - 1038b0 ff25a20b c7016888 000000e9 60f7ffff .%....h.....`... - 1038c0 ff259a0b c7016889 000000e9 50f7ffff .%....h.....P... - 1038d0 ff25920b c701688a 000000e9 40f7ffff .%....h.....@... - 1038e0 ff258a0b c701688b 000000e9 30f7ffff .%....h.....0... - 1038f0 ff25820b c701688c 000000e9 20f7ffff .%....h..... ... - 103900 ff257a0b c701688d 000000e9 10f7ffff .%z...h......... - 103910 ff25720b c701688e 000000e9 00f7ffff .%r...h......... - 103920 ff256a0b c701688f 000000e9 f0f6ffff .%j...h......... - 103930 ff25620b c7016890 000000e9 e0f6ffff .%b...h......... - 103940 ff255a0b c7016891 000000e9 d0f6ffff .%Z...h......... - 103950 ff25520b c7016892 000000e9 c0f6ffff .%R...h......... - 103960 ff254a0b c7016893 000000e9 b0f6ffff .%J...h......... - 103970 ff25420b c7016894 000000e9 a0f6ffff .%B...h......... - 103980 ff253a0b c7016895 000000e9 90f6ffff .%:...h......... - 103990 ff25320b c7016896 000000e9 80f6ffff .%2...h......... - 1039a0 ff252a0b c7016897 000000e9 70f6ffff .%*...h.....p... - 1039b0 ff25220b c7016898 000000e9 60f6ffff .%"...h.....`... - 1039c0 ff251a0b c7016899 000000e9 50f6ffff .%....h.....P... - 1039d0 ff25120b c701689a 000000e9 40f6ffff .%....h.....@... - 1039e0 ff250a0b c701689b 000000e9 30f6ffff .%....h.....0... - 1039f0 ff25020b c701689c 000000e9 20f6ffff .%....h..... ... - 103a00 ff25fa0a c701689d 000000e9 10f6ffff .%....h......... - 103a10 ff25f20a c701689e 000000e9 00f6ffff .%....h......... - 103a20 ff25ea0a c701689f 000000e9 f0f5ffff .%....h......... - 103a30 ff25e20a c70168a0 000000e9 e0f5ffff .%....h......... - 103a40 ff25da0a c70168a1 000000e9 d0f5ffff .%....h......... - 103a50 ff25d20a c70168a2 000000e9 c0f5ffff .%....h......... - 103a60 ff25ca0a c70168a3 000000e9 b0f5ffff .%....h......... - 103a70 ff25c20a c70168a4 000000e9 a0f5ffff .%....h......... - 103a80 ff25ba0a c70168a5 000000e9 90f5ffff .%....h......... - 103a90 ff25b20a c70168a6 000000e9 80f5ffff .%....h......... - 103aa0 ff25aa0a c70168a7 000000e9 70f5ffff .%....h.....p... - 103ab0 ff25a20a c70168a8 000000e9 60f5ffff .%....h.....`... - 103ac0 ff259a0a c70168a9 000000e9 50f5ffff .%....h.....P... - 103ad0 ff25920a c70168aa 000000e9 40f5ffff .%....h.....@... - 103ae0 ff258a0a c70168ab 000000e9 30f5ffff .%....h.....0... - 103af0 ff25820a c70168ac 000000e9 20f5ffff .%....h..... ... - 103b00 ff257a0a c70168ad 000000e9 10f5ffff .%z...h......... - 103b10 ff25720a c70168ae 000000e9 00f5ffff .%r...h......... - 103b20 ff256a0a c70168af 000000e9 f0f4ffff .%j...h......... - 103b30 ff25620a c70168b0 000000e9 e0f4ffff .%b...h......... - 103b40 ff255a0a c70168b1 000000e9 d0f4ffff .%Z...h......... - 103b50 ff25520a c70168b2 000000e9 c0f4ffff .%R...h......... - 103b60 ff254a0a c70168b3 000000e9 b0f4ffff .%J...h......... - 103b70 ff25420a c70168b4 000000e9 a0f4ffff .%B...h......... - 103b80 ff253a0a c70168b5 000000e9 90f4ffff .%:...h......... - 103b90 ff25320a c70168b6 000000e9 80f4ffff .%2...h......... - 103ba0 ff252a0a c70168b7 000000e9 70f4ffff .%*...h.....p... - 103bb0 ff25220a c70168b8 000000e9 60f4ffff .%"...h.....`... - 103bc0 ff251a0a c70168b9 000000e9 50f4ffff .%....h.....P... - 103bd0 ff25120a c70168ba 000000e9 40f4ffff .%....h.....@... - 103be0 ff250a0a c70168bb 000000e9 30f4ffff .%....h.....0... - 103bf0 ff25020a c70168bc 000000e9 20f4ffff .%....h..... ... - 103c00 ff25fa09 c70168bd 000000e9 10f4ffff .%....h......... - 103c10 ff25f209 c70168be 000000e9 00f4ffff .%....h......... - 103c20 ff25ea09 c70168bf 000000e9 f0f3ffff .%....h......... - 103c30 ff25e209 c70168c0 000000e9 e0f3ffff .%....h......... /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .plt.got --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,28 +2,28 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .plt.got: - 111e10 ff25da1e c6016690 ff25fa1e c6016690 .%....f..%....f. - 111e20 ff25021f c6016690 ff25021f c6016690 .%....f..%....f. - 111e30 ff25021f c6016690 ff25121f c6016690 .%....f..%....f. - 111e40 ff251a1f c6016690 ff251a1f c6016690 .%....f..%....f. - 111e50 ff251a1f c6016690 ff25221f c6016690 .%....f..%"...f. - 111e60 ff25221f c6016690 ff252a1f c6016690 .%"...f..%*...f. - 111e70 ff252a1f c6016690 ff25321f c6016690 .%*...f..%2...f. - 111e80 ff253a1f c6016690 ff253a1f c6016690 .%:...f..%:...f. - 111e90 ff254a1f c6016690 ff25521f c6016690 .%J...f..%R...f. - 111ea0 ff25521f c6016690 ff25721f c6016690 .%R...f..%r...f. - 111eb0 ff258a1f c6016690 ff258a1f c6016690 .%....f..%....f. - 111ec0 ff258a1f c6016690 ff258a1f c6016690 .%....f..%....f. - 111ed0 ff25921f c6016690 ff259a1f c6016690 .%....f..%....f. - 111ee0 ff259a1f c6016690 ff259a1f c6016690 .%....f..%....f. - 111ef0 ff25a21f c6016690 ff25a21f c6016690 .%....f..%....f. - 111f00 ff25a21f c6016690 ff25aa1f c6016690 .%....f..%....f. - 111f10 ff25ea1f c6016690 ff25f21f c6016690 .%....f..%....f. - 111f20 ff25fa1f c6016690 ff25fa1f c6016690 .%....f..%....f. - 111f30 ff250a20 c6016690 ff251220 c6016690 .%. ..f..%. ..f. - 111f40 ff252220 c6016690 ff252220 c6016690 .%" ..f..%" ..f. - 111f50 ff252220 c6016690 ff252220 c6016690 .%" ..f..%" ..f. - 111f60 ff252220 c6016690 ff252a20 c6016690 .%" ..f..%* ..f. - 111f70 ff252a20 c6016690 ff253220 c6016690 .%* ..f..%2 ..f. - 111f80 ff253a20 c6016690 ff254a20 c6016690 .%: ..f..%J ..f. - 111f90 ff254a20 c6016690 ff255220 c6016690 .%J ..f..%R ..f. + 111e10 ff25da8e c3016690 ff25fa8e c3016690 .%....f..%....f. + 111e20 ff25028f c3016690 ff25028f c3016690 .%....f..%....f. + 111e30 ff25028f c3016690 ff25128f c3016690 .%....f..%....f. + 111e40 ff251a8f c3016690 ff251a8f c3016690 .%....f..%....f. + 111e50 ff251a8f c3016690 ff25228f c3016690 .%....f..%"...f. + 111e60 ff25228f c3016690 ff252a8f c3016690 .%"...f..%*...f. + 111e70 ff252a8f c3016690 ff25328f c3016690 .%*...f..%2...f. + 111e80 ff253a8f c3016690 ff253a8f c3016690 .%:...f..%:...f. + 111e90 ff254a8f c3016690 ff25528f c3016690 .%J...f..%R...f. + 111ea0 ff25528f c3016690 ff25728f c3016690 .%R...f..%r...f. + 111eb0 ff258a8f c3016690 ff258a8f c3016690 .%....f..%....f. + 111ec0 ff258a8f c3016690 ff258a8f c3016690 .%....f..%....f. + 111ed0 ff25928f c3016690 ff259a8f c3016690 .%....f..%....f. + 111ee0 ff259a8f c3016690 ff259a8f c3016690 .%....f..%....f. + 111ef0 ff25a28f c3016690 ff25a28f c3016690 .%....f..%....f. + 111f00 ff25a28f c3016690 ff25aa8f c3016690 .%....f..%....f. + 111f10 ff25ea8f c3016690 ff25f28f c3016690 .%....f..%....f. + 111f20 ff25fa8f c3016690 ff25fa8f c3016690 .%....f..%....f. + 111f30 ff250a90 c3016690 ff251290 c3016690 .%....f..%....f. + 111f40 ff252290 c3016690 ff252290 c3016690 .%"...f..%"...f. + 111f50 ff252290 c3016690 ff252290 c3016690 .%"...f..%"...f. + 111f60 ff252290 c3016690 ff252a90 c3016690 .%"...f..%*...f. + 111f70 ff252a90 c3016690 ff253290 c3016690 .%*...f..%2...f. + 111f80 ff253a90 c3016690 ff254a90 c3016690 .%:...f..%J...f. + 111f90 ff254a90 c3016690 ff255290 c3016690 .%J...f..%R...f. /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,101 +2,101 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .text: - 0118000 8b0d9a96 c70185c9 7501c350 e8ef71ff ........u..P..q. - 0118010 ffe8da25 ffffc705 8096c701 00000000 ...%............ + 0118000 8b0d9a06 c50185c9 7501c350 e8ef71ff ........u..P..q. + 0118010 ffe8da25 ffffc705 8006c501 00000000 ...%............ 0118020 5ac3662e 0f1f8400 00000000 0f1f4000 Z.f...........@. - 0118030 8b0d6a96 c70185c9 7401c352 31c0e86d ..j.....t..R1..m + 0118030 8b0d6a06 c50185c9 7401c352 31c0e86d ..j.....t..R1..m 0118040 bafeff31 c0e8f615 ffffe891 97ffff48 ...1...........H - 0118050 8b0572be c5018338 00741848 8b0546bd ..r....8.t.H..F. - 0118060 c5018338 007413c7 052f96c7 01010000 ...8.t.../...... + 0118050 8b05722e c3018338 00741848 8b05462d ..r....8.t.H..F- + 0118060 c3018338 007413c7 052f06c5 01010000 ...8.t.../...... 0118070 0058c3e8 1854ffff ebe1e811 1fffffeb .X...T.......... 0118080 e6662e0f 1f840000 0000000f 1f440000 .f...........D.. - 0118090 488d3db1 36c70148 8d05aa36 c7014839 H.=.6..H...6..H9 - 01180a0 f8741548 8b05e6be c5014885 c07409ff .t.H......H..t.. + 0118090 488d3db1 a6c40148 8d05aaa6 c4014839 H.=....H......H9 + 01180a0 f8741548 8b05e62e c3014885 c07409ff .t.H......H..t.. 01180b0 e00f1f80 00000000 c30f1f80 00000000 ................ - 01180c0 488d3d81 36c70148 8d357a36 c7014829 H.=.6..H.5z6..H) + 01180c0 488d3d81 a6c40148 8d357aa6 c4014829 H.=....H.5z...H) 01180d0 fe4889f0 48c1ee3f 48c1f803 4801c648 .H..H..?H...H..H - 01180e0 d1fe7414 488b05e5 bec50148 85c07408 ..t.H......H..t. + 01180e0 d1fe7414 488b05e5 2ec30148 85c07408 ..t.H......H..t. 01180f0 ffe0660f 1f440000 c30f1f80 00000000 ..f..D.......... - 0118100 f30f1efa 803d5536 c7010075 2b554883 .....=U6...u+UH. - 0118110 3d5abcc5 01004889 e5740c48 8b3dfe35 =Z....H..t.H.=.5 - 0118120 c601e829 9dffffe8 64ffffff c6052d36 ...)....d.....-6 - 0118130 c701015d c30f1f00 c30f1f80 00000000 ...]............ + 0118100 f30f1efa 803d55a6 c4010075 2b554883 .....=U....u+UH. + 0118110 3d5a2cc3 01004889 e5740c48 8b3dfea5 =Z,...H..t.H.=.. + 0118120 c301e829 9dffffe8 64ffffff c6052da6 ...)....d.....-. + 0118130 c401015d c30f1f00 c30f1f80 00000000 ...]............ 0118140 f30f1efa e977ffff ff0f1f80 00000000 .....w.......... 0118150 48633f48 85ff7e60 48631248 85d27838 Hc?H..~`Hc.H..x8 - 0118160 4d63004d 85c07810 488b0571 bbc50148 Mc.M..x.H..q...H + 0118160 4d63004d 85c07810 488b0571 2bc30148 Mc.M..x.H..q+..H 0118170 8b00ff60 280f1f00 488d47ff 490fafc0 ...`(...H.G.I... - 0118180 4801c048 29c1488b 0553bbc5 01488b00 H..H).H..S...H.. + 0118180 4801c048 29c1488b 05532bc3 01488b00 H..H).H..S+..H.. 0118190 ff60280f 1f440000 488d47ff 4d630048 .`(..D..H.G.Mc.H 01181a0 0fafc248 c1e00248 29c64d85 c079b9eb ...H...H).M..y.. 01181b0 c70f1f80 00000000 c30f1f80 00000000 ................ 01181c0 48633f48 85ff7e60 48631248 85d27838 Hc?H..~`Hc.H..x8 - 01181d0 4d63004d 85c07810 488b0501 bbc50148 Mc.M..x.H......H + 01181d0 4d63004d 85c07810 488b0501 2bc30148 Mc.M..x.H...+..H 01181e0 8b00ff60 300f1f00 488d47ff 490fafc0 ...`0...H.G.I... - 01181f0 4801c048 29c1488b 05e3bac5 01488b00 H..H).H......H.. + 01181f0 4801c048 29c1488b 05e32ac3 01488b00 H..H).H...*..H.. 0118200 ff60300f 1f440000 488d47ff 4d630048 .`0..D..H.G.Mc.H 0118210 0fafc248 c1e00348 29c64d85 c079b9eb ...H...H).M..y.. 0118220 c70f1f80 00000000 c30f1f80 00000000 ................ 0118230 48633f48 85ff7e58 48631248 85d27838 Hc?H..~XHc.H..x8 - 0118240 4d63004d 85c07810 488b0591 bac50148 Mc.M..x.H......H + 0118240 4d63004d 85c07810 488b0591 2ac30148 Mc.M..x.H...*..H 0118250 8b00ff60 380f1f00 488d47ff 490fafc0 ...`8...H.G.I... - 0118260 48c1e002 4829c148 8b0572ba c501488b H...H).H..r...H. + 0118260 48c1e002 4829c148 8b05722a c301488b H...H).H..r*..H. 0118270 00ff6038 0f1f4000 488d47ff 4d630048 ..`8..@.H.G.Mc.H 0118280 0fafc248 01c04829 c64d85c0 79baebc8 ...H..H).M..y... 0118290 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. 01182a0 48633f48 85ff7e58 48631248 85d27838 Hc?H..~XHc.H..x8 - 01182b0 4d63004d 85c07810 488b0521 bac50148 Mc.M..x.H..!...H + 01182b0 4d63004d 85c07810 488b0521 2ac30148 Mc.M..x.H..!*..H 01182c0 8b00ff60 400f1f00 488d47ff 490fafc0 ...`@...H.G.I... - 01182d0 48c1e003 4829c148 8b0502ba c501488b H...H).H......H. + 01182d0 48c1e003 4829c148 8b05022a c301488b H...H).H...*..H. 01182e0 00ff6040 0f1f4000 488d47ff 4d630048 ..`@..@.H.G.Mc.H 01182f0 0fafc248 01c04829 c64d85c0 79baebc8 ...H..H).M..y... 0118300 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. 0118310 85ff7e5c 85d27840 4585c078 23488b05 ..~\..x@E..x#H.. - 0118320 bcb9c501 4863d248 63ff4d63 c0488b00 ....Hc.Hc.Mc.H.. + 0118320 bc29c301 4863d248 63ff4d63 c0488b00 .)..Hc.Hc.Mc.H.. 0118330 488b4028 ffe0662e 0f1f8400 00000000 H.@(..f......... 0118340 8d47ff41 0fafc048 984801c0 4829c1eb .G.A...H.H..H).. 0118350 cc0f1f80 00000000 8d47ff0f afc24898 .........G....H. 0118360 48c1e002 4829c645 85c079b1 ebd26690 H...H).E..y...f. 0118370 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. 0118380 85ff7e5c 85d27840 4585c078 23488b05 ..~\..x@E..x#H.. - 0118390 4cb9c501 4863d248 63ff4d63 c0488b00 L...Hc.Hc.Mc.H.. + 0118390 4c29c301 4863d248 63ff4d63 c0488b00 L)..Hc.Hc.Mc.H.. 01183a0 488b4030 ffe0662e 0f1f8400 00000000 H.@0..f......... 01183b0 8d47ff41 0fafc048 984801c0 4829c1eb .G.A...H.H..H).. 01183c0 cc0f1f80 00000000 8d47ff0f afc24898 .........G....H. 01183d0 48c1e003 4829c645 85c079b1 ebd26690 H...H).E..y...f. 01183e0 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. 01183f0 85ff7e5c 85d27840 4585c078 23488b05 ..~\..x@E..x#H.. - 0118400 dcb8c501 4863d248 63ff4d63 c0488b00 ....Hc.Hc.Mc.H.. + 0118400 dc28c301 4863d248 63ff4d63 c0488b00 .(..Hc.Hc.Mc.H.. 0118410 488b4038 ffe0662e 0f1f8400 00000000 H.@8..f......... 0118420 8d47ff41 0fafc048 9848c1e0 024829c1 .G.A...H.H...H). 0118430 ebcb660f 1f440000 8d47ff0f afc24898 ..f..D...G....H. 0118440 4801c048 29c64585 c079b2eb d30f1f00 H..H).E..y...... 0118450 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. 0118460 85ff7e5c 85d27840 4585c078 23488b05 ..~\..x@E..x#H.. - 0118470 6cb8c501 4863d248 63ff4d63 c0488b00 l...Hc.Hc.Mc.H.. + 0118470 6c28c301 4863d248 63ff4d63 c0488b00 l(..Hc.Hc.Mc.H.. 0118480 488b4040 ffe0662e 0f1f8400 00000000 H.@@..f......... 0118490 8d47ff41 0fafc048 9848c1e0 034829c1 .G.A...H.H...H). 01184a0 ebcb660f 1f440000 8d47ff0f afc24898 ..f..D...G....H. 01184b0 4801c048 29c64585 c079b2eb d30f1f00 H..H).E..y...... 01184c0 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. 01184d0 48633f48 85ff7e68 48631248 85d27840 Hc?H..~hHc.H..x@ - 01184e0 4d63004d 85c07818 488b05f1 b7c50148 Mc.M..x.H......H + 01184e0 4d63004d 85c07818 488b05f1 27c30148 Mc.M..x.H...'..H 01184f0 8b00ffa0 a8000000 0f1f8400 00000000 ................ 0118500 488d47ff 490fafc0 4801c048 29c1488b H.G.I...H..H).H. - 0118510 05cbb7c5 01488b00 ffa0a800 00006690 .....H........f. + 0118510 05cb27c3 01488b00 ffa0a800 00006690 ..'..H........f. 0118520 488d47ff 4d630048 0fafc248 01c04829 H.G.Mc.H...H..H) 0118530 c64d85c0 79b2ebc8 0f1f8400 00000000 .M..y........... 0118540 660fefc0 c366662e 0f1f8400 00000000 f....ff......... 0118550 85ff7e5c 85d27840 4585c078 23488b05 ..~\..x@E..x#H.. - 0118560 7cb7c501 4863d248 63ff4d63 c0488b00 |...Hc.Hc.Mc.H.. + 0118560 7c27c301 4863d248 63ff4d63 c0488b00 |'..Hc.Hc.Mc.H.. 0118570 488b80a8 000000ff e00f1f80 00000000 H............... 0118580 8d47ff41 0fafc048 984801c0 4829c1eb .G.A...H.H..H).. 0118590 cc0f1f80 00000000 8d47ff0f afc24898 .........G....H. 01185a0 4801c048 29c64585 c079b2eb d30f1f00 H..H).E..y...... 01185b0 660fefc0 c366662e 0f1f8400 00000000 f....ff......... 01185c0 48633f85 ff7e7948 83ec088b 124989c9 Hc?..~yH.....I.. - 01185d0 85d27854 49630085 c0783548 8b0dfeb6 ..xTIc...x5H.... - 01185e0 c5014883 ec084c63 c2660fef c031d24c ..H...Lc.f...1.L + 01185d0 85d27854 49630085 c0783548 8b0dfe26 ..xTIc...x5H...& + 01185e0 c3014883 ec084c63 c2660fef c031d24c ..H...Lc.f...1.L 01185f0 8b196a00 4889f131 f66a0050 41ff9340 ..j.H..1.j.PA..@ 0118600 03000048 83c428c3 0f1f8400 00000000 ...H..(......... 0118610 8d4fff0f afc84863 c948c1e1 024929c9 .O....Hc.H...I). @@ -104,24 +104,24 @@ 0118630 48c1e002 4829c649 630085c0 799debd0 H...H).Ic...y... 0118640 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. 0118650 48633f48 85ff7e68 48631248 85d27840 Hc?H..~hHc.H..x@ - 0118660 4d63004d 85c07818 488b0571 b6c50148 Mc.M..x.H..q...H + 0118660 4d63004d 85c07818 488b0571 26c30148 Mc.M..x.H..q&..H 0118670 8b00ffa0 18030000 0f1f8400 00000000 ................ 0118680 488d47ff 490fafc0 48c1e002 4829c148 H.G.I...H...H).H - 0118690 8b054ab6 c501488b 00ffa018 03000090 ..J...H......... + 0118690 8b054a26 c301488b 00ffa018 03000090 ..J&..H......... 01186a0 488d47ff 4d630048 0fafc248 c1e00248 H.G.Mc.H...H...H 01186b0 29c64d85 c079b1eb c70f1f80 00000000 ).M..y.......... 01186c0 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. 01186d0 48633f48 85ff7e68 48631248 85d27840 Hc?H..~hHc.H..x@ - 01186e0 4d63004d 85c07818 488b05f1 b5c50148 Mc.M..x.H......H + 01186e0 4d63004d 85c07818 488b05f1 25c30148 Mc.M..x.H...%..H 01186f0 8b00ffa0 20030000 0f1f8400 00000000 .... ........... 0118700 488d47ff 490fafc0 48c1e002 4829c148 H.G.I...H...H).H - 0118710 8b05cab5 c501488b 00ffa020 03000090 ......H.... .... + 0118710 8b05ca25 c301488b 00ffa020 03000090 ...%..H.... .... 0118720 488d47ff 4d630048 0fafc248 c1e00248 H.G.Mc.H...H...H 0118730 29c64d85 c079b1eb c70f1f80 00000000 ).M..y.......... 0118740 660fefc0 c366662e 0f1f8400 00000000 f....ff......... 0118750 5348633f 4889f348 85ff7e7c 4889c848 SHc?H..H..~|H..H 0118760 89d64c89 c1486310 4885d278 4b4d6301 ..L..Hc.H..xKMc. - 0118770 4d85c078 2b488b05 64b5c501 488b00ff M..x+H..d...H... + 0118770 4d85c078 2b488b05 6425c301 488b00ff M..x+H..d%..H... 0118780 90a00500 00660f28 c8660fef c0f30f5a .....f.(.f.....Z 0118790 03f20f58 c15bf20f 5ac0c30f 1f440000 ...X.[..Z....D.. 01187a0 488d47ff 490fafc0 48c1e002 4829c1eb H.G.I...H...H).. @@ -129,53 +129,53 @@ 01187c0 0fafc248 c1e00248 29c64d85 c079a6eb ...H...H).M..y.. 01187d0 cf0f1f80 00000000 f30f1006 5bc36690 ............[.f. 01187e0 48633f48 85ff7e68 48631248 85d27840 Hc?H..~hHc.H..x@ - 01187f0 4d63004d 85c07818 488b05e1 b4c50148 Mc.M..x.H......H + 01187f0 4d63004d 85c07818 488b05e1 24c30148 Mc.M..x.H...$..H 0118800 8b00ffa0 a0050000 0f1f8400 00000000 ................ 0118810 488d47ff 490fafc0 48c1e002 4829c148 H.G.I...H...H).H - 0118820 8b05bab4 c501488b 00ffa0a0 05000090 ......H......... + 0118820 8b05ba24 c301488b 00ffa0a0 05000090 ...$..H......... 0118830 488d47ff 4d630048 0fafc248 c1e00248 H.G.Mc.H...H...H 0118840 29c64d85 c079b1eb c70f1f80 00000000 ).M..y.......... 0118850 660fefc0 c366662e 0f1f8400 00000000 f....ff......... - 0118860 48633f48 85ff7e18 488b0571 b4c50148 Hc?H..~.H..q...H + 0118860 48633f48 85ff7e18 488b0571 24c30148 Hc?H..~.H..q$..H 0118870 6312488b 00ffa008 0300000f 1f440000 c.H..........D.. 0118880 660fefc0 c366662e 0f1f8400 00000000 f....ff......... - 0118890 48633f48 85ff7e18 488b0541 b4c50148 Hc?H..~.H..A...H + 0118890 48633f48 85ff7e18 488b0541 24c30148 Hc?H..~.H..A$..H 01188a0 6312488b 00ffa010 0300000f 1f440000 c.H..........D.. 01188b0 660fefc0 c366662e 0f1f8400 00000000 f....ff......... - 01188c0 48633f48 85ff7e18 488b0511 b4c50148 Hc?H..~.H......H + 01188c0 48633f48 85ff7e18 488b0511 24c30148 Hc?H..~.H...$..H 01188d0 6312488b 00ffa000 0300000f 1f440000 c.H..........D.. 01188e0 660fefc0 c366662e 0f1f8400 00000000 f....ff......... - 01188f0 48633f48 85ff7e18 488b05e1 b3c50148 Hc?H..~.H......H + 01188f0 48633f48 85ff7e18 488b05e1 23c30148 Hc?H..~.H...#..H 0118900 6312488b 00ffa0d0 0200000f 1f440000 c.H..........D.. 0118910 660fefc0 c366662e 0f1f8400 00000000 f....ff......... - 0118920 48633f48 85ff7e18 488b05b1 b3c50148 Hc?H..~.H......H + 0118920 48633f48 85ff7e18 488b05b1 23c30148 Hc?H..~.H...#..H 0118930 6312488b 00ffa0c0 0200000f 1f440000 c.H..........D.. 0118940 660fefc0 c366662e 0f1f8400 00000000 f....ff......... - 0118950 48633f48 85ff7e28 488b0581 b3c50153 Hc?H..~(H......S + 0118950 48633f48 85ff7e28 488b0581 23c30153 Hc?H..~(H...#..S 0118960 4889fb48 6312488b 00ff90f0 02000039 H..Hc.H........9 /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .fini --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,4 +2,4 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .fini: - 1baa330 f30f1efa 4883ec08 4883c408 c3 ....H...H.... + 1b82330 f30f1efa 4883ec08 4883c408 c3 ....H...H.... /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .rodata --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,4536 +2,4335 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .rodata: - 1bab000 53424745 4d562000 53424745 4d4d2000 SBGEMV .SBGEMM . - 1bab010 5347454d 56200073 7461636b 5f636865 SGEMV .stack_che - 1bab020 636b203d 3d203078 37666330 31323334 ck == 0x7fc01234 - 1bab030 00534745 52202000 53545253 56200053 .SGER .STRSV .S - 1bab040 54524d56 20005353 594d5620 00535359 TRMV .SSYMV .SSY - 1bab050 52202000 53535952 32200053 47424d56 R .SSYR2 .SGBMV - 1bab060 20005353 424d5620 00535350 4d562000 .SSBMV .SSPMV . - 1bab070 53535052 20200053 53505232 20005354 SSPR .SSPR2 .ST - 1bab080 42535620 00535442 4d562000 53545053 BSV .STBMV .STPS - 1bab090 56200053 54504d56 20005347 454d4d20 V .STPMV .SGEMM - 1bab0a0 00535359 4d4d2000 5354524d 4d200053 .SSYMM .STRMM .S - 1bab0b0 5452534d 20005353 59524b20 00535359 TRSM .SSYRK .SSY - 1bab0c0 52324b00 534f4d41 54434f50 59005349 R2K.SOMATCOPY.SI - 1bab0d0 4d415443 4f505900 4d656d6f 72792061 MATCOPY.Memory a - 1bab0e0 6c6c6f63 20666169 6c656400 53474541 lloc failed.SGEA - 1bab0f0 44442000 53474554 52460053 47455452 DD .SGETRF.SGETR - 1bab100 53005350 4f545246 00534745 54463200 S.SPOTRF.SGETF2. - 1bab110 53504f54 46320053 4c415555 3200534c SPOTF2.SLAUU2.SL - 1bab120 4155554d 00535452 54493200 53545254 AUUM.STRTI2.STRT - 1bab130 52490053 54525452 53004447 454d5620 RI.STRTRS.DGEMV - 1bab140 00444745 52202000 44545253 56200044 .DGER .DTRSV .D - 1bab150 54524d56 20004453 594d5620 00445359 TRMV .DSYMV .DSY - 1bab160 52202000 44535952 32200044 47424d56 R .DSYR2 .DGBMV - 1bab170 20004453 424d5620 00445350 4d562000 .DSBMV .DSPMV . - 1bab180 44535052 20200044 53505232 20004454 DSPR .DSPR2 .DT - 1bab190 42535620 00445442 4d562000 44545053 BSV .DTBMV .DTPS - 1bab1a0 56200044 54504d56 20004447 454d4d20 V .DTPMV .DGEMM - 1bab1b0 00445359 4d4d2000 4454524d 4d200044 .DSYMM .DTRMM .D - 1bab1c0 5452534d 20004453 59524b20 00445359 TRSM .DSYRK .DSY - 1bab1d0 52324b00 444f4d41 54434f50 59004449 R2K.DOMATCOPY.DI - 1bab1e0 4d415443 4f505900 44474541 44442000 MATCOPY.DGEADD . - 1bab1f0 44474554 52460044 47455452 53004450 DGETRF.DGETRS.DP - 1bab200 4f545246 00444745 54463200 44504f54 OTRF.DGETF2.DPOT - 1bab210 46320044 47455356 00444c41 55553200 F2.DGESV.DLAUU2. - 1bab220 444c4155 554d0044 54525449 32004454 DLAUUM.DTRTI2.DT - 1bab230 52545249 00445452 54525300 00000000 RTRI.DTRTRS..... - 1bab240 63626c61 735f6467 65720000 00000000 cblas_dger...... - 1bab250 63626c61 735f6467 656d7600 64676572 cblas_dgemv.dger - 1bab260 5f006467 656d765f 00000000 00000000 _.dgemv_........ - 1bab270 63626c61 735f7367 65720000 00000000 cblas_sger...... - 1bab280 63626c61 735f7367 656d7600 73676572 cblas_sgemv.sger - 1bab290 5f007367 656d765f 00000000 0000803f _.sgemv_.......? - 1bab2a0 000080bf 0000804b 00008039 00008033 .......K...9...3 - 1bab2b0 00008045 00000000 00000000 00000000 ...E............ - 1bab2c0 ffffff7f 00000000 00000000 00000000 ................ - 1bab2d0 00000080 00000000 00000000 00000000 ................ - 1bab2e0 ffffffff ffffff7f 00000000 00000000 ................ - 1bab2f0 00000000 00000080 00000000 00000000 ................ - 1bab300 fdf40201 0000703e 00000000 0000f03f ......p>.......? - 1bab310 00000000 000000c0 00000000 0000f0bf ................ - 1bab320 00000000 00007041 00000000 0000303f ......pA......0? - 1bab330 00000000 0000703e 00000000 0000b040 ......p>.......@ - 1bab340 00000000 00001041 50617261 6d657465 .......AParamete - 1bab350 72202564 20746f20 726f7574 696e6520 r %d to routine - 1bab360 25732077 61732069 6e636f72 72656374 %s was incorrect - 1bab370 0a000000 00000000 4d656d6f 72792061 ........Memory a - 1bab380 6c6c6f63 20666169 6c656420 696e207a lloc failed in z - 1bab390 696d6174 636f7079 00434745 4d562000 imatcopy.CGEMV . - 1bab3a0 7a67656d 762e6300 43474552 55202000 zgemv.c.CGERU . - 1bab3b0 7a676572 2e630043 47455243 20004354 zger.c.CGERC .CT - 1bab3c0 52535620 00435452 4d562000 7a74726d RSV .CTRMV .ztrm - 1bab3d0 762e6300 43535952 32200043 47424d56 v.c.CSYR2 .CGBMV - 1bab3e0 20004353 424d5620 00435350 52322000 .CSBMV .CSPR2 . - 1bab3f0 43544253 56200043 54424d56 20004354 CTBSV .CTBMV .CT - 1bab400 50535620 00435450 4d562000 4348454d PSV .CTPMV .CHEM - 1bab410 56200043 48424d56 20004348 45522020 V .CHBMV .CHER - 1bab420 00434845 52322000 4348504d 56200043 .CHER2 .CHPMV .C - 1bab430 48505220 20004348 50523220 00434745 HPR .CHPR2 .CGE - 1bab440 4d4d2000 4353594d 4d200043 54524d4d MM .CSYMM .CTRMM - 1bab450 20004354 52534d20 00435359 524b2000 .CTRSM .CSYRK . - 1bab460 43535952 324b0043 48454d4d 20004348 CSYR2K.CHEMM .CH - 1bab470 45524b20 00434845 52324b00 434f4d41 ERK .CHER2K.COMA - 1bab480 54434f50 59004349 4d415443 4f505900 TCOPY.CIMATCOPY. - 1bab490 43474541 44442000 4347454d 4d334d20 CGEADD .CGEMM3M - 1bab4a0 00434745 54524600 43474554 52530043 .CGETRF.CGETRS.C - 1bab4b0 504f5452 46004347 45544632 0043504f POTRF.CGETF2.CPO - 1bab4c0 54463200 434c4155 55320043 4c415555 TF2.CLAUU2.CLAUU - 1bab4d0 4d004354 52544932 00435452 54524900 M.CTRTI2.CTRTRI. - 1bab4e0 43545254 5253005a 47454d56 20005a47 CTRTRS.ZGEMV .ZG - 1bab4f0 45525520 20005a47 45524320 20005a54 ERU .ZGERC .ZT - 1bab500 52535620 005a5452 4d562000 5a535952 RSV .ZTRMV .ZSYR - 1bab510 3220005a 47424d56 20005a53 424d5620 2 .ZGBMV .ZSBMV - 1bab520 005a5350 52322000 5a544253 5620005a .ZSPR2 .ZTBSV .Z - 1bab530 54424d56 20005a54 50535620 005a5450 TBMV .ZTPSV .ZTP - 1bab540 4d562000 5a48454d 5620005a 48424d56 MV .ZHEMV .ZHBMV - 1bab550 20005a48 45522020 005a4845 52322000 .ZHER .ZHER2 . - 1bab560 5a48504d 5620005a 48505220 20005a48 ZHPMV .ZHPR .ZH - 1bab570 50523220 005a4745 4d4d2000 5a53594d PR2 .ZGEMM .ZSYM - 1bab580 4d20005a 54524d4d 20005a54 52534d20 M .ZTRMM .ZTRSM - 1bab590 005a5359 524b2000 5a535952 324b005a .ZSYRK .ZSYR2K.Z - 1bab5a0 48454d4d 20005a48 45524b20 005a4845 HEMM .ZHERK .ZHE - 1bab5b0 52324b00 5a4f4d41 54434f50 59005a49 R2K.ZOMATCOPY.ZI - 1bab5c0 4d415443 4f505900 5a474541 44442000 MATCOPY.ZGEADD . - 1bab5d0 5a47454d 4d334d20 005a4745 54524600 ZGEMM3M .ZGETRF. - 1bab5e0 5a474554 5253005a 504f5452 46005a47 ZGETRS.ZPOTRF.ZG - 1bab5f0 45544632 005a504f 54463200 5a474553 ETF2.ZPOTF2.ZGES - 1bab600 56005a4c 41555532 005a4c41 55554d00 V.ZLAUU2.ZLAUUM. - 1bab610 5a545254 4932005a 54525452 49005a54 ZTRTI2.ZTRTRI.ZT - 1bab620 52545253 00000000 63626c61 735f7a74 RTRS....cblas_zt - 1bab630 726d7600 00000000 63626c61 735f7a67 rmv.....cblas_zg - 1bab640 65727500 00000000 63626c61 735f7a67 eru.....cblas_zg - 1bab650 65726300 00000000 63626c61 735f7a67 erc.....cblas_zg - 1bab660 656d7600 7a74726d 765f007a 67657263 emv.ztrmv_.zgerc - 1bab670 5f007a67 6572755f 007a6765 6d765f00 _.zgeru_.zgemv_. - 1bab680 63626c61 735f6374 726d7600 00000000 cblas_ctrmv..... - 1bab690 63626c61 735f6367 65727500 00000000 cblas_cgeru..... - 1bab6a0 63626c61 735f6367 65726300 00000000 cblas_cgerc..... - 1bab6b0 63626c61 735f6367 656d7600 6374726d cblas_cgemv.ctrm - 1bab6c0 765f0063 67657263 5f006367 6572755f v_.cgerc_.cgeru_ - 1bab6d0 00636765 6d765f00 00000000 0000e040 .cgemv_........@ - 1bab6e0 00000000 0000c240 0000803f 00000000 .......@...?.... - 1bab6f0 00000000 0000f03f 4f70656e 424c4153 .......?OpenBLAS - 1bab700 3a206d61 6c6c6f63 20666169 6c656420 : malloc failed - 1bab710 696e2025 730a0000 00000000 00000000 in %s........... - 1bab720 64737972 6b5f7468 72656164 5f4c5400 dsyrk_thread_LT. - 1bab730 64737972 6b5f7468 72656164 5f4c4e00 dsyrk_thread_LN. - 1bab740 64737972 6b5f7468 72656164 5f555400 dsyrk_thread_UT. - 1bab750 64737972 6b5f7468 72656164 5f554e00 dsyrk_thread_UN. - 1bab760 73737972 6b5f7468 72656164 5f4c5400 ssyrk_thread_LT. - 1bab770 73737972 6b5f7468 72656164 5f4c4e00 ssyrk_thread_LN. - 1bab780 73737972 6b5f7468 72656164 5f555400 ssyrk_thread_UT. - 1bab790 73737972 6b5f7468 72656164 5f554e00 ssyrk_thread_UN. - 1bab7a0 00000000 00000000 00000000 00000000 ................ - 1bab7b0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab7c0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab7d0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab7e0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab7f0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab800 63686572 6b5f7468 72656164 5f4c4300 cherk_thread_LC. - 1bab810 63686572 6b5f7468 72656164 5f4c4e00 cherk_thread_LN. - 1bab820 63686572 6b5f7468 72656164 5f554300 cherk_thread_UC. - 1bab830 63686572 6b5f7468 72656164 5f554e00 cherk_thread_UN. - 1bab840 63737972 6b5f7468 72656164 5f4c5400 csyrk_thread_LT. - 1bab850 63737972 6b5f7468 72656164 5f4c4e00 csyrk_thread_LN. - 1bab860 63737972 6b5f7468 72656164 5f555400 csyrk_thread_UT. - 1bab870 63737972 6b5f7468 72656164 5f554e00 csyrk_thread_UN. - 1bab880 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab890 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab8a0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab8b0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab8c0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab8d0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab8e0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab8f0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab900 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab910 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab920 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab930 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab940 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab950 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab960 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab970 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab980 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab990 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab9a0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab9b0 00000000 00000000 00000000 00000000 ................ - 1bab9c0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab9d0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab9e0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1bab9f0 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1baba00 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1baba10 67656d6d 5f647269 76657200 00000000 gemm_driver..... - 1baba20 7a686572 6b5f7468 72656164 5f4c4300 zherk_thread_LC. - 1baba30 7a686572 6b5f7468 72656164 5f4c4e00 zherk_thread_LN. - 1baba40 7a686572 6b5f7468 72656164 5f554300 zherk_thread_UC. - 1baba50 7a686572 6b5f7468 72656164 5f554e00 zherk_thread_UN. - 1baba60 7a737972 6b5f7468 72656164 5f4c5400 zsyrk_thread_LT. - 1baba70 7a737972 6b5f7468 72656164 5f4c4e00 zsyrk_thread_LN. - 1baba80 7a737972 6b5f7468 72656164 5f555400 zsyrk_thread_UT. - 1baba90 7a737972 6b5f7468 72656164 5f554e00 zsyrk_thread_UN. - 1babaa0 4f70656e 424c4153 203a206d 756e6d61 OpenBLAS : munma - 1babab0 70206661 696c6564 3a004f50 454e424c p failed:.OPENBL - 1babac0 41535f56 4552424f 5345004f 50454e42 AS_VERBOSE.OPENB - 1babad0 4c41535f 424c4f43 4b5f4641 43544f52 LAS_BLOCK_FACTOR - 1babae0 004f5045 4e424c41 535f5448 52454144 .OPENBLAS_THREAD - 1babaf0 5f54494d 454f5554 004f5045 4e424c41 _TIMEOUT.OPENBLA - 1babb00 535f4e55 4d5f5448 52454144 5300474f S_NUM_THREADS.GO - 1babb10 544f5f4e 554d5f54 48524541 4453004f TO_NUM_THREADS.O - 1babb20 4d505f4e 554d5f54 48524541 4453004b MP_NUM_THREADS.K - 1babb30 61746d61 6900436f 70706572 6d696e65 atmai.Coppermine - 1babb40 004e6f72 7468776f 6f640050 72657363 .Northwood.Presc - 1babb50 6f747400 42616e69 6173004e 6568616c ott.Banias.Nehal - 1babb60 656d0043 6f726532 00417468 6c6f6e00 em.Core2.Athlon. - 1babb70 42617263 656c6f6e 61005361 6e647962 Barcelona.Sandyb - 1babb80 72696467 65004275 6c6c646f 7a657200 ridge.Bulldozer. - 1babb90 50696c65 64726976 65720048 61737765 Piledriver.Haswe - 1babba0 6c6c0053 7465616d 726f6c6c 65720045 ll.Steamroller.E - 1babbb0 78636176 61746f72 005a656e 00536b79 xcavator.Zen.Sky - 1babbc0 6c616b65 5800436f 6f706572 6c616b65 lakeX.Cooperlake - 1babbd0 00556e6b 6e6f776e 00204d41 585f5448 .Unknown. MAX_TH - 1babbe0 52454144 533d2564 004f5045 4e424c41 READS=%d.OPENBLA - 1babbf0 535f434f 52455459 50450047 656e7569 S_CORETYPE.Genui - 1babc00 6e65496e 74656c00 41757468 656e7469 neIntel.Authenti - 1babc10 63414d44 0043656e 74617572 4861756c cAMD.CentaurHaul /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .eh_frame_hdr --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,6684 +2,6658 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .eh_frame_hdr: - 1bbcb50 011b033b 84a10100 2f340000 d06454fe ...;..../4...dT. - 1bbcb60 a0a10100 c05255fe c8a10100 b0b455fe .....RU.......U. - 1bbcb70 cc5a0500 e0b455fe b05a0500 00b655fe .Z....U..Z....U. - 1bbcb80 e0a10100 70b655fe f4a10100 e0b655fe ....p.U.......U. - 1bbcb90 08a20100 50b755fe 1ca20100 c0b755fe ....P.U.......U. - 1bbcba0 30a20100 30b855fe 44a20100 a0b855fe 0...0.U.D.....U. - 1bbcbb0 58a20100 10b955fe 6ca20100 80b955fe X.....U.l.....U. - 1bbcbc0 80a20100 00ba55fe 94a20100 70ba55fe ......U.....p.U. - 1bbcbd0 a8a20100 00bb55fe d4a20100 80bb55fe ......U.......U. - 1bbcbe0 e8a20100 00bc55fe fca20100 90bc55fe ......U.......U. - 1bbcbf0 1ca30100 10bd55fe 30a30100 40bd55fe ......U.0...@.U. - 1bbcc00 44a30100 70bd55fe 58a30100 a0bd55fe D...p.U.X.....U. - 1bbcc10 6ca30100 d0bd55fe 80a30100 00be55fe l.....U.......U. - 1bbcc20 94a30100 40be55fe b0a30100 80be55fe ....@.U.......U. - 1bbcc30 cca30100 b0be55fe e0a30100 e0be55fe ......U.......U. - 1bbcc40 f4a30100 20bf55fe 10a40100 60bf55fe .... .U.....`.U. - 1bbcc50 2ca40100 e0bf55fe 40a40100 70c155fe ,.....U.@...p.U. - 1bbcc60 5ca40100 a0c455fe 70a40100 c0c855fe \.....U.p.....U. - 1bbcc70 84a40100 50c955fe 98a40100 90c955fe ....P.U.......U. - 1bbcc80 b4a40100 d0c955fe d0a40100 00ca55fe ......U.......U. - 1bbcc90 e4a40100 70ca55fe f8a40100 e0ca55fe ....p.U.......U. - 1bbcca0 0ca50100 80cb55fe 2ca50100 f0cb55fe ......U.,.....U. - 1bbccb0 40a50100 60cc55fe 54a50100 f0cd55fe @...`.U.T.....U. - 1bbccc0 70a50100 10d155fe 84a50100 30d555fe p.....U.....0.U. - 1bbccd0 98a50100 c0d555fe c4a50100 f0d555fe ......U.......U. - 1bbcce0 d8a50100 60d655fe eca50100 a0d655fe ....`.U.......U. - 1bbccf0 08a60100 e0d655fe 24a60100 10d755fe ......U.$.....U. - 1bbcd00 38a60100 a0d755fe 64a60100 20d855fe 8.....U.d... .U. - 1bbcd10 78a60100 a0d855fe 8ca60100 d0d855fe x.....U.......U. - 1bbcd20 a0a60100 00d955fe b4a60100 30d955fe ......U.....0.U. - 1bbcd30 c8a60100 60d955fe dca60100 90d955fe ....`.U.......U. - 1bbcd40 f0a60100 d0d955fe 0ca70100 10da55fe ......U.......U. - 1bbcd50 28a70100 40da55fe 3ca70100 70da55fe (...@.U.<...p.U. - 1bbcd60 50a70100 b0da55fe 6ca70100 f0da55fe P.....U.l.....U. - 1bbcd70 88a70100 70db55fe 9ca70100 00dd55fe ....p.U.......U. - 1bbcd80 b8a70100 40e055fe cca70100 50e455fe ....@.U.....P.U. - 1bbcd90 e0a70100 e0e455fe f4a70100 20e555fe ......U..... .U. - 1bbcda0 10a80100 60e555fe 2ca80100 90e555fe ....`.U.,.....U. - 1bbcdb0 40a80100 00e655fe 54a80100 70e655fe @.....U.T...p.U. - 1bbcdc0 68a80100 e0e655fe 7ca80100 70e855fe h.....U.|...p.U. - 1bbcdd0 98a80100 a0eb55fe aca80100 d0ef55fe ......U.......U. - 1bbcde0 c0a80100 60f055fe eca80100 90f055fe ....`.U.......U. - 1bbcdf0 00a90100 00f155fe 14a90100 40f155fe ......U.....@.U. - 1bbce00 30a90100 80f155fe 4ca90100 b0f155fe 0.....U.L.....U. - 1bbce10 60a90100 c0f355fe dca90100 e0f455fe `.....U.......U. - 1bbce20 54aa0100 e0f655fe fcaa0100 e0f755fe T.....U.......U. - 1bbce30 6cab0100 40f955fe e8ab0100 50fb55fe l...@.U.....P.U. - 1bbce40 64ac0100 70fc55fe dcac0100 70fe55fe d...p.U.....p.U. - 1bbce50 88ad0100 70ff55fe f8ad0100 e00056fe ....p.U.......V. - 1bbce60 78ae0100 300556fe 00af0100 f00956fe x...0.V.......V. - 1bbce70 8caf0100 800e56fe dcaf0100 501556fe ......V.....P.V. - 1bbce80 2cb00100 b01956fe 5cb00100 801d56fe ,.....V.\.....V. - 1bbce90 8cb00100 c01f56fe d8b00100 802256fe ......V......"V. - 1bbcea0 30b10100 902556fe bcb10100 c02856fe 0....%V......(V. - 1bbceb0 38b20100 f02c56fe e8b20100 903056fe 8....,V......0V. - 1bbcec0 84b30100 e03256fe fcb30100 d03456fe .....2V......4V. - 1bbced0 68b40100 e03756fe d8b40100 903b56fe h....7V......;V. - 1bbcee0 78b50100 b03d56fe d4b50100 a04056fe x....=V......@V. - 1bbcef0 3cb60100 604256fe 88b60100 d04456fe <...`BV......DV. - 1bbcf00 d4b60100 e04956fe 04b70100 404e56fe .....IV.....@NV. - 1bbcf10 34b70100 b05156fe c0b70100 c05456fe 4....QV......TV. - 1bbcf20 1cb80100 805756fe 68b80100 f05a56fe .....WV.h....ZV. - 1bbcf30 e4b80100 305f56fe 8cb90100 d06356fe ....0_V......cV. - 1bbcf40 24ba0100 506656fe 98ba0100 a06856fe $...PfV......hV. - 1bbcf50 00bb0100 506c56fe 70bb0100 407056fe ....PlV.p...@pV. - 1bbcf60 10bc0100 507356fe 78bc0100 b07556fe ....PsV.x....uV. - 1bbcf70 d0bc0100 707856fe 1cbd0100 907a56fe ....pxV......zV. - 1bbcf80 68bd0100 307f56fe b8bd0100 508256fe h...0.V.....P.V. - 1bbcf90 08be0100 408656fe 78be0100 308a56fe ....@.V.x...0.V. - 1bbcfa0 e8be0100 108d56fe 38bf0100 109056fe ......V.8.....V. - 1bbcfb0 98bf0100 c09256fe ccbf0100 109756fe ......V.......V. - 1bbcfc0 34c00100 009856fe 58c00100 d09e56fe 4.....V.X.....V. - 1bbcfd0 a8c00100 10a356fe f8c00100 b0a756fe ......V.......V. - 1bbcfe0 68c10100 50ac56fe d8c10100 a0af56fe h...P.V.......V. - 1bbcff0 28c20100 20b356fe 88c20100 60b556fe (... .V.....`.V. - 1bbd000 b4c20100 70b956fe 1cc30100 e0ba56fe ....p.V.......V. - 1bbd010 38c30100 d0bc56fe 84c30100 50bf56fe 8.....V.....P.V. - 1bbd020 d4c30100 b0c156fe 24c40100 00c356fe ......V.$.....V. - 1bbd030 50c40100 b0c456fe 88c40100 40c756fe P.....V.....@.V. - 1bbd040 d4c40100 f0c856fe 0cc50100 30cb56fe ......V.....0.V. - 1bbd050 5cc50100 e0cc56fe 9cc50100 90cf56fe \.....V.......V. - 1bbd060 ecc50100 00d356fe 3cc60100 80d756fe ......V.<.....V. - 1bbd070 6cc60100 50db56fe 9cc60100 90dd56fe l...P.V.......V. - 1bbd080 e8c60100 50e056fe 40c70100 60e356fe ....P.V.@...`.V. - 1bbd090 ccc70100 a0e656fe 48c80100 d0ea56fe ......V.H.....V. - 1bbd0a0 f8c80100 80ee56fe 94c90100 d0f056fe ......V.......V. - 1bbd0b0 0cca0100 d0f256fe 78ca0100 e0f556fe ......V.x.....V. - 1bbd0c0 e8ca0100 b0f956fe 94cb0100 d0fb56fe ......V.......V. - 1bbd0d0 f0cb0100 c0fe56fe 58cc0100 800057fe ......V.X.....W. - 1bbd0e0 a4cc0100 f00257fe f0cc0100 100857fe ......W.......W. - 1bbd0f0 20cd0100 700c57fe 50cd0100 e00f57fe ...p.W.P.....W. - 1bbd100 dccd0100 f01257fe 38ce0100 b01557fe ......W.8.....W. - 1bbd110 84ce0100 301957fe 00cf0100 901d57fe ....0.W.......W. - 1bbd120 b4cf0100 302257fe 4cd00100 c02457fe ....0"W.L....$W. - 1bbd130 c0d00100 102757fe 28d10100 c02a57fe .....'W.(....*W. - 1bbd140 98d10100 d02e57fe 44d20100 e03157fe ......W.D....1W. - 1bbd150 acd20100 403457fe 04d30100 003757fe ....@4W......7W. - 1bbd160 50d30100 203957fe 9cd30100 c03d57fe P... 9W......=W. - 1bbd170 ecd30100 e04057fe 3cd40100 d04457fe .....@W.<....DW. - 1bbd180 acd40100 c04857fe 1cd50100 a04b57fe .....HW......KW. - 1bbd190 6cd50100 a04e57fe ccd50100 505157fe l....NW.....PQW. - 1bbd1a0 00d60100 a05557fe 68d60100 905657fe .....UW.h....VW. - 1bbd1b0 8cd60100 605d57fe dcd60100 a06157fe ....`]W......aW. - 1bbd1c0 2cd70100 606657fe 9cd70100 206b57fe ,...`fW..... kW. - 1bbd1d0 0cd80100 706e57fe 5cd80100 f07157fe ....pnW.\....qW. - 1bbd1e0 bcd80100 307457fe e8d80100 407857fe ....0tW.....@xW. - 1bbd1f0 50d90100 b07957fe 6cd90100 a07b57fe P....yW.l....{W. - 1bbd200 b8d90100 207e57fe 08da0100 808057fe .... ~W.......W. - 1bbd210 58da0100 d08157fe 84da0100 808357fe X.....W.......W. - 1bbd220 bcda0100 108657fe 08db0100 c08757fe ......W.......W. - 1bbd230 40db0100 008a57fe 90db0100 b08b57fe @.....W.......W. - 1bbd240 d0db0100 608e57fe 20dc0100 d09157fe ....`.W. .....W. - 1bbd250 70dc0100 409257fe a8dc0100 c09257fe p...@.W.......W. - 1bbd260 d0dc0100 509357fe fcdc0100 d09357fe ....P.W.......W. - 1bbd270 10dd0100 609457fe 24dd0100 f09457fe ....`.W.$.....W. - 1bbd280 38dd0100 209557fe 4cdd0100 509557fe 8... .W.L...P.W. - 1bbd290 60dd0100 809557fe 74dd0100 b09557fe `.....W.t.....W. - 1bbd2a0 88dd0100 f09557fe a4dd0100 209657fe ......W..... .W. - 1bbd2b0 b8dd0100 609657fe d4dd0100 e09657fe ....`.W.......W. - 1bbd2c0 e8dd0100 f09857fe 04de0100 909957fe ......W.......W. - 1bbd2d0 18de0100 d09957fe 34de0100 109a57fe ......W.4.....W. - 1bbd2e0 50de0100 409a57fe 64de0100 b09a57fe P...@.W.d.....W. - 1bbd2f0 78de0100 309b57fe 8cde0100 b09b57fe x...0.W.......W. - 1bbd300 a0de0100 509c57fe ccde0100 f09c57fe ....P.W.......W. - 1bbd310 f8de0100 909d57fe 24df0100 c09d57fe ......W.$.....W. - 1bbd320 38df0100 609e57fe 4cdf0100 a09e57fe 8...`.W.L.....W. - 1bbd330 68df0100 e09e57fe 84df0100 109f57fe h.....W.......W. - 1bbd340 98df0100 909f57fe acdf0100 a0a157fe ......W.......W. - 1bbd350 c8df0100 30a257fe f4df0100 b0a257fe ....0.W.......W. - 1bbd360 08e00100 30a357fe 1ce00100 b0a357fe ....0.W.......W. - 1bbd370 30e00100 e0a357fe 44e00100 10a457fe 0.....W.D.....W. - 1bbd380 58e00100 40a457fe 6ce00100 70a457fe X...@.W.l...p.W. - 1bbd390 80e00100 b0a457fe 9ce00100 e0a457fe ......W.......W. - 1bbd3a0 b0e00100 20a557fe cce00100 a0a557fe .... .W.......W. - 1bbd3b0 e0e00100 b0a757fe fce00100 50a857fe ......W.....P.W. - 1bbd3c0 10e10100 90a857fe 2ce10100 d0a857fe ......W.,.....W. - 1bbd3d0 48e10100 00a957fe 5ce10100 70a957fe H.....W.\...p.W. - 1bbd3e0 70e10100 e0a957fe 84e10100 50aa57fe p.....W.....P.W. - 1bbd3f0 98e10100 e0aa57fe b8e10100 70ab57fe ......W.....p.W. - 1bbd400 d8e10100 10ac57fe 04e20100 40ac57fe ......W.....@.W. - 1bbd410 18e20100 e0ac57fe 2ce20100 20ad57fe ......W.,... .W. - 1bbd420 48e20100 60ad57fe 64e20100 90ad57fe H...`.W.d.....W. - 1bbd430 78e20100 10ae57fe 8ce20100 20b057fe x.....W..... .W. - 1bbd440 a8e20100 00b157fe c8e20100 60b357fe ......W.....`.W. - 1bbd450 74e30100 c0b557fe 20e40100 e0b657fe t.....W. .....W. - 1bbd460 98e40100 30b857fe 08e50100 b0ba57fe ....0.W.......W. - 1bbd470 a0e50100 c0bb57fe 18e60100 10bd57fe ......W.......W. - 1bbd480 88e60100 70be57fe 04e70100 d0c057fe ....p.W.......W. - 1bbd490 b0e70100 30c357fe 5ce80100 50c457fe ....0.W.\...P.W. - 1bbd4a0 d4e80100 a0c557fe 44e90100 20c857fe ......W.D... .W. - 1bbd4b0 dce90100 30c957fe 54ea0100 80ca57fe ....0.W.T.....W. - 1bbd4c0 c4ea0100 f0cb57fe 44eb0100 a0cd57fe ......W.D.....W. - 1bbd4d0 84eb0100 50cf57fe c4eb0100 50d657fe ....P.W.....P.W. - 1bbd4e0 f4eb0100 e0d957fe 24ec0100 70dd57fe ......W.$...p.W. - 1bbd4f0 54ec0100 b0df57fe a0ec0100 f0e357fe T.....W.......W. - 1bbd500 d0ec0100 b0e657fe 44ed0100 30eb57fe ......W.D...0.W. - 1bbd510 e8ed0100 e0ed57fe 60ee0100 70f057fe ......W.`...p.W. - 1bbd520 ccee0100 90f257fe 28ef0100 80f557fe ......W.(.....W. - 1bbd530 90ef0100 60f757fe dcef0100 e0f957fe ....`.W.......W. - 1bbd540 28f00100 30fe57fe b4f00100 100158fe (...0.W.......X. - 1bbd550 2cf10100 200358fe 84f10100 e00558fe ,... .X.......X. - 1bbd560 f8f10100 f00858fe 80f20100 d00a58fe ......X.......X. - 1bbd570 ccf20100 600d58fe 38f30100 701458fe ....`.X.8...p.X. - 1bbd580 68f30100 601958fe 9cf30100 c01d58fe h...`.X.......X. - 1bbd590 ccf30100 202358fe 70f40100 402658fe .... #X.p...@&X. - 1bbd5a0 e4f40100 b02a58fe 74f50100 002d58fe .....*X.t....-X. - 1bbd5b0 d0f50100 503058fe 40f60100 c03358fe ....P0X.@....3X. - 1bbd5c0 c0f60100 103658fe 0cf70100 203958fe .....6X..... 9X. - 1bbd5d0 7cf70100 303c58fe e4f70100 903e58fe |...0X. - 1bbd5e0 3cf80100 604158fe 88f80100 904358fe <...`AX......CX. - 1bbd5f0 d4f80100 004858fe 04f90100 b04a58fe .....HX......JX. - 1bbd600 50f90100 704f58fe a0f90100 905258fe P...pOX......RX. - 1bbd610 f0f90100 805658fe 60fa0100 705a58fe .....VX.`...pZX. - 1bbd620 d0fa0100 305d58fe 20fb0100 206058fe ....0]X. ... `X. - 1bbd630 80fb0100 406358fe d0fb0100 006658fe ....@cX......fX. - 1bbd640 20fc0100 f06858fe 80fc0100 f06c58fe ....hX......lX. - 1bbd650 acfc0100 207458fe 14fd0100 207558fe .... tX..... uX. - 1bbd660 40fd0100 e07958fe 90fd0100 608158fe @....yX.....`.X. - 1bbd670 e0fd0100 808558fe 30fe0100 308a58fe ......X.0...0.X. - 1bbd680 a0fe0100 e08e58fe 10ff0100 309258fe ......X.....0.X. - 1bbd690 60ff0100 a09558fe c0ff0100 c09958fe `.....X.......X. - 1bbd6a0 10000200 009d58fe 60000200 a0a058fe ......X.`.....X. - 1bbd6b0 c0000200 90a458fe e4000200 40ab58fe ......X.....@.X. - 1bbd6c0 4c010200 d0ac58fe 68010200 50b458fe L.....X.h...P.X. - 1bbd6d0 b8010200 40b658fe 04020200 c0b858fe ....@.X.......X. - 1bbd6e0 54020200 20bb58fe a4020200 70bc58fe T... .X.....p.X. - 1bbd6f0 d0020200 20be58fe 08030200 b0c058fe .... .X.......X. - 1bbd700 54030200 60c258fe 8c030200 a0c458fe T...`.X.......X. - 1bbd710 dc030200 50c658fe 1c040200 10c958fe ....P.X.......X. - 1bbd720 6c040200 80cc58fe bc040200 90d358fe l.....X.......X. - 1bbd730 ec040200 20d758fe 1c050200 b0da58fe .... .X.......X. - 1bbd740 4c050200 f0dc58fe 98050200 30e158fe L.....X.....0.X. - 1bbd750 c8050200 f0e358fe 3c060200 70e858fe ......X.<...p.X. - 1bbd760 e0060200 30eb58fe 58070200 c0ed58fe ....0.X.X.....X. /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,104656 +2,104499 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .eh_frame: - 1bd6cd8 14000000 00000000 017a5200 01781001 .........zR..x.. - 1bd6ce8 1b0c0708 90010000 24000000 1c000000 ........$....... - 1bd6cf8 28c352fe f0ed0000 000e1046 0e184a0f (.R........F..J. - 1bd6d08 0b770880 003f1a3b 2a332422 00000000 .w...?.;*3$".... - 1bd6d18 14000000 44000000 f0b053fe 90010000 ....D.....S..... - 1bd6d28 00000000 00000000 10000000 5c000000 ............\... - 1bd6d38 181454fe 69000000 00000000 10000000 ..T.i........... - 1bd6d48 70000000 741454fe 69000000 00000000 p...t.T.i....... - 1bd6d58 10000000 84000000 d01454fe 61000000 ..........T.a... - 1bd6d68 00000000 10000000 98000000 2c1554fe ............,.T. - 1bd6d78 61000000 00000000 10000000 ac000000 a............... - 1bd6d88 881554fe 61000000 00000000 10000000 ..T.a........... - 1bd6d98 c0000000 e41554fe 61000000 00000000 ......T.a....... - 1bd6da8 10000000 d4000000 401654fe 61000000 ........@.T.a... - 1bd6db8 00000000 10000000 e8000000 9c1654fe ..............T. - 1bd6dc8 61000000 00000000 10000000 fc000000 a............... - 1bd6dd8 f81654fe 75000000 00000000 10000000 ..T.u........... - 1bd6de8 10010000 641754fe 65000000 00000000 ....d.T.e....... - 1bd6df8 28000000 24010000 c01754fe 81000000 (...$.....T..... - 1bd6e08 004b0e10 5b0e184e 0e20470e 28410e30 .K..[..N. G.(A.0 - 1bd6e18 4b0e0849 0e10700e 08000000 10000000 K..I..p......... - 1bd6e28 50010000 241854fe 71000000 00000000 P...$.T.q....... - 1bd6e38 10000000 64010000 901854fe 75000000 ....d.....T.u... - 1bd6e48 00000000 1c000000 78010000 fc1854fe ........x.....T. - 1bd6e58 8e000000 00410e10 83020245 0a0e084a .....A.....E...J - 1bd6e68 0b7d0e08 10000000 98010000 6c1954fe .}..........l.T. - 1bd6e78 75000000 00000000 10000000 ac010000 u............... - 1bd6e88 d81954fe 25000000 00000000 10000000 ..T.%........... - 1bd6e98 c0010000 f41954fe 25000000 00000000 ......T.%....... - 1bd6ea8 10000000 d4010000 101a54fe 25000000 ..........T.%... - 1bd6eb8 00000000 10000000 e8010000 2c1a54fe ............,.T. - 1bd6ec8 25000000 00000000 10000000 fc010000 %............... - 1bd6ed8 481a54fe 25000000 00000000 18000000 H.T.%........... - 1bd6ee8 10020000 641a54fe 33000000 00500e10 ....d.T.3....P.. - 1bd6ef8 8302550e 084bc300 18000000 2c020000 ..U..K......,... - 1bd6f08 881a54fe 33000000 00500e10 8302550e ..T.3....P....U. - 1bd6f18 084bc300 10000000 48020000 ac1a54fe .K......H.....T. - 1bd6f28 25000000 00000000 10000000 5c020000 %...........\... - 1bd6f38 c81a54fe 25000000 00000000 18000000 ..T.%........... - 1bd6f48 70020000 e41a54fe 33000000 00500e10 p.....T.3....P.. - 1bd6f58 8302550e 084bc300 18000000 8c020000 ..U..K.......... - 1bd6f68 081b54fe 33000000 00500e10 8302550e ..T.3....P....U. - 1bd6f78 084bc300 10000000 a8020000 2c1b54fe .K..........,.T. - 1bd6f88 79000000 00000000 18000000 bc020000 y............... - 1bd6f98 981b54fe 8e010000 00470e90 0102630a ..T......G....c. - 1bd6fa8 0e08460b 10000000 d8020000 0c1d54fe ..F...........T. - 1bd6fb8 27030000 00000000 10000000 ec020000 '............... - 1bd6fc8 282054fe 11040000 00000000 10000000 ( T............. - 1bd6fd8 00030000 342454fe 89000000 00000000 ....4$T......... - 1bd6fe8 18000000 14030000 b02454fe 3b000000 .........$T.;... - 1bd6ff8 004c0e10 8302650e 0847c300 18000000 .L....e..G...... - 1bd7008 30030000 d42454fe 3b000000 004c0e10 0....$T.;....L.. - 1bd7018 8302650e 0847c300 10000000 4c030000 ..e..G......L... - 1bd7028 f82454fe 25000000 00000000 10000000 .$T.%........... - 1bd7038 60030000 142554fe 61000000 00000000 `....%T.a....... - 1bd7048 10000000 74030000 702554fe 65000000 ....t...p%T.e... - 1bd7058 00000000 1c000000 88030000 cc2554fe .............%T. - 1bd7068 91000000 004f0e20 720a0e08 5f0b700e .....O. r..._.p. - 1bd7078 08000000 10000000 a8030000 4c2654fe ............L&T. - 1bd7088 65000000 00000000 10000000 bc030000 e............... - 1bd7098 a82654fe 61000000 00000000 18000000 .&T.a........... - 1bd70a8 d0030000 042754fe 8e010000 00470e90 .....'T......G.. - 1bd70b8 0102630a 0e08460b 10000000 ec030000 ..c...F......... - 1bd70c8 782854fe 15030000 00000000 10000000 x(T............. - 1bd70d8 00040000 842b54fe 17040000 00000000 .....+T......... - 1bd70e8 28000000 14040000 902f54fe 81000000 (......../T..... - 1bd70f8 00480e10 620e184b 0e20440e 28420e30 .H..b..K. D.(B.0 - 1bd7108 4e0e0847 0e10700e 08000000 10000000 N..G..p......... - 1bd7118 40040000 f42f54fe 25000000 00000000 @..../T.%....... - 1bd7128 10000000 54040000 103054fe 61000000 ....T....0T.a... - 1bd7138 00000000 18000000 68040000 6c3054fe ........h...l0T. - 1bd7148 3b000000 004c0e10 8302650e 0847c300 ;....L....e..G.. - 1bd7158 18000000 84040000 903054fe 3b000000 .........0T.;... - 1bd7168 004c0e10 8302650e 0847c300 10000000 .L....e..G...... - 1bd7178 a0040000 b43054fe 25000000 00000000 .....0T.%....... - 1bd7188 28000000 b4040000 d03054fe 81000000 (........0T..... - 1bd7198 004b0e10 5b0e184e 0e20470e 28410e30 .K..[..N. G.(A.0 - 1bd71a8 4b0e0849 0e10700e 08000000 10000000 K..I..p......... - 1bd71b8 e0040000 343154fe 71000000 00000000 ....41T.q....... - 1bd71c8 10000000 f4040000 a03154fe 75000000 .........1T.u... - 1bd71d8 00000000 10000000 08050000 0c3254fe .............2T. - 1bd71e8 25000000 00000000 10000000 1c050000 %............... - 1bd71f8 283254fe 25000000 00000000 10000000 (2T.%........... - 1bd7208 30050000 443254fe 25000000 00000000 0...D2T.%....... - 1bd7218 10000000 44050000 603254fe 25000000 ....D...`2T.%... - 1bd7228 00000000 10000000 58050000 7c3254fe ........X...|2T. - 1bd7238 25000000 00000000 18000000 6c050000 %...........l... - 1bd7248 983254fe 33000000 00500e10 8302550e .2T.3....P....U. - 1bd7258 084bc300 18000000 88050000 bc3254fe .K...........2T. - 1bd7268 33000000 00500e10 8302550e 084bc300 3....P....U..K.. - 1bd7278 10000000 a4050000 e03254fe 25000000 .........2T.%... - 1bd7288 00000000 10000000 b8050000 fc3254fe .............2T. - 1bd7298 25000000 00000000 18000000 cc050000 %............... - 1bd72a8 183354fe 33000000 00500e10 8302550e .3T.3....P....U. - 1bd72b8 084bc300 18000000 e8050000 3c3354fe .K..........<3T. - 1bd72c8 33000000 00500e10 8302550e 084bc300 3....P....U..K.. - 1bd72d8 10000000 04060000 603354fe 79000000 ........`3T.y... - 1bd72e8 00000000 18000000 18060000 cc3354fe .............3T. - 1bd72f8 8e010000 00470e90 0102650a 0e08440b .....G....e...D. - 1bd7308 10000000 34060000 403554fe 38030000 ....4...@5T.8... - 1bd7318 00000000 10000000 48060000 6c3854fe ........H...l8T. - 1bd7328 08040000 00000000 10000000 5c060000 ............\... - 1bd7338 683c54fe 89000000 00000000 18000000 hT.a... - 1bd73c8 00000000 18000000 f8060000 5c3e54fe ............\>T. - 1bd73d8 8e010000 00470e90 0102650a 0e08440b .....G....e...D. - 1bd73e8 10000000 14070000 d03f54fe 26030000 .........?T.&... - 1bd73f8 00000000 10000000 28070000 ec4254fe ........(....BT. - 1bd7408 27040000 00000000 28000000 3c070000 '.......(...<... - 1bd7418 084754fe 81000000 00480e10 620e184b .GT......H..b..K - 1bd7428 0e20440e 28420e30 4e0e0847 0e10700e . D.(B.0N..G..p. - 1bd7438 08000000 10000000 68070000 6c4754fe ........h...lGT. - 1bd7448 25000000 00000000 10000000 7c070000 %...........|... - 1bd7458 884754fe 61000000 00000000 18000000 .GT.a........... - 1bd7468 90070000 e44754fe 3b000000 004c0e10 .....GT.;....L.. - 1bd7478 8302650e 0847c300 18000000 ac070000 ..e..G.......... - 1bd7488 084854fe 3b000000 004c0e10 8302650e .HT.;....L....e. - 1bd7498 0847c300 10000000 c8070000 2c4854fe .G..........,HT. - 1bd74a8 25000000 00000000 78000000 dc070000 %.......x....... - 1bd74b8 484854fe 0c020000 00420e10 8f02420e HHT......B....B. - 1bd74c8 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 1bd74d8 8606410e 38830747 0e6002e9 0e68480e ..A.8..G.`...hH. - 1bd74e8 70580e78 420e8001 420e8801 420e9001 pX.xB...B...B... - 1bd74f8 410e9801 420ea001 4e0e605f 0a0e3841 A...B...N.`_..8A - 1bd7508 0e30410e 28420e20 420e1842 0e10420e .0A.(B. B..B..B. - 1bd7518 08460b5b 0e68520e 70420e78 420e8001 .F.[.hR.pB.xB... - 1bd7528 4a0e6000 74000000 58080000 dc4954fe J.`.t...X....IT. - 1bd7538 1b010000 00420e10 8f02420e 188e0342 .....B....B....B - 1bd7548 0e208d04 420e288c 05440e30 8606410e . ..B.(..D.0..A. - 1bd7558 38830744 0e507c0e 58550e60 420e6842 8..D.P|.XU.`B.hB - 1bd7568 0e704a0e 50440a0e 38410e30 410e2842 .pJ.PD..8A.0A.(B - 1bd7578 0e20420e 18420e10 420e0842 0b7e0e58 . B..B..B..B.~.X - 1bd7588 4a0e6059 0e68420e 70420e78 420e8001 J.`Y.hB.pB.xB... - 1bd7598 420e8801 420e9001 490e5000 a4000000 B...B...I.P..... - 1bd75a8 d0080000 844a54fe f9010000 00420e10 .....JT......B.. - 1bd75b8 8f02420e 188e0342 0e208d04 420e288c ..B....B. ..B.(. - 1bd75c8 05410e30 8606410e 38830744 0e5002da .A.0..A.8..D.P.. - 1bd75d8 0e584a0e 60570e68 450e7042 0e78410e .XJ.`W.hE.pB.xA. - 1bd75e8 8001410e 8801430e 90014e0e 50440a0e ..A...C...N.PD.. - 1bd75f8 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 1bd7608 420e0847 0b510e58 560e6044 0e68410e B..G.Q.XV.`D.hA. - 1bd7618 704a0e50 440a0e38 410e3041 0e28420e pJ.PD..8A.0A.(B. - 1bd7628 20420e18 420e1042 0e08440b 026e0e38 B..B..B..D..n.8 - 1bd7638 410e3041 0e28420e 20420e18 420e1042 A.0A.(B. B..B..B - 1bd7648 0e080000 6c000000 78090000 dc4b54fe ....l...x....KT. - 1bd7658 fb000000 00420e10 8e02420e 188d0342 .....B....B....B - 1bd7668 0e208c04 410e2886 05440e30 8306440e . ..A.(..D.0..D. - 1bd7678 40710e48 550e5042 0e58420e 604a0e40 @q.HU.PB.XB.`J.@ - 1bd7688 440a0e30 410e2841 0e20420e 18420e10 D..0A.(A. B..B.. - 1bd7698 420e0841 0b690e48 490e5057 0e58420e B..A.i.HI.PW.XB. - 1bd76a8 60420e68 420e7042 0e78410e 80014e0e `B.hB.pB.xA...N. - 1bd76b8 40000000 78000000 e8090000 6c4c54fe @...x.......lLT. - 1bd76c8 51010000 00420e10 8f02420e 188e0342 Q....B....B....B - 1bd76d8 0e208d04 420e288c 05410e30 8606410e . ..B.(..A.0..A. - 1bd76e8 38830744 0e600288 0e68470e 705b0e78 8..D.`...hG.p[.x - 1bd76f8 410e8001 440e8801 420e9001 420e9801 A...D...B...B... - 1bd7708 420ea001 4e0e6054 0a0e3843 0e30410e B...N.`T..8C.0A. - 1bd7718 28420e20 420e1842 0e10420e 08470b64 (B. B..B..B..G.d - 1bd7728 0e68490e 704b0e78 4c0e8001 4b0e6000 .hI.pK.xL...K.`. - 1bd7738 78000000 640a0000 504d54fe 0c020000 x...d...PMT..... - 1bd7748 00420e10 8f02420e 188e0342 0e208d04 .B....B....B. .. - 1bd7758 420e288c 05410e30 8606410e 38830747 B.(..A.0..A.8..G - 1bd7768 0e6002ea 0e68480e 70580e78 420e8001 .`...hH.pX.xB... - 1bd7778 420e8801 420e9001 410e9801 420ea001 B...B...A...B... - 1bd7788 4e0e605e 0a0e3841 0e30410e 28420e20 N.`^..8A.0A.(B. - 1bd7798 420e1842 0e10420e 08460b5b 0e68520e B..B..B..F.[.hR. - 1bd77a8 70420e78 420e8001 4a0e6000 74000000 pB.xB...J.`.t... - 1bd77b8 e00a0000 e44e54fe 1b010000 00420e10 .....NT......B.. - 1bd77c8 8f02420e 188e0342 0e208d04 420e288c ..B....B. ..B.(. - 1bd77d8 05440e30 8606410e 38830744 0e507d0e .D.0..A.8..D.P}. - 1bd77e8 58550e60 420e6842 0e704a0e 50440a0e XU.`B.hB.pJ.PD.. - 1bd77f8 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 1bd7808 420e0841 0b7e0e58 4a0e6059 0e68420e B..A.~.XJ.`Y.hB. - 1bd7818 70420e78 420e8001 420e8801 420e9001 pB.xB...B...B... - 1bd7828 490e5000 a8000000 580b0000 8c4f54fe I.P.....X....OT. - 1bd7838 f9010000 00420e10 8f02420e 188e0342 .....B....B....B - 1bd7848 0e208d04 420e288c 05410e30 8606410e . ..B.(..A.0..A. - 1bd7858 38830744 0e6002e1 0e684a0e 70570e78 8..D.`...hJ.pW.x - 1bd7868 450e8001 420e8801 410e9001 410e9801 E...B...A...A... - 1bd7878 430ea001 4e0e6044 0a0e3841 0e30410e C...N.`D..8A.0A. - 1bd7888 28420e20 420e1842 0e10420e 08480b51 (B. B..B..B..H.Q - 1bd7898 0e68560e 70440e78 410e8001 4a0e6044 .hV.pD.xA...J.`D - 1bd78a8 0a0e3841 0e30410e 28420e20 420e1842 ..8A.0A.(B. B..B - 1bd78b8 0e10420e 08440b02 660e3841 0e30410e ..B..D..f.8A.0A. - 1bd78c8 28420e20 420e1842 0e10420e 08000000 (B. B..B..B..... - 1bd78d8 6c000000 040c0000 e05054fe fb000000 l........PT..... - 1bd78e8 00420e10 8e02420e 188d0342 0e208c04 .B....B....B. .. /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .init_array --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,4 +2,4 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .init_array: - 1d70b40 40811100 00000000 00000000 00000000 @............... + 1d47b40 40811100 00000000 00000000 00000000 @............... /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .fini_array --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,4 +2,4 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .fini_array: - 1d70b50 00811100 00000000 00000000 00000000 ................ + 1d47b50 00811100 00000000 00000000 00000000 ................ /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .data.rel.ro --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,759 +2,759 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .data.rel.ro: - 1d70b60 d1bbba01 00000000 2fbbba01 00000000 ......../....... - 1d70b70 36bbba01 00000000 41bbba01 00000000 6.......A....... - 1d70b80 4bbbba01 00000000 54bbba01 00000000 K.......T....... - 1d70b90 5abcba01 00000000 63bbba01 00000000 Z.......c....... - 1d70ba0 5fbcba01 00000000 66bcba01 00000000 _.......f....... - 1d70bb0 5bbbba01 00000000 69bbba01 00000000 [.......i....... - 1d70bc0 71bcba01 00000000 79bcba01 00000000 q.......y....... - 1d70bd0 70bbba01 00000000 86bcba01 00000000 p............... - 1d70be0 7abbba01 00000000 8bbcba01 00000000 z............... - 1d70bf0 86bbba01 00000000 90bbba01 00000000 ................ - 1d70c00 9bbbba01 00000000 a3bbba01 00000000 ................ - 1d70c10 afbbba01 00000000 b9bbba01 00000000 ................ - 1d70c20 bdbbba01 00000000 c6bbba01 00000000 ................ - 1d70c30 00000000 00000000 00000000 00000000 ................ - 1d70c40 00000000 00000000 00000000 00000000 ................ - 1d70c50 00000000 00000000 00000000 00000000 ................ - 1d70c60 00000000 00000000 00000000 00000000 ................ - 1d70c70 00000000 00000000 00000000 00000000 ................ - 1d70c80 00000000 00000000 00000000 00000000 ................ - 1d70c90 00000000 00000000 00000000 00000000 ................ - 1d70ca0 00000000 00000000 00000000 00000000 ................ - 1d70cb0 00000000 00000000 00000000 00000000 ................ - 1d70cc0 00000000 00000000 00000000 00000000 ................ - 1d70cd0 00000000 00000000 00000000 00000000 ................ - 1d70ce0 00000000 00000000 00000000 00000000 ................ - 1d70cf0 00000000 00000000 00000000 00000000 ................ - 1d70d00 00000000 00000000 00000000 00000000 ................ - 1d70d10 00000000 00000000 00000000 00000000 ................ - 1d70d20 00000000 00000000 00000000 00000000 ................ - 1d70d30 00000000 00000000 00000000 00000000 ................ - 1d70d40 00000000 00000000 00000000 00000000 ................ - 1d70d50 00000000 00000000 00000000 00000000 ................ - 1d70d60 00000000 00000000 00000000 00000000 ................ - 1d70d70 00000000 00000000 00000000 00000000 ................ - 1d70d80 00000000 00000000 00000000 00000000 ................ - 1d70d90 00000000 00000000 00000000 00000000 ................ - 1d70da0 00000000 00000000 00000000 00000000 ................ - 1d70db0 00000000 00000000 00000000 00000000 ................ - 1d70dc0 00000000 00000000 00000000 00000000 ................ - 1d70dd0 00000000 00000000 00000000 00000000 ................ - 1d70de0 00000000 00000000 00000000 00000000 ................ - 1d70df0 00000000 00000000 00000000 00000000 ................ - 1d70e00 00000000 00000000 00000000 00000000 ................ - 1d70e10 00000000 00000000 00000000 00000000 ................ - 1d70e20 00000000 00000000 00000000 00000000 ................ - 1d70e30 00000000 00000000 00000000 00000000 ................ - 1d70e40 00000000 00000000 00000000 00000000 ................ - 1d70e50 00000000 00000000 00000000 00000000 ................ - 1d70e60 00000000 00000000 00000000 00000000 ................ - 1d70e70 00000000 00000000 00000000 00000000 ................ - 1d70e80 00000000 00000000 00000000 00000000 ................ - 1d70e90 00000000 00000000 00000000 00000000 ................ - 1d70ea0 00000000 00000000 00000000 00000000 ................ - 1d70eb0 00000000 00000000 00000000 00000000 ................ - 1d70ec0 00000000 00000000 00000000 00000000 ................ - 1d70ed0 00000000 00000000 00000000 00000000 ................ - 1d70ee0 00000000 00000000 00000000 00000000 ................ - 1d70ef0 00000000 00000000 00000000 00000000 ................ - 1d70f00 00000000 00000000 00000000 00000000 ................ - 1d70f10 00000000 00000000 00000000 00000000 ................ - 1d70f20 00000000 00000000 00000000 00000000 ................ - 1d70f30 00000000 00000000 00000000 00000000 ................ - 1d70f40 00000000 00000000 00000000 00000000 ................ - 1d70f50 00000000 00000000 00000000 00000000 ................ - 1d70f60 00000000 00000000 00000000 00000000 ................ - 1d70f70 00000000 00000000 00000000 00000000 ................ - 1d70f80 00000000 00000000 00000000 00000000 ................ - 1d70f90 00000000 00000000 00000000 00000000 ................ - 1d70fa0 00000000 00000000 00000000 00000000 ................ - 1d70fb0 00000000 00000000 00000000 00000000 ................ - 1d70fc0 00000000 00000000 00000000 00000000 ................ - 1d70fd0 00000000 00000000 00000000 00000000 ................ - 1d70fe0 00000000 00000000 00000000 00000000 ................ - 1d70ff0 00000000 00000000 00000000 00000000 ................ - 1d71000 00000000 00000000 00000000 00000000 ................ - 1d71010 00000000 00000000 00000000 00000000 ................ - 1d71020 00000000 00000000 00000000 00000000 ................ - 1d71030 00000000 00000000 00000000 00000000 ................ - 1d71040 00000000 00000000 00000000 00000000 ................ - 1d71050 00000000 00000000 00000000 00000000 ................ - 1d71060 00000000 00000000 00000000 00000000 ................ - 1d71070 00000000 00000000 00000000 00000000 ................ - 1d71080 00000000 00000000 00000000 00000000 ................ - 1d71090 00000000 00000000 00000000 00000000 ................ - 1d710a0 00000000 00000000 00000000 00000000 ................ - 1d710b0 00000000 00000000 00000000 00000000 ................ - 1d710c0 00000000 00000000 00000000 00000000 ................ - 1d710d0 00000000 00000000 00000000 00000000 ................ - 1d710e0 00000000 00000000 00000000 00000000 ................ - 1d710f0 00000000 00000000 00000000 00000000 ................ - 1d71100 00000000 00000000 00000000 00000000 ................ - 1d71110 00000000 00000000 00000000 00000000 ................ - 1d71120 00000000 00000000 00000000 00000000 ................ - 1d71130 00000000 00000000 00000000 00000000 ................ - 1d71140 00000000 00000000 00000000 00000000 ................ - 1d71150 00000000 00000000 00000000 00000000 ................ - 1d71160 00000000 00000000 00000000 00000000 ................ - 1d71170 00000000 00000000 00000000 00000000 ................ - 1d71180 00000000 00000000 00000000 00000000 ................ - 1d71190 00000000 00000000 00000000 00000000 ................ - 1d711a0 00000000 00000000 00000000 00000000 ................ - 1d711b0 00000000 00000000 00000000 00000000 ................ - 1d711c0 00000000 00000000 00000000 00000000 ................ - 1d711d0 00000000 00000000 00000000 00000000 ................ - 1d711e0 00000000 00000000 00000000 00000000 ................ - 1d711f0 00000000 00000000 00000000 00000000 ................ - 1d71200 00000000 00000000 00000000 00000000 ................ - 1d71210 00000000 00000000 00000000 00000000 ................ - 1d71220 00000000 00000000 00000000 00000000 ................ - 1d71230 00000000 00000000 00000000 00000000 ................ - 1d71240 00000000 00000000 00000000 00000000 ................ - 1d71250 00000000 00000000 00000000 00000000 ................ - 1d71260 00000000 00000000 00000000 00000000 ................ - 1d71270 00000000 00000000 00000000 00000000 ................ - 1d71280 00000000 00000000 00000000 00000000 ................ - 1d71290 00000000 00000000 00000000 00000000 ................ - 1d712a0 00000000 00000000 00000000 00000000 ................ - 1d712b0 00000000 00000000 00000000 00000000 ................ - 1d712c0 00000000 00000000 00000000 00000000 ................ - 1d712d0 00000000 00000000 00000000 00000000 ................ - 1d712e0 00000000 00000000 00000000 00000000 ................ - 1d712f0 00000000 00000000 00000000 00000000 ................ - 1d71300 00000000 00000000 00000000 00000000 ................ - 1d71310 00000000 00000000 00000000 00000000 ................ - 1d71320 00000000 00000000 00000000 00000000 ................ - 1d71330 00000000 00000000 00000000 00000000 ................ - 1d71340 00000000 00000000 00000000 00000000 ................ - 1d71350 00000000 00000000 00000000 00000000 ................ - 1d71360 00000000 00000000 00000000 00000000 ................ - 1d71370 00000000 00000000 00000000 00000000 ................ - 1d71380 00000000 00000000 00000000 00000000 ................ - 1d71390 00000000 00000000 00000000 00000000 ................ - 1d713a0 00000000 00000000 00000000 00000000 ................ - 1d713b0 00000000 00000000 00000000 00000000 ................ - 1d713c0 00000000 00000000 00000000 00000000 ................ - 1d713d0 00000000 00000000 00000000 00000000 ................ - 1d713e0 00000000 00000000 00000000 00000000 ................ - 1d713f0 00000000 00000000 00000000 00000000 ................ - 1d71400 00000000 00000000 00000000 00000000 ................ - 1d71410 00000000 00000000 00000000 00000000 ................ - 1d71420 00000000 00000000 00000000 00000000 ................ - 1d71430 00000000 00000000 00000000 00000000 ................ - 1d71440 00000000 00000000 00000000 00000000 ................ - 1d71450 00000000 00000000 00000000 00000000 ................ - 1d71460 00000000 00000000 00000000 00000000 ................ - 1d71470 00000000 00000000 00000000 00000000 ................ - 1d71480 00000000 00000000 00000000 00000000 ................ - 1d71490 00000000 00000000 00000000 00000000 ................ - 1d714a0 00000000 00000000 00000000 00000000 ................ - 1d714b0 00000000 00000000 00000000 00000000 ................ - 1d714c0 00000000 00000000 00000000 00000000 ................ - 1d714d0 00000000 00000000 00000000 00000000 ................ - 1d714e0 00000000 00000000 00000000 00000000 ................ - 1d714f0 00000000 00000000 00000000 00000000 ................ - 1d71500 00000000 00000000 00000000 00000000 ................ - 1d71510 00000000 00000000 00000000 00000000 ................ - 1d71520 00000000 00000000 00000000 00000000 ................ - 1d71530 00000000 00000000 00000000 00000000 ................ - 1d71540 00000000 00000000 00000000 00000000 ................ - 1d71550 00000000 00000000 00000000 00000000 ................ - 1d71560 00000000 00000000 00000000 00000000 ................ - 1d71570 00000000 00000000 00000000 00000000 ................ - 1d71580 00000000 00000000 00000000 00000000 ................ - 1d71590 00000000 00000000 00000000 00000000 ................ - 1d715a0 00000000 00000000 00000000 00000000 ................ - 1d715b0 00000000 00000000 00000000 00000000 ................ - 1d715c0 00000000 00000000 00000000 00000000 ................ - 1d715d0 00000000 00000000 00000000 00000000 ................ - 1d715e0 00000000 00000000 00000000 00000000 ................ - 1d715f0 00000000 00000000 00000000 00000000 ................ - 1d71600 00000000 00000000 00000000 00000000 ................ - 1d71610 00000000 00000000 00000000 00000000 ................ - 1d71620 00000000 00000000 00000000 00000000 ................ - 1d71630 00000000 00000000 00000000 00000000 ................ - 1d71640 00000000 00000000 00000000 00000000 ................ - 1d71650 00000000 00000000 00000000 00000000 ................ - 1d71660 00000000 00000000 00000000 00000000 ................ - 1d71670 00000000 00000000 00000000 00000000 ................ - 1d71680 00000000 00000000 00000000 00000000 ................ - 1d71690 00000000 00000000 00000000 00000000 ................ - 1d716a0 00000000 00000000 00000000 00000000 ................ - 1d716b0 00000000 00000000 00000000 00000000 ................ - 1d716c0 00000000 00000000 00000000 00000000 ................ - 1d716d0 00000000 00000000 00000000 00000000 ................ - 1d716e0 00000000 00000000 00000000 00000000 ................ - 1d716f0 00000000 00000000 00000000 00000000 ................ - 1d71700 00000000 00000000 00000000 00000000 ................ - 1d71710 00000000 00000000 00000000 00000000 ................ - 1d71720 00000000 00000000 00000000 00000000 ................ - 1d71730 00000000 00000000 00000000 00000000 ................ - 1d71740 00000000 00000000 00000000 00000000 ................ - 1d71750 00000000 00000000 00000000 00000000 ................ - 1d71760 00000000 00000000 00000000 00000000 ................ - 1d71770 00000000 00000000 00000000 00000000 ................ /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .dynamic --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,37 +2,37 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .dynamic: - 1d73aa0 01000000 00000000 76810300 00000000 ........v....... - 1d73ab0 01000000 00000000 80810300 00000000 ................ - 1d73ac0 01000000 00000000 91810300 00000000 ................ - 1d73ad0 01000000 00000000 9e810300 00000000 ................ - 1d73ae0 01000000 00000000 a8810300 00000000 ................ - 1d73af0 0e000000 00000000 bd810300 00000000 ................ - 1d73b00 0c000000 00000000 00301000 00000000 .........0...... - 1d73b10 0d000000 00000000 30a3ba01 00000000 ........0....... - 1d73b20 19000000 00000000 400bd701 00000000 ........@....... - 1d73b30 1b000000 00000000 10000000 00000000 ................ - 1d73b40 1a000000 00000000 500bd701 00000000 ........P....... - 1d73b50 1c000000 00000000 10000000 00000000 ................ - 1d73b60 04000000 00000000 70030000 00000000 ........p....... - 1d73b70 f5feff6f 00000000 c84e0100 00000000 ...o.....N...... - 1d73b80 05000000 00000000 289b0700 00000000 ........(....... - 1d73b90 06000000 00000000 e0d80200 00000000 ................ - 1d73ba0 0a000000 00000000 67820300 00000000 ........g....... - 1d73bb0 0b000000 00000000 18000000 00000000 ................ - 1d73bc0 03000000 00000000 0040d701 00000000 .........@...... - 1d73bd0 02000000 00000000 d0640100 00000000 .........d...... - 1d73be0 14000000 00000000 07000000 00000000 ................ - 1d73bf0 17000000 00000000 10c60e00 00000000 ................ - 1d73c00 07000000 00000000 58840b00 00000000 ........X....... - 1d73c10 08000000 00000000 b8410300 00000000 .........A...... - 1d73c20 09000000 00000000 18000000 00000000 ................ - 1d73c30 feffff6f 00000000 18830b00 00000000 ...o............ - 1d73c40 ffffff6f 00000000 05000000 00000000 ...o............ - 1d73c50 f0ffff6f 00000000 901d0b00 00000000 ...o............ - 1d73c60 f9ffff6f 00000000 2b000000 00000000 ...o....+....... - 1d73c70 00000000 00000000 00000000 00000000 ................ - 1d73c80 00000000 00000000 00000000 00000000 ................ - 1d73c90 00000000 00000000 00000000 00000000 ................ - 1d73ca0 00000000 00000000 00000000 00000000 ................ - 1d73cb0 00000000 00000000 00000000 00000000 ................ + 1d4aaa0 01000000 00000000 76810300 00000000 ........v....... + 1d4aab0 01000000 00000000 80810300 00000000 ................ + 1d4aac0 01000000 00000000 91810300 00000000 ................ + 1d4aad0 01000000 00000000 9e810300 00000000 ................ + 1d4aae0 01000000 00000000 a8810300 00000000 ................ + 1d4aaf0 0e000000 00000000 bd810300 00000000 ................ + 1d4ab00 0c000000 00000000 00301000 00000000 .........0...... + 1d4ab10 0d000000 00000000 3023b801 00000000 ........0#...... + 1d4ab20 19000000 00000000 407bd401 00000000 ........@{...... + 1d4ab30 1b000000 00000000 10000000 00000000 ................ + 1d4ab40 1a000000 00000000 507bd401 00000000 ........P{...... + 1d4ab50 1c000000 00000000 10000000 00000000 ................ + 1d4ab60 04000000 00000000 70030000 00000000 ........p....... + 1d4ab70 f5feff6f 00000000 c84e0100 00000000 ...o.....N...... + 1d4ab80 05000000 00000000 289b0700 00000000 ........(....... + 1d4ab90 06000000 00000000 e0d80200 00000000 ................ + 1d4aba0 0a000000 00000000 67820300 00000000 ........g....... + 1d4abb0 0b000000 00000000 18000000 00000000 ................ + 1d4abc0 03000000 00000000 00b0d401 00000000 ................ + 1d4abd0 02000000 00000000 d0640100 00000000 .........d...... + 1d4abe0 14000000 00000000 07000000 00000000 ................ + 1d4abf0 17000000 00000000 10c60e00 00000000 ................ + 1d4ac00 07000000 00000000 58840b00 00000000 ........X....... + 1d4ac10 08000000 00000000 b8410300 00000000 .........A...... + 1d4ac20 09000000 00000000 18000000 00000000 ................ + 1d4ac30 feffff6f 00000000 18830b00 00000000 ...o............ + 1d4ac40 ffffff6f 00000000 05000000 00000000 ...o............ + 1d4ac50 f0ffff6f 00000000 901d0b00 00000000 ...o............ + 1d4ac60 f9ffff6f 00000000 2b000000 00000000 ...o....+....... + 1d4ac70 00000000 00000000 00000000 00000000 ................ + 1d4ac80 00000000 00000000 00000000 00000000 ................ + 1d4ac90 00000000 00000000 00000000 00000000 ................ + 1d4aca0 00000000 00000000 00000000 00000000 ................ + 1d4acb0 00000000 00000000 00000000 00000000 ................ /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .got --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,55 +2,55 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .got: - 1d73cc0 00000000 00000000 00000000 00000000 ................ - 1d73cd0 00000000 00000000 00000000 00000000 ................ - 1d73ce0 00000000 00000000 00000000 00000000 ................ - 1d73cf0 00000000 00000000 00000000 00000000 ................ - 1d73d00 00000000 00000000 00000000 00000000 ................ - 1d73d10 00000000 00000000 00000000 00000000 ................ - 1d73d20 00000000 00000000 00000000 00000000 ................ - 1d73d30 00000000 00000000 00000000 00000000 ................ - 1d73d40 00000000 00000000 00000000 00000000 ................ - 1d73d50 00000000 00000000 00000000 00000000 ................ - 1d73d60 00000000 00000000 00000000 00000000 ................ - 1d73d70 00000000 00000000 00000000 00000000 ................ - 1d73d80 00000000 00000000 00000000 00000000 ................ - 1d73d90 00000000 00000000 00000000 00000000 ................ - 1d73da0 00000000 00000000 00000000 00000000 ................ - 1d73db0 00000000 00000000 00000000 00000000 ................ - 1d73dc0 00000000 00000000 00000000 00000000 ................ - 1d73dd0 00000000 00000000 00000000 00000000 ................ - 1d73de0 00000000 00000000 00000000 00000000 ................ - 1d73df0 00000000 00000000 00000000 00000000 ................ - 1d73e00 00000000 00000000 00000000 00000000 ................ - 1d73e10 00000000 00000000 00000000 00000000 ................ - 1d73e20 00000000 00000000 00000000 00000000 ................ - 1d73e30 00000000 00000000 00000000 00000000 ................ - 1d73e40 00000000 00000000 00000000 00000000 ................ - 1d73e50 00000000 00000000 00000000 00000000 ................ - 1d73e60 00000000 00000000 00000000 00000000 ................ - 1d73e70 00000000 00000000 00000000 00000000 ................ - 1d73e80 00000000 00000000 00000000 00000000 ................ - 1d73e90 00000000 00000000 00000000 00000000 ................ - 1d73ea0 00000000 00000000 00000000 00000000 ................ - 1d73eb0 00000000 00000000 00000000 00000000 ................ - 1d73ec0 00000000 00000000 00000000 00000000 ................ - 1d73ed0 00000000 00000000 00000000 00000000 ................ - 1d73ee0 00000000 00000000 00000000 00000000 ................ - 1d73ef0 00000000 00000000 00000000 00000000 ................ - 1d73f00 00000000 00000000 00000000 00000000 ................ - 1d73f10 00000000 00000000 00000000 00000000 ................ - 1d73f20 00000000 00000000 00000000 00000000 ................ - 1d73f30 00000000 00000000 00000000 00000000 ................ - 1d73f40 00000000 00000000 00000000 00000000 ................ - 1d73f50 00000000 00000000 00000000 00000000 ................ - 1d73f60 00000000 00000000 00000000 00000000 ................ - 1d73f70 00000000 00000000 00000000 00000000 ................ - 1d73f80 00000000 00000000 00000000 00000000 ................ - 1d73f90 00000000 00000000 00000000 00000000 ................ - 1d73fa0 00000000 00000000 00000000 00000000 ................ - 1d73fb0 00000000 00000000 00000000 00000000 ................ - 1d73fc0 00000000 00000000 00000000 00000000 ................ - 1d73fd0 00000000 00000000 00000000 00000000 ................ - 1d73fe0 00000000 00000000 00000000 00000000 ................ - 1d73ff0 00000000 00000000 ........ + 1d4acc0 00000000 00000000 00000000 00000000 ................ + 1d4acd0 00000000 00000000 00000000 00000000 ................ + 1d4ace0 00000000 00000000 00000000 00000000 ................ + 1d4acf0 00000000 00000000 00000000 00000000 ................ + 1d4ad00 00000000 00000000 00000000 00000000 ................ + 1d4ad10 00000000 00000000 00000000 00000000 ................ + 1d4ad20 00000000 00000000 00000000 00000000 ................ + 1d4ad30 00000000 00000000 00000000 00000000 ................ + 1d4ad40 00000000 00000000 00000000 00000000 ................ + 1d4ad50 00000000 00000000 00000000 00000000 ................ + 1d4ad60 00000000 00000000 00000000 00000000 ................ + 1d4ad70 00000000 00000000 00000000 00000000 ................ + 1d4ad80 00000000 00000000 00000000 00000000 ................ + 1d4ad90 00000000 00000000 00000000 00000000 ................ + 1d4ada0 00000000 00000000 00000000 00000000 ................ + 1d4adb0 00000000 00000000 00000000 00000000 ................ + 1d4adc0 00000000 00000000 00000000 00000000 ................ + 1d4add0 00000000 00000000 00000000 00000000 ................ + 1d4ade0 00000000 00000000 00000000 00000000 ................ + 1d4adf0 00000000 00000000 00000000 00000000 ................ + 1d4ae00 00000000 00000000 00000000 00000000 ................ + 1d4ae10 00000000 00000000 00000000 00000000 ................ + 1d4ae20 00000000 00000000 00000000 00000000 ................ + 1d4ae30 00000000 00000000 00000000 00000000 ................ + 1d4ae40 00000000 00000000 00000000 00000000 ................ + 1d4ae50 00000000 00000000 00000000 00000000 ................ + 1d4ae60 00000000 00000000 00000000 00000000 ................ + 1d4ae70 00000000 00000000 00000000 00000000 ................ + 1d4ae80 00000000 00000000 00000000 00000000 ................ + 1d4ae90 00000000 00000000 00000000 00000000 ................ + 1d4aea0 00000000 00000000 00000000 00000000 ................ + 1d4aeb0 00000000 00000000 00000000 00000000 ................ + 1d4aec0 00000000 00000000 00000000 00000000 ................ + 1d4aed0 00000000 00000000 00000000 00000000 ................ + 1d4aee0 00000000 00000000 00000000 00000000 ................ + 1d4aef0 00000000 00000000 00000000 00000000 ................ + 1d4af00 00000000 00000000 00000000 00000000 ................ + 1d4af10 00000000 00000000 00000000 00000000 ................ + 1d4af20 00000000 00000000 00000000 00000000 ................ + 1d4af30 00000000 00000000 00000000 00000000 ................ + 1d4af40 00000000 00000000 00000000 00000000 ................ + 1d4af50 00000000 00000000 00000000 00000000 ................ + 1d4af60 00000000 00000000 00000000 00000000 ................ + 1d4af70 00000000 00000000 00000000 00000000 ................ + 1d4af80 00000000 00000000 00000000 00000000 ................ + 1d4af90 00000000 00000000 00000000 00000000 ................ + 1d4afa0 00000000 00000000 00000000 00000000 ................ + 1d4afb0 00000000 00000000 00000000 00000000 ................ + 1d4afc0 00000000 00000000 00000000 00000000 ................ + 1d4afd0 00000000 00000000 00000000 00000000 ................ + 1d4afe0 00000000 00000000 00000000 00000000 ................ + 1d4aff0 00000000 00000000 ........ /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .got.plt --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,1908 +2,1908 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .got.plt: - 1d74000 a03ad701 00000000 00000000 00000000 .:.............. - 1d74010 00000000 00000000 36301000 00000000 ........60...... - 1d74020 46301000 00000000 56301000 00000000 F0......V0...... - 1d74030 66301000 00000000 76301000 00000000 f0......v0...... - 1d74040 86301000 00000000 96301000 00000000 .0.......0...... - 1d74050 a6301000 00000000 b6301000 00000000 .0.......0...... - 1d74060 c6301000 00000000 d6301000 00000000 .0.......0...... - 1d74070 e6301000 00000000 f6301000 00000000 .0.......0...... - 1d74080 06311000 00000000 16311000 00000000 .1.......1...... - 1d74090 26311000 00000000 36311000 00000000 &1......61...... - 1d740a0 46311000 00000000 56311000 00000000 F1......V1...... - 1d740b0 66311000 00000000 76311000 00000000 f1......v1...... - 1d740c0 86311000 00000000 96311000 00000000 .1.......1...... - 1d740d0 a6311000 00000000 b6311000 00000000 .1.......1...... - 1d740e0 c6311000 00000000 d6311000 00000000 .1.......1...... - 1d740f0 e6311000 00000000 f6311000 00000000 .1.......1...... - 1d74100 06321000 00000000 16321000 00000000 .2.......2...... - 1d74110 26321000 00000000 36321000 00000000 &2......62...... - 1d74120 46321000 00000000 56321000 00000000 F2......V2...... - 1d74130 66321000 00000000 76321000 00000000 f2......v2...... - 1d74140 86321000 00000000 96321000 00000000 .2.......2...... - 1d74150 a6321000 00000000 b6321000 00000000 .2.......2...... - 1d74160 c6321000 00000000 d6321000 00000000 .2.......2...... - 1d74170 e6321000 00000000 f6321000 00000000 .2.......2...... - 1d74180 06331000 00000000 16331000 00000000 .3.......3...... - 1d74190 26331000 00000000 36331000 00000000 &3......63...... - 1d741a0 46331000 00000000 56331000 00000000 F3......V3...... - 1d741b0 66331000 00000000 76331000 00000000 f3......v3...... - 1d741c0 86331000 00000000 96331000 00000000 .3.......3...... - 1d741d0 a6331000 00000000 b6331000 00000000 .3.......3...... - 1d741e0 c6331000 00000000 d6331000 00000000 .3.......3...... - 1d741f0 e6331000 00000000 f6331000 00000000 .3.......3...... - 1d74200 06341000 00000000 16341000 00000000 .4.......4...... - 1d74210 26341000 00000000 36341000 00000000 &4......64...... - 1d74220 46341000 00000000 56341000 00000000 F4......V4...... - 1d74230 66341000 00000000 76341000 00000000 f4......v4...... - 1d74240 86341000 00000000 96341000 00000000 .4.......4...... - 1d74250 a6341000 00000000 b6341000 00000000 .4.......4...... - 1d74260 c6341000 00000000 d6341000 00000000 .4.......4...... - 1d74270 e6341000 00000000 f6341000 00000000 .4.......4...... - 1d74280 06351000 00000000 16351000 00000000 .5.......5...... - 1d74290 26351000 00000000 36351000 00000000 &5......65...... - 1d742a0 46351000 00000000 56351000 00000000 F5......V5...... - 1d742b0 66351000 00000000 76351000 00000000 f5......v5...... - 1d742c0 86351000 00000000 96351000 00000000 .5.......5...... - 1d742d0 a6351000 00000000 b6351000 00000000 .5.......5...... - 1d742e0 c6351000 00000000 d6351000 00000000 .5.......5...... - 1d742f0 e6351000 00000000 f6351000 00000000 .5.......5...... - 1d74300 06361000 00000000 16361000 00000000 .6.......6...... - 1d74310 26361000 00000000 36361000 00000000 &6......66...... - 1d74320 46361000 00000000 56361000 00000000 F6......V6...... - 1d74330 66361000 00000000 76361000 00000000 f6......v6...... - 1d74340 86361000 00000000 96361000 00000000 .6.......6...... - 1d74350 a6361000 00000000 b6361000 00000000 .6.......6...... - 1d74360 c6361000 00000000 d6361000 00000000 .6.......6...... - 1d74370 e6361000 00000000 f6361000 00000000 .6.......6...... - 1d74380 06371000 00000000 16371000 00000000 .7.......7...... - 1d74390 26371000 00000000 36371000 00000000 &7......67...... - 1d743a0 46371000 00000000 56371000 00000000 F7......V7...... - 1d743b0 66371000 00000000 76371000 00000000 f7......v7...... - 1d743c0 86371000 00000000 96371000 00000000 .7.......7...... - 1d743d0 a6371000 00000000 b6371000 00000000 .7.......7...... - 1d743e0 c6371000 00000000 d6371000 00000000 .7.......7...... - 1d743f0 e6371000 00000000 f6371000 00000000 .7.......7...... - 1d74400 06381000 00000000 16381000 00000000 .8.......8...... - 1d74410 26381000 00000000 36381000 00000000 &8......68...... - 1d74420 46381000 00000000 56381000 00000000 F8......V8...... - 1d74430 66381000 00000000 76381000 00000000 f8......v8...... - 1d74440 86381000 00000000 96381000 00000000 .8.......8...... - 1d74450 a6381000 00000000 b6381000 00000000 .8.......8...... - 1d74460 c6381000 00000000 d6381000 00000000 .8.......8...... - 1d74470 e6381000 00000000 f6381000 00000000 .8.......8...... - 1d74480 06391000 00000000 16391000 00000000 .9.......9...... - 1d74490 26391000 00000000 36391000 00000000 &9......69...... - 1d744a0 46391000 00000000 56391000 00000000 F9......V9...... - 1d744b0 66391000 00000000 76391000 00000000 f9......v9...... - 1d744c0 86391000 00000000 96391000 00000000 .9.......9...... - 1d744d0 a6391000 00000000 b6391000 00000000 .9.......9...... - 1d744e0 c6391000 00000000 d6391000 00000000 .9.......9...... - 1d744f0 e6391000 00000000 f6391000 00000000 .9.......9...... - 1d74500 063a1000 00000000 163a1000 00000000 .:.......:...... - 1d74510 263a1000 00000000 363a1000 00000000 &:......6:...... - 1d74520 463a1000 00000000 563a1000 00000000 F:......V:...... - 1d74530 663a1000 00000000 763a1000 00000000 f:......v:...... - 1d74540 863a1000 00000000 963a1000 00000000 .:.......:...... - 1d74550 a63a1000 00000000 b63a1000 00000000 .:.......:...... - 1d74560 c63a1000 00000000 d63a1000 00000000 .:.......:...... - 1d74570 e63a1000 00000000 f63a1000 00000000 .:.......:...... - 1d74580 063b1000 00000000 163b1000 00000000 .;.......;...... - 1d74590 263b1000 00000000 363b1000 00000000 &;......6;...... - 1d745a0 463b1000 00000000 563b1000 00000000 F;......V;...... - 1d745b0 663b1000 00000000 763b1000 00000000 f;......v;...... - 1d745c0 863b1000 00000000 963b1000 00000000 .;.......;...... - 1d745d0 a63b1000 00000000 b63b1000 00000000 .;.......;...... - 1d745e0 c63b1000 00000000 d63b1000 00000000 .;.......;...... - 1d745f0 e63b1000 00000000 f63b1000 00000000 .;.......;...... - 1d74600 063c1000 00000000 163c1000 00000000 .<.......<...... - 1d74610 263c1000 00000000 363c1000 00000000 &<......6<...... - 1d74620 463c1000 00000000 563c1000 00000000 F<......V<...... - 1d74630 663c1000 00000000 763c1000 00000000 f<......v<...... - 1d74640 863c1000 00000000 963c1000 00000000 .<.......<...... - 1d74650 a63c1000 00000000 b63c1000 00000000 .<.......<...... - 1d74660 c63c1000 00000000 d63c1000 00000000 .<.......<...... - 1d74670 e63c1000 00000000 f63c1000 00000000 .<.......<...... - 1d74680 063d1000 00000000 163d1000 00000000 .=.......=...... - 1d74690 263d1000 00000000 363d1000 00000000 &=......6=...... - 1d746a0 463d1000 00000000 563d1000 00000000 F=......V=...... - 1d746b0 663d1000 00000000 763d1000 00000000 f=......v=...... - 1d746c0 863d1000 00000000 963d1000 00000000 .=.......=...... - 1d746d0 a63d1000 00000000 b63d1000 00000000 .=.......=...... - 1d746e0 c63d1000 00000000 d63d1000 00000000 .=.......=...... - 1d746f0 e63d1000 00000000 f63d1000 00000000 .=.......=...... - 1d74700 063e1000 00000000 163e1000 00000000 .>.......>...... - 1d74710 263e1000 00000000 363e1000 00000000 &>......6>...... - 1d74720 463e1000 00000000 563e1000 00000000 F>......V>...... - 1d74730 663e1000 00000000 763e1000 00000000 f>......v>...... - 1d74740 863e1000 00000000 963e1000 00000000 .>.......>...... - 1d74750 a63e1000 00000000 b63e1000 00000000 .>.......>...... - 1d74760 c63e1000 00000000 d63e1000 00000000 .>.......>...... - 1d74770 e63e1000 00000000 f63e1000 00000000 .>.......>...... - 1d74780 063f1000 00000000 163f1000 00000000 .?.......?...... - 1d74790 263f1000 00000000 363f1000 00000000 &?......6?...... - 1d747a0 463f1000 00000000 563f1000 00000000 F?......V?...... - 1d747b0 663f1000 00000000 763f1000 00000000 f?......v?...... - 1d747c0 863f1000 00000000 963f1000 00000000 .?.......?...... - 1d747d0 a63f1000 00000000 b63f1000 00000000 .?.......?...... - 1d747e0 c63f1000 00000000 d63f1000 00000000 .?.......?...... - 1d747f0 e63f1000 00000000 f63f1000 00000000 .?.......?...... - 1d74800 06401000 00000000 16401000 00000000 .@.......@...... - 1d74810 26401000 00000000 36401000 00000000 &@......6@...... - 1d74820 46401000 00000000 56401000 00000000 F@......V@...... - 1d74830 66401000 00000000 76401000 00000000 f@......v@...... - 1d74840 86401000 00000000 96401000 00000000 .@.......@...... - 1d74850 a6401000 00000000 b6401000 00000000 .@.......@...... - 1d74860 c6401000 00000000 d6401000 00000000 .@.......@...... - 1d74870 e6401000 00000000 f6401000 00000000 .@.......@...... - 1d74880 06411000 00000000 16411000 00000000 .A.......A...... - 1d74890 26411000 00000000 36411000 00000000 &A......6A...... - 1d748a0 46411000 00000000 56411000 00000000 FA......VA...... - 1d748b0 66411000 00000000 76411000 00000000 fA......vA...... - 1d748c0 86411000 00000000 96411000 00000000 .A.......A...... - 1d748d0 a6411000 00000000 b6411000 00000000 .A.......A...... - 1d748e0 c6411000 00000000 d6411000 00000000 .A.......A...... - 1d748f0 e6411000 00000000 f6411000 00000000 .A.......A...... - 1d74900 06421000 00000000 16421000 00000000 .B.......B...... - 1d74910 26421000 00000000 36421000 00000000 &B......6B...... - 1d74920 46421000 00000000 56421000 00000000 FB......VB...... - 1d74930 66421000 00000000 76421000 00000000 fB......vB...... - 1d74940 86421000 00000000 96421000 00000000 .B.......B...... - 1d74950 a6421000 00000000 b6421000 00000000 .B.......B...... - 1d74960 c6421000 00000000 d6421000 00000000 .B.......B...... - 1d74970 e6421000 00000000 f6421000 00000000 .B.......B...... - 1d74980 06431000 00000000 16431000 00000000 .C.......C...... - 1d74990 26431000 00000000 36431000 00000000 &C......6C...... - 1d749a0 46431000 00000000 56431000 00000000 FC......VC...... - 1d749b0 66431000 00000000 76431000 00000000 fC......vC...... - 1d749c0 86431000 00000000 96431000 00000000 .C.......C...... - 1d749d0 a6431000 00000000 b6431000 00000000 .C.......C...... - 1d749e0 c6431000 00000000 d6431000 00000000 .C.......C...... - 1d749f0 e6431000 00000000 f6431000 00000000 .C.......C...... - 1d74a00 06441000 00000000 16441000 00000000 .D.......D...... - 1d74a10 26441000 00000000 36441000 00000000 &D......6D...... - 1d74a20 46441000 00000000 56441000 00000000 FD......VD...... - 1d74a30 66441000 00000000 76441000 00000000 fD......vD...... - 1d74a40 86441000 00000000 96441000 00000000 .D.......D...... - 1d74a50 a6441000 00000000 b6441000 00000000 .D.......D...... - 1d74a60 c6441000 00000000 d6441000 00000000 .D.......D...... - 1d74a70 e6441000 00000000 f6441000 00000000 .D.......D...... - 1d74a80 06451000 00000000 16451000 00000000 .E.......E...... - 1d74a90 26451000 00000000 36451000 00000000 &E......6E...... - 1d74aa0 46451000 00000000 56451000 00000000 FE......VE...... - 1d74ab0 66451000 00000000 76451000 00000000 fE......vE...... - 1d74ac0 86451000 00000000 96451000 00000000 .E.......E...... - 1d74ad0 a6451000 00000000 b6451000 00000000 .E.......E...... - 1d74ae0 c6451000 00000000 d6451000 00000000 .E.......E...... - 1d74af0 e6451000 00000000 f6451000 00000000 .E.......E...... - 1d74b00 06461000 00000000 16461000 00000000 .F.......F...... - 1d74b10 26461000 00000000 36461000 00000000 &F......6F...... - 1d74b20 46461000 00000000 56461000 00000000 FF......VF...... - 1d74b30 66461000 00000000 76461000 00000000 fF......vF...... - 1d74b40 86461000 00000000 96461000 00000000 .F.......F...... - 1d74b50 a6461000 00000000 b6461000 00000000 .F.......F...... - 1d74b60 c6461000 00000000 d6461000 00000000 .F.......F...... - 1d74b70 e6461000 00000000 f6461000 00000000 .F.......F...... - 1d74b80 06471000 00000000 16471000 00000000 .G.......G...... - 1d74b90 26471000 00000000 36471000 00000000 &G......6G...... - 1d74ba0 46471000 00000000 56471000 00000000 FG......VG...... - 1d74bb0 66471000 00000000 76471000 00000000 fG......vG...... - 1d74bc0 86471000 00000000 96471000 00000000 .G.......G...... - 1d74bd0 a6471000 00000000 b6471000 00000000 .G.......G...... - 1d74be0 c6471000 00000000 d6471000 00000000 .G.......G...... - 1d74bf0 e6471000 00000000 f6471000 00000000 .G.......G...... - 1d74c00 06481000 00000000 16481000 00000000 .H.......H...... - 1d74c10 26481000 00000000 36481000 00000000 &H......6H...... /usr/lib64/libopenblas_openmp.so.0 differs in ELF section .data --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,4102 +2,4102 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section .data: - 1d7b720 20b7d701 00000000 00000000 00000000 ............... - 1d7b730 00000000 00000000 00000000 00000000 ................ - 1d7b740 00000000 01000000 01000080 56555555 ............VUUU - 1d7b750 01000040 34333333 abaaaa2a 25499224 ...@4333...*%I.$ - 1d7b760 01000020 1dc7711c 9a999919 75d14517 ... ..q.....u.E. - 1d7b770 56555515 143bb113 93244912 12111111 VUU..;...$I..... - 1d7b780 01000010 100f0f0f 8fe3380e 5f43790d ..........8._Cy. - 1d7b790 cdcccc0c 0dc3300c bbe8a20b 2d64210b ......0.....-d!. - 1d7b7a0 abaaaa0a a4703d0a 8a9dd809 5f427b09 .....p=....._B{. - 1d7b7b0 4a922409 b1dcd308 89888808 85104208 J.$...........B. - 1d7b7c0 01000008 7df0c107 88878707 08755007 ....}........uP. - 1d7b7d0 c8711c07 463eeb06 b0a1bc06 07699006 .q..F>.......i.. - 1d7b7e0 67666606 64703e06 87611806 d117f405 gff.dp>..a...... - 1d7b7f0 5e74d105 065bb005 17b29005 0b627205 ^t...[.......br. - 1d7b800 56555505 2a783905 52b81e05 06050505 VUU.*x9.R....... - 1d7b810 c54eec04 3f87d404 30a1bd04 4b90a704 .N..?...0...K... - 1d7b820 25499204 20c17d04 59ee6904 98c75604 %I.. .}.Y.i...V. - 1d7b830 45444404 545c3204 43082104 05411004 EDD.T\2.C.!..A.. - 1d7b840 01000004 00000000 00000000 00000000 ................ - 1d7b850 00000000 00000000 00000000 00000000 ................ - 1d7b860 40000000 00000000 00000000 ff3f0000 @............?.. - 1d7b870 00000000 00000000 00000000 08000000 ................ - 1d7b880 04000000 20000000 00000000 00000000 .... ........... - 1d7b890 00000000 00000000 00000000 00000000 ................ - 1d7b8a0 00000000 00000000 00000000 00000000 ................ - 1d7b8b0 00000000 00000000 00000000 00000000 ................ - 1d7b8c0 00000000 00000000 00000000 00000000 ................ - 1d7b8d0 00000000 00000000 00000000 00000000 ................ - 1d7b8e0 00000000 00000000 00000000 00000000 ................ - 1d7b8f0 00000000 00000000 00000000 00000000 ................ - 1d7b900 00000000 00000000 00000000 00000000 ................ - 1d7b910 00000000 00000000 00000000 00000000 ................ - 1d7b920 00000000 00000000 00000000 00000000 ................ - 1d7b930 00000000 00000000 00000000 00000000 ................ - 1d7b940 00000000 00000000 00000000 00000000 ................ - 1d7b950 00000000 00000000 00000000 00000000 ................ - 1d7b960 00000000 00000000 00000000 00000000 ................ - 1d7b970 00000000 00000000 00000000 00000000 ................ - 1d7b980 00000000 00000000 00000000 00000000 ................ - 1d7b990 00000000 00000000 00000000 00000000 ................ - 1d7b9a0 00000000 00000000 00000000 00000000 ................ - 1d7b9b0 00000000 00000000 00000000 00000000 ................ - 1d7b9c0 00000000 00000000 00000000 00000000 ................ - 1d7b9d0 00000000 00000000 00000000 00000000 ................ - 1d7b9e0 00000000 00000000 00000000 00000000 ................ - 1d7b9f0 00000000 00000000 00000000 00000000 ................ - 1d7ba00 00000000 00000000 00000000 00000000 ................ - 1d7ba10 00000000 00000000 00000000 00000000 ................ - 1d7ba20 00000000 00000000 00000000 00000000 ................ - 1d7ba30 00000000 00000000 00000000 00000000 ................ - 1d7ba40 00000000 00000000 00000000 00000000 ................ - 1d7ba50 00000000 00000000 00000000 00000000 ................ - 1d7ba60 00000000 00000000 00000000 00000000 ................ - 1d7ba70 00000000 00000000 00000000 00000000 ................ - 1d7ba80 00000000 00000000 00000000 00000000 ................ - 1d7ba90 00000000 00000000 00000000 00000000 ................ - 1d7baa0 00000000 00000000 00000000 00000000 ................ - 1d7bab0 00000000 00000000 00000000 00000000 ................ - 1d7bac0 00000000 00000000 00000000 00000000 ................ - 1d7bad0 00000000 00000000 00000000 00000000 ................ - 1d7bae0 00000000 00000000 00000000 00000000 ................ - 1d7baf0 00000000 00000000 00000000 00000000 ................ - 1d7bb00 00000000 00000000 00000000 10000000 ................ - 1d7bb10 04000000 20000000 00000000 00000000 .... ........... - 1d7bb20 00000000 00000000 00000000 00000000 ................ - 1d7bb30 00000000 00000000 00000000 00000000 ................ - 1d7bb40 00000000 00000000 00000000 00000000 ................ - 1d7bb50 00000000 00000000 00000000 00000000 ................ - 1d7bb60 00000000 00000000 00000000 00000000 ................ - 1d7bb70 00000000 00000000 00000000 00000000 ................ - 1d7bb80 00000000 00000000 00000000 00000000 ................ - 1d7bb90 00000000 00000000 00000000 00000000 ................ - 1d7bba0 00000000 00000000 00000000 00000000 ................ - 1d7bbb0 00000000 00000000 00000000 00000000 ................ - 1d7bbc0 00000000 00000000 00000000 00000000 ................ - 1d7bbd0 00000000 00000000 00000000 00000000 ................ - 1d7bbe0 00000000 00000000 00000000 00000000 ................ - 1d7bbf0 00000000 00000000 00000000 00000000 ................ - 1d7bc00 00000000 00000000 00000000 00000000 ................ - 1d7bc10 00000000 00000000 00000000 00000000 ................ - 1d7bc20 00000000 00000000 00000000 00000000 ................ - 1d7bc30 00000000 00000000 00000000 00000000 ................ - 1d7bc40 00000000 00000000 00000000 00000000 ................ - 1d7bc50 00000000 00000000 00000000 00000000 ................ - 1d7bc60 00000000 00000000 00000000 00000000 ................ - 1d7bc70 00000000 00000000 00000000 00000000 ................ - 1d7bc80 00000000 00000000 00000000 00000000 ................ - 1d7bc90 00000000 00000000 00000000 00000000 ................ - 1d7bca0 00000000 00000000 00000000 00000000 ................ - 1d7bcb0 00000000 00000000 00000000 00000000 ................ - 1d7bcc0 00000000 00000000 00000000 00000000 ................ - 1d7bcd0 00000000 00000000 00000000 00000000 ................ - 1d7bce0 00000000 00000000 00000000 00000000 ................ - 1d7bcf0 00000000 00000000 00000000 00000000 ................ - 1d7bd00 00000000 00000000 00000000 00000000 ................ - 1d7bd10 00000000 00000000 00000000 00000000 ................ - 1d7bd20 00000000 00000000 00000000 00000000 ................ - 1d7bd30 00000000 00000000 00000000 00000000 ................ - 1d7bd40 00000000 00000000 00000000 00000000 ................ - 1d7bd50 00000000 00000000 00000000 00000000 ................ - 1d7bd60 00000000 00000000 00000000 00000000 ................ - 1d7bd70 00000000 00000000 00000000 00000000 ................ - 1d7bd80 00000000 00000000 00000000 10000000 ................ - 1d7bd90 02000000 20000000 00000000 00000000 .... ........... - 1d7bda0 00000000 00000000 00000000 00000000 ................ - 1d7bdb0 00000000 00000000 00000000 00000000 ................ - 1d7bdc0 00000000 00000000 00000000 00000000 ................ - 1d7bdd0 00000000 00000000 00000000 00000000 ................ - 1d7bde0 00000000 00000000 00000000 00000000 ................ - 1d7bdf0 00000000 00000000 00000000 00000000 ................ - 1d7be00 00000000 00000000 00000000 00000000 ................ - 1d7be10 00000000 00000000 00000000 00000000 ................ - 1d7be20 00000000 00000000 00000000 00000000 ................ - 1d7be30 00000000 00000000 00000000 00000000 ................ - 1d7be40 00000000 00000000 00000000 00000000 ................ - 1d7be50 00000000 00000000 00000000 00000000 ................ - 1d7be60 00000000 00000000 00000000 00000000 ................ - 1d7be70 00000000 00000000 00000000 00000000 ................ - 1d7be80 00000000 00000000 00000000 00000000 ................ - 1d7be90 00000000 00000000 00000000 00000000 ................ - 1d7bea0 00000000 00000000 00000000 00000000 ................ - 1d7beb0 00000000 00000000 00000000 00000000 ................ - 1d7bec0 00000000 00000000 00000000 00000000 ................ - 1d7bed0 00000000 00000000 00000000 00000000 ................ - 1d7bee0 00000000 00000000 00000000 00000000 ................ - 1d7bef0 00000000 00000000 00000000 00000000 ................ - 1d7bf00 00000000 00000000 00000000 00000000 ................ - 1d7bf10 00000000 00000000 00000000 00000000 ................ - 1d7bf20 00000000 00000000 00000000 00000000 ................ - 1d7bf30 00000000 00000000 00000000 00000000 ................ - 1d7bf40 00000000 00000000 00000000 00000000 ................ - 1d7bf50 00000000 00000000 00000000 00000000 ................ - 1d7bf60 00000000 00000000 00000000 00000000 ................ - 1d7bf70 00000000 00000000 00000000 00000000 ................ - 1d7bf80 00000000 00000000 00000000 00000000 ................ - 1d7bf90 00000000 00000000 00000000 00000000 ................ - 1d7bfa0 00000000 00000000 00000000 00000000 ................ - 1d7bfb0 00000000 00000000 00000000 00000000 ................ - 1d7bfc0 00000000 00000000 00000000 00000000 ................ - 1d7bfd0 00000000 00000000 00000000 00000000 ................ - 1d7bfe0 00000000 00000000 00000000 00000000 ................ - 1d7bff0 00000000 00000000 00000000 08000000 ................ - 1d7c000 02000000 08000000 00000000 00000000 ................ - 1d7c010 00000000 00000000 00000000 00000000 ................ - 1d7c020 00000000 00000000 00000000 00000000 ................ - 1d7c030 00000000 00000000 00000000 00000000 ................ - 1d7c040 00000000 00000000 00000000 00000000 ................ - 1d7c050 00000000 00000000 00000000 00000000 ................ - 1d7c060 00000000 00000000 00000000 00000000 ................ - 1d7c070 00000000 00000000 00000000 00000000 ................ - 1d7c080 00000000 00000000 00000000 00000000 ................ - 1d7c090 00000000 00000000 00000000 00000000 ................ - 1d7c0a0 00000000 00000000 00000000 00000000 ................ - 1d7c0b0 00000000 00000000 00000000 00000000 ................ - 1d7c0c0 00000000 00000000 00000000 00000000 ................ - 1d7c0d0 00000000 00000000 00000000 00000000 ................ - 1d7c0e0 00000000 00000000 00000000 00000000 ................ - 1d7c0f0 00000000 00000000 00000000 00000000 ................ - 1d7c100 00000000 00000000 00000000 00000000 ................ - 1d7c110 00000000 00000000 00000000 00000000 ................ - 1d7c120 00000000 00000000 00000000 00000000 ................ - 1d7c130 00000000 00000000 00000000 00000000 ................ - 1d7c140 00000000 00000000 00000000 00000000 ................ - 1d7c150 00000000 00000000 00000000 00000000 ................ - 1d7c160 00000000 00000000 00000000 00000000 ................ - 1d7c170 00000000 00000000 00000000 00000000 ................ - 1d7c180 00000000 00000000 00000000 00000000 ................ - 1d7c190 00000000 00000000 00000000 00000000 ................ - 1d7c1a0 00000000 00000000 00000000 00000000 ................ - 1d7c1b0 00000000 00000000 00000000 00000000 ................ - 1d7c1c0 00000000 00000000 00000000 00000000 ................ - 1d7c1d0 00000000 00000000 00000000 00000000 ................ - 1d7c1e0 00000000 00000000 00000000 00000000 ................ - 1d7c1f0 00000000 00000000 00000000 00000000 ................ - 1d7c200 00000000 00000000 00000000 00000000 ................ - 1d7c210 00000000 00000000 00000000 00000000 ................ - 1d7c220 00000000 00000000 00000000 00000000 ................ - 1d7c230 00000000 00000000 00000000 00000000 ................ - 1d7c240 00000000 00000000 00000000 00000000 ................ - 1d7c250 00000000 00000000 00000000 00000000 ................ - 1d7c260 00000000 00000000 00000000 00000000 ................ - 1d7c270 00000000 00000000 00000000 00000000 ................ - 1d7c280 00000000 00000000 00000000 00000000 ................ - 1d7c290 00000000 00000000 00000000 00000000 ................ - 1d7c2a0 00000000 00000000 00000000 00000000 ................ - 1d7c2b0 00000000 00000000 00000000 00000000 ................ - 1d7c2c0 00000000 00000000 00000000 00000000 ................ - 1d7c2d0 00000000 00000000 00000000 00000000 ................ - 1d7c2e0 00000000 00000000 00000000 00000000 ................ - 1d7c2f0 00000000 00000000 00000000 00000000 ................ - 1d7c300 00000000 00000000 00000000 00000000 ................ - 1d7c310 00000000 00000000 00000000 00000000 ................ - 1d7c320 00000000 08000000 04000000 08000000 ................ - 1d7c330 00000000 00000000 00000000 00000000 ................ /usr/lib64/libopenblas_openmp.so.0 differs in ELF section __patchable_function_entries --- old /usr/lib64/libopenblas_openmp.so.0 (objdump) +++ new /usr/lib64/libopenblas_openmp.so.0 (objdump) @@ -2,4 +2,4 @@ /usr/lib64/libopenblas_openmp.so.0: file format elf64-x86-64 Contents of section __patchable_function_entries: - 1d8b748 10a3ba01 00000000 ........ + 1d62748 1023b801 00000000 .#...... RPMS.2017/openblas_openmp-devel-static-0.3.17-0.0.x86_64.rpm RPMS/openblas_openmp-devel-static-0.3.17-0.0.x86_64.rpm differ: byte 225, line 1 Comparing openblas_openmp-devel-static-0.3.17-0.0.x86_64.rpm to openblas_openmp-devel-static-0.3.17-0.0.x86_64.rpm comparing the rpm tags of openblas_openmp-devel-static --- old-rpm-tags +++ new-rpm-tags @@ -83,7 +83,7 @@ ___QF_FILELIST___ ___QF_CHECKSUM___ -/usr/lib64/libopenblas_openmp.a bff314ff6c0da94d20873e97640d63841b2efe62386577191f141a35692a503e 0 +/usr/lib64/libopenblas_openmp.a 363ce06b47ef01f8765a821088b251cbb696fe06784ca07b32ea3767a46fd828 0 ___QF_CHECKSUM___ comparing rpmtags comparing RELEASE comparing PROVIDES comparing scripts comparing filelist comparing file checksum creating rename script RPM file checksum differs. Extracting packages /usr/lib64/libopenblas_openmp.a/casum_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/casum_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/casum_k_SKYLAKEX.o (disasm) @@ -5,384 +5,167 @@ Disassembly of section .text: asum_compute: - mov %rsi,%rax - mov %rdi,%rcx - mov %rdx,%rsi + mov %rdi,%rax + mov %rsi,%rcx test %rdi,%rdi jle test %rdx,%rdx jle cmp $something,%rdx je - vxorps %xmm2,%xmm2,%xmm2 + vxorps %xmm1,%xmm1,%xmm1 vmovss offset(%rip),%xmm6 # - shl $something,%rsi - add $something,%rax - xor %edx,%edx - vmovaps %xmm2,%xmm3 + shl $something,%rdx + add $something,%rcx + xor %esi,%esi + vmovaps %xmm1,%xmm3 vmovaps %xmm6,%xmm7 - nop - vmovss -offset(%rax),%xmm0 - inc %rdx - vmovaps %xmm0,%xmm1 + nopl offset(%rax) + vmovss -offset(%rcx),%xmm0 + inc %rsi + vmovaps %xmm0,%xmm2 vxorps %xmm6,%xmm0,%xmm4 - vcmpnltss %xmm0,%xmm2,%xmm0 - vblendvps %xmm0,%xmm4,%xmm1,%xmm0 - vmovss (%rax),%xmm1 - add %rsi,%rax - vmovaps %xmm1,%xmm4 - vxorps %xmm7,%xmm1,%xmm5 - vcmpnltss %xmm1,%xmm2,%xmm1 - vblendvps %xmm1,%xmm5,%xmm4,%xmm1 - vaddss %xmm1,%xmm0,%xmm0 + vcmpnltss %xmm0,%xmm1,%xmm0 + vblendvps %xmm0,%xmm4,%xmm2,%xmm0 + vmovss (%rcx),%xmm2 + add %rdx,%rcx + vmovaps %xmm2,%xmm4 + vxorps %xmm7,%xmm2,%xmm5 + vcmpnltss %xmm2,%xmm1,%xmm2 + vblendvps %xmm2,%xmm5,%xmm4,%xmm2 + vaddss %xmm2,%xmm0,%xmm0 vaddss %xmm0,%xmm3,%xmm3 - cmp %rdx,%rcx + cmp %rsi,%rax jg vmovaps %xmm3,%xmm0 ret nopw offset(%rax,%rax,1) - vxorps %xmm3,%xmm3,%xmm3 - vmovaps %xmm3,%xmm0 - ret - nopl offset(%rax) - add %rcx,%rcx - cmp $something,%rcx - jg - prefetcht0 (%rax) - cmp $something,%rcx - jg - vxorps %xmm5,%xmm5,%xmm5 - vmovaps %xmm5,%xmm1 - vmovaps %xmm5,%xmm3 - vmovaps %xmm5,%xmm0 - cmp $something,%rcx - jle - vbroadcastss offset(%rip),%xmm2 # - sub $something,%rcx - vandps (%rax),%xmm2,%xmm7 - vandps offset(%rax),%xmm2,%xmm6 - vandps offset(%rax),%xmm2,%xmm4 - vandps offset(%rax),%xmm2,%xmm2 - vaddps %xmm7,%xmm0,%xmm0 - vaddps %xmm6,%xmm3,%xmm3 - vaddps %xmm4,%xmm1,%xmm1 - vaddps %xmm2,%xmm5,%xmm5 - add $something,%rax - cmp $something,%rcx - jle - vbroadcastss offset(%rip),%xmm2 # - sub $something,%rcx - vandps (%rax),%xmm2,%xmm4 - vandps offset(%rax),%xmm2,%xmm2 - vaddps %xmm4,%xmm0,%xmm0 - vaddps %xmm2,%xmm3,%xmm3 - add $something,%rax - cmp $something,%rcx - jle - vbroadcastss offset(%rip),%xmm2 # - sub $something,%rcx - vandps (%rax),%xmm2,%xmm2 - add $something,%rax - vaddps %xmm2,%xmm0,%xmm0 - vxorps %xmm2,%xmm2,%xmm2 - test %rcx,%rcx - je - vmovss (%rax),%xmm4 - vxorps offset(%rip),%xmm4,%xmm7 # - vmovaps %xmm4,%xmm6 - vcmpnltss %xmm4,%xmm2,%xmm4 - vblendvps %xmm4,%xmm7,%xmm6,%xmm4 - vmovss offset(%rax),%xmm6 - vxorps offset(%rip),%xmm6,%xmm8 # - vmovaps %xmm6,%xmm7 - vcmpnltss %xmm6,%xmm2,%xmm6 - vblendvps %xmm6,%xmm8,%xmm7,%xmm6 - vaddss %xmm6,%xmm4,%xmm4 - vaddss %xmm2,%xmm4,%xmm2 - vaddps %xmm3,%xmm0,%xmm0 - vaddps %xmm5,%xmm1,%xmm1 - vaddps %xmm1,%xmm0,%xmm0 - vhaddps %xmm0,%xmm0,%xmm0 - vhaddps %xmm0,%xmm0,%xmm0 - vaddss %xmm2,%xmm0,%xmm3 - jmp - cmp $something,%rcx - jg - vmovups (%rax),%zmm1 - vmovups offset(%rax),%zmm3 - vmovups offset(%rax),%zmm2 - vmovups offset(%rax),%zmm4 - cmp $something,%rcx - jle - vbroadcastss offset(%rip),%zmm0 # - vxorps %xmm5,%xmm5,%xmm5 - vandps %zmm0,%zmm1,%zmm1 - vandps %zmm0,%zmm3,%zmm3 - vandps %zmm0,%zmm2,%zmm2 - vandps %zmm0,%zmm4,%zmm4 - vaddps %zmm5,%zmm1,%zmm1 - vaddps %zmm5,%zmm3,%zmm3 - vaddps %zmm5,%zmm2,%zmm2 - vaddps %zmm5,%zmm4,%zmm4 - vandps offset(%rax),%zmm0,%zmm9 - vandps offset(%rax),%zmm0,%zmm8 - vandps offset(%rax),%zmm0,%zmm7 - vandps offset(%rax),%zmm0,%zmm6 - add $something,%rcx - vaddps %zmm9,%zmm1,%zmm1 - vaddps %zmm8,%zmm3,%zmm3 - vaddps %zmm7,%zmm2,%zmm2 - vaddps %zmm6,%zmm4,%zmm4 - add $something,%rax - cmp $something,%rcx - jg - cmp $something,%rcx - jle - vandps (%rax),%zmm0,%zmm6 - vandps offset(%rax),%zmm0,%zmm5 - vaddps %zmm6,%zmm1,%zmm1 - vaddps %zmm5,%zmm3,%zmm3 - sub $something,%rcx - sub $something,%rax - cmp $something,%rcx - jle - vandps (%rax),%zmm0,%zmm5 - sub $something,%rcx - vaddps %zmm5,%zmm1,%zmm1 - add $something,%rax - test %rcx,%rcx - je - mov $something,%esi - sub %ecx,%esi - mov $something,%edx - sarx %esi,%edx,%edx - kmovw %edx,%k1 - vmovups (%rax),%zmm5{%k1}{z} - vandps %zmm0,%zmm5,%zmm0 - vaddps %zmm0,%zmm1,%zmm1 - vaddps %zmm3,%zmm1,%zmm1 - vaddps %zmm4,%zmm2,%zmm2 - vaddps %zmm2,%zmm1,%zmm1 - vextractf64x4 $something,%zmm1,%ymm0 - vaddps %ymm1,%ymm0,%ymm0 - vextractf128 $something,%ymm0,%xmm1 - vaddps %xmm0,%xmm1,%xmm1 - vpermilps $something,%xmm1,%xmm0 - vaddps %xmm1,%xmm0,%xmm0 - vmovaps %xmm0,%xmm3 - vshufps $something,%xmm0,%xmm0,%xmm0 - vaddss %xmm0,%xmm3,%xmm3 - vzeroupper - jmp - mov %rax,%rsi - and $something,%esi - mov $something,%edx - sub %rsi,%rdx /usr/lib64/libopenblas_openmp.a/casum_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/casum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/casum_k_SKYLAKEX.o (objdump) @@ -2,142 +2,70 @@ /usr/lib64/libopenblas_openmp.a/casum_k_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 4889f048 89f94889 d64885ff 0f8e7e00 H..H..H..H....~. - 0010 00004885 d27e7948 83fa010f 847f0000 ..H..~yH........ - 0020 00c5e857 d2c5fa10 35000000 0048c1e6 ...W....5....H.. - 0030 034883c0 0431d2c5 f828dac5 f828fe90 .H...1...(...(.. - 0040 c5fa1040 fc48ffc2 c5f828c8 c5f857e6 ...@.H....(...W. - 0050 c5eac2c0 05c4e371 4ac400c5 fa100848 .......qJ......H - 0060 01f0c5f8 28e1c5f0 57efc5ea c2c905c4 ....(...W....... - 0070 e3594acd 10c5fa58 c1c5e258 d84839d1 .YJ....X...X.H9. + 0000 4889f848 89f14885 ff0f8e81 02000048 H..H..H........H + 0010 85d20f8e 78020000 4883fa01 7472c5f0 ....x...H...tr.. + 0020 57c9c5fa 10350000 000048c1 e2034883 W....5....H...H. + 0030 c10431f6 c5f828d9 c5f828fe 0f1f4000 ..1...(...(...@. + 0040 c5fa1041 fc48ffc6 c5f828d0 c5f857e6 ...A.H....(...W. + 0050 c5f2c2c0 05c4e369 4ac400c5 fa101148 .......iJ......H + 0060 01d1c5f8 28e2c5e8 57efc5f2 c2d205c4 ....(...W....... + 0070 e3594ad5 20c5fa58 c2c5e258 d84839f0 .YJ. ..X...X.H9. 0080 7fbec5f8 28c3c366 0f1f8400 00000000 ....(..f........ - 0090 c5e057db c5f828c3 c30f1f80 00000000 ..W...(......... - 00a0 4801c948 83f93f0f 8f030100 000f1808 H..H..?......... - 00b0 4883f91f 0f8f3e05 0000c5d0 57edc5f8 H.....>.....W... - 00c0 28cdc5f8 28ddc5f8 28c54883 f90f7e34 (...(...(.H...~4 - 00d0 c4e27918 15000000 004883e9 10c5e854 ..y......H.....T - 00e0 38c5e854 7010c5e8 546020c5 e8545030 8..Tp...T` ..TP0 - 00f0 c5f858c7 c5e058de c5f058cc c5d058ea ..X...X...X...X. - 0100 4883c040 4883f907 7e22c4e2 79181500 H..@H...~"..y... - 0110 00000048 83e908c5 e85420c5 e8545010 ...H.....T ..TP. - 0120 c5f858c4 c5e058da 4883c020 4883f903 ..X...X.H.. H... - 0130 7e19c4e2 79181500 00000048 83e904c5 ~...y......H.... - 0140 e8541048 83c010c5 f858c2c5 e857d248 .T.H.....X...W.H - 0150 85c9743f c5fa1020 c5d8573d 00000000 ..t?... ..W=.... - 0160 c5f828f4 c5eac2e4 05c4e349 4ae740c5 ..(........IJ.@. - 0170 fa107004 c5485705 00000000 c5f828fe ..p..HW.......(. - 0180 c5eac2f6 05c4c341 4af060c5 da58e6c5 .......AJ.`..X.. - 0190 da58d2c5 f858c3c5 f058cdc5 f858c1c5 .X...X...X...X.. - 01a0 fb7cc0c5 fb7cc0c5 fa58dae9 d2feffff .|...|...X...... - 01b0 4881f9ff 0000000f 8f5e0100 0062f17c H........^...b.| - 01c0 48100862 f17c4810 580162f1 7c481050 H..b.|H.X.b.|H.P - 01d0 0262f17c 48106003 4883f97f 0f8e7d04 .b.|H.`.H.....}. - 01e0 000062f2 7d481805 00000000 c5d057ed ..b.}H........W. - 01f0 62f17448 54c862f1 644854d8 62f16c48 b.tHT.b.dHT.b.lH - 0200 54d062f1 5c4854e0 62f17448 58cd62f1 T.b.\HT.b.tHX.b. - 0210 644858dd 62f16c48 58d562f1 5c4858e5 dHX.b.lHX.b.\HX. - 0220 62717c48 54480462 717c4854 400562f1 bq|HTH.bq|HT@.b. - 0230 7c485478 0662f17c 48547007 4883c180 |HTx.b.|HTp.H... - 0240 62d17448 58c962d1 644858d8 62f16c48 b.tHX.b.dHX.b.lH - 0250 58d762f1 5c4858e6 48050002 00004883 X.b.\HX.H.....H. - 0260 f93f0f8f 17040000 4883f91f 7e2162f1 .?......H...~!b. - 0270 7c485430 62f17c48 54680162 f1744858 |HT0b.|HTh.b.tHX - 0280 ce62f164 4858dd48 83e92048 83e88048 .b.dHX.H.. H...H - 0290 83f90f7e 1462f17c 48542848 83e91062 ...~.b.|HT(H...b - 02a0 f1744858 cd4883c0 404885c9 7427be10 .tHX.H..@H..t'.. - 02b0 00000029 cebaffff 0000c4e2 4af7d2c5 ...)........J... - 02c0 f892ca62 f17cc910 2862f154 4854c062 ...b.|..(b.THT.b - 02d0 f1744858 c862f174 4858cb62 f16c4858 .tHX.b.tHX.b.lHX - 02e0 d462f174 4858ca62 f3fd481b c801c5fc .b.tHX.b..H..... - 02f0 58c1c4e3 7d19c101 c5f058c8 c4e37904 X...}.....X...y. - 0300 c14ec5f8 58c1c5f8 28d8c5f8 c6c055c5 .N..X...(.....U. - 0310 e258d8c5 f877e967 fdffff48 89c683e6 .X...w.g...H.... - 0320 3fba4000 00004829 f248c1ea 0283e20f ?.@...H).H...... - 0330 0f848b03 0000bf10 00000029 d7beffff ...........).... - 0340 00004863 d262f27d 48180500 000000c4 ..Hc.b.}H....... - 0350 e242f7f6 c5f892d6 62f17cca 10284829 .B......b.|..(H) - 0360 d1488d04 90c5f057 c962f154 4854e848 .H.....W.b.THT.H - 0370 83c18062 f1544858 e962f17c 48283062 ...b.THX.b.|H(0b - 0380 717c4828 78016271 7c482870 0262717c q|H(x.bq|H(p.bq| - 0390 48286803 62f17c48 28600462 f17c4828 H(h.b.|H(`.b.|H( - 03a0 580562f1 7c482850 0662f17c 48284807 X.b.|H(P.b.|H(H. - 03b0 48050002 00004883 f97f0f8e 55030000 H.....H.....U... - 03c0 c4411857 e44889ce 4889c262 517c4828 .A.W.H..H..bQ|H( - 03d0 d462517c 4828dc66 0f1f8400 00000000 .bQ|H(.f........ - 03e0 62e14c48 54c06271 044854c8 62710c48 b.LHT.bq.HT.bq.H - 03f0 54c062f1 144854f8 62f17c40 58ed6251 T.b..HT.b.|@X.bQ - 0400 344858cb 62512c48 58c062f1 1c4858ff 4HX.bQ,HX.b..HX. - 0410 62f15c48 54e062f1 644854d8 62f16c48 b.\HT.b.dHT.b.lH - 0420 54d062f1 744854c8 4883c680 62f15448 T.b.tHT.H...b.TH - 0430 58ec6271 344858db 62713c48 58d26271 X.bq4HX.bq imul %rdx,%rdi - vxorpd %xmm1,%xmm1,%xmm1 + vxorpd %xmm2,%xmm2,%xmm2 vmovq offset(%rip),%xmm5 # - vmovsd %xmm1,%xmm1,%xmm7 + mov %rdi,%rsi + vmovsd %xmm2,%xmm2,%xmm7 xor %eax,%eax nopl offset(%rax) vmovsd (%rcx,%rax,8),%xmm0 add %rdx,%rax - vmovsd %xmm0,%xmm0,%xmm2 - vxorpd %xmm5,%xmm0,%xmm3 - vcmpnltsd %xmm0,%xmm1,%xmm0 - vblendvpd %xmm0,%xmm3,%xmm2,%xmm0 + vmovsd %xmm0,%xmm0,%xmm3 + vxorpd %xmm5,%xmm0,%xmm4 + vcmpnltsd %xmm0,%xmm2,%xmm0 + vblendvpd %xmm0,%xmm4,%xmm3,%xmm0 vaddsd %xmm0,%xmm7,%xmm7 - cmp %rax,%rdi + cmp %rax,%rsi jg vmovsd %xmm7,%xmm7,%xmm0 ret nopl offset(%rax) - mov %rdi,%rdx - and $something,%rdx - je - vmovq offset(%rip),%xmm13 # - vxorpd %xmm1,%xmm1,%xmm1 - mov %rsi,%rax - vmovsd %xmm1,%xmm1,%xmm11 - xor %esi,%esi - vmovsd %xmm1,%xmm1,%xmm12 - vmovsd %xmm1,%xmm1,%xmm5 - vmovsd %xmm1,%xmm1,%xmm7 - vmovapd %xmm13,%xmm20 - vmovapd %xmm13,%xmm19 - vmovapd %xmm13,%xmm18 - vmovapd %xmm13,%xmm17 - vmovapd %xmm13,%xmm16 - vmovapd %xmm13,%xmm23 - vmovapd %xmm13,%xmm24 - vmovsd (%rax),%xmm4 - vmovsd offset(%rax),%xmm3 - vmovsd %xmm4,%xmm4,%xmm0 - vxorpd %xmm13,%xmm4,%xmm2 - vcmpnltsd %xmm4,%xmm1,%xmm4 - vmovsd offset(%rax),%xmm10 - vmovsd offset(%rax),%xmm9 - vblendvpd %xmm4,%xmm2,%xmm0,%xmm4 - vmovsd %xmm3,%xmm3,%xmm0 - vxorpd %xmm20,%xmm3,%xmm2 - vcmpnltsd %xmm3,%xmm1,%xmm3 - vaddsd %xmm7,%xmm4,%xmm7 - add $something,%rsi - vblendvpd %xmm3,%xmm2,%xmm0,%xmm3 - vmovsd offset(%rax),%xmm2 - vaddsd %xmm5,%xmm3,%xmm5 - vmovsd %xmm2,%xmm2,%xmm0 - vxorpd %xmm19,%xmm2,%xmm6 - vcmpnltsd %xmm2,%xmm1,%xmm2 - add $something,%rax - vblendvpd %xmm2,%xmm6,%xmm0,%xmm2 - vmovsd -offset(%rax),%xmm0 - vaddsd %xmm12,%xmm2,%xmm12 - vmovsd %xmm0,%xmm0,%xmm6 - vxorpd %xmm18,%xmm0,%xmm8 - vcmpnltsd %xmm0,%xmm1,%xmm0 - vblendvpd %xmm0,%xmm8,%xmm6,%xmm0 - vmovsd %xmm10,%xmm10,%xmm6 - vxorpd %xmm17,%xmm10,%xmm8 - vcmpnltsd %xmm10,%xmm1,%xmm10 - vaddsd %xmm0,%xmm11,%xmm11 - vblendvpd %xmm10,%xmm8,%xmm6,%xmm10 - vmovsd %xmm9,%xmm9,%xmm6 - vxorpd %xmm16,%xmm9,%xmm8 - vcmpnltsd %xmm9,%xmm1,%xmm9 - vaddsd %xmm10,%xmm7,%xmm7 - vblendvpd %xmm9,%xmm8,%xmm6,%xmm9 - vmovsd -offset(%rax),%xmm8 - vaddsd %xmm9,%xmm5,%xmm5 - vmovsd %xmm8,%xmm8,%xmm6 - vxorpd %xmm23,%xmm8,%xmm21 - vcmpnltsd %xmm8,%xmm1,%xmm8 - vmovsd %xmm21,%xmm21,%xmm14 - vblendvpd %xmm8,%xmm14,%xmm6,%xmm8 - vmovsd -offset(%rax),%xmm6 - vaddsd %xmm8,%xmm12,%xmm12 - vmovsd %xmm6,%xmm6,%xmm21 - vxorpd %xmm24,%xmm6,%xmm22 - vcmpnltsd %xmm6,%xmm1,%xmm6 - vmovsd %xmm21,%xmm21,%xmm14 - vmovsd %xmm22,%xmm22,%xmm15 - vblendvpd %xmm6,%xmm15,%xmm14,%xmm6 - vaddsd %xmm6,%xmm11,%xmm11 - cmp %rsi,%rdx + cmp $something,%rdi jg - vaddsd %xmm5,%xmm7,%xmm7 - dec %rdx - shr $something,%rdx - vaddsd %xmm12,%xmm7,%xmm7 - lea offset(,%rdx,8),%rdx - vaddsd %xmm11,%xmm7,%xmm7 - cmp %rdx,%rdi - jle - vmovq offset(%rip),%xmm5 # - vmovsd %xmm1,%xmm1,%xmm0 - nopl offset(%rax,%rax,1) - vmovsd (%rcx,%rdx,8),%xmm2 - inc %rdx - vmovsd %xmm2,%xmm2,%xmm3 - vxorpd %xmm5,%xmm2,%xmm4 - vcmpnltsd %xmm2,%xmm1,%xmm2 - vblendvpd %xmm2,%xmm4,%xmm3,%xmm2 - vaddsd %xmm2,%xmm0,%xmm0 - cmp %rdx,%rdi + mov %rdi,%rsi + and $something,%rsi + cmp $something,%rdi jg - vaddsd %xmm7,%xmm0,%xmm7 + vxorpd %xmm2,%xmm2,%xmm2 + vmovsd %xmm2,%xmm2,%xmm7 + cmp %rdi,%rsi + jge + vmovq offset(%rip),%xmm5 # + lea (%rcx,%rsi,8),%rax + lea (%rcx,%rdi,8),%rdx + nop + vmovsd (%rax),%xmm0 + add $something,%rax + vmovsd %xmm0,%xmm0,%xmm3 + vxorpd %xmm5,%xmm0,%xmm4 + vcmpnltsd %xmm0,%xmm2,%xmm0 + vblendvpd %xmm0,%xmm4,%xmm3,%xmm0 + vaddsd %xmm0,%xmm7,%xmm7 + cmp %rax,%rdx + jne vmovsd %xmm7,%xmm7,%xmm0 ret - nopl (%rax) + nopl offset(%rax) vxorpd %xmm7,%xmm7,%xmm7 vmovsd %xmm7,%xmm7,%xmm0 ret - vxorpd %xmm1,%xmm1,%xmm1 - vmovsd %xmm1,%xmm1,%xmm7 + nopl offset(%rax) + mov %rsi,%rax + mov $something,%edx + and $something,%esi + sub %rsi,%rdx + shr $something,%rdx + and $something,%edx + je + vxorpd %xmm2,%xmm2,%xmm2 + vmovq offset(%rip),%xmm4 # + lea (%rcx,%rdx,8),%rsi + vmovsd %xmm2,%xmm2,%xmm7 + vmovsd (%rax),%xmm0 + add $something,%rax + vmovsd %xmm0,%xmm0,%xmm1 + vxorpd %xmm4,%xmm0,%xmm3 + vcmpnltsd %xmm0,%xmm2,%xmm0 + vblendvpd %xmm0,%xmm3,%xmm1,%xmm0 + vaddsd %xmm0,%xmm7,%xmm7 + cmp %rax,%rsi + jne + sub %rdx,%rdi + mov %rdi,%rsi + mov %rdi,%r8 + lea (%rcx,%rdx,8),%rcx + and $something,%rsi + xor %r8b,%r8b + cmp $something,%rdi + jle + test %r8,%r8 + je + vxorpd %xmm3,%xmm3,%xmm3 + vpbroadcastq offset(%rip),%ymm0 # + mov %rcx,%rax + lea (%rcx,%r8,8),%rdx + vmovapd %ymm3,%ymm4 + vmovapd %ymm3,%ymm5 + vmovapd %ymm3,%ymm1 + nopl offset(%rax) + vpand (%rax),%ymm0,%ymm6 + sub $something,%rax + vaddpd %ymm6,%ymm1,%ymm1 + vpand -offset(%rax),%ymm0,%ymm6 + vaddpd %ymm6,%ymm5,%ymm5 + vpand -offset(%rax),%ymm0,%ymm6 /usr/lib64/libopenblas_openmp.a/dasum_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dasum_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dasum_k_COOPERLAKE.o (objdump) @@ -2,65 +2,68 @@ /usr/lib64/libopenblas_openmp.a/dasum_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 4889f148 85ff0f8e 34020000 4885d20f H..H....4...H... - 0010 8e2b0200 004883fa 01744d48 0faffac5 .+...H...tMH.... - 0020 f157c9c5 fa7e2d00 000000c5 f310f931 .W...~-........1 - 0030 c00f1f80 00000000 c5fb1004 c14801d0 .............H.. - 0040 c5fb10d0 c5f957dd c5f3c2c0 05c4e369 ......W........i - 0050 4bc300c5 c358f848 39c77fdc c5c310c7 K....X.H9....... - 0060 c30f1f80 00000000 4889fa48 83e2f80f ........H..H.... - 0070 84d40100 00c57a7e 2d000000 00c5f157 ......z~-......W - 0080 c94889f0 c57310d9 31f6c573 10e1c5f3 .H...s..1..s.... - 0090 10e9c5f3 10f962c1 fd0828e5 62c1fd08 ......b...(.b... - 00a0 28dd62c1 fd0828d5 62c1fd08 28cd62c1 (.b...(.b...(.b. - 00b0 fd0828c5 62c1fd08 28fd6241 fd0828c5 ..(.b...(.bA..(. - 00c0 c5fb1020 c5fb1058 08c5db10 c4c4c159 ... ...X.......Y - 00d0 57d5c5f3 c2e405c5 7b105020 c57b1048 W.......{.P .{.H - 00e0 28c4e379 4be240c5 e310c362 b1e50857 (..yK.@....b...W - 00f0 d4c5f3c2 db05c5db 58ff4883 c608c4e3 ........X.H..... - 0100 794bda30 c5fb1050 10c5e358 edc5eb10 yK.0...P...X.... - 0110 c262b1ed 0857f3c5 f3c2d205 4883c040 .b...W......H..@ - 0120 c4e3794b d620c5fb 1040d8c4 416b58e4 ..yK. ...@..AkX. - 0130 c5fb10f0 6231fd08 57c2c5f3 c2c005c4 ....b1..W....... - 0140 c3494bc0 00c52b11 d66231ad 0857c1c4 .IK...+..b1..W.. - 0150 4173c2d2 05c52358 d8c44349 4bd0a0c5 As....#X..CIK... - 0160 3311ce62 31b50857 c0c44173 c2c905c4 3..b1..W..As.... - 0170 c14358fa c443494b c890c57b 1040f0c4 .CX..CIK...{.@.. - 0180 c15358e9 c53b11c6 62a1bd08 57efc441 .SX..;..b...W..A - 0190 73c2c005 6231d700 10f5c443 494bc680 s...b1.....CIK.. - 01a0 c5fb1070 f8c4411b 58e062e1 cf0810ee ...p..A.X.b..... - 01b0 6281cd08 57f0c5f3 c2f60562 31d70010 b...W......b1... - 01c0 f56231cf 0010fec4 c3094bf7 60c52358 .b1.......K.`.#X - 01d0 de4839f2 0f8fe6fe ffffc5c3 58fd48ff .H9.........X.H. - 01e0 ca48c1ea 03c4c143 58fc488d 14d50800 .H.....CX.H..... - 01f0 0000c4c1 4358fb48 39d77e57 c5fa7e2d ....CX.H9.~W..~- - 0200 00000000 c5f310c1 0f1f8400 00000000 ................ - 0210 c5fb1014 d148ffc2 c5eb10da c5e957e5 .....H........W. - 0220 c5f3c2d2 05c4e361 4bd420c5 fb58c248 .......aK. ..X.H - 0230 39d77fdc c5fb58ff c5c310c7 c30f1f00 9.....X......... - 0240 c5c157ff c5c310c7 c3c5f157 c9c5f310 ..W........W.... - 0250 f9eba9c5 f310c1eb db0f1f80 00000000 ................ - 0260 4889ce4c 89c2e895 fdffff48 8b442410 H..L.......H.D$. - 0270 c5fb1100 31c0c366 0f1f8400 00000000 ....1..f........ - 0280 41564989 f6415549 89d54154 4989fc55 AVI..AUI..ATI..U - 0290 534881ec 20040000 64488b04 25280000 SH.. ...dH..%(.. - 02a0 00488984 24180400 0031c0e8 00000000 .H..$....1...... - 02b0 83f8010f 84e70000 0089c5e8 00000000 ................ - 02c0 85c00f85 d8000000 488b1d00 00000048 ........H......H - 02d0 630b39cd 740a89ef e8000000 0048630b c.9.t........Hc. - 02e0 4981fca0 8601000f 8eb30000 004d85ed I............M.. - 02f0 0f8eaa00 00004c89 e048ba09 e1d1c611 ......L..H...... - 0300 6bf12948 f7ea4c89 e048c1f8 3f48c1fa k.)H..L..H..?H.. - 0310 0e4829c2 4839ca48 0f4eca48 89cd4883 .H).H9.H.N.H..H. - 0320 f901747c 4883ec08 51488d05 30ffffff ..t|H...QH..0... - 0330 4d89f150 31c931d2 6a004c89 e6bf0300 M..P1.1.j.L..... - 0340 0000488d 5c243053 6a006a00 41554c8d ..H.\$0Sj.j.AUL. - 0350 442448e8 00000000 4883c440 4885ed7e D$H.....H..@H..~ - 0360 6f48c1e5 04488d14 2b4889d8 c5f957c0 oH...H..+H....W. - 0370 c5fb5800 4883c010 4839d075 f3488b84 ..X.H...H9.u.H.. - 0380 24180400 0064482b 04252800 00007546 $....dH+.%(...uF - 0390 4881c420 0400005b 5d415c41 5d415ec3 H.. ...[]A\A]A^. - 03a0 488b8424 18040000 64482b04 25280000 H..$....dH+.%(.. - 03b0 00752348 81c42004 00005b5d 4c89e741 .u#H.. ...[]L..A - 03c0 5c4c89ea 415d4c89 f6415ee9 30fcffff \L..A]L..A^.0... - 03d0 c5f957c0 eba7e800 000000 ..W........ + 0000 4889f148 85ff0f8e c4000000 4885d20f H..H........H... + 0010 8ebb0000 004883fa 01744d48 0faffac5 .....H...tMH.... + 0020 e957d2c5 fa7e2d00 00000048 89fec5eb .W...~-....H.... + 0030 10fa31c0 0f1f4000 c5fb1004 c14801d0 ..1...@......H.. + 0040 c5fb10d8 c5f957e5 c5ebc2c0 05c4e361 ......W........a + 0050 4bc400c5 c358f848 39c67fdc c5c310c7 K....X.H9....... + 0060 c30f1f80 00000000 4881ffff 0000007f ........H....... + 0070 6f4889fe 4883e6f8 4883ff07 0f8fef01 oH..H...H....... + 0080 0000c5e9 57d2c5eb 10fa4839 fe7dcdc5 ....W.....H9.}.. + 0090 fa7e2d00 00000048 8d04f148 8d14f990 .~-....H...H.... + 00a0 c5fb1000 4883c008 c5fb10d8 c5f957e5 ....H.........W. + 00b0 c5ebc2c0 05c4e361 4bc400c5 c358f848 .......aK....X.H + 00c0 39c275dc c5c310c7 c30f1f80 00000000 9.u............. + 00d0 c5c157ff c5c310c7 c30f1f80 00000000 ..W............. + 00e0 4889f0ba 20000000 83e61f48 29f248c1 H... ......H).H. + 00f0 ea0383e2 030f845a 010000c5 e957d2c5 .......Z.....W.. + 0100 fa7e2500 00000048 8d34d1c5 eb10fac5 .~%....H.4...... + 0110 fb100048 83c008c5 fb10c8c5 f957dcc5 ...H.........W.. + 0120 ebc2c005 c4e3714b c300c5c3 58f84839 ......qK....X.H9 + 0130 c675dc48 29d74889 fe4989f8 488d0cd1 .u.H).H..I..H... + 0140 4883e6f8 4530c048 81ffff00 00007e7e H...E0.H......~~ + 0150 4d85c00f 840f0100 00c5e157 dbc4e27d M..........W...} + 0160 59050000 00004889 c84a8d14 c1c5fd28 Y.....H..J.....( + 0170 e3c5fd28 ebc5fd28 cb0f1f80 00000000 ...(...(........ + 0180 c5fddb30 4883e880 c5f558ce c5fddb70 ...0H.....X....p + 0190 a0c5d558 eec5fddb 70c0c5dd 58e6c5fd ...X....p...X... + 01a0 db70e0c5 e558de48 39c275d4 c5f558c5 .p...X.H9.u...X. + 01b0 c5fd58c4 c5fd58c3 62f3fd28 19c101c5 ..X...X.b..(.... + 01c0 f158c0c5 f97cc0c5 c358f8c5 f8774939 .X...|...X...wI9 + 01d0 f00f8d8b 00000048 8d56ff4c 29c24883 .......H.V.L).H. + 01e0 e2f8c5e1 57db4c01 c2c4e279 590d0000 ....W.L....yY... + 01f0 00004a8d 04c1488d 54d140c5 f928e3c5 ..J...H.T.@..(.. + 0200 f928ebc5 f928c366 0f1f8400 00000000 .(...(.f........ + 0210 c5f1db30 4883c040 c5f958c6 c5f1db70 ...0H..@..X....p + 0220 d0c5d158 eec5f1db 70e0c5d9 58e6c5f1 ...X....p...X... + 0230 db70f0c5 e158de48 39c275d4 c5f958c5 .p...X.H9.u...X. + 0240 c5f958c4 c5f958c3 c5f97cc0 c5fb58ff ..X...X...|...X. + 0250 e935feff ffc5e957 d2c5eb10 fae9d1fe .5.....W........ + 0260 ffffc5f9 57c0ebe0 c5f957c0 e947ffff ....W.....W..G.. + 0270 ffc5e957 d24531c0 c5eb10fa e94dffff ...W.E1......M.. + 0280 ff66662e 0f1f8400 00000000 0f1f4000 .ff...........@. + 0290 4883ec08 4889ce4c 89c2e861 fdffff48 H...H..L...a...H + 02a0 8b442418 c5fb1100 31c04883 c408c390 .D$.....1.H..... + 02b0 41564989 f6415549 89d54154 4989fc55 AVI..AUI..ATI..U + 02c0 534881ec 20040000 64488b04 25280000 SH.. ...dH..%(.. + 02d0 00488984 24180400 0031c0e8 00000000 .H..$....1...... + 02e0 83f8010f 84e70000 0089c5e8 00000000 ................ + 02f0 85c00f85 d8000000 488b1d00 00000048 ........H......H + 0300 630b39cd 740a89ef e8000000 0048630b c.9.t........Hc. + 0310 4981fca0 8601000f 8eb30000 004d85ed I............M.. + 0320 0f8eaa00 00004c89 e048ba09 e1d1c611 ......L..H...... + 0330 6bf12948 f7ea4c89 e048c1f8 3f48c1fa k.)H..L..H..?H.. + 0340 0e4829c2 4839ca48 0f4eca48 89cd4883 .H).H9.H.N.H..H. + 0350 f901747c 4883ec08 51488d05 30ffffff ..t|H...QH..0... + 0360 4d89f150 31c931d2 6a004c89 e6bf0300 M..P1.1.j.L..... + 0370 0000488d 5c243053 6a006a00 41554c8d ..H.\$0Sj.j.AUL. + 0380 442448e8 00000000 4883c440 4885ed7e D$H.....H..@H..~ + 0390 6f48c1e5 04488d14 2b4889d8 c5f957c0 oH...H..+H....W. + 03a0 c5fb5800 4883c010 4839d075 f3488b84 ..X.H...H9.u.H.. + 03b0 24180400 0064482b 04252800 00007546 $....dH+.%(...uF + 03c0 4881c420 0400005b 5d415c41 5d415ec3 H.. ...[]A\A]A^. + 03d0 488b8424 18040000 64482b04 25280000 H..$....dH+.%(.. + 03e0 00752348 81c42004 00005b5d 4c89e741 .u#H.. ...[]L..A + 03f0 5c4c89ea 415d4c89 f6415ee9 00fcffff \L..A]L..A^..... + 0400 c5f957c0 eba7e800 000000 ..W........ ELF section: pipe command #0 failed with 1 for old//usr/lib64/libopenblas_openmp.a/dasum_k_COOPERLAKE.o /usr/lib64/libopenblas_openmp.a/dasum_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dasum_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dasum_k_SKYLAKEX.o (disasm) @@ -16,7 +16,7 @@ vxorpd %xmm2,%xmm2,%xmm2 vmovq offset(%rip),%xmm5 # mov %rdi,%rsi - vmovsd %xmm2,%xmm2,%xmm1 + vmovsd %xmm2,%xmm2,%xmm7 xor %eax,%eax nopl offset(%rax) vmovsd (%rcx,%rax,8),%xmm0 @@ -25,10 +25,10 @@ vxorpd %xmm5,%xmm0,%xmm4 vcmpnltsd %xmm0,%xmm2,%xmm0 vblendvpd %xmm0,%xmm4,%xmm3,%xmm0 - vaddsd %xmm0,%xmm1,%xmm1 + vaddsd %xmm0,%xmm7,%xmm7 cmp %rax,%rsi jg - vmovsd %xmm1,%xmm1,%xmm0 + vmovsd %xmm7,%xmm7,%xmm0 ret nopl offset(%rax) cmp $something,%rdi @@ -38,7 +38,7 @@ cmp $something,%rdi jg vxorpd %xmm2,%xmm2,%xmm2 - vmovsd %xmm2,%xmm2,%xmm1 + vmovsd %xmm2,%xmm2,%xmm7 cmp %rdi,%rsi jge vmovq offset(%rip),%xmm5 # @@ -51,14 +51,14 @@ vxorpd %xmm5,%xmm0,%xmm4 vcmpnltsd %xmm0,%xmm2,%xmm0 vblendvpd %xmm0,%xmm4,%xmm3,%xmm0 - vaddsd %xmm0,%xmm1,%xmm1 + vaddsd %xmm0,%xmm7,%xmm7 cmp %rax,%rdx jne - vmovsd %xmm1,%xmm1,%xmm0 + vmovsd %xmm7,%xmm7,%xmm0 ret nopl offset(%rax) - vxorpd %xmm1,%xmm1,%xmm1 - vmovsd %xmm1,%xmm1,%xmm0 + vxorpd %xmm7,%xmm7,%xmm7 + vmovsd %xmm7,%xmm7,%xmm0 ret nopl offset(%rax) mov %rsi,%rax @@ -69,17 +69,16 @@ and $something,%edx je vxorpd %xmm2,%xmm2,%xmm2 - vmovq offset(%rip),%xmm5 # + vmovq offset(%rip),%xmm4 # lea (%rcx,%rdx,8),%rsi - vmovsd %xmm2,%xmm2,%xmm3 - nop + vmovsd %xmm2,%xmm2,%xmm7 vmovsd (%rax),%xmm0 add $something,%rax vmovsd %xmm0,%xmm0,%xmm1 - vxorpd %xmm5,%xmm0,%xmm4 + vxorpd %xmm4,%xmm0,%xmm3 vcmpnltsd %xmm0,%xmm2,%xmm0 - vblendvpd %xmm0,%xmm4,%xmm1,%xmm0 - vaddsd %xmm0,%xmm3,%xmm3 + vblendvpd %xmm0,%xmm3,%xmm1,%xmm0 + vaddsd %xmm0,%xmm7,%xmm7 cmp %rax,%rsi jne sub %rdx,%rdi @@ -92,68 +91,66 @@ jle test %r8,%r8 je - vxorpd %xmm4,%xmm4,%xmm4 - vpbroadcastq offset(%rip),%zmm0 # + vxorpd %xmm3,%xmm3,%xmm3 + vpbroadcastq offset(%rip),%ymm0 # mov %rcx,%rax lea (%rcx,%r8,8),%rdx - vmovapd %zmm4,%zmm5 - vmovapd %zmm4,%zmm6 - vmovapd %zmm4,%zmm1 - nopl (%rax) - vpandq (%rax),%zmm0,%zmm7 - add $something,%rax - vaddpd %zmm7,%zmm1,%zmm1 - vpandq -offset(%rax),%zmm0,%zmm7 - vaddpd %zmm7,%zmm6,%zmm6 - vpandq -offset(%rax),%zmm0,%zmm7 - vaddpd %zmm7,%zmm5,%zmm5 - vpandq -offset(%rax),%zmm0,%zmm7 - vaddpd %zmm7,%zmm4,%zmm4 + vmovapd %ymm3,%ymm4 + vmovapd %ymm3,%ymm5 + vmovapd %ymm3,%ymm1 + nopl offset(%rax) + vpand (%rax),%ymm0,%ymm6 + sub $something,%rax + vaddpd %ymm6,%ymm1,%ymm1 + vpand -offset(%rax),%ymm0,%ymm6 + vaddpd %ymm6,%ymm5,%ymm5 + vpand -offset(%rax),%ymm0,%ymm6 + vaddpd %ymm6,%ymm4,%ymm4 + vpand -offset(%rax),%ymm0,%ymm6 + vaddpd %ymm6,%ymm3,%ymm3 cmp %rax,%rdx jne - vaddpd %zmm6,%zmm1,%zmm0 - vaddpd %zmm5,%zmm0,%zmm0 - vaddpd %zmm4,%zmm0,%zmm0 - vextractf64x4 $something,%zmm0,%ymm1 - vaddpd %ymm0,%ymm1,%ymm1 - vextractf64x2 $something,%ymm1,%xmm0 - vaddpd %xmm1,%xmm0,%xmm0 + vaddpd %ymm5,%ymm1,%ymm0 + vaddpd %ymm4,%ymm0,%ymm0 + vaddpd %ymm3,%ymm0,%ymm0 + vextractf64x2 $something,%ymm0,%xmm1 + vaddpd %xmm0,%xmm1,%xmm0 vhaddpd %xmm0,%xmm0,%xmm0 - vaddsd %xmm0,%xmm3,%xmm3 + vaddsd %xmm0,%xmm7,%xmm7 vzeroupper cmp %rsi,%r8 jge lea -offset(%rsi),%rdx sub %r8,%rdx and $something,%rdx - vxorpd %xmm4,%xmm4,%xmm4 + vxorpd %xmm3,%xmm3,%xmm3 add %r8,%rdx vpbroadcastq offset(%rip),%xmm1 # lea (%rcx,%r8,8),%rax lea offset(%rcx,%rdx,8),%rdx - vmovapd %xmm4,%xmm5 - vmovapd %xmm4,%xmm6 - vmovapd %xmm4,%xmm0 + vmovapd %xmm3,%xmm4 + vmovapd %xmm3,%xmm5 + vmovapd %xmm3,%xmm0 nopw offset(%rax,%rax,1) - vpand (%rax),%xmm1,%xmm7 + vpand (%rax),%xmm1,%xmm6 add $something,%rax - vaddpd %xmm7,%xmm0,%xmm0 - vpand -offset(%rax),%xmm1,%xmm7 - vaddpd %xmm7,%xmm6,%xmm6 - vpand -offset(%rax),%xmm1,%xmm7 - vaddpd %xmm7,%xmm5,%xmm5 - vpand -offset(%rax),%xmm1,%xmm7 - vaddpd %xmm7,%xmm4,%xmm4 + vaddpd %xmm6,%xmm0,%xmm0 + vpand -offset(%rax),%xmm1,%xmm6 + vaddpd %xmm6,%xmm5,%xmm5 + vpand -offset(%rax),%xmm1,%xmm6 + vaddpd %xmm6,%xmm4,%xmm4 + vpand -offset(%rax),%xmm1,%xmm6 + vaddpd %xmm6,%xmm3,%xmm3 cmp %rax,%rdx jne - vaddpd %xmm6,%xmm0,%xmm0 vaddpd %xmm5,%xmm0,%xmm0 vaddpd %xmm4,%xmm0,%xmm0 + vaddpd %xmm3,%xmm0,%xmm0 vhaddpd %xmm0,%xmm0,%xmm0 - vaddsd %xmm3,%xmm0,%xmm1 + vaddsd %xmm7,%xmm0,%xmm7 jmp vxorpd %xmm2,%xmm2,%xmm2 - vmovsd %xmm2,%xmm2,%xmm3 + vmovsd %xmm2,%xmm2,%xmm7 jmp vxorpd %xmm0,%xmm0,%xmm0 jmp @@ -161,8 +158,9 @@ jmp vxorpd %xmm2,%xmm2,%xmm2 xor %r8d,%r8d - vmovsd %xmm2,%xmm2,%xmm3 + vmovsd %xmm2,%xmm2,%xmm7 jmp + data16 cs nopw offset(%rax,%rax,1) nopl offset(%rax) asum_thread_function: /usr/lib64/libopenblas_openmp.a/dasum_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dasum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dasum_k_SKYLAKEX.o (objdump) @@ -5,67 +5,65 @@ 0000 4889f148 85ff0f8e c4000000 4885d20f H..H........H... 0010 8ebb0000 004883fa 01744d48 0faffac5 .....H...tMH.... 0020 e957d2c5 fa7e2d00 00000048 89fec5eb .W...~-....H.... - 0030 10ca31c0 0f1f4000 c5fb1004 c14801d0 ..1...@......H.. + 0030 10fa31c0 0f1f4000 c5fb1004 c14801d0 ..1...@......H.. 0040 c5fb10d8 c5f957e5 c5ebc2c0 05c4e361 ......W........a - 0050 4bc400c5 f358c848 39c67fdc c5f310c1 K....X.H9....... + 0050 4bc400c5 c358f848 39c67fdc c5c310c7 K....X.H9....... 0060 c30f1f80 00000000 4881ffff 0000007f ........H....... - 0070 6f4889fe 4883e6f8 4883ff07 0f8f1702 oH..H...H....... - 0080 0000c5e9 57d2c5eb 10ca4839 fe7dcdc5 ....W.....H9.}.. + 0070 6f4889fe 4883e6f8 4883ff07 0f8fef01 oH..H...H....... + 0080 0000c5e9 57d2c5eb 10fa4839 fe7dcdc5 ....W.....H9.}.. 0090 fa7e2d00 00000048 8d04f148 8d14f990 .~-....H...H.... 00a0 c5fb1000 4883c008 c5fb10d8 c5f957e5 ....H.........W. - 00b0 c5ebc2c0 05c4e361 4bc400c5 f358c848 .......aK....X.H - 00c0 39c275dc c5f310c1 c30f1f80 00000000 9.u............. - 00d0 c5f157c9 c5f310c1 c30f1f80 00000000 ..W............. - 00e0 4889f0ba 40000000 83e63f48 29f248c1 H...@.....?H).H. - 00f0 ea0383e2 070f8482 010000c5 e957d2c5 .............W.. - 0100 fa7e2d00 00000048 8d34d1c5 eb10da90 .~-....H.4...... - 0110 c5fb1000 4883c008 c5fb10c8 c5f957e5 ....H.........W. - 0120 c5ebc2c0 05c4e371 4bc400c5 e358d848 .......qK....X.H - 0130 39c675dc 4829d748 89fe4989 f8488d0c 9.u.H).H..I..H.. - 0140 d14883e6 f84530c0 4881ffff 0000000f .H...E0.H....... - 0150 8ea40000 004d85c0 0f843201 0000c5d9 .....M....2..... - 0160 57e462f2 fd485905 00000000 4889c84a W.b..HY.....H..J - 0170 8d14c162 f1fd4828 ec62f1fd 4828f462 ...b..H(.b..H(.b - 0180 f1fd4828 cc0f1f00 62f1fd48 db384805 ..H(....b..H.8H. - 0190 00010000 62f1f548 58cf62f1 fd48db78 ....b..HX.b..H.x - 01a0 fd62f1cd 4858f762 f1fd48db 78fe62f1 .b..HX.b..H.x.b. - 01b0 d54858ef 62f1fd48 db78ff62 f1dd4858 .HX.b..H.x.b..HX - 01c0 e74839c2 75c262f1 f54858c6 62f1fd48 .H9.u.b..HX.b..H - 01d0 58c562f1 fd4858c4 62f3fd48 1bc101c5 X.b..HX.b..H.... - 01e0 f558c862 f3fd2819 c801c5f9 58c1c5f9 .X.b..(.....X... - 01f0 7cc0c5e3 58d8c5f8 774939f0 0f8d8800 |...X...wI9..... - 0200 0000488d 56ff4c29 c24883e2 f8c5d957 ..H.V.L).H.....W - 0210 e44c01c2 c4e27959 0d000000 004a8d04 .L....yY.....J.. - 0220 c1488d54 d140c5f9 28ecc5f9 28f4c5f9 .H.T.@..(...(... - 0230 28c4660f 1f440000 c5f1db38 4883c040 (.f..D.....8H..@ - 0240 c5f958c7 c5f1db78 d0c5c958 f7c5f1db ..X....x...X.... - 0250 78e0c5d1 58efc5f1 db78f0c5 d958e748 x...X....x...X.H - 0260 39c275d4 c5f958c6 c5f958c5 c5f958c4 9.u...X...X...X. - 0270 c5f97cc0 c5fb58cb e90dfeff ffc5e957 ..|...X........W - 0280 d2c5eb10 dae9aafe ffffc5f9 57c0ebe0 ............W... - 0290 c5f957c0 e93fffff ffc5e957 d24531c0 ..W..?.....W.E1. - 02a0 c5eb10da e950ffff ff0f1f80 00000000 .....P.......... - 02b0 4883ec08 4889ce4c 89c2e841 fdffff48 H...H..L...A...H - 02c0 8b442418 c5fb1100 31c04883 c408c390 .D$.....1.H..... - 02d0 41564989 f6415549 89d54154 4989fc55 AVI..AUI..ATI..U - 02e0 534881ec 20040000 64488b04 25280000 SH.. ...dH..%(.. - 02f0 00488984 24180400 0031c0e8 00000000 .H..$....1...... - 0300 83f8010f 84e70000 0089c5e8 00000000 ................ - 0310 85c00f85 d8000000 488b1d00 00000048 ........H......H - 0320 630b39cd 740a89ef e8000000 0048630b c.9.t........Hc. - 0330 4981fca0 8601000f 8eb30000 004d85ed I............M.. - 0340 0f8eaa00 00004c89 e048ba09 e1d1c611 ......L..H...... - 0350 6bf12948 f7ea4c89 e048c1f8 3f48c1fa k.)H..L..H..?H.. - 0360 0e4829c2 4839ca48 0f4eca48 89cd4883 .H).H9.H.N.H..H. - 0370 f901747c 4883ec08 51488d05 30ffffff ..t|H...QH..0... - 0380 4d89f150 31c931d2 6a004c89 e6bf0300 M..P1.1.j.L..... - 0390 0000488d 5c243053 6a006a00 41554c8d ..H.\$0Sj.j.AUL. - 03a0 442448e8 00000000 4883c440 4885ed7e D$H.....H..@H..~ - 03b0 6f48c1e5 04488d14 2b4889d8 c5f957c0 oH...H..+H....W. - 03c0 c5fb5800 4883c010 4839d075 f3488b84 ..X.H...H9.u.H.. - 03d0 24180400 0064482b 04252800 00007546 $....dH+.%(...uF - 03e0 4881c420 0400005b 5d415c41 5d415ec3 H.. ...[]A\A]A^. - 03f0 488b8424 18040000 64482b04 25280000 H..$....dH+.%(.. - 0400 00752348 81c42004 00005b5d 4c89e741 .u#H.. ...[]L..A - 0410 5c4c89ea 415d4c89 f6415ee9 e0fbffff \L..A]L..A^..... - 0420 c5f957c0 eba7e800 000000 ..W........ + 00b0 c5ebc2c0 05c4e361 4bc400c5 c358f848 .......aK....X.H + 00c0 39c275dc c5c310c7 c30f1f80 00000000 9.u............. + 00d0 c5c157ff c5c310c7 c30f1f80 00000000 ..W............. + 00e0 4889f0ba 20000000 83e61f48 29f248c1 H... ......H).H. + 00f0 ea0383e2 030f845a 010000c5 e957d2c5 .......Z.....W.. + 0100 fa7e2500 00000048 8d34d1c5 eb10fac5 .~%....H.4...... + 0110 fb100048 83c008c5 fb10c8c5 f957dcc5 ...H.........W.. + 0120 ebc2c005 c4e3714b c300c5c3 58f84839 ......qK....X.H9 + 0130 c675dc48 29d74889 fe4989f8 488d0cd1 .u.H).H..I..H... + 0140 4883e6f8 4530c048 81ffff00 00007e7e H...E0.H......~~ + 0150 4d85c00f 840f0100 00c5e157 dbc4e27d M..........W...} + 0160 59050000 00004889 c84a8d14 c1c5fd28 Y.....H..J.....( + 0170 e3c5fd28 ebc5fd28 cb0f1f80 00000000 ...(...(........ + 0180 c5fddb30 4883e880 c5f558ce c5fddb70 ...0H.....X....p + 0190 a0c5d558 eec5fddb 70c0c5dd 58e6c5fd ...X....p...X... + 01a0 db70e0c5 e558de48 39c275d4 c5f558c5 .p...X.H9.u...X. + 01b0 c5fd58c4 c5fd58c3 62f3fd28 19c101c5 ..X...X.b..(.... + 01c0 f158c0c5 f97cc0c5 c358f8c5 f8774939 .X...|...X...wI9 + 01d0 f00f8d8b 00000048 8d56ff4c 29c24883 .......H.V.L).H. + 01e0 e2f8c5e1 57db4c01 c2c4e279 590d0000 ....W.L....yY... + 01f0 00004a8d 04c1488d 54d140c5 f928e3c5 ..J...H.T.@..(.. + 0200 f928ebc5 f928c366 0f1f8400 00000000 .(...(.f........ + 0210 c5f1db30 4883c040 c5f958c6 c5f1db70 ...0H..@..X....p + 0220 d0c5d158 eec5f1db 70e0c5d9 58e6c5f1 ...X....p...X... + 0230 db70f0c5 e158de48 39c275d4 c5f958c5 .p...X.H9.u...X. + 0240 c5f958c4 c5f958c3 c5f97cc0 c5fb58ff ..X...X...|...X. + 0250 e935feff ffc5e957 d2c5eb10 fae9d1fe .5.....W........ + 0260 ffffc5f9 57c0ebe0 c5f957c0 e947ffff ....W.....W..G.. + 0270 ffc5e957 d24531c0 c5eb10fa e94dffff ...W.E1......M.. + 0280 ff66662e 0f1f8400 00000000 0f1f4000 .ff...........@. + 0290 4883ec08 4889ce4c 89c2e861 fdffff48 H...H..L...a...H + 02a0 8b442418 c5fb1100 31c04883 c408c390 .D$.....1.H..... + 02b0 41564989 f6415549 89d54154 4989fc55 AVI..AUI..ATI..U + 02c0 534881ec 20040000 64488b04 25280000 SH.. ...dH..%(.. + 02d0 00488984 24180400 0031c0e8 00000000 .H..$....1...... + 02e0 83f8010f 84e70000 0089c5e8 00000000 ................ + 02f0 85c00f85 d8000000 488b1d00 00000048 ........H......H + 0300 630b39cd 740a89ef e8000000 0048630b c.9.t........Hc. + 0310 4981fca0 8601000f 8eb30000 004d85ed I............M.. + 0320 0f8eaa00 00004c89 e048ba09 e1d1c611 ......L..H...... + 0330 6bf12948 f7ea4c89 e048c1f8 3f48c1fa k.)H..L..H..?H.. + 0340 0e4829c2 4839ca48 0f4eca48 89cd4883 .H).H9.H.N.H..H. + 0350 f901747c 4883ec08 51488d05 30ffffff ..t|H...QH..0... + 0360 4d89f150 31c931d2 6a004c89 e6bf0300 M..P1.1.j.L..... + 0370 0000488d 5c243053 6a006a00 41554c8d ..H.\$0Sj.j.AUL. + 0380 442448e8 00000000 4883c440 4885ed7e D$H.....H..@H..~ + 0390 6f48c1e5 04488d14 2b4889d8 c5f957c0 oH...H..+H....W. + 03a0 c5fb5800 4883c010 4839d075 f3488b84 ..X.H...H9.u.H.. + 03b0 24180400 0064482b 04252800 00007546 $....dH+.%(...uF + 03c0 4881c420 0400005b 5d415c41 5d415ec3 H.. ...[]A\A]A^. + 03d0 488b8424 18040000 64482b04 25280000 H..$....dH+.%(.. + 03e0 00752348 81c42004 00005b5d 4c89e741 .u#H.. ...[]L..A + 03f0 5c4c89ea 415d4c89 f6415ee9 00fcffff \L..A]L..A^..... + 0400 c5f957c0 eba7e800 000000 ..W........ /usr/lib64/libopenblas_openmp.a/dasum_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dasum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dasum_k_SKYLAKEX.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 10000000 1c000000 ................ - 0020 00000000 a9020000 00000000 14000000 ................ + 0020 00000000 81020000 00000000 14000000 ................ 0030 30000000 00000000 1f000000 00440e10 0............D.. 0040 5a0e0800 80000000 48000000 00000000 Z.......H....... 0050 5b010000 00420e10 8e02450e 188d0345 [....B....E....E /usr/lib64/libopenblas_openmp.a/daxpy_k_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/daxpy_k_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/daxpy_k_COOPERLAKE.o (disasm) @@ -4,70 +4,93 @@ Disassembly of section .text: +daxpy_kernel_8: + xor %eax,%eax + vbroadcastsd (%rcx),%ymm0 + nopw offset(%rax,%rax,1) + vmovups (%rdx,%rax,8),%ymm12 + vmovups offset(%rdx,%rax,8),%ymm13 + vmovups offset(%rdx,%rax,8),%ymm14 + vmovups offset(%rdx,%rax,8),%ymm15 + vfmadd231pd (%rsi,%rax,8),%ymm0,%ymm12 + vfmadd231pd offset(%rsi,%rax,8),%ymm0,%ymm13 + vfmadd231pd offset(%rsi,%rax,8),%ymm0,%ymm14 + vfmadd231pd offset(%rsi,%rax,8),%ymm0,%ymm15 + vmovups %ymm12,(%rdx,%rax,8) + vmovups %ymm13,offset(%rdx,%rax,8) + vmovups %ymm14,offset(%rdx,%rax,8) + vmovups %ymm15,offset(%rdx,%rax,8) + add $something,%rax + sub $something,%rdi + jne + vzeroupper + vzeroupper + ret + nopw offset(%rax,%rax,1) + daxpy_k_COOPERLAKE: - push %rbp - mov %rsp,%rbp push %r15 push %r14 push %r13 push %r12 + push %rbp push %rbx - and $something,%rsp - mov offset(%rbp),%rsi + sub $something,%rsp + mov offset(%rsp),%rsi + vmovsd %xmm0,(%rsp) test %rdi,%rdi jle mov %rdi,%r10 - mov %rcx,%rbx + mov %rcx,%rbp cmp $something,%r8 jne cmp $something,%rsi jne - mov %rdi,%rax - and $something,%rax + mov %rdi,%r8 + and $something,%r8 jne + vmovsd (%rsp),%xmm1 nopl offset(%rax) - vmovsd (%rbx,%rax,8),%xmm1 - vfmadd213sd (%r9,%rax,8),%xmm0,%xmm1 - vmovsd %xmm1,(%r9,%rax,8) - inc %rax - cmp %rax,%r10 + vmovsd offset(%rbp,%r8,8),%xmm0 + vfmadd213sd (%r9,%r8,8),%xmm1,%xmm0 + vmovsd %xmm0,(%r9,%r8,8) + inc %r8 + cmp %r8,%r10 jg - lea -offset(%rbp),%rsp - xor %eax,%eax + add $something,%rsp pop %rbx + pop %rbp pop %r12 pop %r13 pop %r14 + xor %eax,%eax pop %r15 - pop %rbp ret - nopw offset(%rax,%rax,1) + nopl offset(%rax) mov %r10,%rcx + vmovsd (%rsp),%xmm0 and $something,%rcx je lea offset(,%r8,4),%rax + lea (%r8,%r8,1),%r12 + lea (%rsi,%rsi,1),%r11 + mov %r8,%r14 + mov %rsi,%r13 kmovq %rax,%k0 lea offset(,%rsi,4),%rax kmovq %rax,%k1 - mov %rsi,%rax - shl $something,%rax - mov %rax,-offset(%rsp) - mov %r10,-offset(%rsp) - lea (%r8,%r8,1),%r13 - lea (%rsi,%rsi,1),%r11 - mov %r8,%r14 - mov -offset(%rsp),%r10 - lea offset(%r13,%r8,1),%r15 - lea (%r11,%rsi,1),%r12 + lea (%r12,%r8,1),%r15 + lea (%r11,%rsi,1),%rbx shl $something,%r14 - mov %rbx,%rdx + mov %rbp,%rdx + shl $something,%r13 mov %r9,%rax xor %edi,%edi - nopl (%rax) + nopw offset(%rax,%rax,1) vmovsd (%rdx),%xmm4 vmovsd (%rdx,%r8,8),%xmm3 vfmadd213sd (%rax),%xmm0,%xmm4 - vmovsd (%rdx,%r13,8),%xmm2 + vmovsd (%rdx,%r12,8),%xmm2 vmovsd (%rdx,%r15,8),%xmm1 add $something,%rdi add %r14,%rdx @@ -76,15 +99,14 @@ vmovsd %xmm3,(%rax,%rsi,8) vfmadd213sd (%rax,%r11,8),%xmm0,%xmm2 vmovsd %xmm2,(%rax,%r11,8) - vfmadd213sd (%rax,%r12,8),%xmm0,%xmm1 - vmovsd %xmm1,(%rax,%r12,8) - add %r10,%rax + vfmadd213sd (%rax,%rbx,8),%xmm0,%xmm1 + vmovsd %xmm1,(%rax,%rbx,8) + add %r13,%rax cmp %rdi,%rcx jg dec %rcx shr $something,%rcx inc %rcx - mov -offset(%rsp),%r10 kmovq %k0,%rdx kmovq %k1,%rax imul %rcx,%rdx @@ -95,8 +117,8 @@ shl $something,%rsi lea (%r9,%rax,8),%rax shl $something,%r8 - lea (%rbx,%rdx,8),%rdx - nop + lea offset(%rbp,%rdx,8),%rdx + nopw offset(%rax,%rax,1) vmovsd (%rdx),%xmm1 inc %rcx vfmadd213sd (%rax),%xmm0,%xmm1 @@ -106,64 +128,15 @@ cmp %rcx,%r10 jg jmp - mov %rdi,%rcx - vbroadcastsd %xmm0,%ymm1 - vbroadcastsd %xmm0,%zmm2 - and $something,%rcx - je - dec %rcx - shr $something,%rcx - mov %rcx,%rdi - shl $something,%rdi + mov %rsp,%rcx mov %r9,%rdx - mov %rbx,%rsi - lea offset(%r9,%rdi,1),%rdi - nopl offset(%rax) - vmovupd (%rsi),%zmm3 - add $something,%rdx - vfmadd213pd -offset(%rdx),%zmm2,%zmm3 - add $something,%rsi - vmovupd %zmm3,-offset(%rdx) - vmovupd -offset(%rsi),%zmm3 - vfmadd213pd -offset(%rdx),%zmm2,%zmm3 - vmovupd %zmm3,-offset(%rdx) - vmovupd -offset(%rsi),%zmm3 - vfmadd213pd -offset(%rdx),%zmm2,%zmm3 - vmovupd %zmm3,-offset(%rdx) - vmovupd -offset(%rsi),%zmm3 - vfmadd213pd -offset(%rdx),%zmm2,%zmm3 - vmovupd %zmm3,-offset(%rdx) - cmp %rdx,%rdi - jne - inc %rcx - shl $something,%rcx - cmp %rcx,%rax - jle - lea (%r9,%rcx,8),%rdx - xchg %ax,%ax - vmovupd (%rbx,%rcx,8),%ymm2 - sub $something,%rdx - vfmadd213pd -offset(%rdx),%ymm1,%ymm2 - vmovupd %ymm2,-offset(%rdx) - vmovupd offset(%rbx,%rcx,8),%ymm2 /usr/lib64/libopenblas_openmp.a/daxpy_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/daxpy_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/daxpy_k_COOPERLAKE.o (objdump) @@ -2,46 +2,37 @@ /usr/lib64/libopenblas_openmp.a/daxpy_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 554889e5 41574156 41554154 534883e4 UH..AWAVAUATSH.. - 0010 c0488b75 104885ff 7e3f4989 fa4889cb .H.u.H..~?I..H.. - 0020 4983f801 754a4883 fe017544 4889f848 I...uJH...uDH..H - 0030 83e0f00f 85470100 000f1f80 00000000 .....G.......... - 0040 c5fb100c c3c4c2f9 a90cc1c4 c17b110c .............{.. - 0050 c148ffc0 4939c27f e7488d65 d831c05b .H..I9...H.e.1.[ - 0060 415c415d 415e415f 5dc3660f 1f440000 A\A]A^A_].f..D.. - 0070 4c89d148 83e1fc0f 84130200 004a8d04 L..H.........J.. - 0080 85000000 00c4e1fb 92c0488d 04b50000 ..........H..... - 0090 0000c4e1 fb92c848 89f048c1 e0054889 .......H..H...H. - 00a0 4424f84c 895424f0 4f8d2c00 4c8d1c36 D$.L.T$.O.,.L..6 - 00b0 4d89c64c 8b5424f8 4f8d7c05 004d8d24 M..L.T$.O.|..M.$ - 00c0 3349c1e6 054889da 4c89c831 ff0f1f00 3I...H..L..1.... - 00d0 c5fb1022 c4a17b10 1cc2c4e2 f9a920c4 ..."..{....... . - 00e0 a17b1014 eac4a17b 100cfa48 83c7044c .{.....{...H...L - 00f0 01f2c5fb 1120c4e2 f9a91cf0 c5fb111c ..... .......... - 0100 f0c4a2f9 a914d8c4 a17b1114 d8c4a2f9 .........{...... - 0110 a90ce0c4 a17b110c e04c01d0 4839f97f .....{...L..H9.. - 0120 af48ffc9 48c1e902 48ffc14c 8b5424f0 .H..H...H..L.T$. - 0130 c4e1fb93 d0c4e1fb 93c1480f afd1480f ..........H...H. - 0140 afc148c1 e1024939 ca0f8e0a ffffff48 ..H...I9.......H - 0150 c1e60349 8d04c149 c1e00348 8d14d390 ...I...I...H.... - 0160 c5fb100a 48ffc1c4 e2f9a908 4c01c2c5 ....H.......L... - 0170 fb110848 01f04939 ca7fe5e9 d9feffff ...H..I9........ - 0180 4889f9c4 e27d19c8 62f2fd48 19d04883 H....}..b..H..H. - 0190 e1e00f84 92000000 48ffc948 c1e90548 ........H..H...H - 01a0 89cf48c1 e7084c89 ca4889de 498dbc39 ..H...L..H..I..9 - 01b0 00010000 0f1f4000 62f1fd48 101e4881 ......@.b..H..H. - 01c0 c2000100 0062f2ed 48a85afc 4881c600 .....b..H.Z.H... - 01d0 01000062 f1fd4811 5afc62f1 fd48105e ...b..H.Z.b..H.^ - 01e0 fd62f2ed 48a85afd 62f1fd48 115afd62 .b..H.Z.b..H.Z.b - 01f0 f1fd4810 5efe62f2 ed48a85a fe62f1fd ..H.^.b..H.Z.b.. - 0200 48115afe 62f1fd48 105eff62 f2ed48a8 H.Z.b..H.^.b..H. - 0210 5aff62f1 fd48115a ff4839d7 759a48ff Z.b..H.Z.H9.u.H. - 0220 c148c1e1 054839c8 7e56498d 14c96690 .H...H9.~VI...f. - 0230 c5fd1014 cb4883ea 80c4e2f5 a85280c5 .....H.......R.. - 0240 fd115280 c5fd1054 cb20c4e2 f5a852a0 ..R....T. ....R. - 0250 c5fd1152 a0c5fd10 54cb40c4 e2f5a852 ...R....T.@....R - 0260 c0c5fd11 52c0c5fd 1054cb60 4883c110 ....R....T.`H... - 0270 c4e2f5a8 52e0c5fd 1152e048 39c87fb0 ....R....R.H9... - 0280 4939c27e 14c5f877 e9b3fdff ff0f1f00 I9.~...w........ - 0290 31c031d2 e9b6feff ffc5f877 e9b8fdff 1.1........w.... - 02a0 ff . + 0000 31c0c4e2 7d190166 0f1f8400 00000000 1...}..f........ + 0010 c57c1024 c2c57c10 6cc220c5 7c1074c2 .|.$..|.l. .|.t. + 0020 40c57c10 7cc260c4 62fdb824 c6c462fd @.|.|.`.b..$..b. + 0030 b86cc620 c462fdb8 74c640c4 62fdb87c .l. .b..t.@.b..| + 0040 c660c57c 1124c2c5 7c116cc2 20c57c11 .`.|.$..|.l. .|. + 0050 74c240c5 7c117cc2 604883c0 104883ef t.@.|.|.`H...H.. + 0060 1075adc5 f877c5f8 77c3660f 1f440000 .u...w..w.f..D.. + 0070 41574156 41554154 55534883 ec08488b AWAVAUATUSH...H. + 0080 742440c5 fb110424 4885ff7e 464989fa t$@....$H..~FI.. + 0090 4889cd49 83f80175 4f4883fe 01754949 H..I...uOH...uII + 00a0 89f84983 e0f00f85 44010000 c5fb100c ..I.....D....... + 00b0 240f1f80 00000000 c4a17b10 44c500c4 $.........{.D... + 00c0 82f1a904 c1c4817b 1104c149 ffc04d39 .......{...I..M9 + 00d0 c27fe548 83c4085b 5d415c41 5d415e31 ...H...[]A\A]A^1 + 00e0 c0415fc3 0f1f4000 4c89d1c5 fb100424 .A_...@.L......$ + 00f0 4883e1fc 0f841601 00004a8d 04850000 H.........J..... + 0100 00004f8d 24004c8d 1c364d89 c64989f5 ..O.$.L..6M..I.. + 0110 c4e1fb92 c0488d04 b5000000 00c4e1fb .....H.......... + 0120 92c84f8d 3c04498d 1c3349c1 e6054889 ..O.<.I..3I...H. + 0130 ea49c1e5 054c89c8 31ff660f 1f440000 .I...L..1.f..D.. + 0140 c5fb1022 c4a17b10 1cc2c4e2 f9a920c4 ..."..{....... . + 0150 a17b1014 e2c4a17b 100cfa48 83c7044c .{.....{...H...L + 0160 01f2c5fb 1120c4e2 f9a91cf0 c5fb111c ..... .......... + 0170 f0c4a2f9 a914d8c4 a17b1114 d8c4e2f9 .........{...... + 0180 a90cd8c5 fb110cd8 4c01e848 39f97fb0 ........L..H9... + 0190 48ffc948 c1e90248 ffc1c4e1 fb93d0c4 H..H...H........ + 01a0 e1fb93c1 480fafd1 480fafc1 48c1e102 ....H...H...H... + 01b0 4939ca0f 8e1affff ff48c1e6 03498d04 I9.......H...I.. + 01c0 c149c1e0 03488d54 d500660f 1f440000 .I...H.T..f..D.. + 01d0 c5fb100a 48ffc1c4 e2f9a908 4c01c2c5 ....H.......L... + 01e0 fb110848 01f04939 ca7fe5e9 e3feffff ...H..I9........ + 01f0 4889e14c 89ca4889 ee4c89c7 e8fffdff H..L..H..L...... + 0200 ff4d39c2 0f8fa2fe ffffe9c4 feffff90 .M9............. + 0210 31c031d2 eba3 1.1... /usr/lib64/libopenblas_openmp.a/daxpy_k_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/daxpy_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/daxpy_k_COOPERLAKE.o (objdump) @@ -4,4 +4,4 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0020 010001c0 04000000 19080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/daxpy_k_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/daxpy_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/daxpy_k_COOPERLAKE.o (objdump) @@ -3,7 +3,10 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 2c000000 1c000000 ........,....... - 0020 00000000 a1020000 00410e10 8602430d .........A....C. - 0030 064d8f03 8e048d05 8c068307 02580a0c .M...........X.. - 0040 0708470b 00000000 ..G..... + 0010 1b0c0708 90010000 10000000 1c000000 ................ + 0020 00000000 6a000000 00000000 48000000 ....j.......H... + 0030 30000000 00000000 a6010000 00420e10 0............B.. + 0040 8f02420e 188e0342 0e208d04 420e288c ..B....B. ..B.(. + 0050 05410e30 8606410e 38830744 0e400259 .A.0..A.8..D.@.Y + 0060 0a0e3841 0e30410e 28420e20 420e1842 ..8A.0A.(B. B..B + 0070 0e10440e 08450b00 ..D..E.. /usr/lib64/libopenblas_openmp.a/daxpy_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/daxpy_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/daxpy_k_SKYLAKEX.o (disasm) @@ -4,70 +4,93 @@ Disassembly of section .text: +daxpy_kernel_8: + xor %eax,%eax + vbroadcastsd (%rcx),%ymm0 + nopw offset(%rax,%rax,1) + vmovups (%rdx,%rax,8),%ymm12 + vmovups offset(%rdx,%rax,8),%ymm13 + vmovups offset(%rdx,%rax,8),%ymm14 + vmovups offset(%rdx,%rax,8),%ymm15 + vfmadd231pd (%rsi,%rax,8),%ymm0,%ymm12 + vfmadd231pd offset(%rsi,%rax,8),%ymm0,%ymm13 + vfmadd231pd offset(%rsi,%rax,8),%ymm0,%ymm14 + vfmadd231pd offset(%rsi,%rax,8),%ymm0,%ymm15 + vmovups %ymm12,(%rdx,%rax,8) + vmovups %ymm13,offset(%rdx,%rax,8) + vmovups %ymm14,offset(%rdx,%rax,8) + vmovups %ymm15,offset(%rdx,%rax,8) + add $something,%rax + sub $something,%rdi + jne + vzeroupper + vzeroupper + ret + nopw offset(%rax,%rax,1) + daxpy_k_SKYLAKEX: - push %rbp - mov %rsp,%rbp push %r15 push %r14 push %r13 push %r12 + push %rbp push %rbx - and $something,%rsp - mov offset(%rbp),%rsi + sub $something,%rsp + mov offset(%rsp),%rsi + vmovsd %xmm0,(%rsp) test %rdi,%rdi jle mov %rdi,%r10 - mov %rcx,%rbx + mov %rcx,%rbp cmp $something,%r8 jne cmp $something,%rsi jne - mov %rdi,%rax - and $something,%rax + mov %rdi,%r8 + and $something,%r8 jne + vmovsd (%rsp),%xmm1 nopl offset(%rax) - vmovsd (%rbx,%rax,8),%xmm1 - vfmadd213sd (%r9,%rax,8),%xmm0,%xmm1 - vmovsd %xmm1,(%r9,%rax,8) - inc %rax - cmp %rax,%r10 + vmovsd offset(%rbp,%r8,8),%xmm0 + vfmadd213sd (%r9,%r8,8),%xmm1,%xmm0 + vmovsd %xmm0,(%r9,%r8,8) + inc %r8 + cmp %r8,%r10 jg - lea -offset(%rbp),%rsp - xor %eax,%eax + add $something,%rsp pop %rbx + pop %rbp pop %r12 pop %r13 pop %r14 + xor %eax,%eax pop %r15 - pop %rbp ret - nopw offset(%rax,%rax,1) + nopl offset(%rax) mov %r10,%rcx + vmovsd (%rsp),%xmm0 and $something,%rcx je lea offset(,%r8,4),%rax + lea (%r8,%r8,1),%r12 + lea (%rsi,%rsi,1),%r11 + mov %r8,%r14 + mov %rsi,%r13 kmovq %rax,%k0 lea offset(,%rsi,4),%rax kmovq %rax,%k1 - mov %rsi,%rax - shl $something,%rax - mov %rax,-offset(%rsp) - mov %r10,-offset(%rsp) - lea (%r8,%r8,1),%r13 - lea (%rsi,%rsi,1),%r11 - mov %r8,%r14 - mov -offset(%rsp),%r10 - lea offset(%r13,%r8,1),%r15 - lea (%r11,%rsi,1),%r12 + lea (%r12,%r8,1),%r15 + lea (%r11,%rsi,1),%rbx shl $something,%r14 - mov %rbx,%rdx + mov %rbp,%rdx + shl $something,%r13 mov %r9,%rax xor %edi,%edi - nopl (%rax) + nopw offset(%rax,%rax,1) vmovsd (%rdx),%xmm4 vmovsd (%rdx,%r8,8),%xmm3 vfmadd213sd (%rax),%xmm0,%xmm4 - vmovsd (%rdx,%r13,8),%xmm2 + vmovsd (%rdx,%r12,8),%xmm2 vmovsd (%rdx,%r15,8),%xmm1 add $something,%rdi add %r14,%rdx @@ -76,15 +99,14 @@ vmovsd %xmm3,(%rax,%rsi,8) vfmadd213sd (%rax,%r11,8),%xmm0,%xmm2 vmovsd %xmm2,(%rax,%r11,8) - vfmadd213sd (%rax,%r12,8),%xmm0,%xmm1 - vmovsd %xmm1,(%rax,%r12,8) - add %r10,%rax + vfmadd213sd (%rax,%rbx,8),%xmm0,%xmm1 + vmovsd %xmm1,(%rax,%rbx,8) + add %r13,%rax cmp %rdi,%rcx jg dec %rcx shr $something,%rcx inc %rcx - mov -offset(%rsp),%r10 kmovq %k0,%rdx kmovq %k1,%rax imul %rcx,%rdx @@ -95,8 +117,8 @@ shl $something,%rsi lea (%r9,%rax,8),%rax shl $something,%r8 - lea (%rbx,%rdx,8),%rdx - nop + lea offset(%rbp,%rdx,8),%rdx + nopw offset(%rax,%rax,1) vmovsd (%rdx),%xmm1 inc %rcx vfmadd213sd (%rax),%xmm0,%xmm1 @@ -106,64 +128,15 @@ cmp %rcx,%r10 jg jmp - mov %rdi,%rcx - vbroadcastsd %xmm0,%ymm1 - vbroadcastsd %xmm0,%zmm2 - and $something,%rcx - je - dec %rcx - shr $something,%rcx - mov %rcx,%rdi - shl $something,%rdi + mov %rsp,%rcx mov %r9,%rdx - mov %rbx,%rsi - lea offset(%r9,%rdi,1),%rdi - nopl offset(%rax) - vmovupd (%rsi),%zmm3 - add $something,%rdx - vfmadd213pd -offset(%rdx),%zmm2,%zmm3 - add $something,%rsi - vmovupd %zmm3,-offset(%rdx) - vmovupd -offset(%rsi),%zmm3 - vfmadd213pd -offset(%rdx),%zmm2,%zmm3 - vmovupd %zmm3,-offset(%rdx) - vmovupd -offset(%rsi),%zmm3 - vfmadd213pd -offset(%rdx),%zmm2,%zmm3 - vmovupd %zmm3,-offset(%rdx) - vmovupd -offset(%rsi),%zmm3 - vfmadd213pd -offset(%rdx),%zmm2,%zmm3 - vmovupd %zmm3,-offset(%rdx) - cmp %rdx,%rdi - jne - inc %rcx - shl $something,%rcx - cmp %rcx,%rax - jle - lea (%r9,%rcx,8),%rdx - xchg %ax,%ax - vmovupd (%rbx,%rcx,8),%ymm2 - sub $something,%rdx - vfmadd213pd -offset(%rdx),%ymm1,%ymm2 - vmovupd %ymm2,-offset(%rdx) - vmovupd offset(%rbx,%rcx,8),%ymm2 /usr/lib64/libopenblas_openmp.a/daxpy_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/daxpy_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/daxpy_k_SKYLAKEX.o (objdump) @@ -2,46 +2,37 @@ /usr/lib64/libopenblas_openmp.a/daxpy_k_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 554889e5 41574156 41554154 534883e4 UH..AWAVAUATSH.. - 0010 c0488b75 104885ff 7e3f4989 fa4889cb .H.u.H..~?I..H.. - 0020 4983f801 754a4883 fe017544 4889f848 I...uJH...uDH..H - 0030 83e0f00f 85470100 000f1f80 00000000 .....G.......... - 0040 c5fb100c c3c4c2f9 a90cc1c4 c17b110c .............{.. - 0050 c148ffc0 4939c27f e7488d65 d831c05b .H..I9...H.e.1.[ - 0060 415c415d 415e415f 5dc3660f 1f440000 A\A]A^A_].f..D.. - 0070 4c89d148 83e1fc0f 84130200 004a8d04 L..H.........J.. - 0080 85000000 00c4e1fb 92c0488d 04b50000 ..........H..... - 0090 0000c4e1 fb92c848 89f048c1 e0054889 .......H..H...H. - 00a0 4424f84c 895424f0 4f8d2c00 4c8d1c36 D$.L.T$.O.,.L..6 - 00b0 4d89c64c 8b5424f8 4f8d7c05 004d8d24 M..L.T$.O.|..M.$ - 00c0 3349c1e6 054889da 4c89c831 ff0f1f00 3I...H..L..1.... - 00d0 c5fb1022 c4a17b10 1cc2c4e2 f9a920c4 ..."..{....... . - 00e0 a17b1014 eac4a17b 100cfa48 83c7044c .{.....{...H...L - 00f0 01f2c5fb 1120c4e2 f9a91cf0 c5fb111c ..... .......... - 0100 f0c4a2f9 a914d8c4 a17b1114 d8c4a2f9 .........{...... - 0110 a90ce0c4 a17b110c e04c01d0 4839f97f .....{...L..H9.. - 0120 af48ffc9 48c1e902 48ffc14c 8b5424f0 .H..H...H..L.T$. - 0130 c4e1fb93 d0c4e1fb 93c1480f afd1480f ..........H...H. - 0140 afc148c1 e1024939 ca0f8e0a ffffff48 ..H...I9.......H - 0150 c1e60349 8d04c149 c1e00348 8d14d390 ...I...I...H.... - 0160 c5fb100a 48ffc1c4 e2f9a908 4c01c2c5 ....H.......L... - 0170 fb110848 01f04939 ca7fe5e9 d9feffff ...H..I9........ - 0180 4889f9c4 e27d19c8 62f2fd48 19d04883 H....}..b..H..H. - 0190 e1e00f84 92000000 48ffc948 c1e90548 ........H..H...H - 01a0 89cf48c1 e7084c89 ca4889de 498dbc39 ..H...L..H..I..9 - 01b0 00010000 0f1f4000 62f1fd48 101e4881 ......@.b..H..H. - 01c0 c2000100 0062f2ed 48a85afc 4881c600 .....b..H.Z.H... - 01d0 01000062 f1fd4811 5afc62f1 fd48105e ...b..H.Z.b..H.^ - 01e0 fd62f2ed 48a85afd 62f1fd48 115afd62 .b..H.Z.b..H.Z.b - 01f0 f1fd4810 5efe62f2 ed48a85a fe62f1fd ..H.^.b..H.Z.b.. - 0200 48115afe 62f1fd48 105eff62 f2ed48a8 H.Z.b..H.^.b..H. - 0210 5aff62f1 fd48115a ff4839d7 759a48ff Z.b..H.Z.H9.u.H. - 0220 c148c1e1 054839c8 7e56498d 14c96690 .H...H9.~VI...f. - 0230 c5fd1014 cb4883ea 80c4e2f5 a85280c5 .....H.......R.. - 0240 fd115280 c5fd1054 cb20c4e2 f5a852a0 ..R....T. ....R. - 0250 c5fd1152 a0c5fd10 54cb40c4 e2f5a852 ...R....T.@....R - 0260 c0c5fd11 52c0c5fd 1054cb60 4883c110 ....R....T.`H... - 0270 c4e2f5a8 52e0c5fd 1152e048 39c87fb0 ....R....R.H9... - 0280 4939c27e 14c5f877 e9b3fdff ff0f1f00 I9.~...w........ - 0290 31c031d2 e9b6feff ffc5f877 e9b8fdff 1.1........w.... - 02a0 ff . + 0000 31c0c4e2 7d190166 0f1f8400 00000000 1...}..f........ + 0010 c57c1024 c2c57c10 6cc220c5 7c1074c2 .|.$..|.l. .|.t. + 0020 40c57c10 7cc260c4 62fdb824 c6c462fd @.|.|.`.b..$..b. + 0030 b86cc620 c462fdb8 74c640c4 62fdb87c .l. .b..t.@.b..| + 0040 c660c57c 1124c2c5 7c116cc2 20c57c11 .`.|.$..|.l. .|. + 0050 74c240c5 7c117cc2 604883c0 104883ef t.@.|.|.`H...H.. + 0060 1075adc5 f877c5f8 77c3660f 1f440000 .u...w..w.f..D.. + 0070 41574156 41554154 55534883 ec08488b AWAVAUATUSH...H. + 0080 742440c5 fb110424 4885ff7e 464989fa t$@....$H..~FI.. + 0090 4889cd49 83f80175 4f4883fe 01754949 H..I...uOH...uII + 00a0 89f84983 e0f00f85 44010000 c5fb100c ..I.....D....... + 00b0 240f1f80 00000000 c4a17b10 44c500c4 $.........{.D... + 00c0 82f1a904 c1c4817b 1104c149 ffc04d39 .......{...I..M9 + 00d0 c27fe548 83c4085b 5d415c41 5d415e31 ...H...[]A\A]A^1 + 00e0 c0415fc3 0f1f4000 4c89d1c5 fb100424 .A_...@.L......$ + 00f0 4883e1fc 0f841601 00004a8d 04850000 H.........J..... + 0100 00004f8d 24004c8d 1c364d89 c64989f5 ..O.$.L..6M..I.. + 0110 c4e1fb92 c0488d04 b5000000 00c4e1fb .....H.......... + 0120 92c84f8d 3c04498d 1c3349c1 e6054889 ..O.<.I..3I...H. + 0130 ea49c1e5 054c89c8 31ff660f 1f440000 .I...L..1.f..D.. + 0140 c5fb1022 c4a17b10 1cc2c4e2 f9a920c4 ..."..{....... . + 0150 a17b1014 e2c4a17b 100cfa48 83c7044c .{.....{...H...L + 0160 01f2c5fb 1120c4e2 f9a91cf0 c5fb111c ..... .......... + 0170 f0c4a2f9 a914d8c4 a17b1114 d8c4e2f9 .........{...... + 0180 a90cd8c5 fb110cd8 4c01e848 39f97fb0 ........L..H9... + 0190 48ffc948 c1e90248 ffc1c4e1 fb93d0c4 H..H...H........ + 01a0 e1fb93c1 480fafd1 480fafc1 48c1e102 ....H...H...H... + 01b0 4939ca0f 8e1affff ff48c1e6 03498d04 I9.......H...I.. + 01c0 c149c1e0 03488d54 d500660f 1f440000 .I...H.T..f..D.. + 01d0 c5fb100a 48ffc1c4 e2f9a908 4c01c2c5 ....H.......L... + 01e0 fb110848 01f04939 ca7fe5e9 e3feffff ...H..I9........ + 01f0 4889e14c 89ca4889 ee4c89c7 e8fffdff H..L..H..L...... + 0200 ff4d39c2 0f8fa2fe ffffe9c4 feffff90 .M9............. + 0210 31c031d2 eba3 1.1... /usr/lib64/libopenblas_openmp.a/daxpy_k_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/daxpy_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/daxpy_k_SKYLAKEX.o (objdump) @@ -4,4 +4,4 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0020 010001c0 04000000 19080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/daxpy_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/daxpy_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/daxpy_k_SKYLAKEX.o (objdump) @@ -3,7 +3,10 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 2c000000 1c000000 ........,....... - 0020 00000000 a1020000 00410e10 8602430d .........A....C. - 0030 064d8f03 8e048d05 8c068307 02580a0c .M...........X.. - 0040 0708470b 00000000 ..G..... + 0010 1b0c0708 90010000 10000000 1c000000 ................ + 0020 00000000 6a000000 00000000 48000000 ....j.......H... + 0030 30000000 00000000 a6010000 00420e10 0............B.. + 0040 8f02420e 188e0342 0e208d04 420e288c ..B....B. ..B.(. + 0050 05410e30 8606410e 38830744 0e400259 .A.0..A.8..D.@.Y + 0060 0a0e3841 0e30410e 28420e20 420e1842 ..8A.0A.(B. B..B + 0070 0e10440e 08450b00 ..D..E.. /usr/lib64/libopenblas_openmp.a/ddot_k_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/ddot_k_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/ddot_k_COOPERLAKE.o (disasm) @@ -4,7 +4,56 @@ Disassembly of section .text: +ddot_kernel_8.constprop.0: + xor %eax,%eax + vxorpd %ymm4,%ymm4,%ymm4 + vxorpd %ymm5,%ymm5,%ymm5 + vxorpd %ymm6,%ymm6,%ymm6 + vxorpd %ymm7,%ymm7,%ymm7 + data16 cs nopw offset(%rax,%rax,1) + nopl (%rax) + vmovups (%rsi,%rax,8),%ymm12 + vmovups offset(%rsi,%rax,8),%ymm13 + vmovups offset(%rsi,%rax,8),%ymm14 + vmovups offset(%rsi,%rax,8),%ymm15 + vfmadd231pd (%rdx,%rax,8),%ymm12,%ymm4 + vfmadd231pd offset(%rdx,%rax,8),%ymm13,%ymm5 + vfmadd231pd offset(%rdx,%rax,8),%ymm14,%ymm6 + vfmadd231pd offset(%rdx,%rax,8),%ymm15,%ymm7 + add $something,%rax + sub $something,%rdi + jne + vextractf128 $something,%ymm4,%xmm12 + vextractf128 $something,%ymm5,%xmm13 + vextractf128 $something,%ymm6,%xmm14 + vextractf128 $something,%ymm7,%xmm15 + vaddpd %xmm4,%xmm12,%xmm4 + vaddpd %xmm5,%xmm13,%xmm5 + vaddpd %xmm6,%xmm14,%xmm6 + vaddpd %xmm7,%xmm15,%xmm7 + vaddpd %xmm4,%xmm5,%xmm4 + vaddpd %xmm6,%xmm7,%xmm6 + vaddpd %xmm4,%xmm6,%xmm4 + vhaddpd %xmm4,%xmm4,%xmm4 + vmovsd %xmm4,(%rcx) + vzeroupper + vzeroupper + ret + nop + dot_compute: + push %r15 + vxorpd %xmm0,%xmm0,%xmm0 + push %r14 + push %r13 + push %r12 + push %rbp + push %rbx + sub $something,%rsp + mov %fs:0x28,%rax + mov %rax,offset(%rsp) + xor %eax,%eax + movq $something,(%rsp) test %rdi,%rdi jle mov %rsi,%r10 @@ -15,69 +64,66 @@ jne cmp $something,%r8 jne - mov %rdi,%rax - vxorpd %xmm0,%xmm0,%xmm0 - and $something,%rax + mov %rdi,%r8 + and $something,%r8 jne - nopw offset(%rax,%rax,1) - vmovsd (%r11,%rax,8),%xmm4 - vfmadd231sd (%r10,%rax,8),%xmm4,%xmm0 - inc %rax - cmp %rax,%r9 + nopl offset(%rax) + vmovsd (%r11,%r8,8),%xmm7 + vfmadd231sd (%r10,%r8,8),%xmm7,%xmm0 + inc %r8 + cmp %r8,%r9 jg + mov offset(%rsp),%rax + sub %fs:0x28,%rax + jne + add $something,%rsp + pop %rbx + pop %rbp + pop %r12 + pop %r13 + pop %r14 + pop %r15 ret - nopl (%rax) - push %rbp + nop mov %r9,%rcx - mov %rsp,%rbp - push %r15 - push %r14 - push %r13 - push %r12 - push %rbx - and $something,%rsp and $something,%rcx je lea offset(,%rsi,4),%rax + lea (%r8,%r8,1),%rbp + lea (%rsi,%rsi,1),%rbx + mov %r8,%r13 + mov %rsi,%r12 + vxorpd %xmm3,%xmm3,%xmm3 kmovq %rax,%k0 lea offset(,%r8,4),%rax kmovq %rax,%k1 - mov %rsi,%rax - shl $something,%rax - mov %rax,-offset(%rsp) - mov %r9,-offset(%rsp) - lea (%r8,%r8,1),%r12 - lea (%rsi,%rsi,1),%rbx - mov %r8,%r13 - vxorpd %xmm0,%xmm0,%xmm0 - mov -offset(%rsp),%r9 - lea (%r12,%r8,1),%r15 + lea offset(%rbp,%r8,1),%r15 lea (%rbx,%rsi,1),%r14 shl $something,%r13 mov %r11,%rdx + shl $something,%r12 mov %r10,%rax - vmovsd %xmm0,%xmm0,%xmm3 + vmovsd %xmm3,%xmm3,%xmm0 xor %edi,%edi - nopl (%rax) + cs nopw offset(%rax,%rax,1) vmovsd (%rdx,%r15,8),%xmm1 - vmovsd (%rdx,%r12,8),%xmm2 + vmovsd (%rdx,%rbp,8),%xmm2 vmulsd (%rax,%r14,8),%xmm1,%xmm1 vmulsd (%rax,%rbx,8),%xmm2,%xmm2 - vmovsd (%rdx),%xmm5 - vmovsd (%rdx,%r8,8),%xmm6 + vmovsd (%rdx),%xmm4 + vmovsd (%rdx,%r8,8),%xmm5 add $something,%rdi - vfmadd231sd (%rax,%rsi,8),%xmm6,%xmm1 - vfmadd231sd (%rax),%xmm5,%xmm2 + vfmadd231sd (%rax,%rsi,8),%xmm5,%xmm1 + vfmadd231sd (%rax),%xmm4,%xmm2 add %r13,%rdx - add %r9,%rax - vaddsd %xmm1,%xmm0,%xmm0 - vaddsd %xmm2,%xmm3,%xmm3 + add %r12,%rax + vaddsd %xmm1,%xmm3,%xmm3 + vaddsd %xmm2,%xmm0,%xmm0 cmp %rdi,%rcx jg dec %rcx shr $something,%rcx inc %rcx - mov -offset(%rsp),%r9 kmovq %k0,%rax kmovq %k1,%rdx imul %rcx,%rax @@ -89,108 +135,33 @@ lea (%r11,%rdx,8),%rdx shl $something,%rsi lea (%r10,%rax,8),%rax - nopl (%rax) - vmovsd (%rdx),%xmm7 + nopw offset(%rax,%rax,1) + vmovsd (%rdx),%xmm6 inc %rcx - vfmadd231sd (%rax),%xmm7,%xmm3 + vfmadd231sd (%rax),%xmm6,%xmm0 add %r8,%rdx add %rsi,%rax cmp %rcx,%r9 jg - lea -offset(%rbp),%rsp - vaddsd %xmm3,%xmm0,%xmm0 - pop %rbx - pop %r12 - pop %r13 - pop %r14 - pop %r15 - pop %rbp - ret - nopw offset(%rax,%rax,1) - vxorpd %xmm0,%xmm0,%xmm0 - ret - nopl (%rax) - mov %eax,%edx - and $something,%edx - jle - dec %edx - shr $something,%edx - mov %edx,%edi - vxorpd %xmm1,%xmm1,%xmm1 - shl $something,%rdi /usr/lib64/libopenblas_openmp.a/ddot_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/ddot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ddot_k_COOPERLAKE.o (objdump) @@ -2,77 +2,69 @@ /usr/lib64/libopenblas_openmp.a/ddot_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 4885ff0f 8e6f0100 004989f2 4989f948 H....o...I..I..H - 0010 89d64989 cb4883fa 01753549 83f80175 ..I..H...u5I...u - 0020 2f4889f8 c5f957c0 4883e0f0 0f854e01 /H....W.H.....N. - 0030 0000660f 1f440000 c4c17b10 24c3c4c2 ..f..D....{.$... - 0040 d9b904c2 48ffc049 39c17fec c30f1f00 ....H..I9....... - 0050 554c89c9 4889e541 57415641 55415453 UL..H..AWAVAUATS - 0060 4883e4c0 4883e1fc 0f845202 0000488d H...H.....R...H. - 0070 04b50000 0000c4e1 fb92c04a 8d048500 ...........J.... - 0080 000000c4 e1fb92c8 4889f048 c1e00548 ........H..H...H - 0090 894424f8 4c894c24 f04f8d24 00488d1c .D$.L.L$.O.$.H.. - 00a0 364d89c5 c5f957c0 4c8b4c24 f84f8d3c 6M....W.L.L$.O.< - 00b0 044c8d34 3349c1e5 054c89da 4c89d0c5 .L.43I...L..L... - 00c0 fb10d831 ff0f1f00 c4a17b10 0cfac4a1 ...1......{..... - 00d0 7b1014e2 c4a17359 0cf0c5eb 5914d8c5 {.....sY....Y... - 00e0 fb102ac4 a17b1034 c24883c7 04c4e2c9 ..*..{.4.H...... - 00f0 b90cf0c4 e2d1b910 4c01ea4c 01c8c5fb ........L..L.... - 0100 58c1c5e3 58da4839 f97fbd48 ffc948c1 X...X.H9...H..H. - 0110 e90248ff c14c8b4c 24f0c4e1 fb93c0c4 ..H..L.L$....... - 0120 e1fb93d1 480fafc1 480fafd1 48c1e102 ....H...H...H... - 0130 4939c97e 2a49c1e0 03498d14 d348c1e6 I9.~*I...I...H.. - 0140 03498d04 c20f1f00 c5fb103a 48ffc1c4 .I.........:H... - 0150 e2c1b918 4c01c248 01f04939 c97fe948 ....L..H..I9...H - 0160 8d65d8c5 fb58c35b 415c415d 415e415f .e...X.[A\A]A^A_ - 0170 5dc3660f 1f440000 c5f957c0 c30f1f00 ].f..D....W..... - 0180 89c283e2 e00f8e4a 010000ff cac1ea05 .......J........ - 0190 89d7c5f1 57c948c1 e7084c89 d14c89de ....W.H...L..L.. - 01a0 498dbc3a 00010000 62f1fd48 28d162f1 I..:....b..H(.b. - 01b0 fd4828d9 62f1fd48 28e1660f 1f440000 .H(.b..H(.f..D.. - 01c0 62f1fd48 102962f1 fd481071 0162f2d5 b..H.)b..H.q.b.. - 01d0 48b82662 f1fd4810 790262f1 fd481069 H.&b..H.y.b..H.i - 01e0 034881c1 00010000 62f2cd48 b85e0162 .H......b..H.^.b - 01f0 f2c548b8 560262f2 d548b84e 034881c6 ..H.V.b..H.N.H.. - 0200 00010000 4839cf75 b7c5fd28 c462f3fd ....H9.u...(.b.. - 0210 481be401 c5fd58c4 ffc2c5fd 28e362f3 H.....X.....(.b. - 0220 fd481bdb 01c5dd58 e3c1e205 c5fd28da .H.....X......(. - 0230 62f3fd48 1bd201c5 e558da48 63d2c5fd b..H.....X.Hc... - 0240 28d162f3 fd481bc9 01c5ed58 d14839d0 (.b..H.....X.H9. - 0250 7e45660f 1f440000 c4c17d10 34d2c4c1 ~Ef..D....}.4... - 0260 7d107cd2 20c4c2cd b804d3c4 c17d106c }.|. ........}.l - 0270 d240c4c1 7d1074d2 60c4c2c5 b864d320 .@..}.t.`....d. - 0280 c4c2d5b8 5cd340c4 c2cdb854 d3604883 ....\.@....T.`H. - 0290 c2104839 d07fc1c5 fd58ccc5 f558cbc5 ..H9.....X...X.. - 02a0 f558ca62 f3fd2819 c801c5f9 58c1c5f9 .X.b..(.....X... - 02b0 7cc04939 c17e1ac5 f877e979 fdffff90 |.I9.~...w.y.... - 02c0 c5f957c0 31d231c0 c5fb10d8 e964feff ..W.1.1......d.. - 02d0 ffc5f877 c3c5f957 c0c5fd28 e0c5fd28 ...w...W...(...( - 02e0 d8c5fd28 d031d2e9 6cffffff 0f1f4000 ...(.1..l.....@. - 02f0 4883ec08 4c89c24c 8b442410 4889ce4c H...L..L.D$.H..L - 0300 89c9e8f9 fcffff48 8b442418 c5fb1100 .......H.D$..... - 0310 31c04883 c408c366 0f1f8400 00000000 1.H....f........ - 0320 41574156 4989ce41 554989f5 41544989 AWAVI..AUI..ATI. - 0330 d4554889 fd534881 ec380400 0064488b .UH..SH..8...dH. - 0340 04252800 00004889 84242804 000031c0 .%(...H..$(...1. - 0350 4d85c00f 94c04881 ff102700 000f9ec2 M.....H...'..... - 0360 08d07505 4d85e475 3f488b84 24280400 ..u.M..u?H..$(.. - 0370 0064482b 04252800 00000f85 16010000 .dH+.%(......... - 0380 4881c438 0400005b 4889ef5d 4c89e241 H..8...[H..]L..A - 0390 5c4c89ee 415d4c89 f1415e41 5fe95efc \L..A]L..A^A_.^. - 03a0 ffff660f 1f440000 4c894424 08e80000 ..f..D..L.D$.... - 03b0 000083f8 014c8b44 240889c3 74abe800 .....L.D$...t... - 03c0 00000085 c04c8b44 2408759d 488b0500 .....L.D$.u.H... - 03d0 0000004c 63384439 fb0f8589 00000048 ...Lc8D9.......H - 03e0 83ec0841 57488d05 04ffffff 4d89e950 ...AWH......M..P - 03f0 31c931d2 6a004889 eebf0300 0000488d 1.1.j.H.......H. - 0400 5c244053 41504156 41544c8d 442458e8 \$@SAPAVATL.D$X. - 0410 00000000 4883c440 4585ff7e 7349c1e7 ....H..@E..~sI.. - 0420 044a8d14 3b4889d8 c5f957c0 0f1f4000 .J..;H....W...@. - 0430 c5fb5800 4883c010 4839d075 f3488b84 ..X.H...H9.u.H.. - 0440 24280400 0064482b 04252800 00007546 $(...dH+.%(...uF - 0450 4881c438 0400005b 5d415c41 5d415e41 H..8...[]A\A]A^A - 0460 5fc3660f 1f440000 89dfe800 00000048 _.f..D.........H - 0470 8b050000 00004c8b 4424084c 63384183 ......L.D$.Lc8A. - 0480 ff010f85 57ffffff e9dcfeff ff0f1f00 ....W........... - 0490 c5f957c0 eba7e800 000000 ..W........ + 0000 31c0c5dd 57e4c5d5 57edc5cd 57f6c5c5 1...W...W...W... + 0010 57ff6666 2e0f1f84 00000000 000f1f00 W.ff............ + 0020 c57c1024 c6c57c10 6cc620c5 7c1074c6 .|.$..|.l. .|.t. + 0030 40c57c10 7cc660c4 e29db824 c2c4e295 @.|.|.`....$.... + 0040 b86cc220 c4e28db8 74c240c4 e285b87c .l. ....t.@....| + 0050 c2604883 c0104883 ef1075c4 c4c37d19 .`H...H...u...}. + 0060 e401c4c3 7d19ed01 c4c37d19 f601c4c3 ....}.....}..... + 0070 7d19ff01 c59958e4 c59158ed c58958f6 }.....X...X...X. + 0080 c58158ff c5d158e4 c5c158f6 c5c958e4 ..X...X...X...X. + 0090 c5d97ce4 c5fb1121 c5f877c5 f877c390 ..|....!..w..w.. + 00a0 4157c5f9 57c04156 41554154 55534883 AW..W.AVAUATUSH. + 00b0 ec186448 8b042528 00000048 89442408 ..dH..%(...H.D$. + 00c0 31c048c7 04240000 00004885 ff7e3d49 1.H..$....H..~=I + 00d0 89f24989 f94889d6 4989cb48 83fa0175 ..I..H..I..H...u + 00e0 4f4983f8 01754949 89f84983 e0f00f85 OI...uII..I..... + 00f0 3c010000 0f1f4000 c4817b10 3cc3c482 <.....@...{.<... + 0100 c1b904c2 49ffc04d 39c17fec 488b4424 ....I..M9...H.D$ + 0110 0864482b 04252800 00000f85 46010000 .dH+.%(.....F... + 0120 4883c418 5b5d415c 415d415e 415fc390 H...[]A\A]A^A_.. + 0130 4c89c948 83e1fc0f 841b0100 00488d04 L..H.........H.. + 0140 b5000000 004b8d2c 00488d1c 364d89c5 .....K.,.H..6M.. + 0150 4989f4c5 e157dbc4 e1fb92c0 4a8d0485 I....W......J... + 0160 00000000 c4e1fb92 c84e8d7c 05004c8d .........N.|..L. + 0170 343349c1 e5054c89 da49c1e4 054c89d0 43I...L..I...L.. + 0180 c5e310c3 31ff662e 0f1f8400 00000000 ....1.f......... + 0190 c4a17b10 0cfac5fb 1014eac4 a173590c ..{..........sY. + 01a0 f0c5eb59 14d8c5fb 1022c4a1 7b102cc2 ...Y....."..{.,. + 01b0 4883c704 c4e2d1b9 0cf0c4e2 d9b9104c H..............L + 01c0 01ea4c01 e0c5e358 d9c5fb58 c24839f9 ..L....X...X.H9. + 01d0 7fbe48ff c948c1e9 0248ffc1 c4e1fb93 ..H..H...H...... + 01e0 c0c4e1fb 93d1480f afc1480f afd148c1 ......H...H...H. + 01f0 e1024939 c97e3049 c1e00349 8d14d348 ..I9.~0I...I...H + 0200 c1e60349 8d04c266 0f1f8400 00000000 ...I...f........ + 0210 c5fb1032 48ffc1c4 e2c9b900 4c01c248 ...2H.......L..H + 0220 01f04939 c97fe9c5 e358c0e9 dcfeffff ..I9.....X...... + 0230 4889e14c 89da4c89 d64c89c7 e8bffdff H..L..L..L...... + 0240 ffc5fb10 04244d39 c10f8fa9 feffffe9 .....$M9........ + 0250 b8feffff 0f1f4000 c5e157db 31d231c0 ......@...W.1.1. + 0260 c5e310c3 eb91e800 0000000f 1f440000 .............D.. + 0270 4883ec08 4c89c24c 8b442410 4889ce4c H...L..L.D$.H..L + 0280 89c9e819 feffff48 8b442418 c5fb1100 .......H.D$..... + 0290 31c04883 c408c366 0f1f8400 00000000 1.H....f........ + 02a0 41574156 4989ce41 554989f5 41544989 AWAVI..AUI..ATI. + 02b0 d4554889 fd534881 ec380400 0064488b .UH..SH..8...dH. + 02c0 04252800 00004889 84242804 000031c0 .%(...H..$(...1. + 02d0 4d85c00f 94c04881 ff102700 000f9ec2 M.....H...'..... + 02e0 08d07505 4d85e475 3f488b84 24280400 ..u.M..u?H..$(.. + 02f0 0064482b 04252800 00000f85 16010000 .dH+.%(......... + 0300 4881c438 0400005b 4889ef5d 4c89e241 H..8...[H..]L..A + 0310 5c4c89ee 415d4c89 f1415e41 5fe97efd \L..A]L..A^A_.~. + 0320 ffff660f 1f440000 4c894424 08e80000 ..f..D..L.D$.... + 0330 000083f8 014c8b44 240889c3 74abe800 .....L.D$...t... + 0340 00000085 c04c8b44 2408759d 488b0500 .....L.D$.u.H... + 0350 0000004c 63384439 fb0f8589 00000048 ...Lc8D9.......H + 0360 83ec0841 57488d05 04ffffff 4d89e950 ...AWH......M..P + 0370 31c931d2 6a004889 eebf0300 0000488d 1.1.j.H.......H. + 0380 5c244053 41504156 41544c8d 442458e8 \$@SAPAVATL.D$X. + 0390 00000000 4883c440 4585ff7e 7349c1e7 ....H..@E..~sI.. + 03a0 044a8d14 3b4889d8 c5f957c0 0f1f4000 .J..;H....W...@. + 03b0 c5fb5800 4883c010 4839d075 f3488b84 ..X.H...H9.u.H.. + 03c0 24280400 0064482b 04252800 00007546 $(...dH+.%(...uF + 03d0 4881c438 0400005b 5d415c41 5d415e41 H..8...[]A\A]A^A + 03e0 5fc3660f 1f440000 89dfe800 00000048 _.f..D.........H + 03f0 8b050000 00004c8b 4424084c 63384183 ......L.D$.Lc8A. + 0400 ff010f85 57ffffff e9dcfeff ff0f1f00 ....W........... + 0410 c5f957c0 eba7e800 000000 ..W........ /usr/lib64/libopenblas_openmp.a/ddot_k_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/ddot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ddot_k_COOPERLAKE.o (objdump) @@ -4,4 +4,4 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0020 010001c0 04000000 19080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/ddot_k_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/ddot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ddot_k_COOPERLAKE.o (objdump) @@ -3,19 +3,20 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 ec020000 0002510e 10860246 ..........Q....F - 0030 0d064d8f 038e048d 058c0683 07030d01 ..M............. - 0040 0c070847 c3c6cccd cecf0348 010c0610 ...G.......H.... - 0050 83078602 8c068d05 8e048f03 510c0708 ............Q... - 0060 c3c6cccd cecf0000 14000000 6c000000 ............l... - 0070 00000000 27000000 00440e10 620e0800 ....'....D..b... - 0080 84000000 84000000 00000000 7b010000 ............{... - 0090 00420e10 8f02420e 188e0345 0e208d04 .B....B....E. .. - 00a0 450e288c 05440e30 8606440e 38830747 E.(..D.0..D.8..G - 00b0 0ef00802 4a0a0e38 410e3044 0e28450e ....J..8A.0D.(E. - 00c0 20450e18 450e1042 0e084b0b 7b0ef808 E..E..B..K.{... - 00d0 420e8009 4b0e8809 460e9009 4e0e9809 B...K...F...N... - 00e0 420ea009 420ea809 420eb009 4e0ef008 B...B...B...N... - 00f0 7f0a0e38 410e3041 0e28420e 20420e18 ...8A.0A.(B. B.. - 0100 420e1042 0e08470b B..B..G. + 0010 1b0c0708 90010000 10000000 1c000000 ................ + 0020 00000000 9f000000 00000000 48000000 ............H... + 0030 30000000 00000000 cb010000 00420e10 0............B.. + 0040 8f02460e 188e0342 0e208d04 420e288c ..F....B. ..B.(. + 0050 05410e30 8606410e 38830744 0e500272 .A.0..A.8..D.P.r + 0060 0a0e3841 0e30410e 28420e20 420e1842 ..8A.0A.(B. B..B + 0070 0e10420e 08420b00 14000000 7c000000 ..B..B......|... + 0080 00000000 27000000 00440e10 620e0800 ....'....D..b... + 0090 84000000 94000000 00000000 7b010000 ............{... + 00a0 00420e10 8f02420e 188e0345 0e208d04 .B....B....E. .. + 00b0 450e288c 05440e30 8606440e 38830747 E.(..D.0..D.8..G + 00c0 0ef00802 4a0a0e38 410e3044 0e28450e ....J..8A.0D.(E. + 00d0 20450e18 450e1042 0e084b0b 7b0ef808 E..E..B..K.{... + 00e0 420e8009 4b0e8809 460e9009 4e0e9809 B...K...F...N... + 00f0 420ea009 420ea809 420eb009 4e0ef008 B...B...B...N... + 0100 7f0a0e38 410e3041 0e28420e 20420e18 ...8A.0A.(B. B.. + 0110 420e1042 0e08470b B..B..G. /usr/lib64/libopenblas_openmp.a/ddot_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/ddot_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/ddot_k_SKYLAKEX.o (disasm) @@ -4,7 +4,56 @@ Disassembly of section .text: +ddot_kernel_8.constprop.0: + xor %eax,%eax + vxorpd %ymm4,%ymm4,%ymm4 + vxorpd %ymm5,%ymm5,%ymm5 + vxorpd %ymm6,%ymm6,%ymm6 + vxorpd %ymm7,%ymm7,%ymm7 + data16 cs nopw offset(%rax,%rax,1) + nopl (%rax) + vmovups (%rsi,%rax,8),%ymm12 + vmovups offset(%rsi,%rax,8),%ymm13 + vmovups offset(%rsi,%rax,8),%ymm14 + vmovups offset(%rsi,%rax,8),%ymm15 + vfmadd231pd (%rdx,%rax,8),%ymm12,%ymm4 + vfmadd231pd offset(%rdx,%rax,8),%ymm13,%ymm5 + vfmadd231pd offset(%rdx,%rax,8),%ymm14,%ymm6 + vfmadd231pd offset(%rdx,%rax,8),%ymm15,%ymm7 + add $something,%rax + sub $something,%rdi + jne + vextractf128 $something,%ymm4,%xmm12 + vextractf128 $something,%ymm5,%xmm13 + vextractf128 $something,%ymm6,%xmm14 + vextractf128 $something,%ymm7,%xmm15 + vaddpd %xmm4,%xmm12,%xmm4 + vaddpd %xmm5,%xmm13,%xmm5 + vaddpd %xmm6,%xmm14,%xmm6 + vaddpd %xmm7,%xmm15,%xmm7 + vaddpd %xmm4,%xmm5,%xmm4 + vaddpd %xmm6,%xmm7,%xmm6 + vaddpd %xmm4,%xmm6,%xmm4 + vhaddpd %xmm4,%xmm4,%xmm4 + vmovsd %xmm4,(%rcx) + vzeroupper + vzeroupper + ret + nop + dot_compute: + push %r15 + vxorpd %xmm0,%xmm0,%xmm0 + push %r14 + push %r13 + push %r12 + push %rbp + push %rbx + sub $something,%rsp + mov %fs:0x28,%rax + mov %rax,offset(%rsp) + xor %eax,%eax + movq $something,(%rsp) test %rdi,%rdi jle mov %rsi,%r10 @@ -15,69 +64,66 @@ jne cmp $something,%r8 jne - mov %rdi,%rax - vxorpd %xmm0,%xmm0,%xmm0 - and $something,%rax + mov %rdi,%r8 + and $something,%r8 jne - nopw offset(%rax,%rax,1) - vmovsd (%r11,%rax,8),%xmm4 - vfmadd231sd (%r10,%rax,8),%xmm4,%xmm0 - inc %rax - cmp %rax,%r9 + nopl offset(%rax) + vmovsd (%r11,%r8,8),%xmm7 + vfmadd231sd (%r10,%r8,8),%xmm7,%xmm0 + inc %r8 + cmp %r8,%r9 jg + mov offset(%rsp),%rax + sub %fs:0x28,%rax + jne + add $something,%rsp + pop %rbx + pop %rbp + pop %r12 + pop %r13 + pop %r14 + pop %r15 ret - nopl (%rax) - push %rbp + nop mov %r9,%rcx - mov %rsp,%rbp - push %r15 - push %r14 - push %r13 - push %r12 - push %rbx - and $something,%rsp and $something,%rcx je lea offset(,%rsi,4),%rax + lea (%r8,%r8,1),%rbp + lea (%rsi,%rsi,1),%rbx + mov %r8,%r13 + mov %rsi,%r12 + vxorpd %xmm3,%xmm3,%xmm3 kmovq %rax,%k0 lea offset(,%r8,4),%rax kmovq %rax,%k1 - mov %rsi,%rax - shl $something,%rax - mov %rax,-offset(%rsp) - mov %r9,-offset(%rsp) - lea (%r8,%r8,1),%r12 - lea (%rsi,%rsi,1),%rbx - mov %r8,%r13 - vxorpd %xmm0,%xmm0,%xmm0 - mov -offset(%rsp),%r9 - lea (%r12,%r8,1),%r15 + lea offset(%rbp,%r8,1),%r15 lea (%rbx,%rsi,1),%r14 shl $something,%r13 mov %r11,%rdx + shl $something,%r12 mov %r10,%rax - vmovsd %xmm0,%xmm0,%xmm3 + vmovsd %xmm3,%xmm3,%xmm0 xor %edi,%edi - nopl (%rax) + cs nopw offset(%rax,%rax,1) vmovsd (%rdx,%r15,8),%xmm1 - vmovsd (%rdx,%r12,8),%xmm2 + vmovsd (%rdx,%rbp,8),%xmm2 vmulsd (%rax,%r14,8),%xmm1,%xmm1 vmulsd (%rax,%rbx,8),%xmm2,%xmm2 - vmovsd (%rdx),%xmm5 - vmovsd (%rdx,%r8,8),%xmm6 + vmovsd (%rdx),%xmm4 + vmovsd (%rdx,%r8,8),%xmm5 add $something,%rdi - vfmadd231sd (%rax,%rsi,8),%xmm6,%xmm1 - vfmadd231sd (%rax),%xmm5,%xmm2 + vfmadd231sd (%rax,%rsi,8),%xmm5,%xmm1 + vfmadd231sd (%rax),%xmm4,%xmm2 add %r13,%rdx - add %r9,%rax - vaddsd %xmm1,%xmm0,%xmm0 - vaddsd %xmm2,%xmm3,%xmm3 + add %r12,%rax + vaddsd %xmm1,%xmm3,%xmm3 + vaddsd %xmm2,%xmm0,%xmm0 cmp %rdi,%rcx jg dec %rcx shr $something,%rcx inc %rcx - mov -offset(%rsp),%r9 kmovq %k0,%rax kmovq %k1,%rdx imul %rcx,%rax @@ -89,108 +135,33 @@ lea (%r11,%rdx,8),%rdx shl $something,%rsi lea (%r10,%rax,8),%rax - nopl (%rax) - vmovsd (%rdx),%xmm7 + nopw offset(%rax,%rax,1) + vmovsd (%rdx),%xmm6 inc %rcx - vfmadd231sd (%rax),%xmm7,%xmm3 + vfmadd231sd (%rax),%xmm6,%xmm0 add %r8,%rdx add %rsi,%rax cmp %rcx,%r9 jg - lea -offset(%rbp),%rsp - vaddsd %xmm3,%xmm0,%xmm0 - pop %rbx - pop %r12 - pop %r13 - pop %r14 - pop %r15 - pop %rbp - ret - nopw offset(%rax,%rax,1) - vxorpd %xmm0,%xmm0,%xmm0 - ret - nopl (%rax) - mov %eax,%edx - and $something,%edx - jle - dec %edx - shr $something,%edx - mov %edx,%edi - vxorpd %xmm1,%xmm1,%xmm1 - shl $something,%rdi /usr/lib64/libopenblas_openmp.a/ddot_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/ddot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ddot_k_SKYLAKEX.o (objdump) @@ -2,77 +2,69 @@ /usr/lib64/libopenblas_openmp.a/ddot_k_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 4885ff0f 8e6f0100 004989f2 4989f948 H....o...I..I..H - 0010 89d64989 cb4883fa 01753549 83f80175 ..I..H...u5I...u - 0020 2f4889f8 c5f957c0 4883e0f0 0f854e01 /H....W.H.....N. - 0030 0000660f 1f440000 c4c17b10 24c3c4c2 ..f..D....{.$... - 0040 d9b904c2 48ffc049 39c17fec c30f1f00 ....H..I9....... - 0050 554c89c9 4889e541 57415641 55415453 UL..H..AWAVAUATS - 0060 4883e4c0 4883e1fc 0f845202 0000488d H...H.....R...H. - 0070 04b50000 0000c4e1 fb92c04a 8d048500 ...........J.... - 0080 000000c4 e1fb92c8 4889f048 c1e00548 ........H..H...H - 0090 894424f8 4c894c24 f04f8d24 00488d1c .D$.L.L$.O.$.H.. - 00a0 364d89c5 c5f957c0 4c8b4c24 f84f8d3c 6M....W.L.L$.O.< - 00b0 044c8d34 3349c1e5 054c89da 4c89d0c5 .L.43I...L..L... - 00c0 fb10d831 ff0f1f00 c4a17b10 0cfac4a1 ...1......{..... - 00d0 7b1014e2 c4a17359 0cf0c5eb 5914d8c5 {.....sY....Y... - 00e0 fb102ac4 a17b1034 c24883c7 04c4e2c9 ..*..{.4.H...... - 00f0 b90cf0c4 e2d1b910 4c01ea4c 01c8c5fb ........L..L.... - 0100 58c1c5e3 58da4839 f97fbd48 ffc948c1 X...X.H9...H..H. - 0110 e90248ff c14c8b4c 24f0c4e1 fb93c0c4 ..H..L.L$....... - 0120 e1fb93d1 480fafc1 480fafd1 48c1e102 ....H...H...H... - 0130 4939c97e 2a49c1e0 03498d14 d348c1e6 I9.~*I...I...H.. - 0140 03498d04 c20f1f00 c5fb103a 48ffc1c4 .I.........:H... - 0150 e2c1b918 4c01c248 01f04939 c97fe948 ....L..H..I9...H - 0160 8d65d8c5 fb58c35b 415c415d 415e415f .e...X.[A\A]A^A_ - 0170 5dc3660f 1f440000 c5f957c0 c30f1f00 ].f..D....W..... - 0180 89c283e2 e00f8e4a 010000ff cac1ea05 .......J........ - 0190 89d7c5f1 57c948c1 e7084c89 d14c89de ....W.H...L..L.. - 01a0 498dbc3a 00010000 62f1fd48 28d162f1 I..:....b..H(.b. - 01b0 fd4828d9 62f1fd48 28e1660f 1f440000 .H(.b..H(.f..D.. - 01c0 62f1fd48 102962f1 fd481071 0162f2d5 b..H.)b..H.q.b.. - 01d0 48b82662 f1fd4810 790262f1 fd481069 H.&b..H.y.b..H.i - 01e0 034881c1 00010000 62f2cd48 b85e0162 .H......b..H.^.b - 01f0 f2c548b8 560262f2 d548b84e 034881c6 ..H.V.b..H.N.H.. - 0200 00010000 4839cf75 b7c5fd28 c462f3fd ....H9.u...(.b.. - 0210 481be401 c5fd58c4 ffc2c5fd 28e362f3 H.....X.....(.b. - 0220 fd481bdb 01c5dd58 e3c1e205 c5fd28da .H.....X......(. - 0230 62f3fd48 1bd201c5 e558da48 63d2c5fd b..H.....X.Hc... - 0240 28d162f3 fd481bc9 01c5ed58 d14839d0 (.b..H.....X.H9. - 0250 7e45660f 1f440000 c4c17d10 34d2c4c1 ~Ef..D....}.4... - 0260 7d107cd2 20c4c2cd b804d3c4 c17d106c }.|. ........}.l - 0270 d240c4c1 7d1074d2 60c4c2c5 b864d320 .@..}.t.`....d. - 0280 c4c2d5b8 5cd340c4 c2cdb854 d3604883 ....\.@....T.`H. - 0290 c2104839 d07fc1c5 fd58ccc5 f558cbc5 ..H9.....X...X.. - 02a0 f558ca62 f3fd2819 c801c5f9 58c1c5f9 .X.b..(.....X... - 02b0 7cc04939 c17e1ac5 f877e979 fdffff90 |.I9.~...w.y.... - 02c0 c5f957c0 31d231c0 c5fb10d8 e964feff ..W.1.1......d.. - 02d0 ffc5f877 c3c5f957 c0c5fd28 e0c5fd28 ...w...W...(...( - 02e0 d8c5fd28 d031d2e9 6cffffff 0f1f4000 ...(.1..l.....@. - 02f0 4883ec08 4c89c24c 8b442410 4889ce4c H...L..L.D$.H..L - 0300 89c9e8f9 fcffff48 8b442418 c5fb1100 .......H.D$..... - 0310 31c04883 c408c366 0f1f8400 00000000 1.H....f........ - 0320 41574156 4989ce41 554989f5 41544989 AWAVI..AUI..ATI. - 0330 d4554889 fd534881 ec380400 0064488b .UH..SH..8...dH. - 0340 04252800 00004889 84242804 000031c0 .%(...H..$(...1. - 0350 4d85c00f 94c04881 ff102700 000f9ec2 M.....H...'..... - 0360 08d07505 4d85e475 3f488b84 24280400 ..u.M..u?H..$(.. - 0370 0064482b 04252800 00000f85 16010000 .dH+.%(......... - 0380 4881c438 0400005b 4889ef5d 4c89e241 H..8...[H..]L..A - 0390 5c4c89ee 415d4c89 f1415e41 5fe95efc \L..A]L..A^A_.^. - 03a0 ffff660f 1f440000 4c894424 08e80000 ..f..D..L.D$.... - 03b0 000083f8 014c8b44 240889c3 74abe800 .....L.D$...t... - 03c0 00000085 c04c8b44 2408759d 488b0500 .....L.D$.u.H... - 03d0 0000004c 63384439 fb0f8589 00000048 ...Lc8D9.......H - 03e0 83ec0841 57488d05 04ffffff 4d89e950 ...AWH......M..P - 03f0 31c931d2 6a004889 eebf0300 0000488d 1.1.j.H.......H. - 0400 5c244053 41504156 41544c8d 442458e8 \$@SAPAVATL.D$X. - 0410 00000000 4883c440 4585ff7e 7349c1e7 ....H..@E..~sI.. - 0420 044a8d14 3b4889d8 c5f957c0 0f1f4000 .J..;H....W...@. - 0430 c5fb5800 4883c010 4839d075 f3488b84 ..X.H...H9.u.H.. - 0440 24280400 0064482b 04252800 00007546 $(...dH+.%(...uF - 0450 4881c438 0400005b 5d415c41 5d415e41 H..8...[]A\A]A^A - 0460 5fc3660f 1f440000 89dfe800 00000048 _.f..D.........H - 0470 8b050000 00004c8b 4424084c 63384183 ......L.D$.Lc8A. - 0480 ff010f85 57ffffff e9dcfeff ff0f1f00 ....W........... - 0490 c5f957c0 eba7e800 000000 ..W........ + 0000 31c0c5dd 57e4c5d5 57edc5cd 57f6c5c5 1...W...W...W... + 0010 57ff6666 2e0f1f84 00000000 000f1f00 W.ff............ + 0020 c57c1024 c6c57c10 6cc620c5 7c1074c6 .|.$..|.l. .|.t. + 0030 40c57c10 7cc660c4 e29db824 c2c4e295 @.|.|.`....$.... + 0040 b86cc220 c4e28db8 74c240c4 e285b87c .l. ....t.@....| + 0050 c2604883 c0104883 ef1075c4 c4c37d19 .`H...H...u...}. + 0060 e401c4c3 7d19ed01 c4c37d19 f601c4c3 ....}.....}..... + 0070 7d19ff01 c59958e4 c59158ed c58958f6 }.....X...X...X. + 0080 c58158ff c5d158e4 c5c158f6 c5c958e4 ..X...X...X...X. + 0090 c5d97ce4 c5fb1121 c5f877c5 f877c390 ..|....!..w..w.. + 00a0 4157c5f9 57c04156 41554154 55534883 AW..W.AVAUATUSH. + 00b0 ec186448 8b042528 00000048 89442408 ..dH..%(...H.D$. + 00c0 31c048c7 04240000 00004885 ff7e3d49 1.H..$....H..~=I + 00d0 89f24989 f94889d6 4989cb48 83fa0175 ..I..H..I..H...u + 00e0 4f4983f8 01754949 89f84983 e0f00f85 OI...uII..I..... + 00f0 3c010000 0f1f4000 c4817b10 3cc3c482 <.....@...{.<... + 0100 c1b904c2 49ffc04d 39c17fec 488b4424 ....I..M9...H.D$ + 0110 0864482b 04252800 00000f85 46010000 .dH+.%(.....F... + 0120 4883c418 5b5d415c 415d415e 415fc390 H...[]A\A]A^A_.. + 0130 4c89c948 83e1fc0f 841b0100 00488d04 L..H.........H.. + 0140 b5000000 004b8d2c 00488d1c 364d89c5 .....K.,.H..6M.. + 0150 4989f4c5 e157dbc4 e1fb92c0 4a8d0485 I....W......J... + 0160 00000000 c4e1fb92 c84e8d7c 05004c8d .........N.|..L. + 0170 343349c1 e5054c89 da49c1e4 054c89d0 43I...L..I...L.. + 0180 c5e310c3 31ff662e 0f1f8400 00000000 ....1.f......... + 0190 c4a17b10 0cfac5fb 1014eac4 a173590c ..{..........sY. + 01a0 f0c5eb59 14d8c5fb 1022c4a1 7b102cc2 ...Y....."..{.,. + 01b0 4883c704 c4e2d1b9 0cf0c4e2 d9b9104c H..............L + 01c0 01ea4c01 e0c5e358 d9c5fb58 c24839f9 ..L....X...X.H9. + 01d0 7fbe48ff c948c1e9 0248ffc1 c4e1fb93 ..H..H...H...... + 01e0 c0c4e1fb 93d1480f afc1480f afd148c1 ......H...H...H. + 01f0 e1024939 c97e3049 c1e00349 8d14d348 ..I9.~0I...I...H + 0200 c1e60349 8d04c266 0f1f8400 00000000 ...I...f........ + 0210 c5fb1032 48ffc1c4 e2c9b900 4c01c248 ...2H.......L..H + 0220 01f04939 c97fe9c5 e358c0e9 dcfeffff ..I9.....X...... + 0230 4889e14c 89da4c89 d64c89c7 e8bffdff H..L..L..L...... + 0240 ffc5fb10 04244d39 c10f8fa9 feffffe9 .....$M9........ + 0250 b8feffff 0f1f4000 c5e157db 31d231c0 ......@...W.1.1. + 0260 c5e310c3 eb91e800 0000000f 1f440000 .............D.. + 0270 4883ec08 4c89c24c 8b442410 4889ce4c H...L..L.D$.H..L + 0280 89c9e819 feffff48 8b442418 c5fb1100 .......H.D$..... + 0290 31c04883 c408c366 0f1f8400 00000000 1.H....f........ + 02a0 41574156 4989ce41 554989f5 41544989 AWAVI..AUI..ATI. + 02b0 d4554889 fd534881 ec380400 0064488b .UH..SH..8...dH. + 02c0 04252800 00004889 84242804 000031c0 .%(...H..$(...1. + 02d0 4d85c00f 94c04881 ff102700 000f9ec2 M.....H...'..... + 02e0 08d07505 4d85e475 3f488b84 24280400 ..u.M..u?H..$(.. + 02f0 0064482b 04252800 00000f85 16010000 .dH+.%(......... + 0300 4881c438 0400005b 4889ef5d 4c89e241 H..8...[H..]L..A + 0310 5c4c89ee 415d4c89 f1415e41 5fe97efd \L..A]L..A^A_.~. + 0320 ffff660f 1f440000 4c894424 08e80000 ..f..D..L.D$.... + 0330 000083f8 014c8b44 240889c3 74abe800 .....L.D$...t... + 0340 00000085 c04c8b44 2408759d 488b0500 .....L.D$.u.H... + 0350 0000004c 63384439 fb0f8589 00000048 ...Lc8D9.......H + 0360 83ec0841 57488d05 04ffffff 4d89e950 ...AWH......M..P + 0370 31c931d2 6a004889 eebf0300 0000488d 1.1.j.H.......H. + 0380 5c244053 41504156 41544c8d 442458e8 \$@SAPAVATL.D$X. + 0390 00000000 4883c440 4585ff7e 7349c1e7 ....H..@E..~sI.. + 03a0 044a8d14 3b4889d8 c5f957c0 0f1f4000 .J..;H....W...@. + 03b0 c5fb5800 4883c010 4839d075 f3488b84 ..X.H...H9.u.H.. + 03c0 24280400 0064482b 04252800 00007546 $(...dH+.%(...uF + 03d0 4881c438 0400005b 5d415c41 5d415e41 H..8...[]A\A]A^A + 03e0 5fc3660f 1f440000 89dfe800 00000048 _.f..D.........H + 03f0 8b050000 00004c8b 4424084c 63384183 ......L.D$.Lc8A. + 0400 ff010f85 57ffffff e9dcfeff ff0f1f00 ....W........... + 0410 c5f957c0 eba7e800 000000 ..W........ /usr/lib64/libopenblas_openmp.a/ddot_k_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/ddot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ddot_k_SKYLAKEX.o (objdump) @@ -4,4 +4,4 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0020 010001c0 04000000 19080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/ddot_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/ddot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ddot_k_SKYLAKEX.o (objdump) @@ -3,19 +3,20 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 ec020000 0002510e 10860246 ..........Q....F - 0030 0d064d8f 038e048d 058c0683 07030d01 ..M............. - 0040 0c070847 c3c6cccd cecf0348 010c0610 ...G.......H.... - 0050 83078602 8c068d05 8e048f03 510c0708 ............Q... - 0060 c3c6cccd cecf0000 14000000 6c000000 ............l... - 0070 00000000 27000000 00440e10 620e0800 ....'....D..b... - 0080 84000000 84000000 00000000 7b010000 ............{... - 0090 00420e10 8f02420e 188e0345 0e208d04 .B....B....E. .. - 00a0 450e288c 05440e30 8606440e 38830747 E.(..D.0..D.8..G - 00b0 0ef00802 4a0a0e38 410e3044 0e28450e ....J..8A.0D.(E. - 00c0 20450e18 450e1042 0e084b0b 7b0ef808 E..E..B..K.{... - 00d0 420e8009 4b0e8809 460e9009 4e0e9809 B...K...F...N... - 00e0 420ea009 420ea809 420eb009 4e0ef008 B...B...B...N... - 00f0 7f0a0e38 410e3041 0e28420e 20420e18 ...8A.0A.(B. B.. - 0100 420e1042 0e08470b B..B..G. + 0010 1b0c0708 90010000 10000000 1c000000 ................ + 0020 00000000 9f000000 00000000 48000000 ............H... + 0030 30000000 00000000 cb010000 00420e10 0............B.. + 0040 8f02460e 188e0342 0e208d04 420e288c ..F....B. ..B.(. + 0050 05410e30 8606410e 38830744 0e500272 .A.0..A.8..D.P.r + 0060 0a0e3841 0e30410e 28420e20 420e1842 ..8A.0A.(B. B..B + 0070 0e10420e 08420b00 14000000 7c000000 ..B..B......|... + 0080 00000000 27000000 00440e10 620e0800 ....'....D..b... + 0090 84000000 94000000 00000000 7b010000 ............{... + 00a0 00420e10 8f02420e 188e0345 0e208d04 .B....B....E. .. + 00b0 450e288c 05440e30 8606440e 38830747 E.(..D.0..D.8..G + 00c0 0ef00802 4a0a0e38 410e3044 0e28450e ....J..8A.0D.(E. + 00d0 20450e18 450e1042 0e084b0b 7b0ef808 E..E..B..K.{... + 00e0 420e8009 4b0e8809 460e9009 4e0e9809 B...K...F...N... + 00f0 420ea009 420ea809 420eb009 4e0ef008 B...B...B...N... + 0100 7f0a0e38 410e3041 0e28420e 20420e18 ...8A.0A.(B. B.. + 0110 420e1042 0e08470b B..B..G. /usr/lib64/libopenblas_openmp.a/dgemv_n_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dgemv_n_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dgemv_n_COOPERLAKE.o (disasm) @@ -4,6 +4,88 @@ Disassembly of section .text: +dgemv_kernel_4x4: + mov (%rsi),%r9 + mov offset(%rsi),%r10 + mov offset(%rsi),%r11 + xor %eax,%eax + mov offset(%rsi),%rsi + vbroadcastsd (%rdx),%ymm12 + vbroadcastsd offset(%rdx),%ymm13 + vbroadcastsd offset(%rdx),%ymm14 + vbroadcastsd offset(%rdx),%ymm15 + vmovups (%r9,%rax,8),%ymm0 + vmovups (%r10,%rax,8),%ymm1 + vmovups (%r11,%rax,8),%ymm2 + vmovups (%rsi,%rax,8),%ymm3 + vbroadcastsd (%r8),%ymm6 + add $something,%rax + sub $something,%rdi + je + vmulpd %ymm0,%ymm12,%ymm4 + vmulpd %ymm1,%ymm13,%ymm5 + vmovups (%r9,%rax,8),%ymm0 + vmovups (%r10,%rax,8),%ymm1 + vfmadd231pd %ymm2,%ymm14,%ymm4 + vfmadd231pd %ymm3,%ymm15,%ymm5 + vmovups (%r11,%rax,8),%ymm2 + vmovups (%rsi,%rax,8),%ymm3 + vmovups -offset(%rcx,%rax,8),%ymm8 + vaddpd %ymm4,%ymm5,%ymm4 + vfmadd231pd %ymm6,%ymm4,%ymm8 + vmovups %ymm8,-offset(%rcx,%rax,8) + add $something,%rax + sub $something,%rdi + jne + vmulpd %ymm0,%ymm12,%ymm4 + vmulpd %ymm1,%ymm13,%ymm5 + vfmadd231pd %ymm2,%ymm14,%ymm4 + vfmadd231pd %ymm3,%ymm15,%ymm5 + vmovups -offset(%rcx,%rax,8),%ymm8 + vaddpd %ymm4,%ymm5,%ymm4 + vfmadd231pd %ymm6,%ymm4,%ymm8 + vmovups %ymm8,-offset(%rcx,%rax,8) + vzeroupper + vzeroupper + ret + data16 cs nopw offset(%rax,%rax,1) + nop + +dgemv_kernel_4x2: + mov (%rsi),%r9 + xor %eax,%eax + mov offset(%rsi),%rsi + vbroadcastsd (%rdx),%ymm12 + vbroadcastsd offset(%rdx),%ymm13 + vmovups (%r9,%rax,8),%ymm0 + vmovups (%rsi,%rax,8),%ymm1 + vbroadcastsd (%r8),%ymm6 + add $something,%rax + sub $something,%rdi + je + vmulpd %ymm0,%ymm12,%ymm4 + vmulpd %ymm1,%ymm13,%ymm5 + vmovups (%r9,%rax,8),%ymm0 + vmovups (%rsi,%rax,8),%ymm1 + vmovups -offset(%rcx,%rax,8),%ymm8 + vaddpd %ymm4,%ymm5,%ymm4 + vfmadd231pd %ymm6,%ymm4,%ymm8 + vmovups %ymm8,-offset(%rcx,%rax,8) + add $something,%rax + sub $something,%rdi + jne + vmulpd %ymm0,%ymm12,%ymm4 + vmulpd %ymm1,%ymm13,%ymm5 + vmovups -offset(%rcx,%rax,8),%ymm8 + vaddpd %ymm4,%ymm5,%ymm4 + vfmadd231pd %ymm6,%ymm4,%ymm8 + vmovups %ymm8,-offset(%rcx,%rax,8) + vzeroupper + vzeroupper + ret + data16 cs nopw offset(%rax,%rax,1) + nop + dgemv_kernel_4x1: xor %eax,%eax movsd (%rdx),%xmm12 @@ -46,433 +128,313 @@ data16 cs nopw offset(%rax,%rax,1) nopl (%rax) -dgemv_kernel_4x4.isra.0: - vmovsd (%rdx),%xmm2 - vmovsd offset(%rdx),%xmm3 - vmovsd offset(%rdx),%xmm4 - vmovsd offset(%rdx),%xmm5 - mov %edi,%eax - vbroadcastsd %xmm2,%ymm6 - vbroadcastsd %xmm3,%ymm7 - vbroadcastsd %xmm4,%ymm8 - vbroadcastsd %xmm5,%ymm9 - vbroadcastsd %xmm0,%ymm10 - vbroadcastsd %xmm2,%zmm2 - vbroadcastsd %xmm3,%zmm3 - vbroadcastsd %xmm4,%zmm4 - vbroadcastsd %xmm5,%zmm5 - vbroadcastsd %xmm0,%zmm0 - and $something,%eax - jle - dec %eax - shr $something,%eax - lea offset(%rax),%r10d - mov %r10,%rax - xor %edx,%edx - shl $something,%r10 - nopw offset(%rax,%rax,1) - mov offset(%rsi),%r9 - mov (%rsi),%r8 - vmulpd (%r9,%rdx,1),%zmm3,%zmm1 - vfmadd231pd (%r8,%rdx,1),%zmm2,%zmm1 - mov offset(%rsi),%r8 - vfmadd231pd (%r8,%rdx,1),%zmm4,%zmm1 - mov offset(%rsi),%r8 - vfmadd231pd (%r8,%rdx,1),%zmm5,%zmm1 - vfmadd213pd (%rcx,%rdx,1),%zmm0,%zmm1 - vmovupd %zmm1,(%rcx,%rdx,1) - add $something,%rdx - cmp %rdx,%r10 - jne - shl $something,%eax - movslq %eax,%rdx - cltq - cmp %rdx,%rdi - jle - nop - mov offset(%rsi),%r8 - mov (%rsi),%rdx - vmulpd (%r8,%rax,8),%ymm7,%ymm0 - vfmadd231pd (%rdx,%rax,8),%ymm6,%ymm0 - mov offset(%rsi),%rdx - vfmadd231pd (%rdx,%rax,8),%ymm8,%ymm0 - mov offset(%rsi),%rdx - vfmadd231pd (%rdx,%rax,8),%ymm9,%ymm0 - vfmadd213pd (%rcx,%rax,8),%ymm10,%ymm0 - vmovupd %ymm0,(%rcx,%rax,8) - add $something,%rax - cmp %rax,%rdi - jg - vzeroupper - ret - nop - xor %edx,%edx - xor %eax,%eax - jmp - cs nopw offset(%rax,%rax,1) - dgemv_n_COOPERLAKE: - lea offset(%rsp),%r10 - and $something,%rsp - push -offset(%r10) - mov %rdi,%rax - push %rbp - mov %rsp,%rbp push %r15 push %r14 push %r13 push %r12 - push %r10 + push %rbp push %rbx sub $something,%rsp - mov offset(%r10),%rdi - mov %rcx,-offset(%rbp) - mov %rdi,-offset(%rbp) - mov offset(%r10),%rdi - mov (%r10),%rcx - mov %rdi,-offset(%rbp) - mov offset(%r10),%rdi - mov %rsi,-offset(%rbp) - mov %r8,-offset(%rbp) - mov %r9,-offset(%rbp) - mov %rcx,-offset(%rbp) - mov %rdi,-offset(%rbp) - vmovsd %xmm0,-offset(%rbp) + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %rsi,offset(%rsp) + mov %r8,offset(%rsp) + mov %r9,offset(%rsp) + mov %rcx,offset(%rsp) + vmovsd %xmm0,offset(%rsp) + mov offset(%rsp),%r12 mov %fs:0x28,%rdx - mov %rdx,-offset(%rbp) + mov %rdx,offset(%rsp) xor %edx,%edx /usr/lib64/libopenblas_openmp.a/dgemv_n_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dgemv_n_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dgemv_n_COOPERLAKE.o (objdump) @@ -2,206 +2,185 @@ /usr/lib64/libopenblas_openmp.a/dgemv_n_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 31c0f244 0f1022f2 450f5920 66450fc6 1..D..".E.Y fE.. - 0010 e400440f 1004c644 0f104cc6 100f1024 ..D....D..L....$ - 0020 c10f106c c1106645 0f59c466 450f59cc ...l..fE.Y.fE.Y. - 0030 66410f58 e066410f 58e90f11 24c10f11 fA.X.fA.X...$... - 0040 6cc11048 83c00448 83ef0475 c5c5f877 l..H...H...u...w - 0050 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. - 0060 4883f901 742b4885 ff7e2648 c1e10348 H...t+H..~&H...H - 0070 8d04fe0f 1f440000 c5fb1002 4883c608 .....D......H... - 0080 c5fb5846 f8c5fb11 024801ca 4839f075 ..XF.....H..H9.u - 0090 e7c36666 2e0f1f84 00000000 000f1f00 ..ff............ - 00a0 c5fb1012 c5fb105a 08c5fb10 6210c5fb .......Z....b... - 00b0 106a1889 f8c4e27d 19f2c4e2 7d19fbc4 .j.....}....}... - 00c0 627d19c4 c4627d19 cdc4627d 19d062f2 b}...b}...b}..b. - 00d0 fd4819d2 62f2fd48 19db62f2 fd4819e4 .H..b..H..b..H.. - 00e0 62f2fd48 19ed62f2 fd4819c0 83e0f80f b..H..b..H...... - 00f0 8eab0000 00ffc8c1 e803448d 50014c89 ..........D.P.L. - 0100 d031d249 c1e20666 0f1f8400 00000000 .1.I...f........ - 0110 4c8b4e08 4c8b0662 d1e54859 0c1162d2 L.N.L..b..HY..b. - 0120 ed48b80c 104c8b46 1062d2dd 48b80c10 .H...L.F.b..H... - 0130 4c8b4618 62d2d548 b80c1062 f2fd48a8 L.F.b..H...b..H. - 0140 0c1162f1 fd48110c 114883c2 404939d2 ..b..H...H..@I9. - 0150 75bec1e0 034863d0 48984839 d77e3c90 u....Hc.H.H9.~<. - 0160 4c8b4608 488b16c4 c1455904 c0c4e2cd L.F.H....EY..... - 0170 b804c248 8b5610c4 e2bdb804 c2488b56 ...H.V.......H.V - 0180 18c4e2b5 b804c2c4 e2ada804 c1c5fd11 ................ - 0190 04c14883 c0044839 c77fc5c5 f877c390 ..H...H9.....w.. - 01a0 31d231c0 ebb2662e 0f1f8400 00000000 1.1...f......... - 01b0 4c8d5424 084883e4 e041ff72 f84889f8 L.T$.H...A.r.H.. - 01c0 554889e5 41574156 41554154 41525348 UH..AWAVAUATARSH - 01d0 81ec6001 0000498b 7a084889 8d18ffff ..`...I.z.H..... - 01e0 ff4889bd 00ffffff 498b7a10 498b0a48 .H......I.z.I..H - 01f0 89bdf8fe ffff498b 7a184889 b5c8feff ......I.z.H..... - 0200 ff4c8985 90feffff 4c898de8 feffff48 .L......L......H - 0210 898de0fe ffff4889 bd10ffff ffc5fb11 ......H......... - 0220 8558ffff ff64488b 14252800 00004889 .X...dH..%(...H. - 0230 55c831d2 4885f60f 8e530400 004885c0 U.1.H....S...H.. - 0240 0f8e4a04 00004889 f74889c3 83e60383 ..J...H..H...... - 0250 e3034889 b5c0feff ff4889c6 25ff0700 ..H......H..%... - 0260 004829d8 488985b0 feffff4c 8d34cd00 .H).H......L.4.. - 0270 00000048 c1e00348 c1e10548 c1ff0248 ...H...H...H...H - 0280 8985a8fe ffff4889 c8480faf c74d89c4 ......H..H...M.. - 0290 49c1e405 4c01c848 8985b8fe ffff4889 I...L..H......H. - 02a0 f8490faf c44889bd 40ffffff 48c1e705 .I...H..@...H... - 02b0 488985d0 feffff48 89f84889 9d98feff H......H..H..... - 02c0 ff4883e6 fc4a8d1c c5000000 004c01c8 .H...J.......L.. - 02d0 49c1e004 4889b5d8 feffff48 899df0fe I...H......H.... - 02e0 ffff4c89 8588feff ff48898d 28ffffff ..L......H..(... - 02f0 488985a0 feffff66 0f1f8400 00000000 H......f........ - 0300 4881add8 feffff00 08000048 c78508ff H..........H.... - 0310 ffff0040 000048c7 8520ffff ff000800 ...@..H.. ...... - 0320 000f88d9 04000048 8b8518ff ffff4989 .......H......I. - 0330 c7488985 60ffffff 488b85f0 feffff49 .H..`...H......I - 0340 01c7498d 1c074c8d 2c034883 bdf8feff ..I...L.,.H..... - 0350 ff014c89 bd68ffff ff48899d 70ffffff ..L..h...H..p... - 0360 4c89ad78 ffffff0f 846b0300 00488b85 L..x.....k...H.. - 0370 20ffffff 488bbd10 ffffff48 8d14c500 ...H......H.... - 0380 00000031 f6c5f877 e8000000 004883bd ...1...w.....H.. - 0390 e0feffff 010f8459 03000048 83bd40ff .......Y...H..@. - 03a0 ffff000f 84f70400 00488d4d 80488bbd .........H.M.H.. - 03b0 e8feffff 48898d30 ffffff4c 89f1488b ....H..0...L..H. - 03c0 8518ffff ff48f7d9 48898d38 ffffff4e .....H..H..8...N - 03d0 8d1c3762 e1ff0810 45eb488b bd20ffff ..7b....E.H.. .. - 03e0 ff488b8d 10ffffff 4e8d1420 4c01e34b .H......N.. L..K - 03f0 8d04274d 01e54531 ff488db5 60ffffff ..'M..E1.H..`... - 0400 c5f8770f 1f440000 48898550 ffffff48 ..w..D..H..P...H - 0410 8b8538ff ffff488b 9530ffff ffc4c17b ..8...H..0.....{ - 0420 1004034c 899548ff ffffc5fb 114580c4 ...L..H......E.. - 0430 c17b1003 49ffc7c5 fb114588 c4817b10 .{..I.....E...{. - 0440 0433c5fb 114590c4 817b1004 73c5fb11 .3...E...{..s... - 0450 459862b1 ff0010c0 e843fcff ff4c8b95 E.b......C...L.. - 0460 48ffffff 488b8550 ffffff4c 899560ff H...H..P...L..`. - 0470 ffff4889 8568ffff ff48899d 70ffffff ..H..h...H..p... - 0480 4c89ad78 ffffff4d 01e24c01 e04c01e3 L..x...M..L..L.. - 0490 4d01e54c 039d28ff ffff4c39 bd40ffff M..L..(...L9.@.. - 04a0 ff0f8561 ffffff48 8bb518ff ffff4c8b ...a...H......L. - 04b0 8db8feff ff4803b5 d0feffff 4c8badc0 .....H......L... - 04c0 feffff4d 85ed7446 4c8b9df0 feffff48 ...M..tFL......H - 04d0 8b9d20ff ffff488b 8d10ffff ff4531d2 .. ...H......E1. - 04e0 4c8d8558 ffffff48 8d5580c5 f877c4c1 L..X...H.U...w.. - 04f0 7b100148 89df49ff c2c5fb11 45804d01 {..H..I.....E.M. - 0500 f1e8fafa ffff4c01 de4d39d5 75e0488b ......L..M9.u.H. - 0510 bd08ffff ff488b9d f8feffff 4801bd18 .....H......H... - 0520 ffffff48 83fb010f 84930100 004c8b85 ...H.........L.. - 0530 00ffffff 488bbd20 ffffff48 8bb510ff ....H.. ...H.... - 0540 ffff4889 d94c89c2 e813fbff ff4889f8 ..H..L.......H.. - 0550 480fafc3 498d04c0 48898500 ffffff48 H...I...H......H - 0560 81bd20ff ffff0008 00000f84 90fdffff .. ............. - 0570 488bbd98 feffff48 85ff0f84 46030000 H......H....F... - 0580 4883bde0 feffff01 0f94c048 83ff030f H..........H.... - 0590 84bf0400 004883bd 98feffff 020f842b .....H.........+ - 05a0 03000048 83bd90fe ffff010f 855e0400 ...H.........^.. - 05b0 0084c00f 84560400 00488b95 c8feffff .....V...H...... - 05c0 4883e2fc 0f849d06 000048ff ca48c1ea H.........H..H.. - 05d0 0248ffc2 488bbd18 ffffff48 89d648c1 .H..H......H..H. - 05e0 e605488b 8de8feff ff4889f8 4801fec5 ..H......H..H... - 05f0 f157c90f 1f440000 c5fb1040 08c5fb10 .W...D.....@.... - 0600 30c5fb59 4108c5fb 10781048 83c02048 0..YA....x.H.. H - 0610 83c120c4 e2c9b941 e0c5fb10 70f8c4e2 .. ....A....p... - 0620 c1b941f0 c4e2c9b9 41f8c5f3 58c84839 ..A.....A...X.H9 - 0630 c675c548 c1e20248 3995c8fe ffff7e2b .u.H...H9.....~+ - 0640 488b85c8 feffff48 8b8d18ff ffff488b H......H......H. - 0650 b5e8feff ff0f1f00 c5fb103c d1c4e2c1 ...........<.... - 0660 b90cd648 ffc24839 d07fed48 8b8500ff ...H..H9...H.... - 0670 ffffc5fb 1038c4e2 c1998d58 ffffffc5 .....8.....X.... - 0680 fb1108c5 f877662e 0f1f8400 00000000 .....wf......... - 0690 488b45c8 64482b04 25280000 000f8500 H.E.dH+.%(...... - 06a0 06000048 81c46001 00005b41 5a415c41 ...H..`...[AZA\A - 06b0 5d415e41 5f31c05d 498d62f8 c30f1f00 ]A^A_1.]I.b..... - 06c0 488b8d08 ffffff48 018d00ff ffffe98c H......H........ - 06d0 feffff0f 1f440000 488b8500 ffffff48 .....D..H......H - 06e0 83bde0fe ffff0148 898510ff ffff0f85 .......H........ - 06f0 a7fcffff 4883bd40 ffffff00 0f84b101 ....H..@........ - 0700 0000488b 8518ffff ff488b95 e8feffff ..H......H...... - 0710 62e1ff08 1045eb48 8bbd20ff ffff488b b....E.H.. ...H. - 0720 8d10ffff ff4c89b5 48ffffff 4f8d1c27 .....L..H...O..' - 0730 4c01e04c 01e34d01 e54531ff 488db560 L..L..M..E1.H..` - 0740 ffffff49 89d6c5f8 770f1f80 00000000 ...I....w....... - 0750 4c89f262 b1ff0010 c0488985 50ffffff L..b.....H..P... - 0760 e83bf9ff ff488b85 50ffffff 49ffc748 .;...H..P...I..H - 0770 898560ff ffff4c89 9d68ffff ff48899d ..`...L..h...H.. - 0780 70ffffff 4c89ad78 ffffff49 83c6204c p...L..x...I.. L - 0790 01e04d01 e34c01e3 4d01e54c 39bd40ff ..M..L..M..L9.@. - 07a0 ffff75ac 488bb518 ffffff4c 8bb548ff ..u.H......L..H. - 07b0 ffff4c8b 8da0feff ff4803b5 d0feffff ..L......H...... - 07c0 f685c8fe ffff0275 67f685c8 feffff01 .......ug....... - 07d0 0f8438fd ffff488b 8d10ffff ff488bbd ..8...H......H.. - 07e0 20ffffff 4c8d8558 ffffff4c 89cac5f8 ...L..X...L.... - 07f0 77e80af8 ffffe913 fdffff0f 1f440000 w............D.. - 0800 488b85b0 feffff48 85c00f84 60fdffff H......H....`... - 0810 488bbda8 feffff48 898520ff ffff4889 H......H.. ...H. - 0820 bd08ffff ffe9fdfa ffff660f 1f440000 ..........f..D.. - 0830 4883bd20 ffffff00 c4c27d19 09c4c27d H.. ......}....} - 0840 195108c4 e27d199d 58ffffff 7e41488b .Q...}..X...~AH. - 0850 8d60ffff ff488b95 68ffffff 4c8b8520 .`...H..h...L.. - 0860 ffffff48 8bbd10ff ffff31c0 0f1f4000 ...H......1...@. - 0870 c5ed5904 c2c4e2f5 b804c1c4 e2e5a804 ..Y............. - 0880 c7c5fd11 04c74883 c0044939 c07fe148 ......H...I9...H - 0890 03b588fe ffff4983 c110e92a ffffff90 ......I....*.... - 08a0 4c8b8de8 feffff48 8bb518ff ffffe909 L......H........ - 08b0 fcffff4c 8b8de8fe ffff488b b518ffff ...L......H..... - 08c0 ffe9fafe ffffc5f8 77e9c2fd ffff4883 ........w.....H. - 08d0 bd90feff ff020f85 f1020000 84c00f84 ................ - 08e0 e9020000 488b8dc8 feffff48 83e1fc0f ....H......H.... - 08f0 84900300 00c5f957 c0488b85 18ffffff .......W.H...... - 0900 488bb5e8 feffffc5 fb10d031 d2c5fb10 H..........1.... - 0910 64d608c5 fb100cd6 c5db5958 10c5db59 d.........YX...Y - 0920 60184883 c040c4e2 f1b958c0 c4e2d999 `.H..@....X..... - 0930 48c8c5e3 58d2c5fb 105cd618 c5f358c0 H...X....\....X. - 0940 c5e35960 f0c5e359 58f8c5fb 104cd610 ..Y`...YX....L.. - 0950 4883c204 c4e2f1b9 60e0c4e2 e19948e8 H.......`.....H. - 0960 c5db58d2 c5f358c0 4839ca7c a048ffc9 ..X...X.H9.|.H.. - 0970 48c1e902 48ffc148 89c848c1 e0064801 H...H..H..H...H. - 0980 8518ffff ff4889c8 48c1e005 48c1e102 .....H..H...H... - 0990 480185e8 feffff48 398dc8fe ffff7e3b H......H9.....~; - 09a0 488bbde8 feffff48 89c848f7 d8488bb5 H......H..H..H.. - 09b0 c8feffff 488b9518 ffffff48 8d04c7c5 ....H......H.... - 09c0 fb100cc8 48ffc1c4 e2f1b912 c4e2f1b9 ....H........... - 09d0 42084883 c2104839 ce7fe448 8b8500ff B.H...H9...H.... - 09e0 ffffc5fb 108d58ff ffff488b 8df8feff ......X...H..... - 09f0 ffc4e2f1 a910c5fb 1110488d 04c8c4e2 ..........H..... - 0a00 f9a908c5 fb1108c5 f877e981 fcffff48 .........w.....H - 0a10 8bb5f0fe ffff488b bdc8feff ff488b95 ......H......H.. - 0a20 18ffffff 488b8de8 feffffc5 f157c931 ....H........W.1 - 0a30 c00f1f80 00000000 c5fb1032 48ffc0c4 ...........2H... - 0a40 e2c9b909 4801f24c 01f14839 c77fe9e9 ....H..L..H9.... - 0a50 17fcffff 4883bd90 feffff03 0f85b301 ....H........... - 0a60 000084c0 0f84ab01 0000488b 8dc8feff ..........H..... - 0a70 ff4883e1 fc0f8417 020000c5 f957c048 .H...........W.H - 0a80 8b8518ff ffff488b b5e8feff ffc5fb10 ......H......... - 0a90 d0c5fb10 d831d2c5 fb106cd6 08c5fb10 .....1....l..... - 0aa0 0cd6c5d3 59601848 83c060c4 e2f1b960 ....Y`.H..`....` - 0ab0 a0c5db58 dbc5d359 60c0c5d3 5968c8c4 ...X...Y`...Yh.. - 0ac0 e2f1b960 a8c4e2d1 9948b0c5 fb106cd6 ...`.....H....l. - 0ad0 18c5db58 d2c5d359 60e8c5f3 58c0c5fb ...X...Y`...X... - 0ae0 104cd610 4883c204 c4e2f1b9 60d0c5db .L..H.......`... - 0af0 58dbc5d3 5960f0c5 d35968f8 c4e2f1b9 X...Y`...Yh..... - 0b00 60d8c4e2 d19948e0 c5db58d2 c5f358c0 `.....H...X...X. - 0b10 4839ca7c 8248ffc9 48c1e902 48ffc148 H9.|.H..H...H..H - 0b20 8d044948 c1e00548 018518ff ffff4889 ..IH...H......H. - 0b30 c848c1e0 0548c1e1 02480185 e8feffff .H...H...H...... - 0b40 48398dc8 feffff7e 41488bbd e8feffff H9.....~AH...... - 0b50 4889c848 f7d8488b b5c8feff ff488b95 H..H..H......H.. - 0b60 18ffffff 488d04c7 c5fb100c c848ffc1 ....H........H.. - 0b70 c4e2f1b9 1ac4e2f1 b95208c4 e2f1b942 .........R.....B - 0b80 104883c2 184839ce 7fdec5fb 108d58ff .H...H9.......X. - 0b90 ffff488b 8500ffff ff488b95 f8feffff ..H......H...... - 0ba0 c4e2f1a9 1848c1e2 03c5fb11 184801d0 .....H.......H.. - 0bb0 c4e2f1a9 10c5fb11 104801d0 c4e2f9a9 .........H...... - 0bc0 08c5fb11 08c5f877 e9c3faff ffc5f957 .......w.......W - 0bd0 c0488bb5 f0feffff 488bbdc8 feffff48 .H......H......H - 0be0 8b9518ff ffff488b 8de8feff ffc5fb10 ......H......... - 0bf0 d031c0c5 fb100948 ffc0c4e2 f1b912c4 .1.....H........ - 0c00 e2f1b942 084c01f1 4801f248 39c77fe3 ...B.L..H..H9... - 0c10 e9c6fdff ffc5f957 c0488bb5 f0feffff .......W.H...... /usr/lib64/libopenblas_openmp.a/dgemv_n_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dgemv_n_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dgemv_n_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39000000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dgemv_n_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dgemv_n_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dgemv_n_COOPERLAKE.o (objdump) @@ -4,11 +4,13 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 10000000 1c000000 ................ - 0020 00000000 51000000 00000000 10000000 ....Q........... - 0030 30000000 00000000 32000000 00000000 0.......2....... - 0040 10000000 44000000 00000000 06010000 ....D........... - 0050 00000000 48000000 58000000 00000000 ....H...X....... - 0060 f80a0000 00450c0a 004f1006 0276004a .....E...O...v.J - 0070 0f037658 06100f02 7678100e 02767010 ..vX....vx...vp. - 0080 0d027668 100c0276 60481003 02765003 ..vh...v`H...vP. - 0090 d7040a0c 0a004f0c 0708440b 00000000 ......O...D..... + 0020 00000000 c4000000 00000000 10000000 ................ + 0030 30000000 00000000 84000000 00000000 0............... + 0040 10000000 44000000 00000000 51000000 ....D.......Q... + 0050 00000000 10000000 58000000 00000000 ........X....... + 0060 32000000 00000000 4c000000 6c000000 2.......L...l... + 0070 00000000 5a090000 00420e10 8f02420e ....Z....B....B. + 0080 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 + 0090 8606410e 38830747 0ee00203 55040a0e ..A.8..G....U... + 00a0 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 00b0 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/dgemv_n_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dgemv_n_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dgemv_n_SKYLAKEX.o (disasm) @@ -4,6 +4,88 @@ Disassembly of section .text: +dgemv_kernel_4x4: + mov (%rsi),%r9 + mov offset(%rsi),%r10 + mov offset(%rsi),%r11 + xor %eax,%eax + mov offset(%rsi),%rsi + vbroadcastsd (%rdx),%ymm12 + vbroadcastsd offset(%rdx),%ymm13 + vbroadcastsd offset(%rdx),%ymm14 + vbroadcastsd offset(%rdx),%ymm15 + vmovups (%r9,%rax,8),%ymm0 + vmovups (%r10,%rax,8),%ymm1 + vmovups (%r11,%rax,8),%ymm2 + vmovups (%rsi,%rax,8),%ymm3 + vbroadcastsd (%r8),%ymm6 + add $something,%rax + sub $something,%rdi + je + vmulpd %ymm0,%ymm12,%ymm4 + vmulpd %ymm1,%ymm13,%ymm5 + vmovups (%r9,%rax,8),%ymm0 + vmovups (%r10,%rax,8),%ymm1 + vfmadd231pd %ymm2,%ymm14,%ymm4 + vfmadd231pd %ymm3,%ymm15,%ymm5 + vmovups (%r11,%rax,8),%ymm2 + vmovups (%rsi,%rax,8),%ymm3 + vmovups -offset(%rcx,%rax,8),%ymm8 + vaddpd %ymm4,%ymm5,%ymm4 + vfmadd231pd %ymm6,%ymm4,%ymm8 + vmovups %ymm8,-offset(%rcx,%rax,8) + add $something,%rax + sub $something,%rdi + jne + vmulpd %ymm0,%ymm12,%ymm4 + vmulpd %ymm1,%ymm13,%ymm5 + vfmadd231pd %ymm2,%ymm14,%ymm4 + vfmadd231pd %ymm3,%ymm15,%ymm5 + vmovups -offset(%rcx,%rax,8),%ymm8 + vaddpd %ymm4,%ymm5,%ymm4 + vfmadd231pd %ymm6,%ymm4,%ymm8 + vmovups %ymm8,-offset(%rcx,%rax,8) + vzeroupper + vzeroupper + ret + data16 cs nopw offset(%rax,%rax,1) + nop + +dgemv_kernel_4x2: + mov (%rsi),%r9 + xor %eax,%eax + mov offset(%rsi),%rsi + vbroadcastsd (%rdx),%ymm12 + vbroadcastsd offset(%rdx),%ymm13 + vmovups (%r9,%rax,8),%ymm0 + vmovups (%rsi,%rax,8),%ymm1 + vbroadcastsd (%r8),%ymm6 + add $something,%rax + sub $something,%rdi + je + vmulpd %ymm0,%ymm12,%ymm4 + vmulpd %ymm1,%ymm13,%ymm5 + vmovups (%r9,%rax,8),%ymm0 + vmovups (%rsi,%rax,8),%ymm1 + vmovups -offset(%rcx,%rax,8),%ymm8 + vaddpd %ymm4,%ymm5,%ymm4 + vfmadd231pd %ymm6,%ymm4,%ymm8 + vmovups %ymm8,-offset(%rcx,%rax,8) + add $something,%rax + sub $something,%rdi + jne + vmulpd %ymm0,%ymm12,%ymm4 + vmulpd %ymm1,%ymm13,%ymm5 + vmovups -offset(%rcx,%rax,8),%ymm8 + vaddpd %ymm4,%ymm5,%ymm4 + vfmadd231pd %ymm6,%ymm4,%ymm8 + vmovups %ymm8,-offset(%rcx,%rax,8) + vzeroupper + vzeroupper + ret + data16 cs nopw offset(%rax,%rax,1) + nop + dgemv_kernel_4x1: xor %eax,%eax movsd (%rdx),%xmm12 @@ -46,433 +128,313 @@ data16 cs nopw offset(%rax,%rax,1) nopl (%rax) -dgemv_kernel_4x4.isra.0: - vmovsd (%rdx),%xmm2 - vmovsd offset(%rdx),%xmm3 - vmovsd offset(%rdx),%xmm4 - vmovsd offset(%rdx),%xmm5 - mov %edi,%eax - vbroadcastsd %xmm2,%ymm6 - vbroadcastsd %xmm3,%ymm7 - vbroadcastsd %xmm4,%ymm8 - vbroadcastsd %xmm5,%ymm9 - vbroadcastsd %xmm0,%ymm10 - vbroadcastsd %xmm2,%zmm2 - vbroadcastsd %xmm3,%zmm3 - vbroadcastsd %xmm4,%zmm4 - vbroadcastsd %xmm5,%zmm5 - vbroadcastsd %xmm0,%zmm0 - and $something,%eax - jle - dec %eax - shr $something,%eax - lea offset(%rax),%r10d - mov %r10,%rax - xor %edx,%edx - shl $something,%r10 - nopw offset(%rax,%rax,1) - mov offset(%rsi),%r9 - mov (%rsi),%r8 - vmulpd (%r9,%rdx,1),%zmm3,%zmm1 - vfmadd231pd (%r8,%rdx,1),%zmm2,%zmm1 - mov offset(%rsi),%r8 - vfmadd231pd (%r8,%rdx,1),%zmm4,%zmm1 - mov offset(%rsi),%r8 - vfmadd231pd (%r8,%rdx,1),%zmm5,%zmm1 - vfmadd213pd (%rcx,%rdx,1),%zmm0,%zmm1 - vmovupd %zmm1,(%rcx,%rdx,1) - add $something,%rdx - cmp %rdx,%r10 - jne - shl $something,%eax - movslq %eax,%rdx - cltq - cmp %rdx,%rdi - jle - nop - mov offset(%rsi),%r8 - mov (%rsi),%rdx - vmulpd (%r8,%rax,8),%ymm7,%ymm0 - vfmadd231pd (%rdx,%rax,8),%ymm6,%ymm0 - mov offset(%rsi),%rdx - vfmadd231pd (%rdx,%rax,8),%ymm8,%ymm0 - mov offset(%rsi),%rdx - vfmadd231pd (%rdx,%rax,8),%ymm9,%ymm0 - vfmadd213pd (%rcx,%rax,8),%ymm10,%ymm0 - vmovupd %ymm0,(%rcx,%rax,8) - add $something,%rax - cmp %rax,%rdi - jg - vzeroupper - ret - nop - xor %edx,%edx - xor %eax,%eax - jmp - cs nopw offset(%rax,%rax,1) - dgemv_n_SKYLAKEX: - lea offset(%rsp),%r10 - and $something,%rsp - push -offset(%r10) - mov %rdi,%rax - push %rbp - mov %rsp,%rbp push %r15 push %r14 push %r13 push %r12 - push %r10 + push %rbp push %rbx sub $something,%rsp - mov offset(%r10),%rdi - mov %rcx,-offset(%rbp) - mov %rdi,-offset(%rbp) - mov offset(%r10),%rdi - mov (%r10),%rcx - mov %rdi,-offset(%rbp) - mov offset(%r10),%rdi - mov %rsi,-offset(%rbp) - mov %r8,-offset(%rbp) - mov %r9,-offset(%rbp) - mov %rcx,-offset(%rbp) - mov %rdi,-offset(%rbp) - vmovsd %xmm0,-offset(%rbp) + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %rsi,offset(%rsp) + mov %r8,offset(%rsp) + mov %r9,offset(%rsp) + mov %rcx,offset(%rsp) + vmovsd %xmm0,offset(%rsp) + mov offset(%rsp),%r12 mov %fs:0x28,%rdx - mov %rdx,-offset(%rbp) + mov %rdx,offset(%rsp) xor %edx,%edx /usr/lib64/libopenblas_openmp.a/dgemv_n_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dgemv_n_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dgemv_n_SKYLAKEX.o (objdump) @@ -2,206 +2,185 @@ /usr/lib64/libopenblas_openmp.a/dgemv_n_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 31c0f244 0f1022f2 450f5920 66450fc6 1..D..".E.Y fE.. - 0010 e400440f 1004c644 0f104cc6 100f1024 ..D....D..L....$ - 0020 c10f106c c1106645 0f59c466 450f59cc ...l..fE.Y.fE.Y. - 0030 66410f58 e066410f 58e90f11 24c10f11 fA.X.fA.X...$... - 0040 6cc11048 83c00448 83ef0475 c5c5f877 l..H...H...u...w - 0050 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. - 0060 4883f901 742b4885 ff7e2648 c1e10348 H...t+H..~&H...H - 0070 8d04fe0f 1f440000 c5fb1002 4883c608 .....D......H... - 0080 c5fb5846 f8c5fb11 024801ca 4839f075 ..XF.....H..H9.u - 0090 e7c36666 2e0f1f84 00000000 000f1f00 ..ff............ - 00a0 c5fb1012 c5fb105a 08c5fb10 6210c5fb .......Z....b... - 00b0 106a1889 f8c4e27d 19f2c4e2 7d19fbc4 .j.....}....}... - 00c0 627d19c4 c4627d19 cdc4627d 19d062f2 b}...b}...b}..b. - 00d0 fd4819d2 62f2fd48 19db62f2 fd4819e4 .H..b..H..b..H.. - 00e0 62f2fd48 19ed62f2 fd4819c0 83e0f80f b..H..b..H...... - 00f0 8eab0000 00ffc8c1 e803448d 50014c89 ..........D.P.L. - 0100 d031d249 c1e20666 0f1f8400 00000000 .1.I...f........ - 0110 4c8b4e08 4c8b0662 d1e54859 0c1162d2 L.N.L..b..HY..b. - 0120 ed48b80c 104c8b46 1062d2dd 48b80c10 .H...L.F.b..H... - 0130 4c8b4618 62d2d548 b80c1062 f2fd48a8 L.F.b..H...b..H. - 0140 0c1162f1 fd48110c 114883c2 404939d2 ..b..H...H..@I9. - 0150 75bec1e0 034863d0 48984839 d77e3c90 u....Hc.H.H9.~<. - 0160 4c8b4608 488b16c4 c1455904 c0c4e2cd L.F.H....EY..... - 0170 b804c248 8b5610c4 e2bdb804 c2488b56 ...H.V.......H.V - 0180 18c4e2b5 b804c2c4 e2ada804 c1c5fd11 ................ - 0190 04c14883 c0044839 c77fc5c5 f877c390 ..H...H9.....w.. - 01a0 31d231c0 ebb2662e 0f1f8400 00000000 1.1...f......... - 01b0 4c8d5424 084883e4 e041ff72 f84889f8 L.T$.H...A.r.H.. - 01c0 554889e5 41574156 41554154 41525348 UH..AWAVAUATARSH - 01d0 81ec6001 0000498b 7a084889 8d18ffff ..`...I.z.H..... - 01e0 ff4889bd 00ffffff 498b7a10 498b0a48 .H......I.z.I..H - 01f0 89bdf8fe ffff498b 7a184889 b5c8feff ......I.z.H..... - 0200 ff4c8985 90feffff 4c898de8 feffff48 .L......L......H - 0210 898de0fe ffff4889 bd10ffff ffc5fb11 ......H......... - 0220 8558ffff ff64488b 14252800 00004889 .X...dH..%(...H. - 0230 55c831d2 4885f60f 8e530400 004885c0 U.1.H....S...H.. - 0240 0f8e4a04 00004889 f74889c3 83e60383 ..J...H..H...... - 0250 e3034889 b5c0feff ff4889c6 25ff0700 ..H......H..%... - 0260 004829d8 488985b0 feffff4c 8d34cd00 .H).H......L.4.. - 0270 00000048 c1e00348 c1e10548 c1ff0248 ...H...H...H...H - 0280 8985a8fe ffff4889 c8480faf c74d89c4 ......H..H...M.. - 0290 49c1e405 4c01c848 8985b8fe ffff4889 I...L..H......H. - 02a0 f8490faf c44889bd 40ffffff 48c1e705 .I...H..@...H... - 02b0 488985d0 feffff48 89f84889 9d98feff H......H..H..... - 02c0 ff4883e6 fc4a8d1c c5000000 004c01c8 .H...J.......L.. - 02d0 49c1e004 4889b5d8 feffff48 899df0fe I...H......H.... - 02e0 ffff4c89 8588feff ff48898d 28ffffff ..L......H..(... - 02f0 488985a0 feffff66 0f1f8400 00000000 H......f........ - 0300 4881add8 feffff00 08000048 c78508ff H..........H.... - 0310 ffff0040 000048c7 8520ffff ff000800 ...@..H.. ...... - 0320 000f88d9 04000048 8b8518ff ffff4989 .......H......I. - 0330 c7488985 60ffffff 488b85f0 feffff49 .H..`...H......I - 0340 01c7498d 1c074c8d 2c034883 bdf8feff ..I...L.,.H..... - 0350 ff014c89 bd68ffff ff48899d 70ffffff ..L..h...H..p... - 0360 4c89ad78 ffffff0f 846b0300 00488b85 L..x.....k...H.. - 0370 20ffffff 488bbd10 ffffff48 8d14c500 ...H......H.... - 0380 00000031 f6c5f877 e8000000 004883bd ...1...w.....H.. - 0390 e0feffff 010f8459 03000048 83bd40ff .......Y...H..@. - 03a0 ffff000f 84f70400 00488d4d 80488bbd .........H.M.H.. - 03b0 e8feffff 48898d30 ffffff4c 89f1488b ....H..0...L..H. - 03c0 8518ffff ff48f7d9 48898d38 ffffff4e .....H..H..8...N - 03d0 8d1c3762 e1ff0810 45eb488b bd20ffff ..7b....E.H.. .. - 03e0 ff488b8d 10ffffff 4e8d1420 4c01e34b .H......N.. L..K - 03f0 8d04274d 01e54531 ff488db5 60ffffff ..'M..E1.H..`... - 0400 c5f8770f 1f440000 48898550 ffffff48 ..w..D..H..P...H - 0410 8b8538ff ffff488b 9530ffff ffc4c17b ..8...H..0.....{ - 0420 1004034c 899548ff ffffc5fb 114580c4 ...L..H......E.. - 0430 c17b1003 49ffc7c5 fb114588 c4817b10 .{..I.....E...{. - 0440 0433c5fb 114590c4 817b1004 73c5fb11 .3...E...{..s... - 0450 459862b1 ff0010c0 e843fcff ff4c8b95 E.b......C...L.. - 0460 48ffffff 488b8550 ffffff4c 899560ff H...H..P...L..`. - 0470 ffff4889 8568ffff ff48899d 70ffffff ..H..h...H..p... - 0480 4c89ad78 ffffff4d 01e24c01 e04c01e3 L..x...M..L..L.. - 0490 4d01e54c 039d28ff ffff4c39 bd40ffff M..L..(...L9.@.. - 04a0 ff0f8561 ffffff48 8bb518ff ffff4c8b ...a...H......L. - 04b0 8db8feff ff4803b5 d0feffff 4c8badc0 .....H......L... - 04c0 feffff4d 85ed7446 4c8b9df0 feffff48 ...M..tFL......H - 04d0 8b9d20ff ffff488b 8d10ffff ff4531d2 .. ...H......E1. - 04e0 4c8d8558 ffffff48 8d5580c5 f877c4c1 L..X...H.U...w.. - 04f0 7b100148 89df49ff c2c5fb11 45804d01 {..H..I.....E.M. - 0500 f1e8fafa ffff4c01 de4d39d5 75e0488b ......L..M9.u.H. - 0510 bd08ffff ff488b9d f8feffff 4801bd18 .....H......H... - 0520 ffffff48 83fb010f 84930100 004c8b85 ...H.........L.. - 0530 00ffffff 488bbd20 ffffff48 8bb510ff ....H.. ...H.... - 0540 ffff4889 d94c89c2 e813fbff ff4889f8 ..H..L.......H.. - 0550 480fafc3 498d04c0 48898500 ffffff48 H...I...H......H - 0560 81bd20ff ffff0008 00000f84 90fdffff .. ............. - 0570 488bbd98 feffff48 85ff0f84 46030000 H......H....F... - 0580 4883bde0 feffff01 0f94c048 83ff030f H..........H.... - 0590 84bf0400 004883bd 98feffff 020f842b .....H.........+ - 05a0 03000048 83bd90fe ffff010f 855e0400 ...H.........^.. - 05b0 0084c00f 84560400 00488b95 c8feffff .....V...H...... - 05c0 4883e2fc 0f849d06 000048ff ca48c1ea H.........H..H.. - 05d0 0248ffc2 488bbd18 ffffff48 89d648c1 .H..H......H..H. - 05e0 e605488b 8de8feff ff4889f8 4801fec5 ..H......H..H... - 05f0 f157c90f 1f440000 c5fb1040 08c5fb10 .W...D.....@.... - 0600 30c5fb59 4108c5fb 10781048 83c02048 0..YA....x.H.. H - 0610 83c120c4 e2c9b941 e0c5fb10 70f8c4e2 .. ....A....p... - 0620 c1b941f0 c4e2c9b9 41f8c5f3 58c84839 ..A.....A...X.H9 - 0630 c675c548 c1e20248 3995c8fe ffff7e2b .u.H...H9.....~+ - 0640 488b85c8 feffff48 8b8d18ff ffff488b H......H......H. - 0650 b5e8feff ff0f1f00 c5fb103c d1c4e2c1 ...........<.... - 0660 b90cd648 ffc24839 d07fed48 8b8500ff ...H..H9...H.... - 0670 ffffc5fb 1038c4e2 c1998d58 ffffffc5 .....8.....X.... - 0680 fb1108c5 f877662e 0f1f8400 00000000 .....wf......... - 0690 488b45c8 64482b04 25280000 000f8500 H.E.dH+.%(...... - 06a0 06000048 81c46001 00005b41 5a415c41 ...H..`...[AZA\A - 06b0 5d415e41 5f31c05d 498d62f8 c30f1f00 ]A^A_1.]I.b..... - 06c0 488b8d08 ffffff48 018d00ff ffffe98c H......H........ - 06d0 feffff0f 1f440000 488b8500 ffffff48 .....D..H......H - 06e0 83bde0fe ffff0148 898510ff ffff0f85 .......H........ - 06f0 a7fcffff 4883bd40 ffffff00 0f84b101 ....H..@........ - 0700 0000488b 8518ffff ff488b95 e8feffff ..H......H...... - 0710 62e1ff08 1045eb48 8bbd20ff ffff488b b....E.H.. ...H. - 0720 8d10ffff ff4c89b5 48ffffff 4f8d1c27 .....L..H...O..' - 0730 4c01e04c 01e34d01 e54531ff 488db560 L..L..M..E1.H..` - 0740 ffffff49 89d6c5f8 770f1f80 00000000 ...I....w....... - 0750 4c89f262 b1ff0010 c0488985 50ffffff L..b.....H..P... - 0760 e83bf9ff ff488b85 50ffffff 49ffc748 .;...H..P...I..H - 0770 898560ff ffff4c89 9d68ffff ff48899d ..`...L..h...H.. - 0780 70ffffff 4c89ad78 ffffff49 83c6204c p...L..x...I.. L - 0790 01e04d01 e34c01e3 4d01e54c 39bd40ff ..M..L..M..L9.@. - 07a0 ffff75ac 488bb518 ffffff4c 8bb548ff ..u.H......L..H. - 07b0 ffff4c8b 8da0feff ff4803b5 d0feffff ..L......H...... - 07c0 f685c8fe ffff0275 67f685c8 feffff01 .......ug....... - 07d0 0f8438fd ffff488b 8d10ffff ff488bbd ..8...H......H.. - 07e0 20ffffff 4c8d8558 ffffff4c 89cac5f8 ...L..X...L.... - 07f0 77e80af8 ffffe913 fdffff0f 1f440000 w............D.. - 0800 488b85b0 feffff48 85c00f84 60fdffff H......H....`... - 0810 488bbda8 feffff48 898520ff ffff4889 H......H.. ...H. - 0820 bd08ffff ffe9fdfa ffff660f 1f440000 ..........f..D.. - 0830 4883bd20 ffffff00 c4c27d19 09c4c27d H.. ......}....} - 0840 195108c4 e27d199d 58ffffff 7e41488b .Q...}..X...~AH. - 0850 8d60ffff ff488b95 68ffffff 4c8b8520 .`...H..h...L.. - 0860 ffffff48 8bbd10ff ffff31c0 0f1f4000 ...H......1...@. - 0870 c5ed5904 c2c4e2f5 b804c1c4 e2e5a804 ..Y............. - 0880 c7c5fd11 04c74883 c0044939 c07fe148 ......H...I9...H - 0890 03b588fe ffff4983 c110e92a ffffff90 ......I....*.... - 08a0 4c8b8de8 feffff48 8bb518ff ffffe909 L......H........ - 08b0 fcffff4c 8b8de8fe ffff488b b518ffff ...L......H..... - 08c0 ffe9fafe ffffc5f8 77e9c2fd ffff4883 ........w.....H. - 08d0 bd90feff ff020f85 f1020000 84c00f84 ................ - 08e0 e9020000 488b8dc8 feffff48 83e1fc0f ....H......H.... - 08f0 84900300 00c5f957 c0488b85 18ffffff .......W.H...... - 0900 488bb5e8 feffffc5 fb10d031 d2c5fb10 H..........1.... - 0910 64d608c5 fb100cd6 c5db5958 10c5db59 d.........YX...Y - 0920 60184883 c040c4e2 f1b958c0 c4e2d999 `.H..@....X..... - 0930 48c8c5e3 58d2c5fb 105cd618 c5f358c0 H...X....\....X. - 0940 c5e35960 f0c5e359 58f8c5fb 104cd610 ..Y`...YX....L.. - 0950 4883c204 c4e2f1b9 60e0c4e2 e19948e8 H.......`.....H. - 0960 c5db58d2 c5f358c0 4839ca7c a048ffc9 ..X...X.H9.|.H.. - 0970 48c1e902 48ffc148 89c848c1 e0064801 H...H..H..H...H. - 0980 8518ffff ff4889c8 48c1e005 48c1e102 .....H..H...H... - 0990 480185e8 feffff48 398dc8fe ffff7e3b H......H9.....~; - 09a0 488bbde8 feffff48 89c848f7 d8488bb5 H......H..H..H.. - 09b0 c8feffff 488b9518 ffffff48 8d04c7c5 ....H......H.... - 09c0 fb100cc8 48ffc1c4 e2f1b912 c4e2f1b9 ....H........... - 09d0 42084883 c2104839 ce7fe448 8b8500ff B.H...H9...H.... - 09e0 ffffc5fb 108d58ff ffff488b 8df8feff ......X...H..... - 09f0 ffc4e2f1 a910c5fb 1110488d 04c8c4e2 ..........H..... - 0a00 f9a908c5 fb1108c5 f877e981 fcffff48 .........w.....H - 0a10 8bb5f0fe ffff488b bdc8feff ff488b95 ......H......H.. - 0a20 18ffffff 488b8de8 feffffc5 f157c931 ....H........W.1 - 0a30 c00f1f80 00000000 c5fb1032 48ffc0c4 ...........2H... - 0a40 e2c9b909 4801f24c 01f14839 c77fe9e9 ....H..L..H9.... - 0a50 17fcffff 4883bd90 feffff03 0f85b301 ....H........... - 0a60 000084c0 0f84ab01 0000488b 8dc8feff ..........H..... - 0a70 ff4883e1 fc0f8417 020000c5 f957c048 .H...........W.H - 0a80 8b8518ff ffff488b b5e8feff ffc5fb10 ......H......... - 0a90 d0c5fb10 d831d2c5 fb106cd6 08c5fb10 .....1....l..... - 0aa0 0cd6c5d3 59601848 83c060c4 e2f1b960 ....Y`.H..`....` - 0ab0 a0c5db58 dbc5d359 60c0c5d3 5968c8c4 ...X...Y`...Yh.. - 0ac0 e2f1b960 a8c4e2d1 9948b0c5 fb106cd6 ...`.....H....l. - 0ad0 18c5db58 d2c5d359 60e8c5f3 58c0c5fb ...X...Y`...X... - 0ae0 104cd610 4883c204 c4e2f1b9 60d0c5db .L..H.......`... - 0af0 58dbc5d3 5960f0c5 d35968f8 c4e2f1b9 X...Y`...Yh..... - 0b00 60d8c4e2 d19948e0 c5db58d2 c5f358c0 `.....H...X...X. - 0b10 4839ca7c 8248ffc9 48c1e902 48ffc148 H9.|.H..H...H..H - 0b20 8d044948 c1e00548 018518ff ffff4889 ..IH...H......H. - 0b30 c848c1e0 0548c1e1 02480185 e8feffff .H...H...H...... - 0b40 48398dc8 feffff7e 41488bbd e8feffff H9.....~AH...... - 0b50 4889c848 f7d8488b b5c8feff ff488b95 H..H..H......H.. - 0b60 18ffffff 488d04c7 c5fb100c c848ffc1 ....H........H.. - 0b70 c4e2f1b9 1ac4e2f1 b95208c4 e2f1b942 .........R.....B - 0b80 104883c2 184839ce 7fdec5fb 108d58ff .H...H9.......X. - 0b90 ffff488b 8500ffff ff488b95 f8feffff ..H......H...... - 0ba0 c4e2f1a9 1848c1e2 03c5fb11 184801d0 .....H.......H.. - 0bb0 c4e2f1a9 10c5fb11 104801d0 c4e2f9a9 .........H...... - 0bc0 08c5fb11 08c5f877 e9c3faff ffc5f957 .......w.......W - 0bd0 c0488bb5 f0feffff 488bbdc8 feffff48 .H......H......H - 0be0 8b9518ff ffff488b 8de8feff ffc5fb10 ......H......... - 0bf0 d031c0c5 fb100948 ffc0c4e2 f1b912c4 .1.....H........ - 0c00 e2f1b942 084c01f1 4801f248 39c77fe3 ...B.L..H..H9... - 0c10 e9c6fdff ffc5f957 c0488bb5 f0feffff .......W.H...... /usr/lib64/libopenblas_openmp.a/dgemv_n_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dgemv_n_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dgemv_n_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39000000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dgemv_n_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dgemv_n_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dgemv_n_SKYLAKEX.o (objdump) @@ -4,11 +4,13 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 10000000 1c000000 ................ - 0020 00000000 51000000 00000000 10000000 ....Q........... - 0030 30000000 00000000 32000000 00000000 0.......2....... - 0040 10000000 44000000 00000000 06010000 ....D........... - 0050 00000000 48000000 58000000 00000000 ....H...X....... - 0060 f80a0000 00450c0a 004f1006 0276004a .....E...O...v.J - 0070 0f037658 06100f02 7678100e 02767010 ..vX....vx...vp. - 0080 0d027668 100c0276 60481003 02765003 ..vh...v`H...vP. - 0090 d7040a0c 0a004f0c 0708440b 00000000 ......O...D..... + 0020 00000000 c4000000 00000000 10000000 ................ + 0030 30000000 00000000 84000000 00000000 0............... + 0040 10000000 44000000 00000000 51000000 ....D.......Q... + 0050 00000000 10000000 58000000 00000000 ........X....... + 0060 32000000 00000000 4c000000 6c000000 2.......L...l... + 0070 00000000 5a090000 00420e10 8f02420e ....Z....B....B. + 0080 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 + 0090 8606410e 38830747 0ee00203 55040a0e ..A.8..G....U... + 00a0 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 00b0 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_COOPERLAKE.o (disasm) @@ -12,199 +12,307 @@ push %rbp push %rbx sub $something,%rsp - mov %rdi,-offset(%rsp) + mov %rdi,offset(%rsp) mov %rsi,-offset(%rsp) - mov %rdx,(%rsp) + mov %rdx,-offset(%rsp) + mov %r9,offset(%rsp) + mov offset(%rsp),%rbp + cmp %rdx,%rsi + jg test %rdi,%rdi jle - mov %rdi,%rbx - lea -offset(%rsi),%rdi - mov %rsi,%rax - lea -offset(%rcx),%r14 - lea (%r9,%rdi,4),%rsi - sar %rbx - mov %r14,-offset(%rsp) - mov %rdi,offset(%rsp) - mov %rsi,offset(%rsp) + lea -offset(%rcx),%rbx + lea -offset(%r9,%rsi,4),%rdx + sar $something,%rdi mov %rbx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %r8,%r12 + kmovq %rdx,%k0 je - sub %rdi,%rdx - mov %rdx,%rdi - and $something,%edx - lea offset(%rsi),%r15 - mov %rdx,-offset(%rsp) - movslq (%rsi),%rdx - movslq offset(%rsi),%rsi + lea offset(%rsi,%r8,1),%rax + lea -offset(%rcx,%rax,8),%rax + mov %rax,-offset(%rsp) + lea offset(,%r8,8),%rax + mov %rax,-offset(%rsp) + mov %r8,%rax + shl $something,%rax + mov %rax,-offset(%rsp) + lea (%r8,%r8,2),%rax + lea offset(,%rax,8),%rcx shl $something,%rax - sar %rdi - lea -offset(%rcx,%rsi,8),%rsi - mov %r15,-offset(%rsp) - lea -offset(%rcx,%rdx,8),%rdx - lea -offset(%rcx,%rax,1),%r15 - mov %rdi,%rcx + mov %rax,offset(%rsp) + mov %r8,%rdx + lea -offset(%r9),%rax + shl $something,%rdx + mov %rcx,(%rsp) + mov %rax,-offset(%rsp) + mov %r8,%rcx + mov %r8,%rax shl $something,%rcx - mov %rdi,-offset(%rsp) - shl $something,%rdi - lea offset(,%r8,8),%r11 - mov %rcx,-offset(%rsp) - mov %rdi,%rcx - mov %rsi,-offset(%rsp) - shl $something,%r8 - lea (%rax,%rdi,1),%rsi - add %r11,%rcx - lea offset(%rax,%r11,1),%rax - mov %r8,-offset(%rsp) - mov %rsi,-offset(%rsp) + mov %rdx,-offset(%rsp) + neg %rax + lea (%r8,%r8,4),%rdx mov %rcx,-offset(%rsp) - mov %rbx,-offset(%rsp) + shl $something,%rax + lea offset(,%rdx,8),%rcx + mov %rcx,offset(%rsp) mov %rax,-offset(%rsp) - jmp + mov %rdi,-offset(%rsp) + mov %r8,%r9 nopl offset(%rax,%rax,1) - cmpq $something,-offset(%rsp) - jne - mov -offset(%rsp),%rbx - mov -offset(%rsp),%r15 + mov -offset(%rsp),%rcx + mov -offset(%rsp),%r12 + mov -offset(%rsp),%r11 + mov (%rsp),%r10 + mov -offset(%rsp),%r8 + mov offset(%rsp),%rdi + mov offset(%rsp),%rsi mov -offset(%rsp),%rdx - add %rbx,-offset(%rsp) - add %rbx,%r14 - add %r11,%r15 - add %r11,%rdx - decq -offset(%rsp) - je - lea (%r11,%r15,1),%rbx - mov %rbx,-offset(%rsp) - mov %rbx,%rcx - cmpq $something,-offset(%rsp) - lea (%r11,%rdx,1),%rbx - mov %rbx,-offset(%rsp) - mov %r15,%rax - mov %rbx,%rbp - jle + add %rcx,%r12 + add %rcx,%r11 + add %rcx,%r10 + add %rcx,%r8 + add %rcx,%rdi + add %rcx,%rsi + nopl offset(%rax) mov -offset(%rsp),%rax - mov -offset(%rsp),%r8 - mov %rax,%rdi - lea (%r11,%rax,1),%r12 + vmovsd (%rbx,%rdx,8),%xmm7 + prefetcht2 (%rax,%rcx,1) mov -offset(%rsp),%rax - mov -offset(%rsp),%rbx - lea (%rax,%r14,1),%rsi - mov offset(%rsp),%rcx - lea offset(%r15),%rax - jmp - nopl offset(%rax) + vmovsd -offset(%rcx),%xmm6 + movslq (%rax,%rdx,4),%rax + vmovsd -offset(%r12),%xmm5 + vmovsd -offset(%r11),%xmm4 + vmovsd -offset(%r10),%xmm3 + vmovsd -offset(%r8),%xmm2 + vmovsd -offset(%rdi),%xmm1 + vmovsd -offset(%rsi),%xmm0 + prefetcht2 (%rcx) + prefetcht2 (%r12) + prefetcht2 (%r11) + prefetcht2 (%r10) + prefetcht2 (%r8) + prefetcht2 (%rdi) + prefetcht2 (%rsi) cmp %rax,%rdx je - vmovsd %xmm7,(%rcx) - vmovsd %xmm6,offset(%rcx) - cmp %rax,%rdi - je - cmp %rdi,%rdx - je - vmovsd %xmm5,offset(%rcx) - vmovsd %xmm4,offset(%rcx) - vmovsd %xmm3,(%rdx) - vmovsd %xmm2,(%rdi) + lea (%rbx,%rax,8),%r15 + add %r9,%rax + lea (%rbx,%rax,8),%r14 + add %r9,%rax + lea (%rbx,%rax,8),%r13 + add %r9,%rax + mov %r13,-offset(%rsp) + lea (%rbx,%rax,8),%r13 + add %r9,%rax + mov %r13,-offset(%rsp) + lea (%rbx,%rax,8),%r13 + add %r9,%rax + mov %r13,-offset(%rsp) + lea (%rbx,%rax,8),%r13 + add %r9,%rax + mov %r13,-offset(%rsp) + lea (%rbx,%rax,8),%r13 + mov %r13,-offset(%rsp) + mov -offset(%rsp),%r13 + add %r9,%rax + vmovsd offset(%r13),%xmm13 + mov -offset(%rsp),%r13 + lea (%rbx,%rax,8),%rax + vmovsd offset(%r13),%xmm12 + mov -offset(%rsp),%r13 + vmovsd (%r14),%xmm14 + vmovsd offset(%r13),%xmm11 + mov -offset(%rsp),%r13 + vmovsd (%r15),%xmm15 + vmovsd offset(%r13),%xmm10 + mov -offset(%rsp),%r13 + vmovsd (%rax),%xmm8 + vmovsd offset(%r13),%xmm9 + vmovsd %xmm7,(%r15) /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_COOPERLAKE.o (objdump) @@ -2,82 +2,89 @@ /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534883 ec204889 AWAVAUATUSH.. H. - 0010 7c24c048 897424f8 48891424 4885ff0f |$.H.t$.H..$H... - 0020 8e210300 004889fb 488d7eff 4889f04c .!...H..H.~.H..L - 0030 8d71f849 8d34b948 d1fb4c89 7424f048 .q.I.4.H..L.t$.H - 0040 897c2408 48897424 1048895c 24180f84 .|$.H.t$.H.\$... - 0050 fa010000 4829fa48 89d783e2 014c8d7e ....H).H.....L.~ - 0060 08488954 24b84863 16486376 0448c1e0 .H.T$.Hc.Hcv.H.. - 0070 0348d1ff 488d74f1 f84c897c 24d8488d .H..H.t..L.|$.H. - 0080 54d1f84c 8d7c01f8 4889f948 c1e10548 T..L.|..H..H...H - 0090 897c2498 48c1e704 4e8d1cc5 00000000 .|$.H...N....... - 00a0 48894c24 d04889f9 48897424 a049c1e0 H.L$.H..H.t$.I.. - 00b0 04488d34 384c01d9 4a8d4418 604c8944 .H.48L..J.D.`L.D - 00c0 24a84889 7424c848 894c24e0 48895c24 $.H.t$.H.L$.H.\$ - 00d0 b0488944 24e8eb3c 0f1f8400 00000000 .H.D$..<........ - 00e0 48837c24 b8000f85 ea020000 488b5c24 H.|$........H.\$ - 00f0 a84c8b7c 2488488b 54249048 015c24a0 .L.|$.H.T$.H.\$. - 0100 4901de4d 01df4c01 da48ff4c 24b00f84 I..M..L..H.L$... - 0110 2c010000 4b8d1c3b 48895c24 884889d9 ,...K..;H.\$.H.. - 0120 48837c24 9800498d 1c134889 5c24904c H.|$..I...H.\$.L - 0130 89f84889 dd7ea948 8b4424a0 4c8b4424 ..H..~.H.D$.L.D$ - 0140 d84889c7 4d8d2403 488b4424 e8488b5c .H..M.$.H.D$.H.\ - 0150 24984a8d 3430488b 4c245849 8d4708eb $.J.40H.L$XI.G.. - 0160 6d0f1f80 00000000 4839c20f 84ef0100 m.......H9...... - 0170 00c5fb11 39c5fb11 71084839 c70f840d ....9...q.H9.... - 0180 02000048 39fa0f84 84020000 c5fb1169 ...H9..........i - 0190 10c5fb11 6118c5fb 111ac5fb 1117c5fb ....a........... - 01a0 114d00c4 c17b1104 244b8d14 d64b8d3c .M...{..$K...K.< - 01b0 ce4883c1 204a8d2c 1a4e8d24 1f4883c6 .H.. J.,.N.$.H.. - 01c0 104883c0 1048ffcb 0f84e201 00004c8d .H...H........L. - 01d0 68f84d63 104d6348 04c5fb10 58f8c5fb h.Mc.McH....X... - 01e0 1010c5fb 104ea0c5 fb1046a8 c5fb103a .....N....F....: - 01f0 c5fb102f c5fb1075 00c4c17b 10242449 .../...u...{.$$I - 0200 83c0080f 1840580f 18064c39 ea0f8555 .....@X...L9...U - 0210 ffffffc5 fb1119c5 fb114908 4839c70f ..........I.H9.. - 0220 840b0200 00c5fb11 6910c5fb 116118c5 ........i....a.. - 0230 fb1117c4 c17b1104 24e96bff ffff6690 .....{..$.k...f. - 0240 488b4424 18480faf c3480144 24f0f644 H.D$.H...H.D$..D - 0250 24c0010f 84ed0000 004c8b1c 24488b7c $........L..$H.| - 0260 24f0488b 4424f848 8b4c2410 4c2b5c24 $.H.D$.H.L$.L+\$ - 0270 084c8d14 c74c89db 48630148 d1fb4989 .L...L..Hc.H..I. - 0280 fc488d14 c74885db 0f8eae00 00004889 .H...H........H. - 0290 c8486340 04488b74 2458488d 3cc7488d .Hc@.H.t$XH.<.H. - 02a0 4908498d 42084889 ddeb460f 1f440000 I.I.B.H...F..D.. - 02b0 4839c20f 84970100 00c5fb11 1e4839c7 H9...........H9. - 02c0 0f84ba01 00004839 fa0f84c1 010000c5 ......H9........ - 02d0 fb115608 c5fb110a c5fb1107 4883c610 ..V.........H... - 02e0 4b8d14cc 4b8d3cc4 4883c010 48ffcd74 K...K.<.H...H..t - 02f0 3f4c8d68 f84c6309 4c634104 c5fb1048 ?L.h.Lc.LcA....H - 0300 f8c5fb10 00c5fb10 1ac5fb10 174883c1 .............H.. - 0310 084c39ea 759ac5fb 110e4839 c70f849d .L9.u.....H9.... - 0320 010000c5 fb115608 c5fb1107 ebae6690 ......V.......f. - 0330 48c1e304 48015c24 584901da 4183e301 H...H.\$XI..A... - 0340 0f855a01 00004883 c4205b5d 415c415d ..Z...H.. []A\A] - 0350 415e31c0 415fc366 0f1f8400 00000000 A^1.A_.f........ - 0360 c5fb1111 c5fb1141 084839f8 0f84ce00 .......A.H9..... - 0370 0000c5fb 116910c5 fb116118 c5fb111f .....i....a..... - 0380 c4c17b11 0c24e91e feffff0f 1f440000 ..{..$.......D.. - 0390 c5fb1151 10c5fb11 4118c5fb 111ac5fb ...Q....A....... - 03a0 114d00e9 01feffff 0f1f8400 00000000 .M.............. - 03b0 488b4424 d0488b4c 24e04801 44245848 H.D$.H.L$.H.D$XH - 03c0 8b4424c8 4c01f94c 01f04883 7c24b800 .D$.L..L..H.|$.. - 03d0 0f8416fd ffff4839 d0c5fb10 08c5fb10 ......H9........ - 03e0 1ac5fb10 01c5fb10 5500488b 44245874 ........U.H.D$Xt - 03f0 7fc5fb11 18c5fb11 5008c5fb 110ac5fb ........P....... - 0400 11450048 83442458 10e9defc ffff6690 .E.H.D$X......f. - 0410 c5fb1159 10c5fb11 4918c5fb 1112c5fb ...Y....I....... - 0420 114500e9 81fdffff 0f1f8400 00000000 .E.............. - 0430 c5fb1151 10c5fb11 4118e96a fdffff90 ...Q....A..j.... - 0440 c5fb1159 10c5fb11 4918e95a fdffff90 ...Y....I..Z.... - 0450 c5fb1106 4839f874 77c5fb11 5608c5fb ....H9.tw...V... - 0460 110fe975 feffff66 0f1f8400 00000000 ...u...f........ - 0470 c5fb1108 c5fb1140 08eb880f 1f440000 .......@.....D.. - 0480 c5fb1146 08c5fb11 0ae94efe ffff6690 ...F......N...f. - 0490 c5fb114e 08c5fb11 02e93efe ffff6690 ...N......>...f. - 04a0 c4c17b10 02c5fb10 0a488b44 24584939 ..{......H.D$XI9 - 04b0 d27427c5 fb1108c5 fb1102e9 86feffff .t'............. - 04c0 c5fb1146 08e912fe ffff660f 1f440000 ...F......f..D.. - 04d0 c5fb114e 08e902fe ffffc5fb 1100e963 ...N...........c - 04e0 feffff ... + 0000 41574156 41554154 55534883 ec384889 AWAVAUATUSH..8H. + 0010 7c241848 897424d0 48895424 b04c894c |$.H.t$.H.T$.L.L + 0020 2428488b 6c247048 39d60f8f 1b050000 $(H.l$pH9....... + 0030 4885ff0f 8e120500 00488d59 f8498d54 H........H.Y.I.T + 0040 b1fc48c1 ff034889 5c242048 897c2430 ..H...H.\$ H.|$0 + 0050 4d89c4c4 e1fb92c2 0f84aa02 00004a8d M.............J. + 0060 44060448 8d44c1f8 48894424 c84a8d04 D..H.D..H.D$.J.. + 0070 c5000000 00488944 24f84c89 c048c1e0 .....H.D$.L..H.. + 0080 04488944 24f04b8d 0440488d 0cc50000 .H.D$.K..@H..... + 0090 000048c1 e0044889 4424104c 89c2498d ..H...H.D$.L..I. + 00a0 41fc48c1 e2064889 0c244889 4424b84c A.H...H..$H.D$.L + 00b0 89c14c89 c048c1e1 05488954 24d848f7 ..L..H...H.T$.H. + 00c0 d84b8d14 8048894c 24e848c1 e003488d .K...H.L$.H...H. + 00d0 0cd50000 00004889 4c240848 894424c0 ......H.L$.H.D$. + 00e0 48897c24 e04d89c1 0f1f8400 00000000 H.|$.M.......... + 00f0 488b4c24 c84c8b64 24f84c8b 5c24f04c H.L$.L.d$.L.\$.L + 0100 8b14244c 8b4424e8 488b7c24 08488b74 ..$L.D$.H.|$.H.t + 0110 2410488b 5424d049 01cc4901 cb4901ca $.H.T$.I..I..I.. + 0120 4901c848 01cf4801 ce0f1f80 00000000 I..H..H......... + 0130 488b4424 c0c5fb10 3cd30f18 1c08488b H.D$....<.....H. + 0140 4424b8c5 fb1071e0 48630490 c4c17b10 D$....q.Hc....{. + 0150 6c24e0c4 c17b1063 e0c4c17b 105ae0c4 l$...{.c...{.Z.. + 0160 c17b1050 e0c5fb10 4fe0c5fb 1046e00f .{.P....O....F.. + 0170 1819410f 181c2441 0f181b41 0f181a41 ..A...$A...A...A + 0180 0f18180f 181f0f18 1e4839c2 0f84f700 .........H9..... + 0190 00004c8d 3cc34c01 c84c8d34 c34c01c8 ..L.<.L..L.4.L.. + 01a0 4c8d2cc3 4c01c84c 896c2488 4c8d2cc3 L.,.L..L.l$.L.,. + 01b0 4c01c84c 896c2490 4c8d2cc3 4c01c84c L..L.l$.L.,.L..L + 01c0 896c2498 4c8d2cc3 4c01c84c 896c24a0 .l$.L.,.L..L.l$. + 01d0 4c8d2cc3 4c896c24 a84c8b6c 24884c01 L.,.L.l$.L.l$.L. + 01e0 c8c4417b 106d004c 8b6c2490 488d04c3 ..A{.m.L.l$.H... + 01f0 c4417b10 65004c8b 6c2498c4 417b1036 .A{.e.L.l$..A{.6 + 0200 c4417b10 5d004c8b 6c24a0c4 417b103f .A{.].L.l$..A{.? + 0210 c4417b10 55004c8b 6c24a8c5 7b1000c4 .A{.U.L.l$..{... + 0220 417b104d 00c4c17b 113f4c8b 6c2490c4 A{.M...{.?L.l$.. + 0230 c17b1136 4c8b7424 88c50311 ffc4c17b .{.6L.t$.......{ + 0240 112ec4c1 7b116500 4c8b6c24 98c50b11 ....{.e.L.l$.... + 0250 f6c4c17b 115d004c 8b6c24a0 c51311ed ...{.].L.l$..... + 0260 c4c17b11 55004c8b 6c24a8c5 1b11e4c4 ..{.U.L.l$...... + 0270 c17b114d 00c52311 dbc5fb11 00c52b11 .{.M..#.......+. + 0280 d2c53311 c9c53b11 c048ffc2 c5fb117d ..3...;..H.....} + 0290 00c5fb11 7508c5fb 116d10c5 fb116518 ....u....m....e. + 02a0 c5fb115d 20c5fb11 5528c5fb 114d30c5 ...] ...U(...M0. + 02b0 fb114538 4883c108 4883c540 4983c408 ..E8H...H..@I... + 02c0 4983c308 4983c208 4983c008 4883c708 I...I...I...H... + 02d0 4883c608 48395424 b00f8d51 feffff48 H...H9T$...Q...H + 02e0 8b7c24d8 48017c24 c84801fb 48ff4c24 .|$.H.|$.H..H.L$ + 02f0 e00f85f9 fdffff48 8b442430 4d89cc48 .......H.D$0M..H + 0300 0fafc748 01442420 f6442418 040f8423 ...H.D$ .D$....# + 0310 010000c4 e1fb93c0 4863304c 8b6c2420 ........Hc0L.l$ + 0320 4a8d0426 4d8d44c5 004c01e0 498d7cc5 J..&M.D..L..I.|. + 0330 004c01e0 498d54c5 004d89e2 4b8d0464 .L..I.T..M..K..d + 0340 49c1e204 4d8d5cc5 004c8b74 24b0488b I...M.\..L.t$.H. + 0350 4424d04c 8b7c2428 4d8d4cf5 004b8d5c D$.L.|$(M.L..K.\ + 0360 e5004d01 ea4889e9 0f1f8400 00000000 ..M..H.......... + 0370 c4c17b10 5cc500c5 fb1014c3 c4c17b10 ..{.\.........{. + 0380 0cc2c4c1 7b1004c3 4839f074 34c4c17b ....{...H9.t4..{ + 0390 1039c4c1 7b1030c5 fb102fc5 fb1022c4 .9..{.0.../...". + 03a0 c17b1119 c4c17b11 10c5c310 dfc5fb11 .{....{......... + 03b0 0fc5cb10 d6c5fb11 02c5d310 cdc5db10 ................ + 03c0 c4496334 8748ffc0 498d1434 4d8d44d5 .Ic4.H..I..4M.D. + 03d0 004c01e2 498d7cd5 004c01e2 c5fb1119 .L..I.|..L...... + 03e0 c5fb1151 08c5fb11 4910c5fb 1141184d ...Q....I....A.M + 03f0 8d4cf500 498d54d5 004883c1 204939c6 .L..I.T..H.. I9. + 0400 0f8d6aff ffff488b 7424b048 8b7c24d0 ..j...H.t$.H.|$. + 0410 488d4601 4829f848 c1e005ba 20000000 H.F.H).H.... ... + 0420 4839f748 0f4fc248 01c54c89 e048c1e0 H9.H.O.H..L..H.. + 0430 05480144 2420f644 2418020f 84a90000 .H.D$ .D$....... + 0440 00488b44 2428488b 7424204c 8d40fc4e .H.D$(H.t$ L.@.N + 0450 8d0ce500 00000048 8b4424d0 4c8b5c24 .......H.D$.L.\$ + 0460 b04a8d3c 0e4889e9 0f1f8400 00000000 .J.<.H.......... + 0470 49631480 c5fb100c c6c5fb10 04c74839 Ic............H9 + 0480 d074254c 8d14d64c 01e2488d 14d6c4c1 .t%L...L..H..... + 0490 7b101ac5 fb1012c4 c17b110a c5fb1102 {........{...... + 04a0 c5e310cb c5eb10c2 48ffc0c5 fb1109c5 ........H....... + 04b0 fb114108 4883c110 4939c37d b3488b74 ..A.H...I9.}.H.t + 04c0 24b0488b 5c24d048 8d460148 29d848c1 $.H.\$.H.F.H).H. + 04d0 e004ba10 00000048 39f3480f 4fc24801 .......H9.H.O.H. + 04e0 c54a8d04 0f488944 2420f644 24180174 .J...H.D$ .D$..t + 04f0 5a488b74 24d0488b 44242848 89f248f7 ZH.t$.H.D$(H..H. + 0500 da488b7c 24204c8b 4424b048 8d4cd500 .H.|$ L.D$.H.L.. + 0510 4883e804 4889f266 0f1f8400 00000000 H...H..f........ + 0520 48633490 c5fb1004 d74839f2 7410488d Hc4......H9.t.H. + 0530 34f7c5fb 100ec5fb 1106c5f3 10c1c5fb 4............... + 0540 1104d148 ffc24939 d07dd548 83c4385b ...H..I9.}.H..8[ + 0550 5d415c41 5d415e31 c0415fc3 ]A\A]A^1.A_. /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 09080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 e3040000 00420e10 8f02420e .........B....B. + 0020 00000000 5c050000 00420e10 8f02420e ....\....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830744 0e58033c 030a0e38 ..A.8..D.X.<...8 - 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D - 0060 0e084a0b 00000000 ..J..... + 0040 8606410e 38830744 0e700341 050e3841 ..A.8..D.p.A..8A + 0050 0e30410e 28420e20 420e1842 0e10440e .0A.(B. B..B..D. + 0060 08000000 00000000 ........ /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_SKYLAKEX.o (disasm) @@ -12,199 +12,307 @@ push %rbp push %rbx sub $something,%rsp - mov %rdi,-offset(%rsp) + mov %rdi,offset(%rsp) mov %rsi,-offset(%rsp) - mov %rdx,(%rsp) + mov %rdx,-offset(%rsp) + mov %r9,offset(%rsp) + mov offset(%rsp),%rbp + cmp %rdx,%rsi + jg test %rdi,%rdi jle - mov %rdi,%rbx - lea -offset(%rsi),%rdi - mov %rsi,%rax - lea -offset(%rcx),%r14 - lea (%r9,%rdi,4),%rsi - sar %rbx - mov %r14,-offset(%rsp) - mov %rdi,offset(%rsp) - mov %rsi,offset(%rsp) + lea -offset(%rcx),%rbx + lea -offset(%r9,%rsi,4),%rdx + sar $something,%rdi mov %rbx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %r8,%r12 + kmovq %rdx,%k0 je - sub %rdi,%rdx - mov %rdx,%rdi - and $something,%edx - lea offset(%rsi),%r15 - mov %rdx,-offset(%rsp) - movslq (%rsi),%rdx - movslq offset(%rsi),%rsi + lea offset(%rsi,%r8,1),%rax + lea -offset(%rcx,%rax,8),%rax + mov %rax,-offset(%rsp) + lea offset(,%r8,8),%rax + mov %rax,-offset(%rsp) + mov %r8,%rax + shl $something,%rax + mov %rax,-offset(%rsp) + lea (%r8,%r8,2),%rax + lea offset(,%rax,8),%rcx shl $something,%rax - sar %rdi - lea -offset(%rcx,%rsi,8),%rsi - mov %r15,-offset(%rsp) - lea -offset(%rcx,%rdx,8),%rdx - lea -offset(%rcx,%rax,1),%r15 - mov %rdi,%rcx + mov %rax,offset(%rsp) + mov %r8,%rdx + lea -offset(%r9),%rax + shl $something,%rdx + mov %rcx,(%rsp) + mov %rax,-offset(%rsp) + mov %r8,%rcx + mov %r8,%rax shl $something,%rcx - mov %rdi,-offset(%rsp) - shl $something,%rdi - lea offset(,%r8,8),%r11 - mov %rcx,-offset(%rsp) - mov %rdi,%rcx - mov %rsi,-offset(%rsp) - shl $something,%r8 - lea (%rax,%rdi,1),%rsi - add %r11,%rcx - lea offset(%rax,%r11,1),%rax - mov %r8,-offset(%rsp) - mov %rsi,-offset(%rsp) + mov %rdx,-offset(%rsp) + neg %rax + lea (%r8,%r8,4),%rdx mov %rcx,-offset(%rsp) - mov %rbx,-offset(%rsp) + shl $something,%rax + lea offset(,%rdx,8),%rcx + mov %rcx,offset(%rsp) mov %rax,-offset(%rsp) - jmp + mov %rdi,-offset(%rsp) + mov %r8,%r9 nopl offset(%rax,%rax,1) - cmpq $something,-offset(%rsp) - jne - mov -offset(%rsp),%rbx - mov -offset(%rsp),%r15 + mov -offset(%rsp),%rcx + mov -offset(%rsp),%r12 + mov -offset(%rsp),%r11 + mov (%rsp),%r10 + mov -offset(%rsp),%r8 + mov offset(%rsp),%rdi + mov offset(%rsp),%rsi mov -offset(%rsp),%rdx - add %rbx,-offset(%rsp) - add %rbx,%r14 - add %r11,%r15 - add %r11,%rdx - decq -offset(%rsp) - je - lea (%r11,%r15,1),%rbx - mov %rbx,-offset(%rsp) - mov %rbx,%rcx - cmpq $something,-offset(%rsp) - lea (%r11,%rdx,1),%rbx - mov %rbx,-offset(%rsp) - mov %r15,%rax - mov %rbx,%rbp - jle + add %rcx,%r12 + add %rcx,%r11 + add %rcx,%r10 + add %rcx,%r8 + add %rcx,%rdi + add %rcx,%rsi + nopl offset(%rax) mov -offset(%rsp),%rax - mov -offset(%rsp),%r8 - mov %rax,%rdi - lea (%r11,%rax,1),%r12 + vmovsd (%rbx,%rdx,8),%xmm7 + prefetcht2 (%rax,%rcx,1) mov -offset(%rsp),%rax - mov -offset(%rsp),%rbx - lea (%rax,%r14,1),%rsi - mov offset(%rsp),%rcx - lea offset(%r15),%rax - jmp - nopl offset(%rax) + vmovsd -offset(%rcx),%xmm6 + movslq (%rax,%rdx,4),%rax + vmovsd -offset(%r12),%xmm5 + vmovsd -offset(%r11),%xmm4 + vmovsd -offset(%r10),%xmm3 + vmovsd -offset(%r8),%xmm2 + vmovsd -offset(%rdi),%xmm1 + vmovsd -offset(%rsi),%xmm0 + prefetcht2 (%rcx) + prefetcht2 (%r12) + prefetcht2 (%r11) + prefetcht2 (%r10) + prefetcht2 (%r8) + prefetcht2 (%rdi) + prefetcht2 (%rsi) cmp %rax,%rdx je - vmovsd %xmm7,(%rcx) - vmovsd %xmm6,offset(%rcx) - cmp %rax,%rdi - je - cmp %rdi,%rdx - je - vmovsd %xmm5,offset(%rcx) - vmovsd %xmm4,offset(%rcx) - vmovsd %xmm3,(%rdx) - vmovsd %xmm2,(%rdi) + lea (%rbx,%rax,8),%r15 + add %r9,%rax + lea (%rbx,%rax,8),%r14 + add %r9,%rax + lea (%rbx,%rax,8),%r13 + add %r9,%rax + mov %r13,-offset(%rsp) + lea (%rbx,%rax,8),%r13 + add %r9,%rax + mov %r13,-offset(%rsp) + lea (%rbx,%rax,8),%r13 + add %r9,%rax + mov %r13,-offset(%rsp) + lea (%rbx,%rax,8),%r13 + add %r9,%rax + mov %r13,-offset(%rsp) + lea (%rbx,%rax,8),%r13 + mov %r13,-offset(%rsp) + mov -offset(%rsp),%r13 + add %r9,%rax + vmovsd offset(%r13),%xmm13 + mov -offset(%rsp),%r13 + lea (%rbx,%rax,8),%rax + vmovsd offset(%r13),%xmm12 + mov -offset(%rsp),%r13 + vmovsd (%r14),%xmm14 + vmovsd offset(%r13),%xmm11 + mov -offset(%rsp),%r13 + vmovsd (%r15),%xmm15 + vmovsd offset(%r13),%xmm10 + mov -offset(%rsp),%r13 + vmovsd (%rax),%xmm8 + vmovsd offset(%r13),%xmm9 + vmovsd %xmm7,(%r15) /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_SKYLAKEX.o (objdump) @@ -2,82 +2,89 @@ /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534883 ec204889 AWAVAUATUSH.. H. - 0010 7c24c048 897424f8 48891424 4885ff0f |$.H.t$.H..$H... - 0020 8e210300 004889fb 488d7eff 4889f04c .!...H..H.~.H..L - 0030 8d71f849 8d34b948 d1fb4c89 7424f048 .q.I.4.H..L.t$.H - 0040 897c2408 48897424 1048895c 24180f84 .|$.H.t$.H.\$... - 0050 fa010000 4829fa48 89d783e2 014c8d7e ....H).H.....L.~ - 0060 08488954 24b84863 16486376 0448c1e0 .H.T$.Hc.Hcv.H.. - 0070 0348d1ff 488d74f1 f84c897c 24d8488d .H..H.t..L.|$.H. - 0080 54d1f84c 8d7c01f8 4889f948 c1e10548 T..L.|..H..H...H - 0090 897c2498 48c1e704 4e8d1cc5 00000000 .|$.H...N....... - 00a0 48894c24 d04889f9 48897424 a049c1e0 H.L$.H..H.t$.I.. - 00b0 04488d34 384c01d9 4a8d4418 604c8944 .H.48L..J.D.`L.D - 00c0 24a84889 7424c848 894c24e0 48895c24 $.H.t$.H.L$.H.\$ - 00d0 b0488944 24e8eb3c 0f1f8400 00000000 .H.D$..<........ - 00e0 48837c24 b8000f85 ea020000 488b5c24 H.|$........H.\$ - 00f0 a84c8b7c 2488488b 54249048 015c24a0 .L.|$.H.T$.H.\$. - 0100 4901de4d 01df4c01 da48ff4c 24b00f84 I..M..L..H.L$... - 0110 2c010000 4b8d1c3b 48895c24 884889d9 ,...K..;H.\$.H.. - 0120 48837c24 9800498d 1c134889 5c24904c H.|$..I...H.\$.L - 0130 89f84889 dd7ea948 8b4424a0 4c8b4424 ..H..~.H.D$.L.D$ - 0140 d84889c7 4d8d2403 488b4424 e8488b5c .H..M.$.H.D$.H.\ - 0150 24984a8d 3430488b 4c245849 8d4708eb $.J.40H.L$XI.G.. - 0160 6d0f1f80 00000000 4839c20f 84ef0100 m.......H9...... - 0170 00c5fb11 39c5fb11 71084839 c70f840d ....9...q.H9.... - 0180 02000048 39fa0f84 84020000 c5fb1169 ...H9..........i - 0190 10c5fb11 6118c5fb 111ac5fb 1117c5fb ....a........... - 01a0 114d00c4 c17b1104 244b8d14 d64b8d3c .M...{..$K...K.< - 01b0 ce4883c1 204a8d2c 1a4e8d24 1f4883c6 .H.. J.,.N.$.H.. - 01c0 104883c0 1048ffcb 0f84e201 00004c8d .H...H........L. - 01d0 68f84d63 104d6348 04c5fb10 58f8c5fb h.Mc.McH....X... - 01e0 1010c5fb 104ea0c5 fb1046a8 c5fb103a .....N....F....: - 01f0 c5fb102f c5fb1075 00c4c17b 10242449 .../...u...{.$$I - 0200 83c0080f 1840580f 18064c39 ea0f8555 .....@X...L9...U - 0210 ffffffc5 fb1119c5 fb114908 4839c70f ..........I.H9.. - 0220 840b0200 00c5fb11 6910c5fb 116118c5 ........i....a.. - 0230 fb1117c4 c17b1104 24e96bff ffff6690 .....{..$.k...f. - 0240 488b4424 18480faf c3480144 24f0f644 H.D$.H...H.D$..D - 0250 24c0010f 84ed0000 004c8b1c 24488b7c $........L..$H.| - 0260 24f0488b 4424f848 8b4c2410 4c2b5c24 $.H.D$.H.L$.L+\$ - 0270 084c8d14 c74c89db 48630148 d1fb4989 .L...L..Hc.H..I. - 0280 fc488d14 c74885db 0f8eae00 00004889 .H...H........H. - 0290 c8486340 04488b74 2458488d 3cc7488d .Hc@.H.t$XH.<.H. - 02a0 4908498d 42084889 ddeb460f 1f440000 I.I.B.H...F..D.. - 02b0 4839c20f 84970100 00c5fb11 1e4839c7 H9...........H9. - 02c0 0f84ba01 00004839 fa0f84c1 010000c5 ......H9........ - 02d0 fb115608 c5fb110a c5fb1107 4883c610 ..V.........H... - 02e0 4b8d14cc 4b8d3cc4 4883c010 48ffcd74 K...K.<.H...H..t - 02f0 3f4c8d68 f84c6309 4c634104 c5fb1048 ?L.h.Lc.LcA....H - 0300 f8c5fb10 00c5fb10 1ac5fb10 174883c1 .............H.. - 0310 084c39ea 759ac5fb 110e4839 c70f849d .L9.u.....H9.... - 0320 010000c5 fb115608 c5fb1107 ebae6690 ......V.......f. - 0330 48c1e304 48015c24 584901da 4183e301 H...H.\$XI..A... - 0340 0f855a01 00004883 c4205b5d 415c415d ..Z...H.. []A\A] - 0350 415e31c0 415fc366 0f1f8400 00000000 A^1.A_.f........ - 0360 c5fb1111 c5fb1141 084839f8 0f84ce00 .......A.H9..... - 0370 0000c5fb 116910c5 fb116118 c5fb111f .....i....a..... - 0380 c4c17b11 0c24e91e feffff0f 1f440000 ..{..$.......D.. - 0390 c5fb1151 10c5fb11 4118c5fb 111ac5fb ...Q....A....... - 03a0 114d00e9 01feffff 0f1f8400 00000000 .M.............. - 03b0 488b4424 d0488b4c 24e04801 44245848 H.D$.H.L$.H.D$XH - 03c0 8b4424c8 4c01f94c 01f04883 7c24b800 .D$.L..L..H.|$.. - 03d0 0f8416fd ffff4839 d0c5fb10 08c5fb10 ......H9........ - 03e0 1ac5fb10 01c5fb10 5500488b 44245874 ........U.H.D$Xt - 03f0 7fc5fb11 18c5fb11 5008c5fb 110ac5fb ........P....... - 0400 11450048 83442458 10e9defc ffff6690 .E.H.D$X......f. - 0410 c5fb1159 10c5fb11 4918c5fb 1112c5fb ...Y....I....... - 0420 114500e9 81fdffff 0f1f8400 00000000 .E.............. - 0430 c5fb1151 10c5fb11 4118e96a fdffff90 ...Q....A..j.... - 0440 c5fb1159 10c5fb11 4918e95a fdffff90 ...Y....I..Z.... - 0450 c5fb1106 4839f874 77c5fb11 5608c5fb ....H9.tw...V... - 0460 110fe975 feffff66 0f1f8400 00000000 ...u...f........ - 0470 c5fb1108 c5fb1140 08eb880f 1f440000 .......@.....D.. - 0480 c5fb1146 08c5fb11 0ae94efe ffff6690 ...F......N...f. - 0490 c5fb114e 08c5fb11 02e93efe ffff6690 ...N......>...f. - 04a0 c4c17b10 02c5fb10 0a488b44 24584939 ..{......H.D$XI9 - 04b0 d27427c5 fb1108c5 fb1102e9 86feffff .t'............. - 04c0 c5fb1146 08e912fe ffff660f 1f440000 ...F......f..D.. - 04d0 c5fb114e 08e902fe ffffc5fb 1100e963 ...N...........c - 04e0 feffff ... + 0000 41574156 41554154 55534883 ec384889 AWAVAUATUSH..8H. + 0010 7c241848 897424d0 48895424 b04c894c |$.H.t$.H.T$.L.L + 0020 2428488b 6c247048 39d60f8f 1b050000 $(H.l$pH9....... + 0030 4885ff0f 8e120500 00488d59 f8498d54 H........H.Y.I.T + 0040 b1fc48c1 ff034889 5c242048 897c2430 ..H...H.\$ H.|$0 + 0050 4d89c4c4 e1fb92c2 0f84aa02 00004a8d M.............J. + 0060 44060448 8d44c1f8 48894424 c84a8d04 D..H.D..H.D$.J.. + 0070 c5000000 00488944 24f84c89 c048c1e0 .....H.D$.L..H.. + 0080 04488944 24f04b8d 0440488d 0cc50000 .H.D$.K..@H..... + 0090 000048c1 e0044889 4424104c 89c2498d ..H...H.D$.L..I. + 00a0 41fc48c1 e2064889 0c244889 4424b84c A.H...H..$H.D$.L + 00b0 89c14c89 c048c1e1 05488954 24d848f7 ..L..H...H.T$.H. + 00c0 d84b8d14 8048894c 24e848c1 e003488d .K...H.L$.H...H. + 00d0 0cd50000 00004889 4c240848 894424c0 ......H.L$.H.D$. + 00e0 48897c24 e04d89c1 0f1f8400 00000000 H.|$.M.......... + 00f0 488b4c24 c84c8b64 24f84c8b 5c24f04c H.L$.L.d$.L.\$.L + 0100 8b14244c 8b4424e8 488b7c24 08488b74 ..$L.D$.H.|$.H.t + 0110 2410488b 5424d049 01cc4901 cb4901ca $.H.T$.I..I..I.. + 0120 4901c848 01cf4801 ce0f1f80 00000000 I..H..H......... + 0130 488b4424 c0c5fb10 3cd30f18 1c08488b H.D$....<.....H. + 0140 4424b8c5 fb1071e0 48630490 c4c17b10 D$....q.Hc....{. + 0150 6c24e0c4 c17b1063 e0c4c17b 105ae0c4 l$...{.c...{.Z.. + 0160 c17b1050 e0c5fb10 4fe0c5fb 1046e00f .{.P....O....F.. + 0170 1819410f 181c2441 0f181b41 0f181a41 ..A...$A...A...A + 0180 0f18180f 181f0f18 1e4839c2 0f84f700 .........H9..... + 0190 00004c8d 3cc34c01 c84c8d34 c34c01c8 ..L.<.L..L.4.L.. + 01a0 4c8d2cc3 4c01c84c 896c2488 4c8d2cc3 L.,.L..L.l$.L.,. + 01b0 4c01c84c 896c2490 4c8d2cc3 4c01c84c L..L.l$.L.,.L..L + 01c0 896c2498 4c8d2cc3 4c01c84c 896c24a0 .l$.L.,.L..L.l$. + 01d0 4c8d2cc3 4c896c24 a84c8b6c 24884c01 L.,.L.l$.L.l$.L. + 01e0 c8c4417b 106d004c 8b6c2490 488d04c3 ..A{.m.L.l$.H... + 01f0 c4417b10 65004c8b 6c2498c4 417b1036 .A{.e.L.l$..A{.6 + 0200 c4417b10 5d004c8b 6c24a0c4 417b103f .A{.].L.l$..A{.? + 0210 c4417b10 55004c8b 6c24a8c5 7b1000c4 .A{.U.L.l$..{... + 0220 417b104d 00c4c17b 113f4c8b 6c2490c4 A{.M...{.?L.l$.. + 0230 c17b1136 4c8b7424 88c50311 ffc4c17b .{.6L.t$.......{ + 0240 112ec4c1 7b116500 4c8b6c24 98c50b11 ....{.e.L.l$.... + 0250 f6c4c17b 115d004c 8b6c24a0 c51311ed ...{.].L.l$..... + 0260 c4c17b11 55004c8b 6c24a8c5 1b11e4c4 ..{.U.L.l$...... + 0270 c17b114d 00c52311 dbc5fb11 00c52b11 .{.M..#.......+. + 0280 d2c53311 c9c53b11 c048ffc2 c5fb117d ..3...;..H.....} + 0290 00c5fb11 7508c5fb 116d10c5 fb116518 ....u....m....e. + 02a0 c5fb115d 20c5fb11 5528c5fb 114d30c5 ...] ...U(...M0. + 02b0 fb114538 4883c108 4883c540 4983c408 ..E8H...H..@I... + 02c0 4983c308 4983c208 4983c008 4883c708 I...I...I...H... + 02d0 4883c608 48395424 b00f8d51 feffff48 H...H9T$...Q...H + 02e0 8b7c24d8 48017c24 c84801fb 48ff4c24 .|$.H.|$.H..H.L$ + 02f0 e00f85f9 fdffff48 8b442430 4d89cc48 .......H.D$0M..H + 0300 0fafc748 01442420 f6442418 040f8423 ...H.D$ .D$....# + 0310 010000c4 e1fb93c0 4863304c 8b6c2420 ........Hc0L.l$ + 0320 4a8d0426 4d8d44c5 004c01e0 498d7cc5 J..&M.D..L..I.|. + 0330 004c01e0 498d54c5 004d89e2 4b8d0464 .L..I.T..M..K..d + 0340 49c1e204 4d8d5cc5 004c8b74 24b0488b I...M.\..L.t$.H. + 0350 4424d04c 8b7c2428 4d8d4cf5 004b8d5c D$.L.|$(M.L..K.\ + 0360 e5004d01 ea4889e9 0f1f8400 00000000 ..M..H.......... + 0370 c4c17b10 5cc500c5 fb1014c3 c4c17b10 ..{.\.........{. + 0380 0cc2c4c1 7b1004c3 4839f074 34c4c17b ....{...H9.t4..{ + 0390 1039c4c1 7b1030c5 fb102fc5 fb1022c4 .9..{.0.../...". + 03a0 c17b1119 c4c17b11 10c5c310 dfc5fb11 .{....{......... + 03b0 0fc5cb10 d6c5fb11 02c5d310 cdc5db10 ................ + 03c0 c4496334 8748ffc0 498d1434 4d8d44d5 .Ic4.H..I..4M.D. + 03d0 004c01e2 498d7cd5 004c01e2 c5fb1119 .L..I.|..L...... + 03e0 c5fb1151 08c5fb11 4910c5fb 1141184d ...Q....I....A.M + 03f0 8d4cf500 498d54d5 004883c1 204939c6 .L..I.T..H.. I9. + 0400 0f8d6aff ffff488b 7424b048 8b7c24d0 ..j...H.t$.H.|$. + 0410 488d4601 4829f848 c1e005ba 20000000 H.F.H).H.... ... + 0420 4839f748 0f4fc248 01c54c89 e048c1e0 H9.H.O.H..L..H.. + 0430 05480144 2420f644 2418020f 84a90000 .H.D$ .D$....... + 0440 00488b44 2428488b 7424204c 8d40fc4e .H.D$(H.t$ L.@.N + 0450 8d0ce500 00000048 8b4424d0 4c8b5c24 .......H.D$.L.\$ + 0460 b04a8d3c 0e4889e9 0f1f8400 00000000 .J.<.H.......... + 0470 49631480 c5fb100c c6c5fb10 04c74839 Ic............H9 + 0480 d074254c 8d14d64c 01e2488d 14d6c4c1 .t%L...L..H..... + 0490 7b101ac5 fb1012c4 c17b110a c5fb1102 {........{...... + 04a0 c5e310cb c5eb10c2 48ffc0c5 fb1109c5 ........H....... + 04b0 fb114108 4883c110 4939c37d b3488b74 ..A.H...I9.}.H.t + 04c0 24b0488b 5c24d048 8d460148 29d848c1 $.H.\$.H.F.H).H. + 04d0 e004ba10 00000048 39f3480f 4fc24801 .......H9.H.O.H. + 04e0 c54a8d04 0f488944 2420f644 24180174 .J...H.D$ .D$..t + 04f0 5a488b74 24d0488b 44242848 89f248f7 ZH.t$.H.D$(H..H. + 0500 da488b7c 24204c8b 4424b048 8d4cd500 .H.|$ L.D$.H.L.. + 0510 4883e804 4889f266 0f1f8400 00000000 H...H..f........ + 0520 48633490 c5fb1004 d74839f2 7410488d Hc4......H9.t.H. + 0530 34f7c5fb 100ec5fb 1106c5f3 10c1c5fb 4............... + 0540 1104d148 ffc24939 d07dd548 83c4385b ...H..I9.}.H..8[ + 0550 5d415c41 5d415e31 c0415fc3 ]A\A]A^1.A_. /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 09080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dlaswp_ncopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 e3040000 00420e10 8f02420e .........B....B. + 0020 00000000 5c050000 00420e10 8f02420e ....\....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830744 0e58033c 030a0e38 ..A.8..D.X.<...8 - 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D - 0060 0e084a0b 00000000 ..J..... + 0040 8606410e 38830744 0e700341 050e3841 ..A.8..D.p.A..8A + 0050 0e30410e 28420e20 420e1842 0e10440e .0A.(B. B..B..D. + 0060 08000000 00000000 ........ /usr/lib64/libopenblas_openmp.a/dneg_tcopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dneg_tcopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dneg_tcopy_COOPERLAKE.o (disasm) @@ -6,156 +6,140 @@ dneg_tcopy_COOPERLAKE: push %r15 - mov %rdi,%r11 - mov %rdx,%r10 + mov %rsi,%rax + and $something,%rax push %r14 + imul %rdi,%rax push %r13 + lea (%r8,%rax,8),%r11 push %r12 push %rbp - mov %rsi,%rbp - sar $something,%rbp push %rbx mov %rsi,%rbx + mov %rbx,%rax + mov %rsi,-offset(%rsp) + and $something,%rax + mov %rdi,%rsi + imul %rsi,%rax + mov %rsi,%r9 + sar $something,%r9 + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rbx,%rdi mov %rcx,-offset(%rsp) - mov %rbp,-offset(%rsp) - test %rbp,%rbp + mov %r9,-offset(%rsp) + lea (%r8,%rax,8),%rbx + test %r9,%r9 jle - mov %rdi,%r12 - mov %rcx,%rdi - shl $something,%rdi - sar %r12 mov %rdi,%rax - imul %r12,%rax - mov %rcx,%rsi + sar $something,%rax + mov %rax,-offset(%rsp) + shl $something,%rax + mov %rax,%r13 + mov %rcx,%rax + shl $something,%rsi + shl $something,%rax vmovq offset(%rip),%xmm0 # - mov %r12,%rcx - mov %r11,%r13 - shl $something,%rcx - lea -offset(,%rsi,8),%rsi - add $something,%rax - mov %rcx,-offset(%rsp) + mov %rax,-offset(%rsp) + mov %rsi,%rbp + lea (%rcx,%rcx,2),%rax + mov %rdi,%rsi + mov %rcx,%r14 + and $something,%esi + and $something,%edi + shl $something,%rax mov %rsi,-offset(%rsp) + mov %rdi,-offset(%rsp) mov %rax,-offset(%rsp) - and $something,%r13d - mov %rdx,%r9 - vmovapd %xmm0,%xmm31 + mov %r8,-offset(%rsp) + lea offset(,%rcx,8),%r15 + shl $something,%r14 + add %rdx,%r13 + mov %r8,%r12 + mov %rdx,%r10 + vmovapd %xmm0,%xmm16 + vmovapd %xmm0,%xmm17 jmp - nopl offset(%rax,%rax,1) - test %r13,%r13 + cs nopw offset(%rax,%rax,1) + cmpq $something,-offset(%rsp) je - vmovsd offset(%rdx),%xmm15 - vmovsd offset(%rdx),%xmm14 - vmovsd offset(%rdx),%xmm13 - vmovsd offset(%rdx),%xmm12 - vmovsd offset(%rdx),%xmm11 - vmovsd offset(%rdx),%xmm10 - vmovsd offset(%rdx),%xmm9 - vmovsd offset(%rdx),%xmm8 - vmovsd offset(%rdx),%xmm7 - vmovsd offset(%rdx),%xmm6 - vmovsd offset(%rdx),%xmm5 - vmovsd offset(%rdx),%xmm4 + vmovsd (%rsi),%xmm8 + vmovsd offset(%rsi),%xmm7 + vmovsd (%rcx),%xmm6 + vmovsd offset(%rcx),%xmm5 + vmovsd (%rdx),%xmm4 vmovsd offset(%rdx),%xmm3 - vmovsd offset(%rdx),%xmm2 - vmovsd offset(%rdx),%xmm1 - vmovsd (%rdx),%xmm16 - vxorpd %xmm31,%xmm15,%xmm15 - vxorpd %xmm31,%xmm16,%xmm16 - vxorpd %xmm31,%xmm14,%xmm14 - vxorpd %xmm31,%xmm13,%xmm13 - vxorpd %xmm31,%xmm12,%xmm12 - vxorpd %xmm31,%xmm11,%xmm11 - vxorpd %xmm31,%xmm10,%xmm10 - vxorpd %xmm31,%xmm9,%xmm9 - vxorpd %xmm31,%xmm8,%xmm8 - vxorpd %xmm31,%xmm7,%xmm7 - vxorpd %xmm31,%xmm6,%xmm6 - vxorpd %xmm31,%xmm5,%xmm5 - vxorpd %xmm31,%xmm4,%xmm4 - vxorpd %xmm31,%xmm3,%xmm3 - vxorpd %xmm31,%xmm2,%xmm2 - vxorpd %xmm31,%xmm1,%xmm1 - vmovsd %xmm16,(%r8) - vmovsd %xmm15,offset(%r8) - vmovsd %xmm14,offset(%r8) - vmovsd %xmm13,offset(%r8) - vmovsd %xmm12,offset(%r8) - vmovsd %xmm11,offset(%r8) - vmovsd %xmm10,offset(%r8) - vmovsd %xmm9,offset(%r8) - vmovsd %xmm8,offset(%r8) - vmovsd %xmm7,offset(%r8) - vmovsd %xmm6,offset(%r8) - vmovsd %xmm5,offset(%r8) - vmovsd %xmm4,offset(%r8) - vmovsd %xmm3,offset(%r8) - vmovsd %xmm2,offset(%r8) - vmovsd %xmm1,offset(%r8) - sub $something,%r8 - dec %rbp + vmovsd (%rdi),%xmm2 + vmovsd offset(%rdi),%xmm1 + vxorpd %xmm16,%xmm8,%xmm8 + vxorpd %xmm16,%xmm7,%xmm7 + vxorpd %xmm16,%xmm6,%xmm6 + vxorpd %xmm16,%xmm5,%xmm5 + vxorpd %xmm16,%xmm4,%xmm4 + vxorpd %xmm16,%xmm3,%xmm3 + vxorpd %xmm16,%xmm2,%xmm2 + vxorpd %xmm16,%xmm1,%xmm1 + vmovsd %xmm8,(%r11) + vmovsd %xmm7,offset(%r11) + vmovsd %xmm6,offset(%r11) + vmovsd %xmm5,offset(%r11) + vmovsd %xmm4,offset(%r11) + vmovsd %xmm3,offset(%r11) + vmovsd %xmm2,offset(%r11) + vmovsd %xmm1,offset(%r11) + add $something,%rsi + add $something,%rcx + add $something,%rdx + add $something,%rdi + add $something,%r11 + cmpq $something,-offset(%rsp) + je + vmovsd (%rcx),%xmm3 + vmovsd (%rdx),%xmm2 + vmovsd (%rdi),%xmm1 + vmovsd (%rsi),%xmm4 + vxorpd %xmm17,%xmm3,%xmm3 + vxorpd %xmm17,%xmm4,%xmm4 + vxorpd %xmm17,%xmm2,%xmm2 + vxorpd %xmm17,%xmm1,%xmm1 + vmovsd %xmm4,(%rbx) + vmovsd %xmm3,offset(%rbx) + vmovsd %xmm2,offset(%rbx) + vmovsd %xmm1,offset(%rbx) + add $something,%rbx + add %r14,%r13 + dec %r9 je - mov %r9,%rdx - sub $something,%r9 - test %r12,%r12 - jle mov -offset(%rsp),%rax - mov %r12,%rsi - lea (%rax,%r9,1),%rcx - mov %r8,%rax - xchg %ax,%ax - vmovsd (%rdx),%xmm30 - mov offset(%rdx),%r15 - vxorpd %xmm0,%xmm30,%xmm30 - mov offset(%rdx),%r14 - vmovsd offset(%rdx),%xmm29 - vmovsd offset(%rdx),%xmm28 - vmovsd offset(%rdx),%xmm27 - vmovsd offset(%rdx),%xmm26 - vmovsd offset(%rdx),%xmm25 /usr/lib64/libopenblas_openmp.a/dneg_tcopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dneg_tcopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dneg_tcopy_COOPERLAKE.o (objdump) @@ -2,146 +2,95 @@ /usr/lib64/libopenblas_openmp.a/dneg_tcopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574989 fb4989d2 41564155 41545548 AWI..I..AVAUATUH - 0010 89f548c1 fd045348 89f34889 4c24f048 ..H...SH..H.L$.H - 0020 896c24f8 4885ed0f 8e2f0400 004989fc .l$.H..../...I.. - 0030 4889cf48 c1e70449 d1fc4889 f8490faf H..H...I..H..I.. - 0040 c44889ce c5fa7e05 00000000 4c89e14d .H....~.....L..M - 0050 89dd48c1 e108488d 34f580ff ffff4883 ..H...H.4.....H. - 0060 c0804889 4c24d848 897424e0 48894424 ..H.L$.H.t$.H.D$ - 0070 e84183e5 014989d1 6261fd08 28f8e92c .A...I..ba..(.., - 0080 0100000f 1f440000 4d85ed0f 84150100 .....D..M....... - 0090 00c57b10 7a08c57b 107210c5 7b106a18 ..{.z..{.r..{.j. - 00a0 c57b1062 20c57b10 5a28c57b 105230c5 .{.b .{.Z(.{.R0. - 00b0 7b104a38 c57b1042 40c5fb10 7a48c5fb {.J8.{.B@...zH.. - 00c0 107250c5 fb106a58 c5fb1062 60c5fb10 .rP...jX...b`... - 00d0 5a68c5fb 105270c5 fb104a78 62e1ff08 Zh...Rp...Jxb... - 00e0 10026211 850857ff 6281fd00 57c76211 ..b...W.b...W.b. - 00f0 8d0857f7 62119508 57ef6211 9d0857e7 ..W.b...W.b...W. - 0100 6211a508 57df6211 ad0857d7 6211b508 b...W.b...W.b... - 0110 57cf6211 bd0857c7 6291c508 57ff6291 W.b...W.b...W.b. - 0120 cd0857f7 6291d508 57ef6291 dd0857e7 ..W.b...W.b...W. - 0130 6291e508 57df6291 ed0857d7 6291f508 b...W.b...W.b... - 0140 57cf62c1 ff081100 c4417b11 7808c441 W.b......A{.x..A - 0150 7b117010 c4417b11 6818c441 7b116020 {.p..A{.h..A{.` - 0160 c4417b11 5828c441 7b115030 c4417b11 .A{.X(.A{.P0.A{. - 0170 4838c441 7b114040 c4c17b11 7848c4c1 H8.A{.@@..{.xH.. - 0180 7b117050 c4c17b11 6858c4c1 7b116060 {.pP..{.hX..{.`` - 0190 c4c17b11 5868c4c1 7b115070 c4c17b11 ..{.Xh..{.Pp..{. - 01a0 48784983 e88048ff cd0f84a1 0200004c HxI...H........L - 01b0 89ca4983 e9804d85 e40f8ec9 feffff48 ..I...M........H - 01c0 8b4424e0 4c89e64a 8d0c084c 89c06690 .D$.L..J...L..f. - 01d0 6261ff08 10324c8b 7a086261 8d0057f0 ba...2L.z.ba..W. - 01e0 4c8b7210 6261ff08 106a0362 61ff0810 L.r.ba...j.ba... - 01f0 62046261 ff08105a 056261ff 08105206 b.ba...Z.ba...R. - 0200 6261ff08 104a0762 61ff0810 420862e1 ba...J.ba...B.b. - 0210 ff08107a 0962e1ff 0810720a 62e1ff08 ...z.b....r.b... - 0220 106a0b62 e1ff0810 620c62e1 ff08105a .j.b....b.b....Z - 0230 0d62e1ff 0810520e 62e1ff08 104a0f62 .b....R.b....J.b - 0240 e1ff0810 01c57b10 7908c57b 107110c5 ......{.y..{.q.. - 0250 7b106918 c57b1061 20c57b10 5928c57b {.i..{.a .{.Y(.{ - 0260 105130c5 7b104938 c57b1041 40c5fb10 .Q0.{.I8.{.A@... - 0270 7948c5fb 107150c5 fb106958 c5fb1061 yH...qP...iX...a - 0280 60c5fb10 5968c5fb 105170c5 fb104978 `...Yh...Qp...Ix - 0290 6261ff08 11306241 fd086ef7 62618d00 ba...0bA..n.ba.. - 02a0 57f06261 ff081170 016241fd 086ef662 W.ba...p.bA..n.b - 02b0 618d0057 f0626195 0057e862 619d0057 a..W.ba..W.ba..W - 02c0 e06261a5 0057d862 61ad0057 d06261b5 .ba..W.ba..W.ba. - 02d0 0057c862 61bd0057 c062e1c5 0057f862 .W.ba..W.b...W.b - 02e0 e1cd0057 f062e1d5 0057e862 e1dd0057 ...W.b...W.b...W - 02f0 e062e1e5 0057d862 e1ed0057 d062e1f5 .b...W.b...W.b.. - 0300 0057c862 e1fd0057 c0c50157 f8c50957 .W.b...W...W...W - 0310 f0c51157 e8c51957 e0c52157 d8c52957 ...W...W..!W..)W - 0320 d0c53157 c8c53957 c0c5c157 f8c5c957 ..1W..9W...W...W - 0330 f0c5d157 e8c5d957 e0c5e157 d8c5e957 ...W...W...W...W - 0340 d0c5f157 c86261ff 08117002 6261ff08 ...W.ba...p.ba.. - 0350 11680362 61ff0811 60046261 ff081158 .h.ba...`.ba...X - 0360 056261ff 08115006 6261ff08 11480762 .ba...P.ba...H.b - 0370 61ff0811 400862e1 ff081178 0962e1ff a...@.b....x.b.. - 0380 0811700a 62e1ff08 11680b62 e1ff0811 ..p.b....h.b.... - 0390 600c62e1 ff081158 0d62e1ff 0811500e `.b....X.b....P. - 03a0 62e1ff08 11480f62 e1ff0811 4010c57b b....H.b....@..{ - 03b0 11b88800 0000c57b 11b09000 0000c57b .......{.......{ - 03c0 11a89800 0000c57b 11a0a000 0000c57b .......{.......{ - 03d0 1198a800 0000c57b 1190b000 0000c57b .......{.......{ - 03e0 1188b800 0000c57b 1180c000 0000c5fb .......{........ - 03f0 11b8c800 0000c5fb 11b0d000 0000c5fb ................ - 0400 11a8d800 0000c5fb 11a0e000 0000c5fb ................ - 0410 1198e800 0000c5fb 1190f000 0000c5fb ................ - 0420 1188f800 00004801 fa4801f9 48050001 ......H..H..H... - 0430 000048ff ce0f8595 fdffff48 8b4424e8 ..H........H.D$. - 0440 4c034424 d8498d14 01e93afc ffff6690 L.D$.I....:...f. - 0450 488b4424 f848c1e0 074901c2 f6c3080f H.D$.H...I...... - 0460 84d70100 004d89d9 49d1f949 8d6a404d .....M..I..I.j@M - 0470 85c90f8e 2c010000 488b4424 f0c5fa7e ....,...H.D$...~ - 0480 05000000 00498d0c c248c1e0 044889c7 .....I...H...H.. - 0490 4c89d24c 89c04c89 ce0f1f80 00000000 L..L..L......... - 04a0 c57b107a 08c57b10 7210c57b 106a18c5 .{.z..{.r..{.j.. - 04b0 7b106220 c57b105a 28c57b10 5230c57b {.b .{.Z(.{.R0.{ - 04c0 104a38c5 7b1001c5 fb107908 c5fb1071 .J8.{.....y....q - 04d0 10c5fb10 6918c5fb 106120c5 fb105928 ....i....a ...Y( - 04e0 c5fb1051 30c5fb10 493862e1 ff081002 ...Q0...I8b..... - 04f0 c50157f8 62e1fd00 57c0c509 57f0c511 ..W.b...W...W... - 0500 57e8c519 57e0c521 57d8c529 57d0c531 W...W..!W..)W..1 - 0510 57c8c539 57c0c5c1 57f8c5c9 57f0c5d1 W..9W...W...W... - 0520 57e8c5d9 57e0c5e1 57d8c5e9 57d0c5f1 W...W...W...W... - 0530 57c862e1 ff081100 c57b1178 08c57b11 W.b......{.x..{. - 0540 7010c57b 116818c5 7b116020 c57b1158 p..{.h..{.` .{.X - 0550 28c57b11 5030c57b 114838c5 7b114040 (.{.P0.{.H8.{.@@ - 0560 c5fb1178 48c5fb11 7050c5fb 116858c5 ...xH...pP...hX. - 0570 fb116060 c5fb1158 68c5fb11 5070c5fb ..``...Xh...Pp.. - 0580 11487848 01fa4801 f94883e8 8048ffce .HxH..H..H...H.. - 0590 0f850aff ffff490f aff949c1 e1074d01 ......I...I...M. - 05a0 c84901fa 41f6c301 0f841203 0000c4c1 .I..A........... - 05b0 7b107a08 c4c17b10 7210c4c1 7b106a18 {.z...{.r...{.j. - 05c0 c4c17b10 6220c4c1 7b105a28 c4c17b10 ..{.b ..{.Z(..{. - 05d0 5230c4c1 7b104a38 c4417b10 02c5fa7e R0..{.J8.A{....~ - 05e0 05000000 004983c0 40c53957 c0c5c157 .....I..@.9W...W - 05f0 f8c5c957 f0c5d157 e8c5d957 e0c5e157 ...W...W...W...W - 0600 d8c5e957 d0c5f157 c0c4417b 1140c0c4 ...W...W..A{.@.. - 0610 c17b1178 c8c4c17b 1170d0c4 c17b1168 .{.x...{.p...{.h - 0620 d8c4c17b 1160e0c4 c17b1158 e8c4c17b ...{.`...{.X...{ - 0630 1150f0c4 c17b1140 f84989ea f6c3040f .P...{.@.I...... - 0640 841d0100 004d89d9 49d1f949 8d6a204d .....M..I..I.j M - 0650 85c90f8e b2000000 488b4424 f0c5fa7e ........H.D$...~ - 0660 05000000 00498d0c c248c1e0 044889c7 .....I...H...H.. - 0670 4c89d24c 89c04c89 ce0f1f80 00000000 L..L..L......... - 0680 c5fb107a 08c5fb10 7210c5fb 106a18c5 ...z....r....j.. - 0690 fb1021c5 fb105908 c5fb1051 10c5fb10 ..!...Y....Q.... - 06a0 4918c57b 1002c5c1 57f8c539 57c0c5c9 I..{....W..9W... - 06b0 57f0c5d1 57e8c5d9 57e0c5e1 57d8c5e9 W...W...W...W... - 06c0 57d0c5f1 57c8c57b 1100c5fb 117808c5 W...W..{.....x.. - 06d0 fb117010 c5fb1168 18c5fb11 6020c5fb ..p....h....` .. - 06e0 115828c5 fb115030 c5fb1148 384801fa .X(...P0...H8H.. - 06f0 4801f948 83c04048 ffce7584 490faff9 H..H..@H..u.I... - 0700 49c1e106 4d01c849 01fa41f6 c3010f84 I...M..I..A..... - 0710 bc010000 c4c17b10 5a08c4c1 7b105210 ......{.Z...{.R. - 0720 c4c17b10 4a18c4c1 7b1022c5 fa7e0500 ..{.J...{."..~.. - 0730 00000049 83c020c5 d957e0c5 e157d8c5 ...I.. ..W...W.. - 0740 e957d0c5 f157c0c4 c17b1160 e0c4c17b .W...W...{.`...{ - 0750 1158e8c4 c17b1150 f0c4c17b 1140f849 .X...{.P...{.@.I - 0760 89eaf6c3 020f84bf 0000004d 89d949d1 ...........M..I. - 0770 f9498d6a 104d85c9 7e78488b 4424f0c5 .I.j.M..~xH.D$.. - 0780 fa7e0500 00000049 8d0cc248 c1e00448 .~.....I...H...H - 0790 89c74c89 d24c89c0 4c89ce0f 1f440000 ..L..L..L....D.. - 07a0 c5fb105a 08c5fb10 11c5fb10 4908c5fb ...Z........I... - 07b0 1022c5e1 57d8c5d9 57e0c5e9 57d0c5f1 ."..W...W...W... - 07c0 57c8c5fb 1120c5fb 115808c5 fb115010 W.... ...X....P. - 07d0 c5fb1148 184801fa 4801f948 83c02048 ...H.H..H..H.. H - 07e0 ffce75bc 490faff9 49c1e105 4d01c849 ..u.I...I...M..I - 07f0 01fa41f6 c3010f84 e4000000 c4c17b10 ..A...........{. - 0800 4a08c4c1 7b1012c5 fa7e0500 00000049 J...{....~.....I - 0810 83c010c5 e957d0c5 f157c0c4 c17b1150 .....W...W...{.P - 0820 f0c4c17b 1140f849 89ea83e3 01747f4d ...{.@.I.....t.M - 0830 89d949d1 f94d85c9 7e5c488b 4424f0c5 ..I..M..~\H.D$.. - 0840 fa7e0500 00000049 8d3cc248 c1e00448 .~.....I.<.H...H - 0850 89c64c89 c24c89c9 31c0660f 1f440000 ..L..L..1.f..D.. - 0860 c5fb100c 07c4c17b 101402c5 f157c8c5 .......{.....W.. - 0870 e957d0c5 fb1112c5 fb114a08 4801f048 .W........J.H..H - 0880 83c21048 ffc975d8 490faff1 49c1e104 ...H..u.I...I... - 0890 4d01c849 01f24183 e3017412 c4c17b10 M..I..A...t...{. - 08a0 02c5f957 05000000 00c4c17b 11005b5d ...W.......{..[] - 08b0 415c415d 415e31c0 415fc30f 1f440000 A\A]A^1.A_...D.. - 08c0 4989eae9 74fdffff 0f1f8400 00000000 I...t........... - 08d0 4989eae9 8afeffff 0f1f8400 00000000 I............... - 08e0 4989eae9 42ffffff I...B... + 0000 41574889 f04883e0 fc415648 0fafc741 AWH..H...AVH...A + 0010 554d8d1c c0415455 534889f3 4889d848 UM...ATUSH..H..H + 0020 897424d8 4883e0fe 4889fe48 0fafc649 .t$.H...H..H...I + 0030 89f149c1 f9024889 7c24e048 895424d0 ..I...H.|$.H.T$. + 0040 4889df48 894c24f0 4c894c24 e8498d1c H..H.L$.L.L$.I.. + 0050 c04d85c9 0f8ee802 00004889 f848c1f8 .M........H..H.. + 0060 02488944 24a848c1 e0054989 c54889c8 .H.D$.H...I..H.. + 0070 48c1e605 48c1e004 c5fa7e05 00000000 H...H.....~..... + 0080 48894424 b04889f5 488d0449 4889fe49 H.D$.H..H..IH..I + 0090 89ce83e6 0283e701 48c1e003 48897424 ........H...H.t$ + 00a0 b848897c 24c04889 4424c84c 894424f8 .H.|$.H.D$.L.D$. + 00b0 4c8d3ccd 00000000 49c1e605 4901d54d L.<.....I...I..M + 00c0 89c44989 d262e1fd 0828c062 e1fd0828 ..I..b...(.b...( + 00d0 c8e90001 0000662e 0f1f8400 00000000 ......f......... + 00e0 48837c24 b8000f84 97000000 c57b1006 H.|$.........{.. + 00f0 c5fb107e 08c5fb10 31c5fb10 6908c5fb ...~....1...i... + 0100 1022c5fb 105a08c5 fb1017c5 fb104f08 ."...Z........O. + 0110 6231bd08 57c062b1 c50857f8 62b1cd08 b1..W.b...W.b... + 0120 57f062b1 d50857e8 62b1dd08 57e062b1 W.b...W.b...W.b. + 0130 e50857d8 62b1ed08 57d062b1 f50857c8 ..W.b...W.b...W. + 0140 c4417b11 03c4c17b 117b08c4 c17b1173 .A{....{.{...{.s + 0150 10c4c17b 116b18c4 c17b1163 20c4c17b ...{.k...{.c ..{ + 0160 115b28c4 c17b1153 30c4c17b 114b3848 .[(..{.S0..{.K8H + 0170 83c61048 83c11048 83c21048 83c71049 ...H...H...H...I + 0180 83c34048 837c24c0 00743fc5 fb1019c5 ..@H.|$..t?..... + 0190 fb1012c5 fb100fc5 fb102662 b1e50857 ..........&b...W + 01a0 d962b1dd 0857e162 b1ed0857 d162b1f5 .b...W.b...W.b.. + 01b0 0857c9c5 fb1123c5 fb115b08 c5fb1153 .W....#...[....S + 01c0 10c5fb11 4b184883 c3204d01 f549ffc9 ....K.H.. M..I.. + 01d0 0f845201 0000488b 4424b04b 8d0c174a ..R...H.D$.K...J + 01e0 8d141048 8b4424c8 4c89d649 8d3c024d ...H.D$.L..I.<.M + 01f0 01f24c89 e04983ec 8048837c 24a8000f ..L..I...H.|$... + 0200 8edbfeff ff4c8b44 24a8660f 1f440000 .....L.D$.f..D.. + 0210 62e1ff08 1016c57b 107e08c5 7b107610 b......{.~..{.v. + 0220 c57b106e 18c57b10 21c57b10 5908c57b .{.n..{.!.{.Y..{ + 0230 105110c5 7b104918 c57b1002 c5fb107a .Q..{.I..{.....z + 0240 08c5fb10 7210c5fb 106a18c5 fb1027c5 ....r....j....'. + 0250 fb105f08 c5fb1057 10c5fb10 4f1862e1 .._....W....O.b. + 0260 ed0057d0 c50157f8 c50957f0 c51157e8 ..W...W...W...W. + 0270 c51957e0 c52157d8 c52957d0 c53157c8 ..W..!W..)W..1W. + 0280 c53957c0 c5c157f8 c5c957f0 c5d157e8 .9W...W...W...W. + 0290 c5d957e0 c5e157d8 c5e957d0 c5f157c8 ..W...W...W...W. + 02a0 62e1ff08 1110c57b 117808c5 7b117010 b......{.x..{.p. + 02b0 c57b1168 18c57b11 6020c57b 115828c5 .{.h..{.` .{.X(. + 02c0 7b115030 c57b1148 38c57b11 4040c5fb {.P0.{.H8.{.@@.. + 02d0 117848c5 fb117050 c5fb1168 58c5fb11 .xH...pP...hX... + 02e0 6060c5fb 115868c5 fb115070 c5fb1148 ``...Xh...Pp...H + 02f0 784883c6 204883c1 204883c2 204883c7 xH.. H.. H.. H.. + 0300 204801e8 49ffc80f 8503ffff ff4b8d0c H..I........K.. + 0310 2f498d14 0f4c89ee 498d3c17 e9bffdff /I...L..I.<..... + 0320 ff0f1f80 00000000 488b4424 e84c8b44 ........H.D$.L.D /usr/lib64/libopenblas_openmp.a/dneg_tcopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dneg_tcopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dneg_tcopy_COOPERLAKE.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 e8080000 00420e10 8f02480e .........B....H. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606480e 38830703 98080a0e 30410e28 ..H.8.......0A.( - 0050 420e2042 0e18420e 10440e08 460b0000 B. B..B..D..F... + 0020 00000000 bd050000 00420e10 8f02490e .........B....I. + 0030 188e0346 0e208d04 460e288c 05410e30 ...F. ..F.(..A.0 + 0040 8606410e 38830703 84050a0e 30410e28 ..A.8.......0A.( + 0050 420e2042 0e18420e 10440e08 480b0000 B. B..B..D..H... /usr/lib64/libopenblas_openmp.a/dneg_tcopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dneg_tcopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dneg_tcopy_SKYLAKEX.o (disasm) @@ -6,156 +6,140 @@ dneg_tcopy_SKYLAKEX: push %r15 - mov %rdi,%r11 - mov %rdx,%r10 + mov %rsi,%rax + and $something,%rax push %r14 + imul %rdi,%rax push %r13 + lea (%r8,%rax,8),%r11 push %r12 push %rbp - mov %rsi,%rbp - sar $something,%rbp push %rbx mov %rsi,%rbx + mov %rbx,%rax + mov %rsi,-offset(%rsp) + and $something,%rax + mov %rdi,%rsi + imul %rsi,%rax + mov %rsi,%r9 + sar $something,%r9 + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rbx,%rdi mov %rcx,-offset(%rsp) - mov %rbp,-offset(%rsp) - test %rbp,%rbp + mov %r9,-offset(%rsp) + lea (%r8,%rax,8),%rbx + test %r9,%r9 jle - mov %rdi,%r12 - mov %rcx,%rdi - shl $something,%rdi - sar %r12 mov %rdi,%rax - imul %r12,%rax - mov %rcx,%rsi + sar $something,%rax + mov %rax,-offset(%rsp) + shl $something,%rax + mov %rax,%r13 + mov %rcx,%rax + shl $something,%rsi + shl $something,%rax vmovq offset(%rip),%xmm0 # - mov %r12,%rcx - mov %r11,%r13 - shl $something,%rcx - lea -offset(,%rsi,8),%rsi - add $something,%rax - mov %rcx,-offset(%rsp) + mov %rax,-offset(%rsp) + mov %rsi,%rbp + lea (%rcx,%rcx,2),%rax + mov %rdi,%rsi + mov %rcx,%r14 + and $something,%esi + and $something,%edi + shl $something,%rax mov %rsi,-offset(%rsp) + mov %rdi,-offset(%rsp) mov %rax,-offset(%rsp) - and $something,%r13d - mov %rdx,%r9 - vmovapd %xmm0,%xmm31 + mov %r8,-offset(%rsp) + lea offset(,%rcx,8),%r15 + shl $something,%r14 + add %rdx,%r13 + mov %r8,%r12 + mov %rdx,%r10 + vmovapd %xmm0,%xmm16 + vmovapd %xmm0,%xmm17 jmp - nopl offset(%rax,%rax,1) - test %r13,%r13 + cs nopw offset(%rax,%rax,1) + cmpq $something,-offset(%rsp) je - vmovsd offset(%rdx),%xmm15 - vmovsd offset(%rdx),%xmm14 - vmovsd offset(%rdx),%xmm13 - vmovsd offset(%rdx),%xmm12 - vmovsd offset(%rdx),%xmm11 - vmovsd offset(%rdx),%xmm10 - vmovsd offset(%rdx),%xmm9 - vmovsd offset(%rdx),%xmm8 - vmovsd offset(%rdx),%xmm7 - vmovsd offset(%rdx),%xmm6 - vmovsd offset(%rdx),%xmm5 - vmovsd offset(%rdx),%xmm4 + vmovsd (%rsi),%xmm8 + vmovsd offset(%rsi),%xmm7 + vmovsd (%rcx),%xmm6 + vmovsd offset(%rcx),%xmm5 + vmovsd (%rdx),%xmm4 vmovsd offset(%rdx),%xmm3 - vmovsd offset(%rdx),%xmm2 - vmovsd offset(%rdx),%xmm1 - vmovsd (%rdx),%xmm16 - vxorpd %xmm31,%xmm15,%xmm15 - vxorpd %xmm31,%xmm16,%xmm16 - vxorpd %xmm31,%xmm14,%xmm14 - vxorpd %xmm31,%xmm13,%xmm13 - vxorpd %xmm31,%xmm12,%xmm12 - vxorpd %xmm31,%xmm11,%xmm11 - vxorpd %xmm31,%xmm10,%xmm10 - vxorpd %xmm31,%xmm9,%xmm9 - vxorpd %xmm31,%xmm8,%xmm8 - vxorpd %xmm31,%xmm7,%xmm7 - vxorpd %xmm31,%xmm6,%xmm6 - vxorpd %xmm31,%xmm5,%xmm5 - vxorpd %xmm31,%xmm4,%xmm4 - vxorpd %xmm31,%xmm3,%xmm3 - vxorpd %xmm31,%xmm2,%xmm2 - vxorpd %xmm31,%xmm1,%xmm1 - vmovsd %xmm16,(%r8) - vmovsd %xmm15,offset(%r8) - vmovsd %xmm14,offset(%r8) - vmovsd %xmm13,offset(%r8) - vmovsd %xmm12,offset(%r8) - vmovsd %xmm11,offset(%r8) - vmovsd %xmm10,offset(%r8) - vmovsd %xmm9,offset(%r8) - vmovsd %xmm8,offset(%r8) - vmovsd %xmm7,offset(%r8) - vmovsd %xmm6,offset(%r8) - vmovsd %xmm5,offset(%r8) - vmovsd %xmm4,offset(%r8) - vmovsd %xmm3,offset(%r8) - vmovsd %xmm2,offset(%r8) - vmovsd %xmm1,offset(%r8) - sub $something,%r8 - dec %rbp + vmovsd (%rdi),%xmm2 + vmovsd offset(%rdi),%xmm1 + vxorpd %xmm16,%xmm8,%xmm8 + vxorpd %xmm16,%xmm7,%xmm7 + vxorpd %xmm16,%xmm6,%xmm6 + vxorpd %xmm16,%xmm5,%xmm5 + vxorpd %xmm16,%xmm4,%xmm4 + vxorpd %xmm16,%xmm3,%xmm3 + vxorpd %xmm16,%xmm2,%xmm2 + vxorpd %xmm16,%xmm1,%xmm1 + vmovsd %xmm8,(%r11) + vmovsd %xmm7,offset(%r11) + vmovsd %xmm6,offset(%r11) + vmovsd %xmm5,offset(%r11) + vmovsd %xmm4,offset(%r11) + vmovsd %xmm3,offset(%r11) + vmovsd %xmm2,offset(%r11) + vmovsd %xmm1,offset(%r11) + add $something,%rsi + add $something,%rcx + add $something,%rdx + add $something,%rdi + add $something,%r11 + cmpq $something,-offset(%rsp) + je + vmovsd (%rcx),%xmm3 + vmovsd (%rdx),%xmm2 + vmovsd (%rdi),%xmm1 + vmovsd (%rsi),%xmm4 + vxorpd %xmm17,%xmm3,%xmm3 + vxorpd %xmm17,%xmm4,%xmm4 + vxorpd %xmm17,%xmm2,%xmm2 + vxorpd %xmm17,%xmm1,%xmm1 + vmovsd %xmm4,(%rbx) + vmovsd %xmm3,offset(%rbx) + vmovsd %xmm2,offset(%rbx) + vmovsd %xmm1,offset(%rbx) + add $something,%rbx + add %r14,%r13 + dec %r9 je - mov %r9,%rdx - sub $something,%r9 - test %r12,%r12 - jle mov -offset(%rsp),%rax - mov %r12,%rsi - lea (%rax,%r9,1),%rcx - mov %r8,%rax - xchg %ax,%ax - vmovsd (%rdx),%xmm30 - mov offset(%rdx),%r15 - vxorpd %xmm0,%xmm30,%xmm30 - mov offset(%rdx),%r14 - vmovsd offset(%rdx),%xmm29 - vmovsd offset(%rdx),%xmm28 - vmovsd offset(%rdx),%xmm27 - vmovsd offset(%rdx),%xmm26 - vmovsd offset(%rdx),%xmm25 /usr/lib64/libopenblas_openmp.a/dneg_tcopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dneg_tcopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dneg_tcopy_SKYLAKEX.o (objdump) @@ -2,146 +2,95 @@ /usr/lib64/libopenblas_openmp.a/dneg_tcopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574989 fb4989d2 41564155 41545548 AWI..I..AVAUATUH - 0010 89f548c1 fd045348 89f34889 4c24f048 ..H...SH..H.L$.H - 0020 896c24f8 4885ed0f 8e2f0400 004989fc .l$.H..../...I.. - 0030 4889cf48 c1e70449 d1fc4889 f8490faf H..H...I..H..I.. - 0040 c44889ce c5fa7e05 00000000 4c89e14d .H....~.....L..M - 0050 89dd48c1 e108488d 34f580ff ffff4883 ..H...H.4.....H. - 0060 c0804889 4c24d848 897424e0 48894424 ..H.L$.H.t$.H.D$ - 0070 e84183e5 014989d1 6261fd08 28f8e92c .A...I..ba..(.., - 0080 0100000f 1f440000 4d85ed0f 84150100 .....D..M....... - 0090 00c57b10 7a08c57b 107210c5 7b106a18 ..{.z..{.r..{.j. - 00a0 c57b1062 20c57b10 5a28c57b 105230c5 .{.b .{.Z(.{.R0. - 00b0 7b104a38 c57b1042 40c5fb10 7a48c5fb {.J8.{.B@...zH.. - 00c0 107250c5 fb106a58 c5fb1062 60c5fb10 .rP...jX...b`... - 00d0 5a68c5fb 105270c5 fb104a78 62e1ff08 Zh...Rp...Jxb... - 00e0 10026211 850857ff 6281fd00 57c76211 ..b...W.b...W.b. - 00f0 8d0857f7 62119508 57ef6211 9d0857e7 ..W.b...W.b...W. - 0100 6211a508 57df6211 ad0857d7 6211b508 b...W.b...W.b... - 0110 57cf6211 bd0857c7 6291c508 57ff6291 W.b...W.b...W.b. - 0120 cd0857f7 6291d508 57ef6291 dd0857e7 ..W.b...W.b...W. - 0130 6291e508 57df6291 ed0857d7 6291f508 b...W.b...W.b... - 0140 57cf62c1 ff081100 c4417b11 7808c441 W.b......A{.x..A - 0150 7b117010 c4417b11 6818c441 7b116020 {.p..A{.h..A{.` - 0160 c4417b11 5828c441 7b115030 c4417b11 .A{.X(.A{.P0.A{. - 0170 4838c441 7b114040 c4c17b11 7848c4c1 H8.A{.@@..{.xH.. - 0180 7b117050 c4c17b11 6858c4c1 7b116060 {.pP..{.hX..{.`` - 0190 c4c17b11 5868c4c1 7b115070 c4c17b11 ..{.Xh..{.Pp..{. - 01a0 48784983 e88048ff cd0f84a1 0200004c HxI...H........L - 01b0 89ca4983 e9804d85 e40f8ec9 feffff48 ..I...M........H - 01c0 8b4424e0 4c89e64a 8d0c084c 89c06690 .D$.L..J...L..f. - 01d0 6261ff08 10324c8b 7a086261 8d0057f0 ba...2L.z.ba..W. - 01e0 4c8b7210 6261ff08 106a0362 61ff0810 L.r.ba...j.ba... - 01f0 62046261 ff08105a 056261ff 08105206 b.ba...Z.ba...R. - 0200 6261ff08 104a0762 61ff0810 420862e1 ba...J.ba...B.b. - 0210 ff08107a 0962e1ff 0810720a 62e1ff08 ...z.b....r.b... - 0220 106a0b62 e1ff0810 620c62e1 ff08105a .j.b....b.b....Z - 0230 0d62e1ff 0810520e 62e1ff08 104a0f62 .b....R.b....J.b - 0240 e1ff0810 01c57b10 7908c57b 107110c5 ......{.y..{.q.. - 0250 7b106918 c57b1061 20c57b10 5928c57b {.i..{.a .{.Y(.{ - 0260 105130c5 7b104938 c57b1041 40c5fb10 .Q0.{.I8.{.A@... - 0270 7948c5fb 107150c5 fb106958 c5fb1061 yH...qP...iX...a - 0280 60c5fb10 5968c5fb 105170c5 fb104978 `...Yh...Qp...Ix - 0290 6261ff08 11306241 fd086ef7 62618d00 ba...0bA..n.ba.. - 02a0 57f06261 ff081170 016241fd 086ef662 W.ba...p.bA..n.b - 02b0 618d0057 f0626195 0057e862 619d0057 a..W.ba..W.ba..W - 02c0 e06261a5 0057d862 61ad0057 d06261b5 .ba..W.ba..W.ba. - 02d0 0057c862 61bd0057 c062e1c5 0057f862 .W.ba..W.b...W.b - 02e0 e1cd0057 f062e1d5 0057e862 e1dd0057 ...W.b...W.b...W - 02f0 e062e1e5 0057d862 e1ed0057 d062e1f5 .b...W.b...W.b.. - 0300 0057c862 e1fd0057 c0c50157 f8c50957 .W.b...W...W...W - 0310 f0c51157 e8c51957 e0c52157 d8c52957 ...W...W..!W..)W - 0320 d0c53157 c8c53957 c0c5c157 f8c5c957 ..1W..9W...W...W - 0330 f0c5d157 e8c5d957 e0c5e157 d8c5e957 ...W...W...W...W - 0340 d0c5f157 c86261ff 08117002 6261ff08 ...W.ba...p.ba.. - 0350 11680362 61ff0811 60046261 ff081158 .h.ba...`.ba...X - 0360 056261ff 08115006 6261ff08 11480762 .ba...P.ba...H.b - 0370 61ff0811 400862e1 ff081178 0962e1ff a...@.b....x.b.. - 0380 0811700a 62e1ff08 11680b62 e1ff0811 ..p.b....h.b.... - 0390 600c62e1 ff081158 0d62e1ff 0811500e `.b....X.b....P. - 03a0 62e1ff08 11480f62 e1ff0811 4010c57b b....H.b....@..{ - 03b0 11b88800 0000c57b 11b09000 0000c57b .......{.......{ - 03c0 11a89800 0000c57b 11a0a000 0000c57b .......{.......{ - 03d0 1198a800 0000c57b 1190b000 0000c57b .......{.......{ - 03e0 1188b800 0000c57b 1180c000 0000c5fb .......{........ - 03f0 11b8c800 0000c5fb 11b0d000 0000c5fb ................ - 0400 11a8d800 0000c5fb 11a0e000 0000c5fb ................ - 0410 1198e800 0000c5fb 1190f000 0000c5fb ................ - 0420 1188f800 00004801 fa4801f9 48050001 ......H..H..H... - 0430 000048ff ce0f8595 fdffff48 8b4424e8 ..H........H.D$. - 0440 4c034424 d8498d14 01e93afc ffff6690 L.D$.I....:...f. - 0450 488b4424 f848c1e0 074901c2 f6c3080f H.D$.H...I...... - 0460 84d70100 004d89d9 49d1f949 8d6a404d .....M..I..I.j@M - 0470 85c90f8e 2c010000 488b4424 f0c5fa7e ....,...H.D$...~ - 0480 05000000 00498d0c c248c1e0 044889c7 .....I...H...H.. - 0490 4c89d24c 89c04c89 ce0f1f80 00000000 L..L..L......... - 04a0 c57b107a 08c57b10 7210c57b 106a18c5 .{.z..{.r..{.j.. - 04b0 7b106220 c57b105a 28c57b10 5230c57b {.b .{.Z(.{.R0.{ - 04c0 104a38c5 7b1001c5 fb107908 c5fb1071 .J8.{.....y....q - 04d0 10c5fb10 6918c5fb 106120c5 fb105928 ....i....a ...Y( - 04e0 c5fb1051 30c5fb10 493862e1 ff081002 ...Q0...I8b..... - 04f0 c50157f8 62e1fd00 57c0c509 57f0c511 ..W.b...W...W... - 0500 57e8c519 57e0c521 57d8c529 57d0c531 W...W..!W..)W..1 - 0510 57c8c539 57c0c5c1 57f8c5c9 57f0c5d1 W..9W...W...W... - 0520 57e8c5d9 57e0c5e1 57d8c5e9 57d0c5f1 W...W...W...W... - 0530 57c862e1 ff081100 c57b1178 08c57b11 W.b......{.x..{. - 0540 7010c57b 116818c5 7b116020 c57b1158 p..{.h..{.` .{.X - 0550 28c57b11 5030c57b 114838c5 7b114040 (.{.P0.{.H8.{.@@ - 0560 c5fb1178 48c5fb11 7050c5fb 116858c5 ...xH...pP...hX. - 0570 fb116060 c5fb1158 68c5fb11 5070c5fb ..``...Xh...Pp.. - 0580 11487848 01fa4801 f94883e8 8048ffce .HxH..H..H...H.. - 0590 0f850aff ffff490f aff949c1 e1074d01 ......I...I...M. - 05a0 c84901fa 41f6c301 0f841203 0000c4c1 .I..A........... - 05b0 7b107a08 c4c17b10 7210c4c1 7b106a18 {.z...{.r...{.j. - 05c0 c4c17b10 6220c4c1 7b105a28 c4c17b10 ..{.b ..{.Z(..{. - 05d0 5230c4c1 7b104a38 c4417b10 02c5fa7e R0..{.J8.A{....~ - 05e0 05000000 004983c0 40c53957 c0c5c157 .....I..@.9W...W - 05f0 f8c5c957 f0c5d157 e8c5d957 e0c5e157 ...W...W...W...W - 0600 d8c5e957 d0c5f157 c0c4417b 1140c0c4 ...W...W..A{.@.. - 0610 c17b1178 c8c4c17b 1170d0c4 c17b1168 .{.x...{.p...{.h - 0620 d8c4c17b 1160e0c4 c17b1158 e8c4c17b ...{.`...{.X...{ - 0630 1150f0c4 c17b1140 f84989ea f6c3040f .P...{.@.I...... - 0640 841d0100 004d89d9 49d1f949 8d6a204d .....M..I..I.j M - 0650 85c90f8e b2000000 488b4424 f0c5fa7e ........H.D$...~ - 0660 05000000 00498d0c c248c1e0 044889c7 .....I...H...H.. - 0670 4c89d24c 89c04c89 ce0f1f80 00000000 L..L..L......... - 0680 c5fb107a 08c5fb10 7210c5fb 106a18c5 ...z....r....j.. - 0690 fb1021c5 fb105908 c5fb1051 10c5fb10 ..!...Y....Q.... - 06a0 4918c57b 1002c5c1 57f8c539 57c0c5c9 I..{....W..9W... - 06b0 57f0c5d1 57e8c5d9 57e0c5e1 57d8c5e9 W...W...W...W... - 06c0 57d0c5f1 57c8c57b 1100c5fb 117808c5 W...W..{.....x.. - 06d0 fb117010 c5fb1168 18c5fb11 6020c5fb ..p....h....` .. - 06e0 115828c5 fb115030 c5fb1148 384801fa .X(...P0...H8H.. - 06f0 4801f948 83c04048 ffce7584 490faff9 H..H..@H..u.I... - 0700 49c1e106 4d01c849 01fa41f6 c3010f84 I...M..I..A..... - 0710 bc010000 c4c17b10 5a08c4c1 7b105210 ......{.Z...{.R. - 0720 c4c17b10 4a18c4c1 7b1022c5 fa7e0500 ..{.J...{."..~.. - 0730 00000049 83c020c5 d957e0c5 e157d8c5 ...I.. ..W...W.. - 0740 e957d0c5 f157c0c4 c17b1160 e0c4c17b .W...W...{.`...{ - 0750 1158e8c4 c17b1150 f0c4c17b 1140f849 .X...{.P...{.@.I - 0760 89eaf6c3 020f84bf 0000004d 89d949d1 ...........M..I. - 0770 f9498d6a 104d85c9 7e78488b 4424f0c5 .I.j.M..~xH.D$.. - 0780 fa7e0500 00000049 8d0cc248 c1e00448 .~.....I...H...H - 0790 89c74c89 d24c89c0 4c89ce0f 1f440000 ..L..L..L....D.. - 07a0 c5fb105a 08c5fb10 11c5fb10 4908c5fb ...Z........I... - 07b0 1022c5e1 57d8c5d9 57e0c5e9 57d0c5f1 ."..W...W...W... - 07c0 57c8c5fb 1120c5fb 115808c5 fb115010 W.... ...X....P. - 07d0 c5fb1148 184801fa 4801f948 83c02048 ...H.H..H..H.. H - 07e0 ffce75bc 490faff9 49c1e105 4d01c849 ..u.I...I...M..I - 07f0 01fa41f6 c3010f84 e4000000 c4c17b10 ..A...........{. - 0800 4a08c4c1 7b1012c5 fa7e0500 00000049 J...{....~.....I - 0810 83c010c5 e957d0c5 f157c0c4 c17b1150 .....W...W...{.P - 0820 f0c4c17b 1140f849 89ea83e3 01747f4d ...{.@.I.....t.M - 0830 89d949d1 f94d85c9 7e5c488b 4424f0c5 ..I..M..~\H.D$.. - 0840 fa7e0500 00000049 8d3cc248 c1e00448 .~.....I.<.H...H - 0850 89c64c89 c24c89c9 31c0660f 1f440000 ..L..L..1.f..D.. - 0860 c5fb100c 07c4c17b 101402c5 f157c8c5 .......{.....W.. - 0870 e957d0c5 fb1112c5 fb114a08 4801f048 .W........J.H..H - 0880 83c21048 ffc975d8 490faff1 49c1e104 ...H..u.I...I... - 0890 4d01c849 01f24183 e3017412 c4c17b10 M..I..A...t...{. - 08a0 02c5f957 05000000 00c4c17b 11005b5d ...W.......{..[] - 08b0 415c415d 415e31c0 415fc30f 1f440000 A\A]A^1.A_...D.. - 08c0 4989eae9 74fdffff 0f1f8400 00000000 I...t........... - 08d0 4989eae9 8afeffff 0f1f8400 00000000 I............... - 08e0 4989eae9 42ffffff I...B... + 0000 41574889 f04883e0 fc415648 0fafc741 AWH..H...AVH...A + 0010 554d8d1c c0415455 534889f3 4889d848 UM...ATUSH..H..H + 0020 897424d8 4883e0fe 4889fe48 0fafc649 .t$.H...H..H...I + 0030 89f149c1 f9024889 7c24e048 895424d0 ..I...H.|$.H.T$. + 0040 4889df48 894c24f0 4c894c24 e8498d1c H..H.L$.L.L$.I.. + 0050 c04d85c9 0f8ee802 00004889 f848c1f8 .M........H..H.. + 0060 02488944 24a848c1 e0054989 c54889c8 .H.D$.H...I..H.. + 0070 48c1e605 48c1e004 c5fa7e05 00000000 H...H.....~..... + 0080 48894424 b04889f5 488d0449 4889fe49 H.D$.H..H..IH..I + 0090 89ce83e6 0283e701 48c1e003 48897424 ........H...H.t$ + 00a0 b848897c 24c04889 4424c84c 894424f8 .H.|$.H.D$.L.D$. + 00b0 4c8d3ccd 00000000 49c1e605 4901d54d L.<.....I...I..M + 00c0 89c44989 d262e1fd 0828c062 e1fd0828 ..I..b...(.b...( + 00d0 c8e90001 0000662e 0f1f8400 00000000 ......f......... + 00e0 48837c24 b8000f84 97000000 c57b1006 H.|$.........{.. + 00f0 c5fb107e 08c5fb10 31c5fb10 6908c5fb ...~....1...i... + 0100 1022c5fb 105a08c5 fb1017c5 fb104f08 ."...Z........O. + 0110 6231bd08 57c062b1 c50857f8 62b1cd08 b1..W.b...W.b... + 0120 57f062b1 d50857e8 62b1dd08 57e062b1 W.b...W.b...W.b. + 0130 e50857d8 62b1ed08 57d062b1 f50857c8 ..W.b...W.b...W. + 0140 c4417b11 03c4c17b 117b08c4 c17b1173 .A{....{.{...{.s + 0150 10c4c17b 116b18c4 c17b1163 20c4c17b ...{.k...{.c ..{ + 0160 115b28c4 c17b1153 30c4c17b 114b3848 .[(..{.S0..{.K8H + 0170 83c61048 83c11048 83c21048 83c71049 ...H...H...H...I + 0180 83c34048 837c24c0 00743fc5 fb1019c5 ..@H.|$..t?..... + 0190 fb1012c5 fb100fc5 fb102662 b1e50857 ..........&b...W + 01a0 d962b1dd 0857e162 b1ed0857 d162b1f5 .b...W.b...W.b.. + 01b0 0857c9c5 fb1123c5 fb115b08 c5fb1153 .W....#...[....S + 01c0 10c5fb11 4b184883 c3204d01 f549ffc9 ....K.H.. M..I.. + 01d0 0f845201 0000488b 4424b04b 8d0c174a ..R...H.D$.K...J + 01e0 8d141048 8b4424c8 4c89d649 8d3c024d ...H.D$.L..I.<.M + 01f0 01f24c89 e04983ec 8048837c 24a8000f ..L..I...H.|$... + 0200 8edbfeff ff4c8b44 24a8660f 1f440000 .....L.D$.f..D.. + 0210 62e1ff08 1016c57b 107e08c5 7b107610 b......{.~..{.v. + 0220 c57b106e 18c57b10 21c57b10 5908c57b .{.n..{.!.{.Y..{ + 0230 105110c5 7b104918 c57b1002 c5fb107a .Q..{.I..{.....z + 0240 08c5fb10 7210c5fb 106a18c5 fb1027c5 ....r....j....'. + 0250 fb105f08 c5fb1057 10c5fb10 4f1862e1 .._....W....O.b. + 0260 ed0057d0 c50157f8 c50957f0 c51157e8 ..W...W...W...W. + 0270 c51957e0 c52157d8 c52957d0 c53157c8 ..W..!W..)W..1W. + 0280 c53957c0 c5c157f8 c5c957f0 c5d157e8 .9W...W...W...W. + 0290 c5d957e0 c5e157d8 c5e957d0 c5f157c8 ..W...W...W...W. + 02a0 62e1ff08 1110c57b 117808c5 7b117010 b......{.x..{.p. + 02b0 c57b1168 18c57b11 6020c57b 115828c5 .{.h..{.` .{.X(. + 02c0 7b115030 c57b1148 38c57b11 4040c5fb {.P0.{.H8.{.@@.. + 02d0 117848c5 fb117050 c5fb1168 58c5fb11 .xH...pP...hX... + 02e0 6060c5fb 115868c5 fb115070 c5fb1148 ``...Xh...Pp...H + 02f0 784883c6 204883c1 204883c2 204883c7 xH.. H.. H.. H.. + 0300 204801e8 49ffc80f 8503ffff ff4b8d0c H..I........K.. + 0310 2f498d14 0f4c89ee 498d3c17 e9bffdff /I...L..I.<..... + 0320 ff0f1f80 00000000 488b4424 e84c8b44 ........H.D$.L.D /usr/lib64/libopenblas_openmp.a/dneg_tcopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dneg_tcopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dneg_tcopy_SKYLAKEX.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 e8080000 00420e10 8f02480e .........B....H. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606480e 38830703 98080a0e 30410e28 ..H.8.......0A.( - 0050 420e2042 0e18420e 10440e08 460b0000 B. B..B..D..F... + 0020 00000000 bd050000 00420e10 8f02490e .........B....I. + 0030 188e0346 0e208d04 460e288c 05410e30 ...F. ..F.(..A.0 + 0040 8606410e 38830703 84050a0e 30410e28 ..A.8.......0A.( + 0050 420e2042 0e18420e 10440e08 480b0000 B. B..B..D..H... /usr/lib64/libopenblas_openmp.a/drot_k_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/drot_k_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/drot_k_COOPERLAKE.o (disasm) @@ -5,131 +5,117 @@ Disassembly of section .text: rot_compute: - mov %rsi,%r9 + mov %rdi,%r9 + mov %rsi,%rax vmovsd %xmm0,%xmm0,%xmm4 - mov %rcx,%rsi test %rdi,%rdi jle cmp $something,%rdx jne cmp $something,%r8 jne - mov %edi,%r10d - mov %edi,%ecx - and $something,%r10d - vbroadcastsd %xmm0,%zmm0 - vbroadcastsd %xmm1,%zmm2 - and $something,%ecx - jle - movslq %ecx,%rcx - dec %rcx - shr $something,%rcx - mov %rcx,%r8 - shl $something,%r8 - mov %r9,%rax - mov %rsi,%rdx - lea offset(%r9,%r8,1),%r8 - nopl offset(%rax) - vmovupd (%rdx),%zmm7 - vmovupd offset(%rdx),%zmm6 - vmovupd offset(%rdx),%zmm5 - vmovupd offset(%rdx),%zmm3 - vmulpd %zmm7,%zmm2,%zmm15 - vmulpd %zmm6,%zmm2,%zmm14 - vmulpd %zmm5,%zmm2,%zmm13 - vmulpd %zmm3,%zmm2,%zmm12 - vmovupd (%rax),%zmm11 - vmovupd offset(%rax),%zmm10 - vmovupd offset(%rax),%zmm9 - vmovupd offset(%rax),%zmm8 - vfmadd231pd %zmm11,%zmm0,%zmm15 - vfmadd231pd %zmm10,%zmm0,%zmm14 - vfmadd231pd %zmm9,%zmm0,%zmm13 - vfmadd231pd %zmm8,%zmm0,%zmm12 - vmulpd %zmm11,%zmm2,%zmm11 - vmulpd %zmm10,%zmm2,%zmm10 - vmulpd %zmm9,%zmm2,%zmm9 - vmulpd %zmm8,%zmm2,%zmm8 - vmovupd %zmm15,(%rax) - vfmsub132pd %zmm0,%zmm11,%zmm7 - vfmsub132pd %zmm0,%zmm10,%zmm6 - vfmsub132pd %zmm0,%zmm9,%zmm5 - vfmsub132pd %zmm0,%zmm8,%zmm3 - vmovupd %zmm14,offset(%rax) - vmovupd %zmm13,offset(%rax) - vmovupd %zmm12,offset(%rax) - add $something,%rax - vmovupd %zmm7,(%rdx) - vmovupd %zmm6,offset(%rdx) - vmovupd %zmm5,offset(%rdx) - vmovupd %zmm3,offset(%rdx) - add $something,%rdx - cmp %rax,%r8 + mov %r9,%r8 + and $something,%rdi + and $something,%r8 + cmp $something,%r9 + jg + test %r8,%r8 + je + lea -offset(,%r8,8),%r10 + and $something,%r10 + mov %rax,%rdx + mov %rcx,%rsi + lea offset(%rax,%r10,1),%r10 + nop + vmovupd (%rsi),%ymm7 + vmovupd offset(%rsi),%ymm6 + vmovupd offset(%rsi),%ymm5 + vmovupd offset(%rsi),%ymm0 + vmulpd %ymm2,%ymm7,%ymm15 + vmulpd %ymm2,%ymm6,%ymm14 + vmulpd %ymm2,%ymm5,%ymm13 + vmulpd %ymm2,%ymm0,%ymm12 + vmovupd (%rdx),%ymm11 + vmovupd offset(%rdx),%ymm10 + vmovupd offset(%rdx),%ymm9 + vmovupd offset(%rdx),%ymm8 + vfmadd231pd %ymm11,%ymm3,%ymm15 + vfmadd231pd %ymm10,%ymm3,%ymm14 + vfmadd231pd %ymm9,%ymm3,%ymm13 + vfmadd231pd %ymm8,%ymm3,%ymm12 + vmulpd %ymm2,%ymm11,%ymm11 + vmulpd %ymm2,%ymm10,%ymm10 + vmulpd %ymm2,%ymm9,%ymm9 + vmulpd %ymm2,%ymm8,%ymm8 + vmovupd %ymm15,(%rdx) + vfmsub132pd %ymm3,%ymm11,%ymm7 + vfmsub132pd %ymm3,%ymm10,%ymm6 + vfmsub132pd %ymm3,%ymm9,%ymm5 + vfmsub132pd %ymm3,%ymm8,%ymm0 + vmovupd %ymm14,offset(%rdx) + vmovupd %ymm13,offset(%rdx) + vmovupd %ymm12,offset(%rdx) + sub $something,%rdx + vmovupd %ymm7,(%rsi) + vmovupd %ymm6,offset(%rsi) + vmovupd %ymm5,offset(%rsi) + vmovupd %ymm0,offset(%rsi) + sub $something,%rsi + cmp %rdx,%r10 jne - lea offset(%rcx),%rax - shl $something,%rax - movslq %r10d,%rcx - cmp %rax,%rcx + cmp %r8,%rdi jle - mov %rax,%rdx - nopl (%rax) - vmovupd (%rsi,%rdx,8),%zmm3 - vmovupd (%r9,%rdx,8),%zmm5 - vmulpd %zmm3,%zmm2,%zmm6 - vfmadd231pd %zmm5,%zmm0,%zmm6 - vmulpd %zmm5,%zmm2,%zmm5 - vmovupd %zmm6,(%r9,%rdx,8) - vfmsub132pd %zmm0,%zmm5,%zmm3 - vmovupd %zmm3,(%rsi,%rdx,8) - add $something,%rdx - cmp %rcx,%rdx - jl - dec %rcx - sub %rax,%rcx - and $something,%rcx - lea offset(%rax,%rcx,1),%rax - cmp %rax,%rdi + nopw offset(%rax,%rax,1) + vmovupd (%rcx,%r8,8),%ymm0 + vmovupd (%rax,%r8,8),%ymm5 + vmulpd %ymm0,%ymm2,%ymm6 + vfmadd231pd %ymm5,%ymm3,%ymm6 + vmulpd %ymm5,%ymm2,%ymm5 + vmovupd %ymm6,(%rax,%r8,8) + vfmsub132pd %ymm3,%ymm5,%ymm0 + vmovupd %ymm0,(%rcx,%r8,8) + add $something,%r8 + cmp %r8,%rdi + jg + cmp %rdi,%r9 jle - nopl offset(%rax) - vmovsd (%rsi,%rax,8),%xmm0 - vmovsd (%r9,%rax,8),%xmm2 + nopl offset(%rax,%rax,1) + vmovsd (%rcx,%rdi,8),%xmm0 + vmovsd (%rax,%rdi,8),%xmm2 vmulsd %xmm0,%xmm1,%xmm3 vfmadd231sd %xmm2,%xmm4,%xmm3 vmulsd %xmm2,%xmm1,%xmm2 vfmsub132sd %xmm4,%xmm2,%xmm0 - vmovsd %xmm0,(%rsi,%rax,8) - vmovsd %xmm3,(%r9,%rax,8) - inc %rax - cmp %rax,%rdi + vmovsd %xmm0,(%rcx,%rdi,8) + vmovsd %xmm3,(%rax,%rdi,8) + inc %rdi + cmp %rdi,%r9 jne vzeroupper ret - nopl offset(%rax) - mov %rsi,%rax + nopw offset(%rax,%rax,1) shl $something,%rdx - mov %r9,%rcx shl $something,%r8 xor %esi,%esi - vmovsd (%rax),%xmm0 - vmovsd (%rcx),%xmm2 + nopw offset(%rax,%rax,1) + vmovsd (%rcx),%xmm0 + vmovsd (%rax),%xmm2 vmulsd %xmm0,%xmm1,%xmm3 inc %rsi vfmadd231sd %xmm2,%xmm4,%xmm3 vmulsd %xmm2,%xmm1,%xmm2 vfmsub132sd %xmm4,%xmm2,%xmm0 - vmovsd %xmm0,(%rax) - vmovsd %xmm3,(%rcx) - add %r8,%rax - add %rdx,%rcx - cmp %rsi,%rdi + vmovsd %xmm0,(%rcx) + vmovsd %xmm3,(%rax) /usr/lib64/libopenblas_openmp.a/drot_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/drot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/drot_k_COOPERLAKE.o (objdump) @@ -2,66 +2,59 @@ /usr/lib64/libopenblas_openmp.a/drot_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 4989f1c5 fb10e048 89ce4885 ff0f8ed8 I......H..H..... - 0010 01000048 83fa010f 85d30100 004983f8 ...H.........I.. - 0020 010f85c9 01000041 89fa89f9 4183e2f8 .......A....A... - 0030 62f2fd48 19c062f2 fd4819d1 83e1e00f b..H..b..H...... - 0040 8eec0100 004863c9 48ffc948 c1e90549 .....Hc.H..H...I - 0050 89c849c1 e0084c89 c84889f2 4f8d8401 ..I...L..H..O... - 0060 00010000 0f1f4000 62f1fd48 103a62f1 ......@.b..H.:b. - 0070 fd481072 0162f1fd 48106a02 62f1fd48 .H.r.b..H.j.b..H - 0080 105a0362 71ed4859 ff6271ed 4859f662 .Z.bq.HY.bq.HY.b - 0090 71ed4859 ed6271ed 4859e362 71fd4810 q.HY.bq.HY.bq.H. - 00a0 186271fd 48105001 6271fd48 10480262 .bq.H.P.bq.H.H.b - 00b0 71fd4810 40036252 fd48b8fb 6252fd48 q.H.@.bR.H..bR.H - 00c0 b8f26252 fd48b8e9 6252fd48 b8e06251 ..bR.H..bR.H..bQ - 00d0 ed4859db 6251ed48 59d26251 ed4859c9 .HY.bQ.HY.bQ.HY. - 00e0 6251ed48 59c06271 fd481138 62f2a548 bQ.HY.bq.H.8b..H - 00f0 9af862f2 ad489af0 62f2b548 9ae862f2 ..b..H..b..H..b. - 0100 bd489ad8 6271fd48 11700162 71fd4811 .H..bq.H.p.bq.H. - 0110 68026271 fd481160 03480500 01000062 h.bq.H.`.H.....b - 0120 f1fd4811 3a62f1fd 48117201 62f1fd48 ..H.:b..H.r.b..H - 0130 116a0262 f1fd4811 5a034881 c2000100 .j.b..H.Z.H..... - 0140 004939c0 0f851eff ffff488d 410148c1 .I9.......H.A.H. - 0150 e0054963 ca4839c1 7e524889 c20f1f00 ..Ic.H9.~RH..... - 0160 62f1fd48 101cd662 d1fd4810 2cd162f1 b..H...b..H.,.b. - 0170 ed4859f3 62f2fd48 b8f562f1 ed4859ed .HY.b..H..b..HY. - 0180 62d1fd48 1134d162 f2d5489a d862f1fd b..H.4.b..H..b.. - 0190 48111cd6 4883c208 4839ca7c c348ffc9 H...H...H9.|.H.. - 01a0 4829c148 83e1f848 8d440808 4839c77e H).H...H.D..H9.~ - 01b0 370f1f80 00000000 c5fb1004 c6c4c17b 7..............{ - 01c0 1014c1c5 f359d8c4 e2d9b9da c5f359d2 .....Y........Y. - 01d0 c4e2e99b c4c5fb11 04c6c4c1 7b111cc1 ............{... - 01e0 48ffc048 39c775d0 c5f877c3 0f1f4000 H..H9.u...w...@. - 01f0 4889f048 c1e2034c 89c949c1 e00331f6 H..H...L..I...1. - 0200 c5fb1000 c5fb1011 c5f359d8 48ffc6c4 ..........Y.H... - 0210 e2d9b9da c5f359d2 c4e2e99b c4c5fb11 ......Y......... - 0220 00c5fb11 194c01c0 4801d148 39f775d0 .....L..H..H9.u. - 0230 c34963ca 31c04585 d20f8f1b ffffffe9 .Ic.1.E......... - 0240 74ffffff 66662e0f 1f840000 00000090 t...ff.......... - 0250 4883ec08 488b4720 4c8b4f30 488b4f08 H...H.G L.O0H.O. - 0260 488b5748 c5fb1048 08c5fb10 004c8b47 H.WH...H.....L.G - 0270 50488b37 4c89cfe8 84fdffff 31c04883 PH.7L.......1.H. - 0280 c408c366 662e0f1f 84000000 00006690 ...ff.........f. - 0290 41574156 4989ce41 554989f5 41544989 AWAVI..AUI..ATI. - 02a0 d4554889 fd534883 ec586448 8b042528 .UH..SH..XdH..%( - 02b0 00000048 89442448 31c04d85 c00f94c0 ...H.D$H1.M..... - 02c0 4881ffa0 8601000f 9ec208d0 c5fb1144 H..............D - 02d0 2430c5fb 114c2438 75054d85 e475394c $0...L$8u.M..u9L - 02e0 89f14c89 e24c89ee 4889efe8 10fdffff ..L..L..H....... - 02f0 488b4424 4864482b 04252800 00000f85 H.D$HdH+.%(..... - 0300 e6000000 4883c458 5b5d415c 415d415e ....H..X[]A\A]A^ - 0310 31c0415f c30f1f00 4c894424 08c5fb11 1.A_....L.D$.... - 0320 4c2418c5 fb114424 10e80000 000083f8 L$....D$........ - 0330 014c8b44 2408c5fb 10442410 c5fb104c .L.D$....D$....L - 0340 24184189 c77498e8 00000000 85c04c8b $.A..t........L. - 0350 442408c5 fb104424 10c5fb10 4c24180f D$....D$....L$.. - 0360 857affff ff488b1d 00000000 c5fb114c .z...H.........L - 0370 24108b03 c5fb1144 24084139 c7754148 $......D$.A9.uAH - 0380 83ec0850 488d05c5 feffff4d 89e95031 ...PH......M..P1 - 0390 c931d26a 004889ee bf034000 00488d44 .1.j.H....@..H.D - 03a0 24485041 50415641 544c8d44 2470e800 $HPAPAVATL.D$p.. - 03b0 00000048 83c440e9 34ffffff 0f1f4000 ...H..@.4.....@. - 03c0 4489ff4c 89442418 e8000000 008b034c D..L.D$........L - 03d0 8b442418 83f801c5 fb104424 08c5fb10 .D$.......D$.... - 03e0 4c241075 9ae9f5fe ffffe800 000000 L$.u........... + 0000 4989f948 89f0c5fb 10e04885 ff0f8e6e I..H......H....n + 0010 01000048 83fa010f 856b0100 004983f8 ...H.....k...I.. + 0020 010f8561 0100004d 89c84883 e7fc4983 ...a...M..H...I. + 0030 e0f04983 f9030f8f 94010000 4d85c00f ..I.........M... + 0040 84f90000 004e8d14 c5f8ffff ff4983e2 .....N.......I.. + 0050 804889c2 4889ce4e 8d941080 00000090 .H..H..N........ + 0060 c5fd103e c5fd1076 20c5fd10 6e40c5fd ...>...v ...n@.. + 0070 104660c5 4559fac5 4d59f2c5 5559eac5 .F`.EY..MY..UY.. + 0080 7d59e2c5 7d101ac5 7d105220 c57d104a }Y..}...}.R .}.J + 0090 40c57d10 4260c442 e5b8fbc4 42e5b8f2 @.}.B`.B....B... + 00a0 c442e5b8 e9c442e5 b8e0c525 59dac52d .B....B....%Y..- + 00b0 59d2c535 59cac53d 59c2c57d 113ac4e2 Y..5Y..=Y..}.:.. + 00c0 a59afbc4 e2ad9af3 c4e2b59a ebc4e2bd ................ + 00d0 9ac3c57d 117220c5 7d116a40 c57d1162 ...}.r .}.j@.}.b + 00e0 604883ea 80c5fd11 3ec5fd11 7620c5fd `H......>...v .. + 00f0 116e40c5 fd114660 4883ee80 4939d20f .n@...F`H...I9.. + 0100 855bffff ff4c39c7 7e39660f 1f440000 .[...L9.~9f..D.. + 0110 c4a17d10 04c1c4a1 7d102cc0 c5ed59f0 ..}.....}.,...Y. + 0120 c4e2e5b8 f5c5ed59 edc4a17d 1134c0c4 .......Y...}.4.. + 0130 e2d59ac3 c4a17d11 04c14983 c0044c39 ......}...I...L9 + 0140 c77fcd49 39f97e36 0f1f8400 00000000 ...I9.~6........ + 0150 c5fb1004 f9c5fb10 14f8c5f3 59d8c4e2 ............Y... + 0160 d9b9dac5 f359d2c4 e2e99bc4 c5fb1104 .....Y.......... + 0170 f9c5fb11 1cf848ff c74939f9 75d2c5f8 ......H..I9.u... + 0180 77c3660f 1f440000 48c1e203 49c1e003 w.f..D..H...I... + 0190 31f6660f 1f440000 c5fb1001 c5fb1010 1.f..D.......... + 01a0 c5f359d8 48ffc6c4 e2d9b9da c5f359d2 ..Y.H.........Y. + 01b0 c4e2e99b c4c5fb11 01c5fb11 184c01c1 .............L.. + 01c0 4801d049 39f175d0 c30f1f80 00000000 H..I9.u......... + 01d0 c4e27d19 d8c4e27d 19d1e95d feffff90 ..}....}...].... + 01e0 4883ec08 488b4720 4c8b4f30 488b4f08 H...H.G L.O0H.O. + 01f0 488b5748 c5fb1048 08c5fb10 004c8b47 H.WH...H.....L.G + 0200 50488b37 4c89cfe8 f4fdffff 31c04883 PH.7L.......1.H. + 0210 c408c366 662e0f1f 84000000 00006690 ...ff.........f. + 0220 41574156 4989ce41 554989f5 41544989 AWAVI..AUI..ATI. + 0230 d4554889 fd534883 ec586448 8b042528 .UH..SH..XdH..%( + 0240 00000048 89442448 31c04d85 c00f94c0 ...H.D$H1.M..... + 0250 4881ffa0 8601000f 9ec208d0 c5fb1144 H..............D + 0260 2430c5fb 114c2438 75054d85 e475394c $0...L$8u.M..u9L + 0270 89f14c89 e24c89ee 4889efe8 80fdffff ..L..L..H....... + 0280 488b4424 4864482b 04252800 00000f85 H.D$HdH+.%(..... + 0290 e6000000 4883c458 5b5d415c 415d415e ....H..X[]A\A]A^ + 02a0 31c0415f c30f1f00 4c894424 08c5fb11 1.A_....L.D$.... + 02b0 4c2418c5 fb114424 10e80000 000083f8 L$....D$........ + 02c0 014c8b44 2408c5fb 10442410 c5fb104c .L.D$....D$....L + 02d0 24184189 c77498e8 00000000 85c04c8b $.A..t........L. + 02e0 442408c5 fb104424 10c5fb10 4c24180f D$....D$....L$.. + 02f0 857affff ff488b1d 00000000 c5fb114c .z...H.........L + 0300 24108b03 c5fb1144 24084139 c7754148 $......D$.A9.uAH + 0310 83ec0850 488d05c5 feffff4d 89e95031 ...PH......M..P1 + 0320 c931d26a 004889ee bf034000 00488d44 .1.j.H....@..H.D + 0330 24485041 50415641 544c8d44 2470e800 $HPAPAVATL.D$p.. + 0340 00000048 83c440e9 34ffffff 0f1f4000 ...H..@.4.....@. + 0350 4489ff4c 89442418 e8000000 008b034c D..L.D$........L + 0360 8b442418 83f801c5 fb104424 08c5fb10 .D$.......D$.... + 0370 4c241075 9ae9f5fe ffffe800 000000 L$.u........... /usr/lib64/libopenblas_openmp.a/drot_k_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/drot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/drot_k_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39000000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/drot_k_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/drot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/drot_k_COOPERLAKE.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 10000000 1c000000 ................ - 0020 00000000 44020000 00000000 14000000 ....D........... + 0020 00000000 df010000 00000000 14000000 ................ 0030 30000000 00000000 33000000 00440e10 0.......3....D.. 0040 6e0e0800 70000000 48000000 00000000 n...p...H....... 0050 5f010000 00420e10 8f02420e 188e0345 _....B....B....E /usr/lib64/libopenblas_openmp.a/drot_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/drot_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/drot_k_SKYLAKEX.o (disasm) @@ -5,118 +5,118 @@ Disassembly of section .text: rot_compute: + mov %rdi,%r9 mov %rsi,%rax + vmovsd %xmm0,%xmm0,%xmm4 test %rdi,%rdi jle cmp $something,%rdx jne cmp $something,%r8 jne - mov %rdi,%r9 - mov %rdi,%r8 - vbroadcastsd %xmm0,%zmm0 - vbroadcastsd %xmm1,%zmm1 - and $something,%r9 + mov %r9,%r8 + and $something,%rdi and $something,%r8 + cmp $something,%r9 + jg + test %r8,%r8 je - mov %rsi,%rdx - lea (%rax,%r8,8),%r10 + lea -offset(,%r8,8),%r10 + and $something,%r10 + mov %rax,%rdx mov %rcx,%rsi - nopw offset(%rax,%rax,1) - vmovupd (%rsi),%zmm5 - vmovupd offset(%rsi),%zmm4 - vmovupd offset(%rsi),%zmm3 - vmovupd offset(%rsi),%zmm2 - vmulpd %zmm5,%zmm1,%zmm13 - vmulpd %zmm4,%zmm1,%zmm12 - vmulpd %zmm3,%zmm1,%zmm11 - vmulpd %zmm2,%zmm1,%zmm10 - vmovupd (%rdx),%zmm9 - vmovupd offset(%rdx),%zmm8 - vmovupd offset(%rdx),%zmm7 - vmovupd offset(%rdx),%zmm6 - vfmadd231pd %zmm9,%zmm0,%zmm13 - vfmadd231pd %zmm8,%zmm0,%zmm12 - vfmadd231pd %zmm7,%zmm0,%zmm11 - vfmadd231pd %zmm6,%zmm0,%zmm10 - vmulpd %zmm9,%zmm1,%zmm9 - vmulpd %zmm8,%zmm1,%zmm8 - vmulpd %zmm7,%zmm1,%zmm7 - vmulpd %zmm6,%zmm1,%zmm6 - vmovupd %zmm13,(%rdx) - vfmsub132pd %zmm0,%zmm9,%zmm5 - vfmsub132pd %zmm0,%zmm8,%zmm4 - vfmsub132pd %zmm0,%zmm7,%zmm3 - vfmsub132pd %zmm0,%zmm6,%zmm2 - vmovupd %zmm12,offset(%rdx) - vmovupd %zmm11,offset(%rdx) - vmovupd %zmm10,offset(%rdx) - add $something,%rdx - vmovupd %zmm5,(%rsi) - vmovupd %zmm4,offset(%rsi) - vmovupd %zmm3,offset(%rsi) - vmovupd %zmm2,offset(%rsi) - add $something,%rsi + lea offset(%rax,%r10,1),%r10 + nop + vmovupd (%rsi),%ymm7 + vmovupd offset(%rsi),%ymm6 + vmovupd offset(%rsi),%ymm5 + vmovupd offset(%rsi),%ymm0 + vmulpd %ymm2,%ymm7,%ymm15 + vmulpd %ymm2,%ymm6,%ymm14 + vmulpd %ymm2,%ymm5,%ymm13 + vmulpd %ymm2,%ymm0,%ymm12 + vmovupd (%rdx),%ymm11 + vmovupd offset(%rdx),%ymm10 + vmovupd offset(%rdx),%ymm9 + vmovupd offset(%rdx),%ymm8 + vfmadd231pd %ymm11,%ymm3,%ymm15 + vfmadd231pd %ymm10,%ymm3,%ymm14 + vfmadd231pd %ymm9,%ymm3,%ymm13 + vfmadd231pd %ymm8,%ymm3,%ymm12 + vmulpd %ymm2,%ymm11,%ymm11 + vmulpd %ymm2,%ymm10,%ymm10 + vmulpd %ymm2,%ymm9,%ymm9 + vmulpd %ymm2,%ymm8,%ymm8 + vmovupd %ymm15,(%rdx) + vfmsub132pd %ymm3,%ymm11,%ymm7 + vfmsub132pd %ymm3,%ymm10,%ymm6 + vfmsub132pd %ymm3,%ymm9,%ymm5 + vfmsub132pd %ymm3,%ymm8,%ymm0 + vmovupd %ymm14,offset(%rdx) + vmovupd %ymm13,offset(%rdx) + vmovupd %ymm12,offset(%rdx) + sub $something,%rdx + vmovupd %ymm7,(%rsi) + vmovupd %ymm6,offset(%rsi) + vmovupd %ymm5,offset(%rsi) + vmovupd %ymm0,offset(%rsi) + sub $something,%rsi cmp %rdx,%r10 jne - cmp %r8,%r9 + cmp %r8,%rdi jle - nopl offset(%rax,%rax,1) - vmovupd (%rcx,%r8,8),%zmm2 - vmovupd (%rax,%r8,8),%zmm3 - vmulpd %zmm2,%zmm1,%zmm4 - vfmadd231pd %zmm3,%zmm0,%zmm4 - vmulpd %zmm3,%zmm1,%zmm3 - vmovupd %zmm4,(%rax,%r8,8) - vfmsub132pd %zmm0,%zmm3,%zmm2 - vmovupd %zmm2,(%rcx,%r8,8) + nopw offset(%rax,%rax,1) + vmovupd (%rcx,%r8,8),%ymm0 + vmovupd (%rax,%r8,8),%ymm5 + vmulpd %ymm0,%ymm2,%ymm6 + vfmadd231pd %ymm5,%ymm3,%ymm6 + vmulpd %ymm5,%ymm2,%ymm5 + vmovupd %ymm6,(%rax,%r8,8) + vfmsub132pd %ymm3,%ymm5,%ymm0 + vmovupd %ymm0,(%rcx,%r8,8) add $something,%r8 - cmp %r8,%r9 + cmp %r8,%rdi jg - and $something,%edi - je - shl $something,%r9 - mov $something,%esi - add %r9,%rax - sub %edi,%esi - add %rcx,%r9 - mov $something,%edx - sarx %esi,%edx,%edi - kmovd %edi,%k1 - vmovupd (%r9),%zmm3{%k1}{z} - vmovupd (%rax),%zmm4{%k1}{z} - vmulpd %zmm3,%zmm1,%zmm2 - vmulpd %zmm4,%zmm1,%zmm1 - vfmadd231pd %zmm4,%zmm0,%zmm2 - vfmsub132pd %zmm3,%zmm1,%zmm0 - vmovupd %zmm2,(%rax){%k1} - vmovupd %zmm0,(%r9){%k1} - vzeroupper - ret - nopl (%rax) + cmp %rdi,%r9 + jle + nopl offset(%rax,%rax,1) + vmovsd (%rcx,%rdi,8),%xmm0 + vmovsd (%rax,%rdi,8),%xmm2 + vmulsd %xmm0,%xmm1,%xmm3 + vfmadd231sd %xmm2,%xmm4,%xmm3 + vmulsd %xmm2,%xmm1,%xmm2 + vfmsub132sd %xmm4,%xmm2,%xmm0 + vmovsd %xmm0,(%rcx,%rdi,8) + vmovsd %xmm3,(%rax,%rdi,8) + inc %rdi + cmp %rdi,%r9 + jne vzeroupper ret - nopl offset(%rax) + nopw offset(%rax,%rax,1) shl $something,%rdx shl $something,%r8 xor %esi,%esi nopw offset(%rax,%rax,1) - vmovsd (%rcx),%xmm2 - vmovsd (%rax),%xmm3 - vmulsd %xmm2,%xmm1,%xmm4 + vmovsd (%rcx),%xmm0 + vmovsd (%rax),%xmm2 + vmulsd %xmm0,%xmm1,%xmm3 inc %rsi - vfmadd231sd %xmm3,%xmm0,%xmm4 - vmulsd %xmm3,%xmm1,%xmm3 - vfmsub132sd %xmm0,%xmm3,%xmm2 - vmovsd %xmm2,(%rcx) - vmovsd %xmm4,(%rax) + vfmadd231sd %xmm2,%xmm4,%xmm3 + vmulsd %xmm2,%xmm1,%xmm2 + vfmsub132sd %xmm4,%xmm2,%xmm0 + vmovsd %xmm0,(%rcx) + vmovsd %xmm3,(%rax) add %r8,%rcx add %rdx,%rax - cmp %rsi,%rdi + cmp %rsi,%r9 jne ret - data16 cs nopw offset(%rax,%rax,1) nopl offset(%rax) + vbroadcastsd %xmm0,%ymm3 /usr/lib64/libopenblas_openmp.a/drot_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/drot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/drot_k_SKYLAKEX.o (objdump) @@ -2,64 +2,59 @@ /usr/lib64/libopenblas_openmp.a/drot_k_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 4889f048 85ff0f8e cf010000 4883fa01 H..H........H... - 0010 0f85ca01 00004983 f8010f85 c0010000 ......I......... - 0020 4989f949 89f862f2 fd4819c0 62f2fd48 I..I..b..H..b..H - 0030 19c94983 e1f84983 e0e00f84 38010000 ..I...I.....8... - 0040 4889f24e 8d14c048 89ce660f 1f440000 H..N...H..f..D.. - 0050 62f1fd48 102e62f1 fd481066 0162f1fd b..H..b..H.f.b.. - 0060 48105e02 62f1fd48 10560362 71f54859 H.^.b..H.V.bq.HY - 0070 ed6271f5 4859e462 71f54859 db6271f5 .bq.HY.bq.HY.bq. - 0080 4859d262 71fd4810 0a6271fd 48104201 HY.bq.H..bq.H.B. - 0090 62f1fd48 107a0262 f1fd4810 72036252 b..H.z.b..H.r.bR - 00a0 fd48b8e9 6252fd48 b8e06272 fd48b8df .H..bR.H..br.H.. - 00b0 6272fd48 b8d66251 f54859c9 6251f548 br.H..bQ.HY.bQ.H - 00c0 59c062f1 f54859ff 62f1f548 59f66271 Y.b..HY.b..HY.bq - 00d0 fd48112a 62f2b548 9ae862f2 bd489ae0 .H.*b..H..b..H.. - 00e0 62f2c548 9ad862f2 cd489ad0 6271fd48 b..H..b..H..bq.H - 00f0 11620162 71fd4811 5a026271 fd481152 .b.bq.H.Z.bq.H.R - 0100 034881c2 00010000 62f1fd48 112e62f1 .H......b..H..b. - 0110 fd481166 0162f1fd 48115e02 62f1fd48 .H.f.b..H.^.b..H - 0120 11560348 81c60001 00004939 d20f851d .V.H......I9.... - 0130 ffffff4d 39c17e45 0f1f8400 00000000 ...M9.~E........ - 0140 62b1fd48 1014c162 b1fd4810 1cc062f1 b..H...b..H...b. - 0150 f54859e2 62f2fd48 b8e362f1 f54859db .HY.b..H..b..HY. - 0160 62b1fd48 1124c062 f2e5489a d062b1fd b..H.$.b..H..b.. - 0170 481114c1 4983c008 4d39c17f c383e707 H...I...M9...... - 0180 745649c1 e103be08 0000004c 01c829fe tVI........L..). - 0190 4901c9ba ff000000 c4e24af7 fac5fb92 I.........J..... - 01a0 cf62d1fd c9101962 f1fdc910 2062f1f5 .b.....b.... b.. - 01b0 4859d362 f1f54859 cc62f2fd 48b8d462 HY.b..HY.b..H..b - 01c0 f2f5489a c362f1fd 49111062 d1fd4911 ..H..b..I..b..I. - 01d0 01c5f877 c30f1f00 c5f877c3 0f1f4000 ...w......w...@. - 01e0 48c1e203 49c1e003 31f6660f 1f440000 H...I...1.f..D.. - 01f0 c5fb1011 c5fb1018 c5f359e2 48ffc6c4 ..........Y.H... - 0200 e2f9b9e3 c5f359db c4e2e19b d0c5fb11 ......Y......... - 0210 11c5fb11 204c01c1 4801d048 39f775d0 .... L..H..H9.u. - 0220 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. - 0230 4883ec08 488b4720 4c8b4f30 488b4f08 H...H.G L.O0H.O. - 0240 488b5748 c5fb1048 08c5fb10 004c8b47 H.WH...H.....L.G - 0250 50488b37 4c89cfe8 a4fdffff 31c04883 PH.7L.......1.H. - 0260 c408c366 662e0f1f 84000000 00006690 ...ff.........f. - 0270 41574156 4989ce41 554989f5 41544989 AWAVI..AUI..ATI. - 0280 d4554889 fd534883 ec586448 8b042528 .UH..SH..XdH..%( - 0290 00000048 89442448 31c04d85 c00f94c0 ...H.D$H1.M..... - 02a0 4881ffa0 8601000f 9ec208d0 c5fb1144 H..............D - 02b0 2430c5fb 114c2438 75054d85 e475394c $0...L$8u.M..u9L - 02c0 89f14c89 e24c89ee 4889efe8 30fdffff ..L..L..H...0... - 02d0 488b4424 4864482b 04252800 00000f85 H.D$HdH+.%(..... - 02e0 e6000000 4883c458 5b5d415c 415d415e ....H..X[]A\A]A^ - 02f0 31c0415f c30f1f00 4c894424 08c5fb11 1.A_....L.D$.... - 0300 4c2418c5 fb114424 10e80000 000083f8 L$....D$........ - 0310 014c8b44 2408c5fb 10442410 c5fb104c .L.D$....D$....L - 0320 24184189 c77498e8 00000000 85c04c8b $.A..t........L. - 0330 442408c5 fb104424 10c5fb10 4c24180f D$....D$....L$.. - 0340 857affff ff488b1d 00000000 c5fb114c .z...H.........L - 0350 24108b03 c5fb1144 24084139 c7754148 $......D$.A9.uAH - 0360 83ec0850 488d05c5 feffff4d 89e95031 ...PH......M..P1 - 0370 c931d26a 004889ee bf034000 00488d44 .1.j.H....@..H.D - 0380 24485041 50415641 544c8d44 2470e800 $HPAPAVATL.D$p.. - 0390 00000048 83c440e9 34ffffff 0f1f4000 ...H..@.4.....@. - 03a0 4489ff4c 89442418 e8000000 008b034c D..L.D$........L - 03b0 8b442418 83f801c5 fb104424 08c5fb10 .D$.......D$.... - 03c0 4c241075 9ae9f5fe ffffe800 000000 L$.u........... + 0000 4989f948 89f0c5fb 10e04885 ff0f8e6e I..H......H....n + 0010 01000048 83fa010f 856b0100 004983f8 ...H.....k...I.. + 0020 010f8561 0100004d 89c84883 e7fc4983 ...a...M..H...I. + 0030 e0f04983 f9030f8f 94010000 4d85c00f ..I.........M... + 0040 84f90000 004e8d14 c5f8ffff ff4983e2 .....N.......I.. + 0050 804889c2 4889ce4e 8d941080 00000090 .H..H..N........ + 0060 c5fd103e c5fd1076 20c5fd10 6e40c5fd ...>...v ...n@.. + 0070 104660c5 4559fac5 4d59f2c5 5559eac5 .F`.EY..MY..UY.. + 0080 7d59e2c5 7d101ac5 7d105220 c57d104a }Y..}...}.R .}.J + 0090 40c57d10 4260c442 e5b8fbc4 42e5b8f2 @.}.B`.B....B... + 00a0 c442e5b8 e9c442e5 b8e0c525 59dac52d .B....B....%Y..- + 00b0 59d2c535 59cac53d 59c2c57d 113ac4e2 Y..5Y..=Y..}.:.. + 00c0 a59afbc4 e2ad9af3 c4e2b59a ebc4e2bd ................ + 00d0 9ac3c57d 117220c5 7d116a40 c57d1162 ...}.r .}.j@.}.b + 00e0 604883ea 80c5fd11 3ec5fd11 7620c5fd `H......>...v .. + 00f0 116e40c5 fd114660 4883ee80 4939d20f .n@...F`H...I9.. + 0100 855bffff ff4c39c7 7e39660f 1f440000 .[...L9.~9f..D.. + 0110 c4a17d10 04c1c4a1 7d102cc0 c5ed59f0 ..}.....}.,...Y. + 0120 c4e2e5b8 f5c5ed59 edc4a17d 1134c0c4 .......Y...}.4.. + 0130 e2d59ac3 c4a17d11 04c14983 c0044c39 ......}...I...L9 + 0140 c77fcd49 39f97e36 0f1f8400 00000000 ...I9.~6........ + 0150 c5fb1004 f9c5fb10 14f8c5f3 59d8c4e2 ............Y... + 0160 d9b9dac5 f359d2c4 e2e99bc4 c5fb1104 .....Y.......... + 0170 f9c5fb11 1cf848ff c74939f9 75d2c5f8 ......H..I9.u... + 0180 77c3660f 1f440000 48c1e203 49c1e003 w.f..D..H...I... + 0190 31f6660f 1f440000 c5fb1001 c5fb1010 1.f..D.......... + 01a0 c5f359d8 48ffc6c4 e2d9b9da c5f359d2 ..Y.H.........Y. + 01b0 c4e2e99b c4c5fb11 01c5fb11 184c01c1 .............L.. + 01c0 4801d049 39f175d0 c30f1f80 00000000 H..I9.u......... + 01d0 c4e27d19 d8c4e27d 19d1e95d feffff90 ..}....}...].... + 01e0 4883ec08 488b4720 4c8b4f30 488b4f08 H...H.G L.O0H.O. + 01f0 488b5748 c5fb1048 08c5fb10 004c8b47 H.WH...H.....L.G + 0200 50488b37 4c89cfe8 f4fdffff 31c04883 PH.7L.......1.H. + 0210 c408c366 662e0f1f 84000000 00006690 ...ff.........f. + 0220 41574156 4989ce41 554989f5 41544989 AWAVI..AUI..ATI. + 0230 d4554889 fd534883 ec586448 8b042528 .UH..SH..XdH..%( + 0240 00000048 89442448 31c04d85 c00f94c0 ...H.D$H1.M..... + 0250 4881ffa0 8601000f 9ec208d0 c5fb1144 H..............D + 0260 2430c5fb 114c2438 75054d85 e475394c $0...L$8u.M..u9L + 0270 89f14c89 e24c89ee 4889efe8 80fdffff ..L..L..H....... + 0280 488b4424 4864482b 04252800 00000f85 H.D$HdH+.%(..... + 0290 e6000000 4883c458 5b5d415c 415d415e ....H..X[]A\A]A^ + 02a0 31c0415f c30f1f00 4c894424 08c5fb11 1.A_....L.D$.... + 02b0 4c2418c5 fb114424 10e80000 000083f8 L$....D$........ + 02c0 014c8b44 2408c5fb 10442410 c5fb104c .L.D$....D$....L + 02d0 24184189 c77498e8 00000000 85c04c8b $.A..t........L. + 02e0 442408c5 fb104424 10c5fb10 4c24180f D$....D$....L$.. + 02f0 857affff ff488b1d 00000000 c5fb114c .z...H.........L + 0300 24108b03 c5fb1144 24084139 c7754148 $......D$.A9.uAH + 0310 83ec0850 488d05c5 feffff4d 89e95031 ...PH......M..P1 + 0320 c931d26a 004889ee bf034000 00488d44 .1.j.H....@..H.D + 0330 24485041 50415641 544c8d44 2470e800 $HPAPAVATL.D$p.. + 0340 00000048 83c440e9 34ffffff 0f1f4000 ...H..@.4.....@. + 0350 4489ff4c 89442418 e8000000 008b034c D..L.D$........L + 0360 8b442418 83f801c5 fb104424 08c5fb10 .D$.......D$.... + 0370 4c241075 9ae9f5fe ffffe800 000000 L$.u........... /usr/lib64/libopenblas_openmp.a/drot_k_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/drot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/drot_k_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/drot_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/drot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/drot_k_SKYLAKEX.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 10000000 1c000000 ................ - 0020 00000000 21020000 00000000 14000000 ....!........... + 0020 00000000 df010000 00000000 14000000 ................ 0030 30000000 00000000 33000000 00440e10 0.......3....D.. 0040 6e0e0800 70000000 48000000 00000000 n...p...H....... 0050 5f010000 00420e10 8f02420e 188e0345 _....B....B....E /usr/lib64/libopenblas_openmp.a/dscal_k_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dscal_k_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dscal_k_COOPERLAKE.o (disasm) @@ -4,6 +4,98 @@ Disassembly of section .text: +dscal_kernel_8: + mov %rdi,%rax + sar $something,%rax + and $something,%edi + vmovddup (%rsi),%xmm0 + add $something,%rdx + cmp $something,%rax + je + vmulpd -offset(%rdx),%xmm0,%xmm4 + vmulpd -offset(%rdx),%xmm0,%xmm5 + vmulpd -offset(%rdx),%xmm0,%xmm6 + vmulpd -offset(%rdx),%xmm0,%xmm7 + vmulpd -offset(%rdx),%xmm0,%xmm8 + vmulpd -offset(%rdx),%xmm0,%xmm9 + vmulpd -offset(%rdx),%xmm0,%xmm10 + vmulpd -offset(%rdx),%xmm0,%xmm11 + sub $something,%rax + je + nopl (%rax) + vmovups %xmm4,-offset(%rdx) + vmovups %xmm5,-offset(%rdx) + vmulpd (%rdx),%xmm0,%xmm4 + vmovups %xmm6,-offset(%rdx) + vmulpd offset(%rdx),%xmm0,%xmm5 + vmovups %xmm7,-offset(%rdx) + vmulpd offset(%rdx),%xmm0,%xmm6 + vmovups %xmm8,-offset(%rdx) + vmulpd offset(%rdx),%xmm0,%xmm7 + vmovups %xmm9,-offset(%rdx) + vmulpd offset(%rdx),%xmm0,%xmm8 + vmovups %xmm10,-offset(%rdx) + vmulpd offset(%rdx),%xmm0,%xmm9 + vmovups %xmm11,-offset(%rdx) + vmulpd offset(%rdx),%xmm0,%xmm10 + vmulpd offset(%rdx),%xmm0,%xmm11 + add $something,%rdx + sub $something,%rax + jne + vmovups %xmm4,-offset(%rdx) + vmovups %xmm5,-offset(%rdx) + vmovups %xmm6,-offset(%rdx) + vmovups %xmm7,-offset(%rdx) + vmovups %xmm8,-offset(%rdx) + vmovups %xmm9,-offset(%rdx) + vmovups %xmm10,-offset(%rdx) + vmovups %xmm11,-offset(%rdx) + add $something,%rdx + cmp $something,%rdi + jne + vmulpd -offset(%rdx),%xmm0,%xmm4 + vmulpd -offset(%rdx),%xmm0,%xmm5 + vmulpd -offset(%rdx),%xmm0,%xmm6 + vmulpd -offset(%rdx),%xmm0,%xmm7 + vmovups %xmm4,-offset(%rdx) + vmovups %xmm5,-offset(%rdx) + vmovups %xmm6,-offset(%rdx) + vmovups %xmm7,-offset(%rdx) + vzeroupper + vzeroupper + ret + +dscal_kernel_8_zero: + mov %rdi,%rax + sar $something,%rax + and $something,%edi + vxorpd %xmm0,%xmm0,%xmm0 + add $something,%rdx + cmp $something,%rax + je + nopl offset(%rax,%rax,1) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + add $something,%rdx + sub $something,%rax + jne + cmp $something,%rdi + jne + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vzeroupper + vzeroupper + ret + cs nopw offset(%rax,%rax,1) + dscal_kernel_inc_8: lea offset(,%rcx,8),%r8 xor %eax,%eax @@ -40,17 +132,10 @@ cs nopw offset(%rax,%rax,1) dscal_k_COOPERLAKE: - push %rbp - vmovsd %xmm0,%xmm0,%xmm1 - mov %rsp,%rbp - push %r13 - push %r12 - mov %rcx,%r12 - push %rbx - mov %rdi,%rbx - and $something,%rsp sub $something,%rsp + mov %rdi,%r9 vmovsd %xmm0,offset(%rsp) + mov %rcx,%r10 cmp $something,%r8 je vucomisd offset(%rip),%xmm0 # @@ -64,7 +149,7 @@ lea (%r8,%r8,1),%rdi shl $something,%rsi xor %ecx,%ecx - nopl offset(%rax) + nopl offset(%rax,%rax,1) add $something,%rcx movq $something,(%rdx) movq $something,(%rdx,%r8,8) @@ -78,117 +163,97 @@ add %rax,%rax mov %rdi,%rdx shl $something,%r8 - lea (%r12,%rdx,8),%rdx - cmp %rax,%rbx + lea (%r10,%rdx,8),%rdx + cmp %rax,%r9 jle nopl offset(%rax,%rax,1) inc %rax movq $something,(%rdx) add %r8,%rdx - cmp %rax,%rbx + cmp %rax,%r9 jne - lea -offset(%rbp),%rsp - pop %rbx - pop %r12 - pop %r13 - xor %eax,%eax - pop %rbp - ret - nop - mov %rdi,%r13 - and $something,%r13 + xor %eax,%eax + add $something,%rsp + ret + nopl offset(%rax) + mov %rdi,%rcx + vxorpd %xmm16,%xmm16,%xmm16 + and $something,%rcx jle - vucomisd offset(%rip),%xmm0 # + vucomisd %xmm16,%xmm0 + lea offset(%rsp),%rsi + mov %r10,%rdx + mov %rcx,%rdi jp jne - lea offset(,%r13,8),%rdx - xor %esi,%esi - mov %rcx,%rdi - call - cmp %r13,%rbx - jle - sub %r13,%rbx - lea (%r12,%r13,8),%rdi - lea offset(,%rbx,8),%rdx - xor %esi,%esi - call - lea -offset(%rbp),%rsp - pop %rbx - pop %r12 - pop %r13 - xor %eax,%eax - pop %rbp - ret - nopw offset(%rax,%rax,1) - vucomisd offset(%rip),%xmm0 # + call + vmovsd offset(%rsp),%xmm0 + vucomisd %xmm16,%xmm0 jp je - cmp %r13,%rbx + cmp %rcx,%r9 jle - lea (%r12,%r13,8),%rax /usr/lib64/libopenblas_openmp.a/dscal_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dscal_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dscal_k_COOPERLAKE.o (objdump) @@ -2,47 +2,70 @@ /usr/lib64/libopenblas_openmp.a/dscal_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 4c8d04cd 00000000 31c0486b c918f20f L.......1.Hk.... - 0010 12064a8d 0482662e 0f1f8400 00000000 ..J...f......... - 0020 f20f1022 66420f16 2402f242 0f102c42 ..."fB..$..B..,B - 0030 660f162c 0af20f10 3066420f 163400f2 f..,....0fB..4.. - 0040 420f103c 40660f16 3c08660f 59e0660f B..<@f..<.f.Y.f. - 0050 59e8660f 59f0660f 59f8f20f 11226642 Y.f.Y.f.Y...."fB - 0060 0f172402 f2420f11 2c42660f 172c0af2 ..$..B..,Bf..,.. - 0070 0f113066 420f1734 00f2420f 113c4066 ..0fB..4..B..<@f - 0080 0f173c08 4a8d14c2 4a8d04c0 4883ef08 ..<.J...J...H... - 0090 758ec5f8 77c3662e 0f1f8400 00000000 u...w.f......... - 00a0 55c5fb10 c84889e5 41554154 4989cc53 U....H..AUATI..S - 00b0 4889fb48 83e4c048 83ec40c5 fb114424 H..H...H..@...D$ - 00c0 384983f8 010f8495 000000c5 f92e0500 8I.............. - 00d0 0000000f 8a270100 000f8521 01000048 .....'.....!...H - 00e0 89f84883 e0fe0f8e c4010000 4c89c648 ..H.........L..H - 00f0 89ca4b8d 3c0048c1 e60431c9 0f1f4000 ..K.<.H...1...@. - 0100 4883c102 48c70200 0000004a c704c200 H...H......J.... - 0110 00000048 01f24839 c87fe548 ffc848d1 ...H..H9...H..H. - 0120 e848ffc0 480faff8 4801c048 89fa49c1 .H..H...H..H..I. - 0130 e003498d 14d44839 c37e170f 1f440000 ..I...H9.~...D.. - 0140 48ffc048 c7020000 00004c01 c24839c3 H..H......L..H9. - 0150 75ee488d 65e85b41 5c415d31 c05dc390 u.H.e.[A\A]1.].. - 0160 4989fd49 83e5f87e 57c5f92e 05000000 I..I...~W....... - 0170 000f8a09 0100000f 85030100 004a8d14 .............J.. - 0180 ed000000 0031f648 89cfe800 0000004c .....1.H.......L - 0190 39eb7ebe 4c29eb4b 8d3cec48 8d14dd00 9.~.L).K.<.H.... - 01a0 00000031 f6e80000 0000488d 65e85b41 ...1......H.e.[A - 01b0 5c415d31 c05dc366 0f1f8400 00000000 \A]1.].f........ - 01c0 c5f92e05 00000000 7a0274c3 4c39eb7e ........z.t.L9.~ - 01d0 814b8d04 ec498d14 dc0f1f80 00000000 .K...I.......... - 01e0 c5f35900 4883c008 c5fb1140 f84839d0 ..Y.H......@.H9. - 01f0 75ee488d 65e85b41 5c415d31 c05dc390 u.H.e.[A\A]1.].. - 0200 4989d949 83e1f87f 474531c9 31c04939 I..I....GE1.1.I9 - 0210 d90f8d3b ffffffc5 fb104c24 3849c1e0 ...;......L$8I.. - 0220 03498d04 c40f1f00 c5f35900 49ffc1c5 .I........Y.I... - 0230 fb11004c 01c04c39 cb75ed48 8d65e85b ...L..L9.u.H.e.[ - 0240 415c415d 31c05dc3 0f1f8400 00000000 A\A]1.]......... - 0250 4c89c148 8d742438 4c89e24c 89cf4c89 L..H.t$8L..L..L. - 0260 442430e8 98fdffff 4c8b4424 304c89c0 D$0.....L.D$0L.. - 0270 490fafc1 eb98662e 0f1f8400 00000000 I.....f......... - 0280 62f2fd48 19d14c89 e04b8d14 ec0f1f00 b..H..L..K...... - 0290 62f1ed48 59004883 c04062f1 fd481140 b..HY.H..@b..H.@ - 02a0 ff4839d0 75eac5f8 77e91eff ffff6690 .H9.u...w.....f. - 02b0 31c031d2 e975feff ff 1.1..u... + 0000 4889f848 c1f80483 e708c5fb 12064881 H..H..........H. + 0010 c2800000 004883f8 000f84bc 000000c5 .....H.......... + 0020 f9596280 c5f9596a 90c5f959 72a0c5f9 .Yb...Yj...Yr... + 0030 597ab0c5 795942c0 c579594a d0c57959 Yz..yYB..yYJ..yY + 0040 52e0c579 595af048 83e80174 5f0f1f00 R..yYZ.H...t_... + 0050 c5f81162 80c5f811 6a90c5f9 5922c5f8 ...b....j...Y".. + 0060 1172a0c5 f9596a10 c5f8117a b0c5f959 .r...Yj....z...Y + 0070 7220c578 1142c0c5 f9597a30 c578114a r .x.B...Yz0.x.J + 0080 d0c57959 4240c578 1152e0c5 79594a50 ..yYB@.x.R..yYJP + 0090 c578115a f0c57959 5260c579 595a7048 .x.Z..yYR`.yYZpH + 00a0 81c28000 00004883 e80175a4 c5f81162 ......H...u....b + 00b0 80c5f811 6a90c5f8 1172a0c5 f8117ab0 ....j....r....z. + 00c0 c5781142 c0c57811 4ad0c578 1152e0c5 .x.B..x.J..x.R.. + 00d0 78115af0 4881c280 00000048 83ff0875 x.Z.H......H...u + 00e0 28c5f959 6280c5f9 596a90c5 f95972a0 (..Yb...Yj...Yr. + 00f0 c5f9597a b0c5f811 6280c5f8 116a90c5 ..Yz....b....j.. + 0100 f81172a0 c5f8117a b0c5f877 c5f877c3 ..r....z...w..w. + 0110 4889f848 c1f80483 e708c5f9 57c04881 H..H........W.H. + 0120 c2800000 004883f8 00743a0f 1f440000 .....H...t:..D.. + 0130 c5f81142 80c5f811 4290c5f8 1142a0c5 ...B....B....B.. + 0140 f81142b0 c5f81142 c0c5f811 42d0c5f8 ..B....B....B... + 0150 1142e0c5 f81142f0 4881c280 00000048 .B....B.H......H + 0160 83e80175 cb4883ff 087514c5 f8114280 ...u.H...u....B. + 0170 c5f81142 90c5f811 42a0c5f8 1142b0c5 ...B....B....B.. + 0180 f877c5f8 77c3662e 0f1f8400 00000000 .w..w.f......... + 0190 4c8d04cd 00000000 31c0486b c918f20f L.......1.Hk.... + 01a0 12064a8d 0482662e 0f1f8400 00000000 ..J...f......... + 01b0 f20f1022 66420f16 2402f242 0f102c42 ..."fB..$..B..,B + 01c0 660f162c 0af20f10 3066420f 163400f2 f..,....0fB..4.. + 01d0 420f103c 40660f16 3c08660f 59e0660f B..<@f..<.f.Y.f. + 01e0 59e8660f 59f0660f 59f8f20f 11226642 Y.f.Y.f.Y...."fB + 01f0 0f172402 f2420f11 2c42660f 172c0af2 ..$..B..,Bf..,.. + 0200 0f113066 420f1734 00f2420f 113c4066 ..0fB..4..B..<@f + 0210 0f173c08 4a8d14c2 4a8d04c0 4883ef08 ..<.J...J...H... + 0220 758ec5f8 77c3662e 0f1f8400 00000000 u...w.f......... + 0230 4883ec18 4989f9c5 fb114424 084989ca H...I.....D$.I.. + 0240 4983f801 0f849600 0000c5f9 2e050000 I............... + 0250 00000f8a f8000000 0f85f200 00004889 ..............H. + 0260 f84883e0 fe0f8eb5 0100004c 89c64889 .H.........L..H. + 0270 ca4b8d3c 0048c1e6 0431c90f 1f440000 .K.<.H...1...D.. + 0280 4883c102 48c70200 0000004a c704c200 H...H......J.... + 0290 00000048 01f24839 c87fe548 ffc848d1 ...H..H9...H..H. + 02a0 e848ffc0 480faff8 4801c048 89fa49c1 .H..H...H..H..I. + 02b0 e003498d 14d24939 c17e170f 1f440000 ..I...I9.~...D.. + 02c0 48ffc048 c7020000 00004c01 c24939c1 H..H......L..I9. + 02d0 75ee31c0 4883c418 c30f1f80 00000000 u.1.H........... + 02e0 4889f962 a1fd0057 c04883e1 f87e2862 H..b...W.H...~(b + 02f0 b1fd082e c0488d74 24084c89 d24889cf .....H.t$.L..H.. + 0300 0f8aca00 00000f85 c4000000 e8fffdff ................ + 0310 ffc5fb10 44240862 b1fd082e c07a0274 ....D$.b.....z.t + 0320 7f4939c9 7eac498d 04ca4b8d 14ca6690 .I9.~.I...K...f. + 0330 c5fb5908 4883c008 c5fb1148 f84839d0 ..Y.H......H.H9. + 0340 75ee31c0 4883c418 c30f1f80 00000000 u.1.H........... + 0350 4d89cb49 83e3f80f 8f930000 004531db M..I.........E1. + 0360 31c04d39 cb0f8d67 ffffffc5 fb104c24 1.M9...g......L$ + 0370 0849c1e0 03498d04 c20f1f80 00000000 .I...I.......... + 0380 c5f35900 49ffc3c5 fb11004c 01c04d39 ..Y.I......L..M9 + 0390 d975ed31 c04883c4 18c3660f 1f440000 .u.1.H....f..D.. + 03a0 4939c90f 8e29ffff ff4929c9 4a8d14cd I9...)...I).J... + 03b0 00000000 498d3cca 31f6e800 00000031 ....I.<.1......1 + 03c0 c04883c4 18c3662e 0f1f8400 00000000 .H....f......... + 03d0 e82bfcff ffc5fb10 44240862 b1fd082e .+......D$.b.... + 03e0 c00f8b38 ffffffe9 35ffffff 0f1f4000 ...8....5.....@. + 03f0 4c89c148 8d742408 4c89d24c 89df4c89 L..H.t$.L..L..L. + 0400 0424e889 fdffff4c 8b04244c 89c0490f .$.....L..$L..I. + 0410 afc3e94b ffffff66 0f1f8400 00000000 ...K...f........ + 0420 31c031d2 e985feff ff 1.1...... /usr/lib64/libopenblas_openmp.a/dscal_k_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dscal_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dscal_k_COOPERLAKE.o (objdump) @@ -4,8 +4,10 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 10000000 1c000000 ................ - 0020 00000000 96000000 00000000 40000000 ............@... - 0030 30000000 00000000 19020000 00410e10 0............A.. - 0040 8602470d 06448d03 8c044483 0502ae0a ..G..D....D..... - 0050 0c070842 0b02560a 0c07084a 0b7e0a0c ...B..V....J.~.. - 0060 0708420b 02470a0c 0708490b 00000000 ..B..G....I..... + 0020 00000000 10010000 00000000 10000000 ................ + 0030 30000000 00000000 76000000 00000000 0.......v....... + 0040 10000000 44000000 00000000 96000000 ....D........... + 0050 00000000 30000000 58000000 00000000 ....0...X....... + 0060 f9010000 00440e20 02a40a0e 08480b02 .....D. .....H.. + 0070 680a0e08 480b0249 0a0e0847 0b650a0e h...H..I...G.e.. + 0080 084b0b00 00000000 .K...... /usr/lib64/libopenblas_openmp.a/dscal_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dscal_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dscal_k_SKYLAKEX.o (disasm) @@ -4,6 +4,98 @@ Disassembly of section .text: +dscal_kernel_8: + mov %rdi,%rax + sar $something,%rax + and $something,%edi + vmovddup (%rsi),%xmm0 + add $something,%rdx + cmp $something,%rax + je + vmulpd -offset(%rdx),%xmm0,%xmm4 + vmulpd -offset(%rdx),%xmm0,%xmm5 + vmulpd -offset(%rdx),%xmm0,%xmm6 + vmulpd -offset(%rdx),%xmm0,%xmm7 + vmulpd -offset(%rdx),%xmm0,%xmm8 + vmulpd -offset(%rdx),%xmm0,%xmm9 + vmulpd -offset(%rdx),%xmm0,%xmm10 + vmulpd -offset(%rdx),%xmm0,%xmm11 + sub $something,%rax + je + nopl (%rax) + vmovups %xmm4,-offset(%rdx) + vmovups %xmm5,-offset(%rdx) + vmulpd (%rdx),%xmm0,%xmm4 + vmovups %xmm6,-offset(%rdx) + vmulpd offset(%rdx),%xmm0,%xmm5 + vmovups %xmm7,-offset(%rdx) + vmulpd offset(%rdx),%xmm0,%xmm6 + vmovups %xmm8,-offset(%rdx) + vmulpd offset(%rdx),%xmm0,%xmm7 + vmovups %xmm9,-offset(%rdx) + vmulpd offset(%rdx),%xmm0,%xmm8 + vmovups %xmm10,-offset(%rdx) + vmulpd offset(%rdx),%xmm0,%xmm9 + vmovups %xmm11,-offset(%rdx) + vmulpd offset(%rdx),%xmm0,%xmm10 + vmulpd offset(%rdx),%xmm0,%xmm11 + add $something,%rdx + sub $something,%rax + jne + vmovups %xmm4,-offset(%rdx) + vmovups %xmm5,-offset(%rdx) + vmovups %xmm6,-offset(%rdx) + vmovups %xmm7,-offset(%rdx) + vmovups %xmm8,-offset(%rdx) + vmovups %xmm9,-offset(%rdx) + vmovups %xmm10,-offset(%rdx) + vmovups %xmm11,-offset(%rdx) + add $something,%rdx + cmp $something,%rdi + jne + vmulpd -offset(%rdx),%xmm0,%xmm4 + vmulpd -offset(%rdx),%xmm0,%xmm5 + vmulpd -offset(%rdx),%xmm0,%xmm6 + vmulpd -offset(%rdx),%xmm0,%xmm7 + vmovups %xmm4,-offset(%rdx) + vmovups %xmm5,-offset(%rdx) + vmovups %xmm6,-offset(%rdx) + vmovups %xmm7,-offset(%rdx) + vzeroupper + vzeroupper + ret + +dscal_kernel_8_zero: + mov %rdi,%rax + sar $something,%rax + and $something,%edi + vxorpd %xmm0,%xmm0,%xmm0 + add $something,%rdx + cmp $something,%rax + je + nopl offset(%rax,%rax,1) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + add $something,%rdx + sub $something,%rax + jne + cmp $something,%rdi + jne + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vmovups %xmm0,-offset(%rdx) + vzeroupper + vzeroupper + ret + cs nopw offset(%rax,%rax,1) + dscal_kernel_inc_8: lea offset(,%rcx,8),%r8 xor %eax,%eax @@ -40,17 +132,10 @@ cs nopw offset(%rax,%rax,1) dscal_k_SKYLAKEX: - push %rbp - vmovsd %xmm0,%xmm0,%xmm1 - mov %rsp,%rbp - push %r13 - push %r12 - mov %rcx,%r12 - push %rbx - mov %rdi,%rbx - and $something,%rsp sub $something,%rsp + mov %rdi,%r9 vmovsd %xmm0,offset(%rsp) + mov %rcx,%r10 cmp $something,%r8 je vucomisd offset(%rip),%xmm0 # @@ -64,7 +149,7 @@ lea (%r8,%r8,1),%rdi shl $something,%rsi xor %ecx,%ecx - nopl offset(%rax) + nopl offset(%rax,%rax,1) add $something,%rcx movq $something,(%rdx) movq $something,(%rdx,%r8,8) @@ -78,117 +163,97 @@ add %rax,%rax mov %rdi,%rdx shl $something,%r8 - lea (%r12,%rdx,8),%rdx - cmp %rax,%rbx + lea (%r10,%rdx,8),%rdx + cmp %rax,%r9 jle nopl offset(%rax,%rax,1) inc %rax movq $something,(%rdx) add %r8,%rdx - cmp %rax,%rbx + cmp %rax,%r9 jne - lea -offset(%rbp),%rsp - pop %rbx - pop %r12 - pop %r13 - xor %eax,%eax - pop %rbp - ret - nop - mov %rdi,%r13 - and $something,%r13 + xor %eax,%eax + add $something,%rsp + ret + nopl offset(%rax) + mov %rdi,%rcx + vxorpd %xmm16,%xmm16,%xmm16 + and $something,%rcx jle - vucomisd offset(%rip),%xmm0 # + vucomisd %xmm16,%xmm0 + lea offset(%rsp),%rsi + mov %r10,%rdx + mov %rcx,%rdi jp jne - lea offset(,%r13,8),%rdx - xor %esi,%esi - mov %rcx,%rdi - call - cmp %r13,%rbx - jle - sub %r13,%rbx - lea (%r12,%r13,8),%rdi - lea offset(,%rbx,8),%rdx - xor %esi,%esi - call - lea -offset(%rbp),%rsp - pop %rbx - pop %r12 - pop %r13 - xor %eax,%eax - pop %rbp - ret - nopw offset(%rax,%rax,1) - vucomisd offset(%rip),%xmm0 # + call + vmovsd offset(%rsp),%xmm0 + vucomisd %xmm16,%xmm0 jp je - cmp %r13,%rbx + cmp %rcx,%r9 jle - lea (%r12,%r13,8),%rax /usr/lib64/libopenblas_openmp.a/dscal_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dscal_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dscal_k_SKYLAKEX.o (objdump) @@ -2,47 +2,70 @@ /usr/lib64/libopenblas_openmp.a/dscal_k_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 4c8d04cd 00000000 31c0486b c918f20f L.......1.Hk.... - 0010 12064a8d 0482662e 0f1f8400 00000000 ..J...f......... - 0020 f20f1022 66420f16 2402f242 0f102c42 ..."fB..$..B..,B - 0030 660f162c 0af20f10 3066420f 163400f2 f..,....0fB..4.. - 0040 420f103c 40660f16 3c08660f 59e0660f B..<@f..<.f.Y.f. - 0050 59e8660f 59f0660f 59f8f20f 11226642 Y.f.Y.f.Y...."fB - 0060 0f172402 f2420f11 2c42660f 172c0af2 ..$..B..,Bf..,.. - 0070 0f113066 420f1734 00f2420f 113c4066 ..0fB..4..B..<@f - 0080 0f173c08 4a8d14c2 4a8d04c0 4883ef08 ..<.J...J...H... - 0090 758ec5f8 77c3662e 0f1f8400 00000000 u...w.f......... - 00a0 55c5fb10 c84889e5 41554154 4989cc53 U....H..AUATI..S - 00b0 4889fb48 83e4c048 83ec40c5 fb114424 H..H...H..@...D$ - 00c0 384983f8 010f8495 000000c5 f92e0500 8I.............. - 00d0 0000000f 8a270100 000f8521 01000048 .....'.....!...H - 00e0 89f84883 e0fe0f8e c4010000 4c89c648 ..H.........L..H - 00f0 89ca4b8d 3c0048c1 e60431c9 0f1f4000 ..K.<.H...1...@. - 0100 4883c102 48c70200 0000004a c704c200 H...H......J.... - 0110 00000048 01f24839 c87fe548 ffc848d1 ...H..H9...H..H. - 0120 e848ffc0 480faff8 4801c048 89fa49c1 .H..H...H..H..I. - 0130 e003498d 14d44839 c37e170f 1f440000 ..I...H9.~...D.. - 0140 48ffc048 c7020000 00004c01 c24839c3 H..H......L..H9. - 0150 75ee488d 65e85b41 5c415d31 c05dc390 u.H.e.[A\A]1.].. - 0160 4989fd49 83e5f87e 57c5f92e 05000000 I..I...~W....... - 0170 000f8a09 0100000f 85030100 004a8d14 .............J.. - 0180 ed000000 0031f648 89cfe800 0000004c .....1.H.......L - 0190 39eb7ebe 4c29eb4b 8d3cec48 8d14dd00 9.~.L).K.<.H.... - 01a0 00000031 f6e80000 0000488d 65e85b41 ...1......H.e.[A - 01b0 5c415d31 c05dc366 0f1f8400 00000000 \A]1.].f........ - 01c0 c5f92e05 00000000 7a0274c3 4c39eb7e ........z.t.L9.~ - 01d0 814b8d04 ec498d14 dc0f1f80 00000000 .K...I.......... - 01e0 c5f35900 4883c008 c5fb1140 f84839d0 ..Y.H......@.H9. - 01f0 75ee488d 65e85b41 5c415d31 c05dc390 u.H.e.[A\A]1.].. - 0200 4989d949 83e1f87f 474531c9 31c04939 I..I....GE1.1.I9 - 0210 d90f8d3b ffffffc5 fb104c24 3849c1e0 ...;......L$8I.. - 0220 03498d04 c40f1f00 c5f35900 49ffc1c5 .I........Y.I... - 0230 fb11004c 01c04c39 cb75ed48 8d65e85b ...L..L9.u.H.e.[ - 0240 415c415d 31c05dc3 0f1f8400 00000000 A\A]1.]......... - 0250 4c89c148 8d742438 4c89e24c 89cf4c89 L..H.t$8L..L..L. - 0260 442430e8 98fdffff 4c8b4424 304c89c0 D$0.....L.D$0L.. - 0270 490fafc1 eb98662e 0f1f8400 00000000 I.....f......... - 0280 62f2fd48 19d14c89 e04b8d14 ec0f1f00 b..H..L..K...... - 0290 62f1ed48 59004883 c04062f1 fd481140 b..HY.H..@b..H.@ - 02a0 ff4839d0 75eac5f8 77e91eff ffff6690 .H9.u...w.....f. - 02b0 31c031d2 e975feff ff 1.1..u... + 0000 4889f848 c1f80483 e708c5fb 12064881 H..H..........H. + 0010 c2800000 004883f8 000f84bc 000000c5 .....H.......... + 0020 f9596280 c5f9596a 90c5f959 72a0c5f9 .Yb...Yj...Yr... + 0030 597ab0c5 795942c0 c579594a d0c57959 Yz..yYB..yYJ..yY + 0040 52e0c579 595af048 83e80174 5f0f1f00 R..yYZ.H...t_... + 0050 c5f81162 80c5f811 6a90c5f9 5922c5f8 ...b....j...Y".. + 0060 1172a0c5 f9596a10 c5f8117a b0c5f959 .r...Yj....z...Y + 0070 7220c578 1142c0c5 f9597a30 c578114a r .x.B...Yz0.x.J + 0080 d0c57959 4240c578 1152e0c5 79594a50 ..yYB@.x.R..yYJP + 0090 c578115a f0c57959 5260c579 595a7048 .x.Z..yYR`.yYZpH + 00a0 81c28000 00004883 e80175a4 c5f81162 ......H...u....b + 00b0 80c5f811 6a90c5f8 1172a0c5 f8117ab0 ....j....r....z. + 00c0 c5781142 c0c57811 4ad0c578 1152e0c5 .x.B..x.J..x.R.. + 00d0 78115af0 4881c280 00000048 83ff0875 x.Z.H......H...u + 00e0 28c5f959 6280c5f9 596a90c5 f95972a0 (..Yb...Yj...Yr. + 00f0 c5f9597a b0c5f811 6280c5f8 116a90c5 ..Yz....b....j.. + 0100 f81172a0 c5f8117a b0c5f877 c5f877c3 ..r....z...w..w. + 0110 4889f848 c1f80483 e708c5f9 57c04881 H..H........W.H. + 0120 c2800000 004883f8 00743a0f 1f440000 .....H...t:..D.. + 0130 c5f81142 80c5f811 4290c5f8 1142a0c5 ...B....B....B.. + 0140 f81142b0 c5f81142 c0c5f811 42d0c5f8 ..B....B....B... + 0150 1142e0c5 f81142f0 4881c280 00000048 .B....B.H......H + 0160 83e80175 cb4883ff 087514c5 f8114280 ...u.H...u....B. + 0170 c5f81142 90c5f811 42a0c5f8 1142b0c5 ...B....B....B.. + 0180 f877c5f8 77c3662e 0f1f8400 00000000 .w..w.f......... + 0190 4c8d04cd 00000000 31c0486b c918f20f L.......1.Hk.... + 01a0 12064a8d 0482662e 0f1f8400 00000000 ..J...f......... + 01b0 f20f1022 66420f16 2402f242 0f102c42 ..."fB..$..B..,B + 01c0 660f162c 0af20f10 3066420f 163400f2 f..,....0fB..4.. + 01d0 420f103c 40660f16 3c08660f 59e0660f B..<@f..<.f.Y.f. + 01e0 59e8660f 59f0660f 59f8f20f 11226642 Y.f.Y.f.Y...."fB + 01f0 0f172402 f2420f11 2c42660f 172c0af2 ..$..B..,Bf..,.. + 0200 0f113066 420f1734 00f2420f 113c4066 ..0fB..4..B..<@f + 0210 0f173c08 4a8d14c2 4a8d04c0 4883ef08 ..<.J...J...H... + 0220 758ec5f8 77c3662e 0f1f8400 00000000 u...w.f......... + 0230 4883ec18 4989f9c5 fb114424 084989ca H...I.....D$.I.. + 0240 4983f801 0f849600 0000c5f9 2e050000 I............... + 0250 00000f8a f8000000 0f85f200 00004889 ..............H. + 0260 f84883e0 fe0f8eb5 0100004c 89c64889 .H.........L..H. + 0270 ca4b8d3c 0048c1e6 0431c90f 1f440000 .K.<.H...1...D.. + 0280 4883c102 48c70200 0000004a c704c200 H...H......J.... + 0290 00000048 01f24839 c87fe548 ffc848d1 ...H..H9...H..H. + 02a0 e848ffc0 480faff8 4801c048 89fa49c1 .H..H...H..H..I. + 02b0 e003498d 14d24939 c17e170f 1f440000 ..I...I9.~...D.. + 02c0 48ffc048 c7020000 00004c01 c24939c1 H..H......L..I9. + 02d0 75ee31c0 4883c418 c30f1f80 00000000 u.1.H........... + 02e0 4889f962 a1fd0057 c04883e1 f87e2862 H..b...W.H...~(b + 02f0 b1fd082e c0488d74 24084c89 d24889cf .....H.t$.L..H.. + 0300 0f8aca00 00000f85 c4000000 e8fffdff ................ + 0310 ffc5fb10 44240862 b1fd082e c07a0274 ....D$.b.....z.t + 0320 7f4939c9 7eac498d 04ca4b8d 14ca6690 .I9.~.I...K...f. + 0330 c5fb5908 4883c008 c5fb1148 f84839d0 ..Y.H......H.H9. + 0340 75ee31c0 4883c418 c30f1f80 00000000 u.1.H........... + 0350 4d89cb49 83e3f80f 8f930000 004531db M..I.........E1. + 0360 31c04d39 cb0f8d67 ffffffc5 fb104c24 1.M9...g......L$ + 0370 0849c1e0 03498d04 c20f1f80 00000000 .I...I.......... + 0380 c5f35900 49ffc3c5 fb11004c 01c04d39 ..Y.I......L..M9 + 0390 d975ed31 c04883c4 18c3660f 1f440000 .u.1.H....f..D.. + 03a0 4939c90f 8e29ffff ff4929c9 4a8d14cd I9...)...I).J... + 03b0 00000000 498d3cca 31f6e800 00000031 ....I.<.1......1 + 03c0 c04883c4 18c3662e 0f1f8400 00000000 .H....f......... + 03d0 e82bfcff ffc5fb10 44240862 b1fd082e .+......D$.b.... + 03e0 c00f8b38 ffffffe9 35ffffff 0f1f4000 ...8....5.....@. + 03f0 4c89c148 8d742408 4c89d24c 89df4c89 L..H.t$.L..L..L. + 0400 0424e889 fdffff4c 8b04244c 89c0490f .$.....L..$L..I. + 0410 afc3e94b ffffff66 0f1f8400 00000000 ...K...f........ + 0420 31c031d2 e985feff ff 1.1...... /usr/lib64/libopenblas_openmp.a/dscal_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dscal_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dscal_k_SKYLAKEX.o (objdump) @@ -4,8 +4,10 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 10000000 1c000000 ................ - 0020 00000000 96000000 00000000 40000000 ............@... - 0030 30000000 00000000 19020000 00410e10 0............A.. - 0040 8602470d 06448d03 8c044483 0502ae0a ..G..D....D..... - 0050 0c070842 0b02560a 0c07084a 0b7e0a0c ...B..V....J.~.. - 0060 0708420b 02470a0c 0708490b 00000000 ..B..G....I..... + 0020 00000000 10010000 00000000 10000000 ................ + 0030 30000000 00000000 76000000 00000000 0.......v....... + 0040 10000000 44000000 00000000 96000000 ....D........... + 0050 00000000 30000000 58000000 00000000 ....0...X....... + 0060 f9010000 00440e20 02a40a0e 08480b02 .....D. .....H.. + 0070 680a0e08 480b0249 0a0e0847 0b650a0e h...H..I...G.e.. + 0080 084b0b00 00000000 .K...... /usr/lib64/libopenblas_openmp.a/dsdot_k_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsdot_k_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsdot_k_COOPERLAKE.o (disasm) @@ -4,134 +4,163 @@ Disassembly of section .text: +sdot_kernel_16.constprop.0: + mov %rdx,%r8 + xor %eax,%eax + mov $something,%edx + vxorps %ymm4,%ymm4,%ymm4 + vxorps %ymm5,%ymm5,%ymm5 + vxorps %ymm6,%ymm6,%ymm6 + vxorps %ymm7,%ymm7,%ymm7 + nopw offset(%rax,%rax,1) + vmovups (%rdi,%rax,4),%ymm12 + vmovups offset(%rdi,%rax,4),%ymm13 + vmovups offset(%rdi,%rax,4),%ymm14 + vmovups offset(%rdi,%rax,4),%ymm15 + vfmadd231ps (%rsi,%rax,4),%ymm12,%ymm4 + vfmadd231ps offset(%rsi,%rax,4),%ymm13,%ymm5 + vfmadd231ps offset(%rsi,%rax,4),%ymm14,%ymm6 + vfmadd231ps offset(%rsi,%rax,4),%ymm15,%ymm7 + vextractf128 $something,%ymm4,%xmm12 + vextractf128 $something,%ymm5,%xmm13 + vextractf128 $something,%ymm6,%xmm14 + vextractf128 $something,%ymm7,%xmm15 + vaddps %xmm4,%xmm12,%xmm4 + vaddps %xmm5,%xmm13,%xmm5 + vaddps %xmm6,%xmm14,%xmm6 + vaddps %xmm7,%xmm15,%xmm7 + vaddps %xmm4,%xmm5,%xmm4 + vaddps %xmm6,%xmm7,%xmm6 + vaddps %xmm4,%xmm6,%xmm4 + vhaddps %xmm4,%xmm4,%xmm4 + vhaddps %xmm4,%xmm4,%xmm4 + vmovss %xmm4,(%r8) + vzeroupper + vzeroupper + ret + nopw offset(%rax,%rax,1) + dsdot_k_COOPERLAKE: + push %r13 + vxorpd %xmm2,%xmm2,%xmm2 + push %r12 + push %rbp + push %rbx + sub $something,%rsp + mov %fs:0x28,%rax + mov %rax,offset(%rsp) + xor %eax,%eax + movl $something,offset(%rsp) test %rdi,%rdi jle - mov %rsi,%r9 - mov %rcx,%r10 + mov %rsi,%r10 + mov %rdi,%r9 mov %rdx,%rsi - vxorps %xmm1,%xmm1,%xmm1 + mov %rcx,%r11 + vxorps %xmm16,%xmm16,%xmm16 cmp $something,%rdx jne cmp $something,%r8 jne - mov %rdi,%rax - and $something,%rax + mov %rdi,%rcx + and $something,%rcx jne - vxorpd %xmm7,%xmm7,%xmm7 - vmovsd %xmm7,%xmm7,%xmm3 - vmovsd %xmm7,%xmm7,%xmm4 + vxorpd %xmm18,%xmm18,%xmm18 + vmovsd %xmm18,%xmm18,%xmm17 + vmovsd %xmm18,%xmm18,%xmm2 nopl offset(%rax,%rax,1) - vcvtss2sd (%r10,%rax,4),%xmm1,%xmm0 - vmovsd %xmm0,%xmm0,%xmm2 - vcvtss2sd (%r9,%rax,4),%xmm1,%xmm0 - inc %rax - vfmadd231sd %xmm0,%xmm2,%xmm4 - cmp %rax,%rdi + vcvtss2sd (%r11,%rcx,4),%xmm16,%xmm0 + vmovsd %xmm0,%xmm0,%xmm1 + vcvtss2sd (%r10,%rcx,4),%xmm16,%xmm0 + inc %rcx + vfmadd231sd %xmm0,%xmm1,%xmm2 + cmp %rcx,%r9 jg - vaddsd %xmm4,%xmm3,%xmm3 - vmovsd %xmm3,%xmm3,%xmm0 + vaddsd %xmm2,%xmm17,%xmm2 + mov offset(%rsp),%rax + sub %fs:0x28,%rax + jne + add $something,%rsp + pop %rbx + pop %rbp + pop %r12 + vmovsd %xmm2,%xmm2,%xmm0 + pop %r13 ret - cs nopw offset(%rax,%rax,1) - push %rbp - mov %rdi,%rax - mov %rsp,%rbp - push %r14 - push %r13 - push %r12 - push %rbx + nopl offset(%rax,%rax,1) + mov %r9,%rax and $something,%rax je - lea (%rsi,%rsi,1),%r13 - lea (%r8,%r8,1),%r14 - lea offset(,%r8,8),%r12 - mov %r10,%rcx + lea (%rsi,%rsi,1),%r12 + lea (%r8,%r8,1),%r13 + lea offset(,%r8,8),%rbp + mov %r11,%rcx lea offset(,%rsi,8),%rbx - mov %r9,%rdx - vxorpd %xmm3,%xmm3,%xmm3 - xor %r11d,%r11d - nopl (%rax) - vcvtss2sd (%rdx),%xmm1,%xmm2 - vcvtss2sd (%rdx,%rsi,4),%xmm1,%xmm5 - vmovsd %xmm2,%xmm2,%xmm4 - vcvtss2sd (%rcx,%r8,4),%xmm1,%xmm2 - vmulsd %xmm5,%xmm2,%xmm2 - vcvtss2sd (%rcx),%xmm1,%xmm0 - add $something,%r11 - add %r12,%rcx + mov %r10,%rdx + vxorpd %xmm2,%xmm2,%xmm2 + xor %edi,%edi + nopl offset(%rax) + vcvtss2sd (%rdx),%xmm16,%xmm1 + vcvtss2sd (%rdx,%rsi,4),%xmm16,%xmm4 + vmovsd %xmm1,%xmm1,%xmm3 + vcvtss2sd (%rcx,%r8,4),%xmm16,%xmm1 + vmulsd %xmm4,%xmm1,%xmm1 + vcvtss2sd (%rcx),%xmm16,%xmm0 + add $something,%rdi + add %rbp,%rcx add %rbx,%rdx - vfmadd132sd %xmm4,%xmm2,%xmm0 - vaddsd %xmm0,%xmm3,%xmm3 - cmp %r11,%rax + vfmadd132sd %xmm3,%xmm1,%xmm0 + vaddsd %xmm0,%xmm2,%xmm2 + cmp %rdi,%rax jg dec %rax shr %rax inc %rax + imul %rax,%r12 imul %rax,%r13 - imul %rax,%r14 add %rax,%rax - cmp %rax,%rdi + cmp %rax,%r9 jle shl $something,%r8 - lea (%r10,%r14,4),%rcx + lea (%r11,%r13,4),%rcx shl $something,%rsi - lea (%r9,%r13,4),%rdx - nopl offset(%rax) - vcvtss2sd (%rcx),%xmm1,%xmm0 + lea (%r10,%r12,4),%rdx + nop + vcvtss2sd (%rcx),%xmm16,%xmm0 inc %rax - vmovsd %xmm0,%xmm0,%xmm2 + vmovsd %xmm0,%xmm0,%xmm1 add %r8,%rcx - vcvtss2sd (%rdx),%xmm1,%xmm0 + vcvtss2sd (%rdx),%xmm16,%xmm0 add %rsi,%rdx - vfmadd231sd %xmm0,%xmm2,%xmm3 - cmp %rax,%rdi + vfmadd231sd %xmm0,%xmm1,%xmm2 + cmp %rax,%r9 jg - pop %rbx - pop %r12 - pop %r13 - pop %r14 - vmovsd %xmm3,%xmm3,%xmm0 - pop %rbp - ret - nopl offset(%rax) - vxorpd %xmm3,%xmm3,%xmm3 - vmovsd %xmm3,%xmm3,%xmm0 /usr/lib64/libopenblas_openmp.a/dsdot_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsdot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsdot_k_COOPERLAKE.o (objdump) @@ -2,35 +2,46 @@ /usr/lib64/libopenblas_openmp.a/dsdot_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 4885ff0f 8e370100 004989f1 4989ca48 H....7...I..I..H - 0010 89d6c5f0 57c94883 fa017554 4983f801 ....W.H...uTI... - 0020 754e4889 f84883e0 e00f8521 010000c5 uNH..H.....!.... - 0030 c157ffc5 c310dfc5 c310e70f 1f440000 .W...........D.. - 0040 c4c1725a 0482c5fb 10d0c4c1 725a0481 ..rZ........rZ.. - 0050 48ffc0c4 e2e9b9e0 4839c77f e3c5e358 H.......H9.....X - 0060 dcc5e310 c3c3662e 0f1f8400 00000000 ......f......... - 0070 554889f8 4889e541 56415541 54534883 UH..H..AVAUATSH. - 0080 e0fe0f84 52010000 4c8d2c36 4f8d3400 ....R...L.,6O.4. - 0090 4e8d24c5 00000000 4c89d148 8d1cf500 N.$.....L..H.... - 00a0 0000004c 89cac5e1 57db4531 db0f1f00 ...L....W.E1.... - 00b0 c5f25a12 c5f25a2c b2c5eb10 e2c4a172 ..Z...Z,.......r - 00c0 5a1481c5 eb59d5c5 f25a0149 83c3024c Z....Y...Z.I...L - 00d0 01e14801 dac4e2e9 99c4c5e3 58d84c39 ..H.........X.L9 - 00e0 d87fcd48 ffc848d1 e848ffc0 4c0fafe8 ...H..H..H..L... - 00f0 4c0faff0 4801c048 39c77e33 49c1e002 L...H..H9.~3I... - 0100 4b8d0cb2 48c1e602 4b8d14a9 0f1f4000 K...H...K.....@. - 0110 c5f25a01 48ffc0c5 fb10d04c 01c1c5f2 ..Z.H......L.... - 0120 5a024801 f2c4e2e9 b9d84839 c77fe15b Z.H.......H9...[ - 0130 415c415d 415ec5e3 10c35dc3 0f1f4000 A\A]A^....]...@. - 0140 c5e157db c5e310c3 c30f1f80 00000000 ..W............. - 0150 c5c157ff c5d857e4 c5c310df 31d26690 ..W...W.....1.f. - 0160 c4c17c10 1491c4c1 7c107491 20c4c25d ..|.....|.t. ..] - 0170 981492c4 c25d9874 9220c4c1 7c106c91 .....].t. ..|.l. - 0180 40c4c17c 10449260 c4c25d98 6c9240c4 @..|.D.`..].l.@. - 0190 c25d9844 9160c5ec 58d64883 c220c5ec .].D.`..X.H.. .. - 01a0 58d5c5fc 58c2c5f8 28d0c4e3 7d19c001 X...X...(...}... - 01b0 c5e858d0 c5eb7cd2 c5eb7cd2 c5ea5ad2 ..X...|...|...Z. - 01c0 c5e358da 4839d07f 97c5c310 e74839c7 ..X.H9.......H9. - 01d0 7e17c5f8 77e95dfe ffff4531 f64531ed ~...w.]...E1.E1. - 01e0 c5e157db e913ffff ffc5f877 e96cfeff ..W........w.l.. - 01f0 ff . + 0000 4989d031 c0ba2000 0000c5dc 57e4c5d4 I..1.. .....W... + 0010 57edc5cc 57f6c5c4 57ff660f 1f440000 W...W...W.f..D.. + 0020 c57c1024 87c57c10 6c8720c5 7c107487 .|.$..|.l. .|.t. + 0030 40c57c10 7c8760c4 e21db824 86c4e215 @.|.|.`....$.... + 0040 b86c8620 c4e20db8 748640c4 e205b87c .l. ....t.@....| + 0050 8660c4c3 7d19e401 c4c37d19 ed01c4c3 .`..}.....}..... + 0060 7d19f601 c4c37d19 ff01c598 58e4c590 }.....}.....X... + 0070 58edc588 58f6c580 58ffc5d0 58e4c5c0 X...X...X...X... + 0080 58f6c5c8 58e4c5db 7ce4c5db 7ce4c4c1 X...X...|...|... + 0090 7a1120c5 f877c5f8 77c3660f 1f440000 z. ..w..w.f..D.. + 00a0 4155c5e9 57d24154 55534883 ec186448 AU..W.ATUSH...dH + 00b0 8b042528 00000048 89442408 31c0c744 ..%(...H.D$.1..D + 00c0 24040000 00004885 ff7e6a49 89f24989 $.....H..~jI..I. + 00d0 f94889d6 4989cb62 a17c0057 c04883fa .H..I..b.|.W.H.. + 00e0 01757d49 83f80175 774889f9 4883e1e0 .u}I...uwH..H... + 00f0 0f853a01 000062a1 ed0057d2 62a1ef00 ..:...b...W.b... + 0100 10ca62b1 ef0010d2 0f1f8400 00000000 ..b............. + 0110 62d17e00 5a048bc5 fb10c862 d17e005a b.~.Z......b.~.Z + 0120 048a48ff c1c4e2f1 b9d04939 c97fe162 ..H.......I9...b + 0130 f1f70058 d2488b44 24086448 2b042528 ...X.H.D$.dH+.%( + 0140 0000000f 855e0100 004883c4 185b5d41 .....^...H...[]A + 0150 5cc5eb10 c2415dc3 0f1f8400 00000000 \....A]......... + 0160 4c89c848 83e0fe0f 842b0100 004c8d24 L..H.....+...L.$ + 0170 364f8d2c 004a8d2c c5000000 004c89d9 6O.,.J.,.....L.. + 0180 488d1cf5 00000000 4c89d2c5 e957d231 H.......L....W.1 + 0190 ff0f1f80 00000000 62f17e00 5a0a62f1 ........b.~.Z.b. + 01a0 7e005a24 b2c5f310 d962b17e 005a0c81 ~.Z$.....b.~.Z.. + 01b0 c5f359cc 62f17e00 5a014883 c7024801 ..Y.b.~.Z.H...H. + 01c0 e94801da c4e2f199 c3c5eb58 d04839f8 .H.........X.H9. + 01d0 7fc648ff c848d1e8 48ffc04c 0fafe04c ..H..H..H..L...L + 01e0 0fafe848 01c04939 c10f8e46 ffffff49 ...H..I9...F...I + 01f0 c1e0024b 8d0cab48 c1e6024b 8d14a290 ...K...H...K.... + 0200 62f17e00 5a0148ff c0c5fb10 c84c01c1 b.~.Z.H......L.. + 0210 62f17e00 5a024801 f2c4e2f1 b9d04939 b.~.Z.H.......I9 + 0220 c17fdde9 0dffffff 0f1f8400 00000000 ................ + 0230 62a1ed00 57d24c89 de4c89d7 62a1ef00 b...W.L..L..b... + 0240 10ca31db 488d6c24 040f1f80 00000000 ..1.H.l$........ + 0250 4889ea48 83c320e8 a4fdffff 62f17e00 H..H.. .....b.~. + 0260 5a442401 4883ef80 62e1f700 58c8c744 ZD$.H...b...X..D + 0270 24040000 00004883 ee804839 d97fd162 $.....H...H9...b + 0280 b1ef0010 d24939c9 0f8f74fe ffffe99c .....I9...t..... + 0290 feffff0f 1f440000 4531ed45 31e4c5e9 .....D..E1.E1... + 02a0 57d2e948 ffffffe8 00000000 W..H........ /usr/lib64/libopenblas_openmp.a/dsdot_k_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dsdot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsdot_k_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 19000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39000000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/dsdot_k_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsdot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsdot_k_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 f1010000 0002710e 10860246 ..........q....F - 0030 0d06478e 038d048c 05830602 bd0c0708 ..G............. - 0040 45c3c6cc cdce029a 0c061083 0686028c E............... - 0050 058d048e 034f0c07 08c3c6cc cdce0000 .....O.......... + 0010 1b0c0708 90010000 10000000 1c000000 ................ + 0020 00000000 9a000000 00000000 38000000 ............8... + 0030 30000000 00000000 0c020000 00420e10 0............B.. + 0040 8d02460e 188c0341 0e208604 410e2883 ..F....A. ..A.(. + 0050 05440e40 029f0a0e 28410e20 410e1842 .D.@....(A. A..B + 0060 0e10460e 08490b00 ..F..I.. /usr/lib64/libopenblas_openmp.a/dsdot_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsdot_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsdot_k_SKYLAKEX.o (disasm) @@ -4,134 +4,163 @@ Disassembly of section .text: +sdot_kernel_16.constprop.0: + mov %rdx,%r8 + xor %eax,%eax + mov $something,%edx + vxorps %ymm4,%ymm4,%ymm4 + vxorps %ymm5,%ymm5,%ymm5 + vxorps %ymm6,%ymm6,%ymm6 + vxorps %ymm7,%ymm7,%ymm7 + nopw offset(%rax,%rax,1) + vmovups (%rdi,%rax,4),%ymm12 + vmovups offset(%rdi,%rax,4),%ymm13 + vmovups offset(%rdi,%rax,4),%ymm14 + vmovups offset(%rdi,%rax,4),%ymm15 + vfmadd231ps (%rsi,%rax,4),%ymm12,%ymm4 + vfmadd231ps offset(%rsi,%rax,4),%ymm13,%ymm5 + vfmadd231ps offset(%rsi,%rax,4),%ymm14,%ymm6 + vfmadd231ps offset(%rsi,%rax,4),%ymm15,%ymm7 + vextractf128 $something,%ymm4,%xmm12 + vextractf128 $something,%ymm5,%xmm13 + vextractf128 $something,%ymm6,%xmm14 + vextractf128 $something,%ymm7,%xmm15 + vaddps %xmm4,%xmm12,%xmm4 + vaddps %xmm5,%xmm13,%xmm5 + vaddps %xmm6,%xmm14,%xmm6 + vaddps %xmm7,%xmm15,%xmm7 + vaddps %xmm4,%xmm5,%xmm4 + vaddps %xmm6,%xmm7,%xmm6 + vaddps %xmm4,%xmm6,%xmm4 + vhaddps %xmm4,%xmm4,%xmm4 + vhaddps %xmm4,%xmm4,%xmm4 + vmovss %xmm4,(%r8) + vzeroupper + vzeroupper + ret + nopw offset(%rax,%rax,1) + dsdot_k_SKYLAKEX: + push %r13 + vxorpd %xmm2,%xmm2,%xmm2 + push %r12 + push %rbp + push %rbx + sub $something,%rsp + mov %fs:0x28,%rax + mov %rax,offset(%rsp) + xor %eax,%eax + movl $something,offset(%rsp) test %rdi,%rdi jle - mov %rsi,%r9 - mov %rcx,%r10 + mov %rsi,%r10 + mov %rdi,%r9 mov %rdx,%rsi - vxorps %xmm1,%xmm1,%xmm1 + mov %rcx,%r11 + vxorps %xmm16,%xmm16,%xmm16 cmp $something,%rdx jne cmp $something,%r8 jne - mov %rdi,%rax - and $something,%rax + mov %rdi,%rcx + and $something,%rcx jne - vxorpd %xmm7,%xmm7,%xmm7 - vmovsd %xmm7,%xmm7,%xmm3 - vmovsd %xmm7,%xmm7,%xmm4 + vxorpd %xmm18,%xmm18,%xmm18 + vmovsd %xmm18,%xmm18,%xmm17 + vmovsd %xmm18,%xmm18,%xmm2 nopl offset(%rax,%rax,1) - vcvtss2sd (%r10,%rax,4),%xmm1,%xmm0 - vmovsd %xmm0,%xmm0,%xmm2 - vcvtss2sd (%r9,%rax,4),%xmm1,%xmm0 - inc %rax - vfmadd231sd %xmm0,%xmm2,%xmm4 - cmp %rax,%rdi + vcvtss2sd (%r11,%rcx,4),%xmm16,%xmm0 + vmovsd %xmm0,%xmm0,%xmm1 + vcvtss2sd (%r10,%rcx,4),%xmm16,%xmm0 + inc %rcx + vfmadd231sd %xmm0,%xmm1,%xmm2 + cmp %rcx,%r9 jg - vaddsd %xmm4,%xmm3,%xmm3 - vmovsd %xmm3,%xmm3,%xmm0 + vaddsd %xmm2,%xmm17,%xmm2 + mov offset(%rsp),%rax + sub %fs:0x28,%rax + jne + add $something,%rsp + pop %rbx + pop %rbp + pop %r12 + vmovsd %xmm2,%xmm2,%xmm0 + pop %r13 ret - cs nopw offset(%rax,%rax,1) - push %rbp - mov %rdi,%rax - mov %rsp,%rbp - push %r14 - push %r13 - push %r12 - push %rbx + nopl offset(%rax,%rax,1) + mov %r9,%rax and $something,%rax je - lea (%rsi,%rsi,1),%r13 - lea (%r8,%r8,1),%r14 - lea offset(,%r8,8),%r12 - mov %r10,%rcx + lea (%rsi,%rsi,1),%r12 + lea (%r8,%r8,1),%r13 + lea offset(,%r8,8),%rbp + mov %r11,%rcx lea offset(,%rsi,8),%rbx - mov %r9,%rdx - vxorpd %xmm3,%xmm3,%xmm3 - xor %r11d,%r11d - nopl (%rax) - vcvtss2sd (%rdx),%xmm1,%xmm2 - vcvtss2sd (%rdx,%rsi,4),%xmm1,%xmm5 - vmovsd %xmm2,%xmm2,%xmm4 - vcvtss2sd (%rcx,%r8,4),%xmm1,%xmm2 - vmulsd %xmm5,%xmm2,%xmm2 - vcvtss2sd (%rcx),%xmm1,%xmm0 - add $something,%r11 - add %r12,%rcx + mov %r10,%rdx + vxorpd %xmm2,%xmm2,%xmm2 + xor %edi,%edi + nopl offset(%rax) + vcvtss2sd (%rdx),%xmm16,%xmm1 + vcvtss2sd (%rdx,%rsi,4),%xmm16,%xmm4 + vmovsd %xmm1,%xmm1,%xmm3 + vcvtss2sd (%rcx,%r8,4),%xmm16,%xmm1 + vmulsd %xmm4,%xmm1,%xmm1 + vcvtss2sd (%rcx),%xmm16,%xmm0 + add $something,%rdi + add %rbp,%rcx add %rbx,%rdx - vfmadd132sd %xmm4,%xmm2,%xmm0 - vaddsd %xmm0,%xmm3,%xmm3 - cmp %r11,%rax + vfmadd132sd %xmm3,%xmm1,%xmm0 + vaddsd %xmm0,%xmm2,%xmm2 + cmp %rdi,%rax jg dec %rax shr %rax inc %rax + imul %rax,%r12 imul %rax,%r13 - imul %rax,%r14 add %rax,%rax - cmp %rax,%rdi + cmp %rax,%r9 jle shl $something,%r8 - lea (%r10,%r14,4),%rcx + lea (%r11,%r13,4),%rcx shl $something,%rsi - lea (%r9,%r13,4),%rdx - nopl offset(%rax) - vcvtss2sd (%rcx),%xmm1,%xmm0 + lea (%r10,%r12,4),%rdx + nop + vcvtss2sd (%rcx),%xmm16,%xmm0 inc %rax - vmovsd %xmm0,%xmm0,%xmm2 + vmovsd %xmm0,%xmm0,%xmm1 add %r8,%rcx - vcvtss2sd (%rdx),%xmm1,%xmm0 + vcvtss2sd (%rdx),%xmm16,%xmm0 add %rsi,%rdx - vfmadd231sd %xmm0,%xmm2,%xmm3 - cmp %rax,%rdi + vfmadd231sd %xmm0,%xmm1,%xmm2 + cmp %rax,%r9 jg - pop %rbx - pop %r12 - pop %r13 - pop %r14 - vmovsd %xmm3,%xmm3,%xmm0 - pop %rbp - ret - nopl offset(%rax) - vxorpd %xmm3,%xmm3,%xmm3 - vmovsd %xmm3,%xmm3,%xmm0 /usr/lib64/libopenblas_openmp.a/dsdot_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsdot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsdot_k_SKYLAKEX.o (objdump) @@ -2,35 +2,46 @@ /usr/lib64/libopenblas_openmp.a/dsdot_k_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 4885ff0f 8e370100 004989f1 4989ca48 H....7...I..I..H - 0010 89d6c5f0 57c94883 fa017554 4983f801 ....W.H...uTI... - 0020 754e4889 f84883e0 e00f8521 010000c5 uNH..H.....!.... - 0030 c157ffc5 c310dfc5 c310e70f 1f440000 .W...........D.. - 0040 c4c1725a 0482c5fb 10d0c4c1 725a0481 ..rZ........rZ.. - 0050 48ffc0c4 e2e9b9e0 4839c77f e3c5e358 H.......H9.....X - 0060 dcc5e310 c3c3662e 0f1f8400 00000000 ......f......... - 0070 554889f8 4889e541 56415541 54534883 UH..H..AVAUATSH. - 0080 e0fe0f84 52010000 4c8d2c36 4f8d3400 ....R...L.,6O.4. - 0090 4e8d24c5 00000000 4c89d148 8d1cf500 N.$.....L..H.... - 00a0 0000004c 89cac5e1 57db4531 db0f1f00 ...L....W.E1.... - 00b0 c5f25a12 c5f25a2c b2c5eb10 e2c4a172 ..Z...Z,.......r - 00c0 5a1481c5 eb59d5c5 f25a0149 83c3024c Z....Y...Z.I...L - 00d0 01e14801 dac4e2e9 99c4c5e3 58d84c39 ..H.........X.L9 - 00e0 d87fcd48 ffc848d1 e848ffc0 4c0fafe8 ...H..H..H..L... - 00f0 4c0faff0 4801c048 39c77e33 49c1e002 L...H..H9.~3I... - 0100 4b8d0cb2 48c1e602 4b8d14a9 0f1f4000 K...H...K.....@. - 0110 c5f25a01 48ffc0c5 fb10d04c 01c1c5f2 ..Z.H......L.... - 0120 5a024801 f2c4e2e9 b9d84839 c77fe15b Z.H.......H9...[ - 0130 415c415d 415ec5e3 10c35dc3 0f1f4000 A\A]A^....]...@. - 0140 c5e157db c5e310c3 c30f1f80 00000000 ..W............. - 0150 c5c157ff c5d857e4 c5c310df 31d26690 ..W...W.....1.f. - 0160 c4c17c10 1491c4c1 7c107491 20c4c25d ..|.....|.t. ..] - 0170 981492c4 c25d9874 9220c4c1 7c106c91 .....].t. ..|.l. - 0180 40c4c17c 10449260 c4c25d98 6c9240c4 @..|.D.`..].l.@. - 0190 c25d9844 9160c5ec 58d64883 c220c5ec .].D.`..X.H.. .. - 01a0 58d5c5fc 58c2c5f8 28d0c4e3 7d19c001 X...X...(...}... - 01b0 c5e858d0 c5eb7cd2 c5eb7cd2 c5ea5ad2 ..X...|...|...Z. - 01c0 c5e358da 4839d07f 97c5c310 e74839c7 ..X.H9.......H9. - 01d0 7e17c5f8 77e95dfe ffff4531 f64531ed ~...w.]...E1.E1. - 01e0 c5e157db e913ffff ffc5f877 e96cfeff ..W........w.l.. - 01f0 ff . + 0000 4989d031 c0ba2000 0000c5dc 57e4c5d4 I..1.. .....W... + 0010 57edc5cc 57f6c5c4 57ff660f 1f440000 W...W...W.f..D.. + 0020 c57c1024 87c57c10 6c8720c5 7c107487 .|.$..|.l. .|.t. + 0030 40c57c10 7c8760c4 e21db824 86c4e215 @.|.|.`....$.... + 0040 b86c8620 c4e20db8 748640c4 e205b87c .l. ....t.@....| + 0050 8660c4c3 7d19e401 c4c37d19 ed01c4c3 .`..}.....}..... + 0060 7d19f601 c4c37d19 ff01c598 58e4c590 }.....}.....X... + 0070 58edc588 58f6c580 58ffc5d0 58e4c5c0 X...X...X...X... + 0080 58f6c5c8 58e4c5db 7ce4c5db 7ce4c4c1 X...X...|...|... + 0090 7a1120c5 f877c5f8 77c3660f 1f440000 z. ..w..w.f..D.. + 00a0 4155c5e9 57d24154 55534883 ec186448 AU..W.ATUSH...dH + 00b0 8b042528 00000048 89442408 31c0c744 ..%(...H.D$.1..D + 00c0 24040000 00004885 ff7e6a49 89f24989 $.....H..~jI..I. + 00d0 f94889d6 4989cb62 a17c0057 c04883fa .H..I..b.|.W.H.. + 00e0 01757d49 83f80175 774889f9 4883e1e0 .u}I...uwH..H... + 00f0 0f853a01 000062a1 ed0057d2 62a1ef00 ..:...b...W.b... + 0100 10ca62b1 ef0010d2 0f1f8400 00000000 ..b............. + 0110 62d17e00 5a048bc5 fb10c862 d17e005a b.~.Z......b.~.Z + 0120 048a48ff c1c4e2f1 b9d04939 c97fe162 ..H.......I9...b + 0130 f1f70058 d2488b44 24086448 2b042528 ...X.H.D$.dH+.%( + 0140 0000000f 855e0100 004883c4 185b5d41 .....^...H...[]A + 0150 5cc5eb10 c2415dc3 0f1f8400 00000000 \....A]......... + 0160 4c89c848 83e0fe0f 842b0100 004c8d24 L..H.....+...L.$ + 0170 364f8d2c 004a8d2c c5000000 004c89d9 6O.,.J.,.....L.. + 0180 488d1cf5 00000000 4c89d2c5 e957d231 H.......L....W.1 + 0190 ff0f1f80 00000000 62f17e00 5a0a62f1 ........b.~.Z.b. + 01a0 7e005a24 b2c5f310 d962b17e 005a0c81 ~.Z$.....b.~.Z.. + 01b0 c5f359cc 62f17e00 5a014883 c7024801 ..Y.b.~.Z.H...H. + 01c0 e94801da c4e2f199 c3c5eb58 d04839f8 .H.........X.H9. + 01d0 7fc648ff c848d1e8 48ffc04c 0fafe04c ..H..H..H..L...L + 01e0 0fafe848 01c04939 c10f8e46 ffffff49 ...H..I9...F...I + 01f0 c1e0024b 8d0cab48 c1e6024b 8d14a290 ...K...H...K.... + 0200 62f17e00 5a0148ff c0c5fb10 c84c01c1 b.~.Z.H......L.. + 0210 62f17e00 5a024801 f2c4e2f1 b9d04939 b.~.Z.H.......I9 + 0220 c17fdde9 0dffffff 0f1f8400 00000000 ................ + 0230 62a1ed00 57d24c89 de4c89d7 62a1ef00 b...W.L..L..b... + 0240 10ca31db 488d6c24 040f1f80 00000000 ..1.H.l$........ + 0250 4889ea48 83c320e8 a4fdffff 62f17e00 H..H.. .....b.~. + 0260 5a442401 4883ef80 62e1f700 58c8c744 ZD$.H...b...X..D + 0270 24040000 00004883 ee804839 d97fd162 $.....H...H9...b + 0280 b1ef0010 d24939c9 0f8f74fe ffffe99c .....I9...t..... + 0290 feffff0f 1f440000 4531ed45 31e4c5e9 .....D..E1.E1... + 02a0 57d2e948 ffffffe8 00000000 W..H........ /usr/lib64/libopenblas_openmp.a/dsdot_k_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dsdot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsdot_k_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 19000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39000000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/dsdot_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsdot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsdot_k_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 f1010000 0002710e 10860246 ..........q....F - 0030 0d06478e 038d048c 05830602 bd0c0708 ..G............. - 0040 45c3c6cc cdce029a 0c061083 0686028c E............... - 0050 058d048e 034f0c07 08c3c6cc cdce0000 .....O.......... + 0010 1b0c0708 90010000 10000000 1c000000 ................ + 0020 00000000 9a000000 00000000 38000000 ............8... + 0030 30000000 00000000 0c020000 00420e10 0............B.. + 0040 8d02460e 188c0341 0e208604 410e2883 ..F....A. ..A.(. + 0050 05440e40 029f0a0e 28410e20 410e1842 .D.@....(A. A..B + 0060 0e10460e 08490b00 ..F..I.. /usr/lib64/libopenblas_openmp.a/dsum_k_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsum_k_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsum_k_COOPERLAKE.o (disasm) @@ -32,32 +32,32 @@ lea -offset(%r9),%rax shr $something,%rax mov %rax,%r9 - vxorpd %xmm0,%xmm0,%xmm0 + vxorpd %xmm3,%xmm3,%xmm3 shl $something,%r9 mov %rcx,%rdx lea offset(%rcx,%r9,1),%r9 - vmovapd %zmm0,%zmm3 - vmovapd %zmm0,%zmm1 - vmovapd %zmm0,%zmm2 - nopw offset(%rax,%rax,1) - vaddpd (%rdx),%zmm2,%zmm2 - vaddpd offset(%rdx),%zmm1,%zmm1 - vaddpd offset(%rdx),%zmm3,%zmm3 - vaddpd offset(%rdx),%zmm0,%zmm0 - add $something,%rdx + vmovapd %ymm3,%ymm0 + vmovapd %ymm3,%ymm2 + vmovapd %ymm3,%ymm1 + nopl offset(%rax) + vaddpd (%rdx),%ymm1,%ymm1 + vaddpd offset(%rdx),%ymm2,%ymm2 + vaddpd offset(%rdx),%ymm0,%ymm0 + vaddpd offset(%rdx),%ymm3,%ymm3 + sub $something,%rdx cmp %rdx,%r9 jne - vaddpd %zmm3,%zmm0,%zmm0 - vaddpd %zmm2,%zmm1,%zmm1 + vaddpd %ymm3,%ymm0,%ymm0 + vaddpd %ymm2,%ymm1,%ymm1 inc %rax shl $something,%rax - vaddpd %zmm1,%zmm0,%zmm0 + vaddpd %ymm1,%ymm0,%ymm1 movslq %r8d,%r8 cmp %rax,%r8 jle mov %rax,%rdx - nopl offset(%rax,%rax,1) - vaddpd (%rcx,%rdx,8),%zmm0,%zmm0 + nopw offset(%rax,%rax,1) + vaddpd (%rcx,%rdx,8),%ymm1,%ymm1 add $something,%rdx cmp %rdx,%r8 jg @@ -65,12 +65,10 @@ sub %rax,%r8 and $something,%r8 lea offset(%rax,%r8,1),%rax - vshuff64x2 $something,%zmm0,%zmm0,%zmm1 - vaddpd %zmm0,%zmm1,%zmm1 - vpermpd $something,%zmm1,%zmm0 - vaddpd %zmm1,%zmm0,%zmm0 - vpermilpd $something,%zmm0,%zmm1 - vaddpd %zmm1,%zmm0,%zmm0 + vhaddpd %ymm1,%ymm1,%ymm1 + vmovapd %xmm1,%xmm0 + vextractf64x2 $something,%ymm1,%xmm1 + vaddpd %xmm1,%xmm0,%xmm0 cmp %rax,%rdi jle vzeroupper @@ -79,11 +77,11 @@ cmp %rax,%rdi jg jmp - nopl offset(%rax) + cs nopw offset(%rax,%rax,1) vxorpd %xmm0,%xmm0,%xmm0 ret nopl (%rax) vzeroupper ret - vxorpd %xmm0,%xmm0,%xmm0 + vxorpd %xmm1,%xmm1,%xmm1 jmp /usr/lib64/libopenblas_openmp.a/dsum_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsum_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsum_k_COOPERLAKE.o (objdump) @@ -2,25 +2,23 @@ /usr/lib64/libopenblas_openmp.a/dsum_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 4889f148 89d64885 ff0f8e39 01000048 H..H..H....9...H - 0010 85d20f8e 30010000 480faffa c5f957c0 ....0...H.....W. + 0000 4889f148 89d64885 ff0f8e11 01000048 H..H..H........H + 0010 85d20f8e 08010000 480faffa c5f957c0 ........H.....W. 0020 31c04883 fa017418 0f1f8400 00000000 1.H...t......... 0030 c5fb5804 c14801f0 4839c77f f3c36690 ..X..H..H9....f. - 0040 4189f841 89f94183 e0f84183 e1e00f8e A..A..A...A..... - 0050 00010000 4d63c949 8d41ff48 c1e80549 ....Mc.I.A.H...I - 0060 89c1c5f9 57c049c1 e1084889 ca4e8d8c ....W.I...H..N.. - 0070 09000100 0062f1fd 4828d862 f1fd4828 .....b..H(.b..H( - 0080 c862f1fd 4828d066 0f1f8400 00000000 .b..H(.f........ - 0090 62f1ed48 581262f1 f548584a 0162f1e5 b..HX.b..HXJ.b.. - 00a0 48585a02 62f1fd48 58420348 81c20001 HXZ.b..HXB.H.... - 00b0 00004939 d175d962 f1fd4858 c362f1f5 ..I9.u.b..HX.b.. - 00c0 4858ca48 ffc048c1 e00562f1 fd4858c1 HX.H..H...b..HX. - 00d0 4d63c049 39c07e27 4889c20f 1f440000 Mc.I9.~'H....D.. - 00e0 62f1fd48 5804d148 83c20849 39d07ff0 b..HX..H...I9... - 00f0 49ffc849 29c04983 e0f84a8d 44000862 I..I).I...J.D..b - 0100 f3fd4823 c8ee62f1 f54858c8 62f3fd48 ..H#..b..HX.b..H - 0110 01c14e62 f1fd4858 c162f3fd 4805c8b1 ..Nb..HX.b..H... - 0120 62f1fd48 58c14839 c77e25c5 f877c5fb b..HX.H9.~%..w.. - 0130 5804c148 01f04839 c70f8ff1 feffffe9 X..H..H9........ - 0140 f9feffff 0f1f4000 c5f957c0 c30f1f00 ......@...W..... - 0150 c5f877c3 c5f957c0 e973ffff ff ..w...W..s... + 0040 4189f841 89f94183 e0fc4183 e1f00f8e A..A..A...A..... + 0050 d8000000 4d63c949 8d41ff48 c1e80449 ....Mc.I.A.H...I + 0060 89c1c5e1 57db49c1 e1074889 ca4e8d8c ....W.I...H..N.. + 0070 09800000 00c5fd28 c3c5fd28 d3c5fd28 .......(...(...( + 0080 cb0f1f80 00000000 c5f5580a c5ed5852 ..........X...XR + 0090 20c5fd58 4240c5e5 585a6048 83ea8049 ..XB@..XZ`H...I + 00a0 39d175e4 c5fd58c3 c5f558ca 48ffc048 9.u...X...X.H..H + 00b0 c1e004c5 fd58c94d 63c04939 c07e2648 .....X.Mc.I9.~&H + 00c0 89c2660f 1f440000 c5f5580c d14883c2 ..f..D....X..H.. + 00d0 044939d0 7ff249ff c84929c0 4983e0fc .I9...I..I).I... + 00e0 4a8d4400 04c5f57c c9c5f928 c162f3fd J.D....|...(.b.. + 00f0 2819c901 c5f958c1 4839c77e 2bc5f877 (.....X.H9.~+..w + 0100 c5fb5804 c14801f0 4839c70f 8f1fffff ..X..H..H9...... + 0110 ffe927ff ffff662e 0f1f8400 00000000 ..'...f......... + 0120 c5f957c0 c30f1f00 c5f877c3 c5f157c9 ..W.......w...W. + 0130 eb85 .. /usr/lib64/libopenblas_openmp.a/dsum_k_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsum_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsum_k_COOPERLAKE.o (objdump) @@ -4,4 +4,4 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 14000000 1c000000 ................ - 0020 00000000 5d010000 00000000 00000000 ....]........... + 0020 00000000 32010000 00000000 00000000 ....2........... /usr/lib64/libopenblas_openmp.a/dsum_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsum_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsum_k_SKYLAKEX.o (disasm) @@ -32,32 +32,32 @@ lea -offset(%r9),%rax shr $something,%rax mov %rax,%r9 - vxorpd %xmm0,%xmm0,%xmm0 + vxorpd %xmm3,%xmm3,%xmm3 shl $something,%r9 mov %rcx,%rdx lea offset(%rcx,%r9,1),%r9 - vmovapd %zmm0,%zmm3 - vmovapd %zmm0,%zmm1 - vmovapd %zmm0,%zmm2 - nopw offset(%rax,%rax,1) - vaddpd (%rdx),%zmm2,%zmm2 - vaddpd offset(%rdx),%zmm1,%zmm1 - vaddpd offset(%rdx),%zmm3,%zmm3 - vaddpd offset(%rdx),%zmm0,%zmm0 - add $something,%rdx + vmovapd %ymm3,%ymm0 + vmovapd %ymm3,%ymm2 + vmovapd %ymm3,%ymm1 + nopl offset(%rax) + vaddpd (%rdx),%ymm1,%ymm1 + vaddpd offset(%rdx),%ymm2,%ymm2 + vaddpd offset(%rdx),%ymm0,%ymm0 + vaddpd offset(%rdx),%ymm3,%ymm3 + sub $something,%rdx cmp %rdx,%r9 jne - vaddpd %zmm3,%zmm0,%zmm0 - vaddpd %zmm2,%zmm1,%zmm1 + vaddpd %ymm3,%ymm0,%ymm0 + vaddpd %ymm2,%ymm1,%ymm1 inc %rax shl $something,%rax - vaddpd %zmm1,%zmm0,%zmm0 + vaddpd %ymm1,%ymm0,%ymm1 movslq %r8d,%r8 cmp %rax,%r8 jle mov %rax,%rdx - nopl offset(%rax,%rax,1) - vaddpd (%rcx,%rdx,8),%zmm0,%zmm0 + nopw offset(%rax,%rax,1) + vaddpd (%rcx,%rdx,8),%ymm1,%ymm1 add $something,%rdx cmp %rdx,%r8 jg @@ -65,12 +65,10 @@ sub %rax,%r8 and $something,%r8 lea offset(%rax,%r8,1),%rax - vshuff64x2 $something,%zmm0,%zmm0,%zmm1 - vaddpd %zmm0,%zmm1,%zmm1 - vpermpd $something,%zmm1,%zmm0 - vaddpd %zmm1,%zmm0,%zmm0 - vpermilpd $something,%zmm0,%zmm1 - vaddpd %zmm1,%zmm0,%zmm0 + vhaddpd %ymm1,%ymm1,%ymm1 + vmovapd %xmm1,%xmm0 + vextractf64x2 $something,%ymm1,%xmm1 + vaddpd %xmm1,%xmm0,%xmm0 cmp %rax,%rdi jle vzeroupper @@ -79,11 +77,11 @@ cmp %rax,%rdi jg jmp - nopl offset(%rax) + cs nopw offset(%rax,%rax,1) vxorpd %xmm0,%xmm0,%xmm0 ret nopl (%rax) vzeroupper ret - vxorpd %xmm0,%xmm0,%xmm0 + vxorpd %xmm1,%xmm1,%xmm1 jmp /usr/lib64/libopenblas_openmp.a/dsum_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsum_k_SKYLAKEX.o (objdump) @@ -2,25 +2,23 @@ /usr/lib64/libopenblas_openmp.a/dsum_k_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 4889f148 89d64885 ff0f8e39 01000048 H..H..H....9...H - 0010 85d20f8e 30010000 480faffa c5f957c0 ....0...H.....W. + 0000 4889f148 89d64885 ff0f8e11 01000048 H..H..H........H + 0010 85d20f8e 08010000 480faffa c5f957c0 ........H.....W. 0020 31c04883 fa017418 0f1f8400 00000000 1.H...t......... 0030 c5fb5804 c14801f0 4839c77f f3c36690 ..X..H..H9....f. - 0040 4189f841 89f94183 e0f84183 e1e00f8e A..A..A...A..... - 0050 00010000 4d63c949 8d41ff48 c1e80549 ....Mc.I.A.H...I - 0060 89c1c5f9 57c049c1 e1084889 ca4e8d8c ....W.I...H..N.. - 0070 09000100 0062f1fd 4828d862 f1fd4828 .....b..H(.b..H( - 0080 c862f1fd 4828d066 0f1f8400 00000000 .b..H(.f........ - 0090 62f1ed48 581262f1 f548584a 0162f1e5 b..HX.b..HXJ.b.. - 00a0 48585a02 62f1fd48 58420348 81c20001 HXZ.b..HXB.H.... - 00b0 00004939 d175d962 f1fd4858 c362f1f5 ..I9.u.b..HX.b.. - 00c0 4858ca48 ffc048c1 e00562f1 fd4858c1 HX.H..H...b..HX. - 00d0 4d63c049 39c07e27 4889c20f 1f440000 Mc.I9.~'H....D.. - 00e0 62f1fd48 5804d148 83c20849 39d07ff0 b..HX..H...I9... - 00f0 49ffc849 29c04983 e0f84a8d 44000862 I..I).I...J.D..b - 0100 f3fd4823 c8ee62f1 f54858c8 62f3fd48 ..H#..b..HX.b..H - 0110 01c14e62 f1fd4858 c162f3fd 4805c8b1 ..Nb..HX.b..H... - 0120 62f1fd48 58c14839 c77e25c5 f877c5fb b..HX.H9.~%..w.. - 0130 5804c148 01f04839 c70f8ff1 feffffe9 X..H..H9........ - 0140 f9feffff 0f1f4000 c5f957c0 c30f1f00 ......@...W..... - 0150 c5f877c3 c5f957c0 e973ffff ff ..w...W..s... + 0040 4189f841 89f94183 e0fc4183 e1f00f8e A..A..A...A..... + 0050 d8000000 4d63c949 8d41ff48 c1e80449 ....Mc.I.A.H...I + 0060 89c1c5e1 57db49c1 e1074889 ca4e8d8c ....W.I...H..N.. + 0070 09800000 00c5fd28 c3c5fd28 d3c5fd28 .......(...(...( + 0080 cb0f1f80 00000000 c5f5580a c5ed5852 ..........X...XR + 0090 20c5fd58 4240c5e5 585a6048 83ea8049 ..XB@..XZ`H...I + 00a0 39d175e4 c5fd58c3 c5f558ca 48ffc048 9.u...X...X.H..H + 00b0 c1e004c5 fd58c94d 63c04939 c07e2648 .....X.Mc.I9.~&H + 00c0 89c2660f 1f440000 c5f5580c d14883c2 ..f..D....X..H.. + 00d0 044939d0 7ff249ff c84929c0 4983e0fc .I9...I..I).I... + 00e0 4a8d4400 04c5f57c c9c5f928 c162f3fd J.D....|...(.b.. + 00f0 2819c901 c5f958c1 4839c77e 2bc5f877 (.....X.H9.~+..w + 0100 c5fb5804 c14801f0 4839c70f 8f1fffff ..X..H..H9...... + 0110 ffe927ff ffff662e 0f1f8400 00000000 ..'...f......... + 0120 c5f957c0 c30f1f00 c5f877c3 c5f157c9 ..W.......w...W. + 0130 eb85 .. /usr/lib64/libopenblas_openmp.a/dsum_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsum_k_SKYLAKEX.o (objdump) @@ -4,4 +4,4 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 14000000 1c000000 ................ - 0020 00000000 5d010000 00000000 00000000 ....]........... + 0020 00000000 32010000 00000000 00000000 ....2........... /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_COOPERLAKE.o (disasm) @@ -10,497 +10,79 @@ push %r13 push %r12 push %rbp + mov %rdi,%rbp push %rbx - sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,-offset(%rsp) - mov %rdx,(%rsp) - mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) - mov %r9,offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %r9,-offset(%rsp) + mov %rsi,-offset(%rsp) + mov offset(%rsp),%r12 test %rsi,%rsi jle - mov %rcx,%r14 - mov %r9,%rax - imul %r14,%rax - mov %rdx,%r11 - mov %rsi,%r10 + mov %rcx,%rax + imul %r8,%rax + mov %r9,%r15 + lea offset(,%rcx,8),%r10 + add %r15,%rax + imul %rcx,%r15 + lea (%rdx,%rax,8),%r14 + mov %r8,%rbx + mov %r15,%rax add %r8,%rax - lea (%r11,%rax,8),%rax - mov %rax,-offset(%rsp) - mov %r14,%rax - shl $something,%rax + lea (%rdx,%rax,8),%r13 + lea (%r8,%rsi,4),%rax mov %rax,-offset(%rsp) mov %r10,%rax - shl $something,%rax - add %r8,%rax - mov %rax,-offset(%rsp) - mov %r14,%rax + neg %rax + lea offset(%r8),%rdx imul %r8,%rax - mov %r9,%rdx - lea offset(,%rcx,8),%rsi - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %r8,%rcx - sub %r9,%rcx - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %rcx,-offset(%rsp) - sub %rdi,%rcx - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %rdi,%r9 - mov %rcx,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax + imul %r10,%rdx + sub %r9,%rbx mov %r8,-offset(%rsp) - movq $something,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - shl $something,%r9 - mov %r9,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax + lea (%rdx,%rax,1),%rdi + lea offset(%r8),%rdx + imul %r10,%rdx + mov %rdi,-offset(%rsp) + mov %rcx,%r9 + lea (%rdx,%rax,1),%rdi + lea offset(%r8),%rdx + imul %r10,%rdx + mov %rdi,-offset(%rsp) + mov %rbx,%r11 add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - mov -offset(%rsp),%rax - mov %rax,%rdx - test %rax,%rax - jle - mov -offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - lea offset(%rax),%rcx - mov -offset(%rsp),%rax - add $something,%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - lea offset(%rax),%r8 - mov -offset(%rsp),%rax - lea offset(%rax),%r9 - mov -offset(%rsp),%rax - lea offset(%rax),%r10 - mov -offset(%rsp),%rax - lea offset(%rax),%r11 - mov -offset(%rsp),%rax - lea offset(%rax),%rbx - mov -offset(%rsp),%rax - lea offset(%rax),%rbp - mov -offset(%rsp),%rax - lea offset(%rax),%r12 - mov -offset(%rsp),%rax - lea offset(%rax),%r13 - mov -offset(%rsp),%rax - lea offset(%rax),%r14 - mov -offset(%rsp),%rax - lea offset(%rax),%r15 - mov -offset(%rsp),%rax - lea offset(%rax),%rdi - cmpq $something,-offset(%rsp) - mov offset(%rsp),%rax - jle - mov %rdx,-offset(%rsp) /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_COOPERLAKE.o (objdump) @@ -2,217 +2,57 @@ /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ecb00000 AWAVAUATUSH..... - 0010 004889b4 24900000 0048c1fe 0448897c .H..$....H...H.| - 0020 24e04889 14244889 4c24084c 89442410 $.H..$H.L$.L.D$. - 0030 4c894c24 184889b4 24a80000 004885f6 L.L$.H..$....H.. - 0040 0f8ee504 00004989 ce4c89c8 490fafc6 ......I..L..I... - 0050 4989d349 89f24c01 c0498d04 c3488944 I..I..L..I...H.D - 0060 24b84c89 f048c1e0 07488944 24e84c89 $.L..H...H.D$.L. - 0070 d048c1e0 044c01c0 48894424 f04c89f0 .H...L..H.D$.L.. - 0080 490fafc0 4c89ca48 8d34cd00 00000048 I...L..H.4.....H - 0090 01d0498d 04c34889 8424a000 0000498d ..I...H..$....I. - 00a0 4001490f afc64c89 c14c29c9 4801d049 @.I...L..L).H..I - 00b0 8d04c348 89842498 00000049 8d400249 ...H..$....I.@.I - 00c0 0fafc648 894c24b0 4829f948 01d0498d ...H.L$.H).H..I. - 00d0 04c34889 44242849 8d400349 0fafc649 ..H.D$(I.@.I...I - 00e0 89f94889 4c24c048 01d0498d 04c34889 ..H.L$.H..I...H. - 00f0 44243049 8d400449 0fafc64c 894424d0 D$0I.@.I...L.D$. - 0100 48c74424 c8000000 004801d0 498d04c3 H.D$.....H..I... - 0110 48894424 38498d40 05490faf c64801d0 H.D$8I.@.I...H.. - 0120 498d04c3 48894424 20498d40 06490faf I...H.D$ I.@.I.. - 0130 c64801d0 498d04c3 48894424 40498d40 .H..I...H.D$@I.@ - 0140 07490faf c64801d0 498d04c3 48894424 .I...H..I...H.D$ - 0150 48498d40 08490faf c64801d0 498d04c3 HI.@.I...H..I... - 0160 48894424 50498d40 09490faf c64801d0 H.D$PI.@.I...H.. - 0170 498d04c3 48894424 58498d40 0a490faf I...H.D$XI.@.I.. - 0180 c64801d0 498d04c3 48894424 60498d40 .H..I...H.D$`I.@ - 0190 0b490faf c64801d0 498d04c3 48894424 .I...H..I...H.D$ - 01a0 68498d40 0c490faf c64801d0 498d04c3 hI.@.I...H..I... - 01b0 48898424 80000000 498d400d 490fafc6 H..$....I.@.I... - 01c0 49c1e107 4c894c24 f84801d0 498d04c3 I...L.L$.H..I... - 01d0 48894424 70498d40 0e490faf c64801d0 H.D$pI.@.I...H.. - 01e0 498d04c3 48894424 78498d40 0f490faf I...H.D$xI.@.I.. - 01f0 c64801d0 498d04c3 48898424 88000000 .H..I...H..$.... - 0200 488b4424 b04889c2 4885c00f 8e9f0400 H.D$.H..H....... - 0210 00488b44 24b84889 44249848 8b4424b8 .H.D$.H.D$.H.D$. - 0220 4883c008 48894424 a0488b44 24b8488d H...H.D$.H.D$.H. - 0230 4810488b 4424b848 83c01848 89442488 H.H.D$.H...H.D$. - 0240 488b4424 b84883c0 20488944 2490488b H.D$.H.. H.D$.H. - 0250 4424b84c 8d402848 8b4424b8 4c8d4830 D$.L.@(H.D$.L.H0 - 0260 488b4424 b84c8d50 38488b44 24b84c8d H.D$.L.P8H.D$.L. - 0270 5840488b 4424b848 8d584848 8b4424b8 X@H.D$.H.XHH.D$. - 0280 488d6850 488b4424 b84c8d60 58488b44 H.hPH.D$.L.`XH.D - 0290 24b84c8d 6860488b 4424b84c 8d706848 $.L.h`H.D$.L.phH - 02a0 8b4424b8 4c8d7870 488b4424 b8488d78 .D$.L.xpH.D$.H.x - 02b0 7848837c 24e00048 8b8424e8 0000000f xH.|$..H..$..... - 02c0 8e1b0200 00488954 24d84889 7c24a848 .....H.T$.H.|$.H - 02d0 89f2488b 7424d8e9 9f000000 0f1f4000 ..H.t$........@. - 02e0 48015424 98480154 24a04801 d1480154 H.T$.H.T$.H..H.T - 02f0 24884801 54249049 01d04901 d14901d2 $.H.T$.I..I..I.. - 0300 4901d348 01d34801 d54901d4 4901d549 I..H..H..I..I..I - 0310 01d64901 d7480154 24a848ff cec57b11 ..I..H.T$.H...{. - 0320 38c57b11 7008c57b 116810c5 7b116018 8.{.p..{.h..{.`. - 0330 c57b1158 20c57b11 5028c57b 114830c5 .{.X .{.P(.{.H0. - 0340 7b114038 c5fb1178 40c5fb11 7048c5fb {.@8...x@...pH.. - 0350 116850c5 fb116058 c5fb1158 60c5fb11 .hP...`X...X`... - 0360 5068c5fb 114870c5 fb114078 4883e880 Ph...Hp...@xH... - 0370 483b7424 c00f8455 01000048 8b7c2498 H;t$...U...H.|$. - 0380 c57b1029 c57b103f 488b7c24 a0c4417b .{.).{.?H.|$..A{ - 0390 1010c57b 1037488b 7c2488c4 417b1009 ...{.7H.|$..A{.. - 03a0 c57b1027 488b7c24 90c4417b 1002c57b .{.'H.|$..A{...{ - 03b0 101f488b 7c24a8c4 c17b103b c5fb1033 ..H.|$...{.;...3 - 03c0 c5fb106d 00c4c17b 102424c4 c17b105d ...m...{.$$..{.] - 03d0 00c4c17b 1016c4c1 7b100fc5 fb100748 ...{....{......H - 03e0 85f60f8f f8feffff 48834424 98084885 ........H.D$..H. - 03f0 f60f84ee feffff48 834424a0 084883fe .......H.D$..H.. - 0400 ff0f84e3 feffff48 83c10848 83fefe0f .......H...H.... - 0410 84d8feff ff488344 24880848 83fefd0f .....H.D$..H.... - 0420 84cdfeff ff488344 24900848 83fefc0f .....H.D$..H.... - 0430 84c2feff ff4983c0 084883fe fb0f84b7 .....I...H...... - 0440 feffff49 83c10848 83fefa0f 84acfeff ...I...H........ - 0450 ff4983c2 084883fe f90f84a1 feffff49 .I...H.........I - 0460 83c30848 83fef80f 8496feff ff4883c3 ...H.........H.. - 0470 084883fe f70f848b feffff48 83c50848 .H.........H...H - 0480 83fef60f 8480feff ff4983c4 084883fe .........I...H.. - 0490 f50f8475 feffff49 83c50848 83fef40f ...u...I...H.... - 04a0 846afeff ff4983c6 084883fe f30f845f .j...I...H....._ - 04b0 feffff49 83c70848 83fef20f 8454feff ...I...H.....T.. - 04c0 ff488344 24a808e9 4efeffff 0f1f4000 .H.D$...N.....@. - 04d0 488b4424 f84889d6 48018424 e8000000 H.D$.H..H..$.... - 04e0 48834424 d010488b 5c24e848 834424b0 H.D$..H.\$.H.D$. - 04f0 1048836c 24b88048 8b4424d0 48834424 .H.l$..H.D$.H.D$ - 0500 c0104801 5c24c848 394424f0 0f85eefc ..H.\$.H9D$..... - 0510 ffff488b 8424a800 0000488b 5c241048 ..H..$....H.\$.H - 0520 c1e00448 01d84889 442410f6 84249000 ...H..H.D$...$.. - 0530 0000080f 84070300 00488b5c 2410488b .........H.\$.H. - 0540 44241848 89da4829 c24885d2 0f8e4f05 D$.H..H).H....O. - 0550 0000480f af442408 4801d848 8b1c244c ..H..D$.H..H..$L - 0560 8d04c348 8b1c244c 8d4cc308 488b1c24 ...H..$L.L..H..$ - 0570 488d74c3 10488b0c 244c8d54 c118488b H.t..H..$L.T..H. - 0580 0c244c8d 5cc12048 8b0c2448 8d5cc128 .$L.\. H..$H.\.( - 0590 488b0c24 488d6cc1 30488b0c 24488d7c H..$H.l.0H..$H.| - 05a0 c138488b 4424084c 8b7c24e0 4989d448 .8H.D$.L.|$.I..H - 05b0 8d0cc500 0000004d 29fc488b 8424e800 .......M).H..$.. - 05c0 00004d85 ff7f58e9 6e020000 0f1f4000 ..M...X.n.....@. - 05d0 4901c849 01c94801 ce4901ca 4901cb48 I..I..H..I..I..H - 05e0 01cb4801 cd4801cf 48ffcac5 fb1138c5 ..H..H..H.....8. - 05f0 fb117008 c5fb1168 10c5fb11 6018c5fb ..p....h....`... - 0600 115820c5 fb115028 c5fb1148 30c5fb11 .X ...P(...H0... - 0610 40384883 c0404939 d40f840a 020000c4 @8H..@I9........ - 0620 c17b1038 c4c17b10 31c5fb10 2ec4c17b .{.8..{.1......{ - 0630 1022c4c1 7b101bc5 fb1013c5 fb104d00 ."..{.........M. - 0640 c5fb1007 4885d27f 874983c0 084885d2 ....H....I...H.. - 0650 74814983 c1084883 faff0f84 76ffffff t.I...H.....v... - 0660 4883c608 4883fafe 0f846bff ffff4983 H...H.....k...I. - 0670 c2084883 fafd0f84 60ffffff 4983c308 ..H.....`...I... - 0680 4883fafc 0f8455ff ffff4883 c3084883 H.....U...H...H. - 0690 fafb0f84 4affffff 4883c508 4883fafa ....J...H...H... - 06a0 0f843fff ffff4883 c708e939 ffffff90 ..?...H....9.... - 06b0 488b4424 c8480384 24a00000 0048837c H.D$.H..$....H.| - 06c0 24b00048 89442498 0f844dfb ffff488b $..H.D$...M...H. - 06d0 84249800 00004803 4424c848 837c24b0 .$....H.D$.H.|$. - 06e0 ff488944 24a00f84 3dfbffff 488b4c24 .H.D$...=...H.L$ - 06f0 2848034c 24c84883 7c24b0fe 0f8430fb (H.L$.H.|$....0. - 0700 ffff488b 44243048 034424c8 48837c24 ..H.D$0H.D$.H.|$ - 0710 b0fd4889 4424880f 8423fbff ff488b44 ..H.D$...#...H.D - 0720 24384803 4424c848 837c24b0 fc488944 $8H.D$.H.|$..H.D - 0730 24900f84 16fbffff 4c8b4424 204c0344 $.......L.D$ L.D - 0740 24c84883 7c24b0fb 0f8409fb ffff4c8b $.H.|$........L. - 0750 4c24404c 034c24c8 48837c24 b0fa0f84 L$@L.L$.H.|$.... - 0760 fcfaffff 4c8b5424 484c0354 24c84883 ....L.T$HL.T$.H. - 0770 7c24b0f9 0f84effa ffff4c8b 5c24504c |$........L.\$PL - 0780 035c24c8 48837c24 b0f80f84 e2faffff .\$.H.|$........ - 0790 488b5c24 5848035c 24c84883 7c24b0f7 H.\$XH.\$.H.|$.. - 07a0 0f84d5fa ffff488b 6c246048 036c24c8 ......H.l$`H.l$. - 07b0 48837c24 b0f60f84 c8faffff 4c8b6424 H.|$........L.d$ - 07c0 684c0364 24c84883 7c24b0f5 0f84bbfa hL.d$.H.|$...... - 07d0 ffff4c8b 6c24c84c 03ac2480 00000048 ..L.l$.L..$....H - 07e0 837c24b0 f40f84ab faffff4c 8b7424c8 .|$........L.t$. - 07f0 4c037424 7048837c 24b0f30f 849efaff L.t$pH.|$....... - 0800 ff4c8b7c 24c84c03 7c247848 837c24b0 .L.|$.L.|$xH.|$. - 0810 f20f8491 faffff48 8b7c24c8 4803bc24 .......H.|$.H..$ - 0820 88000000 e988faff ff488b44 24e048c1 .........H.D$.H. - 0830 e0064801 8424e800 00004883 44241008 ..H..$....H.D$.. - 0840 f6842490 00000004 0f84ed00 0000488b ..$...........H. - 0850 5c241048 8b442418 4889da48 29c24885 \$.H.D$.H..H).H. - 0860 d20f8e6e 03000048 0faf4424 084801d8 ...n...H..D$.H.. - 0870 488b1c24 488d3cc3 488b1c24 4c8d44c3 H..$H.<.H..$L.D. - 0880 08488b1c 24488d4c c310488b 1c24488d .H..$H.L..H..$H. - 0890 74c31848 8b442408 488b5c24 e04989d2 t..H.D$.H.\$.I.. - 08a0 4c8d0cc5 00000000 4929da48 8b8424e8 L.......I).H..$. - 08b0 00000048 85db7f33 eb7b660f 1f440000 ...H...3.{f..D.. - 08c0 4c01cf4d 01c84c01 c94c01ce 48ffcac5 L..M..L..L..H... - 08d0 fb1118c5 fb115008 c5fb1148 10c5fb11 ......P....H.... - 08e0 40184883 c0204939 d27439c5 fb101fc4 @.H.. I9.t9..... - 08f0 c17b1010 c5fb1009 c5fb1006 4885d27f .{..........H... - 0900 bf4883c7 084885d2 74b94983 c0084883 .H...H..t.I...H. - 0910 faff74b2 4883c108 4883fafe 74ab4883 ..t.H...H...t.H. - 0920 c608eba8 488b4424 e048c1e0 05480184 ....H.D$.H...H.. - 0930 24e80000 00488344 241004f6 84249000 $....H.D$....$.. - 0940 0000020f 84b50000 00488b5c 2410488b .........H.\$.H. - 0950 4c241848 89d84829 c84885c0 0f8e3702 L$.H..H).H....7. - 0960 0000480f af4c2408 4889ca48 01da488b ..H..L$.H..H..H. - 0970 1c24488d 34d3488b 1c24488d 4cd30848 .$H.4.H..$H.L..H - 0980 8b5c2408 4989c048 8d3cdd00 00000048 .\$.I..H.<.....H - 0990 8b5c24e0 488b9424 e8000000 4929d848 .\$.H..$....I).H - 09a0 85db7f27 eb52662e 0f1f8400 00000000 ...'.Rf......... - 09b0 4801fe48 01f948ff c8c5fb11 0ac5fb11 H..H..H......... - 09c0 42084883 c2104939 c0741cc5 fb100ec5 B.H...I9.t...... - 09d0 fb100148 85c07fd8 4883c608 4885c074 ...H....H...H..t - 09e0 d24883c1 08ebcf48 8b4424e0 48c1e004 .H.....H.D$.H... - 09f0 48018424 e8000000 48834424 1002f684 H..$....H.D$.... - 0a00 24900000 0001746b 488b5c24 10488b44 $.....tkH.\$.H.D - 0a10 24184889 da4829c2 4885d27e 6a480faf $.H..H).H..~jH.. - 0a20 44240848 01d8488b 1c24488d 04c3488b D$.H..H..$H...H. - 0a30 7c240848 8b5c24e0 4889d648 8b8c24e8 |$.H.\$.H..H..$. - 0a40 00000048 c1e70348 29de4885 db7e2490 ...H...H).H..~$. - 0a50 c5fb1000 4c8d0438 4883c008 4885d249 ....L..8H...H..I - 0a60 0f4fc048 ffcac5fb 11014883 c1084839 .O.H......H...H9 - 0a70 d675dd48 81c4b000 00005b5d 415c415d .u.H......[]A\A] - 0a80 415e31c0 415fc348 8b442410 488b1c24 A^1.A_.H.D$.H..$ - 0a90 480faf44 24084803 44241848 8d04c3eb H..D$.H.D$.H.... - 0aa0 8d488b44 2410488b 5c241848 0faf4424 .H.D$.H.\$.H..D$ - 0ab0 08488d0c 18488b1c 244c8d04 cb4885d2 .H...H..$L...H.. - 0ac0 0f848901 0000488b 4c241848 8b1c2448 ......H.L$.H..$H - 0ad0 03442408 4801c14c 8d0ccb48 83faff0f .D$.H..L...H.... - 0ae0 84820100 00488b5c 24184803 44240848 .....H.\$.H.D$.H - 0af0 8d0c1848 8b1c2448 8d34cb48 83fafe0f ...H..$H.4.H.... - 0b00 847a0100 00488b4c 2418488b 1c244803 .z...H.L$.H..$H. - 0b10 44240848 01c14c8d 14cb4883 fafd0f84 D$.H..L...H..... - 0b20 73010000 488b5c24 18480344 2408488d s...H.\$.H.D$.H. - 0b30 0c18488b 1c244c8d 1ccb4883 fafc0f84 ..H..$L...H..... - 0b40 6b010000 488b4c24 18488b1c 24480344 k...H.L$.H..$H.D - 0b50 24084801 c1488d1c cb4883fa fb0f8464 $.H..H...H.....d - 0b60 01000048 8b4c2418 488b3c24 48034424 ...H.L$.H.<$H.D$ - 0b70 084801c1 488d2ccf 4883fafa 0f845d01 .H..H.,.H.....]. - 0b80 0000488b 0c244803 44240848 03442418 ..H..$H.D$.H.D$. - 0b90 488d3cc1 e909faff ff488b54 2410488b H.<......H.T$.H. - 0ba0 5c241848 0faf5424 08488d0c 1a488b1c \$.H..T$.H...H.. - 0bb0 24488d34 cb4885c0 0f843901 0000488b $H.4.H....9...H. - 0bc0 0c244803 54240848 03542418 488d0cd1 .$H.T$.H.T$.H... - 0bd0 e9aafdff ff488b44 2410488b 4c241848 .....H.D$.H.L$.H - 0be0 0faf4424 08488b1c 244801c1 488d3ccb ..D$.H..$H..H.<. - 0bf0 4885d20f 84160100 00488b4c 2418488b H........H.L$.H. - 0c00 1c244803 44240848 01c14c8d 04cb4883 .$H.D$.H..L...H. - 0c10 faff0f84 0f010000 488b5c24 18480344 ........H.\$.H.D /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_COOPERLAKE.o (objdump) @@ -3,9 +3,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 570d0000 00420e10 8f02420e ....W....B....B. + 0010 1b0c0708 90010000 44000000 1c000000 ........D....... + 0020 00000000 59030000 00420e10 8f02420e ....Y....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ee80103 690a0a0e ..A.8..G....i... - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0040 8606440e 38830703 d9020a0e 30410e28 ..D.8.......0A.( + 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_SKYLAKEX.o (disasm) @@ -10,497 +10,79 @@ push %r13 push %r12 push %rbp + mov %rdi,%rbp push %rbx - sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,-offset(%rsp) - mov %rdx,(%rsp) - mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) - mov %r9,offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %r9,-offset(%rsp) + mov %rsi,-offset(%rsp) + mov offset(%rsp),%r12 test %rsi,%rsi jle - mov %rcx,%r14 - mov %r9,%rax - imul %r14,%rax - mov %rdx,%r11 - mov %rsi,%r10 + mov %rcx,%rax + imul %r8,%rax + mov %r9,%r15 + lea offset(,%rcx,8),%r10 + add %r15,%rax + imul %rcx,%r15 + lea (%rdx,%rax,8),%r14 + mov %r8,%rbx + mov %r15,%rax add %r8,%rax - lea (%r11,%rax,8),%rax - mov %rax,-offset(%rsp) - mov %r14,%rax - shl $something,%rax + lea (%rdx,%rax,8),%r13 + lea (%r8,%rsi,4),%rax mov %rax,-offset(%rsp) mov %r10,%rax - shl $something,%rax - add %r8,%rax - mov %rax,-offset(%rsp) - mov %r14,%rax + neg %rax + lea offset(%r8),%rdx imul %r8,%rax - mov %r9,%rdx - lea offset(,%rcx,8),%rsi - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %r8,%rcx - sub %r9,%rcx - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %rcx,-offset(%rsp) - sub %rdi,%rcx - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %rdi,%r9 - mov %rcx,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax + imul %r10,%rdx + sub %r9,%rbx mov %r8,-offset(%rsp) - movq $something,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - shl $something,%r9 - mov %r9,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax + lea (%rdx,%rax,1),%rdi + lea offset(%r8),%rdx + imul %r10,%rdx + mov %rdi,-offset(%rsp) + mov %rcx,%r9 + lea (%rdx,%rax,1),%rdi + lea offset(%r8),%rdx + imul %r10,%rdx + mov %rdi,-offset(%rsp) + mov %rbx,%r11 add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - mov -offset(%rsp),%rax - mov %rax,%rdx - test %rax,%rax - jle - mov -offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - lea offset(%rax),%rcx - mov -offset(%rsp),%rax - add $something,%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - lea offset(%rax),%r8 - mov -offset(%rsp),%rax - lea offset(%rax),%r9 - mov -offset(%rsp),%rax - lea offset(%rax),%r10 - mov -offset(%rsp),%rax - lea offset(%rax),%r11 - mov -offset(%rsp),%rax - lea offset(%rax),%rbx - mov -offset(%rsp),%rax - lea offset(%rax),%rbp - mov -offset(%rsp),%rax - lea offset(%rax),%r12 - mov -offset(%rsp),%rax - lea offset(%rax),%r13 - mov -offset(%rsp),%rax - lea offset(%rax),%r14 - mov -offset(%rsp),%rax - lea offset(%rax),%r15 - mov -offset(%rsp),%rax - lea offset(%rax),%rdi - cmpq $something,-offset(%rsp) - mov offset(%rsp),%rax - jle - mov %rdx,-offset(%rsp) /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_SKYLAKEX.o (objdump) @@ -2,217 +2,57 @@ /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ecb00000 AWAVAUATUSH..... - 0010 004889b4 24900000 0048c1fe 0448897c .H..$....H...H.| - 0020 24e04889 14244889 4c24084c 89442410 $.H..$H.L$.L.D$. - 0030 4c894c24 184889b4 24a80000 004885f6 L.L$.H..$....H.. - 0040 0f8ee504 00004989 ce4c89c8 490fafc6 ......I..L..I... - 0050 4989d349 89f24c01 c0498d04 c3488944 I..I..L..I...H.D - 0060 24b84c89 f048c1e0 07488944 24e84c89 $.L..H...H.D$.L. - 0070 d048c1e0 044c01c0 48894424 f04c89f0 .H...L..H.D$.L.. - 0080 490fafc0 4c89ca48 8d34cd00 00000048 I...L..H.4.....H - 0090 01d0498d 04c34889 8424a000 0000498d ..I...H..$....I. - 00a0 4001490f afc64c89 c14c29c9 4801d049 @.I...L..L).H..I - 00b0 8d04c348 89842498 00000049 8d400249 ...H..$....I.@.I - 00c0 0fafc648 894c24b0 4829f948 01d0498d ...H.L$.H).H..I. - 00d0 04c34889 44242849 8d400349 0fafc649 ..H.D$(I.@.I...I - 00e0 89f94889 4c24c048 01d0498d 04c34889 ..H.L$.H..I...H. - 00f0 44243049 8d400449 0fafc64c 894424d0 D$0I.@.I...L.D$. - 0100 48c74424 c8000000 004801d0 498d04c3 H.D$.....H..I... - 0110 48894424 38498d40 05490faf c64801d0 H.D$8I.@.I...H.. - 0120 498d04c3 48894424 20498d40 06490faf I...H.D$ I.@.I.. - 0130 c64801d0 498d04c3 48894424 40498d40 .H..I...H.D$@I.@ - 0140 07490faf c64801d0 498d04c3 48894424 .I...H..I...H.D$ - 0150 48498d40 08490faf c64801d0 498d04c3 HI.@.I...H..I... - 0160 48894424 50498d40 09490faf c64801d0 H.D$PI.@.I...H.. - 0170 498d04c3 48894424 58498d40 0a490faf I...H.D$XI.@.I.. - 0180 c64801d0 498d04c3 48894424 60498d40 .H..I...H.D$`I.@ - 0190 0b490faf c64801d0 498d04c3 48894424 .I...H..I...H.D$ - 01a0 68498d40 0c490faf c64801d0 498d04c3 hI.@.I...H..I... - 01b0 48898424 80000000 498d400d 490fafc6 H..$....I.@.I... - 01c0 49c1e107 4c894c24 f84801d0 498d04c3 I...L.L$.H..I... - 01d0 48894424 70498d40 0e490faf c64801d0 H.D$pI.@.I...H.. - 01e0 498d04c3 48894424 78498d40 0f490faf I...H.D$xI.@.I.. - 01f0 c64801d0 498d04c3 48898424 88000000 .H..I...H..$.... - 0200 488b4424 b04889c2 4885c00f 8e9f0400 H.D$.H..H....... - 0210 00488b44 24b84889 44249848 8b4424b8 .H.D$.H.D$.H.D$. - 0220 4883c008 48894424 a0488b44 24b8488d H...H.D$.H.D$.H. - 0230 4810488b 4424b848 83c01848 89442488 H.H.D$.H...H.D$. - 0240 488b4424 b84883c0 20488944 2490488b H.D$.H.. H.D$.H. - 0250 4424b84c 8d402848 8b4424b8 4c8d4830 D$.L.@(H.D$.L.H0 - 0260 488b4424 b84c8d50 38488b44 24b84c8d H.D$.L.P8H.D$.L. - 0270 5840488b 4424b848 8d584848 8b4424b8 X@H.D$.H.XHH.D$. - 0280 488d6850 488b4424 b84c8d60 58488b44 H.hPH.D$.L.`XH.D - 0290 24b84c8d 6860488b 4424b84c 8d706848 $.L.h`H.D$.L.phH - 02a0 8b4424b8 4c8d7870 488b4424 b8488d78 .D$.L.xpH.D$.H.x - 02b0 7848837c 24e00048 8b8424e8 0000000f xH.|$..H..$..... - 02c0 8e1b0200 00488954 24d84889 7c24a848 .....H.T$.H.|$.H - 02d0 89f2488b 7424d8e9 9f000000 0f1f4000 ..H.t$........@. - 02e0 48015424 98480154 24a04801 d1480154 H.T$.H.T$.H..H.T - 02f0 24884801 54249049 01d04901 d14901d2 $.H.T$.I..I..I.. - 0300 4901d348 01d34801 d54901d4 4901d549 I..H..H..I..I..I - 0310 01d64901 d7480154 24a848ff cec57b11 ..I..H.T$.H...{. - 0320 38c57b11 7008c57b 116810c5 7b116018 8.{.p..{.h..{.`. - 0330 c57b1158 20c57b11 5028c57b 114830c5 .{.X .{.P(.{.H0. - 0340 7b114038 c5fb1178 40c5fb11 7048c5fb {.@8...x@...pH.. - 0350 116850c5 fb116058 c5fb1158 60c5fb11 .hP...`X...X`... - 0360 5068c5fb 114870c5 fb114078 4883e880 Ph...Hp...@xH... - 0370 483b7424 c00f8455 01000048 8b7c2498 H;t$...U...H.|$. - 0380 c57b1029 c57b103f 488b7c24 a0c4417b .{.).{.?H.|$..A{ - 0390 1010c57b 1037488b 7c2488c4 417b1009 ...{.7H.|$..A{.. - 03a0 c57b1027 488b7c24 90c4417b 1002c57b .{.'H.|$..A{...{ - 03b0 101f488b 7c24a8c4 c17b103b c5fb1033 ..H.|$...{.;...3 - 03c0 c5fb106d 00c4c17b 102424c4 c17b105d ...m...{.$$..{.] - 03d0 00c4c17b 1016c4c1 7b100fc5 fb100748 ...{....{......H - 03e0 85f60f8f f8feffff 48834424 98084885 ........H.D$..H. - 03f0 f60f84ee feffff48 834424a0 084883fe .......H.D$..H.. - 0400 ff0f84e3 feffff48 83c10848 83fefe0f .......H...H.... - 0410 84d8feff ff488344 24880848 83fefd0f .....H.D$..H.... - 0420 84cdfeff ff488344 24900848 83fefc0f .....H.D$..H.... - 0430 84c2feff ff4983c0 084883fe fb0f84b7 .....I...H...... - 0440 feffff49 83c10848 83fefa0f 84acfeff ...I...H........ - 0450 ff4983c2 084883fe f90f84a1 feffff49 .I...H.........I - 0460 83c30848 83fef80f 8496feff ff4883c3 ...H.........H.. - 0470 084883fe f70f848b feffff48 83c50848 .H.........H...H - 0480 83fef60f 8480feff ff4983c4 084883fe .........I...H.. - 0490 f50f8475 feffff49 83c50848 83fef40f ...u...I...H.... - 04a0 846afeff ff4983c6 084883fe f30f845f .j...I...H....._ - 04b0 feffff49 83c70848 83fef20f 8454feff ...I...H.....T.. - 04c0 ff488344 24a808e9 4efeffff 0f1f4000 .H.D$...N.....@. - 04d0 488b4424 f84889d6 48018424 e8000000 H.D$.H..H..$.... - 04e0 48834424 d010488b 5c24e848 834424b0 H.D$..H.\$.H.D$. - 04f0 1048836c 24b88048 8b4424d0 48834424 .H.l$..H.D$.H.D$ - 0500 c0104801 5c24c848 394424f0 0f85eefc ..H.\$.H9D$..... - 0510 ffff488b 8424a800 0000488b 5c241048 ..H..$....H.\$.H - 0520 c1e00448 01d84889 442410f6 84249000 ...H..H.D$...$.. - 0530 0000080f 84070300 00488b5c 2410488b .........H.\$.H. - 0540 44241848 89da4829 c24885d2 0f8e4f05 D$.H..H).H....O. - 0550 0000480f af442408 4801d848 8b1c244c ..H..D$.H..H..$L - 0560 8d04c348 8b1c244c 8d4cc308 488b1c24 ...H..$L.L..H..$ - 0570 488d74c3 10488b0c 244c8d54 c118488b H.t..H..$L.T..H. - 0580 0c244c8d 5cc12048 8b0c2448 8d5cc128 .$L.\. H..$H.\.( - 0590 488b0c24 488d6cc1 30488b0c 24488d7c H..$H.l.0H..$H.| - 05a0 c138488b 4424084c 8b7c24e0 4989d448 .8H.D$.L.|$.I..H - 05b0 8d0cc500 0000004d 29fc488b 8424e800 .......M).H..$.. - 05c0 00004d85 ff7f58e9 6e020000 0f1f4000 ..M...X.n.....@. - 05d0 4901c849 01c94801 ce4901ca 4901cb48 I..I..H..I..I..H - 05e0 01cb4801 cd4801cf 48ffcac5 fb1138c5 ..H..H..H.....8. - 05f0 fb117008 c5fb1168 10c5fb11 6018c5fb ..p....h....`... - 0600 115820c5 fb115028 c5fb1148 30c5fb11 .X ...P(...H0... - 0610 40384883 c0404939 d40f840a 020000c4 @8H..@I9........ - 0620 c17b1038 c4c17b10 31c5fb10 2ec4c17b .{.8..{.1......{ - 0630 1022c4c1 7b101bc5 fb1013c5 fb104d00 ."..{.........M. - 0640 c5fb1007 4885d27f 874983c0 084885d2 ....H....I...H.. - 0650 74814983 c1084883 faff0f84 76ffffff t.I...H.....v... - 0660 4883c608 4883fafe 0f846bff ffff4983 H...H.....k...I. - 0670 c2084883 fafd0f84 60ffffff 4983c308 ..H.....`...I... - 0680 4883fafc 0f8455ff ffff4883 c3084883 H.....U...H...H. - 0690 fafb0f84 4affffff 4883c508 4883fafa ....J...H...H... - 06a0 0f843fff ffff4883 c708e939 ffffff90 ..?...H....9.... - 06b0 488b4424 c8480384 24a00000 0048837c H.D$.H..$....H.| - 06c0 24b00048 89442498 0f844dfb ffff488b $..H.D$...M...H. - 06d0 84249800 00004803 4424c848 837c24b0 .$....H.D$.H.|$. - 06e0 ff488944 24a00f84 3dfbffff 488b4c24 .H.D$...=...H.L$ - 06f0 2848034c 24c84883 7c24b0fe 0f8430fb (H.L$.H.|$....0. - 0700 ffff488b 44243048 034424c8 48837c24 ..H.D$0H.D$.H.|$ - 0710 b0fd4889 4424880f 8423fbff ff488b44 ..H.D$...#...H.D - 0720 24384803 4424c848 837c24b0 fc488944 $8H.D$.H.|$..H.D - 0730 24900f84 16fbffff 4c8b4424 204c0344 $.......L.D$ L.D - 0740 24c84883 7c24b0fb 0f8409fb ffff4c8b $.H.|$........L. - 0750 4c24404c 034c24c8 48837c24 b0fa0f84 L$@L.L$.H.|$.... - 0760 fcfaffff 4c8b5424 484c0354 24c84883 ....L.T$HL.T$.H. - 0770 7c24b0f9 0f84effa ffff4c8b 5c24504c |$........L.\$PL - 0780 035c24c8 48837c24 b0f80f84 e2faffff .\$.H.|$........ - 0790 488b5c24 5848035c 24c84883 7c24b0f7 H.\$XH.\$.H.|$.. - 07a0 0f84d5fa ffff488b 6c246048 036c24c8 ......H.l$`H.l$. - 07b0 48837c24 b0f60f84 c8faffff 4c8b6424 H.|$........L.d$ - 07c0 684c0364 24c84883 7c24b0f5 0f84bbfa hL.d$.H.|$...... - 07d0 ffff4c8b 6c24c84c 03ac2480 00000048 ..L.l$.L..$....H - 07e0 837c24b0 f40f84ab faffff4c 8b7424c8 .|$........L.t$. - 07f0 4c037424 7048837c 24b0f30f 849efaff L.t$pH.|$....... - 0800 ff4c8b7c 24c84c03 7c247848 837c24b0 .L.|$.L.|$xH.|$. - 0810 f20f8491 faffff48 8b7c24c8 4803bc24 .......H.|$.H..$ - 0820 88000000 e988faff ff488b44 24e048c1 .........H.D$.H. - 0830 e0064801 8424e800 00004883 44241008 ..H..$....H.D$.. - 0840 f6842490 00000004 0f84ed00 0000488b ..$...........H. - 0850 5c241048 8b442418 4889da48 29c24885 \$.H.D$.H..H).H. - 0860 d20f8e6e 03000048 0faf4424 084801d8 ...n...H..D$.H.. - 0870 488b1c24 488d3cc3 488b1c24 4c8d44c3 H..$H.<.H..$L.D. - 0880 08488b1c 24488d4c c310488b 1c24488d .H..$H.L..H..$H. - 0890 74c31848 8b442408 488b5c24 e04989d2 t..H.D$.H.\$.I.. - 08a0 4c8d0cc5 00000000 4929da48 8b8424e8 L.......I).H..$. - 08b0 00000048 85db7f33 eb7b660f 1f440000 ...H...3.{f..D.. - 08c0 4c01cf4d 01c84c01 c94c01ce 48ffcac5 L..M..L..L..H... - 08d0 fb1118c5 fb115008 c5fb1148 10c5fb11 ......P....H.... - 08e0 40184883 c0204939 d27439c5 fb101fc4 @.H.. I9.t9..... - 08f0 c17b1010 c5fb1009 c5fb1006 4885d27f .{..........H... - 0900 bf4883c7 084885d2 74b94983 c0084883 .H...H..t.I...H. - 0910 faff74b2 4883c108 4883fafe 74ab4883 ..t.H...H...t.H. - 0920 c608eba8 488b4424 e048c1e0 05480184 ....H.D$.H...H.. - 0930 24e80000 00488344 241004f6 84249000 $....H.D$....$.. - 0940 0000020f 84b50000 00488b5c 2410488b .........H.\$.H. - 0950 4c241848 89d84829 c84885c0 0f8e3702 L$.H..H).H....7. - 0960 0000480f af4c2408 4889ca48 01da488b ..H..L$.H..H..H. - 0970 1c24488d 34d3488b 1c24488d 4cd30848 .$H.4.H..$H.L..H - 0980 8b5c2408 4989c048 8d3cdd00 00000048 .\$.I..H.<.....H - 0990 8b5c24e0 488b9424 e8000000 4929d848 .\$.H..$....I).H - 09a0 85db7f27 eb52662e 0f1f8400 00000000 ...'.Rf......... - 09b0 4801fe48 01f948ff c8c5fb11 0ac5fb11 H..H..H......... - 09c0 42084883 c2104939 c0741cc5 fb100ec5 B.H...I9.t...... - 09d0 fb100148 85c07fd8 4883c608 4885c074 ...H....H...H..t - 09e0 d24883c1 08ebcf48 8b4424e0 48c1e004 .H.....H.D$.H... - 09f0 48018424 e8000000 48834424 1002f684 H..$....H.D$.... - 0a00 24900000 0001746b 488b5c24 10488b44 $.....tkH.\$.H.D - 0a10 24184889 da4829c2 4885d27e 6a480faf $.H..H).H..~jH.. - 0a20 44240848 01d8488b 1c24488d 04c3488b D$.H..H..$H...H. - 0a30 7c240848 8b5c24e0 4889d648 8b8c24e8 |$.H.\$.H..H..$. - 0a40 00000048 c1e70348 29de4885 db7e2490 ...H...H).H..~$. - 0a50 c5fb1000 4c8d0438 4883c008 4885d249 ....L..8H...H..I - 0a60 0f4fc048 ffcac5fb 11014883 c1084839 .O.H......H...H9 - 0a70 d675dd48 81c4b000 00005b5d 415c415d .u.H......[]A\A] - 0a80 415e31c0 415fc348 8b442410 488b1c24 A^1.A_.H.D$.H..$ - 0a90 480faf44 24084803 44241848 8d04c3eb H..D$.H.D$.H.... - 0aa0 8d488b44 2410488b 5c241848 0faf4424 .H.D$.H.\$.H..D$ - 0ab0 08488d0c 18488b1c 244c8d04 cb4885d2 .H...H..$L...H.. - 0ac0 0f848901 0000488b 4c241848 8b1c2448 ......H.L$.H..$H - 0ad0 03442408 4801c14c 8d0ccb48 83faff0f .D$.H..L...H.... - 0ae0 84820100 00488b5c 24184803 44240848 .....H.\$.H.D$.H - 0af0 8d0c1848 8b1c2448 8d34cb48 83fafe0f ...H..$H.4.H.... - 0b00 847a0100 00488b4c 2418488b 1c244803 .z...H.L$.H..$H. - 0b10 44240848 01c14c8d 14cb4883 fafd0f84 D$.H..L...H..... - 0b20 73010000 488b5c24 18480344 2408488d s...H.\$.H.D$.H. - 0b30 0c18488b 1c244c8d 1ccb4883 fafc0f84 ..H..$L...H..... - 0b40 6b010000 488b4c24 18488b1c 24480344 k...H.L$.H..$H.D - 0b50 24084801 c1488d1c cb4883fa fb0f8464 $.H..H...H.....d - 0b60 01000048 8b4c2418 488b3c24 48034424 ...H.L$.H.<$H.D$ - 0b70 084801c1 488d2ccf 4883fafa 0f845d01 .H..H.,.H.....]. - 0b80 0000488b 0c244803 44240848 03442418 ..H..$H.D$.H.D$. - 0b90 488d3cc1 e909faff ff488b54 2410488b H.<......H.T$.H. - 0ba0 5c241848 0faf5424 08488d0c 1a488b1c \$.H..T$.H...H.. - 0bb0 24488d34 cb4885c0 0f843901 0000488b $H.4.H....9...H. - 0bc0 0c244803 54240848 03542418 488d0cd1 .$H.T$.H.T$.H... - 0bd0 e9aafdff ff488b44 2410488b 4c241848 .....H.D$.H.L$.H - 0be0 0faf4424 08488b1c 244801c1 488d3ccb ..D$.H..$H..H.<. - 0bf0 4885d20f 84160100 00488b4c 2418488b H........H.L$.H. - 0c00 1c244803 44240848 01c14c8d 04cb4883 .$H.D$.H..L...H. - 0c10 faff0f84 0f010000 488b5c24 18480344 ........H.\$.H.D /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_iltcopy_SKYLAKEX.o (objdump) @@ -3,9 +3,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 570d0000 00420e10 8f02420e ....W....B....B. + 0010 1b0c0708 90010000 44000000 1c000000 ........D....... + 0020 00000000 59030000 00420e10 8f02420e ....Y....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ee80103 690a0a0e ..A.8..G....i... - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0040 8606440e 38830703 d9020a0e 30410e28 ..D.8.......0A.( + 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_COOPERLAKE.o (disasm) @@ -10,525 +10,70 @@ push %r13 push %r12 push %rbp + mov %rdi,%rbp push %rbx - sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,-offset(%rsp) - mov %rdx,(%rsp) - mov %rcx,offset(%rsp) - mov %r8,-offset(%rsp) - mov %r9,offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %r9,-offset(%rsp) + mov %rsi,-offset(%rsp) + mov offset(%rsp),%r12 test %rsi,%rsi jle - mov %rcx,%r14 mov %r9,%rax - imul %r14,%rax - mov %rdx,%r11 - mov %rsi,%r10 + imul %rcx,%rax + mov %r8,%rbx + sub %r9,%rbx add %r8,%rax - lea offset(,%rcx,8),%rsi - mov %r8,%rcx - sub %r9,%rcx - lea (%r11,%rax,8),%rax - mov %rax,-offset(%rsp) - mov %rcx,%rax - sub %rdi,%rax - mov %rax,-offset(%rsp) - mov %r14,%rax - shl $something,%rax - mov %rax,-offset(%rsp) - mov %r10,%rax - shl $something,%rax - add %rcx,%rax - mov %rax,-offset(%rsp) - mov %r14,%rax - imul %r8,%rax - mov %r9,%rdx - mov %rdi,%r9 - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %rcx,-offset(%rsp) - movq $something,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) + lea (%rdx,%rax,8),%r14 lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - shl $something,%r9 - mov %r9,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - nopl offset(%rax,%rax,1) - mov -offset(%rsp),%rax - mov %rax,%rdx - test %rax,%rax - jle - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rcx - add offset(%rsp),%rcx - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%r8 - add offset(%rsp),%r8 - mov -offset(%rsp),%r9 - add offset(%rsp),%r9 - mov -offset(%rsp),%r10 - add offset(%rsp),%r10 - mov -offset(%rsp),%r11 - add offset(%rsp),%r11 - mov -offset(%rsp),%rbx - add offset(%rsp),%rbx - mov -offset(%rsp),%rbp - add offset(%rsp),%rbp - mov -offset(%rsp),%r12 - add offset(%rsp),%r12 - mov -offset(%rsp),%r13 - add offset(%rsp),%r13 - mov -offset(%rsp),%r14 - add offset(%rsp),%r14 - mov -offset(%rsp),%r15 - add offset(%rsp),%r15 - mov -offset(%rsp),%rdi - add offset(%rsp),%rdi - cmpq $something,-offset(%rsp) - mov offset(%rsp),%rax - jle - mov %rdx,-offset(%rsp) + imul %rcx,%rax + lea offset(,%rcx,8),%r10 + mov %r8,-offset(%rsp) + add %r9,%rax + lea (%rdx,%rax,8),%r13 + lea (%rbx,%rsi,4),%rax + mov %rax,-offset(%rsp) + mov %r8,%rax + neg %rax + lea -offset(,%rax,8),%rax + mov %r10,%rdx + imul %rcx,%rax + imul %r8,%rdx + mov %rcx,%r15 + mov %rbx,%r11 + lea (%rdx,%rax,1),%rdi + lea offset(%r8),%rdx + imul %r10,%rdx mov %rdi,-offset(%rsp) /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_COOPERLAKE.o (objdump) @@ -2,206 +2,56 @@ /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 eca80000 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 0448897c .H..$....H...H.| - 0020 24d84889 14244889 4c24084c 894424e0 $.H..$H.L$.L.D$. - 0030 4c894c24 104889b4 24a00000 004885f6 L.L$.H..$....H.. - 0040 0f8eff04 00004989 ce4c89c8 490fafc6 ......I..L..I... - 0050 4989d349 89f24c01 c0488d34 cd000000 I..I..L..H.4.... - 0060 004c89c1 4c29c949 8d04c348 894424c8 .L..L).I...H.D$. - 0070 4889c848 29f84889 4424c04c 89f048c1 H..H).H.D$.L..H. - 0080 e0074889 4424e84c 89d048c1 e0044801 ..H.D$.L..H...H. - 0090 c8488944 24f04c89 f0490faf c04c89ca .H.D$.L..I...L.. - 00a0 4989f948 01d0498d 04c34889 44241849 I..H..I...H.D$.I - 00b0 8d400149 0fafc648 894c24b0 48c74424 .@.I...H.L$.H.D$ - 00c0 b8000000 004801d0 498d04c3 48894424 .....H..I...H.D$ - 00d0 20498d40 02490faf c64801d0 498d04c3 I.@.I...H..I... - 00e0 48894424 28498d40 03490faf c64801d0 H.D$(I.@.I...H.. - 00f0 498d04c3 48894424 60498d40 04490faf I...H.D$`I.@.I.. - 0100 c64801d0 498d04c3 48894424 70498d40 .H..I...H.D$pI.@ - 0110 05490faf c64801d0 498d04c3 48898424 .I...H..I...H..$ - 0120 88000000 498d4006 490fafc6 4801d049 ....I.@.I...H..I - 0130 8d04c348 89842490 00000049 8d400749 ...H..$....I.@.I - 0140 0fafc648 01d0498d 04c34889 44246849 ...H..I...H.D$hI - 0150 8d400849 0fafc648 01d0498d 04c34889 .@.I...H..I...H. - 0160 44247849 8d400949 0fafc648 01d0498d D$xI.@.I...H..I. - 0170 04c34889 84248000 0000498d 400a490f ..H..$....I.@.I. - 0180 afc64801 d0498d04 c3488944 2458498d ..H..I...H.D$XI. - 0190 400b490f afc64801 d0498d04 c3488944 @.I...H..I...H.D - 01a0 2450498d 400c490f afc64801 d0498d04 $PI.@.I...H..I.. - 01b0 c3488944 2448498d 400d490f afc649c1 .H.D$HI.@.I...I. - 01c0 e1074c89 4c24f848 01d0498d 04c34889 ..L.L$.H..I...H. - 01d0 44243049 8d400e49 0fafc648 01d0498d D$0I.@.I...H..I. - 01e0 04c34889 44244049 8d400f49 0fafc648 ..H.D$@I.@.I...H - 01f0 01d0498d 04c34889 4424380f 1f440000 ..I...H.D$8..D.. - 0200 488b4424 b04889c2 4885c00f 8e4f0500 H.D$.H..H....O.. - 0210 00488b44 24b84803 44241848 89442498 .H.D$.H.D$.H.D$. - 0220 488b4424 b8480344 24204889 4424a048 H.D$.H.D$ H.D$.H - 0230 8b4c24b8 48034c24 28488b44 24b84803 .L$.H.L$(H.D$.H. - 0240 44246048 89442488 488b4424 b8480344 D$`H.D$.H.D$.H.D - 0250 24704889 4424904c 8b4424b8 4c038424 $pH.D$.L.D$.L..$ - 0260 88000000 4c8b4c24 b84c038c 24900000 ....L.L$.L..$... - 0270 004c8b54 24b84c03 5424684c 8b5c24b8 .L.T$.L.T$hL.\$. - 0280 4c035c24 78488b5c 24b84803 9c248000 L.\$xH.\$.H..$.. - 0290 0000488b 6c24b848 036c2458 4c8b6424 ..H.l$.H.l$XL.d$ - 02a0 b84c0364 24504c8b 6c24b84c 036c2448 .L.d$PL.l$.L.l$H - 02b0 4c8b7424 b84c0374 24304c8b 7c24b84c L.t$.L.t$0L.|$.L - 02c0 037c2440 488b7c24 b848037c 24384883 .|$@H.|$.H.|$8H. - 02d0 7c24d800 488b8424 e0000000 0f8e1e02 |$..H..$........ - 02e0 00004889 5424d048 897c24a8 4889f248 ..H.T$.H.|$.H..H - 02f0 8b7424d0 e9b20000 000f1f80 00000000 .t$............. - 0300 48834424 98084883 4424a008 4883c108 H.D$..H.D$..H... - 0310 48834424 88084883 44249008 4983c008 H.D$..H.D$..I... - 0320 4983c108 4983c208 4983c308 4883c308 I...I...I...H... - 0330 4883c508 4983c408 4983c508 4983c608 H...I...I...I... - 0340 4983c708 48834424 a80848ff cec57b11 I...H.D$..H...{. - 0350 38c57b11 7008c57b 116810c5 7b116018 8.{.p..{.h..{.`. - 0360 c57b1158 20c57b11 5028c57b 114830c5 .{.X .{.P(.{.H0. - 0370 7b114038 c5fb1178 40c5fb11 7048c5fb {.@8...x@...pH.. - 0380 116850c5 fb116058 c5fb1158 60c5fb11 .hP...`X...X`... - 0390 5068c5fb 114870c5 fb114078 4883e880 Ph...Hp...@xH... - 03a0 48397424 c00f8445 01000048 8b7c2498 H9t$...E...H.|$. - 03b0 c57b1029 c57b103f 488b7c24 a0c4417b .{.).{.?H.|$..A{ - 03c0 1010c57b 1037488b 7c2488c4 417b1009 ...{.7H.|$..A{.. - 03d0 c57b1027 488b7c24 90c4417b 1002c57b .{.'H.|$..A{...{ - 03e0 101f488b 7c24a8c4 c17b103b c5fb1033 ..H.|$...{.;...3 - 03f0 c5fb106d 00c4c17b 102424c4 c17b105d ...m...{.$$..{.] - 0400 00c4c17b 1016c4c1 7b100fc5 fb100748 ...{....{......H - 0410 85f60f8f e8feffff 48015424 984885f6 ........H.T$.H.. - 0420 0f84e0fe ffff4801 5424a048 83feff0f ......H.T$.H.... - 0430 84d7feff ff4801d1 4883fefe 0f84cefe .....H..H....... - 0440 ffff4801 54248848 83fefd0f 84c5feff ..H.T$.H........ - 0450 ff480154 24904883 fefc0f84 bcfeffff .H.T$.H......... - 0460 4901d048 83fefb0f 84b3feff ff4901d1 I..H.........I.. - 0470 4883fefa 0f84aafe ffff4901 d24883fe H.........I..H.. - 0480 f90f84a1 feffff49 01d34883 fef80f84 .......I..H..... - 0490 98feffff 4801d348 83fef70f 848ffeff ....H..H........ - 04a0 ff4801d5 4883fef6 0f8486fe ffff4901 .H..H.........I. - 04b0 d44883fe f50f847d feffff49 01d54883 .H.....}...I..H. - 04c0 fef40f84 74feffff 4901d648 83fef30f ....t...I..H.... - 04d0 846bfeff ff4901d7 4883fef2 0f8462fe .k...I..H.....b. - 04e0 ffff4801 5424a8e9 5efeffff 0f1f4000 ..H.T$..^.....@. - 04f0 488b4424 f84889d6 48018424 e0000000 H.D$.H..H..$.... - 0500 48834424 b010488b 5c24e848 836c24c8 H.D$..H.\$.H.l$. - 0510 80488344 24c01048 8b4424b0 48015c24 .H.D$..H.D$.H.\$ - 0520 b8483b44 24f00f85 d4fcffff 488b8424 .H;D$.......H..$ - 0530 a0000000 488b4c24 e048c1e0 044801c8 ....H.L$.H...H.. - 0540 48894424 e0f68424 98000000 080f8477 H.D$...$.......w - 0550 03000048 8b4424e0 488b4c24 104889c2 ...H.D$.H.L$.H.. - 0560 4829ca48 85d20f8e 04060000 480faf44 H).H........H..D - 0570 24084801 c8488b0c 244c8d04 c1488b44 $.H..H..$L...H.D - 0580 24e0488b 0c2448ff c0480faf 44240848 $.H..$H..H..D$.H - 0590 03442410 4c8d0cc1 488b4424 e0488b0c .D$.L...H.D$.H.. - 05a0 244883c0 02480faf 44240848 03442410 $H...H..D$.H.D$. - 05b0 488d34c1 488b4424 e0488b0c 244883c0 H.4.H.D$.H..$H.. - 05c0 03480faf 44240848 03442410 4c8d14c1 .H..D$.H.D$.L... - 05d0 488b4424 e0488b1c 244883c0 04480faf H.D$.H..$H...H.. - 05e0 44240848 03442410 4c8d1cc3 488b4424 D$.H.D$.L...H.D$ - 05f0 e0488b0c 244883c0 05480faf 44240848 .H..$H...H..D$.H - 0600 03442410 488d1cc1 488b4424 e0488b0c .D$.H...H.D$.H.. - 0610 244883c0 06480faf 44240848 03442410 $H...H..D$.H.D$. - 0620 488d2cc1 488b4424 e0488b0c 244883c0 H.,.H.D$.H..$H.. - 0630 07480faf 44240848 03442410 488d3cc1 .H..D$.H.D$.H.<. - 0640 488b4424 084c8b7c 24d84989 d4488d0c H.D$.L.|$.I..H.. - 0650 c5000000 004d29fc 488b8424 e0000000 .....M).H..$.... - 0660 4d85ff7f 62e95a02 0000660f 1f440000 M...b.Z...f..D.. - 0670 4983c008 4983c108 4883c608 4983c208 I...I...H...I... - 0680 4983c308 4883c308 4883c508 4883c708 I...H...H...H... - 0690 48ffcac5 fb1138c5 fb117008 c5fb1168 H.....8...p....h - 06a0 10c5fb11 6018c5fb 115820c5 fb115028 ....`....X ...P( - 06b0 c5fb1148 30c5fb11 40384883 c0404939 ...H0...@8H..@I9 - 06c0 d40f84ec 010000c4 c17b1038 c4c17b10 .........{.8..{. - 06d0 31c5fb10 2ec4c17b 1022c4c1 7b101bc5 1......{."..{... - 06e0 fb1013c5 fb104d00 c5fb1007 4885d20f ......M.....H... - 06f0 8f7bffff ff4901c8 4885d20f 8473ffff .{...I..H....s.. - 0700 ff4901c9 4883faff 0f846aff ffff4801 .I..H.....j...H. - 0710 ce4883fa fe0f8461 ffffff49 01ca4883 .H.....a...I..H. - 0720 fafd0f84 58ffffff 4901cb48 83fafc0f ....X...I..H.... - 0730 844fffff ff4801cb 4883fafb 0f8446ff .O...H..H.....F. - 0740 ffff4801 cd4883fa fa0f843d ffffff48 ..H..H.....=...H - 0750 01cfe939 ffffff66 0f1f8400 00000000 ...9...f........ - 0760 488b4424 c8488944 24980f84 b0faffff H.D$.H.D$....... - 0770 488b4424 c84883c0 0848837c 24b0ff48 H.D$.H...H.|$..H - 0780 894424a0 0f84a5fa ffff488b 4424c848 .D$.......H.D$.H - 0790 837c24b0 fe488d48 100f849a faffff48 .|$..H.H.......H - 07a0 8b4424c8 4883c018 48837c24 b0fd4889 .D$.H...H.|$..H. - 07b0 4424880f 848ffaff ff488b44 24c84883 D$.......H.D$.H. - 07c0 c0204883 7c24b0fc 48894424 900f8484 . H.|$..H.D$.... - 07d0 faffff48 8b4424c8 48837c24 b0fb4c8d ...H.D$.H.|$..L. - 07e0 40280f84 7cfaffff 488b4424 c848837c @(..|...H.D$.H.| - 07f0 24b0fa4c 8d48300f 8474faff ff488b44 $..L.H0..t...H.D - 0800 24c84883 7c24b0f9 4c8d5038 0f8469fa $.H.|$..L.P8..i. - 0810 ffff488b 4424c848 837c24b0 f84c8d58 ..H.D$.H.|$..L.X - 0820 400f845e faffff48 8b4424c8 48837c24 @..^...H.D$.H.|$ - 0830 b0f7488d 58480f84 56faffff 488b4424 ..H.XH..V...H.D$ - 0840 c848837c 24b0f648 8d68500f 844bfaff .H.|$..H.hP..K.. - 0850 ff488b44 24c84883 7c24b0f5 4c8d6058 .H.D$.H.|$..L.`X - 0860 0f8440fa ffff488b 4424c848 837c24b0 ..@...H.D$.H.|$. - 0870 f44c8d68 600f8435 faffff48 8b4424c8 .L.h`..5...H.D$. - 0880 48837c24 b0f34c8d 70680f84 2afaffff H.|$..L.ph..*... - 0890 488b4424 c848837c 24b0f24c 8d78700f H.D$.H.|$..L.xp. - 08a0 841ffaff ff488b44 24c8488d 7878e91b .....H.D$.H.xx.. - 08b0 faffff48 8b4424d8 48c1e006 48018424 ...H.D$.H...H..$ - 08c0 e0000000 48834424 e008f684 24980000 ....H.D$....$... - 08d0 00040f84 23010000 488b4424 e0488b4c ....#...H.D$.H.L - 08e0 24104889 c24829ca 4885d20f 8e570300 $.H..H).H....W.. - 08f0 00480faf 44240848 01c8488b 0c24488d .H..D$.H..H..$H. - 0900 3cc1488b 4424e048 8b0c2448 ffc0480f <.H.D$.H..$H..H. - 0910 af442408 48034424 104c8d04 c1488b44 .D$.H.D$.L...H.D - 0920 24e0488b 1c244883 c002480f af442408 $.H..$H...H..D$. - 0930 48034424 10488d0c c3488b44 24e0488b H.D$.H...H.D$.H. - 0940 1c244883 c003480f af442408 48034424 .$H...H..D$.H.D$ - 0950 10488d34 c3488b44 2408488b 5c24d849 .H.4.H.D$.H.\$.I - 0960 89d24c8d 0cc50000 00004929 da488b84 ..L.......I).H.. - 0970 24e00000 004885db 7f35eb79 0f1f4000 $....H...5.y..@. - 0980 4883c708 4983c008 4883c108 4883c608 H...I...H...H... - 0990 48ffcac5 fb1118c5 fb115008 c5fb1148 H.........P....H - 09a0 10c5fb11 40184883 c0204939 d27435c5 ....@.H.. I9.t5. - 09b0 fb101fc4 c17b1010 c5fb1009 c5fb1006 .....{.......... - 09c0 4885d27f bb4c01cf 4885d274 b74d01c8 H....L..H..t.M.. - 09d0 4883faff 74b24c01 c94883fa fe74ad4c H...t.L..H...t.L - 09e0 01ceebac 488b4424 d848c1e0 05480184 ....H.D$.H...H.. - 09f0 24e00000 00488344 24e004f6 84249800 $....H.D$....$.. - 0a00 0000020f 84c50000 00488b4c 24e0488b .........H.L$.H. - 0a10 5c241048 89c84829 d84885c0 0f8ef301 \$.H..H).H...... - 0a20 0000480f af4c2408 4889ca48 8b0c2448 ..H..L$.H..H..$H - 0a30 01da488d 34d1488b 5c24e048 8d530148 ..H.4.H.\$.H.S.H - 0a40 0faf5424 08488b1c 24480354 2410488d ..T$.H..$H.T$.H. - 0a50 0cd3488b 5c240848 89c74c8d 04dd0000 ..H.\$.H..L..... - 0a60 0000488b 5c24d848 8b9424e0 00000048 ..H.\$.H..$....H - 0a70 29df4885 db7f26eb 4f0f1f80 00000000 ).H...&.O....... - 0a80 4883c608 4883c108 48ffc8c5 fb110ac5 H...H...H....... - 0a90 fb114208 4883c210 4839c774 1ac5fb10 ..B.H...H9.t.... - 0aa0 0ec5fb10 014885c0 7fd64c01 c64885c0 .....H....L..H.. - 0ab0 74d24c01 c1ebd148 8b4424d8 48c1e004 t.L....H.D$.H... - 0ac0 48018424 e0000000 48834424 e002f684 H..$....H.D$.... - 0ad0 24980000 0001746a 488b4424 e0488b4c $.....tjH.D$.H.L - 0ae0 24104889 c24829ca 4885d27e 69480faf $.H..H).H..~iH.. - 0af0 44240848 01c8488b 0c24488d 04c1488b D$.H..H..$H...H. - 0b00 7c240848 8b4c24d8 4889d648 c1e70348 |$.H.L$.H..H...H - 0b10 29ce4885 c97e2b48 8b8c24e0 00000090 ).H..~+H..$..... - 0b20 c5fb1000 4c8d4008 4801f848 85d2490f ....L.@.H..H..I. - 0b30 4fc048ff cac5fb11 014883c1 084839d6 O.H......H...H9. - 0b40 75de4881 c4a80000 005b5d41 5c415d41 u.H......[]A\A]A - 0b50 5e31c041 5fc3488b 44241048 8b0c2448 ^1.A_.H.D$.H..$H - 0b60 0faf4424 08480344 24e0488d 04c1eb8e ..D$.H.D$.H..... - 0b70 488b4424 10488b1c 24480faf 44240848 H.D$.H..$H..D$.H - 0b80 034424e0 48c1e003 4c8d0403 4885d20f .D$.H...L...H... - 0b90 84e8f9ff ff488b0c 244c8d4c 01084883 .....H..$L.L..H. - 0ba0 faff0f84 f0f9ffff 488b0c24 488d7401 ........H..$H.t. - 0bb0 104883fa fe0f84f9 f9ffff48 8b1c244c .H.........H..$L - 0bc0 8d540318 4883fafd 0f8402fa ffff488b .T..H.........H. - 0bd0 0c244c8d 5c012048 83fafc0f 840bfaff .$L.\. H........ - 0be0 ff488b1c 24488d5c 03284883 fafb0f84 .H..$H.\.(H..... - 0bf0 14faffff 488b0c24 488d6c01 304883fa ....H..$H.l.0H.. - 0c00 fa0f841d faffff48 8b0c2448 8d7c0138 .......H..$H.|.8 - 0c10 e92bfaff ff488b54 2410488b 1c24480f .+...H.T$.H..$H. /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_COOPERLAKE.o (objdump) @@ -3,9 +3,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 a10c0000 00420e10 8f02420e .........B....B. + 0010 1b0c0708 90010000 44000000 1c000000 ........D....... + 0020 00000000 50030000 00420e10 8f02420e ....P....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ee00103 380b0a0e ..A.8..G....8... - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0040 8606440e 38830703 e8020a0e 30410e28 ..D.8.......0A.( + 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_SKYLAKEX.o (disasm) @@ -10,525 +10,70 @@ push %r13 push %r12 push %rbp + mov %rdi,%rbp push %rbx - sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,-offset(%rsp) - mov %rdx,(%rsp) - mov %rcx,offset(%rsp) - mov %r8,-offset(%rsp) - mov %r9,offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %r9,-offset(%rsp) + mov %rsi,-offset(%rsp) + mov offset(%rsp),%r12 test %rsi,%rsi jle - mov %rcx,%r14 mov %r9,%rax - imul %r14,%rax - mov %rdx,%r11 - mov %rsi,%r10 + imul %rcx,%rax + mov %r8,%rbx + sub %r9,%rbx add %r8,%rax - lea offset(,%rcx,8),%rsi - mov %r8,%rcx - sub %r9,%rcx - lea (%r11,%rax,8),%rax - mov %rax,-offset(%rsp) - mov %rcx,%rax - sub %rdi,%rax - mov %rax,-offset(%rsp) - mov %r14,%rax - shl $something,%rax - mov %rax,-offset(%rsp) - mov %r10,%rax - shl $something,%rax - add %rcx,%rax - mov %rax,-offset(%rsp) - mov %r14,%rax - imul %r8,%rax - mov %r9,%rdx - mov %rdi,%r9 - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %rcx,-offset(%rsp) - movq $something,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) + lea (%rdx,%rax,8),%r14 lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - shl $something,%r9 - mov %r9,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,8),%rax - mov %rax,offset(%rsp) - nopl offset(%rax,%rax,1) - mov -offset(%rsp),%rax - mov %rax,%rdx - test %rax,%rax - jle - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rcx - add offset(%rsp),%rcx - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%r8 - add offset(%rsp),%r8 - mov -offset(%rsp),%r9 - add offset(%rsp),%r9 - mov -offset(%rsp),%r10 - add offset(%rsp),%r10 - mov -offset(%rsp),%r11 - add offset(%rsp),%r11 - mov -offset(%rsp),%rbx - add offset(%rsp),%rbx - mov -offset(%rsp),%rbp - add offset(%rsp),%rbp - mov -offset(%rsp),%r12 - add offset(%rsp),%r12 - mov -offset(%rsp),%r13 - add offset(%rsp),%r13 - mov -offset(%rsp),%r14 - add offset(%rsp),%r14 - mov -offset(%rsp),%r15 - add offset(%rsp),%r15 - mov -offset(%rsp),%rdi - add offset(%rsp),%rdi - cmpq $something,-offset(%rsp) - mov offset(%rsp),%rax - jle - mov %rdx,-offset(%rsp) + imul %rcx,%rax + lea offset(,%rcx,8),%r10 + mov %r8,-offset(%rsp) + add %r9,%rax + lea (%rdx,%rax,8),%r13 + lea (%rbx,%rsi,4),%rax + mov %rax,-offset(%rsp) + mov %r8,%rax + neg %rax + lea -offset(,%rax,8),%rax + mov %r10,%rdx + imul %rcx,%rax + imul %r8,%rdx + mov %rcx,%r15 + mov %rbx,%r11 + lea (%rdx,%rax,1),%rdi + lea offset(%r8),%rdx + imul %r10,%rdx mov %rdi,-offset(%rsp) /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_SKYLAKEX.o (objdump) @@ -2,206 +2,56 @@ /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 eca80000 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 0448897c .H..$....H...H.| - 0020 24d84889 14244889 4c24084c 894424e0 $.H..$H.L$.L.D$. - 0030 4c894c24 104889b4 24a00000 004885f6 L.L$.H..$....H.. - 0040 0f8eff04 00004989 ce4c89c8 490fafc6 ......I..L..I... - 0050 4989d349 89f24c01 c0488d34 cd000000 I..I..L..H.4.... - 0060 004c89c1 4c29c949 8d04c348 894424c8 .L..L).I...H.D$. - 0070 4889c848 29f84889 4424c04c 89f048c1 H..H).H.D$.L..H. - 0080 e0074889 4424e84c 89d048c1 e0044801 ..H.D$.L..H...H. - 0090 c8488944 24f04c89 f0490faf c04c89ca .H.D$.L..I...L.. - 00a0 4989f948 01d0498d 04c34889 44241849 I..H..I...H.D$.I - 00b0 8d400149 0fafc648 894c24b0 48c74424 .@.I...H.L$.H.D$ - 00c0 b8000000 004801d0 498d04c3 48894424 .....H..I...H.D$ - 00d0 20498d40 02490faf c64801d0 498d04c3 I.@.I...H..I... - 00e0 48894424 28498d40 03490faf c64801d0 H.D$(I.@.I...H.. - 00f0 498d04c3 48894424 60498d40 04490faf I...H.D$`I.@.I.. - 0100 c64801d0 498d04c3 48894424 70498d40 .H..I...H.D$pI.@ - 0110 05490faf c64801d0 498d04c3 48898424 .I...H..I...H..$ - 0120 88000000 498d4006 490fafc6 4801d049 ....I.@.I...H..I - 0130 8d04c348 89842490 00000049 8d400749 ...H..$....I.@.I - 0140 0fafc648 01d0498d 04c34889 44246849 ...H..I...H.D$hI - 0150 8d400849 0fafc648 01d0498d 04c34889 .@.I...H..I...H. - 0160 44247849 8d400949 0fafc648 01d0498d D$xI.@.I...H..I. - 0170 04c34889 84248000 0000498d 400a490f ..H..$....I.@.I. - 0180 afc64801 d0498d04 c3488944 2458498d ..H..I...H.D$XI. - 0190 400b490f afc64801 d0498d04 c3488944 @.I...H..I...H.D - 01a0 2450498d 400c490f afc64801 d0498d04 $PI.@.I...H..I.. - 01b0 c3488944 2448498d 400d490f afc649c1 .H.D$HI.@.I...I. - 01c0 e1074c89 4c24f848 01d0498d 04c34889 ..L.L$.H..I...H. - 01d0 44243049 8d400e49 0fafc648 01d0498d D$0I.@.I...H..I. - 01e0 04c34889 44244049 8d400f49 0fafc648 ..H.D$@I.@.I...H - 01f0 01d0498d 04c34889 4424380f 1f440000 ..I...H.D$8..D.. - 0200 488b4424 b04889c2 4885c00f 8e4f0500 H.D$.H..H....O.. - 0210 00488b44 24b84803 44241848 89442498 .H.D$.H.D$.H.D$. - 0220 488b4424 b8480344 24204889 4424a048 H.D$.H.D$ H.D$.H - 0230 8b4c24b8 48034c24 28488b44 24b84803 .L$.H.L$(H.D$.H. - 0240 44246048 89442488 488b4424 b8480344 D$`H.D$.H.D$.H.D - 0250 24704889 4424904c 8b4424b8 4c038424 $pH.D$.L.D$.L..$ - 0260 88000000 4c8b4c24 b84c038c 24900000 ....L.L$.L..$... - 0270 004c8b54 24b84c03 5424684c 8b5c24b8 .L.T$.L.T$hL.\$. - 0280 4c035c24 78488b5c 24b84803 9c248000 L.\$xH.\$.H..$.. - 0290 0000488b 6c24b848 036c2458 4c8b6424 ..H.l$.H.l$XL.d$ - 02a0 b84c0364 24504c8b 6c24b84c 036c2448 .L.d$PL.l$.L.l$H - 02b0 4c8b7424 b84c0374 24304c8b 7c24b84c L.t$.L.t$0L.|$.L - 02c0 037c2440 488b7c24 b848037c 24384883 .|$@H.|$.H.|$8H. - 02d0 7c24d800 488b8424 e0000000 0f8e1e02 |$..H..$........ - 02e0 00004889 5424d048 897c24a8 4889f248 ..H.T$.H.|$.H..H - 02f0 8b7424d0 e9b20000 000f1f80 00000000 .t$............. - 0300 48834424 98084883 4424a008 4883c108 H.D$..H.D$..H... - 0310 48834424 88084883 44249008 4983c008 H.D$..H.D$..I... - 0320 4983c108 4983c208 4983c308 4883c308 I...I...I...H... - 0330 4883c508 4983c408 4983c508 4983c608 H...I...I...I... - 0340 4983c708 48834424 a80848ff cec57b11 I...H.D$..H...{. - 0350 38c57b11 7008c57b 116810c5 7b116018 8.{.p..{.h..{.`. - 0360 c57b1158 20c57b11 5028c57b 114830c5 .{.X .{.P(.{.H0. - 0370 7b114038 c5fb1178 40c5fb11 7048c5fb {.@8...x@...pH.. - 0380 116850c5 fb116058 c5fb1158 60c5fb11 .hP...`X...X`... - 0390 5068c5fb 114870c5 fb114078 4883e880 Ph...Hp...@xH... - 03a0 48397424 c00f8445 01000048 8b7c2498 H9t$...E...H.|$. - 03b0 c57b1029 c57b103f 488b7c24 a0c4417b .{.).{.?H.|$..A{ - 03c0 1010c57b 1037488b 7c2488c4 417b1009 ...{.7H.|$..A{.. - 03d0 c57b1027 488b7c24 90c4417b 1002c57b .{.'H.|$..A{...{ - 03e0 101f488b 7c24a8c4 c17b103b c5fb1033 ..H.|$...{.;...3 - 03f0 c5fb106d 00c4c17b 102424c4 c17b105d ...m...{.$$..{.] - 0400 00c4c17b 1016c4c1 7b100fc5 fb100748 ...{....{......H - 0410 85f60f8f e8feffff 48015424 984885f6 ........H.T$.H.. - 0420 0f84e0fe ffff4801 5424a048 83feff0f ......H.T$.H.... - 0430 84d7feff ff4801d1 4883fefe 0f84cefe .....H..H....... - 0440 ffff4801 54248848 83fefd0f 84c5feff ..H.T$.H........ - 0450 ff480154 24904883 fefc0f84 bcfeffff .H.T$.H......... - 0460 4901d048 83fefb0f 84b3feff ff4901d1 I..H.........I.. - 0470 4883fefa 0f84aafe ffff4901 d24883fe H.........I..H.. - 0480 f90f84a1 feffff49 01d34883 fef80f84 .......I..H..... - 0490 98feffff 4801d348 83fef70f 848ffeff ....H..H........ - 04a0 ff4801d5 4883fef6 0f8486fe ffff4901 .H..H.........I. - 04b0 d44883fe f50f847d feffff49 01d54883 .H.....}...I..H. - 04c0 fef40f84 74feffff 4901d648 83fef30f ....t...I..H.... - 04d0 846bfeff ff4901d7 4883fef2 0f8462fe .k...I..H.....b. - 04e0 ffff4801 5424a8e9 5efeffff 0f1f4000 ..H.T$..^.....@. - 04f0 488b4424 f84889d6 48018424 e0000000 H.D$.H..H..$.... - 0500 48834424 b010488b 5c24e848 836c24c8 H.D$..H.\$.H.l$. - 0510 80488344 24c01048 8b4424b0 48015c24 .H.D$..H.D$.H.\$ - 0520 b8483b44 24f00f85 d4fcffff 488b8424 .H;D$.......H..$ - 0530 a0000000 488b4c24 e048c1e0 044801c8 ....H.L$.H...H.. - 0540 48894424 e0f68424 98000000 080f8477 H.D$...$.......w - 0550 03000048 8b4424e0 488b4c24 104889c2 ...H.D$.H.L$.H.. - 0560 4829ca48 85d20f8e 04060000 480faf44 H).H........H..D - 0570 24084801 c8488b0c 244c8d04 c1488b44 $.H..H..$L...H.D - 0580 24e0488b 0c2448ff c0480faf 44240848 $.H..$H..H..D$.H - 0590 03442410 4c8d0cc1 488b4424 e0488b0c .D$.L...H.D$.H.. - 05a0 244883c0 02480faf 44240848 03442410 $H...H..D$.H.D$. - 05b0 488d34c1 488b4424 e0488b0c 244883c0 H.4.H.D$.H..$H.. - 05c0 03480faf 44240848 03442410 4c8d14c1 .H..D$.H.D$.L... - 05d0 488b4424 e0488b1c 244883c0 04480faf H.D$.H..$H...H.. - 05e0 44240848 03442410 4c8d1cc3 488b4424 D$.H.D$.L...H.D$ - 05f0 e0488b0c 244883c0 05480faf 44240848 .H..$H...H..D$.H - 0600 03442410 488d1cc1 488b4424 e0488b0c .D$.H...H.D$.H.. - 0610 244883c0 06480faf 44240848 03442410 $H...H..D$.H.D$. - 0620 488d2cc1 488b4424 e0488b0c 244883c0 H.,.H.D$.H..$H.. - 0630 07480faf 44240848 03442410 488d3cc1 .H..D$.H.D$.H.<. - 0640 488b4424 084c8b7c 24d84989 d4488d0c H.D$.L.|$.I..H.. - 0650 c5000000 004d29fc 488b8424 e0000000 .....M).H..$.... - 0660 4d85ff7f 62e95a02 0000660f 1f440000 M...b.Z...f..D.. - 0670 4983c008 4983c108 4883c608 4983c208 I...I...H...I... - 0680 4983c308 4883c308 4883c508 4883c708 I...H...H...H... - 0690 48ffcac5 fb1138c5 fb117008 c5fb1168 H.....8...p....h - 06a0 10c5fb11 6018c5fb 115820c5 fb115028 ....`....X ...P( - 06b0 c5fb1148 30c5fb11 40384883 c0404939 ...H0...@8H..@I9 - 06c0 d40f84ec 010000c4 c17b1038 c4c17b10 .........{.8..{. - 06d0 31c5fb10 2ec4c17b 1022c4c1 7b101bc5 1......{."..{... - 06e0 fb1013c5 fb104d00 c5fb1007 4885d20f ......M.....H... - 06f0 8f7bffff ff4901c8 4885d20f 8473ffff .{...I..H....s.. - 0700 ff4901c9 4883faff 0f846aff ffff4801 .I..H.....j...H. - 0710 ce4883fa fe0f8461 ffffff49 01ca4883 .H.....a...I..H. - 0720 fafd0f84 58ffffff 4901cb48 83fafc0f ....X...I..H.... - 0730 844fffff ff4801cb 4883fafb 0f8446ff .O...H..H.....F. - 0740 ffff4801 cd4883fa fa0f843d ffffff48 ..H..H.....=...H - 0750 01cfe939 ffffff66 0f1f8400 00000000 ...9...f........ - 0760 488b4424 c8488944 24980f84 b0faffff H.D$.H.D$....... - 0770 488b4424 c84883c0 0848837c 24b0ff48 H.D$.H...H.|$..H - 0780 894424a0 0f84a5fa ffff488b 4424c848 .D$.......H.D$.H - 0790 837c24b0 fe488d48 100f849a faffff48 .|$..H.H.......H - 07a0 8b4424c8 4883c018 48837c24 b0fd4889 .D$.H...H.|$..H. - 07b0 4424880f 848ffaff ff488b44 24c84883 D$.......H.D$.H. - 07c0 c0204883 7c24b0fc 48894424 900f8484 . H.|$..H.D$.... - 07d0 faffff48 8b4424c8 48837c24 b0fb4c8d ...H.D$.H.|$..L. - 07e0 40280f84 7cfaffff 488b4424 c848837c @(..|...H.D$.H.| - 07f0 24b0fa4c 8d48300f 8474faff ff488b44 $..L.H0..t...H.D - 0800 24c84883 7c24b0f9 4c8d5038 0f8469fa $.H.|$..L.P8..i. - 0810 ffff488b 4424c848 837c24b0 f84c8d58 ..H.D$.H.|$..L.X - 0820 400f845e faffff48 8b4424c8 48837c24 @..^...H.D$.H.|$ - 0830 b0f7488d 58480f84 56faffff 488b4424 ..H.XH..V...H.D$ - 0840 c848837c 24b0f648 8d68500f 844bfaff .H.|$..H.hP..K.. - 0850 ff488b44 24c84883 7c24b0f5 4c8d6058 .H.D$.H.|$..L.`X - 0860 0f8440fa ffff488b 4424c848 837c24b0 ..@...H.D$.H.|$. - 0870 f44c8d68 600f8435 faffff48 8b4424c8 .L.h`..5...H.D$. - 0880 48837c24 b0f34c8d 70680f84 2afaffff H.|$..L.ph..*... - 0890 488b4424 c848837c 24b0f24c 8d78700f H.D$.H.|$..L.xp. - 08a0 841ffaff ff488b44 24c8488d 7878e91b .....H.D$.H.xx.. - 08b0 faffff48 8b4424d8 48c1e006 48018424 ...H.D$.H...H..$ - 08c0 e0000000 48834424 e008f684 24980000 ....H.D$....$... - 08d0 00040f84 23010000 488b4424 e0488b4c ....#...H.D$.H.L - 08e0 24104889 c24829ca 4885d20f 8e570300 $.H..H).H....W.. - 08f0 00480faf 44240848 01c8488b 0c24488d .H..D$.H..H..$H. - 0900 3cc1488b 4424e048 8b0c2448 ffc0480f <.H.D$.H..$H..H. - 0910 af442408 48034424 104c8d04 c1488b44 .D$.H.D$.L...H.D - 0920 24e0488b 1c244883 c002480f af442408 $.H..$H...H..D$. - 0930 48034424 10488d0c c3488b44 24e0488b H.D$.H...H.D$.H. - 0940 1c244883 c003480f af442408 48034424 .$H...H..D$.H.D$ - 0950 10488d34 c3488b44 2408488b 5c24d849 .H.4.H.D$.H.\$.I - 0960 89d24c8d 0cc50000 00004929 da488b84 ..L.......I).H.. - 0970 24e00000 004885db 7f35eb79 0f1f4000 $....H...5.y..@. - 0980 4883c708 4983c008 4883c108 4883c608 H...I...H...H... - 0990 48ffcac5 fb1118c5 fb115008 c5fb1148 H.........P....H - 09a0 10c5fb11 40184883 c0204939 d27435c5 ....@.H.. I9.t5. - 09b0 fb101fc4 c17b1010 c5fb1009 c5fb1006 .....{.......... - 09c0 4885d27f bb4c01cf 4885d274 b74d01c8 H....L..H..t.M.. - 09d0 4883faff 74b24c01 c94883fa fe74ad4c H...t.L..H...t.L - 09e0 01ceebac 488b4424 d848c1e0 05480184 ....H.D$.H...H.. - 09f0 24e00000 00488344 24e004f6 84249800 $....H.D$....$.. - 0a00 0000020f 84c50000 00488b4c 24e0488b .........H.L$.H. - 0a10 5c241048 89c84829 d84885c0 0f8ef301 \$.H..H).H...... - 0a20 0000480f af4c2408 4889ca48 8b0c2448 ..H..L$.H..H..$H - 0a30 01da488d 34d1488b 5c24e048 8d530148 ..H.4.H.\$.H.S.H - 0a40 0faf5424 08488b1c 24480354 2410488d ..T$.H..$H.T$.H. - 0a50 0cd3488b 5c240848 89c74c8d 04dd0000 ..H.\$.H..L..... - 0a60 0000488b 5c24d848 8b9424e0 00000048 ..H.\$.H..$....H - 0a70 29df4885 db7f26eb 4f0f1f80 00000000 ).H...&.O....... - 0a80 4883c608 4883c108 48ffc8c5 fb110ac5 H...H...H....... - 0a90 fb114208 4883c210 4839c774 1ac5fb10 ..B.H...H9.t.... - 0aa0 0ec5fb10 014885c0 7fd64c01 c64885c0 .....H....L..H.. - 0ab0 74d24c01 c1ebd148 8b4424d8 48c1e004 t.L....H.D$.H... - 0ac0 48018424 e0000000 48834424 e002f684 H..$....H.D$.... - 0ad0 24980000 0001746a 488b4424 e0488b4c $.....tjH.D$.H.L - 0ae0 24104889 c24829ca 4885d27e 69480faf $.H..H).H..~iH.. - 0af0 44240848 01c8488b 0c24488d 04c1488b D$.H..H..$H...H. - 0b00 7c240848 8b4c24d8 4889d648 c1e70348 |$.H.L$.H..H...H - 0b10 29ce4885 c97e2b48 8b8c24e0 00000090 ).H..~+H..$..... - 0b20 c5fb1000 4c8d4008 4801f848 85d2490f ....L.@.H..H..I. - 0b30 4fc048ff cac5fb11 014883c1 084839d6 O.H......H...H9. - 0b40 75de4881 c4a80000 005b5d41 5c415d41 u.H......[]A\A]A - 0b50 5e31c041 5fc3488b 44241048 8b0c2448 ^1.A_.H.D$.H..$H - 0b60 0faf4424 08480344 24e0488d 04c1eb8e ..D$.H.D$.H..... - 0b70 488b4424 10488b1c 24480faf 44240848 H.D$.H..$H..D$.H - 0b80 034424e0 48c1e003 4c8d0403 4885d20f .D$.H...L...H... - 0b90 84e8f9ff ff488b0c 244c8d4c 01084883 .....H..$L.L..H. - 0ba0 faff0f84 f0f9ffff 488b0c24 488d7401 ........H..$H.t. - 0bb0 104883fa fe0f84f9 f9ffff48 8b1c244c .H.........H..$L - 0bc0 8d540318 4883fafd 0f8402fa ffff488b .T..H.........H. - 0bd0 0c244c8d 5c012048 83fafc0f 840bfaff .$L.\. H........ - 0be0 ff488b1c 24488d5c 03284883 fafb0f84 .H..$H.\.(H..... - 0bf0 14faffff 488b0c24 488d6c01 304883fa ....H..$H.l.0H.. - 0c00 fa0f841d faffff48 8b0c2448 8d7c0138 .......H..$H.|.8 - 0c10 e92bfaff ff488b54 2410488b 1c24480f .+...H.T$.H..$H. /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_iutcopy_SKYLAKEX.o (objdump) @@ -3,9 +3,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 a10c0000 00420e10 8f02420e .........B....B. + 0010 1b0c0708 90010000 44000000 1c000000 ........D....... + 0020 00000000 50030000 00420e10 8f02420e ....P....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ee00103 380b0a0e ..A.8..G....8... - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0040 8606440e 38830703 e8020a0e 30410e28 ..D.8.......0A.( + 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_COOPERLAKE.o (disasm) @@ -10,56 +10,280 @@ push %r13 push %r12 push %rbp - mov %rdi,%rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi + sub $something,%rsp + mov %rsi,(%rsp) + sar $something,%rsi + mov %rdi,-offset(%rsp) mov %rdx,-offset(%rsp) mov %rcx,-offset(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,-offset(%rsp) - mov offset(%rsp),%r10 + mov %r8,-offset(%rsp) + mov %r9,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rcx,%rbx - mov %rbx,%rax + mov %rsi,%r11 + mov %rcx,%rsi + mov %rsi,%rax + shl $something,%rax + mov %rax,-offset(%rsp) + mov %rsi,%rax imul %r8,%rax - mov %r9,%rcx - lea offset(,%rbx,8),%r9 - add %rcx,%rax - lea (%rdx,%rax,8),%r12 - mov %rcx,%rax - imul %rbx,%rax - mov %r8,%rdi - mov %r9,-offset(%rsp) - mov %rbx,%r14 + lea offset(,%rcx,8),%rcx + mov %r8,%r13 + add %r9,%rax + lea (%rdx,%rax,8),%r15 + mov %r9,%rax + imul %rsi,%rax + sub %r9,%r13 + mov %r13,%r12 add %r8,%rax - sub %rcx,%rdi - mov %rbp,%r15 - shl $something,%r14 - lea (%rdx,%rax,8),%r11 - sub %rbp,%rdi - lea (%r8,%rsi,2),%r13 - shl $something,%r15 - mov %r8,%rbx - nopl offset(%rax) - lea (%rdi,%rbp,1),%rax - mov %r11,%rsi - test %rax,%rax + lea (%rdx,%rax,8),%r14 + lea (%r8,%r11,8),%rax + mov %rax,-offset(%rsp) + mov %rcx,%rax + neg %rax + lea offset(%r8),%rdx + imul %r8,%rax + imul %rcx,%rdx + sub %rdi,%r12 + shl $something,%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + mov %rdi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + mov %r8,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + add %rdx,%rax + mov %rax,-offset(%rsp) + cs nopw offset(%rax,%rax,1) + mov %r13,%rdx + mov %r14,%rbx + test %r13,%r13 jle - lea offset(%r11),%rcx - mov %r10,%rdx - test %rbp,%rbp + lea offset(%r14),%rbp + lea offset(%r14),%rsi + lea offset(%r14),%r8 + lea offset(%r14),%r9 + lea offset(%r14),%r10 + lea offset(%r14),%r11 + lea offset(%r14),%rdi + cmpq $something,-offset(%rsp) + mov offset(%rsp),%rax jg jmp - cs nopw offset(%rax,%rax,1) - add %r9,%rsi + nopl (%rax) + add %rcx,%rbx + add %rcx,%rbp + add %rcx,%rsi + add %rcx,%r8 + add %rcx,%r9 + add %rcx,%r10 + add %rcx,%r11 + add %rcx,%rdi + dec %rdx + vmovsd %xmm7,(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + add $something,%rax + cmp %r12,%rdx + je + vmovsd (%rbx),%xmm7 + vmovsd offset(%rbp),%xmm6 + vmovsd (%rsi),%xmm5 + vmovsd (%r8),%xmm4 + vmovsd (%r9),%xmm3 + vmovsd (%r10),%xmm2 + vmovsd (%r11),%xmm1 + vmovsd (%rdi),%xmm0 + test %rdx,%rdx + jg + add $something,%rbx + test %rdx,%rdx + je + add $something,%rbp + cmp $something,%rdx + je + add $something,%rsi + cmp $something,%rdx + je + add $something,%r8 + cmp $something,%rdx + je + add $something,%r9 + cmp $something,%rdx + je + add $something,%r10 + cmp $something,%rdx + je + add $something,%r11 + cmp $something,%rdx + je + add $something,%rdi + jmp + nop + mov -offset(%rsp),%rax + add %rax,offset(%rsp) + addq $something,-offset(%rsp) + add $something,%r13 + add -offset(%rsp),%r15 + add $something,%r14 + mov -offset(%rsp),%rax + add $something,%r12 + cmp %rax,-offset(%rsp) + jne + mov -offset(%rsp),%rax + mov offset(%rsp),%rdi + lea (%rax,%rdi,8),%rax + mov %rax,-offset(%rsp) + testb $something,(%rsp) + je + mov -offset(%rsp),%rdi + mov offset(%rsp),%rax + mov %rdi,%rdx + sub %rax,%rdx + test %rdx,%rdx + jle + imul -offset(%rsp),%rax /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_COOPERLAKE.o (objdump) @@ -2,31 +2,106 @@ /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 554889fd 53488974 AWAVAUATUH..SH.t - 0010 24d848d1 fe488954 24f84889 4c24e84c $.H..H.T$.H.L$.L - 0020 894c24f0 48897424 e04c8b54 24384885 .L$.H.t$.L.T$8H. - 0030 f60f8ed9 00000048 89cb4889 d8490faf .......H..H..I.. - 0040 c04c89c9 4c8d0cdd 00000000 4801c84c .L..L.......H..L - 0050 8d24c248 89c8480f afc34c89 c74c894c .$.H..H...L..L.L - 0060 24d04989 de4c01c0 4829cf49 89ef49c1 $.I..L..H).I..I. - 0070 e6044c8d 1cc24829 ef4d8d2c 7049c1e7 ..L...H).M.,pI.. - 0080 044c89c3 0f1f4000 488d042f 4c89de48 .L....@.H../L..H - 0090 85c00f8e f0000000 498d4b08 4c89d248 ........I.K.L..H - 00a0 85ed7f27 eb4d662e 0f1f8400 00000000 ...'.Mf......... - 00b0 4c01ce4c 01c948ff c8c5fb11 0ac5fb11 L..L..H......... - 00c0 42084883 c2104839 f87425c5 fb100ec5 B.H...H9.t%..... - 00d0 fb100148 85c07fd8 4883c608 4885c074 ...H....H...H..t - 00e0 d24883c1 08ebcf66 0f1f8400 00000000 .H.....f........ - 00f0 4d01fa48 83c3024d 01f44983 c3104883 M..H...M..I...H. - 0100 c7024c39 eb758148 8b4424e0 4d8d0440 ..L9.u.H.D$.M..@ - 0110 f64424d8 01745d48 8b4424f0 4c89c248 .D$..t]H.D$.L..H - 0120 29c24885 d27e7748 0faf4424 e8488b5c ).H..~wH..D$.H.\ - 0130 24f84c01 c0488d04 c3488b7c 24e84889 $.L..H...H.|$.H. - 0140 d648c1e7 034829ee 4885ed7e 270f1f00 .H...H).H..~'... - 0150 c5fb1000 488d0c38 4883c008 4885d248 ....H..8H...H..H - 0160 0f4fc148 ffcac4c1 7b110249 83c20848 .O.H....{..I...H - 0170 39d675dc 5b5d415c 415d415e 31c0415f 9.u.[]A\A]A^1.A_ - 0180 c30f1f80 00000000 4c89e60f 8407ffff ........L....... - 0190 ff488b4c 24d04c01 e1e9fefe ffff4c0f .H.L$.L.......L. - 01a0 af4424e8 488b4424 f0488b5c 24f84c01 .D$.H.D$.H.\$.L. - 01b0 c0488d04 c3eb82 .H..... + 0000 41574156 41554154 55534883 ec184889 AWAVAUATUSH...H. + 0010 342448c1 fe034889 7c249048 895424f8 4$H...H.|$.H.T$. + 0020 48894c24 e84c8944 24b04c89 4c240848 H.L$.L.D$.L.L$.H + 0030 89742410 4885f60f 8e470200 004989f3 .t$.H....G...I.. + 0040 4889ce48 89f048c1 e0064889 4424a048 H..H..H...H.D$.H + 0050 89f0490f afc0488d 0ccd0000 00004d89 ..I...H.......M. + 0060 c54c01c8 4c8d3cc2 4c89c848 0fafc64d .L..L.<.L..H...M + 0070 29cd4d89 ec4c01c0 4c8d34c2 4b8d04d8 ).M..L..L.4.K... + 0080 48894424 984889c8 48f7d849 8d500149 H.D$.H..H..I.P.I + 0090 0fafc048 0fafd149 29fc48c1 e706488d ...H...I).H...H. + 00a0 3402498d 5002480f afd14889 7424f048 4.I.P.H...H.t$.H + 00b0 897c24a8 488d3402 498d5003 480fafd1 .|$.H.4.I.P.H... + 00c0 48897424 b84c8944 2488488d 3402498d H.t$.L.D$.H.4.I. + 00d0 5004480f afd14889 7424c848 8d340249 P.H...H.t$.H.4.I + 00e0 8d500548 0fafd148 897424c0 488d3402 .P.H...H.t$.H.4. + 00f0 498d5006 480fafd1 48897424 d8488d34 I.P.H...H.t$.H.4 + 0100 02498d50 07480faf d1488974 24e04801 .I.P.H...H.t$.H. + 0110 d0488944 24d0662e 0f1f8400 00000000 .H.D$.f......... + 0120 4c89ea4c 89f34d85 ed0f8e41 02000049 L..L..M....A...I + 0130 8d6e0849 8d76104d 8d46184d 8d4e204d .n.I.v.M.F.M.N M + 0140 8d56284d 8d5e3049 8d7e3848 837c2490 .V(M.^0I.~8H.|$. + 0150 00488b44 24507f57 e9ed0000 000f1f00 .H.D$P.W........ + 0160 4801cb48 01cd4801 ce4901c8 4901c949 H..H..H..I..I..I + 0170 01ca4901 cb4801cf 48ffcac5 fb1138c5 ..I..H..H.....8. + 0180 fb117008 c5fb1168 10c5fb11 6018c5fb ..p....h....`... + 0190 115820c5 fb115028 c5fb1148 30c5fb11 .X ...P(...H0... + 01a0 40384883 c0404c39 e20f8491 000000c5 @8H..@L9........ + 01b0 fb103bc5 fb107500 c5fb102e c4c17b10 ..;...u.......{. + 01c0 20c4c17b 1019c4c1 7b1012c4 c17b100b ..{....{....{.. + 01d0 c5fb1007 4885d27f 874883c3 084885d2 ....H....H...H.. + 01e0 74814883 c5084883 faff0f84 76ffffff t.H...H.....v... + 01f0 4883c608 4883fafe 0f846bff ffff4983 H...H.....k...I. + 0200 c0084883 fafd0f84 60ffffff 4983c108 ..H.....`...I... + 0210 4883fafc 0f8455ff ffff4983 c2084883 H.....U...I...H. + 0220 fafb0f84 4affffff 4983c308 4883fafa ....J...I...H... + 0230 0f843fff ffff4883 c708e939 ffffff90 ..?...H....9.... + 0240 488b4424 a8480144 24504883 44248808 H.D$.H.D$PH.D$.. + 0250 4983c508 4c037c24 a04983c6 40488b44 I...L.|$.I..@H.D + 0260 24884983 c4084839 4424980f 85affeff $.I...H9D$...... + 0270 ff488b44 24b0488b 7c241048 8d04f848 .H.D$.H.|$.H...H + 0280 894424b0 f6042404 0f847f01 0000488b .D$...$.......H. + 0290 7c24b048 8b442408 4889fa48 29c24885 |$.H.D$.H..H).H. + 02a0 d20f8ef6 02000048 0faf4424 e84801f8 .......H..D$.H.. + 02b0 488b7c24 f8488d3c c7488b74 24f84c8d H.|$.H.<.H.t$.L. + 02c0 44c60848 8b7424f8 488d4cc6 10488b74 D..H.t$.H.L..H.t + 02d0 24f8488d 74c61848 8b4424e8 488b5c24 $.H.t..H.D$.H.\$ + 02e0 904989d2 4c8d0cc5 00000000 4929da48 .I..L.......I).H + 02f0 8b442450 4885db7f 36e90901 00006690 .D$PH...6.....f. + 0300 4c01cf4d 01c84c01 c94c01ce 48ffcac5 L..M..L..L..H... + 0310 fb1118c5 fb115008 c5fb1148 10c5fb11 ......P....H.... + 0320 40184883 c0204939 d20f84ca 000000c5 @.H.. I9........ + 0330 fb101fc4 c17b1010 c5fb1009 c5fb1006 .....{.......... + 0340 4885d27f bb4883c7 084885d2 74b54983 H....H...H..t.I. + 0350 c0084883 faff74ae 4883c108 4883fafe ..H...t.H...H... + 0360 74a74883 c608eba4 0f1f8400 00000000 t.H............. + 0370 4c89fb0f 84b6fdff ff488b44 24f04a8d L........H.D$.J. + 0380 2c384983 fdff0f84 a7fdffff 488b4424 ,8I.........H.D$ + 0390 b84a8d34 384983fd fe0f8498 fdffff48 .J.48I.........H + 03a0 8b4424c8 4e8d0438 4983fdfd 0f8489fd .D$.N..8I....... + 03b0 ffff488b 4424c04e 8d0c3849 83fdfc0f ..H.D$.N..8I.... + 03c0 847afdff ff488b44 24d84d8d 14074983 .z...H.D$.M...I. + 03d0 fdfb0f84 6bfdffff 488b4424 e04d8d1c ....k...H.D$.M.. + 03e0 074983fd fa0f845c fdffff48 8b4424d0 .I.....\...H.D$. + 03f0 498d3c07 e952fdff ff488b44 249048c1 I.<..R...H.D$.H. + 0400 e0054801 44245048 834424b0 04f60424 ..H.D$PH.D$....$ + 0410 020f84a4 00000048 8b7c24b0 488b7424 .......H.|$.H.t$ + 0420 084889f8 4829f048 85c00f8e 2f010000 .H..H).H..../... + 0430 480faf74 24e84889 f24801fa 488b7c24 H..t$.H..H..H.|$ + 0440 f8488d34 d7488b7c 24f8488d 4cd70848 .H.4.H.|$.H.L..H + 0450 8b7c24e8 488b5c24 904989c0 488b5424 .|$.H.\$.I..H.T$ + 0460 5048c1e7 034929d8 4885db7f 1eeb4690 PH...I).H.....F. + 0470 4801fe48 01f948ff c8c5fb11 0ac5fb11 H..H..H......... + 0480 42084883 c2104939 c0741cc5 fb100ec5 B.H...I9.t...... + 0490 fb100148 85c07fd8 4883c608 4885c074 ...H....H...H..t + 04a0 d24883c1 08ebcf48 8b442490 48c1e004 .H.....H.D$.H... + 04b0 48014424 50488344 24b002f6 04240174 H.D$PH.D$....$.t + 04c0 72488b7c 24b0488b 44240848 89fa4829 rH.|$.H.D$.H..H) + 04d0 c24885d2 7e6e480f af4424e8 4801f848 .H..~nH..D$.H..H + 04e0 8b7c24f8 488d04c7 488b7c24 e8488b5c .|$.H...H.|$.H.\ + 04f0 24904889 d6488b4c 245048c1 e7034829 $.H..H.L$PH...H) + 0500 de4885db 7e2d662e 0f1f8400 00000000 .H..~-f......... + 0510 c5fb1000 4c8d0438 4883c008 4885d249 ....L..8H...H..I + 0520 0f4fc048 ffcac5fb 11014883 c1084839 .O.H......H...H9 + 0530 d675dd48 83c4185b 5d415c41 5d415e31 .u.H...[]A\A]A^1 + 0540 c0415fc3 488b4424 b0488b7c 24f8480f .A_.H.D$.H.|$.H. + 0550 af4424e8 48034424 08488d04 c7eb8948 .D$.H.D$.H.....H + 0560 8b5424b0 488b7c24 08480faf 5424e848 .T$.H.|$.H..T$.H + 0570 8d0c3a48 8b7c24f8 488d34cf 4885c00f ..:H.|$.H.4.H... + 0580 848c0000 00488b7c 24f84803 5424e848 .....H.|$.H.T$.H + 0590 03542408 488d0cd7 e9b2feff ff488b44 .T$.H........H.D + 05a0 24e8488b 7c240848 0faf4424 b0488d0c $.H.|$.H..D$.H.. + 05b0 38488b7c 24f8488d 3ccf4885 d2746a48 8H.|$.H.<.H..tjH + 05c0 8b742408 488b5c24 f8480344 24e8488d .t$.H.\$.H.D$.H. + 05d0 0c304c8d 04cb4883 faff7465 488b7424 .0L...H...teH.t$ + 05e0 08480344 24e8488d 0c30488b 7424f848 .H.D$.H..0H.t$.H + 05f0 8d0cce48 83fafe74 5e488b74 24f84803 ...H...t^H.t$.H. + 0600 4424e848 03442408 488d34c6 e9c6fcff D$.H.D$.H.4..... + 0610 ff488b54 2408488b 7c24b048 0faf5424 .H.T$.H.|$.H..T$ + 0620 e84801fa e91cfeff ff488b44 2408488b .H.......H.D$.H. + 0630 7424b048 0faf4424 e84801f0 e978fcff t$.H..D$.H...x.. + 0640 ff488b44 24e8480f afc6488b 7424b048 .H.D$.H...H.t$.H + 0650 01f0e96c fcffff48 8b442408 488b7424 ...l...H.D$.H.t$ + 0660 b0480faf 4424e848 01f0e95e fcffff .H..D$.H...^... /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 b7010000 00420e10 8f02420e .........B....B. + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 6f060000 00420e10 8f02420e ....o....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606440e 38830703 68010a0e 30410e28 ..D.8...h...0A.( - 0050 420e2042 0e18420e 10440e08 480b0000 B. B..B..D..H... + 0040 8606410e 38830744 0e500329 050a0e38 ..A.8..D.P.)...8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08410b 00000000 ..A..... /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_SKYLAKEX.o (disasm) @@ -10,56 +10,280 @@ push %r13 push %r12 push %rbp - mov %rdi,%rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi + sub $something,%rsp + mov %rsi,(%rsp) + sar $something,%rsi + mov %rdi,-offset(%rsp) mov %rdx,-offset(%rsp) mov %rcx,-offset(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,-offset(%rsp) - mov offset(%rsp),%r10 + mov %r8,-offset(%rsp) + mov %r9,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rcx,%rbx - mov %rbx,%rax + mov %rsi,%r11 + mov %rcx,%rsi + mov %rsi,%rax + shl $something,%rax + mov %rax,-offset(%rsp) + mov %rsi,%rax imul %r8,%rax - mov %r9,%rcx - lea offset(,%rbx,8),%r9 - add %rcx,%rax - lea (%rdx,%rax,8),%r12 - mov %rcx,%rax - imul %rbx,%rax - mov %r8,%rdi - mov %r9,-offset(%rsp) - mov %rbx,%r14 + lea offset(,%rcx,8),%rcx + mov %r8,%r13 + add %r9,%rax + lea (%rdx,%rax,8),%r15 + mov %r9,%rax + imul %rsi,%rax + sub %r9,%r13 + mov %r13,%r12 add %r8,%rax - sub %rcx,%rdi - mov %rbp,%r15 - shl $something,%r14 - lea (%rdx,%rax,8),%r11 - sub %rbp,%rdi - lea (%r8,%rsi,2),%r13 - shl $something,%r15 - mov %r8,%rbx - nopl offset(%rax) - lea (%rdi,%rbp,1),%rax - mov %r11,%rsi - test %rax,%rax + lea (%rdx,%rax,8),%r14 + lea (%r8,%r11,8),%rax + mov %rax,-offset(%rsp) + mov %rcx,%rax + neg %rax + lea offset(%r8),%rdx + imul %r8,%rax + imul %rcx,%rdx + sub %rdi,%r12 + shl $something,%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + mov %rdi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + mov %r8,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + add %rdx,%rax + mov %rax,-offset(%rsp) + cs nopw offset(%rax,%rax,1) + mov %r13,%rdx + mov %r14,%rbx + test %r13,%r13 jle - lea offset(%r11),%rcx - mov %r10,%rdx - test %rbp,%rbp + lea offset(%r14),%rbp + lea offset(%r14),%rsi + lea offset(%r14),%r8 + lea offset(%r14),%r9 + lea offset(%r14),%r10 + lea offset(%r14),%r11 + lea offset(%r14),%rdi + cmpq $something,-offset(%rsp) + mov offset(%rsp),%rax jg jmp - cs nopw offset(%rax,%rax,1) - add %r9,%rsi + nopl (%rax) + add %rcx,%rbx + add %rcx,%rbp + add %rcx,%rsi + add %rcx,%r8 + add %rcx,%r9 + add %rcx,%r10 + add %rcx,%r11 + add %rcx,%rdi + dec %rdx + vmovsd %xmm7,(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + add $something,%rax + cmp %r12,%rdx + je + vmovsd (%rbx),%xmm7 + vmovsd offset(%rbp),%xmm6 + vmovsd (%rsi),%xmm5 + vmovsd (%r8),%xmm4 + vmovsd (%r9),%xmm3 + vmovsd (%r10),%xmm2 + vmovsd (%r11),%xmm1 + vmovsd (%rdi),%xmm0 + test %rdx,%rdx + jg + add $something,%rbx + test %rdx,%rdx + je + add $something,%rbp + cmp $something,%rdx + je + add $something,%rsi + cmp $something,%rdx + je + add $something,%r8 + cmp $something,%rdx + je + add $something,%r9 + cmp $something,%rdx + je + add $something,%r10 + cmp $something,%rdx + je + add $something,%r11 + cmp $something,%rdx + je + add $something,%rdi + jmp + nop + mov -offset(%rsp),%rax + add %rax,offset(%rsp) + addq $something,-offset(%rsp) + add $something,%r13 + add -offset(%rsp),%r15 + add $something,%r14 + mov -offset(%rsp),%rax + add $something,%r12 + cmp %rax,-offset(%rsp) + jne + mov -offset(%rsp),%rax + mov offset(%rsp),%rdi + lea (%rax,%rdi,8),%rax + mov %rax,-offset(%rsp) + testb $something,(%rsp) + je + mov -offset(%rsp),%rdi + mov offset(%rsp),%rax + mov %rdi,%rdx + sub %rax,%rdx + test %rdx,%rdx + jle + imul -offset(%rsp),%rax /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_SKYLAKEX.o (objdump) @@ -2,31 +2,106 @@ /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 554889fd 53488974 AWAVAUATUH..SH.t - 0010 24d848d1 fe488954 24f84889 4c24e84c $.H..H.T$.H.L$.L - 0020 894c24f0 48897424 e04c8b54 24384885 .L$.H.t$.L.T$8H. - 0030 f60f8ed9 00000048 89cb4889 d8490faf .......H..H..I.. - 0040 c04c89c9 4c8d0cdd 00000000 4801c84c .L..L.......H..L - 0050 8d24c248 89c8480f afc34c89 c74c894c .$.H..H...L..L.L - 0060 24d04989 de4c01c0 4829cf49 89ef49c1 $.I..L..H).I..I. - 0070 e6044c8d 1cc24829 ef4d8d2c 7049c1e7 ..L...H).M.,pI.. - 0080 044c89c3 0f1f4000 488d042f 4c89de48 .L....@.H../L..H - 0090 85c00f8e f0000000 498d4b08 4c89d248 ........I.K.L..H - 00a0 85ed7f27 eb4d662e 0f1f8400 00000000 ...'.Mf......... - 00b0 4c01ce4c 01c948ff c8c5fb11 0ac5fb11 L..L..H......... - 00c0 42084883 c2104839 f87425c5 fb100ec5 B.H...H9.t%..... - 00d0 fb100148 85c07fd8 4883c608 4885c074 ...H....H...H..t - 00e0 d24883c1 08ebcf66 0f1f8400 00000000 .H.....f........ - 00f0 4d01fa48 83c3024d 01f44983 c3104883 M..H...M..I...H. - 0100 c7024c39 eb758148 8b4424e0 4d8d0440 ..L9.u.H.D$.M..@ - 0110 f64424d8 01745d48 8b4424f0 4c89c248 .D$..t]H.D$.L..H - 0120 29c24885 d27e7748 0faf4424 e8488b5c ).H..~wH..D$.H.\ - 0130 24f84c01 c0488d04 c3488b7c 24e84889 $.L..H...H.|$.H. - 0140 d648c1e7 034829ee 4885ed7e 270f1f00 .H...H).H..~'... - 0150 c5fb1000 488d0c38 4883c008 4885d248 ....H..8H...H..H - 0160 0f4fc148 ffcac4c1 7b110249 83c20848 .O.H....{..I...H - 0170 39d675dc 5b5d415c 415d415e 31c0415f 9.u.[]A\A]A^1.A_ - 0180 c30f1f80 00000000 4c89e60f 8407ffff ........L....... - 0190 ff488b4c 24d04c01 e1e9fefe ffff4c0f .H.L$.L.......L. - 01a0 af4424e8 488b4424 f0488b5c 24f84c01 .D$.H.D$.H.\$.L. - 01b0 c0488d04 c3eb82 .H..... + 0000 41574156 41554154 55534883 ec184889 AWAVAUATUSH...H. + 0010 342448c1 fe034889 7c249048 895424f8 4$H...H.|$.H.T$. + 0020 48894c24 e84c8944 24b04c89 4c240848 H.L$.L.D$.L.L$.H + 0030 89742410 4885f60f 8e470200 004989f3 .t$.H....G...I.. + 0040 4889ce48 89f048c1 e0064889 4424a048 H..H..H...H.D$.H + 0050 89f0490f afc0488d 0ccd0000 00004d89 ..I...H.......M. + 0060 c54c01c8 4c8d3cc2 4c89c848 0fafc64d .L..L.<.L..H...M + 0070 29cd4d89 ec4c01c0 4c8d34c2 4b8d04d8 ).M..L..L.4.K... + 0080 48894424 984889c8 48f7d849 8d500149 H.D$.H..H..I.P.I + 0090 0fafc048 0fafd149 29fc48c1 e706488d ...H...I).H...H. + 00a0 3402498d 5002480f afd14889 7424f048 4.I.P.H...H.t$.H + 00b0 897c24a8 488d3402 498d5003 480fafd1 .|$.H.4.I.P.H... + 00c0 48897424 b84c8944 2488488d 3402498d H.t$.L.D$.H.4.I. + 00d0 5004480f afd14889 7424c848 8d340249 P.H...H.t$.H.4.I + 00e0 8d500548 0fafd148 897424c0 488d3402 .P.H...H.t$.H.4. + 00f0 498d5006 480fafd1 48897424 d8488d34 I.P.H...H.t$.H.4 + 0100 02498d50 07480faf d1488974 24e04801 .I.P.H...H.t$.H. + 0110 d0488944 24d0662e 0f1f8400 00000000 .H.D$.f......... + 0120 4c89ea4c 89f34d85 ed0f8e41 02000049 L..L..M....A...I + 0130 8d6e0849 8d76104d 8d46184d 8d4e204d .n.I.v.M.F.M.N M + 0140 8d56284d 8d5e3049 8d7e3848 837c2490 .V(M.^0I.~8H.|$. + 0150 00488b44 24507f57 e9ed0000 000f1f00 .H.D$P.W........ + 0160 4801cb48 01cd4801 ce4901c8 4901c949 H..H..H..I..I..I + 0170 01ca4901 cb4801cf 48ffcac5 fb1138c5 ..I..H..H.....8. + 0180 fb117008 c5fb1168 10c5fb11 6018c5fb ..p....h....`... + 0190 115820c5 fb115028 c5fb1148 30c5fb11 .X ...P(...H0... + 01a0 40384883 c0404c39 e20f8491 000000c5 @8H..@L9........ + 01b0 fb103bc5 fb107500 c5fb102e c4c17b10 ..;...u.......{. + 01c0 20c4c17b 1019c4c1 7b1012c4 c17b100b ..{....{....{.. + 01d0 c5fb1007 4885d27f 874883c3 084885d2 ....H....H...H.. + 01e0 74814883 c5084883 faff0f84 76ffffff t.H...H.....v... + 01f0 4883c608 4883fafe 0f846bff ffff4983 H...H.....k...I. + 0200 c0084883 fafd0f84 60ffffff 4983c108 ..H.....`...I... + 0210 4883fafc 0f8455ff ffff4983 c2084883 H.....U...I...H. + 0220 fafb0f84 4affffff 4983c308 4883fafa ....J...I...H... + 0230 0f843fff ffff4883 c708e939 ffffff90 ..?...H....9.... + 0240 488b4424 a8480144 24504883 44248808 H.D$.H.D$PH.D$.. + 0250 4983c508 4c037c24 a04983c6 40488b44 I...L.|$.I..@H.D + 0260 24884983 c4084839 4424980f 85affeff $.I...H9D$...... + 0270 ff488b44 24b0488b 7c241048 8d04f848 .H.D$.H.|$.H...H + 0280 894424b0 f6042404 0f847f01 0000488b .D$...$.......H. + 0290 7c24b048 8b442408 4889fa48 29c24885 |$.H.D$.H..H).H. + 02a0 d20f8ef6 02000048 0faf4424 e84801f8 .......H..D$.H.. + 02b0 488b7c24 f8488d3c c7488b74 24f84c8d H.|$.H.<.H.t$.L. + 02c0 44c60848 8b7424f8 488d4cc6 10488b74 D..H.t$.H.L..H.t + 02d0 24f8488d 74c61848 8b4424e8 488b5c24 $.H.t..H.D$.H.\$ + 02e0 904989d2 4c8d0cc5 00000000 4929da48 .I..L.......I).H + 02f0 8b442450 4885db7f 36e90901 00006690 .D$PH...6.....f. + 0300 4c01cf4d 01c84c01 c94c01ce 48ffcac5 L..M..L..L..H... + 0310 fb1118c5 fb115008 c5fb1148 10c5fb11 ......P....H.... + 0320 40184883 c0204939 d20f84ca 000000c5 @.H.. I9........ + 0330 fb101fc4 c17b1010 c5fb1009 c5fb1006 .....{.......... + 0340 4885d27f bb4883c7 084885d2 74b54983 H....H...H..t.I. + 0350 c0084883 faff74ae 4883c108 4883fafe ..H...t.H...H... + 0360 74a74883 c608eba4 0f1f8400 00000000 t.H............. + 0370 4c89fb0f 84b6fdff ff488b44 24f04a8d L........H.D$.J. + 0380 2c384983 fdff0f84 a7fdffff 488b4424 ,8I.........H.D$ + 0390 b84a8d34 384983fd fe0f8498 fdffff48 .J.48I.........H + 03a0 8b4424c8 4e8d0438 4983fdfd 0f8489fd .D$.N..8I....... + 03b0 ffff488b 4424c04e 8d0c3849 83fdfc0f ..H.D$.N..8I.... + 03c0 847afdff ff488b44 24d84d8d 14074983 .z...H.D$.M...I. + 03d0 fdfb0f84 6bfdffff 488b4424 e04d8d1c ....k...H.D$.M.. + 03e0 074983fd fa0f845c fdffff48 8b4424d0 .I.....\...H.D$. + 03f0 498d3c07 e952fdff ff488b44 249048c1 I.<..R...H.D$.H. + 0400 e0054801 44245048 834424b0 04f60424 ..H.D$PH.D$....$ + 0410 020f84a4 00000048 8b7c24b0 488b7424 .......H.|$.H.t$ + 0420 084889f8 4829f048 85c00f8e 2f010000 .H..H).H..../... + 0430 480faf74 24e84889 f24801fa 488b7c24 H..t$.H..H..H.|$ + 0440 f8488d34 d7488b7c 24f8488d 4cd70848 .H.4.H.|$.H.L..H + 0450 8b7c24e8 488b5c24 904989c0 488b5424 .|$.H.\$.I..H.T$ + 0460 5048c1e7 034929d8 4885db7f 1eeb4690 PH...I).H.....F. + 0470 4801fe48 01f948ff c8c5fb11 0ac5fb11 H..H..H......... + 0480 42084883 c2104939 c0741cc5 fb100ec5 B.H...I9.t...... + 0490 fb100148 85c07fd8 4883c608 4885c074 ...H....H...H..t + 04a0 d24883c1 08ebcf48 8b442490 48c1e004 .H.....H.D$.H... + 04b0 48014424 50488344 24b002f6 04240174 H.D$PH.D$....$.t + 04c0 72488b7c 24b0488b 44240848 89fa4829 rH.|$.H.D$.H..H) + 04d0 c24885d2 7e6e480f af4424e8 4801f848 .H..~nH..D$.H..H + 04e0 8b7c24f8 488d04c7 488b7c24 e8488b5c .|$.H...H.|$.H.\ + 04f0 24904889 d6488b4c 245048c1 e7034829 $.H..H.L$PH...H) + 0500 de4885db 7e2d662e 0f1f8400 00000000 .H..~-f......... + 0510 c5fb1000 4c8d0438 4883c008 4885d249 ....L..8H...H..I + 0520 0f4fc048 ffcac5fb 11014883 c1084839 .O.H......H...H9 + 0530 d675dd48 83c4185b 5d415c41 5d415e31 .u.H...[]A\A]A^1 + 0540 c0415fc3 488b4424 b0488b7c 24f8480f .A_.H.D$.H.|$.H. + 0550 af4424e8 48034424 08488d04 c7eb8948 .D$.H.D$.H.....H + 0560 8b5424b0 488b7c24 08480faf 5424e848 .T$.H.|$.H..T$.H + 0570 8d0c3a48 8b7c24f8 488d34cf 4885c00f ..:H.|$.H.4.H... + 0580 848c0000 00488b7c 24f84803 5424e848 .....H.|$.H.T$.H + 0590 03542408 488d0cd7 e9b2feff ff488b44 .T$.H........H.D + 05a0 24e8488b 7c240848 0faf4424 b0488d0c $.H.|$.H..D$.H.. + 05b0 38488b7c 24f8488d 3ccf4885 d2746a48 8H.|$.H.<.H..tjH + 05c0 8b742408 488b5c24 f8480344 24e8488d .t$.H.\$.H.D$.H. + 05d0 0c304c8d 04cb4883 faff7465 488b7424 .0L...H...teH.t$ + 05e0 08480344 24e8488d 0c30488b 7424f848 .H.D$.H..0H.t$.H + 05f0 8d0cce48 83fafe74 5e488b74 24f84803 ...H...t^H.t$.H. + 0600 4424e848 03442408 488d34c6 e9c6fcff D$.H.D$.H.4..... + 0610 ff488b54 2408488b 7c24b048 0faf5424 .H.T$.H.|$.H..T$ + 0620 e84801fa e91cfeff ff488b44 2408488b .H.......H.D$.H. + 0630 7424b048 0faf4424 e84801f0 e978fcff t$.H..D$.H...x.. + 0640 ff488b44 24e8480f afc6488b 7424b048 .H.D$.H...H.t$.H + 0650 01f0e96c fcffff48 8b442408 488b7424 ...l...H.D$.H.t$ + 0660 b0480faf 4424e848 01f0e95e fcffff .H..D$.H...^... /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_oltcopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 b7010000 00420e10 8f02420e .........B....B. + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 6f060000 00420e10 8f02420e ....o....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606440e 38830703 68010a0e 30410e28 ..D.8...h...0A.( - 0050 420e2042 0e18420e 10440e08 480b0000 B. B..B..D..H... + 0040 8606410e 38830744 0e500329 050a0e38 ..A.8..D.P.)...8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08410b 00000000 ..A..... /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_COOPERLAKE.o (disasm) @@ -10,111 +10,340 @@ push %r13 push %r12 push %rbp - mov %rdi,%rbp push %rbx + sub $something,%rsp mov %rsi,-offset(%rsp) - sar %rsi + sar $something,%rsi + mov %rdi,-offset(%rsp) mov %rdx,-offset(%rsp) mov %rcx,-offset(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,-offset(%rsp) - mov offset(%rsp),%r11 + mov %r8,-offset(%rsp) + mov %r9,(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %r9,%rbx - mov %rbx,%rax - imul %rcx,%rax - lea offset(,%rcx,8),%r9 - mov %rcx,%r14 + mov %rsi,%r11 + mov %r9,%rax + mov %rcx,%rsi + imul %rsi,%rax + mov %r8,%r13 + sub %r9,%r13 add %r8,%rax - lea (%rdx,%rax,8),%r12 + lea (%rdx,%rax,8),%r15 + mov %rsi,%rax + shl $something,%rax + mov %rax,-offset(%rsp) lea offset(%r8),%rax - imul %rax,%rcx - mov %rdx,%rdi - mov %r8,%r10 - mov %rcx,%rdx - add %rbx,%rdx - sub %rbx,%r10 - lea (%rdi,%rdx,8),%rbx + imul %rsi,%rax + lea offset(,%rcx,8),%rcx + mov %r13,%r12 + add %r9,%rax + lea (%rdx,%rax,8),%r14 + lea offset(%r13,%r11,8),%rax + mov %rax,-offset(%rsp) + mov %r8,%rax + neg %rax + lea -offset(,%rax,8),%rax mov %r8,%rdx - sub %rax,%rdx - mov %rdx,%rax - imul %r9,%rax - mov %r10,%rdi - mov %rbp,%r15 - mov %r8,-offset(%rsp) - shl $something,%r14 - sub %rbp,%rdi - lea (%r10,%rsi,2),%r13 - shl $something,%r15 - mov %rax,%r8 + imul %rsi,%rax + imul %rcx,%rdx + sub %rdi,%r12 + shl $something,%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + mov %rdi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + add %rdx,%rax + mov %rax,-offset(%rsp) + nopw offset(%rax,%rax,1) + mov %r13,%rdx + test %r13,%r13 + jle + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%rbx + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%rbp + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%rsi + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%r8 + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%r9 + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%r10 + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%r11 + mov %r14,%rdi + cmpq $something,-offset(%rsp) + mov offset(%rsp),%rax + jg + jmp + add $something,%rbx + add $something,%rbp + add $something,%rsi + add $something,%r8 + add $something,%r9 + add $something,%r10 + add $something,%r11 + add $something,%rdi + dec %rdx + vmovsd %xmm7,(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + add $something,%rax + cmp %r12,%rdx + je + vmovsd (%rbx),%xmm7 + vmovsd offset(%rbp),%xmm6 + vmovsd (%rsi),%xmm5 + vmovsd (%r8),%xmm4 + vmovsd (%r9),%xmm3 + vmovsd (%r10),%xmm2 + vmovsd (%r11),%xmm1 + vmovsd (%rdi),%xmm0 + test %rdx,%rdx + jg + add %rcx,%rbx + test %rdx,%rdx + je + add %rcx,%rbp + cmp $something,%rdx + je + add %rcx,%rsi + cmp $something,%rdx + je + add %rcx,%r8 + cmp $something,%rdx + je + add %rcx,%r9 + cmp $something,%rdx + je + add %rcx,%r10 + cmp $something,%rdx + je + add %rcx,%r11 + cmp $something,%rdx + je + add %rcx,%rdi + jmp + nopw offset(%rax,%rax,1) + mov -offset(%rsp),%rax + add %rax,offset(%rsp) + add $something,%r13 + add $something,%r15 + add -offset(%rsp),%r14 + add $something,%r12 + cmp -offset(%rsp),%r13 + jne + mov -offset(%rsp),%rax + mov offset(%rsp),%rdi + lea (%rax,%rdi,8),%rax + mov %rax,-offset(%rsp) + testb $something,-offset(%rsp) + je + mov -offset(%rsp),%rdi + mov (%rsp),%rbx + mov %rdi,%rdx + sub %rbx,%rdx + test %rdx,%rdx + jle + mov -offset(%rsp),%rax + imul %rdi,%rax /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_COOPERLAKE.o (objdump) @@ -2,32 +2,103 @@ /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 554889fd 53488974 AWAVAUATUH..SH.t - 0010 24d048d1 fe488954 24f84889 4c24e04c $.H..H.T$.H.L$.L - 0020 894c24f0 48897424 d84c8b5c 24384885 .L$.H.t$.L.\$8H. - 0030 f60f8eee 0000004c 89cb4889 d8480faf .......L..H..H.. - 0040 c14c8d0c cd000000 004989ce 4c01c04c .L.......I..L..L - 0050 8d24c249 8d400148 0fafc848 89d74d89 .$.I.@.H...H..M. - 0060 c24889ca 4801da49 29da488d 1cd74c89 .H..H..I).H...L. - 0070 c24829c2 4889d049 0fafc14c 89d74989 .H).H..I...L..I. - 0080 ef4c8944 24e849c1 e6044829 ef4d8d2c .L.D$.I...H).M., - 0090 7249c1e7 044989c0 0f1f8400 00000000 rI...I.......... - 00a0 4c89d04a 8d34034d 85d20f8e f0000000 L..J.4.M........ - 00b0 4889d94c 89da4885 ed7f22eb 460f1f00 H..L..H...".F... - 00c0 4883c608 4883c108 48ffc8c5 fb110ac5 H...H...H....... - 00d0 fb114208 4883c210 4839f874 23c5fb10 ..B.H...H9.t#... - 00e0 0ec5fb10 014885c0 7fd64c01 ce4885c0 .....H....L..H.. - 00f0 74d24c01 c9ebd166 0f1f8400 00000000 t.L....f........ - 0100 4d01fb49 83c20249 83c4104c 01f34883 M..I...I...L..H. - 0110 c7024d39 ea75894c 8b4424e8 488b4424 ..M9.u.L.D$.H.D$ - 0120 d84d8d04 40f64424 d001745f 488b4424 .M..@.D$..t_H.D$ - 0130 f04c89c2 4829c248 85d27e77 4c0faf44 .L..H).H..~wL..D - 0140 24e0488b 5c24f84c 01c0488d 04c3488b $.H.\$.L..H...H. - 0150 7c24e048 89d648c1 e7034829 ee4885ed |$.H..H...H).H.. - 0160 7e29660f 1f440000 c5fb1000 488d4808 ~)f..D......H.H. - 0170 4801f848 85d2480f 4fc148ff cac4c17b H..H..H.O.H....{ - 0180 11034983 c3084839 f275dd5b 5d415c41 ..I...H9.u.[]A\A - 0190 5d415e31 c0415fc3 0f1f8400 00000000 ]A^1.A_......... - 01a0 4c89e60f 8407ffff ff498d4c 2408e900 L........I.L$... - 01b0 ffffff48 8b4424f0 488b5c24 f8480faf ...H.D$.H.\$.H.. - 01c0 4424e04c 01c0488d 04c3eb82 D$.L..H..... + 0000 41574156 41554154 55534883 ec104889 AWAVAUATUSH...H. + 0010 7424f848 c1fe0348 897c2488 48895424 t$.H...H.|$.H.T$ + 0020 f048894c 24e84c89 4424a84c 890c2448 .H.L$.L.D$.L..$H + 0030 89742408 4885f60f 8e6c0200 004989f3 .t$.H....l...I.. + 0040 4c89c848 89ce480f afc64d89 c54d29cd L..H..H...M..M). + 0050 4c01c04c 8d3cc248 89f048c1 e0064889 L..L.<.H..H...H. + 0060 44249049 8d400748 0fafc648 8d0ccd00 D$.I.@.H...H.... + 0070 0000004d 89ec4c01 c84c8d34 c24b8d44 ...M..L..L.4.K.D + 0080 dd004889 4424984c 89c048f7 d8488d04 ..H.D$.L..H..H.. + 0090 c5c8ffff ff4c89c2 480fafc6 480fafd1 .....L..H...H... + 00a0 4929fc48 c1e70648 8d340249 8d500148 I).H...H.4.I.P.H + 00b0 0fafd148 897424c0 48897c24 a0488d34 ...H.t$.H.|$.H.4 + 00c0 02498d50 02480faf d1488974 24b8488d .I.P.H...H.t$.H. + 00d0 3402498d 5003480f afd14889 7424b048 4.I.P.H...H.t$.H + 00e0 8d340249 8d500448 0fafd148 897424d8 .4.I.P.H...H.t$. + 00f0 488d3402 498d5005 480fafd1 48897424 H.4.I.P.H...H.t$ + 0100 d0488d34 02498d50 06480faf d1488974 .H.4.I.P.H...H.t + 0110 24c84801 d0488944 24e0660f 1f440000 $.H..H.D$.f..D.. + 0120 4c89ea4d 85ed0f8e a4020000 488b4424 L..M........H.D$ + 0130 c0498d1c 06488b44 24b8498d 2c06488b .I...H.D$.I.,.H. + 0140 4424b049 8d340648 8b4424d8 4d8d0406 D$.I.4.H.D$.M... + 0150 488b4424 d04d8d0c 06488b44 24c84d8d H.D$.M...H.D$.M. + 0160 1406488b 4424e04d 8d1c064c 89f74883 ..H.D$.M...L..H. + 0170 7c248800 488b4424 487f5ce9 fa000000 |$..H.D$H.\..... + 0180 4883c308 4883c508 4883c608 4983c008 H...H...H...I... + 0190 4983c108 4983c208 4983c308 4883c708 I...I...I...H... + 01a0 48ffcac5 fb1138c5 fb117008 c5fb1168 H.....8...p....h + 01b0 10c5fb11 6018c5fb 115820c5 fb115028 ....`....X ...P( + 01c0 c5fb1148 30c5fb11 40384883 c0404c39 ...H0...@8H..@L9 + 01d0 e20f8499 000000c5 fb103bc5 fb107500 ..........;...u. + 01e0 c5fb102e c4c17b10 20c4c17b 1019c4c1 ......{. ..{.... + 01f0 7b1012c4 c17b100b c5fb1007 4885d20f {....{......H... + 0200 8f7bffff ff4801cb 4885d20f 8473ffff .{...H..H....s.. + 0210 ff4801cd 4883faff 0f846aff ffff4801 .H..H.....j...H. + 0220 ce4883fa fe0f8461 ffffff49 01c84883 .H.....a...I..H. + 0230 fafd0f84 58ffffff 4901c948 83fafc0f ....X...I..H.... + 0240 844fffff ff4901ca 4883fafb 0f8446ff .O...I..H.....F. + 0250 ffff4901 cb4883fa fa0f843d ffffff48 ..I..H.....=...H + 0260 01cfe939 ffffff66 0f1f8400 00000000 ...9...f........ + 0270 488b4424 a0480144 24484983 c5084983 H.D$.H.D$HI...I. + 0280 c7404c03 74249049 83c4084c 3b6c2498 .@L.t$.I...L;l$. + 0290 0f858afe ffff488b 4424a848 8b7c2408 ......H.D$.H.|$. + 02a0 488d04f8 48894424 a8f64424 f8040f84 H...H.D$..D$.... + 02b0 96010000 488b7c24 a8488b1c 244889fa ....H.|$.H..$H.. + 02c0 4829da48 85d20f8e 15030000 488b4424 H).H........H.D$ + 02d0 e8480faf c7488b7c 24f04801 d8488d3c .H...H.|$.H..H.< + 02e0 c7488b44 24a8488b 5c24f048 ffc0480f .H.D$.H.\$.H..H. + 02f0 af4424e8 48030424 4c8d04c3 488b4424 .D$.H..$L...H.D$ + 0300 a8488b5c 24f04883 c002480f af4424e8 .H.\$.H...H..D$. + 0310 48030424 488d0cc3 488b4424 a8488b5c H..$H...H.D$.H.\ + 0320 24f04883 c003480f af4424e8 48030424 $.H...H..D$.H..$ + 0330 488d34c3 488b4424 e8488b5c 24884989 H.4.H.D$.H.\$.I. + 0340 d24c8d0c c5000000 004929da 488b4424 .L.......I).H.D$ + 0350 484885db 7f3de9e9 0000000f 1f440000 HH...=.......D.. + 0360 4883c708 4983c008 4883c108 4883c608 H...I...H...H... + 0370 48ffcac5 fb1118c5 fb115008 c5fb1148 H.........P....H + 0380 10c5fb11 40184883 c0204939 d20f84a3 ....@.H.. I9.... + 0390 000000c5 fb101fc4 c17b1010 c5fb1009 .........{...... + 03a0 c5fb1006 4885d27f b74c01cf 4885d274 ....H....L..H..t + 03b0 b34d01c8 4883faff 74ae4c01 c94883fa .M..H...t.L..H.. + 03c0 fe74a94c 01ceeba8 0f1f8400 00000000 .t.L............ + 03d0 4c89fb0f 845cfdff ff498d6f 084983fd L....\...I.o.I.. + 03e0 ff0f8457 fdffff49 8d771049 83fdfe0f ...W...I.w.I.... + 03f0 8452fdff ff4d8d47 184983fd fd0f844d .R...M.G.I.....M + 0400 fdffff4d 8d4f2049 83fdfc0f 8448fdff ...M.O I.....H.. + 0410 ff4d8d57 284983fd fb0f8443 fdffff4d .M.W(I.....C...M + 0420 8d5f3049 83fdfa0f 843efdff ff498d7f ._0I.....>...I.. + 0430 38e938fd ffff488b 44248848 c1e00548 8.8...H.D$.H...H + 0440 01442448 48834424 a804f644 24f8020f .D$HH.D$...D$... + 0450 84be0000 00488b7c 24a8488b 1c244889 .....H.|$.H..$H. + 0460 f84829d8 4885c00f 8e400100 00480faf .H).H....@...H.. + 0470 7c24e848 89fa488b 7c24f048 01da488d |$.H..H.|$.H..H. + 0480 34d7488b 7c24a848 8d570148 0faf5424 4.H.|$.H.W.H..T$ + 0490 e8488b7c 24f04803 1424488d 0cd7488b .H.|$.H..$H...H. + 04a0 7c24e848 8b5c2488 4c8d04fd 00000000 |$.H.\$.L....... + 04b0 4889c748 8b542448 4829df48 85db7f25 H..H.T$HH).H...% + 04c0 eb4b660f 1f440000 4883c608 4883c108 .Kf..D..H...H... + 04d0 48ffc8c5 fb110ac5 fb114208 4883c210 H.........B.H... + 04e0 4839c774 1ac5fb10 0ec5fb10 014885c0 H9.t.........H.. + 04f0 7fd64c01 c64885c0 74d24c01 c1ebd148 ..L..H..t.L....H + 0500 8b442488 48c1e004 48014424 48488344 .D$.H...H.D$HH.D + 0510 24a802f6 4424f801 7468488b 4424a848 $...D$..thH.D$.H + 0520 8b3c2448 89c24829 fa4885d2 7e65480f .<$H..H).H..~eH. + 0530 af4424e8 4801f848 8b7c24f0 488d04c7 .D$.H..H.|$.H... + 0540 488b7c24 e8488b5c 24884889 d6488b4c H.|$.H.\$.H..H.L + 0550 244848c1 e7034829 de4885db 7e246690 $HH...H).H..~$f. + 0560 c5fb1000 4c8d4008 4801f848 85d2490f ....L.@.H..H..I. + 0570 4fc048ff cac5fb11 014883c1 084839d6 O.H......H...H9. + 0580 75de4883 c4105b5d 415c415d 415e31c0 u.H...[]A\A]A^1. + 0590 415fc348 8b042448 8b7c24f0 480faf44 A_.H..$H.|$.H..D + 05a0 24e84803 4424a848 8d04c7eb 93488b14 $.H.D$.H.....H.. + 05b0 24488b7c 24f0480f af5424e8 48035424 $H.|$.H..T$.H.T$ + 05c0 a848c1e2 03488d34 174885c0 0f84b0fe .H...H.4.H...... + 05d0 ffff488b 7c24f048 8d4c1708 e9bdfeff ..H.|$.H.L...... + 05e0 ff488b04 24488b7c 24f0480f af4424e8 .H..$H.|$.H..D$. + 05f0 48034424 a848c1e0 034801c7 4885d20f H.D$.H...H..H... + 0600 84dcfcff ff488b5c 24f04c8d 44030848 .....H.\$.L.D..H + 0610 83faff0f 84e3fcff ff488b5c 24f0488d .........H.\$.H. + 0620 4c031048 83fafe0f 84ebfcff ff488b5c L..H.........H.\ + 0630 24f0488d 740318e9 f8fcffff $.H.t....... /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 cc010000 00420e10 8f02420e .........B....B. + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 3c060000 00420e10 8f02420e ....<....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606440e 38830703 7f010a0e 30410e28 ..D.8.......0A.( - 0050 420e2042 0e18420e 10440e08 490b0000 B. B..B..D..I... + 0040 8606410e 38830744 0e480378 050a0e38 ..A.8..D.H.x...8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08410b 00000000 ..A..... /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_SKYLAKEX.o (disasm) @@ -10,111 +10,340 @@ push %r13 push %r12 push %rbp - mov %rdi,%rbp push %rbx + sub $something,%rsp mov %rsi,-offset(%rsp) - sar %rsi + sar $something,%rsi + mov %rdi,-offset(%rsp) mov %rdx,-offset(%rsp) mov %rcx,-offset(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,-offset(%rsp) - mov offset(%rsp),%r11 + mov %r8,-offset(%rsp) + mov %r9,(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %r9,%rbx - mov %rbx,%rax - imul %rcx,%rax - lea offset(,%rcx,8),%r9 - mov %rcx,%r14 + mov %rsi,%r11 + mov %r9,%rax + mov %rcx,%rsi + imul %rsi,%rax + mov %r8,%r13 + sub %r9,%r13 add %r8,%rax - lea (%rdx,%rax,8),%r12 + lea (%rdx,%rax,8),%r15 + mov %rsi,%rax + shl $something,%rax + mov %rax,-offset(%rsp) lea offset(%r8),%rax - imul %rax,%rcx - mov %rdx,%rdi - mov %r8,%r10 - mov %rcx,%rdx - add %rbx,%rdx - sub %rbx,%r10 - lea (%rdi,%rdx,8),%rbx + imul %rsi,%rax + lea offset(,%rcx,8),%rcx + mov %r13,%r12 + add %r9,%rax + lea (%rdx,%rax,8),%r14 + lea offset(%r13,%r11,8),%rax + mov %rax,-offset(%rsp) + mov %r8,%rax + neg %rax + lea -offset(,%rax,8),%rax mov %r8,%rdx - sub %rax,%rdx - mov %rdx,%rax - imul %r9,%rax - mov %r10,%rdi - mov %rbp,%r15 - mov %r8,-offset(%rsp) - shl $something,%r14 - sub %rbp,%rdi - lea (%r10,%rsi,2),%r13 - shl $something,%r15 - mov %rax,%r8 + imul %rsi,%rax + imul %rcx,%rdx + sub %rdi,%r12 + shl $something,%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + mov %rdi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + add %rdx,%rax + mov %rax,-offset(%rsp) + nopw offset(%rax,%rax,1) + mov %r13,%rdx + test %r13,%r13 + jle + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%rbx + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%rbp + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%rsi + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%r8 + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%r9 + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%r10 + mov -offset(%rsp),%rax + lea (%r14,%rax,1),%r11 + mov %r14,%rdi + cmpq $something,-offset(%rsp) + mov offset(%rsp),%rax + jg + jmp + add $something,%rbx + add $something,%rbp + add $something,%rsi + add $something,%r8 + add $something,%r9 + add $something,%r10 + add $something,%r11 + add $something,%rdi + dec %rdx + vmovsd %xmm7,(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + add $something,%rax + cmp %r12,%rdx + je + vmovsd (%rbx),%xmm7 + vmovsd offset(%rbp),%xmm6 + vmovsd (%rsi),%xmm5 + vmovsd (%r8),%xmm4 + vmovsd (%r9),%xmm3 + vmovsd (%r10),%xmm2 + vmovsd (%r11),%xmm1 + vmovsd (%rdi),%xmm0 + test %rdx,%rdx + jg + add %rcx,%rbx + test %rdx,%rdx + je + add %rcx,%rbp + cmp $something,%rdx + je + add %rcx,%rsi + cmp $something,%rdx + je + add %rcx,%r8 + cmp $something,%rdx + je + add %rcx,%r9 + cmp $something,%rdx + je + add %rcx,%r10 + cmp $something,%rdx + je + add %rcx,%r11 + cmp $something,%rdx + je + add %rcx,%rdi + jmp + nopw offset(%rax,%rax,1) + mov -offset(%rsp),%rax + add %rax,offset(%rsp) + add $something,%r13 + add $something,%r15 + add -offset(%rsp),%r14 + add $something,%r12 + cmp -offset(%rsp),%r13 + jne + mov -offset(%rsp),%rax + mov offset(%rsp),%rdi + lea (%rax,%rdi,8),%rax + mov %rax,-offset(%rsp) + testb $something,-offset(%rsp) + je + mov -offset(%rsp),%rdi + mov (%rsp),%rbx + mov %rdi,%rdx + sub %rbx,%rdx + test %rdx,%rdx + jle + mov -offset(%rsp),%rax + imul %rdi,%rax /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_SKYLAKEX.o (objdump) @@ -2,32 +2,103 @@ /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 554889fd 53488974 AWAVAUATUH..SH.t - 0010 24d048d1 fe488954 24f84889 4c24e04c $.H..H.T$.H.L$.L - 0020 894c24f0 48897424 d84c8b5c 24384885 .L$.H.t$.L.\$8H. - 0030 f60f8eee 0000004c 89cb4889 d8480faf .......L..H..H.. - 0040 c14c8d0c cd000000 004989ce 4c01c04c .L.......I..L..L - 0050 8d24c249 8d400148 0fafc848 89d74d89 .$.I.@.H...H..M. - 0060 c24889ca 4801da49 29da488d 1cd74c89 .H..H..I).H...L. - 0070 c24829c2 4889d049 0fafc14c 89d74989 .H).H..I...L..I. - 0080 ef4c8944 24e849c1 e6044829 ef4d8d2c .L.D$.I...H).M., - 0090 7249c1e7 044989c0 0f1f8400 00000000 rI...I.......... - 00a0 4c89d04a 8d34034d 85d20f8e f0000000 L..J.4.M........ - 00b0 4889d94c 89da4885 ed7f22eb 460f1f00 H..L..H...".F... - 00c0 4883c608 4883c108 48ffc8c5 fb110ac5 H...H...H....... - 00d0 fb114208 4883c210 4839f874 23c5fb10 ..B.H...H9.t#... - 00e0 0ec5fb10 014885c0 7fd64c01 ce4885c0 .....H....L..H.. - 00f0 74d24c01 c9ebd166 0f1f8400 00000000 t.L....f........ - 0100 4d01fb49 83c20249 83c4104c 01f34883 M..I...I...L..H. - 0110 c7024d39 ea75894c 8b4424e8 488b4424 ..M9.u.L.D$.H.D$ - 0120 d84d8d04 40f64424 d001745f 488b4424 .M..@.D$..t_H.D$ - 0130 f04c89c2 4829c248 85d27e77 4c0faf44 .L..H).H..~wL..D - 0140 24e0488b 5c24f84c 01c0488d 04c3488b $.H.\$.L..H...H. - 0150 7c24e048 89d648c1 e7034829 ee4885ed |$.H..H...H).H.. - 0160 7e29660f 1f440000 c5fb1000 488d4808 ~)f..D......H.H. - 0170 4801f848 85d2480f 4fc148ff cac4c17b H..H..H.O.H....{ - 0180 11034983 c3084839 f275dd5b 5d415c41 ..I...H9.u.[]A\A - 0190 5d415e31 c0415fc3 0f1f8400 00000000 ]A^1.A_......... - 01a0 4c89e60f 8407ffff ff498d4c 2408e900 L........I.L$... - 01b0 ffffff48 8b4424f0 488b5c24 f8480faf ...H.D$.H.\$.H.. - 01c0 4424e04c 01c0488d 04c3eb82 D$.L..H..... + 0000 41574156 41554154 55534883 ec104889 AWAVAUATUSH...H. + 0010 7424f848 c1fe0348 897c2488 48895424 t$.H...H.|$.H.T$ + 0020 f048894c 24e84c89 4424a84c 890c2448 .H.L$.L.D$.L..$H + 0030 89742408 4885f60f 8e6c0200 004989f3 .t$.H....l...I.. + 0040 4c89c848 89ce480f afc64d89 c54d29cd L..H..H...M..M). + 0050 4c01c04c 8d3cc248 89f048c1 e0064889 L..L.<.H..H...H. + 0060 44249049 8d400748 0fafc648 8d0ccd00 D$.I.@.H...H.... + 0070 0000004d 89ec4c01 c84c8d34 c24b8d44 ...M..L..L.4.K.D + 0080 dd004889 4424984c 89c048f7 d8488d04 ..H.D$.L..H..H.. + 0090 c5c8ffff ff4c89c2 480fafc6 480fafd1 .....L..H...H... + 00a0 4929fc48 c1e70648 8d340249 8d500148 I).H...H.4.I.P.H + 00b0 0fafd148 897424c0 48897c24 a0488d34 ...H.t$.H.|$.H.4 + 00c0 02498d50 02480faf d1488974 24b8488d .I.P.H...H.t$.H. + 00d0 3402498d 5003480f afd14889 7424b048 4.I.P.H...H.t$.H + 00e0 8d340249 8d500448 0fafd148 897424d8 .4.I.P.H...H.t$. + 00f0 488d3402 498d5005 480fafd1 48897424 H.4.I.P.H...H.t$ + 0100 d0488d34 02498d50 06480faf d1488974 .H.4.I.P.H...H.t + 0110 24c84801 d0488944 24e0660f 1f440000 $.H..H.D$.f..D.. + 0120 4c89ea4d 85ed0f8e a4020000 488b4424 L..M........H.D$ + 0130 c0498d1c 06488b44 24b8498d 2c06488b .I...H.D$.I.,.H. + 0140 4424b049 8d340648 8b4424d8 4d8d0406 D$.I.4.H.D$.M... + 0150 488b4424 d04d8d0c 06488b44 24c84d8d H.D$.M...H.D$.M. + 0160 1406488b 4424e04d 8d1c064c 89f74883 ..H.D$.M...L..H. + 0170 7c248800 488b4424 487f5ce9 fa000000 |$..H.D$H.\..... + 0180 4883c308 4883c508 4883c608 4983c008 H...H...H...I... + 0190 4983c108 4983c208 4983c308 4883c708 I...I...I...H... + 01a0 48ffcac5 fb1138c5 fb117008 c5fb1168 H.....8...p....h + 01b0 10c5fb11 6018c5fb 115820c5 fb115028 ....`....X ...P( + 01c0 c5fb1148 30c5fb11 40384883 c0404c39 ...H0...@8H..@L9 + 01d0 e20f8499 000000c5 fb103bc5 fb107500 ..........;...u. + 01e0 c5fb102e c4c17b10 20c4c17b 1019c4c1 ......{. ..{.... + 01f0 7b1012c4 c17b100b c5fb1007 4885d20f {....{......H... + 0200 8f7bffff ff4801cb 4885d20f 8473ffff .{...H..H....s.. + 0210 ff4801cd 4883faff 0f846aff ffff4801 .H..H.....j...H. + 0220 ce4883fa fe0f8461 ffffff49 01c84883 .H.....a...I..H. + 0230 fafd0f84 58ffffff 4901c948 83fafc0f ....X...I..H.... + 0240 844fffff ff4901ca 4883fafb 0f8446ff .O...I..H.....F. + 0250 ffff4901 cb4883fa fa0f843d ffffff48 ..I..H.....=...H + 0260 01cfe939 ffffff66 0f1f8400 00000000 ...9...f........ + 0270 488b4424 a0480144 24484983 c5084983 H.D$.H.D$HI...I. + 0280 c7404c03 74249049 83c4084c 3b6c2498 .@L.t$.I...L;l$. + 0290 0f858afe ffff488b 4424a848 8b7c2408 ......H.D$.H.|$. + 02a0 488d04f8 48894424 a8f64424 f8040f84 H...H.D$..D$.... + 02b0 96010000 488b7c24 a8488b1c 244889fa ....H.|$.H..$H.. + 02c0 4829da48 85d20f8e 15030000 488b4424 H).H........H.D$ + 02d0 e8480faf c7488b7c 24f04801 d8488d3c .H...H.|$.H..H.< + 02e0 c7488b44 24a8488b 5c24f048 ffc0480f .H.D$.H.\$.H..H. + 02f0 af4424e8 48030424 4c8d04c3 488b4424 .D$.H..$L...H.D$ + 0300 a8488b5c 24f04883 c002480f af4424e8 .H.\$.H...H..D$. + 0310 48030424 488d0cc3 488b4424 a8488b5c H..$H...H.D$.H.\ + 0320 24f04883 c003480f af4424e8 48030424 $.H...H..D$.H..$ + 0330 488d34c3 488b4424 e8488b5c 24884989 H.4.H.D$.H.\$.I. + 0340 d24c8d0c c5000000 004929da 488b4424 .L.......I).H.D$ + 0350 484885db 7f3de9e9 0000000f 1f440000 HH...=.......D.. + 0360 4883c708 4983c008 4883c108 4883c608 H...I...H...H... + 0370 48ffcac5 fb1118c5 fb115008 c5fb1148 H.........P....H + 0380 10c5fb11 40184883 c0204939 d20f84a3 ....@.H.. I9.... + 0390 000000c5 fb101fc4 c17b1010 c5fb1009 .........{...... + 03a0 c5fb1006 4885d27f b74c01cf 4885d274 ....H....L..H..t + 03b0 b34d01c8 4883faff 74ae4c01 c94883fa .M..H...t.L..H.. + 03c0 fe74a94c 01ceeba8 0f1f8400 00000000 .t.L............ + 03d0 4c89fb0f 845cfdff ff498d6f 084983fd L....\...I.o.I.. + 03e0 ff0f8457 fdffff49 8d771049 83fdfe0f ...W...I.w.I.... + 03f0 8452fdff ff4d8d47 184983fd fd0f844d .R...M.G.I.....M + 0400 fdffff4d 8d4f2049 83fdfc0f 8448fdff ...M.O I.....H.. + 0410 ff4d8d57 284983fd fb0f8443 fdffff4d .M.W(I.....C...M + 0420 8d5f3049 83fdfa0f 843efdff ff498d7f ._0I.....>...I.. + 0430 38e938fd ffff488b 44248848 c1e00548 8.8...H.D$.H...H + 0440 01442448 48834424 a804f644 24f8020f .D$HH.D$...D$... + 0450 84be0000 00488b7c 24a8488b 1c244889 .....H.|$.H..$H. + 0460 f84829d8 4885c00f 8e400100 00480faf .H).H....@...H.. + 0470 7c24e848 89fa488b 7c24f048 01da488d |$.H..H.|$.H..H. + 0480 34d7488b 7c24a848 8d570148 0faf5424 4.H.|$.H.W.H..T$ + 0490 e8488b7c 24f04803 1424488d 0cd7488b .H.|$.H..$H...H. + 04a0 7c24e848 8b5c2488 4c8d04fd 00000000 |$.H.\$.L....... + 04b0 4889c748 8b542448 4829df48 85db7f25 H..H.T$HH).H...% + 04c0 eb4b660f 1f440000 4883c608 4883c108 .Kf..D..H...H... + 04d0 48ffc8c5 fb110ac5 fb114208 4883c210 H.........B.H... + 04e0 4839c774 1ac5fb10 0ec5fb10 014885c0 H9.t.........H.. + 04f0 7fd64c01 c64885c0 74d24c01 c1ebd148 ..L..H..t.L....H + 0500 8b442488 48c1e004 48014424 48488344 .D$.H...H.D$HH.D + 0510 24a802f6 4424f801 7468488b 4424a848 $...D$..thH.D$.H + 0520 8b3c2448 89c24829 fa4885d2 7e65480f .<$H..H).H..~eH. + 0530 af4424e8 4801f848 8b7c24f0 488d04c7 .D$.H..H.|$.H... + 0540 488b7c24 e8488b5c 24884889 d6488b4c H.|$.H.\$.H..H.L + 0550 244848c1 e7034829 de4885db 7e246690 $HH...H).H..~$f. + 0560 c5fb1000 4c8d4008 4801f848 85d2490f ....L.@.H..H..I. + 0570 4fc048ff cac5fb11 014883c1 084839d6 O.H......H...H9. + 0580 75de4883 c4105b5d 415c415d 415e31c0 u.H...[]A\A]A^1. + 0590 415fc348 8b042448 8b7c24f0 480faf44 A_.H..$H.|$.H..D + 05a0 24e84803 4424a848 8d04c7eb 93488b14 $.H.D$.H.....H.. + 05b0 24488b7c 24f0480f af5424e8 48035424 $H.|$.H..T$.H.T$ + 05c0 a848c1e2 03488d34 174885c0 0f84b0fe .H...H.4.H...... + 05d0 ffff488b 7c24f048 8d4c1708 e9bdfeff ..H.|$.H.L...... + 05e0 ff488b04 24488b7c 24f0480f af4424e8 .H..$H.|$.H..D$. + 05f0 48034424 a848c1e0 034801c7 4885d20f H.D$.H...H..H... + 0600 84dcfcff ff488b5c 24f04c8d 44030848 .....H.\$.L.D..H + 0610 83faff0f 84e3fcff ff488b5c 24f0488d .........H.\$.H. + 0620 4c031048 83fafe0f 84ebfcff ff488b5c L..H.........H.\ + 0630 24f0488d 740318e9 f8fcffff $.H.t....... /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymm_outcopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 cc010000 00420e10 8f02420e .........B....B. + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 3c060000 00420e10 8f02420e ....<....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606440e 38830703 7f010a0e 30410e28 ..D.8.......0A.( - 0050 420e2042 0e18420e 10440e08 490b0000 B. B..B..D..I... + 0040 8606410e 38830744 0e480378 050a0e38 ..A.8..D.H.x...8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08410b 00000000 ..A..... /usr/lib64/libopenblas_openmp.a/dsymv_L_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsymv_L_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsymv_L_COOPERLAKE.o (disasm) @@ -4,497 +4,502 @@ Disassembly of section .text: +dsymv_kernel_4x4: + push %rbx + mov (%rdx),%rax + mov offset(%rdx),%r10 + mov offset(%rdx),%r11 + mov offset(%rsp),%rbx + mov offset(%rdx),%rdx + vzeroupper + vxorpd %ymm0,%ymm0,%ymm0 + vxorpd %ymm1,%ymm1,%ymm1 + vxorpd %ymm2,%ymm2,%ymm2 + vxorpd %ymm3,%ymm3,%ymm3 + vbroadcastsd (%r9),%ymm4 + vbroadcastsd offset(%r9),%ymm5 + vbroadcastsd offset(%r9),%ymm6 + vbroadcastsd offset(%r9),%ymm7 + nop + vmovups (%r8,%rdi,8),%ymm9 + vmovups (%rcx,%rdi,8),%ymm8 + vmovups (%rax,%rdi,8),%ymm12 + vmovups (%r10,%rdi,8),%ymm13 + vmovups (%r11,%rdi,8),%ymm14 + vmovups (%rdx,%rdi,8),%ymm15 + vfmadd231pd %ymm4,%ymm12,%ymm9 + vfmadd231pd %ymm8,%ymm12,%ymm0 + vfmadd231pd %ymm5,%ymm13,%ymm9 + vfmadd231pd %ymm8,%ymm13,%ymm1 + vfmadd231pd %ymm6,%ymm14,%ymm9 + vfmadd231pd %ymm8,%ymm14,%ymm2 + vfmadd231pd %ymm7,%ymm15,%ymm9 + vfmadd231pd %ymm8,%ymm15,%ymm3 + add $something,%rdi + vmovups %ymm9,-offset(%r8,%rdi,8) + cmp %rdi,%rsi + jne + vmovsd (%rbx),%xmm4 + vmovsd offset(%rbx),%xmm5 + vmovsd offset(%rbx),%xmm6 + vmovsd offset(%rbx),%xmm7 + vextractf128 $something,%ymm0,%xmm12 + vextractf128 $something,%ymm1,%xmm13 + vextractf128 $something,%ymm2,%xmm14 + vextractf128 $something,%ymm3,%xmm15 + vaddpd %xmm0,%xmm12,%xmm0 + vaddpd %xmm1,%xmm13,%xmm1 + vaddpd %xmm2,%xmm14,%xmm2 + vaddpd %xmm3,%xmm15,%xmm3 + vhaddpd %xmm0,%xmm0,%xmm0 + vhaddpd %xmm1,%xmm1,%xmm1 + vhaddpd %xmm2,%xmm2,%xmm2 + vhaddpd %xmm3,%xmm3,%xmm3 + vaddsd %xmm4,%xmm0,%xmm0 + vaddsd %xmm5,%xmm1,%xmm1 + vaddsd %xmm6,%xmm2,%xmm2 + vaddsd %xmm7,%xmm3,%xmm3 + vmovsd %xmm0,(%rbx) + vmovsd %xmm1,offset(%rbx) + vmovsd %xmm2,offset(%rbx) + vmovsd %xmm3,offset(%rbx) + vzeroupper + vzeroupper + pop %rbx + ret + nop + dsymv_L_COOPERLAKE: - push %rbp - vmovsd %xmm0,%xmm0,%xmm7 - mov %rsp,%rbp push %r15 + vmovsd %xmm0,%xmm0,%xmm16 push %r14 push %r13 push %r12 + push %rbp + mov %rdi,%rbp push %rbx - and $something,%rsp sub $something,%rsp - mov %rsi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %r9,(%rsp) - mov offset(%rbp),%rax + mov %rcx,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %r9,offset(%rsp) + mov offset(%rsp),%rbx + mov %r8,%rcx + mov %fs:0x28,%rax + mov %rax,offset(%rsp) + xor %eax,%eax cmp $something,%r9 jne - cmpq $something,offset(%rbp) + cmpq $something,offset(%rsp) jne - mov -offset(%rsp),%rsi - lea offset(%rsi),%rbx - test %rsi,%rsi - cmovns %rsi,%rbx - and $something,%rbx + mov offset(%rsp),%rax + lea offset(%rax),%r14 + test %rax,%rax + cmovns %rax,%r14 + and $something,%r14 jle - lea offset(%rdi),%rcx - test %rdi,%rdi - mov %rcx,%rdx - cmovns %rdi,%rdx - mov -offset(%rsp),%rsi - and $something,%rdx - mov %rdx,(%rsp) - lea offset(%rsi),%rdx - mov %rcx,-offset(%rsp) - mov %rdx,%rcx - lea offset(,%rsi,8),%r15 - shl $something,%rcx - mov -offset(%rsp),%rsi - mov %rbx,-offset(%rsp) - mov %rax,offset(%rbp) - lea offset(%r15,%r15,1),%rdx - mov %rcx,-offset(%rsp) - sub $something,%rcx - mov %rcx,-offset(%rsp) - mov %rsi,%r14 - lea (%rsi,%rdx,1),%r13 - lea -offset(%rsi,%rdx,1),%r9 - mov %rsi,%rcx - mov %rax,%r10 - mov $something,%esi - vxorpd %xmm8,%xmm8,%xmm8 - nop - vmulsd -offset(%r8,%rsi,8),%xmm7,%xmm6 - vmovsd (%r14),%xmm0 - vmulsd -offset(%r8,%rsi,8),%xmm7,%xmm5 - vmulsd -offset(%r8,%rsi,8),%xmm7,%xmm9 - vmulsd -offset(%r8,%rsi,8),%xmm7,%xmm10 - vfmadd213sd (%r10),%xmm6,%xmm0 - mov -offset(%rsp),%r12 - mov offset(%rbp),%rax - sub %rsi,%r12 - lea (%r15,%rcx,1),%rdx - vmovsd %xmm0,(%r10) - vmovsd offset(%r14,%r15,1),%xmm0 - lea (%r15,%r9,1),%r11 - vfmadd213sd offset(%r10),%xmm5,%xmm0 - lea -offset(%rsi),%rbx - vmovsd %xmm8,%xmm8,%xmm2 - vmovsd %xmm0,offset(%r10) - vmovsd offset(%r13),%xmm0 - vfmadd213sd offset(%r10),%xmm9,%xmm0 - vmovsd %xmm0,offset(%r10) - vmovsd offset(%r13,%r15,1),%xmm0 - vfmadd213sd offset(%r10),%xmm10,%xmm0 - vmovsd %xmm0,offset(%r10) - cmp $something,%r12 - jle - vmovsd (%rcx,%rbx,8),%xmm0 - mov %rsi,%r12 - vfmadd213sd (%rax,%rbx,8),%xmm6,%xmm0 - vmovsd %xmm0,(%rax,%rbx,8) - vmovsd (%rcx,%rbx,8),%xmm3 - vfmadd231sd (%r8,%rbx,8),%xmm3,%xmm2 - inc %rbx - cmp %rsi,%rbx - jne - mov %rax,offset(%rbp) - lea -offset(%rsi),%rbx - vmovsd %xmm8,%xmm8,%xmm1 + test %rbp,%rbp + lea offset(%rbp),%rsi + mov offset(%rsp),%rdi + mov %rsi,offset(%rsp) + cmovns %rbp,%rsi + mov offset(%rsp),%r15 + mov %rsi,%rax + mov %rdi,%rsi + lea offset(,%rdi,8),%r11 + and $something,%rax + shl $something,%rdi + shl $something,%rsi + lea offset(%r15,%rdi,1),%r10 + mov %rax,offset(%rsp) + mov %rsi,offset(%rsp) + lea (%r15,%rdi,1),%rax + add $something,%rsi + lea offset(%rsp),%rdi + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + mov %r15,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dsymv_L_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsymv_L_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymv_L_COOPERLAKE.o (objdump) @@ -2,147 +2,160 @@ /usr/lib64/libopenblas_openmp.a/dsymv_L_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 55c5fb10 f84889e5 41574156 41554154 U....H..AWAVAUAT - 0010 534883e4 c04883ec 08488974 24f04889 SH...H...H.t$.H. - 0020 5424d048 894c24c8 4c890c24 488b4510 T$.H.L$.L..$H.E. - 0030 4983f901 0f855607 00004883 7d18010f I.....V...H.}... - 0040 854b0700 00488b74 24f0488d 5e034885 .K...H.t$.H.^.H. - 0050 f6480f49 de4883e3 fc0f8e67 02000048 .H.I.H.....g...H - 0060 8d4f0348 85ff4889 ca480f49 d7488b74 .O.H..H..H.I.H.t - 0070 24c84883 e2fc4889 1424488d 56014889 $.H...H..$H.V.H. - 0080 4c24d848 89d14c8d 3cf50000 000048c1 L$.H..L.<.....H. - 0090 e105488b 7424d048 895c24f8 48894510 ..H.t$.H.\$.H.E. - 00a0 4b8d543f 1048894c 24e04883 e9204889 K.T?.H.L$.H.. H. - 00b0 4c24e849 89f64c8d 2c164c8d 4c16f048 L$.I..L.,.L.L..H - 00c0 89f14989 c2be0400 0000c441 3957c090 ..I........A9W.. - 00d0 c4c14359 74f0e0c4 c17b1006 c4c14359 ..CYt....{....CY - 00e0 6cf0e8c4 4143594c f0f0c441 435954f0 l...ACYL...ACYT. - 00f0 f8c4c2c9 a9024c8b 6424d848 8b451049 ......L.d$.H.E.I - 0100 29f4498d 140fc4c1 7b1102c4 817b1044 ).I.....{....{.D - 0110 3e084f8d 1c0fc4c2 d1a94208 488d5efd >.O.......B.H.^. - 0120 c53b11c2 c4c17b11 4208c4c1 7b104500 .;....{.B...{.E. - 0130 c4c2b1a9 4210c4c1 7b114210 c4817b10 ....B...{.B...{. - 0140 443d08c4 c2a9a942 18c4c17b 11421849 D=.....B...{.B.I - 0150 83fc0b0f 8e570200 00c5fb10 04d94989 .....W........I. - 0160 f4c4e2c9 a904d8c5 fb1104d8 c5fb101c ................ - 0170 d9c4c2e1 b914d848 ffc34839 f375da48 .......H..H9.u.H - 0180 89451048 8d5efec5 3b11c10f 1f440000 .E.H.^..;....D.. - 0190 c5fb1004 dac4e2d1 a904d8c5 fb1104d8 ................ - 01a0 c5fb1024 dac4c2d9 b90cd848 ffc34839 ...$.......H..H9 - 01b0 f375ddc4 c17b1045 08488945 10c4c2b1 .u...{.E.H.E.... - 01c0 a94218c5 3b11c3c4 c17b1142 18c4c17b .B..;....{.B...{ - 01d0 106508c4 c2b99964 f0f84839 34240f8f .e.....d..H94$.. - 01e0 8c030000 488b1c24 4839df7e 76488b45 ....H..$H9.~vH.E - 01f0 100f1f80 00000000 c5fb1004 d9c4e2c9 ................ - 0200 a904d8c5 fb1104d8 c4e2d1b9 04dac57b ...............{ - 0210 103cd9c4 c281b914 d8c5fb11 04d8c4c2 .<.............. - 0220 b1b904d9 c57b102c dac4c291 b90cd8c5 .....{.,........ - 0230 fb1104d8 c4c2a9b9 04dbc441 7b1034d9 ...........A{.4. - 0240 c4c289b9 24d8c5fb 1104d8c4 c17b1004 ....$........{.. - 0250 dbc4c2f9 b91cd848 ffc34839 df759948 .......H..H9.u.H - 0260 894510c4 c2c1a912 c4c2c1a9 4a08c4c2 .E..........J... - 0270 c1a96210 c4c2c1a9 5a18488b 5424e0c4 ..b.....Z.H.T$.. - 0280 c17b1112 4901d649 01d5488b 5424e8c4 .{..I..I..H.T$.. - 0290 c17b114a 08c4c17b 116210c4 c17b115a .{.J...{.b...{.Z - 02a0 184883c6 044983c2 204801d1 4901d14c .H...I.. H..I..L - 02b0 396424f8 0f8f16fe ffff488b 5c24f848 9d$.......H.\$.H - 02c0 8b4510c5 f8774839 5c24f00f 8ece0000 .E...wH9\$...... - 02d0 00488b74 24c84885 ff4c8d4f 034889f2 .H.t$.H..L.O.H.. - 02e0 4c0f49cf 480fafd3 4c8b7c24 d04d89cc L.I.H...L.|$.M.. - 02f0 488d0c13 4c8b7424 f04d8d14 cf49c1fc H...L.t$.M...I.. - 0300 024983e1 fc4c8d1c f5080000 004c8d2c .I...L.......L., - 0310 f5000000 00498d0c d7c44139 57c06690 .....I....A9W.f. - 0320 c4c14359 0cd8c4c1 7b101248 89da4889 ..CY....{..H..H. - 0330 fec4e2f1 a914d8c5 fb1114d8 48ffc348 ............H..H - 0340 29de4883 fe070f8f 64010000 4889dac5 ).H.....d...H... - 0350 3b11c048 39fb7d31 0f1f8400 00000000 ;..H9.}1........ - 0360 c5fb1014 d1c4e2f1 a914d0c5 fb1114d0 ................ - 0370 c5fb1024 d1c4c2d9 b904d048 ffc24839 ...$.......H..H9 - 0380 d775ddc5 fb1054d8 f8c4e2e9 99c74d01 .u....T.......M. - 0390 da4c01e9 c5fb1144 d8f84939 de758148 .L.....D..I9.u.H - 03a0 8d65d831 c05b415c 415d415e 415f5dc3 .e.1.[A\A]A^A_]. - 03b0 c5fb1004 d94989f4 c4e2c9a9 04d8c5fb .....I.......... - 03c0 1104d8c5 fb1024d9 c4c2d9b9 14d848ff ......$.......H. - 03d0 c34839f3 75da4889 4510488d 5efec53b .H9.u.H.E.H.^..; - 03e0 11c1660f 1f440000 c5fb1004 dac4e2d1 ..f..D.......... - 03f0 a904d8c5 fb1104d8 c5fb101c dac4c2e1 ................ - 0400 b90cd848 ffc34839 f375ddc4 c17b1045 ...H..H9.u...{.E - 0410 08488945 10c4c2b1 a94218c4 c17b1142 .H.E.....B...{.B - 0420 18c4c17b 106508c4 c2b99964 f0f84839 ...{.e.....d..H9 - 0430 f70f8e89 04000048 89f3c53b 11c36690 .......H...;..f. - 0440 c5fb1004 d9c4e2c9 a904d8c5 fb1104d8 ................ - 0450 c4e2d1b9 04dac57b 101cd9c4 c2a1b914 .......{........ - 0460 d8c5fb11 04d8c4c2 b1b904d9 c57b1024 .............{.$ - 0470 dac4c299 b90cd8c5 fb1104d8 c4c2a9b9 ................ - 0480 04dbc441 7b103cd9 c4c281b9 24d8c5fb ...A{.<.....$... - 0490 1104d8c4 c17b1004 dbc4c2f9 b91cd848 .....{.........H - 04a0 ffc34839 df7599e9 b3fdffff 0f1f4000 ..H9.u........@. - 04b0 488d7208 4883c205 480f48d6 4989d748 H.r.H...H.H.I..H - 04c0 83e2fc49 c1ff0248 39d30f8d e0030000 ...I...H9....... - 04d0 4889dec5 3b11c066 0f1f8400 00000000 H...;..f........ - 04e0 c5fb1014 f1c4e2f1 a914f0c5 fb1114f0 ................ - 04f0 c5fb1034 f1c4c2c9 b904f048 ffc64839 ...4.......H..H9 - 0500 f275dd4d 39e77d2b 0f1f8400 00000000 .u.M9.}+........ - 0510 c5fb1014 d1c4e2f1 a914d0c5 fb1114d0 ................ - 0520 c5fb102c d1c4c2d1 b904d048 ffc24939 ...,.......H..I9 - 0530 d17fdd4c 89ca4c39 cf0f8e44 feffff90 ...L..L9...D.... - 0540 c5fb1014 d1c4e2f1 a914d0c5 fb1114d0 ................ - 0550 c5fb1034 d1c4c2c9 b904d048 ffc24839 ...4.......H..H9 - 0560 d775dde9 1bfeffff 0f1f8400 00000000 .u.............. - 0570 8b1c24c4 627d19fe 29f383e3 f84863db ..$.b}..)....Hc. - 0580 4801f348 895c24c0 62e2fd28 19c562c2 H..H.\$.b..(..b. - 0590 fd2819c9 62c2fd28 19d262e2 fd4819f6 .(..b..(..b..H.. - 05a0 6262fd48 19c56242 fd4819c9 6242fd48 bb.H..bB.H..bB.H - 05b0 19d24889 d84839f3 0f8e0b03 000062a1 ..H..H9.......b. - 05c0 c50057ff 48897424 b84889f3 4889c648 ..W.H.t$.H..H..H - 05d0 8b451062 a1fd4828 df62a1fd 4828e762 .E.b..H(.b..H(.b - 05e0 a1fd4828 ef0f1f00 6271fd48 102cda62 ..H(....bq.H.,.b - 05f0 71fd4810 34d962d1 bd4059c5 6251fd48 q.H.4.b..@Y.bQ.H - 0600 1024d962 51fd4810 1cdb62d1 fd48101c .$.bQ.H...b..H.. - 0610 d862d2cd 40b8c662 c2e548b8 ee62c2e5 .b..@..b..H..b.. - 0620 48b8e562 c2e548b8 dc62c2e5 48b8fb62 H..b..H..b..H..b - 0630 d2b540b8 c462d2ad 40b8c362 f1fd4858 ..@..b..@..b..HX - 0640 04d862f1 fd481104 d84883c3 084839de ..b..H...H...H9. - 0650 7f96488b 7424b848 8b5c24c0 62a3fd48 ..H.t$.H.\$.b..H - 0660 1bee0148 89451048 29f348c7 c0fbffff ...H.E.H).H..... - 0670 ff488d5c 030462a1 cd2058f5 62a3fd48 .H.\..b.. X.b..H - 0680 1be50162 a1d52058 ec4883e3 f862a3fd ...b.. X.H...b.. - 0690 481bdc01 488b0424 62a1dd20 58e3488d H...H..$b.. X.H. - 06a0 5c1e0862 a3fd481b fb0162a1 e52058df \..b..H...b.. X. - 06b0 4839d874 7a488974 24c04889 c6488b45 H9.tzH.t$.H..H.E - 06c0 100f1f80 00000000 c57d102c dac57d10 .........}.,..}. - 06d0 34d962d1 fd2059c5 c4417d10 24d9c441 4.b.. Y..A}.$..A - 06e0 7d101cdb c4c17d10 1cd8c4c2 85b8c662 }.....}........b - 06f0 c2e528b8 f662c2e5 28b8ed62 c2e528b8 ..(..b..(..b..(. - 0700 e462c2e5 28b8db62 d2f520b8 c462d2ed .b..(..b.. ..b.. - 0710 20b8c3c5 fd5804d8 c5fd1104 d84883c3 ....X.......H.. - 0720 044839de 75a24889 4510488b 7424c062 .H9.u.H.E.H.t$.b - 0730 c3fd2819 f40162c3 fd2819eb 0162e3fd ..(...b..(...b.. - 0740 2819e001 62e3fd28 19db0162 319d0858 (...b..(...b1..X - 0750 e66231a5 0858dd62 b1fd0858 c462b1e5 .b1..X.b...X.b.. - 0760 0858dbc4 41197ce4 c441217c dbc5f97c .X..A.|..A!|...| - 0770 c0c5e17c dbc4c16b 58d4c4c1 7358cbc5 ...|...kX...sX.. - 0780 db58e0c4 c16358d8 e957faff ff0f1f00 .X...cX..W...... - 0790 48837c24 f0000f8e 03fcffff 488b7424 H.|$........H.t$ - 07a0 c84c8b74 24d0488d 0cf50800 000048c1 .L.t$.H.......H. - 07b0 e6034889 7424f848 8b751848 897c24e8 ..H.t$.H.u.H.|$. - 07c0 4c8d1cf5 00000000 4a8d3418 48897424 L.......J.4.H.t$ - 07d0 d8488b34 244d8d0c fe4c8d14 f5000000 .H.4$M...L...... - 07e0 004b8d34 10488974 24e04d8d 7e084531 .K.4.H.t$.M.~.E1 - 07f0 e431db45 31edc441 3957c048 89cf6690 .1.E1..A9W.H..f. - 0800 c4814359 14e8c4c1 7b100e49 ffc4c4e2 ..CY....{..I.... - 0810 e9a90cd8 c5fb110c d84c3964 24e80f8e .........L9d$... - 0820 7c000000 488b7424 d84c89fa 488d0cde |...H.t$.L..H... - 0830 488b7424 e0c53b11 c04a8d34 ee0f1f00 H.t$..;..J.4.... - 0840 c5fb100a 4883c208 c4e2e9a9 09c5fb11 ....H........... - 0850 09c5fb10 62f84c01 d9c4e2d9 b9064c01 ....b.L.......L. - 0860 d64939d1 75dac5fb 100cd8c4 e2f199c7 .I9.u........... - 0870 4c032c24 4901fe49 01ff4c03 4c24f8c5 L.,$I..I..L.L$.. - 0880 fb1104d8 48035d18 4c396424 f00f856d ....H.].L9d$...m - 0890 ffffffe9 07fbffff 0f1f8400 00000000 ................ - 08a0 c53b11c0 ebc5662e 0f1f8400 00000000 .;....f......... - 08b0 c53b11c0 e94afcff ff0f1f80 00000000 .;...J.......... - 08c0 c53b11c3 e99af9ff ff62a1cd 0057f648 .;.......b...W.H - 08d0 897424c0 4889f348 8b451048 8b342462 .t$.H..H.E.H.4$b - 08e0 a1fd2828 ee62a1fd 2828e662 a1fd2828 ..((.b..((.b..(( - 08f0 dee9d2fd ffff ...... + 0000 53488b02 4c8b5208 4c8b5a10 488b5c24 SH..L.R.L.Z.H.\$ + 0010 10488b52 18c5f877 c5fd57c0 c5f557c9 .H.R...w..W...W. + 0020 c5ed57d2 c5e557db c4c27d19 21c4c27d ..W...W...}.!..} + 0030 196908c4 c27d1971 10c4c27d 19791890 .i...}.q...}.y.. + 0040 c4417c10 0cf8c57c 1004f9c5 7c1024f8 .A|....|....|.$. + 0050 c4417c10 2cfac441 7c1034fb c57c103c .A|.,..A|.4..|.< + 0060 fac4629d b8ccc4c2 9db8c0c4 6295b8cd ..b.........b... + 0070 c4c295b8 c8c4628d b8cec4c2 8db8d0c4 ......b......... + 0080 6285b8cf c4c285b8 d84883c7 04c4417c b........H....A| + 0090 114cf8e0 4839fe75 a7c5fb10 23c5fb10 .L..H9.u....#... + 00a0 6b08c5fb 107310c5 fb107b18 c4c37d19 k....s....{...}. + 00b0 c401c4c3 7d19cd01 c4c37d19 d601c4c3 ....}.....}..... + 00c0 7d19df01 c59958c0 c59158c9 c58958d2 }.....X...X...X. + 00d0 c58158db c5f97cc0 c5f17cc9 c5e97cd2 ..X...|...|...|. + 00e0 c5e17cdb c5fb58c4 c5f358cd c5eb58d6 ..|...X...X...X. + 00f0 c5e358df c5fb1103 c5fb114b 08c5fb11 ..X........K.... + 0100 5310c5fb 115b18c5 f877c5f8 775bc390 S....[...w..w[.. + 0110 415762e1 ff0810c0 41564155 41545548 AWb.....AVAUATUH + 0120 89fd5348 81ece800 00004889 4c244848 ..SH......H.L$HH + 0130 89742420 48895424 404c894c 2408488b .t$ H.T$@L.L$.H. + 0140 9c242001 00004c89 c164488b 04252800 .$ ...L..dH..%(. + 0150 00004889 8424d800 000031c0 4983f901 ..H..$....1.I... + 0160 0f852a07 00004883 bc242801 0000010f ..*...H..$(..... + 0170 851b0700 00488b44 24204c8d 70034885 .....H.D$ L.p.H. + 0180 c04c0f49 f04983e6 fc0f8eca 04000048 .L.I.I.........H + 0190 85ed488d 7503488b 7c244848 89742438 ..H.u.H.|$HH.t$8 + 01a0 480f49f5 4c8b7c24 404889f0 4889fe4c H.I.L.|$@H..H..L + 01b0 8d1cfd00 00000048 83e0fc48 c1e70448 .......H...H...H + 01c0 c1e6054d 8d543f10 48894424 10488974 ...M.T?.H.D$.H.t + 01d0 2430498d 043f4883 c620488d 7c247048 $0I..?H.. H.|$pH + 01e0 89742428 48897c24 684c897c 24084c89 .t$(H.|$hL.|$.L. + 01f0 7424184d 89fd4989 c64989dc 41bf0400 t$.M..I..I..A... + 0200 000062a1 f50057c9 4c89d80f 1f440000 ..b...W.L....D.. + 0210 62b1ff00 5974f9fc 488b7c24 0862b1ff b...Yt..H.|$.b.. + 0220 00596cf9 fdc5fb10 0762b1ff 00597cf9 .Yl......b...Y|. + 0230 fec4c2c9 a9042462 31ff0059 44f9ff48 ......$b1..YD..H + 0240 8b542438 4a8d3428 4e8d0430 c4c17b11 .T$8J.4(N..0..{. + 0250 0424c5fb 10440708 4c29fac4 c2d1a944 .$...D..L).....D + 0260 240848c7 84249000 00000000 000048c7 $.H..$........H. + 0270 84249800 00000000 000048c7 8424a000 .$........H..$.. + 0280 00000000 000048c7 8424a800 00000000 ......H..$...... + 0290 0000c4c1 7b114424 08c4c17b 10024c89 ....{.D$...{..L. + 02a0 ac24b000 0000c4c2 c1a94424 104889b4 .$........D$.H.. + 02b0 24b80000 004c89b4 24c00000 004c8984 $....L..$....L.. + 02c0 24c80000 00c5fb11 742470c4 c17b1144 $.......t$p..{.D + 02d0 2410c4c1 7b104402 08c5fb11 6c2478c4 $...{.D.....l$x. + 02e0 c2b9a944 2418c5fb 11bc2480 000000c5 ...D$.....$..... + 02f0 7b118424 88000000 498d7ffd 62b1f700 {..$....I...b... + 0300 10d1c4c1 7b114424 184883fa 0b0f8e9d ....{.D$.H...... + 0310 010000c4 c17b1044 fd004989 f9c4e2c9 .....{.D..I..... /usr/lib64/libopenblas_openmp.a/dsymv_L_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsymv_L_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymv_L_COOPERLAKE.o (objdump) @@ -3,7 +3,11 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 2c000000 1c000000 ........,....... - 0020 00000000 f6080000 00410e10 8602470d .........A....G. - 0030 06518f03 8e048d05 8c068307 0396030a .Q.............. - 0040 0c070841 0b000000 ...A.... + 0010 1b0c0708 90010000 18000000 1c000000 ................ + 0020 00000000 0f010000 00410e10 8302030d .........A...... + 0030 010e0800 58000000 38000000 00000000 ....X...8....... + 0040 c0080000 00420e10 8f02480e 188e0342 .....B....H....B + 0050 0e208d04 420e288c 05410e30 8606440e . ..B.(..A.0..D. + 0060 38830747 0ea00203 26060a0e 38410e30 8..G....&...8A.0 + 0070 410e2842 0e20420e 18420e10 440e0844 A.(B. B..B..D..D + 0080 0b02db0e a8027c0e a0020000 00000000 ......|......... /usr/lib64/libopenblas_openmp.a/dsymv_L_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dsymv_L_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dsymv_L_SKYLAKEX.o (disasm) @@ -4,497 +4,502 @@ Disassembly of section .text: +dsymv_kernel_4x4: + push %rbx + mov (%rdx),%rax + mov offset(%rdx),%r10 + mov offset(%rdx),%r11 + mov offset(%rsp),%rbx + mov offset(%rdx),%rdx + vzeroupper + vxorpd %ymm0,%ymm0,%ymm0 + vxorpd %ymm1,%ymm1,%ymm1 + vxorpd %ymm2,%ymm2,%ymm2 + vxorpd %ymm3,%ymm3,%ymm3 + vbroadcastsd (%r9),%ymm4 + vbroadcastsd offset(%r9),%ymm5 + vbroadcastsd offset(%r9),%ymm6 + vbroadcastsd offset(%r9),%ymm7 + nop + vmovups (%r8,%rdi,8),%ymm9 + vmovups (%rcx,%rdi,8),%ymm8 + vmovups (%rax,%rdi,8),%ymm12 + vmovups (%r10,%rdi,8),%ymm13 + vmovups (%r11,%rdi,8),%ymm14 + vmovups (%rdx,%rdi,8),%ymm15 + vfmadd231pd %ymm4,%ymm12,%ymm9 + vfmadd231pd %ymm8,%ymm12,%ymm0 + vfmadd231pd %ymm5,%ymm13,%ymm9 + vfmadd231pd %ymm8,%ymm13,%ymm1 + vfmadd231pd %ymm6,%ymm14,%ymm9 + vfmadd231pd %ymm8,%ymm14,%ymm2 + vfmadd231pd %ymm7,%ymm15,%ymm9 + vfmadd231pd %ymm8,%ymm15,%ymm3 + add $something,%rdi + vmovups %ymm9,-offset(%r8,%rdi,8) + cmp %rdi,%rsi + jne + vmovsd (%rbx),%xmm4 + vmovsd offset(%rbx),%xmm5 + vmovsd offset(%rbx),%xmm6 + vmovsd offset(%rbx),%xmm7 + vextractf128 $something,%ymm0,%xmm12 + vextractf128 $something,%ymm1,%xmm13 + vextractf128 $something,%ymm2,%xmm14 + vextractf128 $something,%ymm3,%xmm15 + vaddpd %xmm0,%xmm12,%xmm0 + vaddpd %xmm1,%xmm13,%xmm1 + vaddpd %xmm2,%xmm14,%xmm2 + vaddpd %xmm3,%xmm15,%xmm3 + vhaddpd %xmm0,%xmm0,%xmm0 + vhaddpd %xmm1,%xmm1,%xmm1 + vhaddpd %xmm2,%xmm2,%xmm2 + vhaddpd %xmm3,%xmm3,%xmm3 + vaddsd %xmm4,%xmm0,%xmm0 + vaddsd %xmm5,%xmm1,%xmm1 + vaddsd %xmm6,%xmm2,%xmm2 + vaddsd %xmm7,%xmm3,%xmm3 + vmovsd %xmm0,(%rbx) + vmovsd %xmm1,offset(%rbx) + vmovsd %xmm2,offset(%rbx) + vmovsd %xmm3,offset(%rbx) + vzeroupper + vzeroupper + pop %rbx + ret + nop + dsymv_L_SKYLAKEX: - push %rbp - vmovsd %xmm0,%xmm0,%xmm7 - mov %rsp,%rbp push %r15 + vmovsd %xmm0,%xmm0,%xmm16 push %r14 push %r13 push %r12 + push %rbp + mov %rdi,%rbp push %rbx - and $something,%rsp sub $something,%rsp - mov %rsi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %r9,(%rsp) - mov offset(%rbp),%rax + mov %rcx,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %r9,offset(%rsp) + mov offset(%rsp),%rbx + mov %r8,%rcx + mov %fs:0x28,%rax + mov %rax,offset(%rsp) + xor %eax,%eax cmp $something,%r9 jne - cmpq $something,offset(%rbp) + cmpq $something,offset(%rsp) jne - mov -offset(%rsp),%rsi - lea offset(%rsi),%rbx - test %rsi,%rsi - cmovns %rsi,%rbx - and $something,%rbx + mov offset(%rsp),%rax + lea offset(%rax),%r14 + test %rax,%rax + cmovns %rax,%r14 + and $something,%r14 jle - lea offset(%rdi),%rcx - test %rdi,%rdi - mov %rcx,%rdx - cmovns %rdi,%rdx - mov -offset(%rsp),%rsi - and $something,%rdx - mov %rdx,(%rsp) - lea offset(%rsi),%rdx - mov %rcx,-offset(%rsp) - mov %rdx,%rcx - lea offset(,%rsi,8),%r15 - shl $something,%rcx - mov -offset(%rsp),%rsi - mov %rbx,-offset(%rsp) - mov %rax,offset(%rbp) - lea offset(%r15,%r15,1),%rdx - mov %rcx,-offset(%rsp) - sub $something,%rcx - mov %rcx,-offset(%rsp) - mov %rsi,%r14 - lea (%rsi,%rdx,1),%r13 - lea -offset(%rsi,%rdx,1),%r9 - mov %rsi,%rcx - mov %rax,%r10 - mov $something,%esi - vxorpd %xmm8,%xmm8,%xmm8 - nop - vmulsd -offset(%r8,%rsi,8),%xmm7,%xmm6 - vmovsd (%r14),%xmm0 - vmulsd -offset(%r8,%rsi,8),%xmm7,%xmm5 - vmulsd -offset(%r8,%rsi,8),%xmm7,%xmm9 - vmulsd -offset(%r8,%rsi,8),%xmm7,%xmm10 - vfmadd213sd (%r10),%xmm6,%xmm0 - mov -offset(%rsp),%r12 - mov offset(%rbp),%rax - sub %rsi,%r12 - lea (%r15,%rcx,1),%rdx - vmovsd %xmm0,(%r10) - vmovsd offset(%r14,%r15,1),%xmm0 - lea (%r15,%r9,1),%r11 - vfmadd213sd offset(%r10),%xmm5,%xmm0 - lea -offset(%rsi),%rbx - vmovsd %xmm8,%xmm8,%xmm2 - vmovsd %xmm0,offset(%r10) - vmovsd offset(%r13),%xmm0 - vfmadd213sd offset(%r10),%xmm9,%xmm0 - vmovsd %xmm0,offset(%r10) - vmovsd offset(%r13,%r15,1),%xmm0 - vfmadd213sd offset(%r10),%xmm10,%xmm0 - vmovsd %xmm0,offset(%r10) - cmp $something,%r12 - jle - vmovsd (%rcx,%rbx,8),%xmm0 - mov %rsi,%r12 - vfmadd213sd (%rax,%rbx,8),%xmm6,%xmm0 - vmovsd %xmm0,(%rax,%rbx,8) - vmovsd (%rcx,%rbx,8),%xmm3 - vfmadd231sd (%r8,%rbx,8),%xmm3,%xmm2 - inc %rbx - cmp %rsi,%rbx - jne - mov %rax,offset(%rbp) - lea -offset(%rsi),%rbx - vmovsd %xmm8,%xmm8,%xmm1 + test %rbp,%rbp + lea offset(%rbp),%rsi + mov offset(%rsp),%rdi + mov %rsi,offset(%rsp) + cmovns %rbp,%rsi + mov offset(%rsp),%r15 + mov %rsi,%rax + mov %rdi,%rsi + lea offset(,%rdi,8),%r11 + and $something,%rax + shl $something,%rdi + shl $something,%rsi + lea offset(%r15,%rdi,1),%r10 + mov %rax,offset(%rsp) + mov %rsi,offset(%rsp) + lea (%r15,%rdi,1),%rax + add $something,%rsi + lea offset(%rsp),%rdi + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + mov %r15,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dsymv_L_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dsymv_L_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymv_L_SKYLAKEX.o (objdump) @@ -2,147 +2,160 @@ /usr/lib64/libopenblas_openmp.a/dsymv_L_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 55c5fb10 f84889e5 41574156 41554154 U....H..AWAVAUAT - 0010 534883e4 c04883ec 08488974 24f04889 SH...H...H.t$.H. - 0020 5424d048 894c24c8 4c890c24 488b4510 T$.H.L$.L..$H.E. - 0030 4983f901 0f855607 00004883 7d18010f I.....V...H.}... - 0040 854b0700 00488b74 24f0488d 5e034885 .K...H.t$.H.^.H. - 0050 f6480f49 de4883e3 fc0f8e67 02000048 .H.I.H.....g...H - 0060 8d4f0348 85ff4889 ca480f49 d7488b74 .O.H..H..H.I.H.t - 0070 24c84883 e2fc4889 1424488d 56014889 $.H...H..$H.V.H. - 0080 4c24d848 89d14c8d 3cf50000 000048c1 L$.H..L.<.....H. - 0090 e105488b 7424d048 895c24f8 48894510 ..H.t$.H.\$.H.E. - 00a0 4b8d543f 1048894c 24e04883 e9204889 K.T?.H.L$.H.. H. - 00b0 4c24e849 89f64c8d 2c164c8d 4c16f048 L$.I..L.,.L.L..H - 00c0 89f14989 c2be0400 0000c441 3957c090 ..I........A9W.. - 00d0 c4c14359 74f0e0c4 c17b1006 c4c14359 ..CYt....{....CY - 00e0 6cf0e8c4 4143594c f0f0c441 435954f0 l...ACYL...ACYT. - 00f0 f8c4c2c9 a9024c8b 6424d848 8b451049 ......L.d$.H.E.I - 0100 29f4498d 140fc4c1 7b1102c4 817b1044 ).I.....{....{.D - 0110 3e084f8d 1c0fc4c2 d1a94208 488d5efd >.O.......B.H.^. - 0120 c53b11c2 c4c17b11 4208c4c1 7b104500 .;....{.B...{.E. - 0130 c4c2b1a9 4210c4c1 7b114210 c4817b10 ....B...{.B...{. - 0140 443d08c4 c2a9a942 18c4c17b 11421849 D=.....B...{.B.I - 0150 83fc0b0f 8e570200 00c5fb10 04d94989 .....W........I. - 0160 f4c4e2c9 a904d8c5 fb1104d8 c5fb101c ................ - 0170 d9c4c2e1 b914d848 ffc34839 f375da48 .......H..H9.u.H - 0180 89451048 8d5efec5 3b11c10f 1f440000 .E.H.^..;....D.. - 0190 c5fb1004 dac4e2d1 a904d8c5 fb1104d8 ................ - 01a0 c5fb1024 dac4c2d9 b90cd848 ffc34839 ...$.......H..H9 - 01b0 f375ddc4 c17b1045 08488945 10c4c2b1 .u...{.E.H.E.... - 01c0 a94218c5 3b11c3c4 c17b1142 18c4c17b .B..;....{.B...{ - 01d0 106508c4 c2b99964 f0f84839 34240f8f .e.....d..H94$.. - 01e0 8c030000 488b1c24 4839df7e 76488b45 ....H..$H9.~vH.E - 01f0 100f1f80 00000000 c5fb1004 d9c4e2c9 ................ - 0200 a904d8c5 fb1104d8 c4e2d1b9 04dac57b ...............{ - 0210 103cd9c4 c281b914 d8c5fb11 04d8c4c2 .<.............. - 0220 b1b904d9 c57b102c dac4c291 b90cd8c5 .....{.,........ - 0230 fb1104d8 c4c2a9b9 04dbc441 7b1034d9 ...........A{.4. - 0240 c4c289b9 24d8c5fb 1104d8c4 c17b1004 ....$........{.. - 0250 dbc4c2f9 b91cd848 ffc34839 df759948 .......H..H9.u.H - 0260 894510c4 c2c1a912 c4c2c1a9 4a08c4c2 .E..........J... - 0270 c1a96210 c4c2c1a9 5a18488b 5424e0c4 ..b.....Z.H.T$.. - 0280 c17b1112 4901d649 01d5488b 5424e8c4 .{..I..I..H.T$.. - 0290 c17b114a 08c4c17b 116210c4 c17b115a .{.J...{.b...{.Z - 02a0 184883c6 044983c2 204801d1 4901d14c .H...I.. H..I..L - 02b0 396424f8 0f8f16fe ffff488b 5c24f848 9d$.......H.\$.H - 02c0 8b4510c5 f8774839 5c24f00f 8ece0000 .E...wH9\$...... - 02d0 00488b74 24c84885 ff4c8d4f 034889f2 .H.t$.H..L.O.H.. - 02e0 4c0f49cf 480fafd3 4c8b7c24 d04d89cc L.I.H...L.|$.M.. - 02f0 488d0c13 4c8b7424 f04d8d14 cf49c1fc H...L.t$.M...I.. - 0300 024983e1 fc4c8d1c f5080000 004c8d2c .I...L.......L., - 0310 f5000000 00498d0c d7c44139 57c06690 .....I....A9W.f. - 0320 c4c14359 0cd8c4c1 7b101248 89da4889 ..CY....{..H..H. - 0330 fec4e2f1 a914d8c5 fb1114d8 48ffc348 ............H..H - 0340 29de4883 fe070f8f 64010000 4889dac5 ).H.....d...H... - 0350 3b11c048 39fb7d31 0f1f8400 00000000 ;..H9.}1........ - 0360 c5fb1014 d1c4e2f1 a914d0c5 fb1114d0 ................ - 0370 c5fb1024 d1c4c2d9 b904d048 ffc24839 ...$.......H..H9 - 0380 d775ddc5 fb1054d8 f8c4e2e9 99c74d01 .u....T.......M. - 0390 da4c01e9 c5fb1144 d8f84939 de758148 .L.....D..I9.u.H - 03a0 8d65d831 c05b415c 415d415e 415f5dc3 .e.1.[A\A]A^A_]. - 03b0 c5fb1004 d94989f4 c4e2c9a9 04d8c5fb .....I.......... - 03c0 1104d8c5 fb1024d9 c4c2d9b9 14d848ff ......$.......H. - 03d0 c34839f3 75da4889 4510488d 5efec53b .H9.u.H.E.H.^..; - 03e0 11c1660f 1f440000 c5fb1004 dac4e2d1 ..f..D.......... - 03f0 a904d8c5 fb1104d8 c5fb101c dac4c2e1 ................ - 0400 b90cd848 ffc34839 f375ddc4 c17b1045 ...H..H9.u...{.E - 0410 08488945 10c4c2b1 a94218c4 c17b1142 .H.E.....B...{.B - 0420 18c4c17b 106508c4 c2b99964 f0f84839 ...{.e.....d..H9 - 0430 f70f8e89 04000048 89f3c53b 11c36690 .......H...;..f. - 0440 c5fb1004 d9c4e2c9 a904d8c5 fb1104d8 ................ - 0450 c4e2d1b9 04dac57b 101cd9c4 c2a1b914 .......{........ - 0460 d8c5fb11 04d8c4c2 b1b904d9 c57b1024 .............{.$ - 0470 dac4c299 b90cd8c5 fb1104d8 c4c2a9b9 ................ - 0480 04dbc441 7b103cd9 c4c281b9 24d8c5fb ...A{.<.....$... - 0490 1104d8c4 c17b1004 dbc4c2f9 b91cd848 .....{.........H - 04a0 ffc34839 df7599e9 b3fdffff 0f1f4000 ..H9.u........@. - 04b0 488d7208 4883c205 480f48d6 4989d748 H.r.H...H.H.I..H - 04c0 83e2fc49 c1ff0248 39d30f8d e0030000 ...I...H9....... - 04d0 4889dec5 3b11c066 0f1f8400 00000000 H...;..f........ - 04e0 c5fb1014 f1c4e2f1 a914f0c5 fb1114f0 ................ - 04f0 c5fb1034 f1c4c2c9 b904f048 ffc64839 ...4.......H..H9 - 0500 f275dd4d 39e77d2b 0f1f8400 00000000 .u.M9.}+........ - 0510 c5fb1014 d1c4e2f1 a914d0c5 fb1114d0 ................ - 0520 c5fb102c d1c4c2d1 b904d048 ffc24939 ...,.......H..I9 - 0530 d17fdd4c 89ca4c39 cf0f8e44 feffff90 ...L..L9...D.... - 0540 c5fb1014 d1c4e2f1 a914d0c5 fb1114d0 ................ - 0550 c5fb1034 d1c4c2c9 b904d048 ffc24839 ...4.......H..H9 - 0560 d775dde9 1bfeffff 0f1f8400 00000000 .u.............. - 0570 8b1c24c4 627d19fe 29f383e3 f84863db ..$.b}..)....Hc. - 0580 4801f348 895c24c0 62e2fd28 19c562c2 H..H.\$.b..(..b. - 0590 fd2819c9 62c2fd28 19d262e2 fd4819f6 .(..b..(..b..H.. - 05a0 6262fd48 19c56242 fd4819c9 6242fd48 bb.H..bB.H..bB.H - 05b0 19d24889 d84839f3 0f8e0b03 000062a1 ..H..H9.......b. - 05c0 c50057ff 48897424 b84889f3 4889c648 ..W.H.t$.H..H..H - 05d0 8b451062 a1fd4828 df62a1fd 4828e762 .E.b..H(.b..H(.b - 05e0 a1fd4828 ef0f1f00 6271fd48 102cda62 ..H(....bq.H.,.b - 05f0 71fd4810 34d962d1 bd4059c5 6251fd48 q.H.4.b..@Y.bQ.H - 0600 1024d962 51fd4810 1cdb62d1 fd48101c .$.bQ.H...b..H.. - 0610 d862d2cd 40b8c662 c2e548b8 ee62c2e5 .b..@..b..H..b.. - 0620 48b8e562 c2e548b8 dc62c2e5 48b8fb62 H..b..H..b..H..b - 0630 d2b540b8 c462d2ad 40b8c362 f1fd4858 ..@..b..@..b..HX - 0640 04d862f1 fd481104 d84883c3 084839de ..b..H...H...H9. - 0650 7f96488b 7424b848 8b5c24c0 62a3fd48 ..H.t$.H.\$.b..H - 0660 1bee0148 89451048 29f348c7 c0fbffff ...H.E.H).H..... - 0670 ff488d5c 030462a1 cd2058f5 62a3fd48 .H.\..b.. X.b..H - 0680 1be50162 a1d52058 ec4883e3 f862a3fd ...b.. X.H...b.. - 0690 481bdc01 488b0424 62a1dd20 58e3488d H...H..$b.. X.H. - 06a0 5c1e0862 a3fd481b fb0162a1 e52058df \..b..H...b.. X. - 06b0 4839d874 7a488974 24c04889 c6488b45 H9.tzH.t$.H..H.E - 06c0 100f1f80 00000000 c57d102c dac57d10 .........}.,..}. - 06d0 34d962d1 fd2059c5 c4417d10 24d9c441 4.b.. Y..A}.$..A - 06e0 7d101cdb c4c17d10 1cd8c4c2 85b8c662 }.....}........b - 06f0 c2e528b8 f662c2e5 28b8ed62 c2e528b8 ..(..b..(..b..(. - 0700 e462c2e5 28b8db62 d2f520b8 c462d2ed .b..(..b.. ..b.. - 0710 20b8c3c5 fd5804d8 c5fd1104 d84883c3 ....X.......H.. - 0720 044839de 75a24889 4510488b 7424c062 .H9.u.H.E.H.t$.b - 0730 c3fd2819 f40162c3 fd2819eb 0162e3fd ..(...b..(...b.. - 0740 2819e001 62e3fd28 19db0162 319d0858 (...b..(...b1..X - 0750 e66231a5 0858dd62 b1fd0858 c462b1e5 .b1..X.b...X.b.. - 0760 0858dbc4 41197ce4 c441217c dbc5f97c .X..A.|..A!|...| - 0770 c0c5e17c dbc4c16b 58d4c4c1 7358cbc5 ...|...kX...sX.. - 0780 db58e0c4 c16358d8 e957faff ff0f1f00 .X...cX..W...... - 0790 48837c24 f0000f8e 03fcffff 488b7424 H.|$........H.t$ - 07a0 c84c8b74 24d0488d 0cf50800 000048c1 .L.t$.H.......H. - 07b0 e6034889 7424f848 8b751848 897c24e8 ..H.t$.H.u.H.|$. - 07c0 4c8d1cf5 00000000 4a8d3418 48897424 L.......J.4.H.t$ - 07d0 d8488b34 244d8d0c fe4c8d14 f5000000 .H.4$M...L...... - 07e0 004b8d34 10488974 24e04d8d 7e084531 .K.4.H.t$.M.~.E1 - 07f0 e431db45 31edc441 3957c048 89cf6690 .1.E1..A9W.H..f. - 0800 c4814359 14e8c4c1 7b100e49 ffc4c4e2 ..CY....{..I.... - 0810 e9a90cd8 c5fb110c d84c3964 24e80f8e .........L9d$... - 0820 7c000000 488b7424 d84c89fa 488d0cde |...H.t$.L..H... - 0830 488b7424 e0c53b11 c04a8d34 ee0f1f00 H.t$..;..J.4.... - 0840 c5fb100a 4883c208 c4e2e9a9 09c5fb11 ....H........... - 0850 09c5fb10 62f84c01 d9c4e2d9 b9064c01 ....b.L.......L. - 0860 d64939d1 75dac5fb 100cd8c4 e2f199c7 .I9.u........... - 0870 4c032c24 4901fe49 01ff4c03 4c24f8c5 L.,$I..I..L.L$.. - 0880 fb1104d8 48035d18 4c396424 f00f856d ....H.].L9d$...m - 0890 ffffffe9 07fbffff 0f1f8400 00000000 ................ - 08a0 c53b11c0 ebc5662e 0f1f8400 00000000 .;....f......... - 08b0 c53b11c0 e94afcff ff0f1f80 00000000 .;...J.......... - 08c0 c53b11c3 e99af9ff ff62a1cd 0057f648 .;.......b...W.H - 08d0 897424c0 4889f348 8b451048 8b342462 .t$.H..H.E.H.4$b - 08e0 a1fd2828 ee62a1fd 2828e662 a1fd2828 ..((.b..((.b..(( - 08f0 dee9d2fd ffff ...... + 0000 53488b02 4c8b5208 4c8b5a10 488b5c24 SH..L.R.L.Z.H.\$ + 0010 10488b52 18c5f877 c5fd57c0 c5f557c9 .H.R...w..W...W. + 0020 c5ed57d2 c5e557db c4c27d19 21c4c27d ..W...W...}.!..} + 0030 196908c4 c27d1971 10c4c27d 19791890 .i...}.q...}.y.. + 0040 c4417c10 0cf8c57c 1004f9c5 7c1024f8 .A|....|....|.$. + 0050 c4417c10 2cfac441 7c1034fb c57c103c .A|.,..A|.4..|.< + 0060 fac4629d b8ccc4c2 9db8c0c4 6295b8cd ..b.........b... + 0070 c4c295b8 c8c4628d b8cec4c2 8db8d0c4 ......b......... + 0080 6285b8cf c4c285b8 d84883c7 04c4417c b........H....A| + 0090 114cf8e0 4839fe75 a7c5fb10 23c5fb10 .L..H9.u....#... + 00a0 6b08c5fb 107310c5 fb107b18 c4c37d19 k....s....{...}. + 00b0 c401c4c3 7d19cd01 c4c37d19 d601c4c3 ....}.....}..... + 00c0 7d19df01 c59958c0 c59158c9 c58958d2 }.....X...X...X. + 00d0 c58158db c5f97cc0 c5f17cc9 c5e97cd2 ..X...|...|...|. + 00e0 c5e17cdb c5fb58c4 c5f358cd c5eb58d6 ..|...X...X...X. + 00f0 c5e358df c5fb1103 c5fb114b 08c5fb11 ..X........K.... + 0100 5310c5fb 115b18c5 f877c5f8 775bc390 S....[...w..w[.. + 0110 415762e1 ff0810c0 41564155 41545548 AWb.....AVAUATUH + 0120 89fd5348 81ece800 00004889 4c244848 ..SH......H.L$HH + 0130 89742420 48895424 404c894c 2408488b .t$ H.T$@L.L$.H. + 0140 9c242001 00004c89 c164488b 04252800 .$ ...L..dH..%(. + 0150 00004889 8424d800 000031c0 4983f901 ..H..$....1.I... + 0160 0f852a07 00004883 bc242801 0000010f ..*...H..$(..... + 0170 851b0700 00488b44 24204c8d 70034885 .....H.D$ L.p.H. + 0180 c04c0f49 f04983e6 fc0f8eca 04000048 .L.I.I.........H + 0190 85ed488d 7503488b 7c244848 89742438 ..H.u.H.|$HH.t$8 + 01a0 480f49f5 4c8b7c24 404889f0 4889fe4c H.I.L.|$@H..H..L + 01b0 8d1cfd00 00000048 83e0fc48 c1e70448 .......H...H...H + 01c0 c1e6054d 8d543f10 48894424 10488974 ...M.T?.H.D$.H.t + 01d0 2430498d 043f4883 c620488d 7c247048 $0I..?H.. H.|$pH + 01e0 89742428 48897c24 684c897c 24084c89 .t$(H.|$hL.|$.L. + 01f0 7424184d 89fd4989 c64989dc 41bf0400 t$.M..I..I..A... + 0200 000062a1 f50057c9 4c89d80f 1f440000 ..b...W.L....D.. + 0210 62b1ff00 5974f9fc 488b7c24 0862b1ff b...Yt..H.|$.b.. + 0220 00596cf9 fdc5fb10 0762b1ff 00597cf9 .Yl......b...Y|. + 0230 fec4c2c9 a9042462 31ff0059 44f9ff48 ......$b1..YD..H + 0240 8b542438 4a8d3428 4e8d0430 c4c17b11 .T$8J.4(N..0..{. + 0250 0424c5fb 10440708 4c29fac4 c2d1a944 .$...D..L).....D + 0260 240848c7 84249000 00000000 000048c7 $.H..$........H. + 0270 84249800 00000000 000048c7 8424a000 .$........H..$.. + 0280 00000000 000048c7 8424a800 00000000 ......H..$...... + 0290 0000c4c1 7b114424 08c4c17b 10024c89 ....{.D$...{..L. + 02a0 ac24b000 0000c4c2 c1a94424 104889b4 .$........D$.H.. + 02b0 24b80000 004c89b4 24c00000 004c8984 $....L..$....L.. + 02c0 24c80000 00c5fb11 742470c4 c17b1144 $.......t$p..{.D + 02d0 2410c4c1 7b104402 08c5fb11 6c2478c4 $...{.D.....l$x. + 02e0 c2b9a944 2418c5fb 11bc2480 000000c5 ...D$.....$..... + 02f0 7b118424 88000000 498d7ffd 62b1f700 {..$....I...b... + 0300 10d1c4c1 7b114424 184883fa 0b0f8e9d ....{.D$.H...... + 0310 010000c4 c17b1044 fd004989 f9c4e2c9 .....{.D..I..... /usr/lib64/libopenblas_openmp.a/dsymv_L_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dsymv_L_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dsymv_L_SKYLAKEX.o (objdump) @@ -3,7 +3,11 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 2c000000 1c000000 ........,....... - 0020 00000000 f6080000 00410e10 8602470d .........A....G. - 0030 06518f03 8e048d05 8c068307 0396030a .Q.............. - 0040 0c070841 0b000000 ...A.... + 0010 1b0c0708 90010000 18000000 1c000000 ................ + 0020 00000000 0f010000 00410e10 8302030d .........A...... + 0030 010e0800 58000000 38000000 00000000 ....X...8....... + 0040 c0080000 00420e10 8f02480e 188e0342 .....B....H....B + 0050 0e208d04 420e288c 05410e30 8606440e . ..B.(..A.0..D. + 0060 38830747 0ea00203 26060a0e 38410e30 8..G....&...8A.0 + 0070 410e2842 0e20420e 18420e10 440e0844 A.(B. B..B..D..D + 0080 0b02db0e a8027c0e a0020000 00000000 ......|......... /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_COOPERLAKE.o (disasm) @@ -12,1380 +12,326 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) - mov %r9,offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,(%rsp) + mov offset(%rsp),%rbx test %rsi,%rsi jle - mov %r8,%rsi - imul %rcx,%rsi mov %rcx,%rax - mov %r8,%r9 - lea (%rcx,%rsi,1),%rcx - mov %rsi,%rdx - lea (%rax,%rcx,1),%rsi - lea (%rax,%rsi,1),%rdi - lea (%rax,%rdi,1),%r8 - lea (%r8,%rax,1),%r11 - mov %rax,%rbx - add %r11,%rbx - mov %r11,-offset(%rsp) - lea (%rbx,%rax,1),%r11 - mov %rbx,-offset(%rsp) - lea (%r11,%rax,1),%rbx - lea (%rbx,%rax,1),%rbp - lea offset(%rbp,%rax,1),%r12 - lea (%r12,%rax,1),%r13 - lea offset(%r13,%rax,1),%r14 - lea (%r14,%rax,1),%r15 - lea (%r15,%rax,1),%r10 - mov %r10,-offset(%rsp) - mov offset(%rsp),%r10 - shl $something,%rax - sar $something,%r10 - mov %r10,offset(%rsp) - mov offset(%rsp),%r10 - mov %rax,offset(%rsp) - and $something,%r10d - mov %r10,offset(%rsp) - shl $something,%r10 - mov %r10,offset(%rsp) - mov offset(%rsp),%r10 - mov offset(%rsp),%rax - shl $something,%r10 - add %rax,%r10 - mov %r10,offset(%rsp) - mov %rax,%r10 - imul offset(%rsp),%rax + imul %r8,%rax + mov %rsi,%r14 + mov %rdi,%r15 add %r9,%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,8),%r9 - mov %r10,%rax - inc %rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r9,offset(%rsp) - mov %r10,%rax - mov offset(%rsp),%r9 - add %rdx,%rax - lea (%r9,%rax,8),%rdx - mov %rdx,offset(%rsp) - lea (%r10,%rcx,1),%rax - mov %r10,%rdx - mov %r9,%r10 - lea (%r9,%rax,8),%r9 - lea (%rdx,%rsi,1),%rax - mov %rdx,%rcx - lea (%r10,%rax,8),%rsi - lea (%rdx,%rdi,1),%rax - mov %rsi,offset(%rsp) - mov %rdx,%rsi - lea (%r10,%rax,8),%rdx - lea (%rcx,%r8,1),%rax - mov %rdx,offset(%rsp) - lea (%r10,%rax,8),%rdx - mov -offset(%rsp),%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r10,%rax,8),%rdx - mov -offset(%rsp),%rax - mov %rdx,offset(%rsp) - add %rcx,%rax /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_COOPERLAKE.o (objdump) @@ -2,886 +2,116 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24a00000 0048c1fe 044889bc .H..$....H...H.. - 0020 24900000 00488954 24684889 4c24584c $....H.T$hH.L$XL - 0030 89442440 4c898c24 80000000 4889b424 .D$@L..$....H..$ - 0040 c0010000 4885f60f 8ef71600 004c89c6 ....H........L.. - 0050 480faff1 4889c84d 89c1488d 0c314889 H...H..M..H..1H. - 0060 f2488d34 08488d3c 304c8d04 384d8d1c .H.4.H.<0L..8M.. - 0070 004889c3 4c01db4c 895c2488 4c8d1c03 .H..L..L.\$.L... - 0080 48895c24 98498d1c 03488d2c 034c8d64 H.\$.I...H.,.L.d - 0090 05004d8d 2c044d8d 7405004d 8d3c064d ..M.,.M.t..M.<.M - 00a0 8d14074c 89542490 4c8b9424 90000000 ...L.T$.L..$.... - 00b0 48c1e007 49c1fa04 4c899424 88000000 H...I...L..$.... - 00c0 4c8b9424 90000000 48894424 604183e2 L..$....H.D$`A.. - 00d0 0f4c8954 245049c1 e2074c89 9424b801 .L.T$PI...L..$.. - 00e0 00004c8b 9424c001 0000488b 84248000 ..L..$....H..$.. - 00f0 000049c1 e2044901 c24c8994 24980000 ..I...I..L..$... - 0100 004989c2 480faf44 24584c01 c84c8b4c .I..H..D$XL..L.L - 0110 24684d8d 0cc14c89 d048ffc0 480faf44 $hM...L..H..H..D - 0120 24584c89 8c24f800 00004c8b 4c246848 $XL..$....L.L$hH - 0130 03442440 4d8d0cc1 4c89d048 83c00248 .D$@M...L..H...H - 0140 0faf4424 584c898c 24d00000 004c8b4c ..D$XL..$....L.L - 0150 24684803 4424404d 8d0cc14c 89d04883 $hH.D$@M...L..H. - 0160 c003480f af442458 4c898c24 e0000000 ..H..D$XL..$.... - 0170 4c8b4c24 68480344 24404d8d 0cc14c89 L.L$hH.D$@M...L. - 0180 d04883c0 04480faf 4424584c 898c24a8 .H...H..D$XL..$. - 0190 0000004c 8b4c2468 48034424 404d8d0c ...L.L$hH.D$@M.. - 01a0 c14c89d0 4883c005 480faf44 24584c89 .L..H...H..D$XL. - 01b0 8c24c000 00004803 4424404c 8b4c2468 .$....H.D$@L.L$h - 01c0 4d8d0cc1 4c89d048 83c00648 0faf4424 M...L..H...H..D$ - 01d0 584c898c 24000100 004c8b4c 24684803 XL..$....L.L$hH. - 01e0 4424404d 8d0cc14c 89d04883 c007480f D$@M...L..H...H. - 01f0 af442458 4c898c24 10010000 4c8b4c24 .D$XL..$....L.L$ - 0200 68480344 24404d8d 0cc14c89 d04883c0 hH.D$@M...L..H.. - 0210 08480faf 4424584c 898c2420 0100004c .H..D$XL..$ ...L - 0220 8b4c2468 48034424 404d8d0c c14c89d0 .L$hH.D$@M...L.. - 0230 4883c009 480faf44 24584c89 8c243001 H...H..D$XL..$0. - 0240 00004c8b 4c246848 03442440 4d8d0cc1 ..L.L$hH.D$@M... - 0250 4c89d048 83c00a48 0faf4424 584c898c L..H...H..D$XL.. - 0260 24400100 004c8b4c 24684803 4424404d $@...L.L$hH.D$@M - 0270 8d0cc14c 89d04883 c00b480f af442458 ...L..H...H..D$X - 0280 4c898c24 50010000 4c8b4c24 68480344 L..$P...L.L$hH.D - 0290 24404d8d 0cc14c89 d04883c0 0c480faf $@M...L..H...H.. - 02a0 4424584c 898c2460 0100004c 8b4c2468 D$XL..$`...L.L$h - 02b0 48034424 404d8d0c c14c89d0 4883c00d H.D$@M...L..H... - 02c0 480faf44 24584c89 8c247001 00004803 H..D$XL..$p...H. - 02d0 4424404c 8b4c2468 4d8d0cc1 4c89d048 D$@L.L$hM...L..H - 02e0 83c00e48 0faf4424 584c898c 24800100 ...H..D$XL..$... - 02f0 004c8b4c 24684803 4424404d 8d0cc14c .L.L$hH.D$@M...L - 0300 89d04883 c00f480f af442458 4c898c24 ..H...H..D$XL..$ - 0310 90010000 4c8b4c24 68480344 24404d8d ....L.L$hH.D$@M. - 0320 0cc14c89 8c24a001 00004c89 d04c8b4c ..L..$....L..L.L - 0330 24684801 d0498d14 c1488994 24b80000 $hH..I...H..$... - 0340 00498d04 0a4c89d2 4d89ca4d 8d0cc148 .I...L..M..M...H - 0350 8d043248 89d1498d 34c2488d 043a4889 ..2H..I.4.H..:H. - 0360 b424b000 00004889 d6498d14 c24a8d04 .$....H..I...J.. - 0370 01488994 24c80000 00498d14 c2488b44 .H..$....I...H.D - 0380 24884889 9424d800 00004801 c8498d14 $.H..$....H..I.. - 0390 c2488b44 24984889 9424f000 00004801 .H.D$.H..$....H. - 03a0 c8498d14 c24a8d04 19488994 24080100 .I...J...H..$... - 03b0 00498d14 c2488d04 19488994 24180100 .I...H...H..$... - 03c0 00498d14 c2488d04 29488994 24280100 .I...H..)H..$(.. - 03d0 00498d14 c24a8d04 21488994 24380100 .I...J..!H..$8.. - 03e0 00498d14 c24a8d04 29488994 24480100 .I...J..)H..$H.. - 03f0 00498d14 c24a8d04 31488b5c 24904889 .I...J..1H.\$.H. - 0400 94245801 0000498d 14c24a8d 04394889 .$X...I...J..9H. - 0410 94246801 0000498d 14c24889 c84801d8 .$h...I...H..H.. - 0420 48035c24 58488994 24780100 00498d14 H.\$XH..$x...I.. - 0430 c24889d8 4801c849 8d1cc248 899c2498 .H..H..I...H..$. - 0440 0100004c 898c24e8 00000048 89942488 ...L..$....H..$. - 0450 01000048 8bbc2490 00000048 8b4c2440 ...H..$....H.L$@ - 0460 4889f848 83e0f048 01c84889 44244848 H..H...H..H.D$HH - 0470 8b842488 00000048 897424e0 4889c348 ..$....H.t$.H..H - 0480 c1e30b48 c1e00448 01c84889 8424b001 ...H...H..H..$.. - 0490 00004889 f883e00e 48898424 c8010000 ..H.....H..$.... - 04a0 4889f883 e00c83e7 0848899c 24a80100 H........H..$... - 04b0 0048c744 24780000 000048c7 44247000 .H.D$x....H.D$p. - 04c0 00000048 898424d0 01000048 89bc24d8 ...H..$....H..$. - 04d0 010000e9 71010000 0f1f8400 00000000 ....q........... - 04e0 488b4424 70488bbc 24e80000 00488b8c H.D$pH..$....H.. - 04f0 24d80000 004801c7 48897c24 c0488bbc $....H..H.|$.H.. - 0500 24c80000 004801c1 4801c748 897c24d0 $....H..H..H.|$. - 0510 488bbc24 f0000000 48894c24 d84801c7 H..$....H.L$.H.. - 0520 48897c24 f0488bb4 24b80000 00488b8c H.|$.H..$....H.. - 0530 24080100 00488bbc 24180100 004801c6 $....H..$....H.. - 0540 4801c148 01c74889 7424b848 894c24f8 H..H..H.t$.H.L$. - 0550 48893c24 488b9c24 b0000000 488b8c24 H.<$H..$....H..$ - 0560 28010000 488bb424 38010000 488bbc24 (...H..$8...H..$ - 0570 48010000 4801c348 01c14801 c64801c7 H...H..H..H..H.. - 0580 48895c24 c848894c 24084889 74241048 H.\$.H.L$.H.t$.H - 0590 897c2418 488b9c24 58010000 488b8c24 .|$.H..$X...H..$ - 05a0 68010000 488bb424 78010000 488bbc24 h...H..$x...H..$ - 05b0 88010000 4801c348 01c14801 c64801c7 ....H..H..H..H.. - 05c0 48038424 98010000 48895c24 2048894c H..$....H.\$ H.L - 05d0 24284889 74243048 897c24e8 48894424 $(H.t$0H.|$.H.D$ - 05e0 384883bc 24880000 0000488b 4424400f 8H..$.....H.D$@. - 05f0 8f790100 0048837c 24500074 23483944 .y...H.|$P.t#H9D - 0600 24e00f8c 6f290000 0f8e621a 0000488b $...o)....b...H. - 0610 8424b801 00004801 84241802 00006690 .$....H..$....f. - 0620 48834424 e010488b 7c246048 836c2470 H.D$..H.|$`H.l$p - 0630 8048017c 2478488b 4424e048 3b842498 .H.|$xH.D$.H;.$. - 0640 0000000f 84dc1000 00488b4c 24404839 .........H.L$@H9 - 0650 4c24e00f 8d87feff ff488b44 2478488b L$.......H.D$xH. - 0660 bc24f800 0000488b b424d000 0000488b .$....H..$....H. - 0670 9c24e000 00004801 c74801c6 4801c348 .$....H..H..H..H - 0680 897c24b8 48897424 c048895c 24c8488b .|$.H.t$.H.\$.H. - 0690 bc24a800 0000488b b424c000 0000488b .$....H..$....H. - 06a0 9c240001 0000488b 8c241001 00004801 .$....H..$....H. - 06b0 c74801c6 4801c348 01c14889 7c24d048 .H..H..H..H.|$.H - 06c0 897424d8 48895c24 f048894c 24f8488b .t$.H.\$.H.L$.H. - 06d0 b4242001 0000488b bc243001 0000488b .$ ...H..$0...H. - 06e0 9c244001 0000488b 8c245001 00004801 .$@...H..$P...H. - 06f0 c64801c7 4801c348 01c14889 34244889 .H..H..H..H.4$H. - 0700 7c240848 895c2410 48894c24 18488bb4 |$.H.\$.H.L$.H.. - 0710 24600100 00488bbc 24700100 00488b9c $`...H..$p...H.. - 0720 24800100 00488b8c 24900100 004801c6 $....H..$....H.. - 0730 4801c748 01c34801 c1480384 24a00100 H..H..H..H..$... - 0740 00488974 24204889 7c242848 895c2430 .H.t$ H.|$(H.\$0 - 0750 48894c24 e8488944 24384883 bc248800 H.L$.H.D$8H..$.. - 0760 00000048 8b442440 0f8e87fe ffff488b ...H.D$@......H. - 0770 84241802 0000488d 90000800 00488b44 .$....H......H.D - 0780 24404889 4424b0eb 780f1f80 00000000 $@H.D$..x....... - 0790 488b4424 60480144 24b84801 4424c048 H.D$`H.D$.H.D$.H - 07a0 014424c8 48014424 d0480144 24d84801 .D$.H.D$.H.D$.H. - 07b0 4424f048 014424f8 48010424 48014424 D$.H.D$.H..$H.D$ - 07c0 08480144 24104801 44241848 01442420 .H.D$.H.D$.H.D$ - 07d0 48014424 28480144 24304801 4424e848 H.D$(H.D$0H.D$.H - 07e0 01442438 48834424 b0104881 c2000800 .D$8H.D$..H..... - 07f0 00488b44 24b0483b 4424480f 84070f00 .H.D$.H;D$H..... - 0800 00488b7c 24b0488d 8200f8ff ff48397c .H.|$.H......H9| - 0810 24e00f8c 100d0000 0f8f72ff ffff488b $.........r...H. - 0820 4424b848 8b5c24c0 c5fb1000 48c78208 D$.H.\$.....H... - 0830 f8ffff00 00000048 c78210f8 ffff0000 .......H........ - 0840 000048c7 8218f8ff ff000000 0048c782 ..H..........H.. - 0850 20f8ffff 00000000 48c78228 f8ffff00 .......H..(.... - 0860 00000048 c78230f8 ffff0000 000048c7 ...H..0.......H. - 0870 8238f8ff ff000000 0048c782 40f8ffff .8.......H..@... - 0880 00000000 48c78248 f8ffff00 00000048 ....H..H.......H - 0890 c78250f8 ffff0000 000048c7 8258f8ff ..P.......H..X.. - 08a0 ff000000 0048c782 60f8ffff 00000000 .....H..`....... - 08b0 48c78268 f8ffff00 00000048 c78270f8 H..h.......H..p. - 08c0 ffff0000 000048c7 8278f8ff ff000000 ......H..x...... - 08d0 00c5fb11 8200f8ff ff4883eb 80c5fb10 .........H...... - 08e0 4008c5fb 118280f8 ffffc5fb 10438848 @............C.H - 08f0 c78290f8 ffff0000 0000c5fb 118288f8 ................ - 0900 ffff48c7 8298f8ff ff000000 0048c782 ..H..........H.. - 0910 a0f8ffff 00000000 48c782a8 f8ffff00 ........H....... - 0920 00000048 c782b0f8 ffff0000 000048c7 ...H..........H. - 0930 82b8f8ff ff000000 0048c782 c0f8ffff .........H...... - 0940 00000000 48c782c8 f8ffff00 00000048 ....H..........H - 0950 c782d0f8 ffff0000 000048c7 82d8f8ff ..........H..... - 0960 ff000000 0048c782 e0f8ffff 00000000 .....H.......... - 0970 48c782e8 f8ffff00 00000048 c782f0f8 H..........H.... - 0980 ffff0000 000048c7 82f8f8ff ff000000 ......H......... - 0990 00488b74 24c8488b 7c24d0c5 fb104010 .H.t$.H.|$....@. - 09a0 4883ee80 c5fb1182 00f9ffff c5fb1043 H..............C - 09b0 904883ef 80c5fb11 8208f9ff ffc5fb10 .H.............. - 09c0 469048c7 8218f9ff ff000000 0048c782 F.H..........H.. - 09d0 20f9ffff 00000000 48c78228 f9ffff00 .......H..(.... - 09e0 00000048 c78230f9 ffff0000 000048c7 ...H..0.......H. - 09f0 8238f9ff ff000000 0048c782 40f9ffff .8.......H..@... - 0a00 00000000 48c78248 f9ffff00 00000048 ....H..H.......H - 0a10 c78250f9 ffff0000 000048c7 8258f9ff ..P.......H..X.. - 0a20 ff000000 0048c782 60f9ffff 00000000 .....H..`....... - 0a30 48c78268 f9ffff00 00000048 c78270f9 H..h.......H..p. - 0a40 ffff0000 000048c7 8278f9ff ff000000 ......H..x...... - 0a50 00c5fb11 8210f9ff ffc5fb10 4018c5fb ............@... - 0a60 118280f9 ffffc5fb 104398c5 fb118288 .........C...... - 0a70 f9ffffc5 fb104698 c5fb1182 90f9ffff ......F......... - 0a80 c5fb1047 98c5fb11 8298f9ff ff48c782 ...G.........H.. - 0a90 a0f9ffff 00000000 48c782a8 f9ffff00 ........H....... - 0aa0 00000048 c782b0f9 ffff0000 000048c7 ...H..........H. - 0ab0 82b8f9ff ff000000 0048c782 c0f9ffff .........H...... - 0ac0 00000000 48c782c8 f9ffff00 00000048 ....H..........H - 0ad0 c782d0f9 ffff0000 000048c7 82d8f9ff ..........H..... - 0ae0 ff000000 0048c782 e0f9ffff 00000000 .....H.......... - 0af0 48c782e8 f9ffff00 00000048 c782f0f9 H..........H.... - 0b00 ffff0000 000048c7 82f8f9ff ff000000 ......H......... - 0b10 00488b4c 24d8c5fb 104020c5 fb118200 .H.L$....@ ..... - 0b20 faffffc5 fb1043a0 c5fb1182 08faffff ......C......... - 0b30 c5fb1046 a0c5fb11 8210faff ffc5fb10 ...F............ - 0b40 47a0c5fb 118218fa ffffc5fb 10412048 G............A H - 0b50 c78228fa ffff0000 0000c5fb 118220fa ..(........... . - 0b60 ffff48c7 8230faff ff000000 0048c782 ..H..0.......H.. - 0b70 38faffff 00000000 48c78240 faffff00 8.......H..@.... - 0b80 00000048 c78248fa ffff0000 000048c7 ...H..H.......H. - 0b90 8250faff ff000000 0048c782 58faffff .P.......H..X... - 0ba0 00000000 48c78260 faffff00 00000048 ....H..`.......H - 0bb0 c78268fa ffff0000 000048c7 8270faff ..h.......H..p.. - 0bc0 ff000000 0048c782 78faffff 00000000 .....H..x....... - 0bd0 4c8b7424 f0c5fb10 40284983 ee80c5fb L.t$....@(I..... - 0be0 118280fa ffffc5fb 1043a8c5 fb118288 .........C...... - 0bf0 faffffc5 fb1046a8 c5fb1182 90faffff ......F......... - 0c00 c5fb1047 a8c5fb11 8298faff ffc5fb10 ...G............ - 0c10 4128c5fb 1182a0fa ffffc4c1 7b1046a8 A(..........{.F. /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 2c370000 00420e10 8f02420e ....,7...B....B. + 0020 00000000 0e070000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 51200a0e ..A.8..G....Q .. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0842 0b000000 D..B.... + 0040 8606410e 38830744 0e48034e 050a0e38 ..A.8..D.H.N...8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08480b 00000000 ..H..... /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_SKYLAKEX.o (disasm) @@ -12,1380 +12,326 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) - mov %r9,offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,(%rsp) + mov offset(%rsp),%rbx test %rsi,%rsi jle - mov %r8,%rsi - imul %rcx,%rsi mov %rcx,%rax - mov %r8,%r9 - lea (%rcx,%rsi,1),%rcx - mov %rsi,%rdx - lea (%rax,%rcx,1),%rsi - lea (%rax,%rsi,1),%rdi - lea (%rax,%rdi,1),%r8 - lea (%r8,%rax,1),%r11 - mov %rax,%rbx - add %r11,%rbx - mov %r11,-offset(%rsp) - lea (%rbx,%rax,1),%r11 - mov %rbx,-offset(%rsp) - lea (%r11,%rax,1),%rbx - lea (%rbx,%rax,1),%rbp - lea offset(%rbp,%rax,1),%r12 - lea (%r12,%rax,1),%r13 - lea offset(%r13,%rax,1),%r14 - lea (%r14,%rax,1),%r15 - lea (%r15,%rax,1),%r10 - mov %r10,-offset(%rsp) - mov offset(%rsp),%r10 - shl $something,%rax - sar $something,%r10 - mov %r10,offset(%rsp) - mov offset(%rsp),%r10 - mov %rax,offset(%rsp) - and $something,%r10d - mov %r10,offset(%rsp) - shl $something,%r10 - mov %r10,offset(%rsp) - mov offset(%rsp),%r10 - mov offset(%rsp),%rax - shl $something,%r10 - add %rax,%r10 - mov %r10,offset(%rsp) - mov %rax,%r10 - imul offset(%rsp),%rax + imul %r8,%rax + mov %rsi,%r14 + mov %rdi,%r15 add %r9,%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,8),%r9 - mov %r10,%rax - inc %rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %r9,offset(%rsp) - mov %r10,%rax - mov offset(%rsp),%r9 - add %rdx,%rax - lea (%r9,%rax,8),%rdx - mov %rdx,offset(%rsp) - lea (%r10,%rcx,1),%rax - mov %r10,%rdx - mov %r9,%r10 - lea (%r9,%rax,8),%r9 - lea (%rdx,%rsi,1),%rax - mov %rdx,%rcx - lea (%r10,%rax,8),%rsi - lea (%rdx,%rdi,1),%rax - mov %rsi,offset(%rsp) - mov %rdx,%rsi - lea (%r10,%rax,8),%rdx - lea (%rcx,%r8,1),%rax - mov %rdx,offset(%rsp) - lea (%r10,%rax,8),%rdx - mov -offset(%rsp),%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r10,%rax,8),%rdx - mov -offset(%rsp),%rax - mov %rdx,offset(%rsp) - add %rcx,%rax /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_SKYLAKEX.o (objdump) @@ -2,886 +2,116 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24a00000 0048c1fe 044889bc .H..$....H...H.. - 0020 24900000 00488954 24684889 4c24584c $....H.T$hH.L$XL - 0030 89442440 4c898c24 80000000 4889b424 .D$@L..$....H..$ - 0040 c0010000 4885f60f 8ef71600 004c89c6 ....H........L.. - 0050 480faff1 4889c84d 89c1488d 0c314889 H...H..M..H..1H. - 0060 f2488d34 08488d3c 304c8d04 384d8d1c .H.4.H.<0L..8M.. - 0070 004889c3 4c01db4c 895c2488 4c8d1c03 .H..L..L.\$.L... - 0080 48895c24 98498d1c 03488d2c 034c8d64 H.\$.I...H.,.L.d - 0090 05004d8d 2c044d8d 7405004d 8d3c064d ..M.,.M.t..M.<.M - 00a0 8d14074c 89542490 4c8b9424 90000000 ...L.T$.L..$.... - 00b0 48c1e007 49c1fa04 4c899424 88000000 H...I...L..$.... - 00c0 4c8b9424 90000000 48894424 604183e2 L..$....H.D$`A.. - 00d0 0f4c8954 245049c1 e2074c89 9424b801 .L.T$PI...L..$.. - 00e0 00004c8b 9424c001 0000488b 84248000 ..L..$....H..$.. - 00f0 000049c1 e2044901 c24c8994 24980000 ..I...I..L..$... - 0100 004989c2 480faf44 24584c01 c84c8b4c .I..H..D$XL..L.L - 0110 24684d8d 0cc14c89 d048ffc0 480faf44 $hM...L..H..H..D - 0120 24584c89 8c24f800 00004c8b 4c246848 $XL..$....L.L$hH - 0130 03442440 4d8d0cc1 4c89d048 83c00248 .D$@M...L..H...H - 0140 0faf4424 584c898c 24d00000 004c8b4c ..D$XL..$....L.L - 0150 24684803 4424404d 8d0cc14c 89d04883 $hH.D$@M...L..H. - 0160 c003480f af442458 4c898c24 e0000000 ..H..D$XL..$.... - 0170 4c8b4c24 68480344 24404d8d 0cc14c89 L.L$hH.D$@M...L. - 0180 d04883c0 04480faf 4424584c 898c24a8 .H...H..D$XL..$. - 0190 0000004c 8b4c2468 48034424 404d8d0c ...L.L$hH.D$@M.. - 01a0 c14c89d0 4883c005 480faf44 24584c89 .L..H...H..D$XL. - 01b0 8c24c000 00004803 4424404c 8b4c2468 .$....H.D$@L.L$h - 01c0 4d8d0cc1 4c89d048 83c00648 0faf4424 M...L..H...H..D$ - 01d0 584c898c 24000100 004c8b4c 24684803 XL..$....L.L$hH. - 01e0 4424404d 8d0cc14c 89d04883 c007480f D$@M...L..H...H. - 01f0 af442458 4c898c24 10010000 4c8b4c24 .D$XL..$....L.L$ - 0200 68480344 24404d8d 0cc14c89 d04883c0 hH.D$@M...L..H.. - 0210 08480faf 4424584c 898c2420 0100004c .H..D$XL..$ ...L - 0220 8b4c2468 48034424 404d8d0c c14c89d0 .L$hH.D$@M...L.. - 0230 4883c009 480faf44 24584c89 8c243001 H...H..D$XL..$0. - 0240 00004c8b 4c246848 03442440 4d8d0cc1 ..L.L$hH.D$@M... - 0250 4c89d048 83c00a48 0faf4424 584c898c L..H...H..D$XL.. - 0260 24400100 004c8b4c 24684803 4424404d $@...L.L$hH.D$@M - 0270 8d0cc14c 89d04883 c00b480f af442458 ...L..H...H..D$X - 0280 4c898c24 50010000 4c8b4c24 68480344 L..$P...L.L$hH.D - 0290 24404d8d 0cc14c89 d04883c0 0c480faf $@M...L..H...H.. - 02a0 4424584c 898c2460 0100004c 8b4c2468 D$XL..$`...L.L$h - 02b0 48034424 404d8d0c c14c89d0 4883c00d H.D$@M...L..H... - 02c0 480faf44 24584c89 8c247001 00004803 H..D$XL..$p...H. - 02d0 4424404c 8b4c2468 4d8d0cc1 4c89d048 D$@L.L$hM...L..H - 02e0 83c00e48 0faf4424 584c898c 24800100 ...H..D$XL..$... - 02f0 004c8b4c 24684803 4424404d 8d0cc14c .L.L$hH.D$@M...L - 0300 89d04883 c00f480f af442458 4c898c24 ..H...H..D$XL..$ - 0310 90010000 4c8b4c24 68480344 24404d8d ....L.L$hH.D$@M. - 0320 0cc14c89 8c24a001 00004c89 d04c8b4c ..L..$....L..L.L - 0330 24684801 d0498d14 c1488994 24b80000 $hH..I...H..$... - 0340 00498d04 0a4c89d2 4d89ca4d 8d0cc148 .I...L..M..M...H - 0350 8d043248 89d1498d 34c2488d 043a4889 ..2H..I.4.H..:H. - 0360 b424b000 00004889 d6498d14 c24a8d04 .$....H..I...J.. - 0370 01488994 24c80000 00498d14 c2488b44 .H..$....I...H.D - 0380 24884889 9424d800 00004801 c8498d14 $.H..$....H..I.. - 0390 c2488b44 24984889 9424f000 00004801 .H.D$.H..$....H. - 03a0 c8498d14 c24a8d04 19488994 24080100 .I...J...H..$... - 03b0 00498d14 c2488d04 19488994 24180100 .I...H...H..$... - 03c0 00498d14 c2488d04 29488994 24280100 .I...H..)H..$(.. - 03d0 00498d14 c24a8d04 21488994 24380100 .I...J..!H..$8.. - 03e0 00498d14 c24a8d04 29488994 24480100 .I...J..)H..$H.. - 03f0 00498d14 c24a8d04 31488b5c 24904889 .I...J..1H.\$.H. - 0400 94245801 0000498d 14c24a8d 04394889 .$X...I...J..9H. - 0410 94246801 0000498d 14c24889 c84801d8 .$h...I...H..H.. - 0420 48035c24 58488994 24780100 00498d14 H.\$XH..$x...I.. - 0430 c24889d8 4801c849 8d1cc248 899c2498 .H..H..I...H..$. - 0440 0100004c 898c24e8 00000048 89942488 ...L..$....H..$. - 0450 01000048 8bbc2490 00000048 8b4c2440 ...H..$....H.L$@ - 0460 4889f848 83e0f048 01c84889 44244848 H..H...H..H.D$HH - 0470 8b842488 00000048 897424e0 4889c348 ..$....H.t$.H..H - 0480 c1e30b48 c1e00448 01c84889 8424b001 ...H...H..H..$.. - 0490 00004889 f883e00e 48898424 c8010000 ..H.....H..$.... - 04a0 4889f883 e00c83e7 0848899c 24a80100 H........H..$... - 04b0 0048c744 24780000 000048c7 44247000 .H.D$x....H.D$p. - 04c0 00000048 898424d0 01000048 89bc24d8 ...H..$....H..$. - 04d0 010000e9 71010000 0f1f8400 00000000 ....q........... - 04e0 488b4424 70488bbc 24e80000 00488b8c H.D$pH..$....H.. - 04f0 24d80000 004801c7 48897c24 c0488bbc $....H..H.|$.H.. - 0500 24c80000 004801c1 4801c748 897c24d0 $....H..H..H.|$. - 0510 488bbc24 f0000000 48894c24 d84801c7 H..$....H.L$.H.. - 0520 48897c24 f0488bb4 24b80000 00488b8c H.|$.H..$....H.. - 0530 24080100 00488bbc 24180100 004801c6 $....H..$....H.. - 0540 4801c148 01c74889 7424b848 894c24f8 H..H..H.t$.H.L$. - 0550 48893c24 488b9c24 b0000000 488b8c24 H.<$H..$....H..$ - 0560 28010000 488bb424 38010000 488bbc24 (...H..$8...H..$ - 0570 48010000 4801c348 01c14801 c64801c7 H...H..H..H..H.. - 0580 48895c24 c848894c 24084889 74241048 H.\$.H.L$.H.t$.H - 0590 897c2418 488b9c24 58010000 488b8c24 .|$.H..$X...H..$ - 05a0 68010000 488bb424 78010000 488bbc24 h...H..$x...H..$ - 05b0 88010000 4801c348 01c14801 c64801c7 ....H..H..H..H.. - 05c0 48038424 98010000 48895c24 2048894c H..$....H.\$ H.L - 05d0 24284889 74243048 897c24e8 48894424 $(H.t$0H.|$.H.D$ - 05e0 384883bc 24880000 0000488b 4424400f 8H..$.....H.D$@. - 05f0 8f790100 0048837c 24500074 23483944 .y...H.|$P.t#H9D - 0600 24e00f8c 6f290000 0f8e621a 0000488b $...o)....b...H. - 0610 8424b801 00004801 84241802 00006690 .$....H..$....f. - 0620 48834424 e010488b 7c246048 836c2470 H.D$..H.|$`H.l$p - 0630 8048017c 2478488b 4424e048 3b842498 .H.|$xH.D$.H;.$. - 0640 0000000f 84dc1000 00488b4c 24404839 .........H.L$@H9 - 0650 4c24e00f 8d87feff ff488b44 2478488b L$.......H.D$xH. - 0660 bc24f800 0000488b b424d000 0000488b .$....H..$....H. - 0670 9c24e000 00004801 c74801c6 4801c348 .$....H..H..H..H - 0680 897c24b8 48897424 c048895c 24c8488b .|$.H.t$.H.\$.H. - 0690 bc24a800 0000488b b424c000 0000488b .$....H..$....H. - 06a0 9c240001 0000488b 8c241001 00004801 .$....H..$....H. - 06b0 c74801c6 4801c348 01c14889 7c24d048 .H..H..H..H.|$.H - 06c0 897424d8 48895c24 f048894c 24f8488b .t$.H.\$.H.L$.H. - 06d0 b4242001 0000488b bc243001 0000488b .$ ...H..$0...H. - 06e0 9c244001 0000488b 8c245001 00004801 .$@...H..$P...H. - 06f0 c64801c7 4801c348 01c14889 34244889 .H..H..H..H.4$H. - 0700 7c240848 895c2410 48894c24 18488bb4 |$.H.\$.H.L$.H.. - 0710 24600100 00488bbc 24700100 00488b9c $`...H..$p...H.. - 0720 24800100 00488b8c 24900100 004801c6 $....H..$....H.. - 0730 4801c748 01c34801 c1480384 24a00100 H..H..H..H..$... - 0740 00488974 24204889 7c242848 895c2430 .H.t$ H.|$(H.\$0 - 0750 48894c24 e8488944 24384883 bc248800 H.L$.H.D$8H..$.. - 0760 00000048 8b442440 0f8e87fe ffff488b ...H.D$@......H. - 0770 84241802 0000488d 90000800 00488b44 .$....H......H.D - 0780 24404889 4424b0eb 780f1f80 00000000 $@H.D$..x....... - 0790 488b4424 60480144 24b84801 4424c048 H.D$`H.D$.H.D$.H - 07a0 014424c8 48014424 d0480144 24d84801 .D$.H.D$.H.D$.H. - 07b0 4424f048 014424f8 48010424 48014424 D$.H.D$.H..$H.D$ - 07c0 08480144 24104801 44241848 01442420 .H.D$.H.D$.H.D$ - 07d0 48014424 28480144 24304801 4424e848 H.D$(H.D$0H.D$.H - 07e0 01442438 48834424 b0104881 c2000800 .D$8H.D$..H..... - 07f0 00488b44 24b0483b 4424480f 84070f00 .H.D$.H;D$H..... - 0800 00488b7c 24b0488d 8200f8ff ff48397c .H.|$.H......H9| - 0810 24e00f8c 100d0000 0f8f72ff ffff488b $.........r...H. - 0820 4424b848 8b5c24c0 c5fb1000 48c78208 D$.H.\$.....H... - 0830 f8ffff00 00000048 c78210f8 ffff0000 .......H........ - 0840 000048c7 8218f8ff ff000000 0048c782 ..H..........H.. - 0850 20f8ffff 00000000 48c78228 f8ffff00 .......H..(.... - 0860 00000048 c78230f8 ffff0000 000048c7 ...H..0.......H. - 0870 8238f8ff ff000000 0048c782 40f8ffff .8.......H..@... - 0880 00000000 48c78248 f8ffff00 00000048 ....H..H.......H - 0890 c78250f8 ffff0000 000048c7 8258f8ff ..P.......H..X.. - 08a0 ff000000 0048c782 60f8ffff 00000000 .....H..`....... - 08b0 48c78268 f8ffff00 00000048 c78270f8 H..h.......H..p. - 08c0 ffff0000 000048c7 8278f8ff ff000000 ......H..x...... - 08d0 00c5fb11 8200f8ff ff4883eb 80c5fb10 .........H...... - 08e0 4008c5fb 118280f8 ffffc5fb 10438848 @............C.H - 08f0 c78290f8 ffff0000 0000c5fb 118288f8 ................ - 0900 ffff48c7 8298f8ff ff000000 0048c782 ..H..........H.. - 0910 a0f8ffff 00000000 48c782a8 f8ffff00 ........H....... - 0920 00000048 c782b0f8 ffff0000 000048c7 ...H..........H. - 0930 82b8f8ff ff000000 0048c782 c0f8ffff .........H...... - 0940 00000000 48c782c8 f8ffff00 00000048 ....H..........H - 0950 c782d0f8 ffff0000 000048c7 82d8f8ff ..........H..... - 0960 ff000000 0048c782 e0f8ffff 00000000 .....H.......... - 0970 48c782e8 f8ffff00 00000048 c782f0f8 H..........H.... - 0980 ffff0000 000048c7 82f8f8ff ff000000 ......H......... - 0990 00488b74 24c8488b 7c24d0c5 fb104010 .H.t$.H.|$....@. - 09a0 4883ee80 c5fb1182 00f9ffff c5fb1043 H..............C - 09b0 904883ef 80c5fb11 8208f9ff ffc5fb10 .H.............. - 09c0 469048c7 8218f9ff ff000000 0048c782 F.H..........H.. - 09d0 20f9ffff 00000000 48c78228 f9ffff00 .......H..(.... - 09e0 00000048 c78230f9 ffff0000 000048c7 ...H..0.......H. - 09f0 8238f9ff ff000000 0048c782 40f9ffff .8.......H..@... - 0a00 00000000 48c78248 f9ffff00 00000048 ....H..H.......H - 0a10 c78250f9 ffff0000 000048c7 8258f9ff ..P.......H..X.. - 0a20 ff000000 0048c782 60f9ffff 00000000 .....H..`....... - 0a30 48c78268 f9ffff00 00000048 c78270f9 H..h.......H..p. - 0a40 ffff0000 000048c7 8278f9ff ff000000 ......H..x...... - 0a50 00c5fb11 8210f9ff ffc5fb10 4018c5fb ............@... - 0a60 118280f9 ffffc5fb 104398c5 fb118288 .........C...... - 0a70 f9ffffc5 fb104698 c5fb1182 90f9ffff ......F......... - 0a80 c5fb1047 98c5fb11 8298f9ff ff48c782 ...G.........H.. - 0a90 a0f9ffff 00000000 48c782a8 f9ffff00 ........H....... - 0aa0 00000048 c782b0f9 ffff0000 000048c7 ...H..........H. - 0ab0 82b8f9ff ff000000 0048c782 c0f9ffff .........H...... - 0ac0 00000000 48c782c8 f9ffff00 00000048 ....H..........H - 0ad0 c782d0f9 ffff0000 000048c7 82d8f9ff ..........H..... - 0ae0 ff000000 0048c782 e0f9ffff 00000000 .....H.......... - 0af0 48c782e8 f9ffff00 00000048 c782f0f9 H..........H.... - 0b00 ffff0000 000048c7 82f8f9ff ff000000 ......H......... - 0b10 00488b4c 24d8c5fb 104020c5 fb118200 .H.L$....@ ..... - 0b20 faffffc5 fb1043a0 c5fb1182 08faffff ......C......... - 0b30 c5fb1046 a0c5fb11 8210faff ffc5fb10 ...F............ - 0b40 47a0c5fb 118218fa ffffc5fb 10412048 G............A H - 0b50 c78228fa ffff0000 0000c5fb 118220fa ..(........... . - 0b60 ffff48c7 8230faff ff000000 0048c782 ..H..0.......H.. - 0b70 38faffff 00000000 48c78240 faffff00 8.......H..@.... - 0b80 00000048 c78248fa ffff0000 000048c7 ...H..H.......H. - 0b90 8250faff ff000000 0048c782 58faffff .P.......H..X... - 0ba0 00000000 48c78260 faffff00 00000048 ....H..`.......H - 0bb0 c78268fa ffff0000 000048c7 8270faff ..h.......H..p.. - 0bc0 ff000000 0048c782 78faffff 00000000 .....H..x....... - 0bd0 4c8b7424 f0c5fb10 40284983 ee80c5fb L.t$....@(I..... - 0be0 118280fa ffffc5fb 1043a8c5 fb118288 .........C...... - 0bf0 faffffc5 fb1046a8 c5fb1182 90faffff ......F......... - 0c00 c5fb1047 a8c5fb11 8298faff ffc5fb10 ...G............ - 0c10 4128c5fb 1182a0fa ffffc4c1 7b1046a8 A(..........{.F. /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnncopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 2c370000 00420e10 8f02420e ....,7...B....B. + 0020 00000000 0e070000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 51200a0e ..A.8..G....Q .. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0842 0b000000 D..B.... + 0040 8606410e 38830744 0e48034e 050a0e38 ..A.8..D.H.N...8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08480b 00000000 ..H..... /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_COOPERLAKE.o (disasm) @@ -12,1350 +12,339 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) - mov %r9,offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,(%rsp) + mov offset(%rsp),%rbx test %rsi,%rsi jle - mov %r8,%rbx - imul %rcx,%rbx mov %rcx,%rax - mov %r8,%r9 - lea (%rcx,%rbx,1),%rcx - lea (%rax,%rcx,1),%rsi - mov %rbx,%rdx - lea (%rax,%rsi,1),%rbx - lea (%rax,%rbx,1),%r8 - mov %rbx,-offset(%rsp) - lea (%r8,%rax,1),%rbx - lea (%rbx,%rax,1),%r10 - lea (%r10,%rax,1),%r11 - mov %rbx,-offset(%rsp) - lea (%r11,%rax,1),%rbx - lea (%rbx,%rax,1),%rbp - lea offset(%rbp,%rax,1),%r12 - lea (%r12,%rax,1),%r13 - lea offset(%r13,%rax,1),%r14 - lea (%r14,%rax,1),%r15 - lea (%r15,%rax,1),%rdi - mov %rdi,-offset(%rsp) - mov offset(%rsp),%rdi - shl $something,%rax - sar $something,%rdi - mov %rdi,offset(%rsp) - mov offset(%rsp),%rdi - mov %rax,offset(%rsp) - and $something,%edi - mov %rdi,offset(%rsp) - shl $something,%rdi - mov %rdi,offset(%rsp) - mov offset(%rsp),%rdi - mov offset(%rsp),%rax - shl $something,%rdi - add %rax,%rdi - mov %rdi,offset(%rsp) - mov %rax,%rdi - imul offset(%rsp),%rax + imul %r8,%rax + mov %rsi,%r14 + mov %rdi,%r15 add %r9,%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - inc %rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 + lea (%rdx,%rax,8),%r13 + mov %rcx,%rax + imul %r9,%rax + mov %rdi,%rsi + mov %rcx,%rbp + add %r8,%rax + lea (%rdx,%rax,8),%r12 + lea (%r9,%r14,4),%rax + mov %rax,-offset(%rsp) + mov %rcx,%rax + neg %rax + lea offset(,%rax,8),%rdx + mov %rdx,%rax + mov %rdx,-offset(%rsp) + neg %rdx + mov %rdi,%r10 + mov %rcx,%rdi + mov %rdx,%rcx + lea offset(%r9),%rdx + imul %r9,%rax + imul %rcx,%rdx + sar $something,%r15 + mov %rsi,%r14 + add %rax,%rdx + mov %rdx,-offset(%rsp) + lea offset(%r9),%rdx + imul %rcx,%rdx + and $something,%r14 /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_COOPERLAKE.o (objdump) @@ -2,861 +2,121 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24a00000 0048c1fe 044889bc .H..$....H...H.. - 0020 24900000 00488954 24684889 4c24584c $....H.T$hH.L$XL - 0030 89442438 4c898c24 80000000 4889b424 .D$8L..$....H..$ - 0040 c0010000 4885f60f 8e971600 004c89c3 ....H........L.. - 0050 480fafd9 4889c84d 89c1488d 0c19488d H...H..M..H...H. - 0060 34084889 da488d1c 304c8d04 1848895c 4.H..H..0L...H.\ - 0070 2498498d 1c004c8d 14034d8d 1c024889 $.I...L...M...H. - 0080 5c249049 8d1c0348 8d2c034c 8d640500 \$.I...H.,.L.d.. - 0090 4d8d2c04 4d8d7405 004d8d3c 06498d3c M.,.M.t..M.<.I.< - 00a0 0748897c 2488488b bc249000 000048c1 .H.|$.H..$....H. - 00b0 e00748c1 ff044889 bc248800 0000488b ..H...H..$....H. - 00c0 bc249000 00004889 44246083 e70f4889 .$....H.D$`...H. - 00d0 7c245048 c1e70748 89bc24b8 01000048 |$PH...H..$....H - 00e0 8bbc24c0 01000048 8b842480 00000048 ..$....H..$....H - 00f0 c1e70448 01c74889 bc249800 00004889 ...H..H..$....H. - 0100 c7480faf 4424584c 01c84c8b 4c24684d .H..D$XL..L.L$hM - 0110 8d0cc148 89f848ff c0480faf 4424584c ...H..H..H..D$XL - 0120 898c24b8 0000004c 8b4c2468 48034424 ..$....L.L$hH.D$ - 0130 384d8d0c c14889f8 4883c002 480faf44 8M...H..H...H..D - 0140 24584c89 8c24c800 00004c8b 4c246848 $XL..$....L.L$hH - 0150 03442438 4d8d0cc1 4889f848 83c00348 .D$8M...H..H...H - 0160 0faf4424 584c898c 24d80000 004c8b4c ..D$XL..$....L.L - 0170 24684803 4424384d 8d0cc148 89f84883 $hH.D$8M...H..H. - 0180 c004480f af442458 4c898c24 a8000000 ..H..D$XL..$.... - 0190 4c8b4c24 68480344 24384d8d 0cc14889 L.L$hH.D$8M...H. - 01a0 f84883c0 05480faf 4424584c 898c24f0 .H...H..D$XL..$. - 01b0 00000048 03442438 4c8b4c24 684d8d0c ...H.D$8L.L$hM.. - 01c0 c14889f8 4883c006 480faf44 24584c89 .H..H...H..D$XL. - 01d0 8c240001 00004c8b 4c246848 03442438 .$....L.L$hH.D$8 - 01e0 4d8d0cc1 4889f848 83c00748 0faf4424 M...H..H...H..D$ - 01f0 584c898c 24100100 004c8b4c 24684803 XL..$....L.L$hH. - 0200 4424384d 8d0cc148 89f84883 c008480f D$8M...H..H...H. - 0210 af442458 4c898c24 20010000 4c8b4c24 .D$XL..$ ...L.L$ - 0220 68480344 24384d8d 0cc14889 f84883c0 hH.D$8M...H..H.. - 0230 09480faf 4424584c 898c2430 0100004c .H..D$XL..$0...L - 0240 8b4c2468 48034424 384d8d0c c14889f8 .L$hH.D$8M...H.. - 0250 4883c00a 480faf44 24584c89 8c244001 H...H..D$XL..$@. - 0260 00004c8b 4c246848 03442438 4d8d0cc1 ..L.L$hH.D$8M... - 0270 4889f848 83c00b48 0faf4424 584c898c H..H...H..D$XL.. - 0280 24500100 004c8b4c 24684803 4424384d $P...L.L$hH.D$8M - 0290 8d0cc148 89f84883 c00c480f af442458 ...H..H...H..D$X - 02a0 4c898c24 60010000 4c8b4c24 68480344 L..$`...L.L$hH.D - 02b0 24384d8d 0cc14889 f84883c0 0d480faf $8M...H..H...H.. - 02c0 4424584c 898c2470 01000048 03442438 D$XL..$p...H.D$8 - 02d0 4c8b4c24 684d8d0c c14889f8 4883c00e L.L$hM...H..H... - 02e0 480faf44 24584c89 8c248001 00004c8b H..D$XL..$....L. - 02f0 4c246848 03442438 4d8d0cc1 4889f848 L$hH.D$8M...H..H - 0300 83c00f48 0faf4424 584c898c 24900100 ...H..D$XL..$... - 0310 004c8b4c 24684803 4424384d 8d0cc14c .L.L$hH.D$8M...L - 0320 898c24a0 01000048 89f84c8b 4c246848 ..$....H..L.L$hH - 0330 01d0498d 14c1488d 040f498d 04c14889 ..I...H...I...H. - 0340 8424e000 0000488d 04374889 9424d000 .$....H..7H..$.. - 0350 0000498d 14c1488b 44249848 899424b0 ..I...H.D$.H..$. - 0360 00000048 01f8498d 14c14a8d 04074889 ...H..I...J...H. - 0370 9424c000 0000498d 14c1488b 44249048 .$....I...H.D$.H - 0380 899424e8 00000048 01f8498d 14c14a8d ..$....H..I...J. - 0390 04174889 9424f800 0000498d 14c14a8d ..H..$....I...J. - 03a0 041f4889 94240801 0000498d 14c1488d ..H..$....I...H. - 03b0 041f4889 94241801 0000498d 14c1488d ..H..$....I...H. - 03c0 042f4889 94242801 0000498d 14c14a8d ./H..$(...I...J. - 03d0 04274889 94243801 0000498d 14c14a8d .'H..$8...I...J. - 03e0 042f4889 94244801 0000498d 14c14a8d ./H..$H...I...J. - 03f0 0437488b 4c248848 89942458 01000049 .7H.L$.H..$X...I - 0400 8d14c14a 8d043f48 89942468 01000049 ...J..?H..$h...I - 0410 8d14c148 89f84801 c848034c 24584889 ...H..H..H.L$XH. - 0420 94247801 0000498d 14c14889 c84801f8 .$x...I...H..H.. - 0430 498d0cc1 48898c24 98010000 48899424 I...H..$....H..$ - 0440 88010000 488b9c24 90000000 488b7424 ....H..$....H.t$ - 0450 384889d8 4883e0f0 4801f048 89442448 8H..H...H..H.D$H - 0460 488b8424 88000000 48897c24 d84889c1 H..$....H.|$.H.. - 0470 48c1e004 48c1e10b 4801f048 898424b0 H...H...H..H..$. - 0480 01000048 89d883e0 0e488984 24c80100 ...H.....H..$... - 0490 004889d8 83e00c83 e3084889 8c24a801 .H........H..$.. - 04a0 000048c7 44247800 00000048 c7442470 ..H.D$x....H.D$p - 04b0 00000000 48898424 d0010000 48899c24 ....H..$....H..$ - 04c0 d8010000 c5fb100d 00000000 e9780100 .............x.. - 04d0 000f1f80 00000000 488b4424 70488bbc ........H.D$pH.. - 04e0 24d00000 00488b8c 24c00000 004801c7 $....H..$....H.. - 04f0 48897c24 b8488bbc 24e00000 004801c1 H.|$.H..$....H.. - 0500 4801c748 897c24c0 488bbc24 b0000000 H..H.|$.H..$.... - 0510 48894c24 d04801c7 48897c24 c8488bbc H.L$.H..H.|$.H.. - 0520 24e80000 00488b8c 24f80000 004801c7 $....H..$....H.. - 0530 48897c24 e0488bbc 24080100 004801c1 H.|$.H..$....H.. - 0540 4801c748 894c24e8 48897c24 f0488b8c H..H.L$.H.|$.H.. - 0550 24180100 00488bb4 24280100 00488bbc $....H..$(...H.. - 0560 24380100 00488b9c 24480100 004801c1 $8...H..$H...H.. - 0570 4801c648 01c74801 c348894c 24f84889 H..H..H..H.L$.H. - 0580 34244889 7c240848 895c2410 488b8c24 4$H.|$.H.\$.H..$ - 0590 58010000 488bb424 68010000 488bbc24 X...H..$h...H..$ - 05a0 78010000 488b9c24 88010000 4801c148 x...H..$....H..H - 05b0 01c64801 c74801c3 48038424 98010000 ..H..H..H..$.... - 05c0 48894c24 18488974 24204889 7c242848 H.L$.H.t$ H.|$(H - 05d0 895c2430 48894424 404883bc 24880000 .\$0H.D$@H..$... - 05e0 0000488b 4424380f 8f810100 0048837c ..H.D$8......H.| - 05f0 24500074 2b483944 24d80f8c 06280000 $P.t+H9D$....(.. - 0600 0f8eea19 0000488b 8424b801 00004801 ......H..$....H. - 0610 84241802 0000662e 0f1f8400 00000000 .$....f......... - 0620 48834424 d810488b 74246048 836c2470 H.D$..H.t$`H.l$p - 0630 80480174 2478488b 4424d848 3b842498 .H.t$xH.D$.H;.$. - 0640 0000000f 847c1000 00488b74 24384839 .....|...H.t$8H9 - 0650 7424d80f 8d7ffeff ff488b44 2478488b t$.......H.D$xH. - 0660 9c24b800 0000488b bc24c800 0000488b .$....H..$....H. - 0670 b424d800 00004801 c34801c7 4801c648 .$....H..H..H..H - 0680 895c24b8 48897c24 c0488974 24c8488b .\$.H.|$.H.t$.H. - 0690 9c24a800 0000488b 8c24f000 0000488b .$....H..$....H. - 06a0 b4240001 0000488b bc241001 00004801 .$....H..$....H. - 06b0 c34801c1 4801c648 01c74889 5c24d048 .H..H..H..H.\$.H - 06c0 894c24e0 48897424 e848897c 24f0488b .L$.H.t$.H.|$.H. - 06d0 9c242001 0000488b 8c243001 0000488b .$ ...H..$0...H. - 06e0 b4244001 0000488b bc245001 00004801 .$@...H..$P...H. - 06f0 c34801c1 4801c648 01c74889 5c24f848 .H..H..H..H.\$.H - 0700 890c2448 89742408 48897c24 10488b9c ..$H.t$.H.|$.H.. - 0710 24600100 00488b8c 24700100 00488bb4 $`...H..$p...H.. - 0720 24800100 00488bbc 24900100 004801c3 $....H..$....H.. - 0730 4801c148 01c64801 c7480384 24a00100 H..H..H..H..$... - 0740 0048895c 24184889 4c242048 89742428 .H.\$.H.L$ H.t$( - 0750 48897c24 30488944 24404883 bc248800 H.|$0H.D$@H..$.. - 0760 00000048 8b442438 0f8e7ffe ffff488b ...H.D$8......H. - 0770 84241802 0000488d 90000800 00488b44 .$....H......H.D - 0780 24384889 4424b0eb 780f1f80 00000000 $8H.D$..x....... - 0790 488b4424 60480144 24b84801 4424c048 H.D$`H.D$.H.D$.H - 07a0 014424c8 48014424 d0480144 24e04801 .D$.H.D$.H.D$.H. - 07b0 4424e848 014424f0 48014424 f8480104 D$.H.D$.H.D$.H.. - 07c0 24480144 24084801 44241048 01442418 $H.D$.H.D$.H.D$. - 07d0 48014424 20480144 24284801 44243048 H.D$ H.D$(H.D$0H - 07e0 01442440 48834424 b0104881 c2000800 .D$@H.D$..H..... - 07f0 00488b44 24b0483b 4424480f 84a70e00 .H.D$.H;D$H..... - 0800 00488b4c 24b0488d 8200f8ff ff48394c .H.L$.H......H9L - 0810 24d80f8c a80c0000 0f8f72ff ffff48c7 $.........r...H. - 0820 8208f8ff ff000000 0048c782 10f8ffff .........H...... - 0830 00000000 48c78218 f8ffff00 00000048 ....H..........H - 0840 c78220f8 ffff0000 000048c7 8228f8ff .. .......H..(.. - 0850 ff000000 0048c782 30f8ffff 00000000 .....H..0....... - 0860 48c78238 f8ffff00 00000048 c78240f8 H..8.......H..@. - 0870 ffff0000 000048c7 8248f8ff ff000000 ......H..H...... - 0880 0048c782 50f8ffff 00000000 48c78258 .H..P.......H..X - 0890 f8ffff00 00000048 c78260f8 ffff0000 .......H..`..... - 08a0 000048c7 8268f8ff ff000000 0048c782 ..H..h.......H.. - 08b0 70f8ffff 00000000 48c78278 f8ffff00 p.......H..x.... - 08c0 00000048 8b4424b8 c5fb118a 00f8ffff ...H.D$......... - 08d0 c5fb1040 0848c782 90f8ffff 00000000 ...@.H.......... - 08e0 c5fb1182 80f8ffff 48c78298 f8ffff00 ........H....... - 08f0 00000048 c782a0f8 ffff0000 000048c7 ...H..........H. - 0900 82a8f8ff ff000000 0048c782 b0f8ffff .........H...... - 0910 00000000 48c782b8 f8ffff00 00000048 ....H..........H - 0920 c782c0f8 ffff0000 000048c7 82c8f8ff ..........H..... - 0930 ff000000 0048c782 d0f8ffff 00000000 .....H.......... - 0940 48c782d8 f8ffff00 00000048 c782e0f8 H..........H.... - 0950 ffff0000 000048c7 82e8f8ff ff000000 ......H......... - 0960 00c5fb11 8a88f8ff ff48c782 f0f8ffff .........H...... - 0970 00000000 48c782f8 f8ffff00 00000048 ....H..........H - 0980 8b5c24c0 488b7424 c8c5fb10 40104883 .\$.H.t$....@.H. - 0990 eb80c5fb 118200f9 ffffc5fb 10439048 .............C.H - 09a0 c78218f9 ffff0000 000048c7 8220f9ff ..........H.. .. - 09b0 ff000000 0048c782 28f9ffff 00000000 .....H..(....... - 09c0 48c78230 f9ffff00 00000048 c78238f9 H..0.......H..8. - 09d0 ffff0000 000048c7 8240f9ff ff000000 ......H..@...... - 09e0 0048c782 48f9ffff 00000000 48c78250 .H..H.......H..P - 09f0 f9ffff00 00000048 c78258f9 ffff0000 .......H..X..... - 0a00 000048c7 8260f9ff ff000000 0048c782 ..H..`.......H.. - 0a10 68f9ffff 00000000 48c78270 f9ffff00 h.......H..p.... - 0a20 00000048 c78278f9 ffff0000 0000c5fb ...H..x......... - 0a30 118208f9 ffffc5fb 118a10f9 ffffc5fb ................ - 0a40 10401848 83ee80c5 fb118280 f9ffffc5 .@.H............ - 0a50 fb104398 c5fb1182 88f9ffff c5fb1046 ..C............F - 0a60 9848c782 a0f9ffff 00000000 c5fb1182 .H.............. - 0a70 90f9ffff 48c782a8 f9ffff00 00000048 ....H..........H - 0a80 c782b0f9 ffff0000 000048c7 82b8f9ff ..........H..... - 0a90 ff000000 00c5fb11 8a98f9ff ff48c782 .............H.. - 0aa0 c0f9ffff 00000000 48c782c8 f9ffff00 ........H....... - 0ab0 00000048 c782d0f9 ffff0000 000048c7 ...H..........H. - 0ac0 82d8f9ff ff000000 0048c782 e0f9ffff .........H...... - 0ad0 00000000 48c782e8 f9ffff00 00000048 ....H..........H - 0ae0 c782f0f9 ffff0000 000048c7 82f8f9ff ..........H..... - 0af0 ff000000 00488b7c 24d0c5fb 10402048 .....H.|$....@ H - 0b00 83ef80c5 fb118200 faffffc5 fb1043a0 ..............C. - 0b10 c5fb1182 08faffff c5fb1046 a0c5fb11 ...........F.... - 0b20 8210faff ffc5fb10 47a048c7 8228faff ........G.H..(.. - 0b30 ff000000 0048c782 30faffff 00000000 .....H..0....... - 0b40 48c78238 faffff00 00000048 c78240fa H..8.......H..@. - 0b50 ffff0000 000048c7 8248faff ff000000 ......H..H...... - 0b60 0048c782 50faffff 00000000 48c78258 .H..P.......H..X - 0b70 faffff00 00000048 c78260fa ffff0000 .......H..`..... - 0b80 000048c7 8268faff ff000000 0048c782 ..H..h.......H.. - 0b90 70faffff 00000000 48c78278 faffff00 p.......H..x.... - 0ba0 000000c5 fb118218 faffffc5 fb118a20 ............... - 0bb0 faffffc5 fb104028 c5fb1182 80faffff ......@(........ - 0bc0 c5fb1043 a8c5fb11 8288faff ffc5fb10 ...C............ - 0bd0 46a8488b 4c24e0c5 fb118290 faffffc5 F.H.L$.......... - 0be0 fb1047a8 4c8b7424 e8c5fb11 8298faff ..G.L.t$........ - 0bf0 ffc5fb10 412848c7 82b0faff ff000000 ....A(H......... - 0c00 0048c782 b8faffff 00000000 48c782c0 .H..........H... - 0c10 faffff00 00000048 c782c8fa ffff0000 .......H........ /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 98350000 00420e10 8f02420e .....5...B....B. + 0020 00000000 55070000 00420e10 8f02420e ....U....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 c91f0a0e ..A.8..G........ - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e084a 0b000000 D..J.... + 0040 8606410e 38830744 0e48039a 050a0e38 ..A.8..D.H.....8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08440b 00000000 ..D..... /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_SKYLAKEX.o (disasm) @@ -12,1350 +12,339 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) - mov %r9,offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,(%rsp) + mov offset(%rsp),%rbx test %rsi,%rsi jle - mov %r8,%rbx - imul %rcx,%rbx mov %rcx,%rax - mov %r8,%r9 - lea (%rcx,%rbx,1),%rcx - lea (%rax,%rcx,1),%rsi - mov %rbx,%rdx - lea (%rax,%rsi,1),%rbx - lea (%rax,%rbx,1),%r8 - mov %rbx,-offset(%rsp) - lea (%r8,%rax,1),%rbx - lea (%rbx,%rax,1),%r10 - lea (%r10,%rax,1),%r11 - mov %rbx,-offset(%rsp) - lea (%r11,%rax,1),%rbx - lea (%rbx,%rax,1),%rbp - lea offset(%rbp,%rax,1),%r12 - lea (%r12,%rax,1),%r13 - lea offset(%r13,%rax,1),%r14 - lea (%r14,%rax,1),%r15 - lea (%r15,%rax,1),%rdi - mov %rdi,-offset(%rsp) - mov offset(%rsp),%rdi - shl $something,%rax - sar $something,%rdi - mov %rdi,offset(%rsp) - mov offset(%rsp),%rdi - mov %rax,offset(%rsp) - and $something,%edi - mov %rdi,offset(%rsp) - shl $something,%rdi - mov %rdi,offset(%rsp) - mov offset(%rsp),%rdi - mov offset(%rsp),%rax - shl $something,%rdi - add %rax,%rdi - mov %rdi,offset(%rsp) - mov %rax,%rdi - imul offset(%rsp),%rax + imul %r8,%rax + mov %rsi,%r14 + mov %rdi,%r15 add %r9,%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - inc %rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,8),%r9 + lea (%rdx,%rax,8),%r13 + mov %rcx,%rax + imul %r9,%rax + mov %rdi,%rsi + mov %rcx,%rbp + add %r8,%rax + lea (%rdx,%rax,8),%r12 + lea (%r9,%r14,4),%rax + mov %rax,-offset(%rsp) + mov %rcx,%rax + neg %rax + lea offset(,%rax,8),%rdx + mov %rdx,%rax + mov %rdx,-offset(%rsp) + neg %rdx + mov %rdi,%r10 + mov %rcx,%rdi + mov %rdx,%rcx + lea offset(%r9),%rdx + imul %r9,%rax + imul %rcx,%rdx + sar $something,%r15 + mov %rsi,%r14 + add %rax,%rdx + mov %rdx,-offset(%rsp) + lea offset(%r9),%rdx + imul %rcx,%rdx + and $something,%r14 /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_SKYLAKEX.o (objdump) @@ -2,861 +2,121 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24a00000 0048c1fe 044889bc .H..$....H...H.. - 0020 24900000 00488954 24684889 4c24584c $....H.T$hH.L$XL - 0030 89442438 4c898c24 80000000 4889b424 .D$8L..$....H..$ - 0040 c0010000 4885f60f 8e971600 004c89c3 ....H........L.. - 0050 480fafd9 4889c84d 89c1488d 0c19488d H...H..M..H...H. - 0060 34084889 da488d1c 304c8d04 1848895c 4.H..H..0L...H.\ - 0070 2498498d 1c004c8d 14034d8d 1c024889 $.I...L...M...H. - 0080 5c249049 8d1c0348 8d2c034c 8d640500 \$.I...H.,.L.d.. - 0090 4d8d2c04 4d8d7405 004d8d3c 06498d3c M.,.M.t..M.<.I.< - 00a0 0748897c 2488488b bc249000 000048c1 .H.|$.H..$....H. - 00b0 e00748c1 ff044889 bc248800 0000488b ..H...H..$....H. - 00c0 bc249000 00004889 44246083 e70f4889 .$....H.D$`...H. - 00d0 7c245048 c1e70748 89bc24b8 01000048 |$PH...H..$....H - 00e0 8bbc24c0 01000048 8b842480 00000048 ..$....H..$....H - 00f0 c1e70448 01c74889 bc249800 00004889 ...H..H..$....H. - 0100 c7480faf 4424584c 01c84c8b 4c24684d .H..D$XL..L.L$hM - 0110 8d0cc148 89f848ff c0480faf 4424584c ...H..H..H..D$XL - 0120 898c24b8 0000004c 8b4c2468 48034424 ..$....L.L$hH.D$ - 0130 384d8d0c c14889f8 4883c002 480faf44 8M...H..H...H..D - 0140 24584c89 8c24c800 00004c8b 4c246848 $XL..$....L.L$hH - 0150 03442438 4d8d0cc1 4889f848 83c00348 .D$8M...H..H...H - 0160 0faf4424 584c898c 24d80000 004c8b4c ..D$XL..$....L.L - 0170 24684803 4424384d 8d0cc148 89f84883 $hH.D$8M...H..H. - 0180 c004480f af442458 4c898c24 a8000000 ..H..D$XL..$.... - 0190 4c8b4c24 68480344 24384d8d 0cc14889 L.L$hH.D$8M...H. - 01a0 f84883c0 05480faf 4424584c 898c24f0 .H...H..D$XL..$. - 01b0 00000048 03442438 4c8b4c24 684d8d0c ...H.D$8L.L$hM.. - 01c0 c14889f8 4883c006 480faf44 24584c89 .H..H...H..D$XL. - 01d0 8c240001 00004c8b 4c246848 03442438 .$....L.L$hH.D$8 - 01e0 4d8d0cc1 4889f848 83c00748 0faf4424 M...H..H...H..D$ - 01f0 584c898c 24100100 004c8b4c 24684803 XL..$....L.L$hH. - 0200 4424384d 8d0cc148 89f84883 c008480f D$8M...H..H...H. - 0210 af442458 4c898c24 20010000 4c8b4c24 .D$XL..$ ...L.L$ - 0220 68480344 24384d8d 0cc14889 f84883c0 hH.D$8M...H..H.. - 0230 09480faf 4424584c 898c2430 0100004c .H..D$XL..$0...L - 0240 8b4c2468 48034424 384d8d0c c14889f8 .L$hH.D$8M...H.. - 0250 4883c00a 480faf44 24584c89 8c244001 H...H..D$XL..$@. - 0260 00004c8b 4c246848 03442438 4d8d0cc1 ..L.L$hH.D$8M... - 0270 4889f848 83c00b48 0faf4424 584c898c H..H...H..D$XL.. - 0280 24500100 004c8b4c 24684803 4424384d $P...L.L$hH.D$8M - 0290 8d0cc148 89f84883 c00c480f af442458 ...H..H...H..D$X - 02a0 4c898c24 60010000 4c8b4c24 68480344 L..$`...L.L$hH.D - 02b0 24384d8d 0cc14889 f84883c0 0d480faf $8M...H..H...H.. - 02c0 4424584c 898c2470 01000048 03442438 D$XL..$p...H.D$8 - 02d0 4c8b4c24 684d8d0c c14889f8 4883c00e L.L$hM...H..H... - 02e0 480faf44 24584c89 8c248001 00004c8b H..D$XL..$....L. - 02f0 4c246848 03442438 4d8d0cc1 4889f848 L$hH.D$8M...H..H - 0300 83c00f48 0faf4424 584c898c 24900100 ...H..D$XL..$... - 0310 004c8b4c 24684803 4424384d 8d0cc14c .L.L$hH.D$8M...L - 0320 898c24a0 01000048 89f84c8b 4c246848 ..$....H..L.L$hH - 0330 01d0498d 14c1488d 040f498d 04c14889 ..I...H...I...H. - 0340 8424e000 0000488d 04374889 9424d000 .$....H..7H..$.. - 0350 0000498d 14c1488b 44249848 899424b0 ..I...H.D$.H..$. - 0360 00000048 01f8498d 14c14a8d 04074889 ...H..I...J...H. - 0370 9424c000 0000498d 14c1488b 44249048 .$....I...H.D$.H - 0380 899424e8 00000048 01f8498d 14c14a8d ..$....H..I...J. - 0390 04174889 9424f800 0000498d 14c14a8d ..H..$....I...J. - 03a0 041f4889 94240801 0000498d 14c1488d ..H..$....I...H. - 03b0 041f4889 94241801 0000498d 14c1488d ..H..$....I...H. - 03c0 042f4889 94242801 0000498d 14c14a8d ./H..$(...I...J. - 03d0 04274889 94243801 0000498d 14c14a8d .'H..$8...I...J. - 03e0 042f4889 94244801 0000498d 14c14a8d ./H..$H...I...J. - 03f0 0437488b 4c248848 89942458 01000049 .7H.L$.H..$X...I - 0400 8d14c14a 8d043f48 89942468 01000049 ...J..?H..$h...I - 0410 8d14c148 89f84801 c848034c 24584889 ...H..H..H.L$XH. - 0420 94247801 0000498d 14c14889 c84801f8 .$x...I...H..H.. - 0430 498d0cc1 48898c24 98010000 48899424 I...H..$....H..$ - 0440 88010000 488b9c24 90000000 488b7424 ....H..$....H.t$ - 0450 384889d8 4883e0f0 4801f048 89442448 8H..H...H..H.D$H - 0460 488b8424 88000000 48897c24 d84889c1 H..$....H.|$.H.. - 0470 48c1e004 48c1e10b 4801f048 898424b0 H...H...H..H..$. - 0480 01000048 89d883e0 0e488984 24c80100 ...H.....H..$... - 0490 004889d8 83e00c83 e3084889 8c24a801 .H........H..$.. - 04a0 000048c7 44247800 00000048 c7442470 ..H.D$x....H.D$p - 04b0 00000000 48898424 d0010000 48899c24 ....H..$....H..$ - 04c0 d8010000 c5fb100d 00000000 e9780100 .............x.. - 04d0 000f1f80 00000000 488b4424 70488bbc ........H.D$pH.. - 04e0 24d00000 00488b8c 24c00000 004801c7 $....H..$....H.. - 04f0 48897c24 b8488bbc 24e00000 004801c1 H.|$.H..$....H.. - 0500 4801c748 897c24c0 488bbc24 b0000000 H..H.|$.H..$.... - 0510 48894c24 d04801c7 48897c24 c8488bbc H.L$.H..H.|$.H.. - 0520 24e80000 00488b8c 24f80000 004801c7 $....H..$....H.. - 0530 48897c24 e0488bbc 24080100 004801c1 H.|$.H..$....H.. - 0540 4801c748 894c24e8 48897c24 f0488b8c H..H.L$.H.|$.H.. - 0550 24180100 00488bb4 24280100 00488bbc $....H..$(...H.. - 0560 24380100 00488b9c 24480100 004801c1 $8...H..$H...H.. - 0570 4801c648 01c74801 c348894c 24f84889 H..H..H..H.L$.H. - 0580 34244889 7c240848 895c2410 488b8c24 4$H.|$.H.\$.H..$ - 0590 58010000 488bb424 68010000 488bbc24 X...H..$h...H..$ - 05a0 78010000 488b9c24 88010000 4801c148 x...H..$....H..H - 05b0 01c64801 c74801c3 48038424 98010000 ..H..H..H..$.... - 05c0 48894c24 18488974 24204889 7c242848 H.L$.H.t$ H.|$(H - 05d0 895c2430 48894424 404883bc 24880000 .\$0H.D$@H..$... - 05e0 0000488b 4424380f 8f810100 0048837c ..H.D$8......H.| - 05f0 24500074 2b483944 24d80f8c 06280000 $P.t+H9D$....(.. - 0600 0f8eea19 0000488b 8424b801 00004801 ......H..$....H. - 0610 84241802 0000662e 0f1f8400 00000000 .$....f......... - 0620 48834424 d810488b 74246048 836c2470 H.D$..H.t$`H.l$p - 0630 80480174 2478488b 4424d848 3b842498 .H.t$xH.D$.H;.$. - 0640 0000000f 847c1000 00488b74 24384839 .....|...H.t$8H9 - 0650 7424d80f 8d7ffeff ff488b44 2478488b t$.......H.D$xH. - 0660 9c24b800 0000488b bc24c800 0000488b .$....H..$....H. - 0670 b424d800 00004801 c34801c7 4801c648 .$....H..H..H..H - 0680 895c24b8 48897c24 c0488974 24c8488b .\$.H.|$.H.t$.H. - 0690 9c24a800 0000488b 8c24f000 0000488b .$....H..$....H. - 06a0 b4240001 0000488b bc241001 00004801 .$....H..$....H. - 06b0 c34801c1 4801c648 01c74889 5c24d048 .H..H..H..H.\$.H - 06c0 894c24e0 48897424 e848897c 24f0488b .L$.H.t$.H.|$.H. - 06d0 9c242001 0000488b 8c243001 0000488b .$ ...H..$0...H. - 06e0 b4244001 0000488b bc245001 00004801 .$@...H..$P...H. - 06f0 c34801c1 4801c648 01c74889 5c24f848 .H..H..H..H.\$.H - 0700 890c2448 89742408 48897c24 10488b9c ..$H.t$.H.|$.H.. - 0710 24600100 00488b8c 24700100 00488bb4 $`...H..$p...H.. - 0720 24800100 00488bbc 24900100 004801c3 $....H..$....H.. - 0730 4801c148 01c64801 c7480384 24a00100 H..H..H..H..$... - 0740 0048895c 24184889 4c242048 89742428 .H.\$.H.L$ H.t$( - 0750 48897c24 30488944 24404883 bc248800 H.|$0H.D$@H..$.. - 0760 00000048 8b442438 0f8e7ffe ffff488b ...H.D$8......H. - 0770 84241802 0000488d 90000800 00488b44 .$....H......H.D - 0780 24384889 4424b0eb 780f1f80 00000000 $8H.D$..x....... - 0790 488b4424 60480144 24b84801 4424c048 H.D$`H.D$.H.D$.H - 07a0 014424c8 48014424 d0480144 24e04801 .D$.H.D$.H.D$.H. - 07b0 4424e848 014424f0 48014424 f8480104 D$.H.D$.H.D$.H.. - 07c0 24480144 24084801 44241048 01442418 $H.D$.H.D$.H.D$. - 07d0 48014424 20480144 24284801 44243048 H.D$ H.D$(H.D$0H - 07e0 01442440 48834424 b0104881 c2000800 .D$@H.D$..H..... - 07f0 00488b44 24b0483b 4424480f 84a70e00 .H.D$.H;D$H..... - 0800 00488b4c 24b0488d 8200f8ff ff48394c .H.L$.H......H9L - 0810 24d80f8c a80c0000 0f8f72ff ffff48c7 $.........r...H. - 0820 8208f8ff ff000000 0048c782 10f8ffff .........H...... - 0830 00000000 48c78218 f8ffff00 00000048 ....H..........H - 0840 c78220f8 ffff0000 000048c7 8228f8ff .. .......H..(.. - 0850 ff000000 0048c782 30f8ffff 00000000 .....H..0....... - 0860 48c78238 f8ffff00 00000048 c78240f8 H..8.......H..@. - 0870 ffff0000 000048c7 8248f8ff ff000000 ......H..H...... - 0880 0048c782 50f8ffff 00000000 48c78258 .H..P.......H..X - 0890 f8ffff00 00000048 c78260f8 ffff0000 .......H..`..... - 08a0 000048c7 8268f8ff ff000000 0048c782 ..H..h.......H.. - 08b0 70f8ffff 00000000 48c78278 f8ffff00 p.......H..x.... - 08c0 00000048 8b4424b8 c5fb118a 00f8ffff ...H.D$......... - 08d0 c5fb1040 0848c782 90f8ffff 00000000 ...@.H.......... - 08e0 c5fb1182 80f8ffff 48c78298 f8ffff00 ........H....... - 08f0 00000048 c782a0f8 ffff0000 000048c7 ...H..........H. - 0900 82a8f8ff ff000000 0048c782 b0f8ffff .........H...... - 0910 00000000 48c782b8 f8ffff00 00000048 ....H..........H - 0920 c782c0f8 ffff0000 000048c7 82c8f8ff ..........H..... - 0930 ff000000 0048c782 d0f8ffff 00000000 .....H.......... - 0940 48c782d8 f8ffff00 00000048 c782e0f8 H..........H.... - 0950 ffff0000 000048c7 82e8f8ff ff000000 ......H......... - 0960 00c5fb11 8a88f8ff ff48c782 f0f8ffff .........H...... - 0970 00000000 48c782f8 f8ffff00 00000048 ....H..........H - 0980 8b5c24c0 488b7424 c8c5fb10 40104883 .\$.H.t$....@.H. - 0990 eb80c5fb 118200f9 ffffc5fb 10439048 .............C.H - 09a0 c78218f9 ffff0000 000048c7 8220f9ff ..........H.. .. - 09b0 ff000000 0048c782 28f9ffff 00000000 .....H..(....... - 09c0 48c78230 f9ffff00 00000048 c78238f9 H..0.......H..8. - 09d0 ffff0000 000048c7 8240f9ff ff000000 ......H..@...... - 09e0 0048c782 48f9ffff 00000000 48c78250 .H..H.......H..P - 09f0 f9ffff00 00000048 c78258f9 ffff0000 .......H..X..... - 0a00 000048c7 8260f9ff ff000000 0048c782 ..H..`.......H.. - 0a10 68f9ffff 00000000 48c78270 f9ffff00 h.......H..p.... - 0a20 00000048 c78278f9 ffff0000 0000c5fb ...H..x......... - 0a30 118208f9 ffffc5fb 118a10f9 ffffc5fb ................ - 0a40 10401848 83ee80c5 fb118280 f9ffffc5 .@.H............ - 0a50 fb104398 c5fb1182 88f9ffff c5fb1046 ..C............F - 0a60 9848c782 a0f9ffff 00000000 c5fb1182 .H.............. - 0a70 90f9ffff 48c782a8 f9ffff00 00000048 ....H..........H - 0a80 c782b0f9 ffff0000 000048c7 82b8f9ff ..........H..... - 0a90 ff000000 00c5fb11 8a98f9ff ff48c782 .............H.. - 0aa0 c0f9ffff 00000000 48c782c8 f9ffff00 ........H....... - 0ab0 00000048 c782d0f9 ffff0000 000048c7 ...H..........H. - 0ac0 82d8f9ff ff000000 0048c782 e0f9ffff .........H...... - 0ad0 00000000 48c782e8 f9ffff00 00000048 ....H..........H - 0ae0 c782f0f9 ffff0000 000048c7 82f8f9ff ..........H..... - 0af0 ff000000 00488b7c 24d0c5fb 10402048 .....H.|$....@ H - 0b00 83ef80c5 fb118200 faffffc5 fb1043a0 ..............C. - 0b10 c5fb1182 08faffff c5fb1046 a0c5fb11 ...........F.... - 0b20 8210faff ffc5fb10 47a048c7 8228faff ........G.H..(.. - 0b30 ff000000 0048c782 30faffff 00000000 .....H..0....... - 0b40 48c78238 faffff00 00000048 c78240fa H..8.......H..@. - 0b50 ffff0000 000048c7 8248faff ff000000 ......H..H...... - 0b60 0048c782 50faffff 00000000 48c78258 .H..P.......H..X - 0b70 faffff00 00000048 c78260fa ffff0000 .......H..`..... - 0b80 000048c7 8268faff ff000000 0048c782 ..H..h.......H.. - 0b90 70faffff 00000000 48c78278 faffff00 p.......H..x.... - 0ba0 000000c5 fb118218 faffffc5 fb118a20 ............... - 0bb0 faffffc5 fb104028 c5fb1182 80faffff ......@(........ - 0bc0 c5fb1043 a8c5fb11 8288faff ffc5fb10 ...C............ - 0bd0 46a8488b 4c24e0c5 fb118290 faffffc5 F.H.L$.......... - 0be0 fb1047a8 4c8b7424 e8c5fb11 8298faff ..G.L.t$........ - 0bf0 ffc5fb10 412848c7 82b0faff ff000000 ....A(H......... - 0c00 0048c782 b8faffff 00000000 48c782c0 .H..........H... - 0c10 faffff00 00000048 c782c8fa ffff0000 .......H........ /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ilnucopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 98350000 00420e10 8f02420e .....5...B....B. + 0020 00000000 55070000 00420e10 8f02420e ....U....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 c91f0a0e ..A.8..G........ - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e084a 0b000000 D..J.... + 0040 8606410e 38830744 0e48039a 050a0e38 ..A.8..D.H.....8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08440b 00000000 ..D..... /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_COOPERLAKE.o (disasm) @@ -12,1733 +12,320 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) + mov %rdi,-offset(%rsp) mov %rdx,-offset(%rsp) - mov %rcx,(%rsp) - mov %r8,-offset(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov %rcx,-offset(%rsp) + mov %rsi,(%rsp) + mov offset(%rsp),%rbx test %rsi,%rsi jle - mov %r8,%rbx - imul %rcx,%rbx - mov %r8,%rdi mov %rcx,%rax - lea (%rcx,%rbx,1),%r11 - lea (%r11,%rcx,1),%r10 - lea (%rcx,%r10,1),%r9 - lea (%r9,%rcx,1),%r8 - lea (%rcx,%r8,1),%rsi - mov %rsi,-offset(%rsp) - add %rcx,%rsi - lea (%rcx,%rsi,1),%rcx - lea (%rax,%rcx,1),%rdx - lea (%rax,%rdx,1),%rbp - lea (%rax,%rbp,1),%r12 - lea (%rax,%r12,1),%r13 - lea (%rax,%r13,1),%r14 - mov %rcx,-offset(%rsp) - lea (%rax,%r14,1),%rcx - mov %rcx,-offset(%rsp) - mov -offset(%rsp),%rcx - add %rax,%rcx - mov %rcx,-offset(%rsp) - mov offset(%rsp),%rcx - sar $something,%rcx - mov %rcx,offset(%rsp) - lea offset(,%rax,8),%rcx - mov %rcx,offset(%rsp) - mov %rax,%rcx - mov offset(%rsp),%rax - shl $something,%rcx - and $something,%eax + imul %r8,%rax + mov %rsi,%r14 + mov %rdi,%r10 + add %r9,%rax + lea (%rdx,%rax,8),%r13 + mov %rcx,%rax + imul %r9,%rax + mov %rcx,%rdi + mov %rcx,%rbp + add %r8,%rax + lea (%rdx,%rax,8),%r12 + lea (%r9,%r14,4),%rax mov %rax,-offset(%rsp) - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - mov %rcx,-offset(%rsp) - mov -offset(%rsp),%rcx - shl $something,%rax - add %rcx,%rax - mov %rax,offset(%rsp) - mov (%rsp),%rax - imul %rcx,%rax - add %rdi,%rax - mov -offset(%rsp),%rdi - lea (%rdi,%rax,8),%rdi mov %rcx,%rax - mov (%rsp),%rcx - inc %rax - imul %rcx,%rax - mov %rdi,offset(%rsp) - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - add -offset(%rsp),%rax - mov -offset(%rsp),%rdi - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - add -offset(%rsp),%rax - mov -offset(%rsp),%rdi - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rcx - add -offset(%rsp),%rax - lea (%rcx,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add %rax,%r10 - lea (%rcx,%r10,8),%r10 - add %rax,%r9 - mov -offset(%rsp),%rdi - add %rax,%rbx - add %rax,%r11 - add %rax,%r8 - mov %r10,offset(%rsp) - lea (%rcx,%r9,8),%r10 - add %rax,%rdi - add %rax,%rsi - lea (%rcx,%rbx,8),%rbx /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_COOPERLAKE.o (objdump) @@ -2,743 +2,111 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ec700100 AWAVAUATUSH..p.. - 0010 00488974 242048c1 fe044889 7c241048 .H.t$ H...H.|$.H - 0020 895424e0 48890c24 4c894424 a84c894c .T$.H..$L.D$.L.L - 0030 24c84889 b4245001 00004c8b bc24a801 $.H..$P...L..$.. - 0040 00004885 f60f8e9e 1e00004c 89c3480f ..H........L..H. - 0050 afd94c89 c74889c8 4c8d1c19 4d8d140b ..L..H..L...M... - 0060 4e8d0c11 4d8d0409 4a8d3401 48897424 N...M...J.4.H.t$ - 0070 904801ce 488d0c31 488d1408 488d2c10 .H..H..1H...H.,. - 0080 4c8d2428 4e8d2c20 4e8d3428 48894c24 L.$(N., N.4(H.L$ - 0090 a04a8d0c 3048894c 2488488b 4c248848 .J..0H.L$.H.L$.H - 00a0 01c14889 4c249848 8b4c2410 48c1f904 ..H.L$.H.L$.H... - 00b0 48894c24 08488d0c c5000000 0048898c H.L$.H.......H.. - 00c0 24300100 004889c1 488b4424 1048c1e1 $0...H..H.D$.H.. - 00d0 0783e00f 48894424 d848c1e0 07488984 ....H.D$.H...H.. - 00e0 24480100 00488b84 24500100 0048894c $H...H..$P...H.L - 00f0 24f8488b 4c24c848 c1e00448 01c84889 $.H.L$.H...H..H. - 0100 44241848 8b042448 0fafc148 01f8488b D$.H..$H...H..H. - 0110 7c24e048 8d3cc748 89c8488b 0c2448ff |$.H.<.H..H..$H. - 0120 c0480faf c148897c 2438488b 7c24e048 .H...H.|$8H.|$.H - 0130 034424a8 488d3cc7 488b4424 c848897c .D$.H.<.H.D$.H.| - 0140 24484883 c002480f afc1488b 7c24e048 $HH...H...H.|$.H - 0150 034424a8 488d3cc7 488b4424 c848897c .D$.H.<.H.D$.H.| - 0160 24584883 c003480f afc1488b 7c24e048 $XH...H...H.|$.H - 0170 034424a8 488d3cc7 488b4424 c848897c .D$.H.<.H.D$.H.| - 0180 24684883 c004480f afc14803 4424a848 $hH...H...H.D$.H - 0190 8b7c24e0 488d3cc7 488b4424 c848897c .|$.H.<.H.D$.H.| - 01a0 24784883 c005480f afc1488b 7c24e048 $xH...H...H.|$.H - 01b0 034424a8 488d3cc7 488b4424 c84889bc .D$.H.<.H.D$.H.. - 01c0 24880000 004883c0 06480faf c1488b7c $....H...H...H.| - 01d0 24e04803 4424a848 8d3cc748 8b4424c8 $.H.D$.H.<.H.D$. - 01e0 4889bc24 98000000 4883c007 480fafc1 H..$....H...H... - 01f0 488b7c24 e0480344 24a8488d 3cc7488b H.|$.H.D$.H.<.H. - 0200 4424c848 89bc24a8 00000048 83c00848 D$.H..$....H...H - 0210 0fafc148 8b7c24e0 48034424 a8488d3c ...H.|$.H.D$.H.< - 0220 c7488b44 24c84889 bc24b800 00004883 .H.D$.H..$....H. - 0230 c009480f afc1488b 7c24e048 034424a8 ..H...H.|$.H.D$. - 0240 488d3cc7 488b4424 c84889bc 24c80000 H.<.H.D$.H..$... - 0250 004883c0 0a480faf c1488b7c 24e04803 .H...H...H.|$.H. - 0260 4424a848 8d3cc748 8b4424c8 4889bc24 D$.H.<.H.D$.H..$ - 0270 d8000000 4883c00b 480fafc1 488b7c24 ....H...H...H.|$ - 0280 e0480344 24a8488d 3cc7488b 4424c848 .H.D$.H.<.H.D$.H - 0290 89bc24e8 00000048 83c00c48 0fafc148 ..$....H...H...H - 02a0 034424a8 488b7c24 e0488d3c c7488b44 .D$.H.|$.H.<.H.D - 02b0 24c84889 bc24f800 00004883 c00d480f $.H..$....H...H. - 02c0 afc1488b 7c24e048 034424a8 488d3cc7 ..H.|$.H.D$.H.<. - 02d0 488b4424 c84889bc 24080100 004883c0 H.D$.H..$....H.. - 02e0 0e480faf c1488b7c 24e04803 4424a848 .H...H.|$.H.D$.H - 02f0 8d3cc748 8b4424c8 4889bc24 18010000 .<.H.D$.H..$.... - 0300 4883c00f 480fafc1 488b4c24 e0480344 H...H...H.L$.H.D - 0310 24a8488d 3cc1488b 4424c848 89bc2428 $.H.<.H.D$.H..$( - 0320 01000049 01c24e8d 14d14901 c1488b7c ...I..N...I..H.| - 0330 24904801 c34901c3 4901c04c 89542450 $.H..I..I..L.T$P - 0340 4e8d14c9 4801c748 01c6488d 1cd94e8d N...H..H..H...N. - 0350 1cd94c89 5424604e 8d14c148 895c2430 ..L.T$`N...H.\$0 - 0360 4c895c24 404889cb 4c8d1cf1 4c895424 L.\$@H..L...L.T$ - 0370 704c8d14 f9488b4c 24a04c89 9c249000 pL...H.L$.L..$.. - 0380 00004801 c14c8d1c cb4801c2 4c899c24 ..H..L...H..L..$ - 0390 a0000000 4c8d1cd3 488b5424 884801c5 ....L...H.T$.H.. - 03a0 4c899c24 b0000000 4901c44c 8d1ceb49 L..$....I..L...I - 03b0 01c54901 c64801c2 488d14d3 4c899424 ..I..H..H...L..$ - 03c0 80000000 4c899c24 c0000000 4e8d14e3 ....L..$....N... - 03d0 4e8d1ceb 4e8d34f3 4889de48 89942400 N...N.4.H..H..$. - 03e0 0100004c 899424d0 0000004c 899c24e0 ...L..$....L..$. - 03f0 0000004c 89b424f0 00000048 8b5c2498 ...L..$....H.\$. - 0400 4889c748 89d84801 f8488d14 c6488b04 H..H..H..H...H.. - 0410 24488994 24100100 004801d8 4801f848 $H..$....H..H..H - 0420 8d14c648 8b742410 4889fb48 89f0488b ...H.t$.H..H..H. - 0430 7c24a848 83e0f048 01f84889 4424d048 |$.H...H..H.D$.H - 0440 8b442408 48899424 20010000 4889c248 .D$.H..$ ...H..H - 0450 c1e00448 01f84889 84243801 00004889 ...H..H..$8...H. - 0460 f083e00e 48898424 58010000 4889f048 ....H..$X...H..H - 0470 c1e20b83 e00c83e6 08488994 24400100 .........H..$@.. - 0480 0048895c 249048c7 4424f000 00000048 .H.\$.H.D$.....H - 0490 c74424e8 00000000 48898424 60010000 .D$.....H..$`... - 04a0 4889b424 68010000 e9110100 000f1f00 H..$h........... - 04b0 488b4424 e8488b8c 24e00000 00488b74 H.D$.H..$....H.t - 04c0 24304801 c148894c 2498488b 8c24f000 $0H..H.L$.H..$.. - 04d0 0000488b 7c244048 01c14889 4c24a048 ..H.|$@H..H.L$.H - 04e0 8b8c2400 0100004c 8b442450 4801c148 ..$....L.D$PH..H - 04f0 894c24b0 4c8b4c24 604c8b54 24704c8b .L$.L.L$`L.T$pL. - 0500 9c248000 0000488b 9c249000 0000488b .$....H..$....H. - 0510 ac24a000 00004c8b a424b000 00004c8b .$....L..$....L. - 0520 ac24c000 00004c8b b424d000 0000488b .$....L..$....H. - 0530 8c241001 00004801 c64801c1 4801c749 .$....H..H..H..I - 0540 01c04901 c14901c2 4901c348 01c34801 ..I..I..I..H..H. - 0550 c54901c4 4901c549 01c64803 84242001 .I..I..I..H..$ . - 0560 00004883 7c240800 48894424 c048894c ..H.|$..H.D$.H.L - 0570 24b8488b 4424a80f 8f1e0100 0048837c $.H.D$.......H.| - 0580 24d80074 13483944 24900f8d 880f0000 $..t.H9D$....... - 0590 4c03bc24 48010000 48834424 9010488b L..$H...H.D$..H. - 05a0 7c24f848 836c24e8 8048017c 24f0488b |$.H.l$..H.|$.H. - 05b0 44249048 3b442418 0f841219 0000488b D$.H;D$.......H. - 05c0 5c24a848 395c2490 0f8de2fe ffff488b \$.H9\$.......H. - 05d0 4424f048 8b8c24e8 00000048 8b742438 D$.H..$....H.t$8 - 05e0 4801c148 894c2498 488b8c24 f8000000 H..H.L$.H..$.... - 05f0 488b7c24 484801c1 48894c24 a0488b8c H.|$HH..H.L$.H.. - 0600 24080100 004c8b44 24584801 c148894c $....L.D$XH..H.L - 0610 24b04c8b 4c24684c 8b542478 4c8b9c24 $.L.L$hL.T$xL..$ - 0620 88000000 488b9c24 98000000 488bac24 ....H..$....H..$ - 0630 a8000000 4c8ba424 b8000000 4c8bac24 ....L..$....L..$ - 0640 c8000000 4c8bb424 d8000000 488b8c24 ....L..$....H..$ - 0650 18010000 4801c648 01c14801 c74901c0 ....H..H..H..I.. - 0660 4901c149 01c24901 c34801c3 4801c549 I..I..I..H..H..I - 0670 01c44901 c54901c6 48038424 28010000 ..I..I..H..$(... - 0680 48837c24 08004889 4424c048 894c24b8 H.|$..H.D$.H.L$. - 0690 488b4424 a80f8ee2 feffff48 8b5424a8 H.D$.......H.T$. - 06a0 4c89bc24 a8010000 48895424 88498d87 L..$....H.T$.I.. - 06b0 00080000 eb70662e 0f1f8400 00000000 .....pf......... - 06c0 48836c24 98804883 6c24a080 48836c24 H.l$..H.l$..H.l$ - 06d0 b0804883 6c24b880 48836c24 c0804883 ..H.l$..H.l$..H. - 06e0 ee804883 ef804983 e8804983 e9804983 ..H...I...I...I. - 06f0 ea804983 eb804883 eb804883 ed804983 ..I...H...H...I. - 0700 ec804983 ed804983 ee804883 44248810 ..I...I...H.D$.. - 0710 48050008 0000488b 4c248848 3b4c24d0 H.....H.L$.H;L$. - 0720 0f84d20d 00004c8b 7c248848 8d9000f8 ......L.|$.H.... - 0730 ffff4c39 7c24907c 87c5fb10 060f8f9d ..L9|$.|........ - 0740 0c0000c5 fb118000 f8ffffc5 fb104608 ..............F. - 0750 4883ef80 c5fb1180 08f8ffff c5fb1046 H..............F - 0760 104983e8 80c5fb11 8010f8ff ffc5fb10 .I.............. - 0770 46184983 e980c5fb 118018f8 ffffc5fb F.I............. - 0780 10462049 83ea80c5 fb118020 f8ffffc5 .F I....... .... - 0790 fb104628 4983eb80 c5fb1180 28f8ffff ..F(I.......(... - 07a0 c5fb1046 304883eb 80c5fb11 8030f8ff ...F0H.......0.. - 07b0 ffc5fb10 46384883 ed80c5fb 118038f8 ....F8H.......8. - 07c0 ffffc5fb 10464049 83ec80c5 fb118040 .....F@I.......@ - 07d0 f8ffffc5 fb104648 4983ed80 c5fb1180 ......FHI....... - 07e0 48f8ffff c5fb1046 504983ee 80c5fb11 H......FPI...... - 07f0 8050f8ff ffc5fb10 46584883 ee80c5fb .P......FXH..... - 0800 118058f8 ffffc5fb 1046e0c5 fb118060 ..X......F.....` - 0810 f8ffffc5 fb1046e8 c5fb1180 68f8ffff ......F.....h... - 0820 c5fb1046 f0c5fb11 8070f8ff ffc5fb10 ...F.....p...... - 0830 46f848c7 8080f8ff ff000000 00c5fb11 F.H............. - 0840 8078f8ff ffc5fb10 4788c5fb 118088f8 .x......G....... - 0850 ffffc5fb 104790c5 fb118090 f8ffffc5 .....G.......... - 0860 fb104798 c5fb1180 98f8ffff c5fb1047 ..G............G - 0870 a0c5fb11 80a0f8ff ffc5fb10 47a8c5fb ............G... - 0880 1180a8f8 ffffc5fb 1047b0c5 fb1180b0 .........G...... - 0890 f8ffffc5 fb1047b8 c5fb1180 b8f8ffff ......G......... - 08a0 c5fb1047 c0c5fb11 80c0f8ff ffc5fb10 ...G............ - 08b0 47c8c5fb 1180c8f8 ffffc5fb 1047d0c5 G............G.. - 08c0 fb1180d0 f8ffffc5 fb1047d8 c5fb1180 ..........G..... - 08d0 d8f8ffff c5fb1047 e0c5fb11 80e0f8ff .......G........ - 08e0 ffc5fb10 47e8c5fb 1180e8f8 ffffc5fb ....G........... - 08f0 1047f0c5 fb1180f0 f8ffffc5 fb1047f8 .G............G. - 0900 48c78000 f9ffff00 00000048 c78008f9 H..........H.... - 0910 ffff0000 0000c5fb 1180f8f8 ffffc4c1 ................ - 0920 7b104090 c5fb1180 10f9ffff c4c17b10 {.@...........{. - 0930 4098c5fb 118018f9 ffffc4c1 7b1040a0 @...........{.@. - 0940 c5fb1180 20f9ffff c4c17b10 40a8c5fb .... .....{.@... - 0950 118028f9 ffffc4c1 7b1040b0 c5fb1180 ..(.....{.@..... - 0960 30f9ffff c4c17b10 40b8c5fb 118038f9 0.....{.@.....8. - 0970 ffffc4c1 7b1040c0 c5fb1180 40f9ffff ....{.@.....@... - 0980 c4c17b10 40c8c5fb 118048f9 ffffc4c1 ..{.@.....H..... - 0990 7b1040d0 c5fb1180 50f9ffff c4c17b10 {.@.....P.....{. - 09a0 40d8c5fb 118058f9 ffffc4c1 7b1040e0 @.....X.....{.@. - 09b0 c5fb1180 60f9ffff c4c17b10 40e8c5fb ....`.....{.@... - 09c0 118068f9 ffffc4c1 7b1040f0 c5fb1180 ..h.....{.@..... - 09d0 70f9ffff c4c17b10 40f848c7 8080f9ff p.....{.@.H..... - 09e0 ff000000 0048c780 88f9ffff 00000000 .....H.......... - 09f0 48c78090 f9ffff00 000000c5 fb118078 H..............x - 0a00 f9ffffc4 c17b1041 98c5fb11 8098f9ff .....{.A........ - 0a10 ffc4c17b 1041a0c5 fb1180a0 f9ffffc4 ...{.A.......... - 0a20 c17b1041 a8c5fb11 80a8f9ff ffc4c17b .{.A...........{ - 0a30 1041b0c5 fb1180b0 f9ffffc4 c17b1041 .A...........{.A - 0a40 b8c5fb11 80b8f9ff ffc4c17b 1041c0c5 ...........{.A.. - 0a50 fb1180c0 f9ffffc4 c17b1041 c8c5fb11 .........{.A.... - 0a60 80c8f9ff ffc4c17b 1041d0c5 fb1180d0 .......{.A...... - 0a70 f9ffffc4 c17b1041 d8c5fb11 80d8f9ff .....{.A........ - 0a80 ffc4c17b 1041e0c5 fb1180e0 f9ffffc4 ...{.A.......... - 0a90 c17b1041 e8c5fb11 80e8f9ff ffc4c17b .{.A...........{ - 0aa0 1041f0c5 fb1180f0 f9ffffc4 c17b1041 .A...........{.A - 0ab0 f848c780 00faffff 00000000 48c78008 .H..........H... - 0ac0 faffff00 00000048 c78010fa ffff0000 .......H........ - 0ad0 000048c7 8018faff ff000000 00c5fb11 ..H............. - 0ae0 80f8f9ff ffc4c17b 1042a0c5 fb118020 .......{.B..... - 0af0 faffffc4 c17b1042 a8c5fb11 8028faff .....{.B.....(.. - 0b00 ffc4c17b 1042b0c5 fb118030 faffffc4 ...{.B.....0.... - 0b10 c17b1042 b8c5fb11 8038faff ffc4c17b .{.B.....8.....{ - 0b20 1042c0c5 fb118040 faffffc4 c17b1042 .B.....@.....{.B - 0b30 c8c5fb11 8048faff ffc4c17b 1042d0c5 .....H.....{.B.. - 0b40 fb118050 faffffc4 c17b1042 d8c5fb11 ...P.....{.B.... - 0b50 8058faff ffc4c17b 1042e0c5 fb118060 .X.....{.B.....` - 0b60 faffffc4 c17b1042 e8c5fb11 8068faff .....{.B.....h.. - 0b70 ffc4c17b 1042f0c5 fb118070 faffffc4 ...{.B.....p.... - 0b80 c17b1042 f848c780 80faffff 00000000 .{.B.H.......... - 0b90 48c78088 faffff00 00000048 c78090fa H..........H.... - 0ba0 ffff0000 000048c7 8098faff ff000000 ......H......... - 0bb0 0048c780 a0faffff 00000000 c5fb1180 .H.............. - 0bc0 78faffff c4c17b10 43a8c5fb 1180a8fa x.....{.C....... - 0bd0 ffffc4c1 7b1043b0 c5fb1180 b0faffff ....{.C......... - 0be0 c4c17b10 43b8c5fb 1180b8fa ffffc4c1 ..{.C........... - 0bf0 7b1043c0 c5fb1180 c0faffff c4c17b10 {.C...........{. - 0c00 43c8c5fb 1180c8fa ffffc4c1 7b1043d0 C...........{.C. - 0c10 c5fb1180 d0faffff c4c17b10 43d8c5fb ..........{.C... /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 342e0000 00420e10 8f02420e ....4....B....B. + 0020 00000000 bd060000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ea80303 0d280a0e ..A.8..G.....(.. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0846 0b000000 D..F.... + 0040 8606410e 38830744 0e500336 050a0e38 ..A.8..D.P.6...8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08480b 00000000 ..H..... /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_SKYLAKEX.o (disasm) @@ -12,1733 +12,320 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) + mov %rdi,-offset(%rsp) mov %rdx,-offset(%rsp) - mov %rcx,(%rsp) - mov %r8,-offset(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov %rcx,-offset(%rsp) + mov %rsi,(%rsp) + mov offset(%rsp),%rbx test %rsi,%rsi jle - mov %r8,%rbx - imul %rcx,%rbx - mov %r8,%rdi mov %rcx,%rax - lea (%rcx,%rbx,1),%r11 - lea (%r11,%rcx,1),%r10 - lea (%rcx,%r10,1),%r9 - lea (%r9,%rcx,1),%r8 - lea (%rcx,%r8,1),%rsi - mov %rsi,-offset(%rsp) - add %rcx,%rsi - lea (%rcx,%rsi,1),%rcx - lea (%rax,%rcx,1),%rdx - lea (%rax,%rdx,1),%rbp - lea (%rax,%rbp,1),%r12 - lea (%rax,%r12,1),%r13 - lea (%rax,%r13,1),%r14 - mov %rcx,-offset(%rsp) - lea (%rax,%r14,1),%rcx - mov %rcx,-offset(%rsp) - mov -offset(%rsp),%rcx - add %rax,%rcx - mov %rcx,-offset(%rsp) - mov offset(%rsp),%rcx - sar $something,%rcx - mov %rcx,offset(%rsp) - lea offset(,%rax,8),%rcx - mov %rcx,offset(%rsp) - mov %rax,%rcx - mov offset(%rsp),%rax - shl $something,%rcx - and $something,%eax + imul %r8,%rax + mov %rsi,%r14 + mov %rdi,%r10 + add %r9,%rax + lea (%rdx,%rax,8),%r13 + mov %rcx,%rax + imul %r9,%rax + mov %rcx,%rdi + mov %rcx,%rbp + add %r8,%rax + lea (%rdx,%rax,8),%r12 + lea (%r9,%r14,4),%rax mov %rax,-offset(%rsp) - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - mov %rcx,-offset(%rsp) - mov -offset(%rsp),%rcx - shl $something,%rax - add %rcx,%rax - mov %rax,offset(%rsp) - mov (%rsp),%rax - imul %rcx,%rax - add %rdi,%rax - mov -offset(%rsp),%rdi - lea (%rdi,%rax,8),%rdi mov %rcx,%rax - mov (%rsp),%rcx - inc %rax - imul %rcx,%rax - mov %rdi,offset(%rsp) - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - add -offset(%rsp),%rax - mov -offset(%rsp),%rdi - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - add -offset(%rsp),%rax - mov -offset(%rsp),%rdi - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rcx - add -offset(%rsp),%rax - lea (%rcx,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add %rax,%r10 - lea (%rcx,%r10,8),%r10 - add %rax,%r9 - mov -offset(%rsp),%rdi - add %rax,%rbx - add %rax,%r11 - add %rax,%r8 - mov %r10,offset(%rsp) - lea (%rcx,%r9,8),%r10 - add %rax,%rdi - add %rax,%rsi - lea (%rcx,%rbx,8),%rbx /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_SKYLAKEX.o (objdump) @@ -2,743 +2,111 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ec700100 AWAVAUATUSH..p.. - 0010 00488974 242048c1 fe044889 7c241048 .H.t$ H...H.|$.H - 0020 895424e0 48890c24 4c894424 a84c894c .T$.H..$L.D$.L.L - 0030 24c84889 b4245001 00004c8b bc24a801 $.H..$P...L..$.. - 0040 00004885 f60f8e9e 1e00004c 89c3480f ..H........L..H. - 0050 afd94c89 c74889c8 4c8d1c19 4d8d140b ..L..H..L...M... - 0060 4e8d0c11 4d8d0409 4a8d3401 48897424 N...M...J.4.H.t$ - 0070 904801ce 488d0c31 488d1408 488d2c10 .H..H..1H...H.,. - 0080 4c8d2428 4e8d2c20 4e8d3428 48894c24 L.$(N., N.4(H.L$ - 0090 a04a8d0c 3048894c 2488488b 4c248848 .J..0H.L$.H.L$.H - 00a0 01c14889 4c249848 8b4c2410 48c1f904 ..H.L$.H.L$.H... - 00b0 48894c24 08488d0c c5000000 0048898c H.L$.H.......H.. - 00c0 24300100 004889c1 488b4424 1048c1e1 $0...H..H.D$.H.. - 00d0 0783e00f 48894424 d848c1e0 07488984 ....H.D$.H...H.. - 00e0 24480100 00488b84 24500100 0048894c $H...H..$P...H.L - 00f0 24f8488b 4c24c848 c1e00448 01c84889 $.H.L$.H...H..H. - 0100 44241848 8b042448 0fafc148 01f8488b D$.H..$H...H..H. - 0110 7c24e048 8d3cc748 89c8488b 0c2448ff |$.H.<.H..H..$H. - 0120 c0480faf c148897c 2438488b 7c24e048 .H...H.|$8H.|$.H - 0130 034424a8 488d3cc7 488b4424 c848897c .D$.H.<.H.D$.H.| - 0140 24484883 c002480f afc1488b 7c24e048 $HH...H...H.|$.H - 0150 034424a8 488d3cc7 488b4424 c848897c .D$.H.<.H.D$.H.| - 0160 24584883 c003480f afc1488b 7c24e048 $XH...H...H.|$.H - 0170 034424a8 488d3cc7 488b4424 c848897c .D$.H.<.H.D$.H.| - 0180 24684883 c004480f afc14803 4424a848 $hH...H...H.D$.H - 0190 8b7c24e0 488d3cc7 488b4424 c848897c .|$.H.<.H.D$.H.| - 01a0 24784883 c005480f afc1488b 7c24e048 $xH...H...H.|$.H - 01b0 034424a8 488d3cc7 488b4424 c84889bc .D$.H.<.H.D$.H.. - 01c0 24880000 004883c0 06480faf c1488b7c $....H...H...H.| - 01d0 24e04803 4424a848 8d3cc748 8b4424c8 $.H.D$.H.<.H.D$. - 01e0 4889bc24 98000000 4883c007 480fafc1 H..$....H...H... - 01f0 488b7c24 e0480344 24a8488d 3cc7488b H.|$.H.D$.H.<.H. - 0200 4424c848 89bc24a8 00000048 83c00848 D$.H..$....H...H - 0210 0fafc148 8b7c24e0 48034424 a8488d3c ...H.|$.H.D$.H.< - 0220 c7488b44 24c84889 bc24b800 00004883 .H.D$.H..$....H. - 0230 c009480f afc1488b 7c24e048 034424a8 ..H...H.|$.H.D$. - 0240 488d3cc7 488b4424 c84889bc 24c80000 H.<.H.D$.H..$... - 0250 004883c0 0a480faf c1488b7c 24e04803 .H...H...H.|$.H. - 0260 4424a848 8d3cc748 8b4424c8 4889bc24 D$.H.<.H.D$.H..$ - 0270 d8000000 4883c00b 480fafc1 488b7c24 ....H...H...H.|$ - 0280 e0480344 24a8488d 3cc7488b 4424c848 .H.D$.H.<.H.D$.H - 0290 89bc24e8 00000048 83c00c48 0fafc148 ..$....H...H...H - 02a0 034424a8 488b7c24 e0488d3c c7488b44 .D$.H.|$.H.<.H.D - 02b0 24c84889 bc24f800 00004883 c00d480f $.H..$....H...H. - 02c0 afc1488b 7c24e048 034424a8 488d3cc7 ..H.|$.H.D$.H.<. - 02d0 488b4424 c84889bc 24080100 004883c0 H.D$.H..$....H.. - 02e0 0e480faf c1488b7c 24e04803 4424a848 .H...H.|$.H.D$.H - 02f0 8d3cc748 8b4424c8 4889bc24 18010000 .<.H.D$.H..$.... - 0300 4883c00f 480fafc1 488b4c24 e0480344 H...H...H.L$.H.D - 0310 24a8488d 3cc1488b 4424c848 89bc2428 $.H.<.H.D$.H..$( - 0320 01000049 01c24e8d 14d14901 c1488b7c ...I..N...I..H.| - 0330 24904801 c34901c3 4901c04c 89542450 $.H..I..I..L.T$P - 0340 4e8d14c9 4801c748 01c6488d 1cd94e8d N...H..H..H...N. - 0350 1cd94c89 5424604e 8d14c148 895c2430 ..L.T$`N...H.\$0 - 0360 4c895c24 404889cb 4c8d1cf1 4c895424 L.\$@H..L...L.T$ - 0370 704c8d14 f9488b4c 24a04c89 9c249000 pL...H.L$.L..$.. - 0380 00004801 c14c8d1c cb4801c2 4c899c24 ..H..L...H..L..$ - 0390 a0000000 4c8d1cd3 488b5424 884801c5 ....L...H.T$.H.. - 03a0 4c899c24 b0000000 4901c44c 8d1ceb49 L..$....I..L...I - 03b0 01c54901 c64801c2 488d14d3 4c899424 ..I..H..H...L..$ - 03c0 80000000 4c899c24 c0000000 4e8d14e3 ....L..$....N... - 03d0 4e8d1ceb 4e8d34f3 4889de48 89942400 N...N.4.H..H..$. - 03e0 0100004c 899424d0 0000004c 899c24e0 ...L..$....L..$. - 03f0 0000004c 89b424f0 00000048 8b5c2498 ...L..$....H.\$. - 0400 4889c748 89d84801 f8488d14 c6488b04 H..H..H..H...H.. - 0410 24488994 24100100 004801d8 4801f848 $H..$....H..H..H - 0420 8d14c648 8b742410 4889fb48 89f0488b ...H.t$.H..H..H. - 0430 7c24a848 83e0f048 01f84889 4424d048 |$.H...H..H.D$.H - 0440 8b442408 48899424 20010000 4889c248 .D$.H..$ ...H..H - 0450 c1e00448 01f84889 84243801 00004889 ...H..H..$8...H. - 0460 f083e00e 48898424 58010000 4889f048 ....H..$X...H..H - 0470 c1e20b83 e00c83e6 08488994 24400100 .........H..$@.. - 0480 0048895c 249048c7 4424f000 00000048 .H.\$.H.D$.....H - 0490 c74424e8 00000000 48898424 60010000 .D$.....H..$`... - 04a0 4889b424 68010000 e9110100 000f1f00 H..$h........... - 04b0 488b4424 e8488b8c 24e00000 00488b74 H.D$.H..$....H.t - 04c0 24304801 c148894c 2498488b 8c24f000 $0H..H.L$.H..$.. - 04d0 0000488b 7c244048 01c14889 4c24a048 ..H.|$@H..H.L$.H - 04e0 8b8c2400 0100004c 8b442450 4801c148 ..$....L.D$PH..H - 04f0 894c24b0 4c8b4c24 604c8b54 24704c8b .L$.L.L$`L.T$pL. - 0500 9c248000 0000488b 9c249000 0000488b .$....H..$....H. - 0510 ac24a000 00004c8b a424b000 00004c8b .$....L..$....L. - 0520 ac24c000 00004c8b b424d000 0000488b .$....L..$....H. - 0530 8c241001 00004801 c64801c1 4801c749 .$....H..H..H..I - 0540 01c04901 c14901c2 4901c348 01c34801 ..I..I..I..H..H. - 0550 c54901c4 4901c549 01c64803 84242001 .I..I..I..H..$ . - 0560 00004883 7c240800 48894424 c048894c ..H.|$..H.D$.H.L - 0570 24b8488b 4424a80f 8f1e0100 0048837c $.H.D$.......H.| - 0580 24d80074 13483944 24900f8d 880f0000 $..t.H9D$....... - 0590 4c03bc24 48010000 48834424 9010488b L..$H...H.D$..H. - 05a0 7c24f848 836c24e8 8048017c 24f0488b |$.H.l$..H.|$.H. - 05b0 44249048 3b442418 0f841219 0000488b D$.H;D$.......H. - 05c0 5c24a848 395c2490 0f8de2fe ffff488b \$.H9\$.......H. - 05d0 4424f048 8b8c24e8 00000048 8b742438 D$.H..$....H.t$8 - 05e0 4801c148 894c2498 488b8c24 f8000000 H..H.L$.H..$.... - 05f0 488b7c24 484801c1 48894c24 a0488b8c H.|$HH..H.L$.H.. - 0600 24080100 004c8b44 24584801 c148894c $....L.D$XH..H.L - 0610 24b04c8b 4c24684c 8b542478 4c8b9c24 $.L.L$hL.T$xL..$ - 0620 88000000 488b9c24 98000000 488bac24 ....H..$....H..$ - 0630 a8000000 4c8ba424 b8000000 4c8bac24 ....L..$....L..$ - 0640 c8000000 4c8bb424 d8000000 488b8c24 ....L..$....H..$ - 0650 18010000 4801c648 01c14801 c74901c0 ....H..H..H..I.. - 0660 4901c149 01c24901 c34801c3 4801c549 I..I..I..H..H..I - 0670 01c44901 c54901c6 48038424 28010000 ..I..I..H..$(... - 0680 48837c24 08004889 4424c048 894c24b8 H.|$..H.D$.H.L$. - 0690 488b4424 a80f8ee2 feffff48 8b5424a8 H.D$.......H.T$. - 06a0 4c89bc24 a8010000 48895424 88498d87 L..$....H.T$.I.. - 06b0 00080000 eb70662e 0f1f8400 00000000 .....pf......... - 06c0 48836c24 98804883 6c24a080 48836c24 H.l$..H.l$..H.l$ - 06d0 b0804883 6c24b880 48836c24 c0804883 ..H.l$..H.l$..H. - 06e0 ee804883 ef804983 e8804983 e9804983 ..H...I...I...I. - 06f0 ea804983 eb804883 eb804883 ed804983 ..I...H...H...I. - 0700 ec804983 ed804983 ee804883 44248810 ..I...I...H.D$.. - 0710 48050008 0000488b 4c248848 3b4c24d0 H.....H.L$.H;L$. - 0720 0f84d20d 00004c8b 7c248848 8d9000f8 ......L.|$.H.... - 0730 ffff4c39 7c24907c 87c5fb10 060f8f9d ..L9|$.|........ - 0740 0c0000c5 fb118000 f8ffffc5 fb104608 ..............F. - 0750 4883ef80 c5fb1180 08f8ffff c5fb1046 H..............F - 0760 104983e8 80c5fb11 8010f8ff ffc5fb10 .I.............. - 0770 46184983 e980c5fb 118018f8 ffffc5fb F.I............. - 0780 10462049 83ea80c5 fb118020 f8ffffc5 .F I....... .... - 0790 fb104628 4983eb80 c5fb1180 28f8ffff ..F(I.......(... - 07a0 c5fb1046 304883eb 80c5fb11 8030f8ff ...F0H.......0.. - 07b0 ffc5fb10 46384883 ed80c5fb 118038f8 ....F8H.......8. - 07c0 ffffc5fb 10464049 83ec80c5 fb118040 .....F@I.......@ - 07d0 f8ffffc5 fb104648 4983ed80 c5fb1180 ......FHI....... - 07e0 48f8ffff c5fb1046 504983ee 80c5fb11 H......FPI...... - 07f0 8050f8ff ffc5fb10 46584883 ee80c5fb .P......FXH..... - 0800 118058f8 ffffc5fb 1046e0c5 fb118060 ..X......F.....` - 0810 f8ffffc5 fb1046e8 c5fb1180 68f8ffff ......F.....h... - 0820 c5fb1046 f0c5fb11 8070f8ff ffc5fb10 ...F.....p...... - 0830 46f848c7 8080f8ff ff000000 00c5fb11 F.H............. - 0840 8078f8ff ffc5fb10 4788c5fb 118088f8 .x......G....... - 0850 ffffc5fb 104790c5 fb118090 f8ffffc5 .....G.......... - 0860 fb104798 c5fb1180 98f8ffff c5fb1047 ..G............G - 0870 a0c5fb11 80a0f8ff ffc5fb10 47a8c5fb ............G... - 0880 1180a8f8 ffffc5fb 1047b0c5 fb1180b0 .........G...... - 0890 f8ffffc5 fb1047b8 c5fb1180 b8f8ffff ......G......... - 08a0 c5fb1047 c0c5fb11 80c0f8ff ffc5fb10 ...G............ - 08b0 47c8c5fb 1180c8f8 ffffc5fb 1047d0c5 G............G.. - 08c0 fb1180d0 f8ffffc5 fb1047d8 c5fb1180 ..........G..... - 08d0 d8f8ffff c5fb1047 e0c5fb11 80e0f8ff .......G........ - 08e0 ffc5fb10 47e8c5fb 1180e8f8 ffffc5fb ....G........... - 08f0 1047f0c5 fb1180f0 f8ffffc5 fb1047f8 .G............G. - 0900 48c78000 f9ffff00 00000048 c78008f9 H..........H.... - 0910 ffff0000 0000c5fb 1180f8f8 ffffc4c1 ................ - 0920 7b104090 c5fb1180 10f9ffff c4c17b10 {.@...........{. - 0930 4098c5fb 118018f9 ffffc4c1 7b1040a0 @...........{.@. - 0940 c5fb1180 20f9ffff c4c17b10 40a8c5fb .... .....{.@... - 0950 118028f9 ffffc4c1 7b1040b0 c5fb1180 ..(.....{.@..... - 0960 30f9ffff c4c17b10 40b8c5fb 118038f9 0.....{.@.....8. - 0970 ffffc4c1 7b1040c0 c5fb1180 40f9ffff ....{.@.....@... - 0980 c4c17b10 40c8c5fb 118048f9 ffffc4c1 ..{.@.....H..... - 0990 7b1040d0 c5fb1180 50f9ffff c4c17b10 {.@.....P.....{. - 09a0 40d8c5fb 118058f9 ffffc4c1 7b1040e0 @.....X.....{.@. - 09b0 c5fb1180 60f9ffff c4c17b10 40e8c5fb ....`.....{.@... - 09c0 118068f9 ffffc4c1 7b1040f0 c5fb1180 ..h.....{.@..... - 09d0 70f9ffff c4c17b10 40f848c7 8080f9ff p.....{.@.H..... - 09e0 ff000000 0048c780 88f9ffff 00000000 .....H.......... - 09f0 48c78090 f9ffff00 000000c5 fb118078 H..............x - 0a00 f9ffffc4 c17b1041 98c5fb11 8098f9ff .....{.A........ - 0a10 ffc4c17b 1041a0c5 fb1180a0 f9ffffc4 ...{.A.......... - 0a20 c17b1041 a8c5fb11 80a8f9ff ffc4c17b .{.A...........{ - 0a30 1041b0c5 fb1180b0 f9ffffc4 c17b1041 .A...........{.A - 0a40 b8c5fb11 80b8f9ff ffc4c17b 1041c0c5 ...........{.A.. - 0a50 fb1180c0 f9ffffc4 c17b1041 c8c5fb11 .........{.A.... - 0a60 80c8f9ff ffc4c17b 1041d0c5 fb1180d0 .......{.A...... - 0a70 f9ffffc4 c17b1041 d8c5fb11 80d8f9ff .....{.A........ - 0a80 ffc4c17b 1041e0c5 fb1180e0 f9ffffc4 ...{.A.......... - 0a90 c17b1041 e8c5fb11 80e8f9ff ffc4c17b .{.A...........{ - 0aa0 1041f0c5 fb1180f0 f9ffffc4 c17b1041 .A...........{.A - 0ab0 f848c780 00faffff 00000000 48c78008 .H..........H... - 0ac0 faffff00 00000048 c78010fa ffff0000 .......H........ - 0ad0 000048c7 8018faff ff000000 00c5fb11 ..H............. - 0ae0 80f8f9ff ffc4c17b 1042a0c5 fb118020 .......{.B..... - 0af0 faffffc4 c17b1042 a8c5fb11 8028faff .....{.B.....(.. - 0b00 ffc4c17b 1042b0c5 fb118030 faffffc4 ...{.B.....0.... - 0b10 c17b1042 b8c5fb11 8038faff ffc4c17b .{.B.....8.....{ - 0b20 1042c0c5 fb118040 faffffc4 c17b1042 .B.....@.....{.B - 0b30 c8c5fb11 8048faff ffc4c17b 1042d0c5 .....H.....{.B.. - 0b40 fb118050 faffffc4 c17b1042 d8c5fb11 ...P.....{.B.... - 0b50 8058faff ffc4c17b 1042e0c5 fb118060 .X.....{.B.....` - 0b60 faffffc4 c17b1042 e8c5fb11 8068faff .....{.B.....h.. - 0b70 ffc4c17b 1042f0c5 fb118070 faffffc4 ...{.B.....p.... - 0b80 c17b1042 f848c780 80faffff 00000000 .{.B.H.......... - 0b90 48c78088 faffff00 00000048 c78090fa H..........H.... - 0ba0 ffff0000 000048c7 8098faff ff000000 ......H......... - 0bb0 0048c780 a0faffff 00000000 c5fb1180 .H.............. - 0bc0 78faffff c4c17b10 43a8c5fb 1180a8fa x.....{.C....... - 0bd0 ffffc4c1 7b1043b0 c5fb1180 b0faffff ....{.C......... - 0be0 c4c17b10 43b8c5fb 1180b8fa ffffc4c1 ..{.C........... - 0bf0 7b1043c0 c5fb1180 c0faffff c4c17b10 {.C...........{. - 0c00 43c8c5fb 1180c8fa ffffc4c1 7b1043d0 C...........{.C. - 0c10 c5fb1180 d0faffff c4c17b10 43d8c5fb ..........{.C... /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltncopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 342e0000 00420e10 8f02420e ....4....B....B. + 0020 00000000 bd060000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ea80303 0d280a0e ..A.8..G.....(.. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0846 0b000000 D..F.... + 0040 8606410e 38830744 0e500336 050a0e38 ..A.8..D.P.6...8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08480b 00000000 ..H..... /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_COOPERLAKE.o (disasm) @@ -12,1637 +12,326 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,(%rsp) - mov %rdx,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) mov %rcx,-offset(%rsp) - mov %r8,-offset(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov %rsi,(%rsp) + mov offset(%rsp),%rbx test %rsi,%rsi jle - mov %r8,%rbx - imul %rcx,%rbx - mov %r8,%rdi mov %rcx,%rax - lea (%rcx,%rbx,1),%r11 - lea (%r11,%rcx,1),%rsi - lea (%rcx,%rsi,1),%r9 - lea (%r9,%rcx,1),%r8 - mov %rsi,-offset(%rsp) - lea (%rcx,%r8,1),%rsi - mov %rsi,-offset(%rsp) - add %rcx,%rsi - lea (%rcx,%rsi,1),%rcx - lea (%rax,%rcx,1),%rdx - lea (%rax,%rdx,1),%rbp - lea (%rax,%rbp,1),%r12 - lea (%rax,%r12,1),%r13 - lea (%rax,%r13,1),%r14 - lea (%rax,%r14,1),%r10 - mov %r10,-offset(%rsp) - mov (%rsp),%r10 - sar $something,%r10 - mov %r10,-offset(%rsp) - lea offset(,%rax,8),%r10 - mov %r10,offset(%rsp) - mov (%rsp),%r10 + imul %r8,%rax + mov %rsi,%r14 + mov %rdi,%r10 + add %r9,%rax + lea (%rdx,%rax,8),%r13 + mov %rcx,%rax + imul %r9,%rax + mov %rcx,%rdi + mov %rcx,%rbp + add %r8,%rax + lea (%rdx,%rax,8),%r12 + lea (%r9,%r14,4),%rax + mov %rax,-offset(%rsp) + mov %rcx,%rax + neg %rax + mov %rcx,%rsi + lea offset(,%rax,8),%rcx + mov %rcx,%rax + mov %rcx,-offset(%rsp) + lea offset(%r9),%rdx + neg %rcx + imul %r9,%rax + imul %rcx,%rdx + mov %r10,%r15 + sar $something,%r15 + add %rax,%rdx + mov %rdx,-offset(%rsp) + lea offset(%r9),%rdx + imul %rcx,%rdx + shl $something,%rsi + mov %rsi,offset(%rsp) + add %rax,%rdx + mov %rdx,-offset(%rsp) + lea offset(%r9),%rdx + imul %rcx,%rdx + mov %r10,%rsi + mov %rsi,%r14 + add %rdx,%rax + mov %rax,-offset(%rsp) + mov %rdi,%rax shl $something,%rax - and $something,%r10d - mov %r10,-offset(%rsp) - shl $something,%r10 mov %rax,-offset(%rsp) - mov %r10,offset(%rsp) - mov -offset(%rsp),%rax - mov offset(%rsp),%r10 - imul -offset(%rsp),%rax - shl $something,%r10 - add -offset(%rsp),%r10 - mov %r10,offset(%rsp) - mov offset(%rsp),%r10 - add %rdi,%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - inc %rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov %rdi,offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov %rdi,offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add %rax,%rbx - add %rax,%r11 - mov %r10,%rdi - lea (%r10,%rbx,8),%rbx - lea (%r10,%r11,8),%r11 - mov -offset(%rsp),%r10 - mov %rbx,offset(%rsp) - mov %rax,%rbx - add %rbx,%r10 - mov %r11,offset(%rsp) - add %rbx,%r9 /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_COOPERLAKE.o (objdump) @@ -2,718 +2,116 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ec580100 AWAVAUATUSH..X.. - 0010 00488974 241048c1 fe044889 3c244889 .H.t$.H...H.<$H. - 0020 54242048 894c24d8 4c894424 b04c894c T$ H.L$.L.D$.L.L - 0030 24c04889 b4243801 00004c8b bc249001 $.H..$8...L..$.. - 0040 00004885 f60f8e56 1d00004c 89c3480f ..H....V...L..H. - 0050 afd94c89 c74889c8 4c8d1c19 498d340b ..L..H..L...I.4. - 0060 4c8d0c31 4d8d0409 48897424 984a8d34 L..1M...H.t$.J.4 - 0070 01488974 24884801 ce488d0c 31488d14 .H.t$.H..H..1H.. - 0080 08488d2c 104c8d24 284e8d2c 204e8d34 .H.,.L.$(N., N.4 - 0090 284e8d14 304c8954 24904c8b 142449c1 (N..0L.T$.L..$I. - 00a0 fa044c89 5424f84c 8d14c500 0000004c ..L.T$.L.......L - 00b0 89942418 0100004c 8b142448 c1e00741 ..$....L..$H...A - 00c0 83e20f4c 895424d0 49c1e207 48894424 ...L.T$.I...H.D$ - 00d0 f04c8994 24300100 00488b44 24d84c8b .L..$0...H.D$.L. - 00e0 94243801 0000480f af4424c0 49c1e204 .$8...H..D$.I... - 00f0 4c035424 c04c8954 24084c8b 54242048 L.T$.L.T$.L.T$ H - 0100 01f8498d 3cc2488b 4424c048 897c2430 ..I.<.H.D$.H.|$0 - 0110 48ffc048 0faf4424 d8480344 24b0498d H..H..D$.H.D$.I. - 0120 3cc2488b 4424c048 897c2440 4883c002 <.H.D$.H.|$@H... - 0130 480faf44 24d84803 4424b049 8d3cc248 H..D$.H.D$.I.<.H - 0140 8b4424c0 48897c24 504883c0 03480faf .D$.H.|$PH...H.. - 0150 4424d848 034424b0 498d3cc2 488b4424 D$.H.D$.I.<.H.D$ - 0160 c048897c 24604883 c004480f af4424d8 .H.|$`H...H..D$. - 0170 48034424 b0498d3c c248897c 2470488b H.D$.I.<.H.|$pH. - 0180 4424c048 83c00548 0faf4424 d8480344 D$.H...H..D$.H.D - 0190 24b0498d 3cc2488b 4424c048 89bc2480 $.I.<.H.D$.H..$. - 01a0 00000048 83c00648 0faf4424 d8480344 ...H...H..D$.H.D - 01b0 24b0498d 3cc2488b 4424c048 89bc2490 $.I.<.H.D$.H..$. - 01c0 00000048 83c00748 0faf4424 d8480344 ...H...H..D$.H.D - 01d0 24b0498d 3cc2488b 4424c048 89bc24a0 $.I.<.H.D$.H..$. - 01e0 00000048 83c00848 0faf4424 d8480344 ...H...H..D$.H.D - 01f0 24b0498d 3cc2488b 4424c048 89bc24b0 $.I.<.H.D$.H..$. - 0200 00000048 83c00948 0faf4424 d8480344 ...H...H..D$.H.D - 0210 24b0498d 3cc2488b 4424c048 89bc24c0 $.I.<.H.D$.H..$. - 0220 00000048 83c00a48 0faf4424 d8480344 ...H...H..D$.H.D - 0230 24b0498d 3cc2488b 4424c048 89bc24d0 $.I.<.H.D$.H..$. - 0240 00000048 83c00b48 0faf4424 d8480344 ...H...H..D$.H.D - 0250 24b0498d 3cc2488b 4424c048 89bc24e0 $.I.<.H.D$.H..$. - 0260 00000048 83c00c48 0faf4424 d8480344 ...H...H..D$.H.D - 0270 24b0498d 3cc24889 bc24f000 0000488b $.I.<.H..$....H. - 0280 4424c048 83c00d48 0faf4424 d8480344 D$.H...H..D$.H.D - 0290 24b0498d 3cc2488b 4424c048 89bc2400 $.I.<.H.D$.H..$. - 02a0 01000048 83c00e48 0faf4424 d8480344 ...H...H..D$.H.D - 02b0 24b0498d 3cc2488b 4424c048 89bc2410 $.I.<.H.D$.H..$. - 02c0 01000048 01c34901 c34c89d7 498d1cda ...H..I..L..I... - 02d0 4f8d1cda 4c8b5424 9848895c 24284889 O...L.T$.H.\$(H. - 02e0 c34901da 4c895c24 384901d9 4e8d1cd7 .I..L.\$8I..N... - 02f0 4801d948 8d0ccf48 01da4c89 5c244849 H..H...H..L.\$HI - 0300 01d84e8d 1ccf4c89 5c245848 898c2498 ..N...L.\$XH..$. - 0310 0000004e 8d1cc748 8d0cd748 01dd488b ...N...H...H..H. - 0320 5424904c 895c2468 48898c24 a8000000 T$.L.\$hH..$.... - 0330 4c8b5c24 88488d0c ef4901dc 48898c24 L.\$.H...I..H..$ - 0340 b8000000 4901dd4a 8d0ce748 01de4889 ....I..J...H..H. - 0350 8c24c800 00004901 db4a8d0c ef4901de .$....I..J...I.. - 0360 4889d04e 8d1cdf48 035424d8 48898c24 H..N...H.T$.H..$ - 0370 d8000000 4801d84a 8d0cf74c 895c2478 ....H..J...L.\$x - 0380 48898c24 e8000000 4c8d1cf7 488d0cc7 H..$....L...H... - 0390 488b3424 4889d048 01d8488d 14c7488b H.4$H..H..H...H. - 03a0 7c24b048 89f04883 e0f04801 f8488944 |$.H..H...H..H.D - 03b0 24c8488b 4424f848 89942408 01000048 $.H.D$.H..$....H - 03c0 89c248c1 e0044801 f848c1e2 0b4c899c ..H...H..H...L.. - 03d0 24880000 0048898c 24f80000 00488994 $....H..$....H.. - 03e0 24200100 00488984 24280100 004889f0 $ ...H..$(...H.. - 03f0 83e00e48 89842440 01000048 89f083e0 ...H..$@...H.... - 0400 0c83e608 48895c24 9048c744 24e80000 ....H.\$.H.D$... - 0410 000048c7 4424e000 00000048 89842448 ..H.D$.....H..$H - 0420 01000048 89b42450 010000c5 fb100500 ...H..$P........ - 0430 000000e9 03010000 0f1f8400 00000000 ................ - 0440 488b4424 e0488b8c 24d80000 00488b74 H.D$.H..$....H.t - 0450 24284801 c148894c 24b8488b 8c24e800 $(H..H.L$.H..$.. - 0460 0000488b 7c243848 01c14889 4c24984c ..H.|$8H..H.L$.L - 0470 8b442448 4c8b4c24 584c8b54 24684c8b .D$HL.L$XL.T$hL. - 0480 5c247848 8b9c2488 00000048 8bac2498 \$xH..$....H..$. - 0490 0000004c 8ba424a8 0000004c 8bac24b8 ...L..$....L..$. - 04a0 0000004c 8bb424c8 00000048 8b8c24f8 ...L..$....H..$. - 04b0 00000048 01c64801 c14801c7 4901c049 ...H..H..H..I..I - 04c0 01c14901 c24901c3 4801c348 01c54901 ..I..I..H..H..I. - 04d0 c44901c5 4901c648 03842408 01000048 .I..I..H..$....H - 04e0 837c24f8 00488944 24a84889 4c24a048 .|$..H.D$.H.L$.H - 04f0 8b4424b0 0f8f0e01 00004883 7c24d000 .D$.......H.|$.. - 0500 74134839 4424900f 8d130f00 004c03bc t.H9D$.......L.. - 0510 24300100 00488344 24901048 8b7c24f0 $0...H.D$..H.|$. - 0520 48836c24 e0804801 7c24e848 8b442490 H.l$..H.|$.H.D$. - 0530 483b4424 080f844d 18000048 8b5c24b0 H;D$...M...H.\$. - 0540 48395c24 900f8df5 feffff48 8b4424e8 H9\$.......H.D$. - 0550 488b8c24 e0000000 488b7424 304801c1 H..$....H.t$0H.. - 0560 48894c24 b8488b8c 24f00000 00488b7c H.L$.H..$....H.| - 0570 24404801 c148894c 24984c8b 4424504c $@H..H.L$.L.D$PL - 0580 8b4c2460 4c8b5424 704c8b9c 24800000 .L$`L.T$pL..$... - 0590 00488b9c 24900000 00488bac 24a00000 .H..$....H..$... - 05a0 004c8ba4 24b00000 004c8bac 24c00000 .L..$....L..$... - 05b0 004c8bb4 24d00000 00488b8c 24000100 .L..$....H..$... - 05c0 004801c6 4801c148 01c74901 c04901c1 .H..H..H..I..I.. - 05d0 4901c249 01c34801 c34801c5 4901c449 I..I..H..H..I..I - 05e0 01c54901 c6480384 24100100 0048837c ..I..H..$....H.| - 05f0 24f80048 894424a8 48894c24 a0488b44 $..H.D$.H.L$.H.D - 0600 24b00f8e f2feffff 488b5424 b04c89bc $.......H.T$.L.. - 0610 24900100 00498d87 00080000 48895424 $....I......H.T$ - 0620 884c8b7c 24b8eb66 0f1f8400 00000000 .L.|$..f........ - 0630 48836c24 98804883 6c24a080 48836c24 H.l$..H.l$..H.l$ - 0640 a8804883 ee804883 ef804983 e8804983 ..H...H...I...I. - 0650 e9804983 ea804983 eb804883 eb804883 ..I...I...H...H. - 0660 ed804983 ec804983 ed804983 ee804983 ..I...I...I...I. - 0670 ef804883 44248810 48050008 0000488b ..H.D$..H.....H. - 0680 4c248848 3b4c24c8 0f846a0d 0000488d L$.H;L$...j...H. - 0690 9000f8ff ff488954 24b8488b 54248848 .....H.T$.H.T$.H - 06a0 39542490 7c8a0f8f 3c0c0000 c5fb1180 9T$.|...<....... - 06b0 00f8ffff c5fb104e 084883ef 80c5fb11 .......N.H...... - 06c0 8808f8ff ffc5fb10 4e104983 e880c5fb ........N.I..... - 06d0 118810f8 ffffc5fb 104e1849 83e980c5 .........N.I.... - 06e0 fb118818 f8ffffc5 fb104e20 4983ea80 ..........N I... - 06f0 c5fb1188 20f8ffff c5fb104e 284983eb .... ......N(I.. - 0700 80c5fb11 8828f8ff ffc5fb10 4e304883 .....(......N0H. - 0710 eb80c5fb 118830f8 ffffc5fb 104e3848 ......0......N8H - 0720 83ed80c5 fb118838 f8ffffc5 fb104e40 .......8......N@ - 0730 4983ec80 c5fb1188 40f8ffff c5fb104e I.......@......N - 0740 484983ed 80c5fb11 8848f8ff ffc5fb10 HI.......H...... - 0750 4e504983 ee80c5fb 118850f8 ffffc5fb NPI.......P..... - 0760 104e5849 83ef80c5 fb118858 f8ffffc5 .NXI.......X.... - 0770 fb104e60 4883ee80 c5fb1188 60f8ffff ..N`H.......`... - 0780 c5fb104e e8c5fb11 8868f8ff ffc5fb10 ...N.....h...... - 0790 4ef0c5fb 118870f8 ffffc5fb 104ef848 N.....p......N.H - 07a0 c78080f8 ffff0000 0000c5fb 118878f8 ..............x. - 07b0 ffffc5fb 118088f8 ffffc5fb 104f90c5 .............O.. - 07c0 fb118890 f8ffffc5 fb104f98 c5fb1188 ..........O..... - 07d0 98f8ffff c5fb104f a0c5fb11 88a0f8ff .......O........ - 07e0 ffc5fb10 4fa8c5fb 1188a8f8 ffffc5fb ....O........... - 07f0 104fb0c5 fb1188b0 f8ffffc5 fb104fb8 .O............O. - 0800 c5fb1188 b8f8ffff c5fb104f c0c5fb11 ...........O.... - 0810 88c0f8ff ffc5fb10 4fc8c5fb 1188c8f8 ........O....... - 0820 ffffc5fb 104fd0c5 fb1188d0 f8ffffc5 .....O.......... - 0830 fb104fd8 c5fb1188 d8f8ffff c5fb104f ..O............O - 0840 e0c5fb11 88e0f8ff ffc5fb10 4fe8c5fb ............O... - 0850 1188e8f8 ffffc5fb 104ff0c5 fb1188f0 .........O...... - 0860 f8ffffc5 fb104ff8 48c78000 f9ffff00 ......O.H....... - 0870 00000048 c78008f9 ffff0000 0000c5fb ...H............ - 0880 1188f8f8 ffffc5fb 118010f9 ffffc4c1 ................ - 0890 7b104898 c5fb1188 18f9ffff c4c17b10 {.H...........{. - 08a0 48a0c5fb 118820f9 ffffc4c1 7b1048a8 H..... .....{.H. - 08b0 c5fb1188 28f9ffff c4c17b10 48b0c5fb ....(.....{.H... - 08c0 118830f9 ffffc4c1 7b1048b8 c5fb1188 ..0.....{.H..... - 08d0 38f9ffff c4c17b10 48c0c5fb 118840f9 8.....{.H.....@. - 08e0 ffffc4c1 7b1048c8 c5fb1188 48f9ffff ....{.H.....H... - 08f0 c4c17b10 48d0c5fb 118850f9 ffffc4c1 ..{.H.....P..... - 0900 7b1048d8 c5fb1188 58f9ffff c4c17b10 {.H.....X.....{. - 0910 48e0c5fb 118860f9 ffffc4c1 7b1048e8 H.....`.....{.H. - 0920 c5fb1188 68f9ffff c4c17b10 48f0c5fb ....h.....{.H... - 0930 118870f9 ffffc4c1 7b1048f8 48c78080 ..p.....{.H.H... - 0940 f9ffff00 00000048 c78088f9 ffff0000 .......H........ - 0950 000048c7 8090f9ff ff000000 00c5fb11 ..H............. - 0960 8878f9ff ffc5fb11 8098f9ff ffc4c17b .x.............{ - 0970 1049a0c5 fb1188a0 f9ffffc4 c17b1049 .I...........{.I - 0980 a8c5fb11 88a8f9ff ffc4c17b 1049b0c5 ...........{.I.. - 0990 fb1188b0 f9ffffc4 c17b1049 b8c5fb11 .........{.I.... - 09a0 88b8f9ff ffc4c17b 1049c0c5 fb1188c0 .......{.I...... - 09b0 f9ffffc4 c17b1049 c8c5fb11 88c8f9ff .....{.I........ - 09c0 ffc4c17b 1049d0c5 fb1188d0 f9ffffc4 ...{.I.......... - 09d0 c17b1049 d8c5fb11 88d8f9ff ffc4c17b .{.I...........{ - 09e0 1049e0c5 fb1188e0 f9ffffc4 c17b1049 .I...........{.I - 09f0 e8c5fb11 88e8f9ff ffc4c17b 1049f0c5 ...........{.I.. - 0a00 fb1188f0 f9ffffc4 c17b1049 f848c780 .........{.I.H.. - 0a10 00faffff 00000000 48c78008 faffff00 ........H....... - 0a20 00000048 c78010fa ffff0000 000048c7 ...H..........H. - 0a30 8018faff ff000000 00c5fb11 88f8f9ff ................ - 0a40 ffc5fb11 8020faff ffc4c17b 104aa8c5 ..... .....{.J.. - 0a50 fb118828 faffffc4 c17b104a b0c5fb11 ...(.....{.J.... - 0a60 8830faff ffc4c17b 104ab8c5 fb118838 .0.....{.J.....8 - 0a70 faffffc4 c17b104a c0c5fb11 8840faff .....{.J.....@.. - 0a80 ffc4c17b 104ac8c5 fb118848 faffffc4 ...{.J.....H.... - 0a90 c17b104a d0c5fb11 8850faff ffc4c17b .{.J.....P.....{ - 0aa0 104ad8c5 fb118858 faffffc4 c17b104a .J.....X.....{.J - 0ab0 e0c5fb11 8860faff ffc4c17b 104ae8c5 .....`.....{.J.. - 0ac0 fb118868 faffffc4 c17b104a f0c5fb11 ...h.....{.J.... - 0ad0 8870faff ffc4c17b 104af848 c78080fa .p.....{.J.H.... - 0ae0 ffff0000 000048c7 8088faff ff000000 ......H......... - 0af0 0048c780 90faffff 00000000 48c78098 .H..........H... - 0b00 faffff00 00000048 c780a0fa ffff0000 .......H........ - 0b10 0000c5fb 118878fa ffffc5fb 1180a8fa ......x......... - 0b20 ffffc4c1 7b104bb0 c5fb1188 b0faffff ....{.K......... - 0b30 c4c17b10 4bb8c5fb 1188b8fa ffffc4c1 ..{.K........... - 0b40 7b104bc0 c5fb1188 c0faffff c4c17b10 {.K...........{. - 0b50 4bc8c5fb 1188c8fa ffffc4c1 7b104bd0 K...........{.K. - 0b60 c5fb1188 d0faffff c4c17b10 4bd8c5fb ..........{.K... - 0b70 1188d8fa ffffc4c1 7b104be0 c5fb1188 ........{.K..... - 0b80 e0faffff c4c17b10 4be8c5fb 1188e8fa ......{.K....... - 0b90 ffffc4c1 7b104bf0 c5fb1188 f0faffff ....{.K......... - 0ba0 c4c17b10 4bf848c7 8000fbff ff000000 ..{.K.H......... - 0bb0 0048c780 08fbffff 00000000 48c78010 .H..........H... - 0bc0 fbffff00 00000048 c78018fb ffff0000 .......H........ - 0bd0 000048c7 8020fbff ff000000 0048c780 ..H.. .......H.. - 0be0 28fbffff 00000000 c5fb1188 f8faffff (............... - 0bf0 c5fb1180 30fbffff c5fb104b b8c5fb11 ....0......K.... - 0c00 8838fbff ffc5fb10 4bc0c5fb 118840fb .8......K.....@. - 0c10 ffffc5fb 104bc8c5 fb118848 fbffffc5 .....K.....H.... /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 ab2c0000 00420e10 8f02420e .....,...B....B. + 0020 00000000 04070000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e900303 79260a0e ..A.8..G....y&.. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e084a 0b000000 D..J.... + 0040 8606410e 38830744 0e500362 050a0e38 ..A.8..D.P.b...8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08440b 00000000 ..D..... /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_SKYLAKEX.o (disasm) @@ -12,1637 +12,326 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,(%rsp) - mov %rdx,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) mov %rcx,-offset(%rsp) - mov %r8,-offset(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov %rsi,(%rsp) + mov offset(%rsp),%rbx test %rsi,%rsi jle - mov %r8,%rbx - imul %rcx,%rbx - mov %r8,%rdi mov %rcx,%rax - lea (%rcx,%rbx,1),%r11 - lea (%r11,%rcx,1),%rsi - lea (%rcx,%rsi,1),%r9 - lea (%r9,%rcx,1),%r8 - mov %rsi,-offset(%rsp) - lea (%rcx,%r8,1),%rsi - mov %rsi,-offset(%rsp) - add %rcx,%rsi - lea (%rcx,%rsi,1),%rcx - lea (%rax,%rcx,1),%rdx - lea (%rax,%rdx,1),%rbp - lea (%rax,%rbp,1),%r12 - lea (%rax,%r12,1),%r13 - lea (%rax,%r13,1),%r14 - lea (%rax,%r14,1),%r10 - mov %r10,-offset(%rsp) - mov (%rsp),%r10 - sar $something,%r10 - mov %r10,-offset(%rsp) - lea offset(,%rax,8),%r10 - mov %r10,offset(%rsp) - mov (%rsp),%r10 + imul %r8,%rax + mov %rsi,%r14 + mov %rdi,%r10 + add %r9,%rax + lea (%rdx,%rax,8),%r13 + mov %rcx,%rax + imul %r9,%rax + mov %rcx,%rdi + mov %rcx,%rbp + add %r8,%rax + lea (%rdx,%rax,8),%r12 + lea (%r9,%r14,4),%rax + mov %rax,-offset(%rsp) + mov %rcx,%rax + neg %rax + mov %rcx,%rsi + lea offset(,%rax,8),%rcx + mov %rcx,%rax + mov %rcx,-offset(%rsp) + lea offset(%r9),%rdx + neg %rcx + imul %r9,%rax + imul %rcx,%rdx + mov %r10,%r15 + sar $something,%r15 + add %rax,%rdx + mov %rdx,-offset(%rsp) + lea offset(%r9),%rdx + imul %rcx,%rdx + shl $something,%rsi + mov %rsi,offset(%rsp) + add %rax,%rdx + mov %rdx,-offset(%rsp) + lea offset(%r9),%rdx + imul %rcx,%rdx + mov %r10,%rsi + mov %rsi,%r14 + add %rdx,%rax + mov %rax,-offset(%rsp) + mov %rdi,%rax shl $something,%rax - and $something,%r10d - mov %r10,-offset(%rsp) - shl $something,%r10 mov %rax,-offset(%rsp) - mov %r10,offset(%rsp) - mov -offset(%rsp),%rax - mov offset(%rsp),%r10 - imul -offset(%rsp),%rax - shl $something,%r10 - add -offset(%rsp),%r10 - mov %r10,offset(%rsp) - mov offset(%rsp),%r10 - add %rdi,%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - inc %rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov %rdi,offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov %rdi,offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,8),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add %rax,%rbx - add %rax,%r11 - mov %r10,%rdi - lea (%r10,%rbx,8),%rbx - lea (%r10,%r11,8),%r11 - mov -offset(%rsp),%r10 - mov %rbx,offset(%rsp) - mov %rax,%rbx - add %rbx,%r10 - mov %r11,offset(%rsp) - add %rbx,%r9 /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_SKYLAKEX.o (objdump) @@ -2,718 +2,116 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ec580100 AWAVAUATUSH..X.. - 0010 00488974 241048c1 fe044889 3c244889 .H.t$.H...H.<$H. - 0020 54242048 894c24d8 4c894424 b04c894c T$ H.L$.L.D$.L.L - 0030 24c04889 b4243801 00004c8b bc249001 $.H..$8...L..$.. - 0040 00004885 f60f8e56 1d00004c 89c3480f ..H....V...L..H. - 0050 afd94c89 c74889c8 4c8d1c19 498d340b ..L..H..L...I.4. - 0060 4c8d0c31 4d8d0409 48897424 984a8d34 L..1M...H.t$.J.4 - 0070 01488974 24884801 ce488d0c 31488d14 .H.t$.H..H..1H.. - 0080 08488d2c 104c8d24 284e8d2c 204e8d34 .H.,.L.$(N., N.4 - 0090 284e8d14 304c8954 24904c8b 142449c1 (N..0L.T$.L..$I. - 00a0 fa044c89 5424f84c 8d14c500 0000004c ..L.T$.L.......L - 00b0 89942418 0100004c 8b142448 c1e00741 ..$....L..$H...A - 00c0 83e20f4c 895424d0 49c1e207 48894424 ...L.T$.I...H.D$ - 00d0 f04c8994 24300100 00488b44 24d84c8b .L..$0...H.D$.L. - 00e0 94243801 0000480f af4424c0 49c1e204 .$8...H..D$.I... - 00f0 4c035424 c04c8954 24084c8b 54242048 L.T$.L.T$.L.T$ H - 0100 01f8498d 3cc2488b 4424c048 897c2430 ..I.<.H.D$.H.|$0 - 0110 48ffc048 0faf4424 d8480344 24b0498d H..H..D$.H.D$.I. - 0120 3cc2488b 4424c048 897c2440 4883c002 <.H.D$.H.|$@H... - 0130 480faf44 24d84803 4424b049 8d3cc248 H..D$.H.D$.I.<.H - 0140 8b4424c0 48897c24 504883c0 03480faf .D$.H.|$PH...H.. - 0150 4424d848 034424b0 498d3cc2 488b4424 D$.H.D$.I.<.H.D$ - 0160 c048897c 24604883 c004480f af4424d8 .H.|$`H...H..D$. - 0170 48034424 b0498d3c c248897c 2470488b H.D$.I.<.H.|$pH. - 0180 4424c048 83c00548 0faf4424 d8480344 D$.H...H..D$.H.D - 0190 24b0498d 3cc2488b 4424c048 89bc2480 $.I.<.H.D$.H..$. - 01a0 00000048 83c00648 0faf4424 d8480344 ...H...H..D$.H.D - 01b0 24b0498d 3cc2488b 4424c048 89bc2490 $.I.<.H.D$.H..$. - 01c0 00000048 83c00748 0faf4424 d8480344 ...H...H..D$.H.D - 01d0 24b0498d 3cc2488b 4424c048 89bc24a0 $.I.<.H.D$.H..$. - 01e0 00000048 83c00848 0faf4424 d8480344 ...H...H..D$.H.D - 01f0 24b0498d 3cc2488b 4424c048 89bc24b0 $.I.<.H.D$.H..$. - 0200 00000048 83c00948 0faf4424 d8480344 ...H...H..D$.H.D - 0210 24b0498d 3cc2488b 4424c048 89bc24c0 $.I.<.H.D$.H..$. - 0220 00000048 83c00a48 0faf4424 d8480344 ...H...H..D$.H.D - 0230 24b0498d 3cc2488b 4424c048 89bc24d0 $.I.<.H.D$.H..$. - 0240 00000048 83c00b48 0faf4424 d8480344 ...H...H..D$.H.D - 0250 24b0498d 3cc2488b 4424c048 89bc24e0 $.I.<.H.D$.H..$. - 0260 00000048 83c00c48 0faf4424 d8480344 ...H...H..D$.H.D - 0270 24b0498d 3cc24889 bc24f000 0000488b $.I.<.H..$....H. - 0280 4424c048 83c00d48 0faf4424 d8480344 D$.H...H..D$.H.D - 0290 24b0498d 3cc2488b 4424c048 89bc2400 $.I.<.H.D$.H..$. - 02a0 01000048 83c00e48 0faf4424 d8480344 ...H...H..D$.H.D - 02b0 24b0498d 3cc2488b 4424c048 89bc2410 $.I.<.H.D$.H..$. - 02c0 01000048 01c34901 c34c89d7 498d1cda ...H..I..L..I... - 02d0 4f8d1cda 4c8b5424 9848895c 24284889 O...L.T$.H.\$(H. - 02e0 c34901da 4c895c24 384901d9 4e8d1cd7 .I..L.\$8I..N... - 02f0 4801d948 8d0ccf48 01da4c89 5c244849 H..H...H..L.\$HI - 0300 01d84e8d 1ccf4c89 5c245848 898c2498 ..N...L.\$XH..$. - 0310 0000004e 8d1cc748 8d0cd748 01dd488b ...N...H...H..H. - 0320 5424904c 895c2468 48898c24 a8000000 T$.L.\$hH..$.... - 0330 4c8b5c24 88488d0c ef4901dc 48898c24 L.\$.H...I..H..$ - 0340 b8000000 4901dd4a 8d0ce748 01de4889 ....I..J...H..H. - 0350 8c24c800 00004901 db4a8d0c ef4901de .$....I..J...I.. - 0360 4889d04e 8d1cdf48 035424d8 48898c24 H..N...H.T$.H..$ - 0370 d8000000 4801d84a 8d0cf74c 895c2478 ....H..J...L.\$x - 0380 48898c24 e8000000 4c8d1cf7 488d0cc7 H..$....L...H... - 0390 488b3424 4889d048 01d8488d 14c7488b H.4$H..H..H...H. - 03a0 7c24b048 89f04883 e0f04801 f8488944 |$.H..H...H..H.D - 03b0 24c8488b 4424f848 89942408 01000048 $.H.D$.H..$....H - 03c0 89c248c1 e0044801 f848c1e2 0b4c899c ..H...H..H...L.. - 03d0 24880000 0048898c 24f80000 00488994 $....H..$....H.. - 03e0 24200100 00488984 24280100 004889f0 $ ...H..$(...H.. - 03f0 83e00e48 89842440 01000048 89f083e0 ...H..$@...H.... - 0400 0c83e608 48895c24 9048c744 24e80000 ....H.\$.H.D$... - 0410 000048c7 4424e000 00000048 89842448 ..H.D$.....H..$H - 0420 01000048 89b42450 010000c5 fb100500 ...H..$P........ - 0430 000000e9 03010000 0f1f8400 00000000 ................ - 0440 488b4424 e0488b8c 24d80000 00488b74 H.D$.H..$....H.t - 0450 24284801 c148894c 24b8488b 8c24e800 $(H..H.L$.H..$.. - 0460 0000488b 7c243848 01c14889 4c24984c ..H.|$8H..H.L$.L - 0470 8b442448 4c8b4c24 584c8b54 24684c8b .D$HL.L$XL.T$hL. - 0480 5c247848 8b9c2488 00000048 8bac2498 \$xH..$....H..$. - 0490 0000004c 8ba424a8 0000004c 8bac24b8 ...L..$....L..$. - 04a0 0000004c 8bb424c8 00000048 8b8c24f8 ...L..$....H..$. - 04b0 00000048 01c64801 c14801c7 4901c049 ...H..H..H..I..I - 04c0 01c14901 c24901c3 4801c348 01c54901 ..I..I..H..H..I. - 04d0 c44901c5 4901c648 03842408 01000048 .I..I..H..$....H - 04e0 837c24f8 00488944 24a84889 4c24a048 .|$..H.D$.H.L$.H - 04f0 8b4424b0 0f8f0e01 00004883 7c24d000 .D$.......H.|$.. - 0500 74134839 4424900f 8d130f00 004c03bc t.H9D$.......L.. - 0510 24300100 00488344 24901048 8b7c24f0 $0...H.D$..H.|$. - 0520 48836c24 e0804801 7c24e848 8b442490 H.l$..H.|$.H.D$. - 0530 483b4424 080f844d 18000048 8b5c24b0 H;D$...M...H.\$. - 0540 48395c24 900f8df5 feffff48 8b4424e8 H9\$.......H.D$. - 0550 488b8c24 e0000000 488b7424 304801c1 H..$....H.t$0H.. - 0560 48894c24 b8488b8c 24f00000 00488b7c H.L$.H..$....H.| - 0570 24404801 c148894c 24984c8b 4424504c $@H..H.L$.L.D$PL - 0580 8b4c2460 4c8b5424 704c8b9c 24800000 .L$`L.T$pL..$... - 0590 00488b9c 24900000 00488bac 24a00000 .H..$....H..$... - 05a0 004c8ba4 24b00000 004c8bac 24c00000 .L..$....L..$... - 05b0 004c8bb4 24d00000 00488b8c 24000100 .L..$....H..$... - 05c0 004801c6 4801c148 01c74901 c04901c1 .H..H..H..I..I.. - 05d0 4901c249 01c34801 c34801c5 4901c449 I..I..H..H..I..I - 05e0 01c54901 c6480384 24100100 0048837c ..I..H..$....H.| - 05f0 24f80048 894424a8 48894c24 a0488b44 $..H.D$.H.L$.H.D - 0600 24b00f8e f2feffff 488b5424 b04c89bc $.......H.T$.L.. - 0610 24900100 00498d87 00080000 48895424 $....I......H.T$ - 0620 884c8b7c 24b8eb66 0f1f8400 00000000 .L.|$..f........ - 0630 48836c24 98804883 6c24a080 48836c24 H.l$..H.l$..H.l$ - 0640 a8804883 ee804883 ef804983 e8804983 ..H...H...I...I. - 0650 e9804983 ea804983 eb804883 eb804883 ..I...I...H...H. - 0660 ed804983 ec804983 ed804983 ee804983 ..I...I...I...I. - 0670 ef804883 44248810 48050008 0000488b ..H.D$..H.....H. - 0680 4c248848 3b4c24c8 0f846a0d 0000488d L$.H;L$...j...H. - 0690 9000f8ff ff488954 24b8488b 54248848 .....H.T$.H.T$.H - 06a0 39542490 7c8a0f8f 3c0c0000 c5fb1180 9T$.|...<....... - 06b0 00f8ffff c5fb104e 084883ef 80c5fb11 .......N.H...... - 06c0 8808f8ff ffc5fb10 4e104983 e880c5fb ........N.I..... - 06d0 118810f8 ffffc5fb 104e1849 83e980c5 .........N.I.... - 06e0 fb118818 f8ffffc5 fb104e20 4983ea80 ..........N I... - 06f0 c5fb1188 20f8ffff c5fb104e 284983eb .... ......N(I.. - 0700 80c5fb11 8828f8ff ffc5fb10 4e304883 .....(......N0H. - 0710 eb80c5fb 118830f8 ffffc5fb 104e3848 ......0......N8H - 0720 83ed80c5 fb118838 f8ffffc5 fb104e40 .......8......N@ - 0730 4983ec80 c5fb1188 40f8ffff c5fb104e I.......@......N - 0740 484983ed 80c5fb11 8848f8ff ffc5fb10 HI.......H...... - 0750 4e504983 ee80c5fb 118850f8 ffffc5fb NPI.......P..... - 0760 104e5849 83ef80c5 fb118858 f8ffffc5 .NXI.......X.... - 0770 fb104e60 4883ee80 c5fb1188 60f8ffff ..N`H.......`... - 0780 c5fb104e e8c5fb11 8868f8ff ffc5fb10 ...N.....h...... - 0790 4ef0c5fb 118870f8 ffffc5fb 104ef848 N.....p......N.H - 07a0 c78080f8 ffff0000 0000c5fb 118878f8 ..............x. - 07b0 ffffc5fb 118088f8 ffffc5fb 104f90c5 .............O.. - 07c0 fb118890 f8ffffc5 fb104f98 c5fb1188 ..........O..... - 07d0 98f8ffff c5fb104f a0c5fb11 88a0f8ff .......O........ - 07e0 ffc5fb10 4fa8c5fb 1188a8f8 ffffc5fb ....O........... - 07f0 104fb0c5 fb1188b0 f8ffffc5 fb104fb8 .O............O. - 0800 c5fb1188 b8f8ffff c5fb104f c0c5fb11 ...........O.... - 0810 88c0f8ff ffc5fb10 4fc8c5fb 1188c8f8 ........O....... - 0820 ffffc5fb 104fd0c5 fb1188d0 f8ffffc5 .....O.......... - 0830 fb104fd8 c5fb1188 d8f8ffff c5fb104f ..O............O - 0840 e0c5fb11 88e0f8ff ffc5fb10 4fe8c5fb ............O... - 0850 1188e8f8 ffffc5fb 104ff0c5 fb1188f0 .........O...... - 0860 f8ffffc5 fb104ff8 48c78000 f9ffff00 ......O.H....... - 0870 00000048 c78008f9 ffff0000 0000c5fb ...H............ - 0880 1188f8f8 ffffc5fb 118010f9 ffffc4c1 ................ - 0890 7b104898 c5fb1188 18f9ffff c4c17b10 {.H...........{. - 08a0 48a0c5fb 118820f9 ffffc4c1 7b1048a8 H..... .....{.H. - 08b0 c5fb1188 28f9ffff c4c17b10 48b0c5fb ....(.....{.H... - 08c0 118830f9 ffffc4c1 7b1048b8 c5fb1188 ..0.....{.H..... - 08d0 38f9ffff c4c17b10 48c0c5fb 118840f9 8.....{.H.....@. - 08e0 ffffc4c1 7b1048c8 c5fb1188 48f9ffff ....{.H.....H... - 08f0 c4c17b10 48d0c5fb 118850f9 ffffc4c1 ..{.H.....P..... - 0900 7b1048d8 c5fb1188 58f9ffff c4c17b10 {.H.....X.....{. - 0910 48e0c5fb 118860f9 ffffc4c1 7b1048e8 H.....`.....{.H. - 0920 c5fb1188 68f9ffff c4c17b10 48f0c5fb ....h.....{.H... - 0930 118870f9 ffffc4c1 7b1048f8 48c78080 ..p.....{.H.H... - 0940 f9ffff00 00000048 c78088f9 ffff0000 .......H........ - 0950 000048c7 8090f9ff ff000000 00c5fb11 ..H............. - 0960 8878f9ff ffc5fb11 8098f9ff ffc4c17b .x.............{ - 0970 1049a0c5 fb1188a0 f9ffffc4 c17b1049 .I...........{.I - 0980 a8c5fb11 88a8f9ff ffc4c17b 1049b0c5 ...........{.I.. - 0990 fb1188b0 f9ffffc4 c17b1049 b8c5fb11 .........{.I.... - 09a0 88b8f9ff ffc4c17b 1049c0c5 fb1188c0 .......{.I...... - 09b0 f9ffffc4 c17b1049 c8c5fb11 88c8f9ff .....{.I........ - 09c0 ffc4c17b 1049d0c5 fb1188d0 f9ffffc4 ...{.I.......... - 09d0 c17b1049 d8c5fb11 88d8f9ff ffc4c17b .{.I...........{ - 09e0 1049e0c5 fb1188e0 f9ffffc4 c17b1049 .I...........{.I - 09f0 e8c5fb11 88e8f9ff ffc4c17b 1049f0c5 ...........{.I.. - 0a00 fb1188f0 f9ffffc4 c17b1049 f848c780 .........{.I.H.. - 0a10 00faffff 00000000 48c78008 faffff00 ........H....... - 0a20 00000048 c78010fa ffff0000 000048c7 ...H..........H. - 0a30 8018faff ff000000 00c5fb11 88f8f9ff ................ - 0a40 ffc5fb11 8020faff ffc4c17b 104aa8c5 ..... .....{.J.. - 0a50 fb118828 faffffc4 c17b104a b0c5fb11 ...(.....{.J.... - 0a60 8830faff ffc4c17b 104ab8c5 fb118838 .0.....{.J.....8 - 0a70 faffffc4 c17b104a c0c5fb11 8840faff .....{.J.....@.. - 0a80 ffc4c17b 104ac8c5 fb118848 faffffc4 ...{.J.....H.... - 0a90 c17b104a d0c5fb11 8850faff ffc4c17b .{.J.....P.....{ - 0aa0 104ad8c5 fb118858 faffffc4 c17b104a .J.....X.....{.J - 0ab0 e0c5fb11 8860faff ffc4c17b 104ae8c5 .....`.....{.J.. - 0ac0 fb118868 faffffc4 c17b104a f0c5fb11 ...h.....{.J.... - 0ad0 8870faff ffc4c17b 104af848 c78080fa .p.....{.J.H.... - 0ae0 ffff0000 000048c7 8088faff ff000000 ......H......... - 0af0 0048c780 90faffff 00000000 48c78098 .H..........H... - 0b00 faffff00 00000048 c780a0fa ffff0000 .......H........ - 0b10 0000c5fb 118878fa ffffc5fb 1180a8fa ......x......... - 0b20 ffffc4c1 7b104bb0 c5fb1188 b0faffff ....{.K......... - 0b30 c4c17b10 4bb8c5fb 1188b8fa ffffc4c1 ..{.K........... - 0b40 7b104bc0 c5fb1188 c0faffff c4c17b10 {.K...........{. - 0b50 4bc8c5fb 1188c8fa ffffc4c1 7b104bd0 K...........{.K. - 0b60 c5fb1188 d0faffff c4c17b10 4bd8c5fb ..........{.K... - 0b70 1188d8fa ffffc4c1 7b104be0 c5fb1188 ........{.K..... - 0b80 e0faffff c4c17b10 4be8c5fb 1188e8fa ......{.K....... - 0b90 ffffc4c1 7b104bf0 c5fb1188 f0faffff ....{.K......... - 0ba0 c4c17b10 4bf848c7 8000fbff ff000000 ..{.K.H......... - 0bb0 0048c780 08fbffff 00000000 48c78010 .H..........H... - 0bc0 fbffff00 00000048 c78018fb ffff0000 .......H........ - 0bd0 000048c7 8020fbff ff000000 0048c780 ..H.. .......H.. - 0be0 28fbffff 00000000 c5fb1188 f8faffff (............... - 0bf0 c5fb1180 30fbffff c5fb104b b8c5fb11 ....0......K.... - 0c00 8838fbff ffc5fb10 4bc0c5fb 118840fb .8......K.....@. - 0c10 ffffc5fb 104bc8c5 fb118848 fbffffc5 .....K.....H.... /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iltucopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 ab2c0000 00420e10 8f02420e .....,...B....B. + 0020 00000000 04070000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e900303 79260a0e ..A.8..G....y&.. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e084a 0b000000 D..J.... + 0040 8606410e 38830744 0e500362 050a0e38 ..A.8..D.P.b...8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08440b 00000000 ..D..... /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_COOPERLAKE.o (disasm) @@ -12,1523 +12,341 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) - mov %r9,offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,(%rsp) + mov offset(%rsp),%rbx test %rsi,%rsi jle + mov %rcx,%rax + imul %r8,%rax + mov %rdx,%r11 + mov %rsi,%r14 + mov %rdi,%r15 + mov %rdi,%rsi + add %r9,%rax + mov %rcx,%rdi + mov %rcx,%rbp + mov %rsi,%r10 + mov %rsi,%rcx + lea (%r11,%rax,8),%r12 + mov %rdi,%rsi + lea (%r9,%r14,4),%rax + imul %r9,%rsi + mov %rax,-offset(%rsp) mov %rdi,%rax - sar $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - mov %r8,%r12 - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - imul %rcx,%r12 - and $something,%eax - mov %rax,offset(%rsp) shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - shl $something,%rax - lea (%rcx,%rbx,1),%r11 - add offset(%rsp),%rax - lea (%rcx,%r11,1),%r10 - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%r10,%rcx,1),%r9 - add offset(%rsp),%r12 - lea (%r9,%rcx,1),%r8 - lea (%rax,%r12,8),%r12 - lea (%r8,%rcx,1),%rdi - mov %r12,offset(%rsp) - mov offset(%rsp),%r12 - lea (%rdi,%rcx,1),%rsi - mov %rcx,%r13 - add %r12,%rbp - lea (%rsi,%rcx,1),%rcx - lea (%rcx,%r13,1),%rdx - lea (%rax,%rbp,8),%rbp - lea (%rdx,%r13,1),%r15 - mov %rbp,offset(%rsp) - mov %r12,%rbp - mov %r15,-offset(%rsp) - add %rbp,%r11 - lea (%rax,%r11,8),%r11 - add %rbp,%rsi - add %rbp,%r9 - add %r12,%rbx - lea (%rax,%r9,8),%r9 - add %rbp,%rcx - mov %r11,offset(%rsp) - add %rbp,%r10 - lea (%rax,%rsi,8),%r11 - add %rbp,%r8 - add %rbp,%rdi - add %rbp,%rdx - mov %rax,%r12 - lea (%rax,%rbx,8),%rbx - lea (%rax,%rdx,8),%rdx - mov %r9,offset(%rsp) - mov %r11,offset(%rsp) - lea (%rax,%r10,8),%r10 - lea (%rax,%rcx,8),%r11 - lea (%rax,%r8,8),%r9 - lea (%rax,%rdi,8),%rdi - mov -offset(%rsp),%rax - lea (%r15,%r13,1),%r14 - add %rbp,%rax - lea (%r14,%r13,1),%r15 - mov %rdx,offset(%rsp) - add %rbp,%r14 - lea (%r12,%rax,8),%rdx - mov offset(%rsp),%rsi - add %r15,%r13 - mov %rdx,offset(%rsp) - add %rbp,%r15 - lea (%r12,%r14,8),%rdx - mov %rdx,offset(%rsp) - lea offset(%rbp,%r13,1),%rax - lea (%r12,%r15,8),%rdx - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - lea offset(%r13,%rsi,1),%rax - add %rbp,%rax - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - mov %rbp,%rax - imul %rsi,%rax - mov offset(%rsp),%rcx - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rbx,offset(%rsp) - mov %r10,offset(%rsp) - add %rcx,%rax - mov %r9,offset(%rsp) - mov %rdi,offset(%rsp) - mov %r11,offset(%rsp) - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - mov %rbp,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_COOPERLAKE.o (objdump) @@ -2,936 +2,120 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 044889bc .H..$....H...H.. - 0020 24800000 00488994 24a00000 0048898c $....H..$....H.. - 0030 24900000 004c8944 24404c89 4c246048 $....L.D$@L.L$`H - 0040 89b424c0 01000048 85f60f8e 4e180000 ..$....H....N... - 0050 4889f848 c1f80448 89442478 488b8424 H..H...H.D$xH..$ - 0060 90000000 4d89c448 c1e00748 89442448 ....M..H...H.D$H - 0070 488b8424 80000000 4c0fafe1 83e00f48 H..$....L......H - 0080 89442458 48c1e007 48898424 b8010000 .D$XH...H..$.... - 0090 488b8424 c0010000 4a8d2c21 488d1c29 H..$....J.,!H..) - 00a0 48c1e004 4c8d1c19 48034424 604e8d14 H...L...H.D$`N.. - 00b0 19488984 24880000 00488b84 24a00000 .H..$....H..$... - 00c0 004d8d0c 0a4c0364 24604d8d 04094e8d .M...L.d$`M...N. - 00d0 24e0498d 3c084c89 a424f800 00004c8b $.I.<.L..$....L. - 00e0 64246048 8d340f49 89cd4c01 e5488d0c d$`H.4.I..L..H.. - 00f0 0e4a8d14 29488d2c e84e8d3c 2a4889ac .J..)H.,.N.<*H.. - 0100 24e00000 004c89e5 4c897c24 884901eb $....L..L.|$.I.. - 0110 4e8d1cd8 4801ee49 01e94c01 e34e8d0c N...H..I..L..N.. - 0120 c84801e9 4c899c24 e8000000 4901ea4c .H..L..$....I..L - 0130 8d1cf049 01e84801 ef4801ea 4989c448 ...I..H..H..I..H - 0140 8d1cd848 8d14d04c 898c24b8 0000004c ...H...L..$....L - 0150 899c2430 0100004e 8d14d04c 8d1cc84e ..$0...N...L...N - 0160 8d0cc048 8d3cf848 8b442488 4f8d342f ...H.<.H.D$.O.4/ - 0170 4801e84f 8d3c2e48 89942450 01000049 H..O.<.H..$P...I - 0180 01ee498d 14c4488b b4249000 00004d01 ..I...H..$....M. - 0190 fd488994 24600100 004901ef 4b8d14f4 .H..$`...I..K... - 01a0 48899424 70010000 4a8d442d 004b8d14 H..$p...J.D-.K.. - 01b0 fc488994 24800100 00498d14 c4498d44 .H..$....I...I.D - 01c0 35004801 e8488994 24900100 00498d14 5.H..H..$....I.. - 01d0 c44889e8 480fafc6 488b4c24 40488994 .H..H...H.L$@H.. - 01e0 24a00100 004801c8 498d14c4 488d4501 $....H..I...H.E. - 01f0 480fafc6 48899c24 d8000000 4c899424 H...H..$....L..$ - 0200 18010000 4801c84c 898c24c8 00000048 ....H..L..$....H - 0210 89bc2420 0100004c 899c2440 01000048 ..$ ...L..$@...H - 0220 89942410 01000049 8d14c448 8d450248 ..$....I...H.E.H - 0230 0fafc648 89942408 01000048 896c2430 ...H..$....H.l$0 - 0240 4801c849 8d14c448 8d450348 0fafc648 H..I...H.E.H...H - 0250 89942400 01000048 c7442470 00000000 ..$....H.D$p.... - 0260 4801c849 8d14c448 8d450448 0fafc648 H..I...H.E.H...H - 0270 899424b0 00000048 c7442468 00000000 ..$....H.D$h.... - 0280 4801c849 8d14c448 8d450548 0fafc648 H..I...H.E.H...H - 0290 899424c0 00000048 01c8498d 14c4488d ..$....H..I...H. - 02a0 4506480f afc64889 9424d000 00004801 E.H...H..$....H. - 02b0 c8498d14 c4488d45 07480faf c6488994 .I...H.E.H...H.. - 02c0 24f00000 004801c8 498d14c4 488d4508 $....H..I...H.E. - 02d0 480fafc6 48899424 a8000000 4801c849 H...H..$....H..I - 02e0 8d14c448 8d450948 0fafc648 89942428 ...H.E.H...H..$( - 02f0 01000048 01c8498d 14c4488d 450a480f ...H..I...H.E.H. - 0300 afc64889 94243801 00004801 c8498d14 ..H..$8...H..I.. - 0310 c4488d45 0b480faf c6488994 24480100 .H.E.H...H..$H.. - 0320 004801c8 498d14c4 488d450c 480fafc6 .H..I...H.E.H... - 0330 48899424 58010000 4801c849 8d14c448 H..$X...H..I...H - 0340 8d450d48 0fafc648 89942468 01000048 .E.H...H..$h...H - 0350 01c8498d 14c4488d 450e480f afc64889 ..I...H.E.H...H. - 0360 94247801 00004801 c8498d14 c4488d45 .$x...H..I...H.E - 0370 0f480faf c6488bb4 24800000 00488994 .H...H..$....H.. - 0380 24880100 004801c8 498d1cc4 48899c24 $....H..I...H..$ - 0390 98010000 4889f348 8b442478 4883e3f0 ....H..H.D$xH... - 03a0 4801cb48 895c2450 4889c348 c1e00448 H..H.\$PH..H...H - 03b0 01c84889 8424b001 00004889 f083e00e ..H..$....H..... - 03c0 48898424 c8010000 4889f048 c1e30b83 H..$....H..H.... - 03d0 e00c83e6 0848899c 24a80100 00488984 .....H..$....H.. - 03e0 24d00100 004889b4 24d80100 00e96f01 $....H..$.....o. - 03f0 0000660f 1f440000 488b4424 68488b9c ..f..D..H.D$hH.. - 0400 24100100 00488bb4 24b00000 004801c3 $....H..$....H.. - 0410 48895c24 28488b9c 24080100 004801c6 H.\$(H..$....H.. - 0420 4801c348 895c2420 488b9c24 00010000 H..H.\$ H..$.... - 0430 48897424 084801c3 48895c24 18488b9c H.t$.H..H.\$.H.. - 0440 24c00000 00488bbc 24480100 004801c3 $....H..$H...H.. - 0450 48895c24 10488b9c 24d00000 00488bb4 H.\$.H..$....H.. - 0460 24580100 004801c3 48891c24 488b9c24 $X...H..H..$H..$ - 0470 f0000000 4801c748 01c34889 5c24e848 ....H..H..H.\$.H - 0480 8b9c24a8 00000048 01c64801 c348895c ..$....H..H..H.\ - 0490 24e0488b 9c242801 00004889 7c24c848 $.H..$(...H.|$.H - 04a0 01c34889 5c24d848 8b9c2438 01000048 ..H.\$.H..$8...H - 04b0 897424c0 4801c348 895c24d0 488bbc24 .t$.H..H.\$.H..$ - 04c0 78010000 488b9c24 68010000 488bb424 x...H..$h...H..$ - 04d0 88010000 4801c348 01c74801 c6480384 ....H..H..H..H.. - 04e0 24980100 0048895c 24b84889 7c24b048 $....H.\$.H.|$.H - 04f0 897424a8 48894424 3848837c 24780048 .t$.H.D$8H.|$x.H - 0500 8b442440 0f8f7901 00004883 7c245800 .D$@..y...H.|$X. - 0510 74264839 4424300f 8ff42c00 000f8d6d t&H9D$0...,....m - 0520 1d000048 8b8424b8 01000048 01842418 ...H..$....H..$. - 0530 0200000f 1f440000 48834424 3010488b .....D..H.D$0.H. - 0540 7c244848 836c2470 8048017c 2468488b |$HH.l$p.H.|$hH. - 0550 44243048 3b842488 0000000f 84241300 D$0H;.$......$.. - 0560 00488b7c 24404839 7c24300f 8d87feff .H.|$@H9|$0..... - 0570 ff488b44 2470488b bc24e000 0000488b .H.D$pH..$....H. - 0580 b424f800 00004801 c748897c 2420488b .$....H..H.|$ H. - 0590 bc241801 00004801 c64801c7 48897424 .$....H..H..H.t$ - 05a0 2848897c 2410488b b424e800 0000488b (H.|$.H..$....H. - 05b0 bc24b800 00004801 c64801c7 48897424 .$....H..H..H.t$ - 05c0 0848893c 24488bb4 24200100 00488bbc .H.<$H..$ ...H.. - 05d0 24300100 004801c6 4801c748 897424e0 $0...H..H..H.t$. - 05e0 48897c24 d8488bb4 24400100 00488bbc H.|$.H..$@...H.. - 05f0 24500100 004801c6 4801c748 897424d0 $P...H..H..H.t$. - 0600 48897c24 c8488b9c 24d80000 00488bb4 H.|$.H..$....H.. - 0610 24600100 00488bbc 24700100 004801c3 $`...H..$p...H.. - 0620 4801c648 01c74889 5c241848 897424c0 H..H..H.\$.H.t$. - 0630 48897c24 b8488b9c 24c80000 00488bb4 H.|$.H..$....H.. - 0640 24800100 00488bbc 24900100 004801c3 $....H..$....H.. - 0650 4801c648 01c74803 8424a001 00004889 H..H..H..$....H. - 0660 5c24e848 897424b0 48897c24 a8488944 \$.H.t$.H.|$.H.D - 0670 24384883 7c247800 488b4424 400f8e87 $8H.|$x.H.D$@... - 0680 feffff48 8b842418 02000048 8d900008 ...H..$....H.... - 0690 0000488b 44244048 894424f8 e9ae0e00 ..H.D$@H.D$..... - 06a0 000f1f80 00000000 488b4c24 28c5fb10 ........H.L$(... - 06b0 01488b4c 2420c5fb 118200f8 ffffc5fb .H.L$ .......... - 06c0 1001488b 4c2418c5 fb118208 f8ffffc5 ..H.L$.......... - 06d0 fb100148 8b4c2408 c5fb1182 10f8ffff ...H.L$......... - 06e0 c5fb1001 488b4c24 10c5fb11 8218f8ff ....H.L$........ - 06f0 ffc5fb10 01488b0c 24c5fb11 8220f8ff .....H..$.... .. - 0700 ffc5fb10 01488b4c 24e8c5fb 118228f8 .....H.L$.....(. - 0710 ffffc5fb 1001488b 4c24e0c5 fb118230 ......H.L$.....0 - 0720 f8ffffc5 fb100148 8b4c24d8 c5fb1182 .......H.L$..... - 0730 38f8ffff c5fb1001 488b4c24 d0c5fb11 8.......H.L$.... - 0740 8240f8ff ffc5fb10 01488b4c 24c8c5fb .@.......H.L$... - 0750 118248f8 ffffc5fb 1001c5fb 118250f8 ..H...........P. - 0760 ffff488b 4c24c048 8b442438 c5fb1001 ..H.L$.H.D$8.... - 0770 488b4c24 b8c5fb11 8258f8ff ffc5fb10 H.L$.....X...... - 0780 01488b4c 24b0c5fb 118260f8 ffffc5fb .H.L$.....`..... - 0790 1001488b 4c24a8c5 fb118268 f8ffffc5 ..H.L$.....h.... - 07a0 fb100148 8b4c2420 c5fb1182 70f8ffff ...H.L$ ....p... - 07b0 c5fb1000 48c78280 f8ffff00 000000c5 ....H........... - 07c0 fb118278 f8ffffc5 fb104108 488b4c24 ...x......A.H.L$ - 07d0 18c5fb11 8288f8ff ffc5fb10 4108488b ............A.H. - 07e0 4c2408c5 fb118290 f8ffffc5 fb104108 L$............A. - 07f0 488b4c24 10c5fb11 8298f8ff ffc5fb10 H.L$............ - 0800 4108488b 0c24c5fb 1182a0f8 ffffc5fb A.H..$.......... - 0810 10410848 8b4c24e8 c5fb1182 a8f8ffff .A.H.L$......... - 0820 c5fb1041 08488b4c 24e0c5fb 1182b0f8 ...A.H.L$....... - 0830 ffffc5fb 10410848 8b4c24d8 c5fb1182 .....A.H.L$..... - 0840 b8f8ffff c5fb1041 08488b4c 24d0c5fb .......A.H.L$... - 0850 1182c0f8 ffffc5fb 10410848 8b4c24c8 .........A.H.L$. - 0860 c5fb1182 c8f8ffff c5fb1041 08488b4c ...........A.H.L - 0870 24c0c5fb 1182d0f8 ffffc5fb 10410848 $............A.H - 0880 8b4c24b8 c5fb1182 d8f8ffff c5fb1041 .L$............A - 0890 08488b4c 24b0c5fb 1182e0f8 ffffc5fb .H.L$........... - 08a0 10410848 8b4c24a8 c5fb1182 e8f8ffff .A.H.L$......... - 08b0 c5fb1041 08488b4c 2418c5fb 1182f0f8 ...A.H.L$....... - 08c0 ffffc5fb 10400848 c78200f9 ffff0000 .....@.H........ - 08d0 000048c7 8208f9ff ff000000 00c5fb11 ..H............. - 08e0 82f8f8ff ffc5fb10 4110c5fb 118210f9 ........A....... - 08f0 ffff488b 4c2408c5 fb104110 488b4c24 ..H.L$....A.H.L$ - 0900 10c5fb11 8218f9ff ffc5fb10 4110488b ............A.H. - 0910 0c24c5fb 118220f9 ffffc5fb 10411048 .$.... ......A.H - 0920 8b4c24e8 c5fb1182 28f9ffff c5fb1041 .L$.....(......A - 0930 10488b4c 24e0c5fb 118230f9 ffffc5fb .H.L$.....0..... - 0940 10411048 8b4c24d8 c5fb1182 38f9ffff .A.H.L$.....8... - 0950 c5fb1041 10488b4c 24d0c5fb 118240f9 ...A.H.L$.....@. - 0960 ffffc5fb 10411048 8b4c24c8 c5fb1182 .....A.H.L$..... - 0970 48f9ffff c5fb1041 10488b4c 24c0c5fb H......A.H.L$... - 0980 118250f9 ffffc5fb 10411048 8b4c24b8 ..P......A.H.L$. - 0990 c5fb1182 58f9ffff c5fb1041 10488b4c ....X......A.H.L - 09a0 24b0c5fb 118260f9 ffffc5fb 104110c5 $.....`......A.. - 09b0 fb118268 f9ffff48 8b4c24a8 c5fb1041 ...h...H.L$....A - 09c0 10488b4c 2408c5fb 118270f9 ffffc5fb .H.L$.....p..... - 09d0 10401048 c78280f9 ffff0000 000048c7 .@.H..........H. - 09e0 8288f9ff ff000000 0048c782 90f9ffff .........H...... - 09f0 00000000 c5fb1182 78f9ffff c5fb1041 ........x......A - 0a00 18488b4c 2410c5fb 118298f9 ffffc5fb .H.L$........... - 0a10 10411848 8b0c24c5 fb1182a0 f9ffffc5 .A.H..$......... - 0a20 fb104118 488b4c24 e8c5fb11 82a8f9ff ..A.H.L$........ - 0a30 ffc5fb10 4118488b 4c24e0c5 fb1182b0 ....A.H.L$...... - 0a40 f9ffffc5 fb104118 488b4c24 d8c5fb11 ......A.H.L$.... - 0a50 82b8f9ff ffc5fb10 4118488b 4c24d0c5 ........A.H.L$.. - 0a60 fb1182c0 f9ffffc5 fb104118 488b4c24 ..........A.H.L$ - 0a70 c8c5fb11 82c8f9ff ffc5fb10 4118c5fb ............A... - 0a80 1182d0f9 ffff488b 4c24c0c5 fb104118 ......H.L$....A. - 0a90 488b4c24 b8c5fb11 82d8f9ff ffc5fb10 H.L$............ - 0aa0 4118488b 4c24b0c5 fb1182e0 f9ffffc5 A.H.L$.......... - 0ab0 fb104118 488b4c24 a8c5fb11 82e8f9ff ..A.H.L$........ - 0ac0 ffc5fb10 4118488b 4c2410c5 fb1182f0 ....A.H.L$...... - 0ad0 f9ffffc5 fb104018 48c78200 faffff00 ......@.H....... - 0ae0 00000048 c78208fa ffff0000 000048c7 ...H..........H. - 0af0 8210faff ff000000 0048c782 18faffff .........H...... - 0b00 00000000 c5fb1182 f8f9ffff c5fb1041 ...............A - 0b10 20488b0c 24c5fb11 8220faff ffc5fb10 H..$.... ...... - 0b20 4120488b 4c24e8c5 fb118228 faffffc5 A H.L$.....(.... - 0b30 fb104120 488b4c24 e0c5fb11 8230faff ..A H.L$.....0.. - 0b40 ffc5fb10 4120488b 4c24d8c5 fb118238 ....A H.L$.....8 - 0b50 faffffc5 fb104120 c5fb1182 40faffff ......A ....@... - 0b60 488b4c24 d0c5fb10 4120488b 4c24c8c5 H.L$....A H.L$.. - 0b70 fb118248 faffffc5 fb104120 488b4c24 ...H......A H.L$ - 0b80 c0c5fb11 8250faff ffc5fb10 4120488b .....P......A H. - 0b90 4c24b8c5 fb118258 faffffc5 fb104120 L$.....X......A - 0ba0 488b4c24 b0c5fb11 8260faff ffc5fb10 H.L$.....`...... - 0bb0 4120488b 4c24a8c5 fb118268 faffffc5 A H.L$.....h.... - 0bc0 fb104120 488b0c24 c5fb1182 70faffff ..A H..$....p... - 0bd0 c5fb1040 2048c782 80faffff 00000000 ...@ H.......... - 0be0 48c78288 faffff00 00000048 c78290fa H..........H.... - 0bf0 ffff0000 000048c7 8298faff ff000000 ......H......... - 0c00 0048c782 a0faffff 00000000 c5fb1182 .H.............. - 0c10 78faffff c5fb1041 28488b4c 24e8c5fb x......A(H.L$... /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 463a0000 00420e10 8f02420e ....F:...B....B. + 0020 00000000 46070000 00420e10 8f02420e ....F....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 71220a0e ..A.8..G....q".. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0842 0b000000 D..B.... + 0040 8606410e 38830744 0e4803a0 050a0e38 ..A.8..D.H.....8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08460b 00000000 ..F..... /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_SKYLAKEX.o (disasm) @@ -12,1523 +12,341 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) - mov %r9,offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,(%rsp) + mov offset(%rsp),%rbx test %rsi,%rsi jle + mov %rcx,%rax + imul %r8,%rax + mov %rdx,%r11 + mov %rsi,%r14 + mov %rdi,%r15 + mov %rdi,%rsi + add %r9,%rax + mov %rcx,%rdi + mov %rcx,%rbp + mov %rsi,%r10 + mov %rsi,%rcx + lea (%r11,%rax,8),%r12 + mov %rdi,%rsi + lea (%r9,%r14,4),%rax + imul %r9,%rsi + mov %rax,-offset(%rsp) mov %rdi,%rax - sar $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - mov %r8,%r12 - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - imul %rcx,%r12 - and $something,%eax - mov %rax,offset(%rsp) shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - shl $something,%rax - lea (%rcx,%rbx,1),%r11 - add offset(%rsp),%rax - lea (%rcx,%r11,1),%r10 - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%r10,%rcx,1),%r9 - add offset(%rsp),%r12 - lea (%r9,%rcx,1),%r8 - lea (%rax,%r12,8),%r12 - lea (%r8,%rcx,1),%rdi - mov %r12,offset(%rsp) - mov offset(%rsp),%r12 - lea (%rdi,%rcx,1),%rsi - mov %rcx,%r13 - add %r12,%rbp - lea (%rsi,%rcx,1),%rcx - lea (%rcx,%r13,1),%rdx - lea (%rax,%rbp,8),%rbp - lea (%rdx,%r13,1),%r15 - mov %rbp,offset(%rsp) - mov %r12,%rbp - mov %r15,-offset(%rsp) - add %rbp,%r11 - lea (%rax,%r11,8),%r11 - add %rbp,%rsi - add %rbp,%r9 - add %r12,%rbx - lea (%rax,%r9,8),%r9 - add %rbp,%rcx - mov %r11,offset(%rsp) - add %rbp,%r10 - lea (%rax,%rsi,8),%r11 - add %rbp,%r8 - add %rbp,%rdi - add %rbp,%rdx - mov %rax,%r12 - lea (%rax,%rbx,8),%rbx - lea (%rax,%rdx,8),%rdx - mov %r9,offset(%rsp) - mov %r11,offset(%rsp) - lea (%rax,%r10,8),%r10 - lea (%rax,%rcx,8),%r11 - lea (%rax,%r8,8),%r9 - lea (%rax,%rdi,8),%rdi - mov -offset(%rsp),%rax - lea (%r15,%r13,1),%r14 - add %rbp,%rax - lea (%r14,%r13,1),%r15 - mov %rdx,offset(%rsp) - add %rbp,%r14 - lea (%r12,%rax,8),%rdx - mov offset(%rsp),%rsi - add %r15,%r13 - mov %rdx,offset(%rsp) - add %rbp,%r15 - lea (%r12,%r14,8),%rdx - mov %rdx,offset(%rsp) - lea offset(%rbp,%r13,1),%rax - lea (%r12,%r15,8),%rdx - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - lea offset(%r13,%rsi,1),%rax - add %rbp,%rax - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - mov %rbp,%rax - imul %rsi,%rax - mov offset(%rsp),%rcx - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rbx,offset(%rsp) - mov %r10,offset(%rsp) - add %rcx,%rax - mov %r9,offset(%rsp) - mov %rdi,offset(%rsp) - mov %r11,offset(%rsp) - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - mov %rbp,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_SKYLAKEX.o (objdump) @@ -2,936 +2,120 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 044889bc .H..$....H...H.. - 0020 24800000 00488994 24a00000 0048898c $....H..$....H.. - 0030 24900000 004c8944 24404c89 4c246048 $....L.D$@L.L$`H - 0040 89b424c0 01000048 85f60f8e 4e180000 ..$....H....N... - 0050 4889f848 c1f80448 89442478 488b8424 H..H...H.D$xH..$ - 0060 90000000 4d89c448 c1e00748 89442448 ....M..H...H.D$H - 0070 488b8424 80000000 4c0fafe1 83e00f48 H..$....L......H - 0080 89442458 48c1e007 48898424 b8010000 .D$XH...H..$.... - 0090 488b8424 c0010000 4a8d2c21 488d1c29 H..$....J.,!H..) - 00a0 48c1e004 4c8d1c19 48034424 604e8d14 H...L...H.D$`N.. - 00b0 19488984 24880000 00488b84 24a00000 .H..$....H..$... - 00c0 004d8d0c 0a4c0364 24604d8d 04094e8d .M...L.d$`M...N. - 00d0 24e0498d 3c084c89 a424f800 00004c8b $.I.<.L..$....L. - 00e0 64246048 8d340f49 89cd4c01 e5488d0c d$`H.4.I..L..H.. - 00f0 0e4a8d14 29488d2c e84e8d3c 2a4889ac .J..)H.,.N.<*H.. - 0100 24e00000 004c89e5 4c897c24 884901eb $....L..L.|$.I.. - 0110 4e8d1cd8 4801ee49 01e94c01 e34e8d0c N...H..I..L..N.. - 0120 c84801e9 4c899c24 e8000000 4901ea4c .H..L..$....I..L - 0130 8d1cf049 01e84801 ef4801ea 4989c448 ...I..H..H..I..H - 0140 8d1cd848 8d14d04c 898c24b8 0000004c ...H...L..$....L - 0150 899c2430 0100004e 8d14d04c 8d1cc84e ..$0...N...L...N - 0160 8d0cc048 8d3cf848 8b442488 4f8d342f ...H.<.H.D$.O.4/ - 0170 4801e84f 8d3c2e48 89942450 01000049 H..O.<.H..$P...I - 0180 01ee498d 14c4488b b4249000 00004d01 ..I...H..$....M. - 0190 fd488994 24600100 004901ef 4b8d14f4 .H..$`...I..K... - 01a0 48899424 70010000 4a8d442d 004b8d14 H..$p...J.D-.K.. - 01b0 fc488994 24800100 00498d14 c4498d44 .H..$....I...I.D - 01c0 35004801 e8488994 24900100 00498d14 5.H..H..$....I.. - 01d0 c44889e8 480fafc6 488b4c24 40488994 .H..H...H.L$@H.. - 01e0 24a00100 004801c8 498d14c4 488d4501 $....H..I...H.E. - 01f0 480fafc6 48899c24 d8000000 4c899424 H...H..$....L..$ - 0200 18010000 4801c84c 898c24c8 00000048 ....H..L..$....H - 0210 89bc2420 0100004c 899c2440 01000048 ..$ ...L..$@...H - 0220 89942410 01000049 8d14c448 8d450248 ..$....I...H.E.H - 0230 0fafc648 89942408 01000048 896c2430 ...H..$....H.l$0 - 0240 4801c849 8d14c448 8d450348 0fafc648 H..I...H.E.H...H - 0250 89942400 01000048 c7442470 00000000 ..$....H.D$p.... - 0260 4801c849 8d14c448 8d450448 0fafc648 H..I...H.E.H...H - 0270 899424b0 00000048 c7442468 00000000 ..$....H.D$h.... - 0280 4801c849 8d14c448 8d450548 0fafc648 H..I...H.E.H...H - 0290 899424c0 00000048 01c8498d 14c4488d ..$....H..I...H. - 02a0 4506480f afc64889 9424d000 00004801 E.H...H..$....H. - 02b0 c8498d14 c4488d45 07480faf c6488994 .I...H.E.H...H.. - 02c0 24f00000 004801c8 498d14c4 488d4508 $....H..I...H.E. - 02d0 480fafc6 48899424 a8000000 4801c849 H...H..$....H..I - 02e0 8d14c448 8d450948 0fafc648 89942428 ...H.E.H...H..$( - 02f0 01000048 01c8498d 14c4488d 450a480f ...H..I...H.E.H. - 0300 afc64889 94243801 00004801 c8498d14 ..H..$8...H..I.. - 0310 c4488d45 0b480faf c6488994 24480100 .H.E.H...H..$H.. - 0320 004801c8 498d14c4 488d450c 480fafc6 .H..I...H.E.H... - 0330 48899424 58010000 4801c849 8d14c448 H..$X...H..I...H - 0340 8d450d48 0fafc648 89942468 01000048 .E.H...H..$h...H - 0350 01c8498d 14c4488d 450e480f afc64889 ..I...H.E.H...H. - 0360 94247801 00004801 c8498d14 c4488d45 .$x...H..I...H.E - 0370 0f480faf c6488bb4 24800000 00488994 .H...H..$....H.. - 0380 24880100 004801c8 498d1cc4 48899c24 $....H..I...H..$ - 0390 98010000 4889f348 8b442478 4883e3f0 ....H..H.D$xH... - 03a0 4801cb48 895c2450 4889c348 c1e00448 H..H.\$PH..H...H - 03b0 01c84889 8424b001 00004889 f083e00e ..H..$....H..... - 03c0 48898424 c8010000 4889f048 c1e30b83 H..$....H..H.... - 03d0 e00c83e6 0848899c 24a80100 00488984 .....H..$....H.. - 03e0 24d00100 004889b4 24d80100 00e96f01 $....H..$.....o. - 03f0 0000660f 1f440000 488b4424 68488b9c ..f..D..H.D$hH.. - 0400 24100100 00488bb4 24b00000 004801c3 $....H..$....H.. - 0410 48895c24 28488b9c 24080100 004801c6 H.\$(H..$....H.. - 0420 4801c348 895c2420 488b9c24 00010000 H..H.\$ H..$.... - 0430 48897424 084801c3 48895c24 18488b9c H.t$.H..H.\$.H.. - 0440 24c00000 00488bbc 24480100 004801c3 $....H..$H...H.. - 0450 48895c24 10488b9c 24d00000 00488bb4 H.\$.H..$....H.. - 0460 24580100 004801c3 48891c24 488b9c24 $X...H..H..$H..$ - 0470 f0000000 4801c748 01c34889 5c24e848 ....H..H..H.\$.H - 0480 8b9c24a8 00000048 01c64801 c348895c ..$....H..H..H.\ - 0490 24e0488b 9c242801 00004889 7c24c848 $.H..$(...H.|$.H - 04a0 01c34889 5c24d848 8b9c2438 01000048 ..H.\$.H..$8...H - 04b0 897424c0 4801c348 895c24d0 488bbc24 .t$.H..H.\$.H..$ - 04c0 78010000 488b9c24 68010000 488bb424 x...H..$h...H..$ - 04d0 88010000 4801c348 01c74801 c6480384 ....H..H..H..H.. - 04e0 24980100 0048895c 24b84889 7c24b048 $....H.\$.H.|$.H - 04f0 897424a8 48894424 3848837c 24780048 .t$.H.D$8H.|$x.H - 0500 8b442440 0f8f7901 00004883 7c245800 .D$@..y...H.|$X. - 0510 74264839 4424300f 8ff42c00 000f8d6d t&H9D$0...,....m - 0520 1d000048 8b8424b8 01000048 01842418 ...H..$....H..$. - 0530 0200000f 1f440000 48834424 3010488b .....D..H.D$0.H. - 0540 7c244848 836c2470 8048017c 2468488b |$HH.l$p.H.|$hH. - 0550 44243048 3b842488 0000000f 84241300 D$0H;.$......$.. - 0560 00488b7c 24404839 7c24300f 8d87feff .H.|$@H9|$0..... - 0570 ff488b44 2470488b bc24e000 0000488b .H.D$pH..$....H. - 0580 b424f800 00004801 c748897c 2420488b .$....H..H.|$ H. - 0590 bc241801 00004801 c64801c7 48897424 .$....H..H..H.t$ - 05a0 2848897c 2410488b b424e800 0000488b (H.|$.H..$....H. - 05b0 bc24b800 00004801 c64801c7 48897424 .$....H..H..H.t$ - 05c0 0848893c 24488bb4 24200100 00488bbc .H.<$H..$ ...H.. - 05d0 24300100 004801c6 4801c748 897424e0 $0...H..H..H.t$. - 05e0 48897c24 d8488bb4 24400100 00488bbc H.|$.H..$@...H.. - 05f0 24500100 004801c6 4801c748 897424d0 $P...H..H..H.t$. - 0600 48897c24 c8488b9c 24d80000 00488bb4 H.|$.H..$....H.. - 0610 24600100 00488bbc 24700100 004801c3 $`...H..$p...H.. - 0620 4801c648 01c74889 5c241848 897424c0 H..H..H.\$.H.t$. - 0630 48897c24 b8488b9c 24c80000 00488bb4 H.|$.H..$....H.. - 0640 24800100 00488bbc 24900100 004801c3 $....H..$....H.. - 0650 4801c648 01c74803 8424a001 00004889 H..H..H..$....H. - 0660 5c24e848 897424b0 48897c24 a8488944 \$.H.t$.H.|$.H.D - 0670 24384883 7c247800 488b4424 400f8e87 $8H.|$x.H.D$@... - 0680 feffff48 8b842418 02000048 8d900008 ...H..$....H.... - 0690 0000488b 44244048 894424f8 e9ae0e00 ..H.D$@H.D$..... - 06a0 000f1f80 00000000 488b4c24 28c5fb10 ........H.L$(... - 06b0 01488b4c 2420c5fb 118200f8 ffffc5fb .H.L$ .......... - 06c0 1001488b 4c2418c5 fb118208 f8ffffc5 ..H.L$.......... - 06d0 fb100148 8b4c2408 c5fb1182 10f8ffff ...H.L$......... - 06e0 c5fb1001 488b4c24 10c5fb11 8218f8ff ....H.L$........ - 06f0 ffc5fb10 01488b0c 24c5fb11 8220f8ff .....H..$.... .. - 0700 ffc5fb10 01488b4c 24e8c5fb 118228f8 .....H.L$.....(. - 0710 ffffc5fb 1001488b 4c24e0c5 fb118230 ......H.L$.....0 - 0720 f8ffffc5 fb100148 8b4c24d8 c5fb1182 .......H.L$..... - 0730 38f8ffff c5fb1001 488b4c24 d0c5fb11 8.......H.L$.... - 0740 8240f8ff ffc5fb10 01488b4c 24c8c5fb .@.......H.L$... - 0750 118248f8 ffffc5fb 1001c5fb 118250f8 ..H...........P. - 0760 ffff488b 4c24c048 8b442438 c5fb1001 ..H.L$.H.D$8.... - 0770 488b4c24 b8c5fb11 8258f8ff ffc5fb10 H.L$.....X...... - 0780 01488b4c 24b0c5fb 118260f8 ffffc5fb .H.L$.....`..... - 0790 1001488b 4c24a8c5 fb118268 f8ffffc5 ..H.L$.....h.... - 07a0 fb100148 8b4c2420 c5fb1182 70f8ffff ...H.L$ ....p... - 07b0 c5fb1000 48c78280 f8ffff00 000000c5 ....H........... - 07c0 fb118278 f8ffffc5 fb104108 488b4c24 ...x......A.H.L$ - 07d0 18c5fb11 8288f8ff ffc5fb10 4108488b ............A.H. - 07e0 4c2408c5 fb118290 f8ffffc5 fb104108 L$............A. - 07f0 488b4c24 10c5fb11 8298f8ff ffc5fb10 H.L$............ - 0800 4108488b 0c24c5fb 1182a0f8 ffffc5fb A.H..$.......... - 0810 10410848 8b4c24e8 c5fb1182 a8f8ffff .A.H.L$......... - 0820 c5fb1041 08488b4c 24e0c5fb 1182b0f8 ...A.H.L$....... - 0830 ffffc5fb 10410848 8b4c24d8 c5fb1182 .....A.H.L$..... - 0840 b8f8ffff c5fb1041 08488b4c 24d0c5fb .......A.H.L$... - 0850 1182c0f8 ffffc5fb 10410848 8b4c24c8 .........A.H.L$. - 0860 c5fb1182 c8f8ffff c5fb1041 08488b4c ...........A.H.L - 0870 24c0c5fb 1182d0f8 ffffc5fb 10410848 $............A.H - 0880 8b4c24b8 c5fb1182 d8f8ffff c5fb1041 .L$............A - 0890 08488b4c 24b0c5fb 1182e0f8 ffffc5fb .H.L$........... - 08a0 10410848 8b4c24a8 c5fb1182 e8f8ffff .A.H.L$......... - 08b0 c5fb1041 08488b4c 2418c5fb 1182f0f8 ...A.H.L$....... - 08c0 ffffc5fb 10400848 c78200f9 ffff0000 .....@.H........ - 08d0 000048c7 8208f9ff ff000000 00c5fb11 ..H............. - 08e0 82f8f8ff ffc5fb10 4110c5fb 118210f9 ........A....... - 08f0 ffff488b 4c2408c5 fb104110 488b4c24 ..H.L$....A.H.L$ - 0900 10c5fb11 8218f9ff ffc5fb10 4110488b ............A.H. - 0910 0c24c5fb 118220f9 ffffc5fb 10411048 .$.... ......A.H - 0920 8b4c24e8 c5fb1182 28f9ffff c5fb1041 .L$.....(......A - 0930 10488b4c 24e0c5fb 118230f9 ffffc5fb .H.L$.....0..... - 0940 10411048 8b4c24d8 c5fb1182 38f9ffff .A.H.L$.....8... - 0950 c5fb1041 10488b4c 24d0c5fb 118240f9 ...A.H.L$.....@. - 0960 ffffc5fb 10411048 8b4c24c8 c5fb1182 .....A.H.L$..... - 0970 48f9ffff c5fb1041 10488b4c 24c0c5fb H......A.H.L$... - 0980 118250f9 ffffc5fb 10411048 8b4c24b8 ..P......A.H.L$. - 0990 c5fb1182 58f9ffff c5fb1041 10488b4c ....X......A.H.L - 09a0 24b0c5fb 118260f9 ffffc5fb 104110c5 $.....`......A.. - 09b0 fb118268 f9ffff48 8b4c24a8 c5fb1041 ...h...H.L$....A - 09c0 10488b4c 2408c5fb 118270f9 ffffc5fb .H.L$.....p..... - 09d0 10401048 c78280f9 ffff0000 000048c7 .@.H..........H. - 09e0 8288f9ff ff000000 0048c782 90f9ffff .........H...... - 09f0 00000000 c5fb1182 78f9ffff c5fb1041 ........x......A - 0a00 18488b4c 2410c5fb 118298f9 ffffc5fb .H.L$........... - 0a10 10411848 8b0c24c5 fb1182a0 f9ffffc5 .A.H..$......... - 0a20 fb104118 488b4c24 e8c5fb11 82a8f9ff ..A.H.L$........ - 0a30 ffc5fb10 4118488b 4c24e0c5 fb1182b0 ....A.H.L$...... - 0a40 f9ffffc5 fb104118 488b4c24 d8c5fb11 ......A.H.L$.... - 0a50 82b8f9ff ffc5fb10 4118488b 4c24d0c5 ........A.H.L$.. - 0a60 fb1182c0 f9ffffc5 fb104118 488b4c24 ..........A.H.L$ - 0a70 c8c5fb11 82c8f9ff ffc5fb10 4118c5fb ............A... - 0a80 1182d0f9 ffff488b 4c24c0c5 fb104118 ......H.L$....A. - 0a90 488b4c24 b8c5fb11 82d8f9ff ffc5fb10 H.L$............ - 0aa0 4118488b 4c24b0c5 fb1182e0 f9ffffc5 A.H.L$.......... - 0ab0 fb104118 488b4c24 a8c5fb11 82e8f9ff ..A.H.L$........ - 0ac0 ffc5fb10 4118488b 4c2410c5 fb1182f0 ....A.H.L$...... - 0ad0 f9ffffc5 fb104018 48c78200 faffff00 ......@.H....... - 0ae0 00000048 c78208fa ffff0000 000048c7 ...H..........H. - 0af0 8210faff ff000000 0048c782 18faffff .........H...... - 0b00 00000000 c5fb1182 f8f9ffff c5fb1041 ...............A - 0b10 20488b0c 24c5fb11 8220faff ffc5fb10 H..$.... ...... - 0b20 4120488b 4c24e8c5 fb118228 faffffc5 A H.L$.....(.... - 0b30 fb104120 488b4c24 e0c5fb11 8230faff ..A H.L$.....0.. - 0b40 ffc5fb10 4120488b 4c24d8c5 fb118238 ....A H.L$.....8 - 0b50 faffffc5 fb104120 c5fb1182 40faffff ......A ....@... - 0b60 488b4c24 d0c5fb10 4120488b 4c24c8c5 H.L$....A H.L$.. - 0b70 fb118248 faffffc5 fb104120 488b4c24 ...H......A H.L$ - 0b80 c0c5fb11 8250faff ffc5fb10 4120488b .....P......A H. - 0b90 4c24b8c5 fb118258 faffffc5 fb104120 L$.....X......A - 0ba0 488b4c24 b0c5fb11 8260faff ffc5fb10 H.L$.....`...... - 0bb0 4120488b 4c24a8c5 fb118268 faffffc5 A H.L$.....h.... - 0bc0 fb104120 488b0c24 c5fb1182 70faffff ..A H..$....p... - 0bd0 c5fb1040 2048c782 80faffff 00000000 ...@ H.......... - 0be0 48c78288 faffff00 00000048 c78290fa H..........H.... - 0bf0 ffff0000 000048c7 8298faff ff000000 ......H......... - 0c00 0048c782 a0faffff 00000000 c5fb1182 .H.............. - 0c10 78faffff c5fb1041 28488b4c 24e8c5fb x......A(H.L$... /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunncopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 463a0000 00420e10 8f02420e ....F:...B....B. + 0020 00000000 46070000 00420e10 8f02420e ....F....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 71220a0e ..A.8..G....q".. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0842 0b000000 D..B.... + 0040 8606410e 38830744 0e4803a0 050a0e38 ..A.8..D.H.....8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08460b 00000000 ..F..... /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_COOPERLAKE.o (disasm) @@ -12,1460 +12,349 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) - mov %r9,offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,(%rsp) + mov offset(%rsp),%rbx test %rsi,%rsi jle + mov %rcx,%rax + imul %r8,%rax + mov %rdx,%r11 + mov %rsi,%r14 + mov %rdi,%r15 + mov %rdi,%rsi + add %r9,%rax + mov %rcx,%rdi + mov %rcx,%rbp + mov %rsi,%r10 + mov %rsi,%rcx + lea (%r11,%rax,8),%r12 + mov %rdi,%rsi + lea (%r9,%r14,4),%rax + imul %r9,%rsi + mov %rax,-offset(%rsp) mov %rdi,%rax - sar $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - mov %r8,%r12 shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - imul %rcx,%r12 - and $something,%eax - mov %rax,offset(%rsp) - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - shl $something,%rax - lea (%rcx,%rbx,1),%r11 - add offset(%rsp),%rax - lea (%rcx,%r11,1),%r10 - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%r10,%rcx,1),%r9 - add offset(%rsp),%r12 - lea (%r9,%rcx,1),%r8 - lea (%rax,%r12,8),%r12 - lea (%r8,%rcx,1),%rdi - mov %r12,offset(%rsp) - mov offset(%rsp),%r12 - lea (%rdi,%rcx,1),%rsi - mov %rcx,%r13 - add %r12,%rbp - lea (%rsi,%rcx,1),%rcx - lea (%rcx,%r13,1),%rdx - lea (%rax,%rbp,8),%rbp - lea (%rdx,%r13,1),%r15 - mov %rbp,offset(%rsp) - mov %r12,%rbp - mov %r15,-offset(%rsp) - add %rbp,%r11 - lea (%rax,%r11,8),%r11 - add %rbp,%r9 - add %rbp,%r8 - add %r12,%rbx - lea (%rax,%r9,8),%r9 - add %rbp,%rdi - add %rbp,%rcx - mov %r11,offset(%rsp) - add %rbp,%r10 - lea (%rax,%r8,8),%r11 - add %rbp,%rsi - add %rbp,%rdx - mov %rax,%r12 - lea (%rax,%rsi,8),%rsi - lea (%rax,%rdx,8),%rdx - mov %r9,offset(%rsp) - mov %r11,offset(%rsp) - lea (%rax,%rcx,8),%r9 - lea (%rax,%rdi,8),%r11 - lea (%rax,%rbx,8),%rbx - lea (%rax,%r10,8),%r10 - mov -offset(%rsp),%rax - lea (%r15,%r13,1),%r14 - add %rbp,%rax - lea (%r14,%r13,1),%r15 - mov %rdx,offset(%rsp) - add %rbp,%r14 - lea (%r12,%rax,8),%rdx - mov offset(%rsp),%rdi - add %r15,%r13 - mov %rdx,offset(%rsp) - add %rbp,%r15 - lea (%r12,%r14,8),%rdx - mov %rdx,offset(%rsp) - lea offset(%rbp,%r13,1),%rax - lea (%r12,%r15,8),%rdx - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - lea offset(%r13,%rdi,1),%rax - add %rbp,%rax - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - mov %rbp,%rax - imul %rdi,%rax - mov offset(%rsp),%rcx - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rsi,offset(%rsp) - mov %rbx,offset(%rsp) - add %rcx,%rax - mov %r10,offset(%rsp) - mov %r11,offset(%rsp) - mov %r9,offset(%rsp) - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - mov %rbp,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - vmovsd offset(%rip),%xmm1 # - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_COOPERLAKE.o (objdump) @@ -2,899 +2,122 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 044889bc .H..$....H...H.. - 0020 24800000 00488994 24a00000 0048898c $....H..$....H.. - 0030 24900000 004c8944 24404c89 4c246048 $....L.D$@L.L$`H - 0040 89b424c0 01000048 85f60f8e 4e170000 ..$....H....N... - 0050 4889f848 c1f80448 89442478 488b8424 H..H...H.D$xH..$ - 0060 90000000 4d89c448 c1e00748 89442448 ....M..H...H.D$H - 0070 488b8424 80000000 4c0fafe1 83e00f48 H..$....L......H - 0080 89442458 48c1e007 48898424 b8010000 .D$XH...H..$.... - 0090 488b8424 c0010000 4a8d2c21 488d1c29 H..$....J.,!H..) - 00a0 48c1e004 4c8d1c19 48034424 604e8d14 H...L...H.D$`N.. - 00b0 19488984 24880000 00488b84 24a00000 .H..$....H..$... - 00c0 004d8d0c 0a4c0364 24604d8d 04094e8d .M...L.d$`M...N. - 00d0 24e0498d 3c084c89 a424d000 00004c8b $.I.<.L..$....L. - 00e0 64246048 8d340f49 89cd4c01 e5488d0c d$`H.4.I..L..H.. - 00f0 0e4a8d14 29488d2c e84e8d3c 2a4889ac .J..)H.,.N.<*H.. - 0100 24b80000 004c89e5 4c897c24 884901eb $....L..L.|$.I.. - 0110 4e8d1cd8 4901e949 01e84c01 e34e8d0c N...I..I..L..N.. - 0120 c84801ef 4801e94c 899c24e0 00000049 .H..H..L..$....I - 0130 01ea4e8d 1cc04801 ee4801ea 4989c448 ..N...H..H..I..H - 0140 8d34f048 8d14d04c 898c24b0 0000004c .4.H...L..$....L - 0150 899c2410 0100004c 8d0cc84c 8d1cf848 ..$....L...L...H - 0160 8d1cd84e 8d14d048 8b442488 4f8d342f ...N...H.D$.O.4/ - 0170 4801e84f 8d3c2e48 89942450 01000049 H..O.<.H..$P...I - 0180 01ee498d 14c4488b bc249000 00004d01 ..I...H..$....M. - 0190 fd488994 24600100 004901ef 4b8d14f4 .H..$`...I..K... - 01a0 48899424 70010000 4a8d442d 004b8d14 H..$p...J.D-.K.. - 01b0 fc488994 24800100 00498d14 c4498d44 .H..$....I...I.D - 01c0 3d004801 e8488994 24900100 00498d14 =.H..H..$....I.. - 01d0 c44889e8 480fafc7 488b4c24 40488994 .H..H...H.L$@H.. - 01e0 24a00100 004801c8 498d14c4 488d4501 $....H..I...H.E. - 01f0 480fafc7 4889b424 30010000 48899c24 H...H..$0...H..$ - 0200 c8000000 4801c84c 899424f8 0000004c ....H..L..$....L - 0210 899c2420 0100004c 898c2440 01000048 ..$ ...L..$@...H - 0220 899424f0 00000049 8d14c448 8d450248 ..$....I...H.E.H - 0230 0fafc748 899424d8 00000048 896c2428 ...H..$....H.l$( - 0240 4801c849 8d14c448 8d450348 0fafc748 H..I...H.E.H...H - 0250 899424e8 00000048 c7442468 00000000 ..$....H.D$h.... - 0260 4801c849 8d14c448 8d450448 0fafc748 H..I...H.E.H...H - 0270 89942400 01000048 c7442470 00000000 ..$....H.D$p.... - 0280 4801c849 8d14c448 8d450548 0fafc748 H..I...H.E.H...H - 0290 899424a8 000000c5 fb100d00 00000048 ..$............H - 02a0 01c8498d 14c4488d 4506480f afc74889 ..I...H.E.H...H. - 02b0 9424c000 00004801 c8498d14 c4488d45 .$....H..I...H.E - 02c0 07480faf c7488994 24080100 004801c8 .H...H..$....H.. - 02d0 498d14c4 488d4508 480fafc7 48899424 I...H.E.H...H..$ - 02e0 18010000 4801c849 8d14c448 8d450948 ....H..I...H.E.H - 02f0 0fafc748 89942428 01000048 01c8498d ...H..$(...H..I. - 0300 14c4488d 450a480f afc74889 94243801 ..H.E.H...H..$8. - 0310 00004801 c8498d14 c4488d45 0b480faf ..H..I...H.E.H.. - 0320 c7488994 24480100 004801c8 498d14c4 .H..$H...H..I... - 0330 488d450c 480fafc7 48899424 58010000 H.E.H...H..$X... - 0340 4801c849 8d14c448 8d450d48 0fafc748 H..I...H.E.H...H - 0350 89942468 01000048 01c8498d 14c4488d ..$h...H..I...H. - 0360 450e480f afc74889 94247801 00004801 E.H...H..$x...H. - 0370 c8498d14 c4488d45 0f480faf c7488bbc .I...H.E.H...H.. - 0380 24800000 00488994 24880100 004801c8 $....H..$....H.. - 0390 498d34c4 4889b424 98010000 4889fe48 I.4.H..$....H..H - 03a0 8b442478 4883e6f0 4801ce48 89742450 .D$xH...H..H.t$P - 03b0 4889c648 c1e00448 01c84889 8424b001 H..H...H..H..$.. - 03c0 00004889 f883e00e 48898424 c8010000 ..H.....H..$.... - 03d0 4889f848 c1e60b83 e00c83e7 084889b4 H..H.........H.. - 03e0 24a80100 00488984 24d00100 004889bc $....H..$....H.. - 03f0 24d80100 00e96f01 0000660f 1f440000 $.....o...f..D.. - 0400 488b4424 70488b9c 24e80000 00488bb4 H.D$pH..$....H.. - 0410 24f00000 004801c3 48895c24 18488b9c $....H..H.\$.H.. - 0420 24000100 004801c6 4801c348 895c2408 $....H..H..H.\$. - 0430 488b9c24 08010000 48897424 384801c3 H..$....H.t$8H.. - 0440 48895c24 f8488b9c 24180100 00488bbc H.\$.H..$....H.. - 0450 24d80000 004801c3 48895c24 e0488b9c $....H..H.\$.H.. - 0460 24280100 00488bb4 24a80000 004801c3 $(...H..$....H.. - 0470 48895c24 d8488b9c 24380100 004801c7 H.\$.H..$8...H.. - 0480 4801c348 895c24d0 488b9c24 48010000 H..H.\$.H..$H... - 0490 4801c648 01c34889 5c24c848 8b9c2458 H..H..H.\$.H..$X - 04a0 01000048 897c2420 4801c348 895c24c0 ...H.|$ H..H.\$. - 04b0 488b9c24 68010000 48897424 104801c3 H..$h...H.t$.H.. - 04c0 48895c24 b8488bbc 24c00000 00488bb4 H.\$.H..$....H.. - 04d0 24780100 00488b9c 24880100 004801c7 $x...H..$....H.. - 04e0 4801c648 01c34803 84249801 00004889 H..H..H..$....H. - 04f0 3c244889 7424b048 895c24a8 48894424 <$H.t$.H.\$.H.D$ - 0500 3048837c 24780048 8b442440 0f8f7901 0H.|$x.H.D$@..y. - 0510 00004883 7c245800 74264839 4424280f ..H.|$X.t&H9D$(. - 0520 8fca2a00 000f8d35 1c000048 8b8424b8 ..*....5...H..$. - 0530 01000048 01842418 0200000f 1f440000 ...H..$......D.. - 0540 48834424 2810488b 7c244848 836c2468 H.D$(.H.|$HH.l$h - 0550 8048017c 2470488b 44242848 3b842488 .H.|$pH.D$(H;.$. - 0560 0000000f 841c1200 00488b5c 24404839 .........H.\$@H9 - 0570 5c24280f 8d87feff ff488b44 2468488b \$(......H.D$hH. - 0580 9c24d000 0000488b b424b800 0000488b .$....H..$....H. - 0590 bc24c800 00004801 c34801c6 4801c748 .$....H..H..H..H - 05a0 895c2438 48897424 2048897c 2418488b .\$8H.t$ H.|$.H. - 05b0 9c24e000 0000488b bc24f800 0000488b .$....H..$....H. - 05c0 b424b000 00004801 c34801c7 4801c648 .$....H..H..H..H - 05d0 895c2408 48897c24 10488934 24488b9c .\$.H.|$.H.4$H.. - 05e0 24200100 00488bb4 24100100 00488bbc $ ...H..$....H.. - 05f0 24300100 004801c6 4801c348 01c74889 $0...H..H..H..H. - 0600 7424f848 895c24e0 48897c24 d8488bb4 t$.H.\$.H.|$.H.. - 0610 24400100 00488b9c 24500100 00488bbc $@...H..$P...H.. - 0620 24600100 004801c6 4801c348 01c74889 $`...H..H..H..H. - 0630 7424d048 895c24c8 48897c24 c0488bb4 t$.H.\$.H.|$.H.. - 0640 24700100 00488b9c 24800100 00488bbc $p...H..$....H.. - 0650 24900100 004801c6 4801c348 01c74803 $....H..H..H..H. - 0660 8424a001 00004889 7424b848 895c24b0 .$....H.t$.H.\$. - 0670 48897c24 a8488944 24304883 7c247800 H.|$.H.D$0H.|$x. - 0680 488b4424 400f8e87 feffff48 8b842418 H.D$@......H..$. - 0690 02000048 8d900008 0000488b 44244048 ...H......H.D$@H - 06a0 894424f0 e90b0e00 000f1f80 00000000 .D$............. - 06b0 488b4c24 20c5fb11 8a00f8ff ffc5fb10 H.L$ ........... - 06c0 01488b4c 2418c5fb 118208f8 ffffc5fb .H.L$........... - 06d0 1001488b 4c2408c5 fb118210 f8ffffc5 ..H.L$.......... - 06e0 fb100148 8b4c2410 c5fb1182 18f8ffff ...H.L$......... - 06f0 c5fb1001 488b0c24 c5fb1182 20f8ffff ....H..$.... ... - 0700 c5fb1001 488b4c24 f8c5fb11 8228f8ff ....H.L$.....(.. - 0710 ffc5fb10 01488b4c 24e0c5fb 118230f8 .....H.L$.....0. - 0720 ffffc5fb 1001488b 4c24d8c5 fb118238 ......H.L$.....8 - 0730 f8ffffc5 fb100148 8b4c24d0 c5fb1182 .......H.L$..... - 0740 40f8ffff c5fb1001 488b4c24 c8c5fb11 @.......H.L$.... - 0750 8248f8ff ffc5fb10 01488b4c 24c0c5fb .H.......H.L$... - 0760 118250f8 ffffc5fb 1001488b 4c24b8c5 ..P.......H.L$.. - 0770 fb118258 f8ffffc5 fb100148 8b4c24b0 ...X.......H.L$. - 0780 c5fb1182 60f8ffff c5fb1001 488b4c24 ....`.......H.L$ - 0790 a8c5fb11 8268f8ff ffc5fb10 01488b44 .....h.......H.D - 07a0 2430c5fb 118270f8 ffffc5fb 100048c7 $0....p.......H. - 07b0 8280f8ff ff000000 00488b4c 2418c5fb .........H.L$... - 07c0 118278f8 ffffc5fb 118a88f8 ffffc5fb ..x............. - 07d0 10410848 8b4c2408 c5fb1182 90f8ffff .A.H.L$......... - 07e0 c5fb1041 08488b4c 2410c5fb 118298f8 ...A.H.L$....... - 07f0 ffffc5fb 10410848 8b0c24c5 fb1182a0 .....A.H..$..... - 0800 f8ffffc5 fb104108 488b4c24 f8c5fb11 ......A.H.L$.... - 0810 82a8f8ff ffc5fb10 4108488b 4c24e0c5 ........A.H.L$.. - 0820 fb1182b0 f8ffffc5 fb104108 488b4c24 ..........A.H.L$ - 0830 d8c5fb11 82b8f8ff ffc5fb10 4108488b ............A.H. - 0840 4c24d0c5 fb1182c0 f8ffffc5 fb104108 L$............A. - 0850 488b4c24 c8c5fb11 82c8f8ff ffc5fb10 H.L$............ - 0860 4108488b 4c24c0c5 fb1182d0 f8ffffc5 A.H.L$.......... - 0870 fb104108 488b4c24 b8c5fb11 82d8f8ff ..A.H.L$........ - 0880 ffc5fb10 4108488b 4c24b0c5 fb1182e0 ....A.H.L$...... - 0890 f8ffffc5 fb104108 488b4c24 a8c5fb11 ......A.H.L$.... - 08a0 82e8f8ff ffc5fb10 4108488b 4c2408c5 ........A.H.L$.. - 08b0 fb1182f0 f8ffffc5 fb104008 48c78200 ..........@.H... - 08c0 f9ffff00 00000048 c78208f9 ffff0000 .......H........ - 08d0 0000c5fb 1182f8f8 ffffc5fb 118a10f9 ................ - 08e0 ffffc5fb 10411048 8b4c2410 c5fb1182 .....A.H.L$..... - 08f0 18f9ffff c5fb1041 10488b0c 24c5fb11 .......A.H..$... - 0900 8220f9ff ffc5fb10 4110488b 4c24f8c5 . ......A.H.L$.. - 0910 fb118228 f9ffffc5 fb104110 488b4c24 ...(......A.H.L$ - 0920 e0c5fb11 8230f9ff ffc5fb10 4110488b .....0......A.H. - 0930 4c24d8c5 fb118238 f9ffffc5 fb104110 L$.....8......A. - 0940 488b4c24 d0c5fb11 8240f9ff ffc5fb10 H.L$.....@...... - 0950 4110488b 4c24c8c5 fb118248 f9ffffc5 A.H.L$.....H.... - 0960 fb104110 488b4c24 c0c5fb11 8250f9ff ..A.H.L$.....P.. - 0970 ffc5fb10 4110488b 4c24b8c5 fb118258 ....A.H.L$.....X - 0980 f9ffffc5 fb104110 488b4c24 b0c5fb11 ......A.H.L$.... - 0990 8260f9ff ffc5fb10 4110488b 4c24a8c5 .`......A.H.L$.. - 09a0 fb118268 f9ffffc5 fb104110 c5fb1182 ...h......A..... - 09b0 70f9ffff c5fb1040 1048c782 80f9ffff p......@.H...... - 09c0 00000000 48c78288 f9ffff00 00000048 ....H..........H - 09d0 c78290f9 ffff0000 0000488b 4c2410c5 ..........H.L$.. - 09e0 fb118278 f9ffffc5 fb118a98 f9ffffc5 ...x............ - 09f0 fb104118 488b0c24 c5fb1182 a0f9ffff ..A.H..$........ - 0a00 c5fb1041 18488b4c 24f8c5fb 1182a8f9 ...A.H.L$....... - 0a10 ffffc5fb 10411848 8b4c24e0 c5fb1182 .....A.H.L$..... - 0a20 b0f9ffff c5fb1041 18488b4c 24d8c5fb .......A.H.L$... - 0a30 1182b8f9 ffffc5fb 10411848 8b4c24d0 .........A.H.L$. - 0a40 c5fb1182 c0f9ffff c5fb1041 18488b4c ...........A.H.L - 0a50 24c8c5fb 1182c8f9 ffffc5fb 10411848 $............A.H - 0a60 8b4c24c0 c5fb1182 d0f9ffff c5fb1041 .L$............A - 0a70 18488b4c 24b8c5fb 1182d8f9 ffffc5fb .H.L$........... - 0a80 104118c5 fb1182e0 f9ffff48 8b4c24b0 .A.........H.L$. - 0a90 c5fb1041 18488b4c 24a8c5fb 1182e8f9 ...A.H.L$....... - 0aa0 ffffc5fb 10411848 8b0c24c5 fb1182f0 .....A.H..$..... - 0ab0 f9ffffc5 fb104018 48c78200 faffff00 ......@.H....... - 0ac0 00000048 c78208fa ffff0000 000048c7 ...H..........H. - 0ad0 8210faff ff000000 0048c782 18faffff .........H...... - 0ae0 00000000 c5fb1182 f8f9ffff c5fb118a ................ - 0af0 20faffff c5fb1041 20488b4c 24f8c5fb ......A H.L$... - 0b00 118228fa ffffc5fb 10412048 8b4c24e0 ..(......A H.L$. - 0b10 c5fb1182 30faffff c5fb1041 20488b4c ....0......A H.L - 0b20 24d8c5fb 118238fa ffffc5fb 10412048 $.....8......A H - 0b30 8b4c24d0 c5fb1182 40faffff c5fb1041 .L$.....@......A - 0b40 20488b4c 24c8c5fb 118248fa ffffc5fb H.L$.....H..... - 0b50 10412048 8b4c24c0 c5fb1182 50faffff .A H.L$.....P... - 0b60 c5fb1041 20488b4c 24b8c5fb 118258fa ...A H.L$.....X. - 0b70 ffffc5fb 10412048 8b4c24b0 c5fb1182 .....A H.L$..... - 0b80 60faffff c5fb1041 20488b4c 24a8c5fb `......A H.L$... - 0b90 118268fa ffffc5fb 10412048 8b4c24f8 ..h......A H.L$. - 0ba0 c5fb1182 70faffff c5fb1040 2048c782 ....p......@ H.. - 0bb0 80faffff 00000000 48c78288 faffff00 ........H....... - 0bc0 00000048 c78290fa ffff0000 000048c7 ...H..........H. - 0bd0 8298faff ff000000 0048c782 a0faffff .........H...... - 0be0 00000000 c5fb1182 78faffff c5fb118a ........x....... - 0bf0 a8faffff c5fb1041 28488b4c 24e0c5fb .......A(H.L$... - 0c00 1182b0fa ffffc5fb 10412848 8b4c24d8 .........A(H.L$. - 0c10 c5fb1182 b8faffff c5fb1041 28488b4c ...........A(H.L /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 f6370000 00420e10 8f02420e .....7...B....B. + 0020 00000000 64070000 00420e10 8f02420e ....d....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 41210a0e ..A.8..G....A!.. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0842 0b000000 D..B.... + 0040 8606410e 38830744 0e4803d7 050a0e38 ..A.8..D.H.....8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08470b 00000000 ..G..... /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_SKYLAKEX.o (disasm) @@ -12,1460 +12,349 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) - mov %r9,offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,(%rsp) + mov offset(%rsp),%rbx test %rsi,%rsi jle + mov %rcx,%rax + imul %r8,%rax + mov %rdx,%r11 + mov %rsi,%r14 + mov %rdi,%r15 + mov %rdi,%rsi + add %r9,%rax + mov %rcx,%rdi + mov %rcx,%rbp + mov %rsi,%r10 + mov %rsi,%rcx + lea (%r11,%rax,8),%r12 + mov %rdi,%rsi + lea (%r9,%r14,4),%rax + imul %r9,%rsi + mov %rax,-offset(%rsp) mov %rdi,%rax - sar $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - mov %r8,%r12 shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - imul %rcx,%r12 - and $something,%eax - mov %rax,offset(%rsp) - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - shl $something,%rax - lea (%rcx,%rbx,1),%r11 - add offset(%rsp),%rax - lea (%rcx,%r11,1),%r10 - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%r10,%rcx,1),%r9 - add offset(%rsp),%r12 - lea (%r9,%rcx,1),%r8 - lea (%rax,%r12,8),%r12 - lea (%r8,%rcx,1),%rdi - mov %r12,offset(%rsp) - mov offset(%rsp),%r12 - lea (%rdi,%rcx,1),%rsi - mov %rcx,%r13 - add %r12,%rbp - lea (%rsi,%rcx,1),%rcx - lea (%rcx,%r13,1),%rdx - lea (%rax,%rbp,8),%rbp - lea (%rdx,%r13,1),%r15 - mov %rbp,offset(%rsp) - mov %r12,%rbp - mov %r15,-offset(%rsp) - add %rbp,%r11 - lea (%rax,%r11,8),%r11 - add %rbp,%r9 - add %rbp,%r8 - add %r12,%rbx - lea (%rax,%r9,8),%r9 - add %rbp,%rdi - add %rbp,%rcx - mov %r11,offset(%rsp) - add %rbp,%r10 - lea (%rax,%r8,8),%r11 - add %rbp,%rsi - add %rbp,%rdx - mov %rax,%r12 - lea (%rax,%rsi,8),%rsi - lea (%rax,%rdx,8),%rdx - mov %r9,offset(%rsp) - mov %r11,offset(%rsp) - lea (%rax,%rcx,8),%r9 - lea (%rax,%rdi,8),%r11 - lea (%rax,%rbx,8),%rbx - lea (%rax,%r10,8),%r10 - mov -offset(%rsp),%rax - lea (%r15,%r13,1),%r14 - add %rbp,%rax - lea (%r14,%r13,1),%r15 - mov %rdx,offset(%rsp) - add %rbp,%r14 - lea (%r12,%rax,8),%rdx - mov offset(%rsp),%rdi - add %r15,%r13 - mov %rdx,offset(%rsp) - add %rbp,%r15 - lea (%r12,%r14,8),%rdx - mov %rdx,offset(%rsp) - lea offset(%rbp,%r13,1),%rax - lea (%r12,%r15,8),%rdx - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - lea offset(%r13,%rdi,1),%rax - add %rbp,%rax - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - mov %rbp,%rax - imul %rdi,%rax - mov offset(%rsp),%rcx - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rsi,offset(%rsp) - mov %rbx,offset(%rsp) - add %rcx,%rax - mov %r10,offset(%rsp) - mov %r11,offset(%rsp) - mov %r9,offset(%rsp) - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - mov %rbp,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - vmovsd offset(%rip),%xmm1 # - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rdx /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_SKYLAKEX.o (objdump) @@ -2,899 +2,122 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 044889bc .H..$....H...H.. - 0020 24800000 00488994 24a00000 0048898c $....H..$....H.. - 0030 24900000 004c8944 24404c89 4c246048 $....L.D$@L.L$`H - 0040 89b424c0 01000048 85f60f8e 4e170000 ..$....H....N... - 0050 4889f848 c1f80448 89442478 488b8424 H..H...H.D$xH..$ - 0060 90000000 4d89c448 c1e00748 89442448 ....M..H...H.D$H - 0070 488b8424 80000000 4c0fafe1 83e00f48 H..$....L......H - 0080 89442458 48c1e007 48898424 b8010000 .D$XH...H..$.... - 0090 488b8424 c0010000 4a8d2c21 488d1c29 H..$....J.,!H..) - 00a0 48c1e004 4c8d1c19 48034424 604e8d14 H...L...H.D$`N.. - 00b0 19488984 24880000 00488b84 24a00000 .H..$....H..$... - 00c0 004d8d0c 0a4c0364 24604d8d 04094e8d .M...L.d$`M...N. - 00d0 24e0498d 3c084c89 a424d000 00004c8b $.I.<.L..$....L. - 00e0 64246048 8d340f49 89cd4c01 e5488d0c d$`H.4.I..L..H.. - 00f0 0e4a8d14 29488d2c e84e8d3c 2a4889ac .J..)H.,.N.<*H.. - 0100 24b80000 004c89e5 4c897c24 884901eb $....L..L.|$.I.. - 0110 4e8d1cd8 4901e949 01e84c01 e34e8d0c N...I..I..L..N.. - 0120 c84801ef 4801e94c 899c24e0 00000049 .H..H..L..$....I - 0130 01ea4e8d 1cc04801 ee4801ea 4989c448 ..N...H..H..I..H - 0140 8d34f048 8d14d04c 898c24b0 0000004c .4.H...L..$....L - 0150 899c2410 0100004c 8d0cc84c 8d1cf848 ..$....L...L...H - 0160 8d1cd84e 8d14d048 8b442488 4f8d342f ...N...H.D$.O.4/ - 0170 4801e84f 8d3c2e48 89942450 01000049 H..O.<.H..$P...I - 0180 01ee498d 14c4488b bc249000 00004d01 ..I...H..$....M. - 0190 fd488994 24600100 004901ef 4b8d14f4 .H..$`...I..K... - 01a0 48899424 70010000 4a8d442d 004b8d14 H..$p...J.D-.K.. - 01b0 fc488994 24800100 00498d14 c4498d44 .H..$....I...I.D - 01c0 3d004801 e8488994 24900100 00498d14 =.H..H..$....I.. - 01d0 c44889e8 480fafc7 488b4c24 40488994 .H..H...H.L$@H.. - 01e0 24a00100 004801c8 498d14c4 488d4501 $....H..I...H.E. - 01f0 480fafc7 4889b424 30010000 48899c24 H...H..$0...H..$ - 0200 c8000000 4801c84c 899424f8 0000004c ....H..L..$....L - 0210 899c2420 0100004c 898c2440 01000048 ..$ ...L..$@...H - 0220 899424f0 00000049 8d14c448 8d450248 ..$....I...H.E.H - 0230 0fafc748 899424d8 00000048 896c2428 ...H..$....H.l$( - 0240 4801c849 8d14c448 8d450348 0fafc748 H..I...H.E.H...H - 0250 899424e8 00000048 c7442468 00000000 ..$....H.D$h.... - 0260 4801c849 8d14c448 8d450448 0fafc748 H..I...H.E.H...H - 0270 89942400 01000048 c7442470 00000000 ..$....H.D$p.... - 0280 4801c849 8d14c448 8d450548 0fafc748 H..I...H.E.H...H - 0290 899424a8 000000c5 fb100d00 00000048 ..$............H - 02a0 01c8498d 14c4488d 4506480f afc74889 ..I...H.E.H...H. - 02b0 9424c000 00004801 c8498d14 c4488d45 .$....H..I...H.E - 02c0 07480faf c7488994 24080100 004801c8 .H...H..$....H.. - 02d0 498d14c4 488d4508 480fafc7 48899424 I...H.E.H...H..$ - 02e0 18010000 4801c849 8d14c448 8d450948 ....H..I...H.E.H - 02f0 0fafc748 89942428 01000048 01c8498d ...H..$(...H..I. - 0300 14c4488d 450a480f afc74889 94243801 ..H.E.H...H..$8. - 0310 00004801 c8498d14 c4488d45 0b480faf ..H..I...H.E.H.. - 0320 c7488994 24480100 004801c8 498d14c4 .H..$H...H..I... - 0330 488d450c 480fafc7 48899424 58010000 H.E.H...H..$X... - 0340 4801c849 8d14c448 8d450d48 0fafc748 H..I...H.E.H...H - 0350 89942468 01000048 01c8498d 14c4488d ..$h...H..I...H. - 0360 450e480f afc74889 94247801 00004801 E.H...H..$x...H. - 0370 c8498d14 c4488d45 0f480faf c7488bbc .I...H.E.H...H.. - 0380 24800000 00488994 24880100 004801c8 $....H..$....H.. - 0390 498d34c4 4889b424 98010000 4889fe48 I.4.H..$....H..H - 03a0 8b442478 4883e6f0 4801ce48 89742450 .D$xH...H..H.t$P - 03b0 4889c648 c1e00448 01c84889 8424b001 H..H...H..H..$.. - 03c0 00004889 f883e00e 48898424 c8010000 ..H.....H..$.... - 03d0 4889f848 c1e60b83 e00c83e7 084889b4 H..H.........H.. - 03e0 24a80100 00488984 24d00100 004889bc $....H..$....H.. - 03f0 24d80100 00e96f01 0000660f 1f440000 $.....o...f..D.. - 0400 488b4424 70488b9c 24e80000 00488bb4 H.D$pH..$....H.. - 0410 24f00000 004801c3 48895c24 18488b9c $....H..H.\$.H.. - 0420 24000100 004801c6 4801c348 895c2408 $....H..H..H.\$. - 0430 488b9c24 08010000 48897424 384801c3 H..$....H.t$8H.. - 0440 48895c24 f8488b9c 24180100 00488bbc H.\$.H..$....H.. - 0450 24d80000 004801c3 48895c24 e0488b9c $....H..H.\$.H.. - 0460 24280100 00488bb4 24a80000 004801c3 $(...H..$....H.. - 0470 48895c24 d8488b9c 24380100 004801c7 H.\$.H..$8...H.. - 0480 4801c348 895c24d0 488b9c24 48010000 H..H.\$.H..$H... - 0490 4801c648 01c34889 5c24c848 8b9c2458 H..H..H.\$.H..$X - 04a0 01000048 897c2420 4801c348 895c24c0 ...H.|$ H..H.\$. - 04b0 488b9c24 68010000 48897424 104801c3 H..$h...H.t$.H.. - 04c0 48895c24 b8488bbc 24c00000 00488bb4 H.\$.H..$....H.. - 04d0 24780100 00488b9c 24880100 004801c7 $x...H..$....H.. - 04e0 4801c648 01c34803 84249801 00004889 H..H..H..$....H. - 04f0 3c244889 7424b048 895c24a8 48894424 <$H.t$.H.\$.H.D$ - 0500 3048837c 24780048 8b442440 0f8f7901 0H.|$x.H.D$@..y. - 0510 00004883 7c245800 74264839 4424280f ..H.|$X.t&H9D$(. - 0520 8fca2a00 000f8d35 1c000048 8b8424b8 ..*....5...H..$. - 0530 01000048 01842418 0200000f 1f440000 ...H..$......D.. - 0540 48834424 2810488b 7c244848 836c2468 H.D$(.H.|$HH.l$h - 0550 8048017c 2470488b 44242848 3b842488 .H.|$pH.D$(H;.$. - 0560 0000000f 841c1200 00488b5c 24404839 .........H.\$@H9 - 0570 5c24280f 8d87feff ff488b44 2468488b \$(......H.D$hH. - 0580 9c24d000 0000488b b424b800 0000488b .$....H..$....H. - 0590 bc24c800 00004801 c34801c6 4801c748 .$....H..H..H..H - 05a0 895c2438 48897424 2048897c 2418488b .\$8H.t$ H.|$.H. - 05b0 9c24e000 0000488b bc24f800 0000488b .$....H..$....H. - 05c0 b424b000 00004801 c34801c7 4801c648 .$....H..H..H..H - 05d0 895c2408 48897c24 10488934 24488b9c .\$.H.|$.H.4$H.. - 05e0 24200100 00488bb4 24100100 00488bbc $ ...H..$....H.. - 05f0 24300100 004801c6 4801c348 01c74889 $0...H..H..H..H. - 0600 7424f848 895c24e0 48897c24 d8488bb4 t$.H.\$.H.|$.H.. - 0610 24400100 00488b9c 24500100 00488bbc $@...H..$P...H.. - 0620 24600100 004801c6 4801c348 01c74889 $`...H..H..H..H. - 0630 7424d048 895c24c8 48897c24 c0488bb4 t$.H.\$.H.|$.H.. - 0640 24700100 00488b9c 24800100 00488bbc $p...H..$....H.. - 0650 24900100 004801c6 4801c348 01c74803 $....H..H..H..H. - 0660 8424a001 00004889 7424b848 895c24b0 .$....H.t$.H.\$. - 0670 48897c24 a8488944 24304883 7c247800 H.|$.H.D$0H.|$x. - 0680 488b4424 400f8e87 feffff48 8b842418 H.D$@......H..$. - 0690 02000048 8d900008 0000488b 44244048 ...H......H.D$@H - 06a0 894424f0 e90b0e00 000f1f80 00000000 .D$............. - 06b0 488b4c24 20c5fb11 8a00f8ff ffc5fb10 H.L$ ........... - 06c0 01488b4c 2418c5fb 118208f8 ffffc5fb .H.L$........... - 06d0 1001488b 4c2408c5 fb118210 f8ffffc5 ..H.L$.......... - 06e0 fb100148 8b4c2410 c5fb1182 18f8ffff ...H.L$......... - 06f0 c5fb1001 488b0c24 c5fb1182 20f8ffff ....H..$.... ... - 0700 c5fb1001 488b4c24 f8c5fb11 8228f8ff ....H.L$.....(.. - 0710 ffc5fb10 01488b4c 24e0c5fb 118230f8 .....H.L$.....0. - 0720 ffffc5fb 1001488b 4c24d8c5 fb118238 ......H.L$.....8 - 0730 f8ffffc5 fb100148 8b4c24d0 c5fb1182 .......H.L$..... - 0740 40f8ffff c5fb1001 488b4c24 c8c5fb11 @.......H.L$.... - 0750 8248f8ff ffc5fb10 01488b4c 24c0c5fb .H.......H.L$... - 0760 118250f8 ffffc5fb 1001488b 4c24b8c5 ..P.......H.L$.. - 0770 fb118258 f8ffffc5 fb100148 8b4c24b0 ...X.......H.L$. - 0780 c5fb1182 60f8ffff c5fb1001 488b4c24 ....`.......H.L$ - 0790 a8c5fb11 8268f8ff ffc5fb10 01488b44 .....h.......H.D - 07a0 2430c5fb 118270f8 ffffc5fb 100048c7 $0....p.......H. - 07b0 8280f8ff ff000000 00488b4c 2418c5fb .........H.L$... - 07c0 118278f8 ffffc5fb 118a88f8 ffffc5fb ..x............. - 07d0 10410848 8b4c2408 c5fb1182 90f8ffff .A.H.L$......... - 07e0 c5fb1041 08488b4c 2410c5fb 118298f8 ...A.H.L$....... - 07f0 ffffc5fb 10410848 8b0c24c5 fb1182a0 .....A.H..$..... - 0800 f8ffffc5 fb104108 488b4c24 f8c5fb11 ......A.H.L$.... - 0810 82a8f8ff ffc5fb10 4108488b 4c24e0c5 ........A.H.L$.. - 0820 fb1182b0 f8ffffc5 fb104108 488b4c24 ..........A.H.L$ - 0830 d8c5fb11 82b8f8ff ffc5fb10 4108488b ............A.H. - 0840 4c24d0c5 fb1182c0 f8ffffc5 fb104108 L$............A. - 0850 488b4c24 c8c5fb11 82c8f8ff ffc5fb10 H.L$............ - 0860 4108488b 4c24c0c5 fb1182d0 f8ffffc5 A.H.L$.......... - 0870 fb104108 488b4c24 b8c5fb11 82d8f8ff ..A.H.L$........ - 0880 ffc5fb10 4108488b 4c24b0c5 fb1182e0 ....A.H.L$...... - 0890 f8ffffc5 fb104108 488b4c24 a8c5fb11 ......A.H.L$.... - 08a0 82e8f8ff ffc5fb10 4108488b 4c2408c5 ........A.H.L$.. - 08b0 fb1182f0 f8ffffc5 fb104008 48c78200 ..........@.H... - 08c0 f9ffff00 00000048 c78208f9 ffff0000 .......H........ - 08d0 0000c5fb 1182f8f8 ffffc5fb 118a10f9 ................ - 08e0 ffffc5fb 10411048 8b4c2410 c5fb1182 .....A.H.L$..... - 08f0 18f9ffff c5fb1041 10488b0c 24c5fb11 .......A.H..$... - 0900 8220f9ff ffc5fb10 4110488b 4c24f8c5 . ......A.H.L$.. - 0910 fb118228 f9ffffc5 fb104110 488b4c24 ...(......A.H.L$ - 0920 e0c5fb11 8230f9ff ffc5fb10 4110488b .....0......A.H. - 0930 4c24d8c5 fb118238 f9ffffc5 fb104110 L$.....8......A. - 0940 488b4c24 d0c5fb11 8240f9ff ffc5fb10 H.L$.....@...... - 0950 4110488b 4c24c8c5 fb118248 f9ffffc5 A.H.L$.....H.... - 0960 fb104110 488b4c24 c0c5fb11 8250f9ff ..A.H.L$.....P.. - 0970 ffc5fb10 4110488b 4c24b8c5 fb118258 ....A.H.L$.....X - 0980 f9ffffc5 fb104110 488b4c24 b0c5fb11 ......A.H.L$.... - 0990 8260f9ff ffc5fb10 4110488b 4c24a8c5 .`......A.H.L$.. - 09a0 fb118268 f9ffffc5 fb104110 c5fb1182 ...h......A..... - 09b0 70f9ffff c5fb1040 1048c782 80f9ffff p......@.H...... - 09c0 00000000 48c78288 f9ffff00 00000048 ....H..........H - 09d0 c78290f9 ffff0000 0000488b 4c2410c5 ..........H.L$.. - 09e0 fb118278 f9ffffc5 fb118a98 f9ffffc5 ...x............ - 09f0 fb104118 488b0c24 c5fb1182 a0f9ffff ..A.H..$........ - 0a00 c5fb1041 18488b4c 24f8c5fb 1182a8f9 ...A.H.L$....... - 0a10 ffffc5fb 10411848 8b4c24e0 c5fb1182 .....A.H.L$..... - 0a20 b0f9ffff c5fb1041 18488b4c 24d8c5fb .......A.H.L$... - 0a30 1182b8f9 ffffc5fb 10411848 8b4c24d0 .........A.H.L$. - 0a40 c5fb1182 c0f9ffff c5fb1041 18488b4c ...........A.H.L - 0a50 24c8c5fb 1182c8f9 ffffc5fb 10411848 $............A.H - 0a60 8b4c24c0 c5fb1182 d0f9ffff c5fb1041 .L$............A - 0a70 18488b4c 24b8c5fb 1182d8f9 ffffc5fb .H.L$........... - 0a80 104118c5 fb1182e0 f9ffff48 8b4c24b0 .A.........H.L$. - 0a90 c5fb1041 18488b4c 24a8c5fb 1182e8f9 ...A.H.L$....... - 0aa0 ffffc5fb 10411848 8b0c24c5 fb1182f0 .....A.H..$..... - 0ab0 f9ffffc5 fb104018 48c78200 faffff00 ......@.H....... - 0ac0 00000048 c78208fa ffff0000 000048c7 ...H..........H. - 0ad0 8210faff ff000000 0048c782 18faffff .........H...... - 0ae0 00000000 c5fb1182 f8f9ffff c5fb118a ................ - 0af0 20faffff c5fb1041 20488b4c 24f8c5fb ......A H.L$... - 0b00 118228fa ffffc5fb 10412048 8b4c24e0 ..(......A H.L$. - 0b10 c5fb1182 30faffff c5fb1041 20488b4c ....0......A H.L - 0b20 24d8c5fb 118238fa ffffc5fb 10412048 $.....8......A H - 0b30 8b4c24d0 c5fb1182 40faffff c5fb1041 .L$.....@......A - 0b40 20488b4c 24c8c5fb 118248fa ffffc5fb H.L$.....H..... - 0b50 10412048 8b4c24c0 c5fb1182 50faffff .A H.L$.....P... - 0b60 c5fb1041 20488b4c 24b8c5fb 118258fa ...A H.L$.....X. - 0b70 ffffc5fb 10412048 8b4c24b0 c5fb1182 .....A H.L$..... - 0b80 60faffff c5fb1041 20488b4c 24a8c5fb `......A H.L$... - 0b90 118268fa ffffc5fb 10412048 8b4c24f8 ..h......A H.L$. - 0ba0 c5fb1182 70faffff c5fb1040 2048c782 ....p......@ H.. - 0bb0 80faffff 00000000 48c78288 faffff00 ........H....... - 0bc0 00000048 c78290fa ffff0000 000048c7 ...H..........H. - 0bd0 8298faff ff000000 0048c782 a0faffff .........H...... - 0be0 00000000 c5fb1182 78faffff c5fb118a ........x....... - 0bf0 a8faffff c5fb1041 28488b4c 24e0c5fb .......A(H.L$... - 0c00 1182b0fa ffffc5fb 10412848 8b4c24d8 .........A(H.L$. - 0c10 c5fb1182 b8faffff c5fb1041 28488b4c ...........A(H.L /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iunucopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 f6370000 00420e10 8f02420e .....7...B....B. + 0020 00000000 64070000 00420e10 8f02420e ....d....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 41210a0e ..A.8..G....A!.. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0842 0b000000 D..B.... + 0040 8606410e 38830744 0e4803d7 050a0e38 ..A.8..D.H.....8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08470b 00000000 ..G..... /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_COOPERLAKE.o (disasm) @@ -12,1686 +12,334 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) + mov %rdi,(%rsp) mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,-offset(%rsp) - mov %r9,offset(%rsp) + mov %rcx,-offset(%rsp) + mov %r9,-offset(%rsp) mov %rsi,offset(%rsp) - mov offset(%rsp),%r14 + mov offset(%rsp),%rbx test %rsi,%rsi jle - mov %r8,%r12 - imul %rcx,%r12 - mov %rcx,%r15 - mov offset(%rsp),%r9 - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - lea (%rcx,%rbx,1),%r11 - lea (%r11,%rcx,1),%r10 - lea (%rcx,%r10,1),%rax - lea (%rax,%rcx,1),%r8 - lea (%rcx,%r8,1),%rdi - lea (%rcx,%rdi,1),%rsi + mov %rcx,%r14 + mov %r9,%r15 + mov %rcx,%rax + imul %r14,%r15 + imul %r8,%rax + mov %rdx,%rbp + mov %r15,%rdx + add %r8,%rdx + mov %rsi,%r13 + add %r9,%rax + lea offset(%rbp,%rdx,8),%r12 + lea offset(%rbp,%rax,8),%rbp + lea (%r9,%r13,4),%rax mov %rax,-offset(%rsp) - lea (%rcx,%rsi,1),%rax - lea (%rcx,%rax,1),%rdx + mov %r14,%rax + shl $something,%rax + mov %rdi,%rsi + mov %rcx,%r11 mov %rax,-offset(%rsp) - lea (%rcx,%rdx,1),%rax - lea (%rcx,%rax,1),%r13 - mov %r13,%rcx - mov %r15,%r13 - add %rcx,%r13 - mov %rcx,-offset(%rsp) - mov %r13,%rcx - mov %r15,%r13 - add %rcx,%r13 - mov %rcx,-offset(%rsp) - mov %r9,%rcx - sar $something,%rcx - and $something,%r9d - mov %rcx,offset(%rsp) - mov %r9,offset(%rsp) - mov %r15,%rcx - shl $something,%r9 shl $something,%rcx - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 + lea (%r14,%r14,2),%rax + lea offset(,%r14,8),%rdx + shl $something,%rax mov %rcx,offset(%rsp) - mov offset(%rsp),%rcx - shl $something,%r9 - add %rcx,%r9 - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add %rcx,%r12 - lea (%r9,%r12,8),%r12 - add %rcx,%rbp - lea (%r9,%rbp,8),%rbp - mov %r12,offset(%rsp) - mov %rcx,%r12 - mov %rbp,offset(%rsp) - mov %r12,%rbp - add %r12,%rbx - add %rbp,%rdx - mov %r9,%r12 - add %rbp,%rax - lea (%r12,%rdx,8),%rdx - mov %rdx,offset(%rsp) - add %rbp,%r11 - lea (%r12,%rax,8),%rdx - add %rbp,%r10 - mov -offset(%rsp),%rax - mov %r9,%rcx - lea (%r9,%r11,8),%r11 - lea (%r9,%r10,8),%r10 - lea (%r9,%rbx,8),%rbx - mov -offset(%rsp),%r9 - add %rbp,%rax - add %rbp,%r9 - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - mov -offset(%rsp),%rax - add %rbp,%rsi - mov %r10,offset(%rsp) - add %rbp,%r8 - lea (%rcx,%r9,8),%r10 - add %rbp,%rdi - mov %r11,offset(%rsp) - mov %r10,offset(%rsp) - lea (%rcx,%rsi,8),%r11 - lea (%rcx,%r8,8),%r10 - lea (%rcx,%rdi,8),%rdi - add %rbp,%rax - mov -offset(%rsp),%rcx - lea (%r12,%rax,8),%rax - add %rbp,%rcx - mov %rax,offset(%rsp) - lea offset(%r13,%rbp,1),%rax - mov %r11,offset(%rsp) - lea (%r12,%rax,8),%rax - lea (%r12,%rcx,8),%r11 - mov %r10,offset(%rsp) - mov %rax,offset(%rsp) - mov %rbx,offset(%rsp) - mov %rdi,offset(%rsp) - mov %r11,offset(%rsp) - mov %rdx,offset(%rsp) - mov offset(%rsp),%rsi - mov -offset(%rsp),%rcx - lea (%rsi,%r13,1),%rax - add %rbp,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - mov %rsi,%rax - imul %rbp,%rax - shl $something,%r15 - mov offset(%rsp),%r9 - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rbp,-offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - movq $something,offset(%rsp) - mov %r14,%r10 - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_COOPERLAKE.o (objdump) @@ -2,752 +2,123 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24900000 0048c1fe 0448897c .H..$....H...H.| - 0020 24784889 94249800 00004889 8c248800 $xH..$....H..$.. - 0030 00004c89 4424c04c 894c2458 4889b424 ..L.D$.L.L$XH..$ - 0040 c0010000 4c8bb424 18020000 4885f60f ....L..$....H... - 0050 8e5f1f00 004d89c4 4c0fafe1 4989cf4c ._...M..L...I..L - 0060 8b4c2478 4a8d2c21 488d1c29 4c8d1c19 .L$xJ.,!H..)L... - 0070 4d8d140b 4a8d0411 4c8d0408 4a8d3c01 M...J...L...J.<. - 0080 488d3439 48894424 98488d04 31488d14 H.49H.D$.H..1H.. - 0090 01488944 24a0488d 04114c8d 2c014c89 .H.D$.H...L.,.L. - 00a0 e94d89fd 4901cd48 894c2488 4c89e94d .M..I..H.L$.L..M - 00b0 89fd4901 cd48894c 24904c89 c948c1f9 ..I..H.L$.L..H.. - 00c0 044183e1 0f48894c 24704c89 4c24504c .A...H.L$pL.L$PL - 00d0 89f949c1 e10748c1 e1034c89 8c24b801 ..I...H...L..$.. - 00e0 00004c8b 8c24c001 00004889 8c24a001 ..L..$....H..$.. - 00f0 0000488b 4c245849 c1e10449 01c94c89 ..H.L$XI...I..L. - 0100 8c248000 00004c8b 8c249800 00004901 .$....L..$....I. - 0110 cc4f8d24 e14801cd 498d2ce9 4c89a424 .O.$.H..I.,.L..$ - 0120 a8000000 4989cc48 89ac24b8 0000004c ....I..H..$....L - 0130 89e54c01 e34801ea 4d89cc48 01e8498d ..L..H..M..H..I. - 0140 14d44889 94244801 00004901 eb498d14 ..H..$H...I..I.. - 0150 c44901ea 488b4424 884c89c9 4f8d1cd9 .I..H.D$.L..O... - 0160 4f8d14d1 498d1cd9 4c8b4c24 984801e8 O...I...L.L$.H.. - 0170 4901e948 89942458 01000049 8d14c448 I..H..$X...I...H - 0180 8b442490 4801ee4c 899424e8 00000049 .D$.H..L..$....I - 0190 01e84e8d 14c94801 ef4c899c 24d80000 ..N...H..L..$... - 01a0 004c8994 24f80000 004c8d1c f14e8d14 .L..$....L...N.. - 01b0 c1488d3c f94801e8 488b4c24 a0498d04 .H.<.H..H.L$.I.. - 01c0 c44801e9 48898424 78010000 498d442d .H..H..$x...I.D- - 01d0 004c899c 24280100 00498d04 c44d8d1c .L..$(...I...M.. - 01e0 cc4c8994 24080100 00488984 24880100 .L..$....H..$... - 01f0 0048899c 24c80000 004889bc 24180100 .H..$....H..$... - 0200 004c899c 24380100 00488994 24680100 .L..$8...H..$h.. - 0210 00488bb4 24880000 00488b4c 24c04a8d .H..$....H.L$.J. - 0220 042e4801 e8498d04 c4488984 24980100 ..H..I...H..$... - 0230 004889f0 480fafc5 49c1e707 4c8b4c24 .H..H...I...L.L$ - 0240 704801c8 498d04c4 48898424 a0000000 pH..I...H..$.... - 0250 488d4501 480fafc6 48896c24 9048c744 H.E.H...H.l$.H.D - 0260 24680000 00004801 c8498d04 c4488984 $h....H..I...H.. - 0270 24b00000 00488d45 02480faf c648c744 $....H.E.H...H.D - 0280 24600000 00004d89 f24801c8 498d04c4 $`....M..H..I... - 0290 48898424 c0000000 488d4503 480fafc6 H..$....H.E.H... - 02a0 4801c849 8d04c448 898424d0 00000048 H..I...H..$....H - 02b0 8d450448 0fafc648 01c8498d 04c44889 .E.H...H..I...H. - 02c0 8424e000 0000488d 4505480f afc64801 .$....H.E.H...H. - 02d0 c8498d04 c4488984 24f00000 00488d45 .I...H..$....H.E - 02e0 06480faf c64801c8 498d04c4 48898424 .H...H..I...H..$ - 02f0 00010000 488d4507 480fafc6 4801c849 ....H.E.H...H..I - 0300 8d04c448 89842410 01000048 8d450848 ...H..$....H.E.H - 0310 0fafc648 01c8498d 04c44889 84242001 ...H..I...H..$ . - 0320 0000488d 4509480f afc64801 c8498d04 ..H.E.H...H..I.. - 0330 c4488984 24300100 00488d45 0a480faf .H..$0...H.E.H.. - 0340 c64801c8 498d04c4 48898424 40010000 .H..I...H..$@... - 0350 488d450b 480fafc6 4801c849 8d04c448 H.E.H...H..I...H - 0360 89842450 01000048 8d450c48 0fafc648 ..$P...H.E.H...H - 0370 01c8498d 04c44889 84246001 0000488d ..I...H..$`...H. - 0380 450d480f afc64801 c8498d04 c4488984 E.H...H..I...H.. - 0390 24700100 00488d45 0e480faf c64801c8 $p...H.E.H...H.. - 03a0 498d04c4 48898424 80010000 488d450f I...H..$....H.E. - 03b0 480fafc6 488b7424 784801c8 498d04c4 H...H.t$xH..I... - 03c0 48898424 90010000 4889f048 83e0f048 H..$....H..H...H - 03d0 01c84889 4424d04c 89c848c1 e00b4889 ..H.D$.L..H...H. - 03e0 8424a801 00004c89 c848c1e0 044801c8 .$....L..H...H.. - 03f0 48898424 b0010000 4889f083 e00e4889 H..$....H.....H. - 0400 8424c801 00004889 f083e00c 83e60848 .$....H........H - 0410 89b424d8 01000048 898424d0 0100004c ..$....H..$....L - 0420 89fee927 01000066 0f1f8400 00000000 ...'...f........ - 0430 488b4424 60488bbc 24b00000 004c8b8c H.D$`H..$....L.. - 0440 24a00000 004801c7 48897c24 98488bbc $....H..H.|$.H.. - 0450 24c00000 00488b8c 24100100 004801c7 $....H..$....H.. - 0460 48897c24 a0488bbc 24d00000 004c8bbc H.|$.H..$....L.. - 0470 24200100 004801c7 48897c24 a8488bbc $ ...H..H.|$.H.. - 0480 24e00000 004c8bb4 24300100 004801c7 $....L..$0...H.. - 0490 48897c24 b0488bbc 24f00000 004c8bac H.|$.H..$....L.. - 04a0 24400100 004801c7 48897c24 c84c8ba4 $@...H..H.|$.L.. - 04b0 24500100 00488bbc 24000100 00488bac $P...H..$....H.. - 04c0 24600100 00488b9c 24700100 004c8b9c $`...H..$p...L.. - 04d0 24800100 004901c1 4801c748 01c14901 $....I..H..H..I. - 04e0 c74901c6 4901c549 01c44801 c54801c3 .I..I..I..H..H.. - 04f0 4901c348 03842490 01000048 837c2470 I..H..$....H.|$p - 0500 004889c2 488b4424 c00f8f2e 01000048 .H..H.D$.......H - 0510 837c2450 00741348 39442490 0f8eae10 .|$P.t.H9D$..... - 0520 00004c03 9424b801 00004883 44249010 ..L..$....H.D$.. - 0530 48017424 6048836c 24688048 8b442490 H.t$`H.l$h.H.D$. - 0540 483b8424 80000000 0f844a1a 0000488b H;.$......J...H. - 0550 7c24c048 397c2490 0f8dd2fe ffff488b |$.H9|$.......H. - 0560 44246848 8b9c24b8 00000048 8bbc24c8 D$hH..$....H..$. - 0570 00000048 01c34889 5c249848 8b9c24d8 ...H..H.\$.H..$. - 0580 00000048 01c74801 c348897c 24a04889 ...H..H..H.|$.H. - 0590 5c24a848 8bbc24e8 00000048 8b9c24f8 \$.H..$....H..$. - 05a0 00000048 01c74801 c348897c 24b04889 ...H..H..H.|$.H. - 05b0 5c24c84c 8b8c24a8 00000048 8bbc2408 \$.L..$....H..$. - 05c0 01000048 8b8c2418 0100004c 8bbc2428 ...H..$....L..$( - 05d0 0100004c 8bb42438 0100004c 8bac2448 ...L..$8...L..$H - 05e0 0100004c 8ba42458 01000048 8bac2468 ...L..$X...H..$h - 05f0 01000048 8b9c2478 0100004c 8b9c2488 ...H..$x...L..$. - 0600 01000049 01c14801 c74801c1 4901c749 ...I..H..H..I..I - 0610 01c64901 c54901c4 4801c548 01c34901 ..I..I..H..H..I. - 0620 c3480384 24980100 0048837c 24700048 .H..$....H.|$p.H - 0630 89c2488b 4424c00f 8ed2feff ff4c894c ..H.D$.......L.L - 0640 24b84c89 94241802 00004d8d 82000800 $.L..$....M..... - 0650 004989d1 4d89da48 89442488 488b5424 .I..M..H.D$.H.T$ - 0660 c84989f3 eb71662e 0f1f8400 00000000 .I...qf......... - 0670 48836c24 b8804883 6c249880 48836c24 H.l$..H.l$..H.l$ - 0680 a0804883 6c24a880 48836c24 b0804883 ..H.l$..H.l$..H. - 0690 ea804883 ef804883 e9804983 ef804983 ..H...H...I...I. - 06a0 ee804983 ed804983 ec804883 ed804883 ..I...I...H...H. - 06b0 eb804983 ea804983 e9804883 44248810 ..I...I...H.D$.. - 06c0 4981c000 08000048 8b442488 483b4424 I......H.D$.H;D$ - 06d0 d00f84c9 0e000049 8d8000f8 ffff4889 .......I......H. - 06e0 4424c848 8b442488 48394424 907f8148 D$.H.D$.H9D$...H - 06f0 8b4424b8 488b7424 88c5fb10 00488b44 .D$.H.t$.....H.D - 0700 24984c01 d8488944 2418488b 4424a04c $.L..H.D$.H.D$.L - 0710 01d84889 44241048 8b4424a8 4c01d848 ..H.D$.H.D$.L..H - 0720 894424f8 488b4424 b04c01d8 48894424 .D$.H.D$.L..H.D$ - 0730 084a8d04 1a488944 24f04a8d 041f4889 .J...H.D$.J...H. - 0740 04244a8d 04194889 4424e84b 8d041f48 .$J...H.D$.K...H - 0750 89442448 4b8d041e 48894424 404b8d44 .D$HK...H.D$@K.D - 0760 1d004889 4424384b 8d041c48 894424e0 ..H.D$8K...H.D$. - 0770 4a8d441d 00488944 24304a8d 041b4889 J.D..H.D$0J...H. - 0780 4424d84b 8d041a48 89442428 4b8d0419 D$.K...H.D$(K... - 0790 48894424 20483974 24900f8c 300d0000 H.D$ H9t$...0... - 07a0 49c78008 f8ffff00 00000049 c78010f8 I..........I.... - 07b0 ffff0000 000049c7 8018f8ff ff000000 ......I......... - 07c0 0049c780 20f8ffff 00000000 49c78028 .I.. .......I..( - 07d0 f8ffff00 00000049 c78030f8 ffff0000 .......I..0..... - 07e0 000049c7 8038f8ff ff000000 0049c780 ..I..8.......I.. - 07f0 40f8ffff 00000000 49c78048 f8ffff00 @.......I..H.... - 0800 00000049 c78050f8 ffff0000 000049c7 ...I..P.......I. - 0810 8058f8ff ff000000 0049c780 60f8ffff .X.......I..`... - 0820 00000000 49c78068 f8ffff00 00000049 ....I..h.......I - 0830 c78070f8 ffff0000 000049c7 8078f8ff ..p.......I..x.. - 0840 ff000000 00488b44 2498c4c1 7b118000 .....H.D$...{... - 0850 f8ffffc5 fb1000c4 c17b1180 80f8ffff .........{...... - 0860 c5fb1040 0849c780 90f8ffff 00000000 ...@.I.......... - 0870 c4c17b11 8088f8ff ff49c780 98f8ffff ..{......I...... - 0880 00000000 49c780a0 f8ffff00 00000049 ....I..........I - 0890 c780a8f8 ffff0000 000049c7 80b0f8ff ..........I..... - 08a0 ff000000 0049c780 b8f8ffff 00000000 .....I.......... - 08b0 49c780c0 f8ffff00 00000049 c780c8f8 I..........I.... - 08c0 ffff0000 000049c7 80d0f8ff ff000000 ......I......... - 08d0 0049c780 d8f8ffff 00000000 49c780e0 .I..........I... - 08e0 f8ffff00 00000049 c780e8f8 ffff0000 .......I........ - 08f0 000049c7 80f0f8ff ff000000 0049c780 ..I..........I.. - 0900 f8f8ffff 00000000 488b4424 a0c5fb10 ........H.D$.... - 0910 00c4c17b 118000f9 ffffc5fb 104008c4 ...{.........@.. - 0920 c17b1180 08f9ffff c5fb1040 1049c780 .{.........@.I.. - 0930 18f9ffff 00000000 49c78020 f9ffff00 ........I.. .... - 0940 00000049 c78028f9 ffff0000 000049c7 ...I..(.......I. - 0950 8030f9ff ff000000 0049c780 38f9ffff .0.......I..8... - 0960 00000000 49c78040 f9ffff00 00000049 ....I..@.......I - 0970 c78048f9 ffff0000 000049c7 8050f9ff ..H.......I..P.. - 0980 ff000000 0049c780 58f9ffff 00000000 .....I..X....... - 0990 49c78060 f9ffff00 00000049 c78068f9 I..`.......I..h. - 09a0 ffff0000 000049c7 8070f9ff ff000000 ......I..p...... - 09b0 0049c780 78f9ffff 00000000 488b4424 .I..x.......H.D$ - 09c0 a8c4c17b 118010f9 ffffc5fb 1000c4c1 ...{............ - 09d0 7b118080 f9ffffc5 fb104008 c4c17b11 {.........@...{. - 09e0 8088f9ff ffc5fb10 4010c4c1 7b118090 ........@...{... - 09f0 f9ffffc5 fb104018 49c780a0 f9ffff00 ......@.I....... - 0a00 000000c4 c17b1180 98f9ffff 49c780a8 .....{......I... - 0a10 f9ffff00 00000049 c780b0f9 ffff0000 .......I........ - 0a20 000049c7 80b8f9ff ff000000 0049c780 ..I..........I.. - 0a30 c0f9ffff 00000000 49c780c8 f9ffff00 ........I....... - 0a40 00000049 c780d0f9 ffff0000 000049c7 ...I..........I. - 0a50 80d8f9ff ff000000 0049c780 e0f9ffff .........I...... - 0a60 00000000 49c780e8 f9ffff00 00000049 ....I..........I - 0a70 c780f0f9 ffff0000 000049c7 80f8f9ff ..........I..... - 0a80 ff000000 00488b44 24b0c5fb 1000c4c1 .....H.D$....... - 0a90 7b118000 faffffc5 fb104008 c4c17b11 {.........@...{. - 0aa0 8008faff ffc5fb10 4010c4c1 7b118010 ........@...{... - 0ab0 faffffc5 fb104018 c4c17b11 8018faff ......@...{..... - 0ac0 ffc5fb10 402049c7 8028faff ff000000 ....@ I..(...... - 0ad0 0049c780 30faffff 00000000 49c78038 .I..0.......I..8 - 0ae0 faffff00 00000049 c78040fa ffff0000 .......I..@..... - 0af0 000049c7 8048faff ff000000 0049c780 ..I..H.......I.. - 0b00 50faffff 00000000 49c78058 faffff00 P.......I..X.... - 0b10 00000049 c78060fa ffff0000 000049c7 ...I..`.......I. - 0b20 8068faff ff000000 0049c780 70faffff .h.......I..p... - 0b30 00000000 49c78078 faffff00 000000c4 ....I..x........ - 0b40 c17b1180 20faffff c5fb1002 c4c17b11 .{.. .........{. - 0b50 8080faff ffc5fb10 4208c4c1 7b118088 ........B...{... - 0b60 faffffc5 fb104210 c4c17b11 8090faff ......B...{..... - 0b70 ffc5fb10 4218c4c1 7b118098 faffffc5 ....B...{....... - 0b80 fb104220 c4c17b11 80a0faff ffc5fb10 ..B ..{......... - 0b90 422849c7 80b0faff ff000000 0049c780 B(I..........I.. - 0ba0 b8faffff 00000000 49c780c0 faffff00 ........I....... - 0bb0 00000049 c780c8fa ffff0000 000049c7 ...I..........I. - 0bc0 80d0faff ff000000 0049c780 d8faffff .........I...... - 0bd0 00000000 49c780e0 faffff00 00000049 ....I..........I - 0be0 c780e8fa ffff0000 000049c7 80f0faff ..........I..... - 0bf0 ff000000 0049c780 f8faffff 00000000 .....I.......... - 0c00 c4c17b11 80a8faff ffc5fb10 07c4c17b ..{............{ - 0c10 118000fb ffffc5fb 104708c4 c17b1180 .........G...{.. /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 c82e0000 00420e10 8f02420e .........B....B. + 0020 00000000 74070000 00420e10 8f02420e ....t....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 2b280a0e ..A.8..G....+(.. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0040 8606410e 38830744 0e68039c 050a0e38 ..A.8..D.h.....8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e084a0b 00000000 ..J..... /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_SKYLAKEX.o (disasm) @@ -12,1686 +12,334 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) + mov %rdi,(%rsp) mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,-offset(%rsp) - mov %r9,offset(%rsp) + mov %rcx,-offset(%rsp) + mov %r9,-offset(%rsp) mov %rsi,offset(%rsp) - mov offset(%rsp),%r14 + mov offset(%rsp),%rbx test %rsi,%rsi jle - mov %r8,%r12 - imul %rcx,%r12 - mov %rcx,%r15 - mov offset(%rsp),%r9 - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - lea (%rcx,%rbx,1),%r11 - lea (%r11,%rcx,1),%r10 - lea (%rcx,%r10,1),%rax - lea (%rax,%rcx,1),%r8 - lea (%rcx,%r8,1),%rdi - lea (%rcx,%rdi,1),%rsi + mov %rcx,%r14 + mov %r9,%r15 + mov %rcx,%rax + imul %r14,%r15 + imul %r8,%rax + mov %rdx,%rbp + mov %r15,%rdx + add %r8,%rdx + mov %rsi,%r13 + add %r9,%rax + lea offset(%rbp,%rdx,8),%r12 + lea offset(%rbp,%rax,8),%rbp + lea (%r9,%r13,4),%rax mov %rax,-offset(%rsp) - lea (%rcx,%rsi,1),%rax - lea (%rcx,%rax,1),%rdx + mov %r14,%rax + shl $something,%rax + mov %rdi,%rsi + mov %rcx,%r11 mov %rax,-offset(%rsp) - lea (%rcx,%rdx,1),%rax - lea (%rcx,%rax,1),%r13 - mov %r13,%rcx - mov %r15,%r13 - add %rcx,%r13 - mov %rcx,-offset(%rsp) - mov %r13,%rcx - mov %r15,%r13 - add %rcx,%r13 - mov %rcx,-offset(%rsp) - mov %r9,%rcx - sar $something,%rcx - and $something,%r9d - mov %rcx,offset(%rsp) - mov %r9,offset(%rsp) - mov %r15,%rcx - shl $something,%r9 shl $something,%rcx - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 + lea (%r14,%r14,2),%rax + lea offset(,%r14,8),%rdx + shl $something,%rax mov %rcx,offset(%rsp) - mov offset(%rsp),%rcx - shl $something,%r9 - add %rcx,%r9 - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add %rcx,%r12 - lea (%r9,%r12,8),%r12 - add %rcx,%rbp - lea (%r9,%rbp,8),%rbp - mov %r12,offset(%rsp) - mov %rcx,%r12 - mov %rbp,offset(%rsp) - mov %r12,%rbp - add %r12,%rbx - add %rbp,%rdx - mov %r9,%r12 - add %rbp,%rax - lea (%r12,%rdx,8),%rdx - mov %rdx,offset(%rsp) - add %rbp,%r11 - lea (%r12,%rax,8),%rdx - add %rbp,%r10 - mov -offset(%rsp),%rax - mov %r9,%rcx - lea (%r9,%r11,8),%r11 - lea (%r9,%r10,8),%r10 - lea (%r9,%rbx,8),%rbx - mov -offset(%rsp),%r9 - add %rbp,%rax - add %rbp,%r9 - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - mov -offset(%rsp),%rax - add %rbp,%rsi - mov %r10,offset(%rsp) - add %rbp,%r8 - lea (%rcx,%r9,8),%r10 - add %rbp,%rdi - mov %r11,offset(%rsp) - mov %r10,offset(%rsp) - lea (%rcx,%rsi,8),%r11 - lea (%rcx,%r8,8),%r10 - lea (%rcx,%rdi,8),%rdi - add %rbp,%rax - mov -offset(%rsp),%rcx - lea (%r12,%rax,8),%rax - add %rbp,%rcx - mov %rax,offset(%rsp) - lea offset(%r13,%rbp,1),%rax - mov %r11,offset(%rsp) - lea (%r12,%rax,8),%rax - lea (%r12,%rcx,8),%r11 - mov %r10,offset(%rsp) - mov %rax,offset(%rsp) - mov %rbx,offset(%rsp) - mov %rdi,offset(%rsp) - mov %r11,offset(%rsp) - mov %rdx,offset(%rsp) - mov offset(%rsp),%rsi - mov -offset(%rsp),%rcx - lea (%rsi,%r13,1),%rax - add %rbp,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - mov %rsi,%rax - imul %rbp,%rax - shl $something,%r15 - mov offset(%rsp),%r9 - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rbp,-offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - movq $something,offset(%rsp) - mov %r14,%r10 - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_SKYLAKEX.o (objdump) @@ -2,752 +2,123 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24900000 0048c1fe 0448897c .H..$....H...H.| - 0020 24784889 94249800 00004889 8c248800 $xH..$....H..$.. - 0030 00004c89 4424c04c 894c2458 4889b424 ..L.D$.L.L$XH..$ - 0040 c0010000 4c8bb424 18020000 4885f60f ....L..$....H... - 0050 8e5f1f00 004d89c4 4c0fafe1 4989cf4c ._...M..L...I..L - 0060 8b4c2478 4a8d2c21 488d1c29 4c8d1c19 .L$xJ.,!H..)L... - 0070 4d8d140b 4a8d0411 4c8d0408 4a8d3c01 M...J...L...J.<. - 0080 488d3439 48894424 98488d04 31488d14 H.49H.D$.H..1H.. - 0090 01488944 24a0488d 04114c8d 2c014c89 .H.D$.H...L.,.L. - 00a0 e94d89fd 4901cd48 894c2488 4c89e94d .M..I..H.L$.L..M - 00b0 89fd4901 cd48894c 24904c89 c948c1f9 ..I..H.L$.L..H.. - 00c0 044183e1 0f48894c 24704c89 4c24504c .A...H.L$pL.L$PL - 00d0 89f949c1 e10748c1 e1034c89 8c24b801 ..I...H...L..$.. - 00e0 00004c8b 8c24c001 00004889 8c24a001 ..L..$....H..$.. - 00f0 0000488b 4c245849 c1e10449 01c94c89 ..H.L$XI...I..L. - 0100 8c248000 00004c8b 8c249800 00004901 .$....L..$....I. - 0110 cc4f8d24 e14801cd 498d2ce9 4c89a424 .O.$.H..I.,.L..$ - 0120 a8000000 4989cc48 89ac24b8 0000004c ....I..H..$....L - 0130 89e54c01 e34801ea 4d89cc48 01e8498d ..L..H..M..H..I. - 0140 14d44889 94244801 00004901 eb498d14 ..H..$H...I..I.. - 0150 c44901ea 488b4424 884c89c9 4f8d1cd9 .I..H.D$.L..O... - 0160 4f8d14d1 498d1cd9 4c8b4c24 984801e8 O...I...L.L$.H.. - 0170 4901e948 89942458 01000049 8d14c448 I..H..$X...I...H - 0180 8b442490 4801ee4c 899424e8 00000049 .D$.H..L..$....I - 0190 01e84e8d 14c94801 ef4c899c 24d80000 ..N...H..L..$... - 01a0 004c8994 24f80000 004c8d1c f14e8d14 .L..$....L...N.. - 01b0 c1488d3c f94801e8 488b4c24 a0498d04 .H.<.H..H.L$.I.. - 01c0 c44801e9 48898424 78010000 498d442d .H..H..$x...I.D- - 01d0 004c899c 24280100 00498d04 c44d8d1c .L..$(...I...M.. - 01e0 cc4c8994 24080100 00488984 24880100 .L..$....H..$... - 01f0 0048899c 24c80000 004889bc 24180100 .H..$....H..$... - 0200 004c899c 24380100 00488994 24680100 .L..$8...H..$h.. - 0210 00488bb4 24880000 00488b4c 24c04a8d .H..$....H.L$.J. - 0220 042e4801 e8498d04 c4488984 24980100 ..H..I...H..$... - 0230 004889f0 480fafc5 49c1e707 4c8b4c24 .H..H...I...L.L$ - 0240 704801c8 498d04c4 48898424 a0000000 pH..I...H..$.... - 0250 488d4501 480fafc6 48896c24 9048c744 H.E.H...H.l$.H.D - 0260 24680000 00004801 c8498d04 c4488984 $h....H..I...H.. - 0270 24b00000 00488d45 02480faf c648c744 $....H.E.H...H.D - 0280 24600000 00004d89 f24801c8 498d04c4 $`....M..H..I... - 0290 48898424 c0000000 488d4503 480fafc6 H..$....H.E.H... - 02a0 4801c849 8d04c448 898424d0 00000048 H..I...H..$....H - 02b0 8d450448 0fafc648 01c8498d 04c44889 .E.H...H..I...H. - 02c0 8424e000 0000488d 4505480f afc64801 .$....H.E.H...H. - 02d0 c8498d04 c4488984 24f00000 00488d45 .I...H..$....H.E - 02e0 06480faf c64801c8 498d04c4 48898424 .H...H..I...H..$ - 02f0 00010000 488d4507 480fafc6 4801c849 ....H.E.H...H..I - 0300 8d04c448 89842410 01000048 8d450848 ...H..$....H.E.H - 0310 0fafc648 01c8498d 04c44889 84242001 ...H..I...H..$ . - 0320 0000488d 4509480f afc64801 c8498d04 ..H.E.H...H..I.. - 0330 c4488984 24300100 00488d45 0a480faf .H..$0...H.E.H.. - 0340 c64801c8 498d04c4 48898424 40010000 .H..I...H..$@... - 0350 488d450b 480fafc6 4801c849 8d04c448 H.E.H...H..I...H - 0360 89842450 01000048 8d450c48 0fafc648 ..$P...H.E.H...H - 0370 01c8498d 04c44889 84246001 0000488d ..I...H..$`...H. - 0380 450d480f afc64801 c8498d04 c4488984 E.H...H..I...H.. - 0390 24700100 00488d45 0e480faf c64801c8 $p...H.E.H...H.. - 03a0 498d04c4 48898424 80010000 488d450f I...H..$....H.E. - 03b0 480fafc6 488b7424 784801c8 498d04c4 H...H.t$xH..I... - 03c0 48898424 90010000 4889f048 83e0f048 H..$....H..H...H - 03d0 01c84889 4424d04c 89c848c1 e00b4889 ..H.D$.L..H...H. - 03e0 8424a801 00004c89 c848c1e0 044801c8 .$....L..H...H.. - 03f0 48898424 b0010000 4889f083 e00e4889 H..$....H.....H. - 0400 8424c801 00004889 f083e00c 83e60848 .$....H........H - 0410 89b424d8 01000048 898424d0 0100004c ..$....H..$....L - 0420 89fee927 01000066 0f1f8400 00000000 ...'...f........ - 0430 488b4424 60488bbc 24b00000 004c8b8c H.D$`H..$....L.. - 0440 24a00000 004801c7 48897c24 98488bbc $....H..H.|$.H.. - 0450 24c00000 00488b8c 24100100 004801c7 $....H..$....H.. - 0460 48897c24 a0488bbc 24d00000 004c8bbc H.|$.H..$....L.. - 0470 24200100 004801c7 48897c24 a8488bbc $ ...H..H.|$.H.. - 0480 24e00000 004c8bb4 24300100 004801c7 $....L..$0...H.. - 0490 48897c24 b0488bbc 24f00000 004c8bac H.|$.H..$....L.. - 04a0 24400100 004801c7 48897c24 c84c8ba4 $@...H..H.|$.L.. - 04b0 24500100 00488bbc 24000100 00488bac $P...H..$....H.. - 04c0 24600100 00488b9c 24700100 004c8b9c $`...H..$p...L.. - 04d0 24800100 004901c1 4801c748 01c14901 $....I..H..H..I. - 04e0 c74901c6 4901c549 01c44801 c54801c3 .I..I..I..H..H.. - 04f0 4901c348 03842490 01000048 837c2470 I..H..$....H.|$p - 0500 004889c2 488b4424 c00f8f2e 01000048 .H..H.D$.......H - 0510 837c2450 00741348 39442490 0f8eae10 .|$P.t.H9D$..... - 0520 00004c03 9424b801 00004883 44249010 ..L..$....H.D$.. - 0530 48017424 6048836c 24688048 8b442490 H.t$`H.l$h.H.D$. - 0540 483b8424 80000000 0f844a1a 0000488b H;.$......J...H. - 0550 7c24c048 397c2490 0f8dd2fe ffff488b |$.H9|$.......H. - 0560 44246848 8b9c24b8 00000048 8bbc24c8 D$hH..$....H..$. - 0570 00000048 01c34889 5c249848 8b9c24d8 ...H..H.\$.H..$. - 0580 00000048 01c74801 c348897c 24a04889 ...H..H..H.|$.H. - 0590 5c24a848 8bbc24e8 00000048 8b9c24f8 \$.H..$....H..$. - 05a0 00000048 01c74801 c348897c 24b04889 ...H..H..H.|$.H. - 05b0 5c24c84c 8b8c24a8 00000048 8bbc2408 \$.L..$....H..$. - 05c0 01000048 8b8c2418 0100004c 8bbc2428 ...H..$....L..$( - 05d0 0100004c 8bb42438 0100004c 8bac2448 ...L..$8...L..$H - 05e0 0100004c 8ba42458 01000048 8bac2468 ...L..$X...H..$h - 05f0 01000048 8b9c2478 0100004c 8b9c2488 ...H..$x...L..$. - 0600 01000049 01c14801 c74801c1 4901c749 ...I..H..H..I..I - 0610 01c64901 c54901c4 4801c548 01c34901 ..I..I..H..H..I. - 0620 c3480384 24980100 0048837c 24700048 .H..$....H.|$p.H - 0630 89c2488b 4424c00f 8ed2feff ff4c894c ..H.D$.......L.L - 0640 24b84c89 94241802 00004d8d 82000800 $.L..$....M..... - 0650 004989d1 4d89da48 89442488 488b5424 .I..M..H.D$.H.T$ - 0660 c84989f3 eb71662e 0f1f8400 00000000 .I...qf......... - 0670 48836c24 b8804883 6c249880 48836c24 H.l$..H.l$..H.l$ - 0680 a0804883 6c24a880 48836c24 b0804883 ..H.l$..H.l$..H. - 0690 ea804883 ef804883 e9804983 ef804983 ..H...H...I...I. - 06a0 ee804983 ed804983 ec804883 ed804883 ..I...I...H...H. - 06b0 eb804983 ea804983 e9804883 44248810 ..I...I...H.D$.. - 06c0 4981c000 08000048 8b442488 483b4424 I......H.D$.H;D$ - 06d0 d00f84c9 0e000049 8d8000f8 ffff4889 .......I......H. - 06e0 4424c848 8b442488 48394424 907f8148 D$.H.D$.H9D$...H - 06f0 8b4424b8 488b7424 88c5fb10 00488b44 .D$.H.t$.....H.D - 0700 24984c01 d8488944 2418488b 4424a04c $.L..H.D$.H.D$.L - 0710 01d84889 44241048 8b4424a8 4c01d848 ..H.D$.H.D$.L..H - 0720 894424f8 488b4424 b04c01d8 48894424 .D$.H.D$.L..H.D$ - 0730 084a8d04 1a488944 24f04a8d 041f4889 .J...H.D$.J...H. - 0740 04244a8d 04194889 4424e84b 8d041f48 .$J...H.D$.K...H - 0750 89442448 4b8d041e 48894424 404b8d44 .D$HK...H.D$@K.D - 0760 1d004889 4424384b 8d041c48 894424e0 ..H.D$8K...H.D$. - 0770 4a8d441d 00488944 24304a8d 041b4889 J.D..H.D$0J...H. - 0780 4424d84b 8d041a48 89442428 4b8d0419 D$.K...H.D$(K... - 0790 48894424 20483974 24900f8c 300d0000 H.D$ H9t$...0... - 07a0 49c78008 f8ffff00 00000049 c78010f8 I..........I.... - 07b0 ffff0000 000049c7 8018f8ff ff000000 ......I......... - 07c0 0049c780 20f8ffff 00000000 49c78028 .I.. .......I..( - 07d0 f8ffff00 00000049 c78030f8 ffff0000 .......I..0..... - 07e0 000049c7 8038f8ff ff000000 0049c780 ..I..8.......I.. - 07f0 40f8ffff 00000000 49c78048 f8ffff00 @.......I..H.... - 0800 00000049 c78050f8 ffff0000 000049c7 ...I..P.......I. - 0810 8058f8ff ff000000 0049c780 60f8ffff .X.......I..`... - 0820 00000000 49c78068 f8ffff00 00000049 ....I..h.......I - 0830 c78070f8 ffff0000 000049c7 8078f8ff ..p.......I..x.. - 0840 ff000000 00488b44 2498c4c1 7b118000 .....H.D$...{... - 0850 f8ffffc5 fb1000c4 c17b1180 80f8ffff .........{...... - 0860 c5fb1040 0849c780 90f8ffff 00000000 ...@.I.......... - 0870 c4c17b11 8088f8ff ff49c780 98f8ffff ..{......I...... - 0880 00000000 49c780a0 f8ffff00 00000049 ....I..........I - 0890 c780a8f8 ffff0000 000049c7 80b0f8ff ..........I..... - 08a0 ff000000 0049c780 b8f8ffff 00000000 .....I.......... - 08b0 49c780c0 f8ffff00 00000049 c780c8f8 I..........I.... - 08c0 ffff0000 000049c7 80d0f8ff ff000000 ......I......... - 08d0 0049c780 d8f8ffff 00000000 49c780e0 .I..........I... - 08e0 f8ffff00 00000049 c780e8f8 ffff0000 .......I........ - 08f0 000049c7 80f0f8ff ff000000 0049c780 ..I..........I.. - 0900 f8f8ffff 00000000 488b4424 a0c5fb10 ........H.D$.... - 0910 00c4c17b 118000f9 ffffc5fb 104008c4 ...{.........@.. - 0920 c17b1180 08f9ffff c5fb1040 1049c780 .{.........@.I.. - 0930 18f9ffff 00000000 49c78020 f9ffff00 ........I.. .... - 0940 00000049 c78028f9 ffff0000 000049c7 ...I..(.......I. - 0950 8030f9ff ff000000 0049c780 38f9ffff .0.......I..8... - 0960 00000000 49c78040 f9ffff00 00000049 ....I..@.......I - 0970 c78048f9 ffff0000 000049c7 8050f9ff ..H.......I..P.. - 0980 ff000000 0049c780 58f9ffff 00000000 .....I..X....... - 0990 49c78060 f9ffff00 00000049 c78068f9 I..`.......I..h. - 09a0 ffff0000 000049c7 8070f9ff ff000000 ......I..p...... - 09b0 0049c780 78f9ffff 00000000 488b4424 .I..x.......H.D$ - 09c0 a8c4c17b 118010f9 ffffc5fb 1000c4c1 ...{............ - 09d0 7b118080 f9ffffc5 fb104008 c4c17b11 {.........@...{. - 09e0 8088f9ff ffc5fb10 4010c4c1 7b118090 ........@...{... - 09f0 f9ffffc5 fb104018 49c780a0 f9ffff00 ......@.I....... - 0a00 000000c4 c17b1180 98f9ffff 49c780a8 .....{......I... - 0a10 f9ffff00 00000049 c780b0f9 ffff0000 .......I........ - 0a20 000049c7 80b8f9ff ff000000 0049c780 ..I..........I.. - 0a30 c0f9ffff 00000000 49c780c8 f9ffff00 ........I....... - 0a40 00000049 c780d0f9 ffff0000 000049c7 ...I..........I. - 0a50 80d8f9ff ff000000 0049c780 e0f9ffff .........I...... - 0a60 00000000 49c780e8 f9ffff00 00000049 ....I..........I - 0a70 c780f0f9 ffff0000 000049c7 80f8f9ff ..........I..... - 0a80 ff000000 00488b44 24b0c5fb 1000c4c1 .....H.D$....... - 0a90 7b118000 faffffc5 fb104008 c4c17b11 {.........@...{. - 0aa0 8008faff ffc5fb10 4010c4c1 7b118010 ........@...{... - 0ab0 faffffc5 fb104018 c4c17b11 8018faff ......@...{..... - 0ac0 ffc5fb10 402049c7 8028faff ff000000 ....@ I..(...... - 0ad0 0049c780 30faffff 00000000 49c78038 .I..0.......I..8 - 0ae0 faffff00 00000049 c78040fa ffff0000 .......I..@..... - 0af0 000049c7 8048faff ff000000 0049c780 ..I..H.......I.. - 0b00 50faffff 00000000 49c78058 faffff00 P.......I..X.... - 0b10 00000049 c78060fa ffff0000 000049c7 ...I..`.......I. - 0b20 8068faff ff000000 0049c780 70faffff .h.......I..p... - 0b30 00000000 49c78078 faffff00 000000c4 ....I..x........ - 0b40 c17b1180 20faffff c5fb1002 c4c17b11 .{.. .........{. - 0b50 8080faff ffc5fb10 4208c4c1 7b118088 ........B...{... - 0b60 faffffc5 fb104210 c4c17b11 8090faff ......B...{..... - 0b70 ffc5fb10 4218c4c1 7b118098 faffffc5 ....B...{....... - 0b80 fb104220 c4c17b11 80a0faff ffc5fb10 ..B ..{......... - 0b90 422849c7 80b0faff ff000000 0049c780 B(I..........I.. - 0ba0 b8faffff 00000000 49c780c0 faffff00 ........I....... - 0bb0 00000049 c780c8fa ffff0000 000049c7 ...I..........I. - 0bc0 80d0faff ff000000 0049c780 d8faffff .........I...... - 0bd0 00000000 49c780e0 faffff00 00000049 ....I..........I - 0be0 c780e8fa ffff0000 000049c7 80f0faff ..........I..... - 0bf0 ff000000 0049c780 f8faffff 00000000 .....I.......... - 0c00 c4c17b11 80a8faff ffc5fb10 07c4c17b ..{............{ - 0c10 118000fb ffffc5fb 104708c4 c17b1180 .........G...{.. /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutncopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 c82e0000 00420e10 8f02420e .........B....B. + 0020 00000000 74070000 00420e10 8f02420e ....t....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 2b280a0e ..A.8..G....+(.. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0040 8606410e 38830744 0e68039c 050a0e38 ..A.8..D.h.....8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e084a0b 00000000 ..J..... /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_COOPERLAKE.o (disasm) @@ -12,1652 +12,351 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) + mov %rdi,(%rsp) mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,-offset(%rsp) - mov %r9,offset(%rsp) + mov %rcx,-offset(%rsp) + mov %r9,-offset(%rsp) mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov offset(%rsp),%rbx test %rsi,%rsi jle - mov %r8,%r12 - imul %rcx,%r12 + mov %rcx,%rax mov %rcx,%r14 - mov offset(%rsp),%r9 - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - lea (%rcx,%rbx,1),%r11 - lea (%r11,%rcx,1),%r10 - lea (%rcx,%r10,1),%rax - lea (%rax,%rcx,1),%r8 - lea (%rcx,%r8,1),%rdi - lea (%rcx,%rdi,1),%rsi - mov %rax,-offset(%rsp) - lea (%rcx,%rsi,1),%rax - lea (%rcx,%rax,1),%rdx - mov %rax,-offset(%rsp) - lea (%rcx,%rdx,1),%rax - lea (%rcx,%rax,1),%r13 - mov %r13,%rcx - mov %r14,%r13 - add %rcx,%r13 - mov %rcx,-offset(%rsp) - mov %r13,%rcx - mov %r14,%r13 - add %rcx,%r13 - mov %rcx,-offset(%rsp) - mov %r9,%rcx - sar $something,%rcx - and $something,%r9d - mov %rcx,offset(%rsp) - mov %r9,offset(%rsp) - mov %r14,%rcx - shl $something,%r9 + mov %rsi,%r13 + mov %rcx,%r11 + mov %rdi,%rsi shl $something,%rcx - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 + imul %r8,%rax mov %rcx,offset(%rsp) - mov offset(%rsp),%rcx - shl $something,%r9 - add %rcx,%r9 - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add %rcx,%r12 - lea (%r9,%r12,8),%r12 - add %rcx,%rbp - lea (%r9,%rbp,8),%rbp - mov %r12,offset(%rsp) - mov %rcx,%r12 - mov %rbp,offset(%rsp) - mov %r12,%rbp - add %r12,%rbx - add %rbp,%rdx - mov %r9,%r12 - add %rbp,%rax - lea (%r12,%rdx,8),%rdx - mov %rdx,offset(%rsp) - add %rbp,%r11 - lea (%r12,%rax,8),%rdx - add %rbp,%r10 - mov -offset(%rsp),%rax - mov %r9,%rcx - lea (%r9,%r11,8),%r11 - lea (%r9,%r10,8),%r10 - lea (%r9,%rbx,8),%rbx - mov -offset(%rsp),%r9 - add %rbp,%rax - add %rbp,%r9 - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - mov -offset(%rsp),%rax - add %rbp,%rsi - mov %r10,offset(%rsp) - add %rbp,%r8 - lea (%rcx,%r9,8),%r10 - add %rbp,%rdi - mov %r11,offset(%rsp) - mov %r10,offset(%rsp) - lea (%rcx,%rsi,8),%r11 - lea (%rcx,%r8,8),%r10 - lea (%rcx,%rdi,8),%rdi - add %rbp,%rax - mov -offset(%rsp),%rcx - lea (%r12,%rax,8),%rax - add %rbp,%rcx - mov %rax,offset(%rsp) - lea offset(%r13,%rbp,1),%rax - mov %r11,offset(%rsp) - lea (%r12,%rax,8),%rax - lea (%r12,%rcx,8),%r11 - mov %r10,offset(%rsp) - mov %rax,offset(%rsp) - mov %rbx,offset(%rsp) - mov %rdi,offset(%rsp) - mov %r11,offset(%rsp) - mov %rdx,offset(%rsp) - mov offset(%rsp),%rsi - mov -offset(%rsp),%rcx - lea (%rsi,%r13,1),%rax - add %rbp,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - mov %rsi,%rax - imul %rbp,%rax - shl $something,%r14 - mov offset(%rsp),%r9 - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rbp,-offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - movq $something,offset(%rsp) - vmovsd offset(%rip),%xmm0 # - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - mov %r15,%r10 - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_COOPERLAKE.o (objdump) @@ -2,742 +2,128 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24900000 0048c1fe 0448897c .H..$....H...H.| - 0020 24784889 94249800 00004889 8c248800 $xH..$....H..$.. - 0030 00004c89 4424c04c 894c2458 4889b424 ..L.D$.L.L$XH..$ - 0040 c0010000 4c8bbc24 18020000 4885f60f ....L..$....H... - 0050 8eaf1e00 004d89c4 4c0fafe1 4989ce4c .....M..L...I..L - 0060 8b4c2478 4a8d2c21 488d1c29 4c8d1c19 .L$xJ.,!H..)L... - 0070 4d8d140b 4a8d0411 4c8d0408 4a8d3c01 M...J...L...J.<. - 0080 488d3439 48894424 98488d04 31488d14 H.49H.D$.H..1H.. - 0090 01488944 24a0488d 04114c8d 2c014c89 .H.D$.H...L.,.L. - 00a0 e94d89f5 4901cd48 894c2488 4c89e94d .M..I..H.L$.L..M - 00b0 89f54901 cd48894c 24904c89 c948c1f9 ..I..H.L$.L..H.. - 00c0 044183e1 0f48894c 24704c89 4c24504c .A...H.L$pL.L$PL - 00d0 89f149c1 e10748c1 e1034c89 8c24b801 ..I...H...L..$.. - 00e0 00004c8b 8c24c001 00004889 8c24a001 ..L..$....H..$.. - 00f0 0000488b 4c245849 c1e10449 01c94c89 ..H.L$XI...I..L. - 0100 8c248000 00004c8b 8c249800 00004901 .$....L..$....I. - 0110 cc4f8d24 e14801cd 498d2ce9 4c89a424 .O.$.H..I.,.L..$ - 0120 a8000000 4989cc48 89ac24b8 0000004c ....I..H..$....L - 0130 89e54c01 e34801ea 4d89cc48 01e8498d ..L..H..M..H..I. - 0140 14d44889 94244801 00004901 eb498d14 ..H..$H...I..I.. - 0150 c44901ea 488b4424 884c89c9 4f8d1cd9 .I..H.D$.L..O... - 0160 4f8d14d1 498d1cd9 4c8b4c24 984801e8 O...I...L.L$.H.. - 0170 4901e948 89942458 01000049 8d14c448 I..H..$X...I...H - 0180 8b442490 4801ee4c 899424e8 00000049 .D$.H..L..$....I - 0190 01e84e8d 14c94801 ef4c899c 24d80000 ..N...H..L..$... - 01a0 004c8994 24f80000 004c8d1c f14e8d14 .L..$....L...N.. - 01b0 c1488d3c f94801e8 488b4c24 a0498d04 .H.<.H..H.L$.I.. - 01c0 c44801e9 48898424 78010000 498d442d .H..H..$x...I.D- - 01d0 004c899c 24280100 00498d04 c44d8d1c .L..$(...I...M.. - 01e0 cc4c8994 24080100 00488984 24880100 .L..$....H..$... - 01f0 0048899c 24c80000 004889bc 24180100 .H..$....H..$... - 0200 004c899c 24380100 00488994 24680100 .L..$8...H..$h.. - 0210 00488bb4 24880000 00488b4c 24c04a8d .H..$....H.L$.J. - 0220 042e4801 e8498d04 c4488984 24980100 ..H..I...H..$... - 0230 004889f0 480fafc5 49c1e607 4c8b4c24 .H..H...I...L.L$ - 0240 704801c8 498d04c4 48898424 a0000000 pH..I...H..$.... - 0250 488d4501 480fafc6 48896c24 9048c744 H.E.H...H.l$.H.D - 0260 24680000 00004801 c8498d04 c4488984 $h....H..I...H.. - 0270 24b00000 00488d45 02480faf c648c744 $....H.E.H...H.D - 0280 24600000 0000c5fb 10050000 00004801 $`............H. - 0290 c8498d04 c4488984 24c00000 00488d45 .I...H..$....H.E - 02a0 03480faf c64d89fa 4801c849 8d04c448 .H...M..H..I...H - 02b0 898424d0 00000048 8d450448 0fafc648 ..$....H.E.H...H - 02c0 01c8498d 04c44889 8424e000 0000488d ..I...H..$....H. - 02d0 4505480f afc64801 c8498d04 c4488984 E.H...H..I...H.. - 02e0 24f00000 00488d45 06480faf c64801c8 $....H.E.H...H.. - 02f0 498d04c4 48898424 00010000 488d4507 I...H..$....H.E. - 0300 480fafc6 4801c849 8d04c448 89842410 H...H..I...H..$. - 0310 01000048 8d450848 0fafc648 01c8498d ...H.E.H...H..I. - 0320 04c44889 84242001 0000488d 4509480f ..H..$ ...H.E.H. - 0330 afc64801 c8498d04 c4488984 24300100 ..H..I...H..$0.. - 0340 00488d45 0a480faf c64801c8 498d04c4 .H.E.H...H..I... - 0350 48898424 40010000 488d450b 480fafc6 H..$@...H.E.H... - 0360 4801c849 8d04c448 89842450 01000048 H..I...H..$P...H - 0370 8d450c48 0fafc648 01c8498d 04c44889 .E.H...H..I...H. - 0380 84246001 0000488d 450d480f afc64801 .$`...H.E.H...H. - 0390 c8498d04 c4488984 24700100 00488d45 .I...H..$p...H.E - 03a0 0e480faf c64801c8 498d04c4 48898424 .H...H..I...H..$ - 03b0 80010000 488d450f 480fafc6 488b7424 ....H.E.H...H.t$ - 03c0 784801c8 498d04c4 48898424 90010000 xH..I...H..$.... - 03d0 4889f048 83e0f048 01c84889 4424d04c H..H...H..H.D$.L - 03e0 89c848c1 e00b4889 8424b001 00004c89 ..H...H..$....L. - 03f0 c848c1e0 044801c8 48898424 a8010000 .H...H..H..$.... - 0400 4889f083 e00e4889 8424c801 00004889 H.....H..$....H. - 0410 f083e00c 83e60848 89b424d8 01000048 .......H..$....H - 0420 898424d0 0100004c 89f6e91f 01000090 ..$....L........ - 0430 488b4424 60488bbc 24b00000 004c8b8c H.D$`H..$....L.. - 0440 24a00000 004801c7 48897c24 98488bbc $....H..H.|$.H.. - 0450 24c00000 00488b8c 24100100 004801c7 $....H..$....H.. - 0460 48897c24 a0488bbc 24d00000 004c8bbc H.|$.H..$....L.. - 0470 24200100 004801c7 48897c24 a8488bbc $ ...H..H.|$.H.. - 0480 24e00000 004c8bb4 24300100 004801c7 $....L..$0...H.. - 0490 48897c24 b0488bbc 24f00000 004c8bac H.|$.H..$....L.. - 04a0 24400100 004801c7 48897c24 c84c8ba4 $@...H..H.|$.L.. - 04b0 24500100 00488bbc 24000100 00488bac $P...H..$....H.. - 04c0 24600100 00488b9c 24700100 004c8b9c $`...H..$p...L.. - 04d0 24800100 004901c1 4801c748 01c14901 $....I..H..H..I. - 04e0 c74901c6 4901c549 01c44801 c54801c3 .I..I..I..H..H.. - 04f0 4901c348 03842490 01000048 837c2470 I..H..$....H.|$p - 0500 004889c2 488b4424 c00f8f2e 01000048 .H..H.D$.......H - 0510 837c2450 00741348 39442490 0f8e4e10 .|$P.t.H9D$...N. - 0520 00004c03 9424b801 00004883 44249010 ..L..$....H.D$.. - 0530 48017424 6048836c 24688048 8b442490 H.t$`H.l$h.H.D$. - 0540 483b8424 80000000 0f849a19 0000488b H;.$..........H. - 0550 7c24c048 397c2490 0f8dd2fe ffff488b |$.H9|$.......H. - 0560 44246848 8b9c24b8 00000048 8bbc24c8 D$hH..$....H..$. - 0570 00000048 01c34889 5c249848 8b9c24d8 ...H..H.\$.H..$. - 0580 00000048 01c74801 c348897c 24a04889 ...H..H..H.|$.H. - 0590 5c24a848 8bbc24e8 00000048 8b9c24f8 \$.H..$....H..$. - 05a0 00000048 01c74801 c348897c 24b04889 ...H..H..H.|$.H. - 05b0 5c24c84c 8b8c24a8 00000048 8bbc2408 \$.L..$....H..$. - 05c0 01000048 8b8c2418 0100004c 8bbc2428 ...H..$....L..$( - 05d0 0100004c 8bb42438 0100004c 8bac2448 ...L..$8...L..$H - 05e0 0100004c 8ba42458 01000048 8bac2468 ...L..$X...H..$h - 05f0 01000048 8b9c2478 0100004c 8b9c2488 ...H..$x...L..$. - 0600 01000049 01c14801 c74801c1 4901c749 ...I..H..H..I..I - 0610 01c64901 c54901c4 4801c548 01c34901 ..I..I..H..H..I. - 0620 c3480384 24980100 0048837c 24700048 .H..$....H.|$p.H - 0630 89c2488b 4424c00f 8ed2feff ff4c894c ..H.D$.......L.L - 0640 24b84c89 94241802 00004d8d 82000800 $.L..$....M..... - 0650 004989d1 4d89da48 89442488 488b5424 .I..M..H.D$.H.T$ - 0660 c84989f3 eb71662e 0f1f8400 00000000 .I...qf......... - 0670 48836c24 b8804883 6c249880 48836c24 H.l$..H.l$..H.l$ - 0680 a0804883 6c24a880 48836c24 b0804883 ..H.l$..H.l$..H. - 0690 ea804883 ef804883 e9804983 ef804983 ..H...H...I...I. - 06a0 ee804983 ed804983 ec804883 ed804883 ..I...I...H...H. - 06b0 eb804983 ea804983 e9804883 44248810 ..I...I...H.D$.. - 06c0 4981c000 08000048 8b442488 483b4424 I......H.D$.H;D$ - 06d0 d00f8469 0e000049 8d8000f8 ffff4889 ...i...I......H. - 06e0 4424c848 8b442488 48394424 907f8148 D$.H.D$.H9D$...H - 06f0 8b442498 488b7424 884c01d8 48894424 .D$.H.t$.L..H.D$ - 0700 38488b44 24a04c01 d8488904 24488b44 8H.D$.L..H..$H.D - 0710 24a84c01 d8488944 2420488b 4424b04c $.L..H.D$ H.D$.L - 0720 01d84889 4424f04a 8d041a48 89442430 ..H.D$.J...H.D$0 - 0730 4a8d041f 48894424 f84a8d04 19488944 J...H.D$.J...H.D - 0740 24284b8d 041f4889 4424184b 8d041e48 $(K...H.D$.K...H - 0750 894424e8 4b8d441d 00488944 24104b8d .D$.K.D..H.D$.K. - 0760 041c4889 4424e04a 8d441d00 48894424 ..H.D$.J.D..H.D$ - 0770 084a8d04 1b488944 24d84b8d 041a4889 .J...H.D$.K...H. - 0780 4424484b 8d041948 89442440 48397424 D$HK...H.D$@H9t$ - 0790 900f8cd9 0c000049 c78008f8 ffff0000 .......I........ - 07a0 000049c7 8010f8ff ff000000 0049c780 ..I..........I.. - 07b0 18f8ffff 00000000 49c78020 f8ffff00 ........I.. .... - 07c0 00000049 c78028f8 ffff0000 000049c7 ...I..(.......I. - 07d0 8030f8ff ff000000 0049c780 38f8ffff .0.......I..8... - 07e0 00000000 49c78040 f8ffff00 00000049 ....I..@.......I - 07f0 c78048f8 ffff0000 000049c7 8050f8ff ..H.......I..P.. - 0800 ff000000 0049c780 58f8ffff 00000000 .....I..X....... - 0810 49c78060 f8ffff00 00000049 c78068f8 I..`.......I..h. - 0820 ffff0000 000049c7 8070f8ff ff000000 ......I..p...... - 0830 0049c780 78f8ffff 00000000 488b4424 .I..x.......H.D$ - 0840 98c4c17b 118000f8 ffffc5fb 100849c7 ...{..........I. - 0850 8090f8ff ff000000 00c4c17b 118880f8 ...........{.... - 0860 ffff49c7 8098f8ff ff000000 0049c780 ..I..........I.. - 0870 a0f8ffff 00000000 49c780a8 f8ffff00 ........I....... - 0880 00000049 c780b0f8 ffff0000 000049c7 ...I..........I. - 0890 80b8f8ff ff000000 0049c780 c0f8ffff .........I...... - 08a0 00000000 49c780c8 f8ffff00 00000049 ....I..........I - 08b0 c780d0f8 ffff0000 000049c7 80d8f8ff ..........I..... - 08c0 ff000000 0049c780 e0f8ffff 00000000 .....I.......... - 08d0 49c780e8 f8ffff00 000000c4 c17b1180 I............{.. - 08e0 88f8ffff 49c780f0 f8ffff00 00000049 ....I..........I - 08f0 c780f8f8 ffff0000 0000488b 4424a0c5 ..........H.D$.. - 0900 fb1008c4 c17b1188 00f9ffff c5fb1048 .....{.........H - 0910 0849c780 18f9ffff 00000000 49c78020 .I..........I.. - 0920 f9ffff00 00000049 c78028f9 ffff0000 .......I..(..... - 0930 000049c7 8030f9ff ff000000 0049c780 ..I..0.......I.. - 0940 38f9ffff 00000000 49c78040 f9ffff00 8.......I..@.... - 0950 00000049 c78048f9 ffff0000 000049c7 ...I..H.......I. - 0960 8050f9ff ff000000 0049c780 58f9ffff .P.......I..X... - 0970 00000000 49c78060 f9ffff00 00000049 ....I..`.......I - 0980 c78068f9 ffff0000 000049c7 8070f9ff ..h.......I..p.. - 0990 ff000000 0049c780 78f9ffff 00000000 .....I..x....... - 09a0 488b4424 a8c4c17b 118808f9 ffffc4c1 H.D$...{........ - 09b0 7b118010 f9ffffc5 fb1008c4 c17b1188 {............{.. - 09c0 80f9ffff c5fb1048 08c4c17b 118888f9 .......H...{.... - 09d0 ffffc5fb 10481049 c780a0f9 ffff0000 .....H.I........ - 09e0 0000c4c1 7b118890 f9ffff49 c780a8f9 ....{......I.... - 09f0 ffff0000 000049c7 80b0f9ff ff000000 ......I......... - 0a00 0049c780 b8f9ffff 00000000 c4c17b11 .I............{. - 0a10 8098f9ff ff49c780 c0f9ffff 00000000 .....I.......... - 0a20 49c780c8 f9ffff00 00000049 c780d0f9 I..........I.... - 0a30 ffff0000 000049c7 80d8f9ff ff000000 ......I......... - 0a40 0049c780 e0f9ffff 00000000 49c780e8 .I..........I... - 0a50 f9ffff00 00000049 c780f0f9 ffff0000 .......I........ - 0a60 000049c7 80f8f9ff ff000000 00488b44 ..I..........H.D - 0a70 24b0c5fb 1008c4c1 7b118800 faffffc5 $.......{....... - 0a80 fb104808 c4c17b11 8808faff ffc5fb10 ..H...{......... - 0a90 4810c4c1 7b118810 faffffc5 fb104818 H...{.........H. - 0aa0 49c78028 faffff00 00000049 c78030fa I..(.......I..0. - 0ab0 ffff0000 000049c7 8038faff ff000000 ......I..8...... - 0ac0 0049c780 40faffff 00000000 49c78048 .I..@.......I..H - 0ad0 faffff00 00000049 c78050fa ffff0000 .......I..P..... - 0ae0 000049c7 8058faff ff000000 0049c780 ..I..X.......I.. - 0af0 60faffff 00000000 49c78068 faffff00 `.......I..h.... - 0b00 00000049 c78070fa ffff0000 000049c7 ...I..p.......I. - 0b10 8078faff ff000000 00c4c17b 118818fa .x.........{.... - 0b20 ffffc4c1 7b118020 faffffc5 fb100ac4 ....{.. ........ - 0b30 c17b1188 80faffff c5fb104a 08c4c17b .{.........J...{ - 0b40 118888fa ffffc5fb 104a10c4 c17b1188 .........J...{.. - 0b50 90faffff c5fb104a 18c4c17b 118898fa .......J...{.... - 0b60 ffffc5fb 104a2049 c780b0fa ffff0000 .....J I........ - 0b70 000049c7 80b8faff ff000000 0049c780 ..I..........I.. - 0b80 c0faffff 00000000 49c780c8 faffff00 ........I....... - 0b90 00000049 c780d0fa ffff0000 000049c7 ...I..........I. - 0ba0 80d8faff ff000000 0049c780 e0faffff .........I...... - 0bb0 00000000 49c780e8 faffff00 00000049 ....I..........I - 0bc0 c780f0fa ffff0000 000049c7 80f8faff ..........I..... - 0bd0 ff000000 00c4c17b 1188a0fa ffffc4c1 .......{........ - 0be0 7b1180a8 faffffc5 fb100fc4 c17b1188 {............{.. - 0bf0 00fbffff c5fb104f 08c4c17b 118808fb .......O...{.... - 0c00 ffffc5fb 104f10c4 c17b1188 10fbffff .....O...{...... - 0c10 c5fb104f 18c4c17b 118818fb ffffc5fb ...O...{........ /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 292e0000 00420e10 8f02420e ....)....B....B. + 0020 00000000 cb070000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 75270a0e ..A.8..G....u'.. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0040 8606410e 38830744 0e7003f6 050a0e38 ..A.8..D.p.....8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08480b 00000000 ..H..... /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_SKYLAKEX.o (disasm) @@ -12,1652 +12,351 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdi,offset(%rsp) + mov %rdi,(%rsp) mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,-offset(%rsp) - mov %r9,offset(%rsp) + mov %rcx,-offset(%rsp) + mov %r9,-offset(%rsp) mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov offset(%rsp),%rbx test %rsi,%rsi jle - mov %r8,%r12 - imul %rcx,%r12 + mov %rcx,%rax mov %rcx,%r14 - mov offset(%rsp),%r9 - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - lea (%rcx,%rbx,1),%r11 - lea (%r11,%rcx,1),%r10 - lea (%rcx,%r10,1),%rax - lea (%rax,%rcx,1),%r8 - lea (%rcx,%r8,1),%rdi - lea (%rcx,%rdi,1),%rsi - mov %rax,-offset(%rsp) - lea (%rcx,%rsi,1),%rax - lea (%rcx,%rax,1),%rdx - mov %rax,-offset(%rsp) - lea (%rcx,%rdx,1),%rax - lea (%rcx,%rax,1),%r13 - mov %r13,%rcx - mov %r14,%r13 - add %rcx,%r13 - mov %rcx,-offset(%rsp) - mov %r13,%rcx - mov %r14,%r13 - add %rcx,%r13 - mov %rcx,-offset(%rsp) - mov %r9,%rcx - sar $something,%rcx - and $something,%r9d - mov %rcx,offset(%rsp) - mov %r9,offset(%rsp) - mov %r14,%rcx - shl $something,%r9 + mov %rsi,%r13 + mov %rcx,%r11 + mov %rdi,%rsi shl $something,%rcx - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 + imul %r8,%rax mov %rcx,offset(%rsp) - mov offset(%rsp),%rcx - shl $something,%r9 - add %rcx,%r9 - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add %rcx,%r12 - lea (%r9,%r12,8),%r12 - add %rcx,%rbp - lea (%r9,%rbp,8),%rbp - mov %r12,offset(%rsp) - mov %rcx,%r12 - mov %rbp,offset(%rsp) - mov %r12,%rbp - add %r12,%rbx - add %rbp,%rdx - mov %r9,%r12 - add %rbp,%rax - lea (%r12,%rdx,8),%rdx - mov %rdx,offset(%rsp) - add %rbp,%r11 - lea (%r12,%rax,8),%rdx - add %rbp,%r10 - mov -offset(%rsp),%rax - mov %r9,%rcx - lea (%r9,%r11,8),%r11 - lea (%r9,%r10,8),%r10 - lea (%r9,%rbx,8),%rbx - mov -offset(%rsp),%r9 - add %rbp,%rax - add %rbp,%r9 - mov %rdx,offset(%rsp) - lea (%r12,%rax,8),%rdx - mov -offset(%rsp),%rax - add %rbp,%rsi - mov %r10,offset(%rsp) - add %rbp,%r8 - lea (%rcx,%r9,8),%r10 - add %rbp,%rdi - mov %r11,offset(%rsp) - mov %r10,offset(%rsp) - lea (%rcx,%rsi,8),%r11 - lea (%rcx,%r8,8),%r10 - lea (%rcx,%rdi,8),%rdi - add %rbp,%rax - mov -offset(%rsp),%rcx - lea (%r12,%rax,8),%rax - add %rbp,%rcx - mov %rax,offset(%rsp) - lea offset(%r13,%rbp,1),%rax - mov %r11,offset(%rsp) - lea (%r12,%rax,8),%rax - lea (%r12,%rcx,8),%r11 - mov %r10,offset(%rsp) - mov %rax,offset(%rsp) - mov %rbx,offset(%rsp) - mov %rdi,offset(%rsp) - mov %r11,offset(%rsp) - mov %rdx,offset(%rsp) - mov offset(%rsp),%rsi - mov -offset(%rsp),%rcx - lea (%rsi,%r13,1),%rax - add %rbp,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - mov %rsi,%rax - imul %rbp,%rax - shl $something,%r14 - mov offset(%rsp),%r9 - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rbp,-offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - movq $something,offset(%rsp) - vmovsd offset(%rip),%xmm0 # - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - mov %r15,%r10 - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - add %rcx,%rax - lea (%r12,%rax,8),%rax - mov %rax,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_SKYLAKEX.o (objdump) @@ -2,742 +2,128 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24900000 0048c1fe 0448897c .H..$....H...H.| - 0020 24784889 94249800 00004889 8c248800 $xH..$....H..$.. - 0030 00004c89 4424c04c 894c2458 4889b424 ..L.D$.L.L$XH..$ - 0040 c0010000 4c8bbc24 18020000 4885f60f ....L..$....H... - 0050 8eaf1e00 004d89c4 4c0fafe1 4989ce4c .....M..L...I..L - 0060 8b4c2478 4a8d2c21 488d1c29 4c8d1c19 .L$xJ.,!H..)L... - 0070 4d8d140b 4a8d0411 4c8d0408 4a8d3c01 M...J...L...J.<. - 0080 488d3439 48894424 98488d04 31488d14 H.49H.D$.H..1H.. - 0090 01488944 24a0488d 04114c8d 2c014c89 .H.D$.H...L.,.L. - 00a0 e94d89f5 4901cd48 894c2488 4c89e94d .M..I..H.L$.L..M - 00b0 89f54901 cd48894c 24904c89 c948c1f9 ..I..H.L$.L..H.. - 00c0 044183e1 0f48894c 24704c89 4c24504c .A...H.L$pL.L$PL - 00d0 89f149c1 e10748c1 e1034c89 8c24b801 ..I...H...L..$.. - 00e0 00004c8b 8c24c001 00004889 8c24a001 ..L..$....H..$.. - 00f0 0000488b 4c245849 c1e10449 01c94c89 ..H.L$XI...I..L. - 0100 8c248000 00004c8b 8c249800 00004901 .$....L..$....I. - 0110 cc4f8d24 e14801cd 498d2ce9 4c89a424 .O.$.H..I.,.L..$ - 0120 a8000000 4989cc48 89ac24b8 0000004c ....I..H..$....L - 0130 89e54c01 e34801ea 4d89cc48 01e8498d ..L..H..M..H..I. - 0140 14d44889 94244801 00004901 eb498d14 ..H..$H...I..I.. - 0150 c44901ea 488b4424 884c89c9 4f8d1cd9 .I..H.D$.L..O... - 0160 4f8d14d1 498d1cd9 4c8b4c24 984801e8 O...I...L.L$.H.. - 0170 4901e948 89942458 01000049 8d14c448 I..H..$X...I...H - 0180 8b442490 4801ee4c 899424e8 00000049 .D$.H..L..$....I - 0190 01e84e8d 14c94801 ef4c899c 24d80000 ..N...H..L..$... - 01a0 004c8994 24f80000 004c8d1c f14e8d14 .L..$....L...N.. - 01b0 c1488d3c f94801e8 488b4c24 a0498d04 .H.<.H..H.L$.I.. - 01c0 c44801e9 48898424 78010000 498d442d .H..H..$x...I.D- - 01d0 004c899c 24280100 00498d04 c44d8d1c .L..$(...I...M.. - 01e0 cc4c8994 24080100 00488984 24880100 .L..$....H..$... - 01f0 0048899c 24c80000 004889bc 24180100 .H..$....H..$... - 0200 004c899c 24380100 00488994 24680100 .L..$8...H..$h.. - 0210 00488bb4 24880000 00488b4c 24c04a8d .H..$....H.L$.J. - 0220 042e4801 e8498d04 c4488984 24980100 ..H..I...H..$... - 0230 004889f0 480fafc5 49c1e607 4c8b4c24 .H..H...I...L.L$ - 0240 704801c8 498d04c4 48898424 a0000000 pH..I...H..$.... - 0250 488d4501 480fafc6 48896c24 9048c744 H.E.H...H.l$.H.D - 0260 24680000 00004801 c8498d04 c4488984 $h....H..I...H.. - 0270 24b00000 00488d45 02480faf c648c744 $....H.E.H...H.D - 0280 24600000 0000c5fb 10050000 00004801 $`............H. - 0290 c8498d04 c4488984 24c00000 00488d45 .I...H..$....H.E - 02a0 03480faf c64d89fa 4801c849 8d04c448 .H...M..H..I...H - 02b0 898424d0 00000048 8d450448 0fafc648 ..$....H.E.H...H - 02c0 01c8498d 04c44889 8424e000 0000488d ..I...H..$....H. - 02d0 4505480f afc64801 c8498d04 c4488984 E.H...H..I...H.. - 02e0 24f00000 00488d45 06480faf c64801c8 $....H.E.H...H.. - 02f0 498d04c4 48898424 00010000 488d4507 I...H..$....H.E. - 0300 480fafc6 4801c849 8d04c448 89842410 H...H..I...H..$. - 0310 01000048 8d450848 0fafc648 01c8498d ...H.E.H...H..I. - 0320 04c44889 84242001 0000488d 4509480f ..H..$ ...H.E.H. - 0330 afc64801 c8498d04 c4488984 24300100 ..H..I...H..$0.. - 0340 00488d45 0a480faf c64801c8 498d04c4 .H.E.H...H..I... - 0350 48898424 40010000 488d450b 480fafc6 H..$@...H.E.H... - 0360 4801c849 8d04c448 89842450 01000048 H..I...H..$P...H - 0370 8d450c48 0fafc648 01c8498d 04c44889 .E.H...H..I...H. - 0380 84246001 0000488d 450d480f afc64801 .$`...H.E.H...H. - 0390 c8498d04 c4488984 24700100 00488d45 .I...H..$p...H.E - 03a0 0e480faf c64801c8 498d04c4 48898424 .H...H..I...H..$ - 03b0 80010000 488d450f 480fafc6 488b7424 ....H.E.H...H.t$ - 03c0 784801c8 498d04c4 48898424 90010000 xH..I...H..$.... - 03d0 4889f048 83e0f048 01c84889 4424d04c H..H...H..H.D$.L - 03e0 89c848c1 e00b4889 8424b001 00004c89 ..H...H..$....L. - 03f0 c848c1e0 044801c8 48898424 a8010000 .H...H..H..$.... - 0400 4889f083 e00e4889 8424c801 00004889 H.....H..$....H. - 0410 f083e00c 83e60848 89b424d8 01000048 .......H..$....H - 0420 898424d0 0100004c 89f6e91f 01000090 ..$....L........ - 0430 488b4424 60488bbc 24b00000 004c8b8c H.D$`H..$....L.. - 0440 24a00000 004801c7 48897c24 98488bbc $....H..H.|$.H.. - 0450 24c00000 00488b8c 24100100 004801c7 $....H..$....H.. - 0460 48897c24 a0488bbc 24d00000 004c8bbc H.|$.H..$....L.. - 0470 24200100 004801c7 48897c24 a8488bbc $ ...H..H.|$.H.. - 0480 24e00000 004c8bb4 24300100 004801c7 $....L..$0...H.. - 0490 48897c24 b0488bbc 24f00000 004c8bac H.|$.H..$....L.. - 04a0 24400100 004801c7 48897c24 c84c8ba4 $@...H..H.|$.L.. - 04b0 24500100 00488bbc 24000100 00488bac $P...H..$....H.. - 04c0 24600100 00488b9c 24700100 004c8b9c $`...H..$p...L.. - 04d0 24800100 004901c1 4801c748 01c14901 $....I..H..H..I. - 04e0 c74901c6 4901c549 01c44801 c54801c3 .I..I..I..H..H.. - 04f0 4901c348 03842490 01000048 837c2470 I..H..$....H.|$p - 0500 004889c2 488b4424 c00f8f2e 01000048 .H..H.D$.......H - 0510 837c2450 00741348 39442490 0f8e4e10 .|$P.t.H9D$...N. - 0520 00004c03 9424b801 00004883 44249010 ..L..$....H.D$.. - 0530 48017424 6048836c 24688048 8b442490 H.t$`H.l$h.H.D$. - 0540 483b8424 80000000 0f849a19 0000488b H;.$..........H. - 0550 7c24c048 397c2490 0f8dd2fe ffff488b |$.H9|$.......H. - 0560 44246848 8b9c24b8 00000048 8bbc24c8 D$hH..$....H..$. - 0570 00000048 01c34889 5c249848 8b9c24d8 ...H..H.\$.H..$. - 0580 00000048 01c74801 c348897c 24a04889 ...H..H..H.|$.H. - 0590 5c24a848 8bbc24e8 00000048 8b9c24f8 \$.H..$....H..$. - 05a0 00000048 01c74801 c348897c 24b04889 ...H..H..H.|$.H. - 05b0 5c24c84c 8b8c24a8 00000048 8bbc2408 \$.L..$....H..$. - 05c0 01000048 8b8c2418 0100004c 8bbc2428 ...H..$....L..$( - 05d0 0100004c 8bb42438 0100004c 8bac2448 ...L..$8...L..$H - 05e0 0100004c 8ba42458 01000048 8bac2468 ...L..$X...H..$h - 05f0 01000048 8b9c2478 0100004c 8b9c2488 ...H..$x...L..$. - 0600 01000049 01c14801 c74801c1 4901c749 ...I..H..H..I..I - 0610 01c64901 c54901c4 4801c548 01c34901 ..I..I..H..H..I. - 0620 c3480384 24980100 0048837c 24700048 .H..$....H.|$p.H - 0630 89c2488b 4424c00f 8ed2feff ff4c894c ..H.D$.......L.L - 0640 24b84c89 94241802 00004d8d 82000800 $.L..$....M..... - 0650 004989d1 4d89da48 89442488 488b5424 .I..M..H.D$.H.T$ - 0660 c84989f3 eb71662e 0f1f8400 00000000 .I...qf......... - 0670 48836c24 b8804883 6c249880 48836c24 H.l$..H.l$..H.l$ - 0680 a0804883 6c24a880 48836c24 b0804883 ..H.l$..H.l$..H. - 0690 ea804883 ef804883 e9804983 ef804983 ..H...H...I...I. - 06a0 ee804983 ed804983 ec804883 ed804883 ..I...I...H...H. - 06b0 eb804983 ea804983 e9804883 44248810 ..I...I...H.D$.. - 06c0 4981c000 08000048 8b442488 483b4424 I......H.D$.H;D$ - 06d0 d00f8469 0e000049 8d8000f8 ffff4889 ...i...I......H. - 06e0 4424c848 8b442488 48394424 907f8148 D$.H.D$.H9D$...H - 06f0 8b442498 488b7424 884c01d8 48894424 .D$.H.t$.L..H.D$ - 0700 38488b44 24a04c01 d8488904 24488b44 8H.D$.L..H..$H.D - 0710 24a84c01 d8488944 2420488b 4424b04c $.L..H.D$ H.D$.L - 0720 01d84889 4424f04a 8d041a48 89442430 ..H.D$.J...H.D$0 - 0730 4a8d041f 48894424 f84a8d04 19488944 J...H.D$.J...H.D - 0740 24284b8d 041f4889 4424184b 8d041e48 $(K...H.D$.K...H - 0750 894424e8 4b8d441d 00488944 24104b8d .D$.K.D..H.D$.K. - 0760 041c4889 4424e04a 8d441d00 48894424 ..H.D$.J.D..H.D$ - 0770 084a8d04 1b488944 24d84b8d 041a4889 .J...H.D$.K...H. - 0780 4424484b 8d041948 89442440 48397424 D$HK...H.D$@H9t$ - 0790 900f8cd9 0c000049 c78008f8 ffff0000 .......I........ - 07a0 000049c7 8010f8ff ff000000 0049c780 ..I..........I.. - 07b0 18f8ffff 00000000 49c78020 f8ffff00 ........I.. .... - 07c0 00000049 c78028f8 ffff0000 000049c7 ...I..(.......I. - 07d0 8030f8ff ff000000 0049c780 38f8ffff .0.......I..8... - 07e0 00000000 49c78040 f8ffff00 00000049 ....I..@.......I - 07f0 c78048f8 ffff0000 000049c7 8050f8ff ..H.......I..P.. - 0800 ff000000 0049c780 58f8ffff 00000000 .....I..X....... - 0810 49c78060 f8ffff00 00000049 c78068f8 I..`.......I..h. - 0820 ffff0000 000049c7 8070f8ff ff000000 ......I..p...... - 0830 0049c780 78f8ffff 00000000 488b4424 .I..x.......H.D$ - 0840 98c4c17b 118000f8 ffffc5fb 100849c7 ...{..........I. - 0850 8090f8ff ff000000 00c4c17b 118880f8 ...........{.... - 0860 ffff49c7 8098f8ff ff000000 0049c780 ..I..........I.. - 0870 a0f8ffff 00000000 49c780a8 f8ffff00 ........I....... - 0880 00000049 c780b0f8 ffff0000 000049c7 ...I..........I. - 0890 80b8f8ff ff000000 0049c780 c0f8ffff .........I...... - 08a0 00000000 49c780c8 f8ffff00 00000049 ....I..........I - 08b0 c780d0f8 ffff0000 000049c7 80d8f8ff ..........I..... - 08c0 ff000000 0049c780 e0f8ffff 00000000 .....I.......... - 08d0 49c780e8 f8ffff00 000000c4 c17b1180 I............{.. - 08e0 88f8ffff 49c780f0 f8ffff00 00000049 ....I..........I - 08f0 c780f8f8 ffff0000 0000488b 4424a0c5 ..........H.D$.. - 0900 fb1008c4 c17b1188 00f9ffff c5fb1048 .....{.........H - 0910 0849c780 18f9ffff 00000000 49c78020 .I..........I.. - 0920 f9ffff00 00000049 c78028f9 ffff0000 .......I..(..... - 0930 000049c7 8030f9ff ff000000 0049c780 ..I..0.......I.. - 0940 38f9ffff 00000000 49c78040 f9ffff00 8.......I..@.... - 0950 00000049 c78048f9 ffff0000 000049c7 ...I..H.......I. - 0960 8050f9ff ff000000 0049c780 58f9ffff .P.......I..X... - 0970 00000000 49c78060 f9ffff00 00000049 ....I..`.......I - 0980 c78068f9 ffff0000 000049c7 8070f9ff ..h.......I..p.. - 0990 ff000000 0049c780 78f9ffff 00000000 .....I..x....... - 09a0 488b4424 a8c4c17b 118808f9 ffffc4c1 H.D$...{........ - 09b0 7b118010 f9ffffc5 fb1008c4 c17b1188 {............{.. - 09c0 80f9ffff c5fb1048 08c4c17b 118888f9 .......H...{.... - 09d0 ffffc5fb 10481049 c780a0f9 ffff0000 .....H.I........ - 09e0 0000c4c1 7b118890 f9ffff49 c780a8f9 ....{......I.... - 09f0 ffff0000 000049c7 80b0f9ff ff000000 ......I......... - 0a00 0049c780 b8f9ffff 00000000 c4c17b11 .I............{. - 0a10 8098f9ff ff49c780 c0f9ffff 00000000 .....I.......... - 0a20 49c780c8 f9ffff00 00000049 c780d0f9 I..........I.... - 0a30 ffff0000 000049c7 80d8f9ff ff000000 ......I......... - 0a40 0049c780 e0f9ffff 00000000 49c780e8 .I..........I... - 0a50 f9ffff00 00000049 c780f0f9 ffff0000 .......I........ - 0a60 000049c7 80f8f9ff ff000000 00488b44 ..I..........H.D - 0a70 24b0c5fb 1008c4c1 7b118800 faffffc5 $.......{....... - 0a80 fb104808 c4c17b11 8808faff ffc5fb10 ..H...{......... - 0a90 4810c4c1 7b118810 faffffc5 fb104818 H...{.........H. - 0aa0 49c78028 faffff00 00000049 c78030fa I..(.......I..0. - 0ab0 ffff0000 000049c7 8038faff ff000000 ......I..8...... - 0ac0 0049c780 40faffff 00000000 49c78048 .I..@.......I..H - 0ad0 faffff00 00000049 c78050fa ffff0000 .......I..P..... - 0ae0 000049c7 8058faff ff000000 0049c780 ..I..X.......I.. - 0af0 60faffff 00000000 49c78068 faffff00 `.......I..h.... - 0b00 00000049 c78070fa ffff0000 000049c7 ...I..p.......I. - 0b10 8078faff ff000000 00c4c17b 118818fa .x.........{.... - 0b20 ffffc4c1 7b118020 faffffc5 fb100ac4 ....{.. ........ - 0b30 c17b1188 80faffff c5fb104a 08c4c17b .{.........J...{ - 0b40 118888fa ffffc5fb 104a10c4 c17b1188 .........J...{.. - 0b50 90faffff c5fb104a 18c4c17b 118898fa .......J...{.... - 0b60 ffffc5fb 104a2049 c780b0fa ffff0000 .....J I........ - 0b70 000049c7 80b8faff ff000000 0049c780 ..I..........I.. - 0b80 c0faffff 00000000 49c780c8 faffff00 ........I....... - 0b90 00000049 c780d0fa ffff0000 000049c7 ...I..........I. - 0ba0 80d8faff ff000000 0049c780 e0faffff .........I...... - 0bb0 00000000 49c780e8 faffff00 00000049 ....I..........I - 0bc0 c780f0fa ffff0000 000049c7 80f8faff ..........I..... - 0bd0 ff000000 00c4c17b 1188a0fa ffffc4c1 .......{........ - 0be0 7b1180a8 faffffc5 fb100fc4 c17b1188 {............{.. - 0bf0 00fbffff c5fb104f 08c4c17b 118808fb .......O...{.... - 0c00 ffffc5fb 104f10c4 c17b1188 10fbffff .....O...{...... - 0c10 c5fb104f 18c4c17b 118818fb ffffc5fb ...O...{........ /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_iutucopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 292e0000 00420e10 8f02420e ....)....B....B. + 0020 00000000 cb070000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 75270a0e ..A.8..G....u'.. - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0040 8606410e 38830744 0e7003f6 050a0e38 ..A.8..D.p.....8 + 0050 410e3041 0e28420e 20420e18 420e1044 A.0A.(B. B..B..D + 0060 0e08480b 00000000 ..H..... /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_COOPERLAKE.o (disasm) @@ -11,79 +11,900 @@ push %r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,-offset(%rsp) + mov %r9,offset(%rsp) + mov %rsi,offset(%rsp) mov offset(%rsp),%rbp test %rsi,%rsi jle - mov %rcx,%rax - imul %r8,%rax - mov %rdi,%r13 - mov %rcx,%r12 - add %r9,%rax - lea (%rdx,%rax,8),%rbx - mov %rcx,%rax - imul %r9,%rax - neg %rcx - sar %r13 - add %r8,%rax - lea (%rdx,%rax,8),%r11 - mov %r9,%rax - not %rax - mov %rdi,%r15 - lea offset(,%rcx,8),%rcx - add %r9,%rax - and $something,%rdi - mov %rdi,%r10 + mov %rcx,%rsi + imul %r8,%rsi + mov %rdi,%r12 + mov %r12,%rax + mov %r9,%r15 + and $something,%eax + lea (%rsi,%rcx,2),%rdi + mov %rax,offset(%rsp) + lea (%r15,%rsi,1),%rax + lea (%rdi,%rcx,1),%r8 + lea (%rdx,%rax,8),%r14 + mov %r15,%rax + lea (%r8,%rcx,1),%r9 imul %rcx,%rax - lea (%r8,%r13,2),%rdi - mov %rdi,-offset(%rsp) - mov %r13,%rdi - shl $something,%rdi - mov %rdi,-offset(%rsp) - mov %r9,-offset(%rsp) - lea (%r9,%rsi,2),%r14 - mov %r9,%rdi - mov %rcx,-offset(%rsp) - shl $something,%r12 - and $something,%r15d + lea (%rcx,%r9,1),%r10 + lea (%rcx,%r10,1),%r11 + mov %rcx,%rdx + mov %rcx,%r13 + mov offset(%rsp),%rcx + add -offset(%rsp),%rax + lea (%rcx,%rax,8),%r15 + mov offset(%rsp),%rcx + mov offset(%rsp),%rax + sub %rsi,%rdi + lea (%rcx,%rax,8),%rax + mov %rax,offset(%rsp) + mov %rdx,%rax + neg %rax + lea offset(,%rax,8),%rdx + mov %rdx,%rax + imul %rcx,%rax + mov %rdx,offset(%rsp) + inc %rcx + neg %rdx + imul %rdx,%rcx + lea offset(,%rdi,8),%rdi + mov %rdi,offset(%rsp) + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %r8,%rdi + add $something,%rcx + imul %rdx,%rcx + mov %r12,%rbx + sub %rsi,%rdi + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + sar $something,%rbx + add $something,%rcx + imul %rdx,%rcx + sub %rsi,%r9 + shl $something,%r13 + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + lea offset(,%rdi,8),%rdi + add $something,%rcx + imul %rdx,%rcx + mov %rdi,offset(%rsp) + lea offset(,%r9,8),%rdi + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %rdi,offset(%rsp) + add $something,%rcx + imul %rdx,%rcx + mov -offset(%rsp),%r8 + mov %rbx,offset(%rsp) + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + sub %rsi,%r10 + lea offset(,%r10,8),%rdi + lea (%rcx,%rax,1),%rdx + mov offset(%rsp),%rax + mov %rdi,offset(%rsp) + add %r11,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r11,%rdi + mov %r12,%rax + sub %rsi,%rdi + and $something,%rax + add %r8,%rax + lea offset(,%rdi,8),%rdi + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + mov %r12,%rdi + lea (%r8,%rbx,8),%rax + mov %rax,offset(%rsp) + mov %rdi,%rax + shl $something,%rbx + and $something,%eax + mov %rbx,offset(%rsp) + mov %rdx,offset(%rsp) + mov offset(%rsp),%r12 + mov %rax,offset(%rsp) + mov %rdi,%rax + and $something,%eax + mov %rax,offset(%rsp) + mov %rdi,%rax + and $something,%eax + and $something,%edi + mov %r12,%r9 + vmovsd %xmm30,-offset(%rsp) + mov %r14,%r12 + mov %rax,offset(%rsp) + mov %rdi,offset(%rsp) + mov %r13,%r8 + vmovsd %xmm27,-offset(%rsp) + vmovsd %xmm26,-offset(%rsp) + vmovsd %xmm28,-offset(%rsp) + vmovsd %xmm29,-offset(%rsp) + vmovsd %xmm31,offset(%rsp) + vmovsd %xmm19,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm16,-offset(%rsp) + vmovsd %xmm17,-offset(%rsp) + vmovsd %xmm18,offset(%rsp) + vmovsd %xmm20,-offset(%rsp) + vmovsd %xmm21,-offset(%rsp) + vmovsd %xmm22,(%rsp) + vmovsd %xmm23,offset(%rsp) + vmovsd %xmm24,offset(%rsp) + vmovsd %xmm25,%xmm25,%xmm30 + vmovsd %xmm10,-offset(%rsp) + mov %r15,%r14 + mov %rbp,%rbx + jmp + nop + mov offset(%rsp),%rax + mov %r12,%rcx + lea (%rax,%r12,1),%rsi + mov offset(%rsp),%rax + sub offset(%rsp),%rcx + lea (%rax,%r12,1),%rdi + mov offset(%rsp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_COOPERLAKE.o (objdump) @@ -2,45 +2,456 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e0488b 6c243848 85f60f8e .H.t$.H.l$8H.... - 0030 8b010000 4889c849 0fafc049 89fd4989 ....H..I...I..I. - 0040 cc4c01c8 488d1cc2 4889c849 0fafc148 .L..H...H..I...H - 0050 f7d949d1 fd4c01c0 4c8d1cc2 4c89c848 ..I..L..L...L..H - 0060 f7d04989 ff488d0c cd000000 004c01c8 ..I..H.......L.. - 0070 4883e7fe 4989fa48 0fafc14b 8d3c6848 H...I..H...K..{.b .{.B(b + 0860 e1ff0810 410362e1 ff081049 0462e1ff ....A.b....I.b.. + 0870 08105105 62e1ff08 10590662 e1ff0810 ..Q.b....Y.b.... + 0880 660262e1 ff08106e 0362e1ff 08107604 f.b....n.b....v. + 0890 62e1ff08 107e0562 61ff0810 4606c5fb b....~.ba...F... + 08a0 115c24c0 c5fb114c 24d0c5fb 114424d8 .\$....L$....D$. + 08b0 c57b1174 2488c5fb 11542490 c5fb1174 .{.t$....T$....t + 08c0 24e0c5fb 117c24e8 c57b115c 24f0c57b $....|$..{.\$..{ + 08d0 106e38c5 7b1017c5 7b104f08 6261ff08 .n8.{...{.O.ba.. + 08e0 104f02c5 fb107738 6261ff08 106d0062 .O....w8ba...m.b + 08f0 61ff0810 75016261 ff08107d 02c5fb10 a...u.ba...}.... + 0900 5d18c4c1 7b1012c4 c17b104a 08c4c17b ]...{....{.J...{ + 0910 10421062 61ff0810 57046261 ff08105f .B.ba...W.ba..._ + 0920 056261ff 08106706 c57b116c 24f8c57b .ba...g..{.l$..{ + 0930 111424c5 7b114c24 086261ff 08114c24 ..$.{.L$.ba...L$ + 0940 02c5fb11 74241862 61ff0810 4f036261 ....t$.ba...O.ba + 0950 ff08116c 24046261 ff081174 24056261 ...l$.ba...t$.ba + 0960 ff08106d 046261ff 08107505 6261ff08 ...m.ba...u.ba.. + 0970 117c2406 c5fb115c 24386261 ff08107d .|$....\$8ba...} /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 95020000 00420e10 8f02420e .........B....B. + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 4a1c0000 00420e10 8f02420e ....J....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830703 2f020a0e 30410e28 ..A.8.../...0A.( - 0050 420e2042 0e18420e 10440e08 440b0000 B. B..B..D..D... + 0040 8606410e 38830747 0ec00303 b5150a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_SKYLAKEX.o (disasm) @@ -11,79 +11,900 @@ push %r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,-offset(%rsp) + mov %r9,offset(%rsp) + mov %rsi,offset(%rsp) mov offset(%rsp),%rbp test %rsi,%rsi jle - mov %rcx,%rax - imul %r8,%rax - mov %rdi,%r13 - mov %rcx,%r12 - add %r9,%rax - lea (%rdx,%rax,8),%rbx - mov %rcx,%rax - imul %r9,%rax - neg %rcx - sar %r13 - add %r8,%rax - lea (%rdx,%rax,8),%r11 - mov %r9,%rax - not %rax - mov %rdi,%r15 - lea offset(,%rcx,8),%rcx - add %r9,%rax - and $something,%rdi - mov %rdi,%r10 + mov %rcx,%rsi + imul %r8,%rsi + mov %rdi,%r12 + mov %r12,%rax + mov %r9,%r15 + and $something,%eax + lea (%rsi,%rcx,2),%rdi + mov %rax,offset(%rsp) + lea (%r15,%rsi,1),%rax + lea (%rdi,%rcx,1),%r8 + lea (%rdx,%rax,8),%r14 + mov %r15,%rax + lea (%r8,%rcx,1),%r9 imul %rcx,%rax - lea (%r8,%r13,2),%rdi - mov %rdi,-offset(%rsp) - mov %r13,%rdi - shl $something,%rdi - mov %rdi,-offset(%rsp) - mov %r9,-offset(%rsp) - lea (%r9,%rsi,2),%r14 - mov %r9,%rdi - mov %rcx,-offset(%rsp) - shl $something,%r12 - and $something,%r15d + lea (%rcx,%r9,1),%r10 + lea (%rcx,%r10,1),%r11 + mov %rcx,%rdx + mov %rcx,%r13 + mov offset(%rsp),%rcx + add -offset(%rsp),%rax + lea (%rcx,%rax,8),%r15 + mov offset(%rsp),%rcx + mov offset(%rsp),%rax + sub %rsi,%rdi + lea (%rcx,%rax,8),%rax + mov %rax,offset(%rsp) + mov %rdx,%rax + neg %rax + lea offset(,%rax,8),%rdx + mov %rdx,%rax + imul %rcx,%rax + mov %rdx,offset(%rsp) + inc %rcx + neg %rdx + imul %rdx,%rcx + lea offset(,%rdi,8),%rdi + mov %rdi,offset(%rsp) + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %r8,%rdi + add $something,%rcx + imul %rdx,%rcx + mov %r12,%rbx + sub %rsi,%rdi + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + sar $something,%rbx + add $something,%rcx + imul %rdx,%rcx + sub %rsi,%r9 + shl $something,%r13 + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + lea offset(,%rdi,8),%rdi + add $something,%rcx + imul %rdx,%rcx + mov %rdi,offset(%rsp) + lea offset(,%r9,8),%rdi + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %rdi,offset(%rsp) + add $something,%rcx + imul %rdx,%rcx + mov -offset(%rsp),%r8 + mov %rbx,offset(%rsp) + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + sub %rsi,%r10 + lea offset(,%r10,8),%rdi + lea (%rcx,%rax,1),%rdx + mov offset(%rsp),%rax + mov %rdi,offset(%rsp) + add %r11,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r11,%rdi + mov %r12,%rax + sub %rsi,%rdi + and $something,%rax + add %r8,%rax + lea offset(,%rdi,8),%rdi + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + mov %r12,%rdi + lea (%r8,%rbx,8),%rax + mov %rax,offset(%rsp) + mov %rdi,%rax + shl $something,%rbx + and $something,%eax + mov %rbx,offset(%rsp) + mov %rdx,offset(%rsp) + mov offset(%rsp),%r12 + mov %rax,offset(%rsp) + mov %rdi,%rax + and $something,%eax + mov %rax,offset(%rsp) + mov %rdi,%rax + and $something,%eax + and $something,%edi + mov %r12,%r9 + vmovsd %xmm30,-offset(%rsp) + mov %r14,%r12 + mov %rax,offset(%rsp) + mov %rdi,offset(%rsp) + mov %r13,%r8 + vmovsd %xmm27,-offset(%rsp) + vmovsd %xmm26,-offset(%rsp) + vmovsd %xmm28,-offset(%rsp) + vmovsd %xmm29,-offset(%rsp) + vmovsd %xmm31,offset(%rsp) + vmovsd %xmm19,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm16,-offset(%rsp) + vmovsd %xmm17,-offset(%rsp) + vmovsd %xmm18,offset(%rsp) + vmovsd %xmm20,-offset(%rsp) + vmovsd %xmm21,-offset(%rsp) + vmovsd %xmm22,(%rsp) + vmovsd %xmm23,offset(%rsp) + vmovsd %xmm24,offset(%rsp) + vmovsd %xmm25,%xmm25,%xmm30 + vmovsd %xmm10,-offset(%rsp) + mov %r15,%r14 + mov %rbp,%rbx + jmp + nop + mov offset(%rsp),%rax + mov %r12,%rcx + lea (%rax,%r12,1),%rsi + mov offset(%rsp),%rax + sub offset(%rsp),%rcx + lea (%rax,%r12,1),%rdi + mov offset(%rsp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_SKYLAKEX.o (objdump) @@ -2,45 +2,456 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e0488b 6c243848 85f60f8e .H.t$.H.l$8H.... - 0030 8b010000 4889c849 0fafc049 89fd4989 ....H..I...I..I. - 0040 cc4c01c8 488d1cc2 4889c849 0fafc148 .L..H...H..I...H - 0050 f7d949d1 fd4c01c0 4c8d1cc2 4c89c848 ..I..L..L...L..H - 0060 f7d04989 ff488d0c cd000000 004c01c8 ..I..H.......L.. - 0070 4883e7fe 4989fa48 0fafc14b 8d3c6848 H...I..H...K..{.b .{.B(b + 0860 e1ff0810 410362e1 ff081049 0462e1ff ....A.b....I.b.. + 0870 08105105 62e1ff08 10590662 e1ff0810 ..Q.b....Y.b.... + 0880 660262e1 ff08106e 0362e1ff 08107604 f.b....n.b....v. + 0890 62e1ff08 107e0562 61ff0810 4606c5fb b....~.ba...F... + 08a0 115c24c0 c5fb114c 24d0c5fb 114424d8 .\$....L$....D$. + 08b0 c57b1174 2488c5fb 11542490 c5fb1174 .{.t$....T$....t + 08c0 24e0c5fb 117c24e8 c57b115c 24f0c57b $....|$..{.\$..{ + 08d0 106e38c5 7b1017c5 7b104f08 6261ff08 .n8.{...{.O.ba.. + 08e0 104f02c5 fb107738 6261ff08 106d0062 .O....w8ba...m.b + 08f0 61ff0810 75016261 ff08107d 02c5fb10 a...u.ba...}.... + 0900 5d18c4c1 7b1012c4 c17b104a 08c4c17b ]...{....{.J...{ + 0910 10421062 61ff0810 57046261 ff08105f .B.ba...W.ba..._ + 0920 056261ff 08106706 c57b116c 24f8c57b .ba...g..{.l$..{ + 0930 111424c5 7b114c24 086261ff 08114c24 ..$.{.L$.ba...L$ + 0940 02c5fb11 74241862 61ff0810 4f036261 ....t$.ba...O.ba + 0950 ff08116c 24046261 ff081174 24056261 ...l$.ba...t$.ba + 0960 ff08106d 046261ff 08107505 6261ff08 ...m.ba...u.ba.. + 0970 117c2406 c5fb115c 24386261 ff08107d .|$....\$8ba...} /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_olnncopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 95020000 00420e10 8f02420e .........B....B. + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 4a1c0000 00420e10 8f02420e ....J....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830703 2f020a0e 30410e28 ..A.8.../...0A.( - 0050 420e2042 0e18420e 10440e08 440b0000 B. B..B..D..D... + 0040 8606410e 38830747 0ec00303 b5150a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/dtrmm_olnucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_olnucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_olnucopy_COOPERLAKE.o (disasm) @@ -11,83 +11,875 @@ push %r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,-offset(%rsp) + mov %r9,offset(%rsp) + mov %rsi,offset(%rsp) mov offset(%rsp),%rbp test %rsi,%rsi jle + mov %rcx,%r15 + mov %r8,%rbx + imul %r15,%rbx + mov %rdi,%r12 + mov %r12,%rax + mov %rbx,%rsi + mov %r9,%rcx + and $something,%eax + lea (%rbx,%r15,2),%rdi + mov %rax,offset(%rsp) + lea (%rcx,%rsi,1),%rax + lea (%rdi,%r15,1),%r8 + lea (%rdx,%rax,8),%r14 mov %rcx,%rax - imul %r8,%rax - mov %rdi,%r13 - mov %rcx,%r12 - add %r9,%rax - lea (%rdx,%rax,8),%rbx - mov %rcx,%rax - imul %r9,%rax - neg %rcx - sar %r13 - add %r8,%rax - lea (%rdx,%rax,8),%r11 - mov %r9,%rax - not %rax - mov %rdi,%r15 - lea offset(,%rcx,8),%rcx - add %r9,%rax - and $something,%rdi - mov %rdi,%r10 + lea (%r8,%r15,1),%r9 + imul %r15,%rax + lea (%r9,%r15,1),%r10 + lea (%r10,%r15,1),%r11 + mov %r15,%rdx + mov %r15,%r13 + mov offset(%rsp),%r15 + add -offset(%rsp),%rax + lea (%r15,%rax,8),%r15 + mov offset(%rsp),%rax + sub %rsi,%rdi + lea (%rcx,%rax,8),%rax + mov %rax,offset(%rsp) + mov %rdx,%rax + neg %rax + lea offset(,%rax,8),%rdx + mov %rdx,%rax imul %rcx,%rax - lea (%r8,%r13,2),%rdi - mov %rdi,-offset(%rsp) - mov %r13,%rdi - shl $something,%rdi - mov %rdi,-offset(%rsp) - mov %r9,-offset(%rsp) - lea (%r9,%rsi,2),%r14 - mov %r9,%rdi - mov %rcx,-offset(%rsp) - vmovsd offset(%rip),%xmm4 # - shl $something,%r12 - and $something,%r15d - add %r8,%r10 - mov %rax,%r9 + mov %rdx,offset(%rsp) + inc %rcx + neg %rdx + imul %rdx,%rcx + lea offset(,%rdi,8),%rdi + mov %rdi,offset(%rsp) + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %r12,%rbx + add $something,%rcx + imul %rdx,%rcx + mov %r8,%rdi + sar $something,%rbx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + sub %rsi,%r9 + add $something,%rcx + imul %rdx,%rcx + shl $something,%r13 + sub %rsi,%rdi + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov -offset(%rsp),%r8 + add $something,%rcx + imul %rdx,%rcx + lea offset(,%rdi,8),%rdi + mov %rdi,offset(%rsp) + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + lea offset(,%r9,8),%rdi + add $something,%rcx + imul %rdx,%rcx + mov %rdi,offset(%rsp) + mov %rbx,offset(%rsp) + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %r14,%r9 + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + sub %rsi,%r10 + lea offset(,%r10,8),%rdi + lea (%rcx,%rax,1),%rdx + mov offset(%rsp),%rax + mov %rdx,offset(%rsp) + add %r11,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r12,%rax + and $something,%rax + add %r8,%rax + mov %r12,%rdx + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + mov %r11,%rdi + lea (%r8,%rbx,8),%rax + mov %rax,offset(%rsp) + sub %rsi,%rdi + mov %rdx,%rax + shl $something,%rbx + and $something,%eax + lea offset(,%rdi,8),%rdi + mov %rbx,offset(%rsp) + mov offset(%rsp),%r12 + mov %rdi,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + mov %rax,offset(%rsp) + mov %rdx,%rax + and $something,%eax + mov %rax,offset(%rsp) + mov %rdx,%rax + and $something,%eax + and $something,%edx + mov %rdx,offset(%rsp) + vmovsd %xmm23,-offset(%rsp) + mov %rax,offset(%rsp) + vmovsd %xmm24,%xmm24,%xmm23 + mov %r13,%rdx + vmovsd %xmm25,%xmm25,%xmm24 + mov %r12,%rcx + vmovsd %xmm26,%xmm26,%xmm25 + vmovsd %xmm30,-offset(%rsp) + vmovsd %xmm27,%xmm27,%xmm26 + vmovsd %xmm31,-offset(%rsp) + vmovsd %xmm28,%xmm28,%xmm27 + mov %r15,%r8 + vmovsd %xmm29,%xmm29,%xmm28 + mov %rbp,%rbx jmp - nopl offset(%rax) - mov %rbx,%rsi - mov %rbx,%rcx - sub -offset(%rsp),%rsi - mov %r8,%rax - test %r13,%r13 + nopl offset(%rax,%rax,1) + mov offset(%rsp),%rax + mov %r9,%r15 + lea (%rax,%r9,1),%r14 + mov offset(%rsp),%rax + sub offset(%rsp),%r15 + lea (%r9,%rax,1),%r13 /usr/lib64/libopenblas_openmp.a/dtrmm_olnucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_olnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_olnucopy_COOPERLAKE.o (objdump) @@ -2,48 +2,430 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_olnucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e0488b 6c243848 85f60f8e .H.t$.H.l$8H.... - 0030 ca010000 4889c849 0fafc049 89fd4989 ....H..I...I..I. - 0040 cc4c01c8 488d1cc2 4889c849 0fafc148 .L..H...H..I...H - 0050 f7d949d1 fd4c01c0 4c8d1cc2 4c89c848 ..I..L..L...L..H - 0060 f7d04989 ff488d0c cd000000 004c01c8 ..I..H.......L.. - 0070 4883e7fe 4989fa48 0fafc14b 8d3c6848 H...I..H...K. + mov %rcx,%r15 + mov %r8,%rbx + imul %r15,%rbx + mov %rdi,%r12 + mov %r12,%rax + mov %rbx,%rsi + mov %r9,%rcx + and $something,%eax + lea (%rbx,%r15,2),%rdi + mov %rax,offset(%rsp) + lea (%rcx,%rsi,1),%rax + lea (%rdi,%r15,1),%r8 + lea (%rdx,%rax,8),%r14 mov %rcx,%rax - imul %r8,%rax - mov %rdi,%r13 - mov %rcx,%r12 - add %r9,%rax - lea (%rdx,%rax,8),%rbx - mov %rcx,%rax - imul %r9,%rax - neg %rcx - sar %r13 - add %r8,%rax - lea (%rdx,%rax,8),%r11 - mov %r9,%rax - not %rax - mov %rdi,%r15 - lea offset(,%rcx,8),%rcx - add %r9,%rax - and $something,%rdi - mov %rdi,%r10 + lea (%r8,%r15,1),%r9 + imul %r15,%rax + lea (%r9,%r15,1),%r10 + lea (%r10,%r15,1),%r11 + mov %r15,%rdx + mov %r15,%r13 + mov offset(%rsp),%r15 + add -offset(%rsp),%rax + lea (%r15,%rax,8),%r15 + mov offset(%rsp),%rax + sub %rsi,%rdi + lea (%rcx,%rax,8),%rax + mov %rax,offset(%rsp) + mov %rdx,%rax + neg %rax + lea offset(,%rax,8),%rdx + mov %rdx,%rax imul %rcx,%rax - lea (%r8,%r13,2),%rdi - mov %rdi,-offset(%rsp) - mov %r13,%rdi - shl $something,%rdi - mov %rdi,-offset(%rsp) - mov %r9,-offset(%rsp) - lea (%r9,%rsi,2),%r14 - mov %r9,%rdi - mov %rcx,-offset(%rsp) - vmovsd offset(%rip),%xmm4 # - shl $something,%r12 - and $something,%r15d - add %r8,%r10 - mov %rax,%r9 + mov %rdx,offset(%rsp) + inc %rcx + neg %rdx + imul %rdx,%rcx + lea offset(,%rdi,8),%rdi + mov %rdi,offset(%rsp) + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %r12,%rbx + add $something,%rcx + imul %rdx,%rcx + mov %r8,%rdi + sar $something,%rbx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + sub %rsi,%r9 + add $something,%rcx + imul %rdx,%rcx + shl $something,%r13 + sub %rsi,%rdi + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov -offset(%rsp),%r8 + add $something,%rcx + imul %rdx,%rcx + lea offset(,%rdi,8),%rdi + mov %rdi,offset(%rsp) + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + lea offset(,%r9,8),%rdi + add $something,%rcx + imul %rdx,%rcx + mov %rdi,offset(%rsp) + mov %rbx,offset(%rsp) + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %r14,%r9 + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + sub %rsi,%r10 + lea offset(,%r10,8),%rdi + lea (%rcx,%rax,1),%rdx + mov offset(%rsp),%rax + mov %rdx,offset(%rsp) + add %r11,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r12,%rax + and $something,%rax + add %r8,%rax + mov %r12,%rdx + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + mov %r11,%rdi + lea (%r8,%rbx,8),%rax + mov %rax,offset(%rsp) + sub %rsi,%rdi + mov %rdx,%rax + shl $something,%rbx + and $something,%eax + lea offset(,%rdi,8),%rdi + mov %rbx,offset(%rsp) + mov offset(%rsp),%r12 + mov %rdi,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + mov %rax,offset(%rsp) + mov %rdx,%rax + and $something,%eax + mov %rax,offset(%rsp) + mov %rdx,%rax + and $something,%eax + and $something,%edx + mov %rdx,offset(%rsp) + vmovsd %xmm23,-offset(%rsp) + mov %rax,offset(%rsp) + vmovsd %xmm24,%xmm24,%xmm23 + mov %r13,%rdx + vmovsd %xmm25,%xmm25,%xmm24 + mov %r12,%rcx + vmovsd %xmm26,%xmm26,%xmm25 + vmovsd %xmm30,-offset(%rsp) + vmovsd %xmm27,%xmm27,%xmm26 + vmovsd %xmm31,-offset(%rsp) + vmovsd %xmm28,%xmm28,%xmm27 + mov %r15,%r8 + vmovsd %xmm29,%xmm29,%xmm28 + mov %rbp,%rbx jmp - nopl offset(%rax) - mov %rbx,%rsi - mov %rbx,%rcx - sub -offset(%rsp),%rsi - mov %r8,%rax - test %r13,%r13 + nopl offset(%rax,%rax,1) + mov offset(%rsp),%rax + mov %r9,%r15 + lea (%rax,%r9,1),%r14 + mov offset(%rsp),%rax + sub offset(%rsp),%r15 + lea (%r9,%rax,1),%r13 /usr/lib64/libopenblas_openmp.a/dtrmm_olnucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_olnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_olnucopy_SKYLAKEX.o (objdump) @@ -2,48 +2,430 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_olnucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e0488b 6c243848 85f60f8e .H.t$.H.l$8H.... - 0030 ca010000 4889c849 0fafc049 89fd4989 ....H..I...I..I. - 0040 cc4c01c8 488d1cc2 4889c849 0fafc148 .L..H...H..I...H - 0050 f7d949d1 fd4c01c0 4c8d1cc2 4c89c848 ..I..L..L...L..H - 0060 f7d04989 ff488d0c cd000000 004c01c8 ..I..H.......L.. - 0070 4883e7fe 4989fa48 0fafc14b 8d3c6848 H...I..H...K. + mov %rcx,%rsi + imul %r8,%rsi + mov %rcx,%rbx + mov %rdi,%r12 + lea (%rsi,%rcx,2),%rdi + lea (%rdi,%rcx,1),%r8 + mov %rbx,%rax + mov %r9,%r15 + shl $something,%rax + lea (%r8,%rcx,1),%r9 + lea (%rcx,%r9,1),%r10 + mov %rax,offset(%rsp) + mov %rbx,%rax + lea (%rcx,%r10,1),%r11 + shl $something,%rax + mov %r12,%rcx + mov %rax,offset(%rsp) mov %rcx,%rax - imul %r8,%rax - mov %rdi,%r13 - mov %rcx,%r12 - add %r9,%rax - lea (%rdx,%rax,8),%rbx - mov %rcx,%rax - imul %r9,%rax - neg %rcx - sar %r13 - add %r8,%rax - lea (%rdx,%rax,8),%r11 + and $something,%eax + mov %rax,-offset(%rsp) + lea (%r15,%rsi,1),%rax + lea (%rdx,%rax,8),%r14 + mov %r15,%rax + imul %rbx,%rax + mov %rdx,%rcx + mov %r15,%rdx + add -offset(%rsp),%rax + lea (%rcx,%rax,8),%r15 + mov offset(%rsp),%rax + mov %rdx,%rcx + lea (%rdx,%rax,8),%rax + mov %rax,offset(%rsp) + mov %rbx,%rax + neg %rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %rdx,%rax + inc %rcx + mov offset(%rsp),%rdx + mov %rbx,%r13 + imul %rdx,%rax + neg %rdx + imul %rdx,%rcx + sar $something,%r12 + shl $something,%r13 + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + mov %r12,offset(%rsp) + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rcx,%rax + mov %rax,offset(%rsp) + mov %rdi,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r8,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) mov %r9,%rax - not %rax - mov %rdi,%r15 - lea offset(,%rcx,8),%rcx - add %r9,%rax - and $something,%rdi - mov %rdi,%r10 - imul %rcx,%rax - lea (%r8,%r13,2),%rdi - mov %rdi,-offset(%rsp) - mov %r13,%rdi - shl $something,%rdi - mov %rdi,-offset(%rsp) - mov %r9,-offset(%rsp) - lea (%r9,%rsi,2),%r14 - mov %r9,%rdi - mov %rcx,-offset(%rsp) - shl $something,%r12 - and $something,%r15d - add %r8,%r10 - mov %rax,%r9 + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r10,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r11,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + lea (%rbx,%r11,1),%rax + sub %rsi,%rax + mov offset(%rsp),%rbx + shl $something,%rax + mov -offset(%rsp),%r8 + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%rax + add %r8,%rax + mov %rax,offset(%rsp) + mov %r12,%rax + lea (%r8,%r12,8),%rsi + shl $something,%rax + mov %rsi,offset(%rsp) + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%eax + mov -offset(%rsp),%r12 + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%eax + mov %rax,offset(%rsp) + and $something,%ebx + mov %r12,%rax + vmovsd %xmm11,offset(%rsp) + mov %r13,%r12 + vmovsd %xmm12,%xmm12,%xmm11 + mov %rbx,offset(%rsp) + vmovsd %xmm9,-offset(%rsp) + vmovsd %xmm14,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm16,-offset(%rsp) + vmovsd %xmm17,-offset(%rsp) + vmovsd %xmm18,-offset(%rsp) + vmovsd %xmm19,-offset(%rsp) + vmovsd %xmm20,-offset(%rsp) + vmovsd %xmm21,(%rsp) + vmovsd %xmm22,offset(%rsp) + vmovsd %xmm23,offset(%rsp) + vmovsd %xmm24,offset(%rsp) + vmovsd %xmm25,offset(%rsp) + vmovsd %xmm26,offset(%rsp) + vmovsd %xmm27,offset(%rsp) + vmovsd %xmm28,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrmm_oltncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_oltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_oltncopy_COOPERLAKE.o (objdump) @@ -2,43 +2,450 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_oltncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e0488b 6c243848 85f60f8e .H.t$.H.l$8H.... - 0030 a9010000 4889c849 0fafc049 89fd4989 ....H..I...I..I. - 0040 cc4c01c8 488d1cc2 4889c849 0fafc148 .L..H...H..I...H - 0050 f7d949d1 fd4c01c0 4c8d1cc2 4c89c848 ..I..L..L...L..H - 0060 f7d04989 ff488d0c cd000000 004c01c8 ..I..H.......L.. - 0070 4883e7fe 4989fa48 0fafc14b 8d3c6848 H...I..H...K. + mov %rcx,%rsi + imul %r8,%rsi + mov %rcx,%rbx + mov %rdi,%r12 + lea (%rsi,%rcx,2),%rdi + lea (%rdi,%rcx,1),%r8 + mov %rbx,%rax + mov %r9,%r15 + shl $something,%rax + lea (%r8,%rcx,1),%r9 + lea (%rcx,%r9,1),%r10 + mov %rax,offset(%rsp) + mov %rbx,%rax + lea (%rcx,%r10,1),%r11 + shl $something,%rax + mov %r12,%rcx + mov %rax,offset(%rsp) mov %rcx,%rax - imul %r8,%rax - mov %rdi,%r13 - mov %rcx,%r12 - add %r9,%rax - lea (%rdx,%rax,8),%rbx - mov %rcx,%rax - imul %r9,%rax - neg %rcx - sar %r13 - add %r8,%rax - lea (%rdx,%rax,8),%r11 + and $something,%eax + mov %rax,-offset(%rsp) + lea (%r15,%rsi,1),%rax + lea (%rdx,%rax,8),%r14 + mov %r15,%rax + imul %rbx,%rax + mov %rdx,%rcx + mov %r15,%rdx + add -offset(%rsp),%rax + lea (%rcx,%rax,8),%r15 + mov offset(%rsp),%rax + mov %rdx,%rcx + lea (%rdx,%rax,8),%rax + mov %rax,offset(%rsp) + mov %rbx,%rax + neg %rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %rdx,%rax + inc %rcx + mov offset(%rsp),%rdx + mov %rbx,%r13 + imul %rdx,%rax + neg %rdx + imul %rdx,%rcx + sar $something,%r12 + shl $something,%r13 + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + mov %r12,offset(%rsp) + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rcx,%rax + mov %rax,offset(%rsp) + mov %rdi,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r8,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) mov %r9,%rax - not %rax - mov %rdi,%r15 - lea offset(,%rcx,8),%rcx - add %r9,%rax - and $something,%rdi - mov %rdi,%r10 - imul %rcx,%rax - lea (%r8,%r13,2),%rdi - mov %rdi,-offset(%rsp) - mov %r13,%rdi - shl $something,%rdi - mov %rdi,-offset(%rsp) - mov %r9,-offset(%rsp) - lea (%r9,%rsi,2),%r14 - mov %r9,%rdi - mov %rcx,-offset(%rsp) - shl $something,%r12 - and $something,%r15d - add %r8,%r10 - mov %rax,%r9 + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r10,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r11,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + lea (%rbx,%r11,1),%rax + sub %rsi,%rax + mov offset(%rsp),%rbx + shl $something,%rax + mov -offset(%rsp),%r8 + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%rax + add %r8,%rax + mov %rax,offset(%rsp) + mov %r12,%rax + lea (%r8,%r12,8),%rsi + shl $something,%rax + mov %rsi,offset(%rsp) + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%eax + mov -offset(%rsp),%r12 + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%eax + mov %rax,offset(%rsp) + and $something,%ebx + mov %r12,%rax + vmovsd %xmm11,offset(%rsp) + mov %r13,%r12 + vmovsd %xmm12,%xmm12,%xmm11 + mov %rbx,offset(%rsp) + vmovsd %xmm9,-offset(%rsp) + vmovsd %xmm14,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm16,-offset(%rsp) + vmovsd %xmm17,-offset(%rsp) + vmovsd %xmm18,-offset(%rsp) + vmovsd %xmm19,-offset(%rsp) + vmovsd %xmm20,-offset(%rsp) + vmovsd %xmm21,(%rsp) + vmovsd %xmm22,offset(%rsp) + vmovsd %xmm23,offset(%rsp) + vmovsd %xmm24,offset(%rsp) + vmovsd %xmm25,offset(%rsp) + vmovsd %xmm26,offset(%rsp) + vmovsd %xmm27,offset(%rsp) + vmovsd %xmm28,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrmm_oltncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_oltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_oltncopy_SKYLAKEX.o (objdump) @@ -2,43 +2,450 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_oltncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e0488b 6c243848 85f60f8e .H.t$.H.l$8H.... - 0030 a9010000 4889c849 0fafc049 89fd4989 ....H..I...I..I. - 0040 cc4c01c8 488d1cc2 4889c849 0fafc148 .L..H...H..I...H - 0050 f7d949d1 fd4c01c0 4c8d1cc2 4c89c848 ..I..L..L...L..H - 0060 f7d04989 ff488d0c cd000000 004c01c8 ..I..H.......L.. - 0070 4883e7fe 4989fa48 0fafc14b 8d3c6848 H...I..H...K. + mov %rcx,%rsi + imul %r8,%rsi + mov %rcx,%rbx + mov %rdi,%r12 + lea (%rsi,%rcx,2),%rdi + lea (%rdi,%rcx,1),%r8 + mov %rbx,%rax + mov %r9,%r15 + shl $something,%rax + lea (%r8,%rcx,1),%r9 + lea (%rcx,%r9,1),%r10 + mov %rax,offset(%rsp) + mov %rbx,%rax + lea (%rcx,%r10,1),%r11 + shl $something,%rax + mov %r12,%rcx + mov %rax,offset(%rsp) mov %rcx,%rax - imul %r8,%rax - mov %rdi,%r13 - mov %rcx,%r12 - add %r9,%rax - lea (%rdx,%rax,8),%rbx - mov %rcx,%rax - imul %r9,%rax - neg %rcx - sar %r13 - add %r8,%rax - lea (%rdx,%rax,8),%r11 + and $something,%eax + mov %rax,-offset(%rsp) + lea (%r15,%rsi,1),%rax + lea (%rdx,%rax,8),%r14 + mov %r15,%rax + imul %rbx,%rax + mov %rdx,%rcx + mov %r15,%rdx + add -offset(%rsp),%rax + lea (%rcx,%rax,8),%r15 + mov offset(%rsp),%rax + mov %rdx,%rcx + lea (%rdx,%rax,8),%rax + mov %rax,offset(%rsp) + mov %rbx,%rax + neg %rax + shl $something,%rax + mov %rax,offset(%rsp) + imul %rdx,%rax + inc %rcx + mov offset(%rsp),%rdx + mov %rbx,%r13 + neg %rdx + imul %rdx,%rcx + sar $something,%r12 + shl $something,%r13 + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + mov %r12,offset(%rsp) + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rcx,%rax + mov %rax,offset(%rsp) + mov %rdi,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r8,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) mov %r9,%rax - not %rax - mov %rdi,%r15 - lea offset(,%rcx,8),%rcx - add %r9,%rax - and $something,%rdi - mov %rdi,%r10 - imul %rcx,%rax - lea (%r8,%r13,2),%rdi - mov %rdi,-offset(%rsp) + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r10,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r11,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + lea (%rbx,%r11,1),%rax + sub %rsi,%rax + mov offset(%rsp),%rbx + shl $something,%rax + mov -offset(%rsp),%r8 + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%rax + add %r8,%rax + mov %rax,offset(%rsp) + mov %r12,%rax + lea (%r8,%r12,8),%rdi + shl $something,%rax + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%eax + mov %rax,offset(%rsp) + mov -offset(%rsp),%r12 + mov %rbx,%rax + and $something,%eax + and $something,%ebx + mov %rbx,offset(%rsp) + vmovsd %xmm27,-offset(%rsp) + vmovsd %xmm28,-offset(%rsp) + mov %r14,%r11 + mov %rax,offset(%rsp) + vmovsd offset(%rip),%xmm0 # mov %r13,%rdi - shl $something,%rdi - mov %rdi,-offset(%rsp) - mov %r9,-offset(%rsp) - lea (%r9,%rsi,2),%r14 - mov %r9,%rdi - mov %rcx,-offset(%rsp) - vmovsd offset(%rip),%xmm1 # - shl $something,%r12 - and $something,%r15d - add %r8,%r10 - mov %rax,%r9 + mov %r12,%r8 + vmovsd %xmm18,-offset(%rsp) + vmovsd %xmm19,-offset(%rsp) + vmovsd %xmm20,-offset(%rsp) + vmovsd %xmm21,-offset(%rsp) + vmovsd %xmm22,-offset(%rsp) + vmovsd %xmm23,-offset(%rsp) + vmovsd %xmm24,-offset(%rsp) + vmovsd %xmm25,-offset(%rsp) + vmovsd %xmm26,-offset(%rsp) + vmovsd %xmm31,-offset(%rsp) + vmovsd %xmm10,(%rsp) + vmovsd %xmm11,offset(%rsp) + vmovsd %xmm12,offset(%rsp) + vmovsd %xmm13,offset(%rsp) + vmovsd %xmm14,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrmm_oltucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_oltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_oltucopy_COOPERLAKE.o (objdump) @@ -2,47 +2,449 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_oltucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e0488b 6c243848 85f60f8e .H.t$.H.l$8H.... - 0030 b9010000 4889c849 0fafc049 89fd4989 ....H..I...I..I. - 0040 cc4c01c8 488d1cc2 4889c849 0fafc148 .L..H...H..I...H - 0050 f7d949d1 fd4c01c0 4c8d1cc2 4c89c848 ..I..L..L...L..H - 0060 f7d04989 ff488d0c cd000000 004c01c8 ..I..H.......L.. - 0070 4883e7fe 4989fa48 0fafc14b 8d3c6848 H...I..H...K. + mov %rcx,%rsi + imul %r8,%rsi + mov %rcx,%rbx + mov %rdi,%r12 + lea (%rsi,%rcx,2),%rdi + lea (%rdi,%rcx,1),%r8 + mov %rbx,%rax + mov %r9,%r15 + shl $something,%rax + lea (%r8,%rcx,1),%r9 + lea (%rcx,%r9,1),%r10 + mov %rax,offset(%rsp) + mov %rbx,%rax + lea (%rcx,%r10,1),%r11 + shl $something,%rax + mov %r12,%rcx + mov %rax,offset(%rsp) mov %rcx,%rax - imul %r8,%rax - mov %rdi,%r13 - mov %rcx,%r12 - add %r9,%rax - lea (%rdx,%rax,8),%rbx - mov %rcx,%rax - imul %r9,%rax - neg %rcx - sar %r13 - add %r8,%rax - lea (%rdx,%rax,8),%r11 + and $something,%eax + mov %rax,-offset(%rsp) + lea (%r15,%rsi,1),%rax + lea (%rdx,%rax,8),%r14 + mov %r15,%rax + imul %rbx,%rax + mov %rdx,%rcx + mov %r15,%rdx + add -offset(%rsp),%rax + lea (%rcx,%rax,8),%r15 + mov offset(%rsp),%rax + mov %rdx,%rcx + lea (%rdx,%rax,8),%rax + mov %rax,offset(%rsp) + mov %rbx,%rax + neg %rax + shl $something,%rax + mov %rax,offset(%rsp) + imul %rdx,%rax + inc %rcx + mov offset(%rsp),%rdx + mov %rbx,%r13 + neg %rdx + imul %rdx,%rcx + sar $something,%r12 + shl $something,%r13 + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + mov %r12,offset(%rsp) + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rax,%rcx + mov %rcx,offset(%rsp) + mov -offset(%rsp),%rcx + add $something,%rcx + imul %rdx,%rcx + add %rcx,%rax + mov %rax,offset(%rsp) + mov %rdi,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r8,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) mov %r9,%rax - not %rax - mov %rdi,%r15 - lea offset(,%rcx,8),%rcx - add %r9,%rax - and $something,%rdi - mov %rdi,%r10 - imul %rcx,%rax - lea (%r8,%r13,2),%rdi - mov %rdi,-offset(%rsp) + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r10,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + mov %r11,%rax + sub %rsi,%rax + shl $something,%rax + mov %rax,offset(%rsp) + lea (%rbx,%r11,1),%rax + sub %rsi,%rax + mov offset(%rsp),%rbx + shl $something,%rax + mov -offset(%rsp),%r8 + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%rax + add %r8,%rax + mov %rax,offset(%rsp) + mov %r12,%rax + lea (%r8,%r12,8),%rdi + shl $something,%rax + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + and $something,%eax + mov %rax,offset(%rsp) + mov -offset(%rsp),%r12 + mov %rbx,%rax + and $something,%eax + and $something,%ebx + mov %rbx,offset(%rsp) + vmovsd %xmm27,-offset(%rsp) + vmovsd %xmm28,-offset(%rsp) + mov %r14,%r11 + mov %rax,offset(%rsp) + vmovsd offset(%rip),%xmm0 # mov %r13,%rdi - shl $something,%rdi - mov %rdi,-offset(%rsp) - mov %r9,-offset(%rsp) - lea (%r9,%rsi,2),%r14 - mov %r9,%rdi - mov %rcx,-offset(%rsp) - vmovsd offset(%rip),%xmm1 # - shl $something,%r12 - and $something,%r15d - add %r8,%r10 - mov %rax,%r9 + mov %r12,%r8 + vmovsd %xmm18,-offset(%rsp) + vmovsd %xmm19,-offset(%rsp) + vmovsd %xmm20,-offset(%rsp) + vmovsd %xmm21,-offset(%rsp) + vmovsd %xmm22,-offset(%rsp) + vmovsd %xmm23,-offset(%rsp) + vmovsd %xmm24,-offset(%rsp) + vmovsd %xmm25,-offset(%rsp) + vmovsd %xmm26,-offset(%rsp) + vmovsd %xmm31,-offset(%rsp) + vmovsd %xmm10,(%rsp) + vmovsd %xmm11,offset(%rsp) + vmovsd %xmm12,offset(%rsp) + vmovsd %xmm13,offset(%rsp) + vmovsd %xmm14,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrmm_oltucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_oltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_oltucopy_SKYLAKEX.o (objdump) @@ -2,47 +2,449 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_oltucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e0488b 6c243848 85f60f8e .H.t$.H.l$8H.... - 0030 b9010000 4889c849 0fafc049 89fd4989 ....H..I...I..I. - 0040 cc4c01c8 488d1cc2 4889c849 0fafc148 .L..H...H..I...H - 0050 f7d949d1 fd4c01c0 4c8d1cc2 4c89c848 ..I..L..L...L..H - 0060 f7d04989 ff488d0c cd000000 004c01c8 ..I..H.......L.. - 0070 4883e7fe 4989fa48 0fafc14b 8d3c6848 H...I..H...K. + mov %rdi,%r11 + mov %r9,%r10 mov %rcx,%rax - imul %r9,%rax - mov %rdi,%r15 - sar %r15 - add %r8,%rax - lea (%rdx,%rax,8),%r13 - mov %rcx,%rax + mov %rdi,%rbx + and $something,%edi + mov %rcx,%rbp imul %r8,%rax + mov %rdi,offset(%rsp) + mov %r10,%rdi + imul %rbp,%rdi + mov %r8,%r12 + lea (%rax,%rcx,2),%rsi + mov %rax,%r8 + mov %rdx,%r13 + lea (%rsi,%rcx,1),%rcx + add %r12,%rdi + sub %r8,%rsi + lea (%rcx,%rbp,1),%rdx + mov %r13,%r12 + shl $something,%rsi + sub %r8,%rcx + lea offset(%r13,%rdi,8),%r13 + lea (%r10,%r8,1),%rdi + lea offset(%rbp,%rdx,1),%rax + lea (%r12,%rdi,8),%r12 + mov %rsi,offset(%rsp) + mov %r10,%rdi + lea offset(,%rcx,8),%rsi + mov offset(%rsp),%r10 + sub %r8,%rdx + lea offset(%rbp,%rax,1),%r9 + mov %rsi,offset(%rsp) + sub %r8,%rax + lea offset(,%rdx,8),%rsi + lea (%rdi,%r10,8),%r10 + mov %rsi,offset(%rsp) + lea offset(,%rax,8),%rsi + mov %r10,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rbp,%r10 + mov %r9,%rsi + lea (%r10,%r9,1),%rax + sub %r8,%rsi + mov %rbp,%r15 + lea offset(,%rsi,8),%rsi + lea offset(,%rbp,8),%rbp + sub %r8,%rax + mov %rsi,offset(%rsp) + lea offset(,%rax,8),%rsi + mov %rbp,%rax + mov %rsi,offset(%rsp) + lea offset(%rdi),%rdx + mov %rbp,%rsi + neg %rax + imul %rdi,%rax + imul %rsi,%rdx + mov %rbp,offset(%rsp) mov %rdi,%rbp - and $something,%rdi - add %r9,%rax - lea (%rdx,%rax,8),%r12 - lea (%r9,%rsi,2),%rax - mov %rax,-offset(%rsp) - lea offset(,%rcx,8),%rax - mov %rax,-offset(%rsp) - mov %rax,-offset(%rsp) - lea (%r8,%r15,2),%rax - mov %rax,-offset(%rsp) - mov %r15,%rax - mov %rdi,%r11 - mov %rcx,%r10 - shl $something,%rax - mov %rax,-offset(%rsp) - mov %r9,-offset(%rsp) - shl $something,%r10 - and $something,%ebp - add %r8,%r11 - mov %r9,%rdi - jmp - nopw offset(%rax,%rax,1) + mov %rsi,%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %rdi,%rdx + mov %rsi,offset(%rsp) + sar $something,%rbx + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %rdi,%rdx + mov %rcx,offset(%rsp) + mov %rbx,offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %rdi,%rdx + mov %rsi,offset(%rsp) + shl $something,%r15 + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %rdi,%rdx + mov %rcx,offset(%rsp) + vmovsd %xmm31,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %rdi,%rdx + mov %rsi,offset(%rsp) + vmovsd %xmm14,-offset(%rsp) + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %rdi,%rdx + mov %rcx,offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + lea (%rdx,%rax,1),%rdi + mov %r11,%rax + and $something,%rax + mov %rax,%rsi mov -offset(%rsp),%rax - mov %r13,%rsi + mov %rdi,offset(%rsp) + add %rax,%rsi + lea (%rax,%rbx,8),%rax + mov %rax,offset(%rsp) + mov %r11,%rax + and $something,%eax + mov %rax,offset(%rsp) + shl $something,%rbx + mov %r11,%rax + mov %rbx,offset(%rsp) + and $something,%eax + mov %r11,%rbx + mov %rax,offset(%rsp) + and $something,%ebx + mov %r12,%rax + and $something,%r11d + mov %rsi,-offset(%rsp) + mov %rbx,offset(%rsp) + mov %r11,offset(%rsp) + vmovsd %xmm16,-offset(%rsp) + vmovsd %xmm17,-offset(%rsp) + vmovsd %xmm18,-offset(%rsp) + vmovsd %xmm9,%xmm9,%xmm31 + vmovsd %xmm19,-offset(%rsp) + vmovsd %xmm10,%xmm10,%xmm9 + vmovsd %xmm11,-offset(%rsp) + mov %r15,%r12 + vmovsd %xmm12,%xmm12,%xmm11 + mov %r14,%r10 + vmovsd %xmm20,-offset(%rsp) + vmovsd %xmm21,(%rsp) + vmovsd %xmm22,offset(%rsp) + vmovsd %xmm23,-offset(%rsp) + vmovsd %xmm24,offset(%rsp) + vmovsd %xmm25,offset(%rsp) + vmovsd %xmm26,offset(%rsp) + vmovsd %xmm27,offset(%rsp) + vmovsd %xmm28,-offset(%rsp) + vmovsd %xmm29,offset(%rsp) + vmovsd %xmm30,offset(%rsp) + vmovsd %xmm0,%xmm0,%xmm10 + vmovsd %xmm13,%xmm13,%xmm12 + mov %rbp,%r14 + mov %rax,%r15 + jmp + cs nopw offset(%rax,%rax,1) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea offset(%r13,%rax,1),%rbx + mov offset(%rsp),%rax + mov %r13,%r9 + lea offset(%r13,%rax,1),%r11 + mov offset(%rsp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_COOPERLAKE.o (objdump) @@ -2,46 +2,480 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e04c8b 74243848 85f60f8e .H.t$.L.t$8H.... - 0030 ba010000 4889c849 0fafc149 89ff49d1 ....H..I...I..I. - 0040 ff4c01c0 4c8d2cc2 4889c849 0fafc048 .L..L.,.H..I...H - 0050 89fd4883 e7fe4c01 c84c8d24 c2498d04 ..H...L..L.$.I.. - 0060 71488944 24a8488d 04cd0000 00004889 qH.D$.H.......H. - 0070 4424b848 894424b0 4b8d0478 48894424 D$.H.D$.K..xH.D$ - 0080 c84c89f8 4989fb49 89ca48c1 e0054889 .L..I..I..H...H. - 0090 4424c04c 894c24f8 49c1e204 83e5014d D$.L.L$.I......M - 00a0 01c34c89 cfeb4f66 0f1f8400 00000000 ..L...Of........ - 00b0 488b4424 b04c89ee 498d4c05 004c89c0 H.D$.L..I.L..L.. - 00c0 4d85ff7f 4a4885ed 7416498d 56104839 M...JH..t.I.V.H9 - 00d0 c70f8fd9 0000000f 8dd30000 004989d6 .............I.. - 00e0 4883c702 4d01d549 83c41048 3b7c24a8 H...M..I...H;|$. - 00f0 0f84ea00 00004c39 c77db548 8b4424b8 ......L9.}.H.D$. - 0100 4c89e649 8d0c044c 89c04d85 ff7eb64c L..I...L..M..~.L - 0110 89c24c89 f0eb4066 0f1f8400 00000000 ..L...@f........ - 0120 c5fb101e c5fb104e 08c5fb10 11c5fb10 .......N........ - 0130 41084883 c610c5fb 1158e0c5 fb1150e8 A.H......X....P. - 0140 c5fb1148 f0c5fb11 40f84883 c1104883 ...H....@.H...H. - 0150 c2024c39 da744648 83c02048 39d77fc0 ..L9.tFH.. H9... - 0160 4e8d0c16 4a8d1c11 7c66c5fb 1016c5fb N...J...|f...... - 0170 1009c5fb 10410848 83c20248 c740f000 .....A.H...H.@.. - 0180 000000c5 fb1150e0 c5fb1148 e8c5fb11 ......P....H.... - 0190 40f84889 d94c89ce 4c39da75 ba488b44 @.H..L..L9.u.H.D - 01a0 24c84c03 7424c0e9 19ffffff 0f1f4000 $.L.t$........@. - 01b0 c5fb100e c5fb1001 c4c17b11 0ec4c17b ..........{....{ - 01c0 11460849 89d6e915 ffffff0f 1f440000 .F.I.........D.. - 01d0 4889d94c 89cee973 ffffff0f 1f440000 H..L...s.....D.. - 01e0 4c8b4c24 f8488b44 24e04d8d 0c41f644 L.L$.H.D$.M..A.D - 01f0 24d0010f 847d0000 00488b44 24d84d39 $....}...H.D$.M9 - 0200 c10f8d81 00000049 0fafc048 8b5c24f0 .......I...H.\$. - 0210 4c01c848 8d04c348 8b5c24e8 4885db7e L..H...H.\$.H..~ - 0220 55488b4c 24d84c89 c64c01c3 48f7de48 UH.L$.L..L..H..H - 0230 c1e10348 89da498d 3cf6eb1a 0f1f4000 ...H..I.<.....@. - 0240 c5fb1000 4883c008 c4a17b11 04c749ff ....H.....{...I. - 0250 c04c39c2 74204d39 c17fe548 8d34087c .L9.t M9...H.4.| - 0260 3fc5fb10 004889f0 c4a17b11 04c749ff ?....H....{...I. - 0270 c04c39c2 75e05b5d 415c415d 415e31c0 .L9.u.[]A\A]A^1. - 0280 415fc30f 1f440000 490fafc1 488b5c24 A_...D..I...H.\$ - 0290 f04c01c0 488d04c3 e97affff ff0f1f00 .L..H....z...... - 02a0 4889f0eb a9 H.... + 0000 41574156 41554154 55534881 ec800100 AWAVAUATUSH..... + 0010 004889b4 24a80000 0048c1fe 034889bc .H..$....H...H.. + 0020 24c80000 00488994 24680100 0048898c $....H..$h...H.. + 0030 24d00000 004c8944 24a84c89 8c249000 $....L.D$.L..$.. + 0040 00004889 b4247001 00004c8b b424b801 ..H..$p...L..$.. + 0050 00004885 f60f8efc 11000049 89fb4d89 ..H........I..M. + 0060 ca4889c8 4889fb83 e7074889 cd490faf .H..H.....H..I.. + 0070 c04889bc 24880000 004c89d7 480faffd .H..$....L..H... + 0080 4d89c448 8d344849 89c04989 d5488d0c M..H.4HI..I..H.. + 0090 0e4c01e7 4c29c648 8d14294d 89ec48c1 .L..L).H..)M..H. + 00a0 e6034c29 c14d8d6c fd004b8d 3c02488d ..L).M.l..K.<.H. + 00b0 4415004d 8d24fc48 89b42418 0100004c D..M.$.H..$....L + 00c0 89d7488d 34cd0000 00004c8b 94247001 ..H.4.....L..$p. + 00d0 00004c29 c24c8d4c 05004889 b4243801 ..L).L.L..H..$8. + 00e0 00004c29 c0488d34 d5000000 004e8d14 ..L).H.4.....N.. + 00f0 d74889b4 24080100 00488d34 c5000000 .H..$....H.4.... + 0100 004c8994 24a00000 004889b4 24280100 .L..$....H..$(.. + 0110 004989ea 4c89ce4b 8d040a4c 29c64989 .I..L..K...L).I. + 0120 ef488d34 f5000000 00488d2c ed000000 .H.4.....H.,.... + 0130 004c29c0 4889b424 20010000 488d34c5 .L).H..$ ...H.4. + 0140 00000000 4889e848 89b424e8 00000048 ....H..H..$....H + 0150 8d570148 89ee48f7 d8480faf c7480faf .W.H..H..H...H.. + 0160 d64889ac 24e00000 004889fd 4889f748 .H..$....H..H..H + 0170 8d340248 8d550248 0fafd748 89b42440 .4.H.U.H...H..$@ + 0180 01000048 c1fb0348 8d0c0248 8d550348 ...H...H...H.U.H + 0190 0fafd748 898c24d8 00000048 899c2498 ...H..$....H..$. + 01a0 00000048 8d340248 8d550448 0fafd748 ...H.4.H.U.H...H + 01b0 89b42410 01000049 c1e70648 8d0c0248 ..$....I...H...H + 01c0 8d550548 0fafd748 898c2430 01000062 .U.H...H..$0...b + 01d0 61ff0811 7c24f248 8d340248 8d550648 a...|$.H.4.H.U.H + 01e0 0fafd748 89b42400 010000c5 7b117424 ...H..$.....{.t$ + 01f0 88488d0c 02488d55 07480faf d748898c .H...H.U.H...H.. + 0200 24f00000 00c57b11 7c24e048 8d3c024c $.....{.|$.H.<.L + 0210 89d84883 e0f84889 c6488b44 24a84889 ..H...H..H.D$.H. + 0220 bc24f800 00004801 c6488d04 d8488984 .$....H..H...H.. + 0230 24580100 004c89d8 83e00648 89842478 $X...L.....H..$x + 0240 01000048 c1e3094c 89d84889 9c246001 ...H...L..H..$`. + 0250 000083e0 024c89db 48898424 48010000 .....L..H..$H... + 0260 83e3044c 89e04183 e3014889 7424b048 ...L..A...H.t$.H + 0270 899c24b0 0000004c 899c2450 01000062 ..$....L..$P...b + 0280 e1ff0811 4424f862 e1ff0811 4c24fd62 ....D$.b....L$.b + 0290 e1ff0811 5424fe62 41b70810 f962e1ff ....T$.bA....b.. + 02a0 08115c24 f9c4412b 10cac57b 115c2498 ..\$..A+...{.\$. + 02b0 4d89fcc4 411b10dc 4d89f262 e1ff0811 M...A...M..b.... + 02c0 6424ff62 e1ff0811 2c2462e1 ff081174 d$.b....,$b....t + 02d0 240562e1 ff08117c 24fa6261 ff081144 $.b....|$.ba...D + 02e0 24016261 ff08114c 24026261 ff081154 $.ba...L$.ba...T + 02f0 24066261 ff08115c 24076261 ff081164 $.ba...\$.ba...d + 0300 24fb6261 ff08116c 24036261 ff081174 $.ba...l$.ba...t + 0310 2404c57b 10d0c441 1310e549 89ee4989 $..{...A...I..I. + 0320 c7e96304 0000662e 0f1f8400 00000000 ..c...f......... + 0330 488b8424 40010000 4883bc24 98000000 H..$@...H..$.... + 0340 00498d5c 0500488b 8424d800 00004d89 .I.\..H..$....M. + 0350 e94d8d5c 0500488b 84241001 00004d8d .M.\..H..$....M. + 0360 44050048 8b842430 01000049 8d7c0500 D..H..$0...I.|.. + 0370 488b8424 00010000 498d7405 00488b84 H..$....I.t..H.. + 0380 24f00000 00498d4c 0500488b 8424f800 $....I.L..H..$.. + 0390 0000498d 54050048 8b4424a8 0f8f5d04 ..I.T..H.D$...]. + 03a0 00004883 bc248800 0000000f 84bf0300 ..H..$.......... + 03b0 004939c6 0f8e360e 00004883 bc24b000 .I9...6...H..$.. + 03c0 0000000f 842d0200 00c57b10 6b08c441 .....-....{.k..A + 03d0 7b107308 c4417b10 7b106241 ff081048 {.s..A{.{.bA...H + 03e0 016241ff 08105002 6241ff08 10600362 .bA...P.bA...`.b + 03f0 61ff0810 6f016261 ff081077 0262e1ff a...o.ba...w.b.. + 0400 08104703 62e1ff08 104e0162 e1ff0810 ..G.b....N.b.... + 0410 5602c4c1 7b107908 62c1ff08 10790262 V...{.y.b....y.b + 0420 41ff0810 4103c5fb 1033c57b 10431048 A...A....3.{.C.H + 0430 8b6b18c4 c17b102b 498b4318 c4c17b10 .k...{.+I.C...{. + 0440 20c5fb10 1fc5fb10 16c57b11 6c2490c5 .........{.l$.. + 0450 7b117424 88c57b11 7c24e062 61ff0811 {.t$..{.|$.ba... + 0460 4c24f862 61ff0811 5424fd62 61ff0811 L$.ba...T$.ba... + 0470 6424fe62 61ff0811 6c24f962 61ff0811 d$.ba...l$.ba... + 0480 7424ff62 e1ff0811 042462e1 ff08114c t$.b.....$b....L + 0490 24fa62e1 ff081154 240162e1 ff08105e $.b....T$.b....^ + 04a0 0362e1ff 08106902 62e1ff08 10710362 .b....i.b....q.b + 04b0 e1ff0810 6101c57b 106210c5 7b105218 ....a..{.b..{.R. + 04c0 c5fb1009 c5fb1002 c57b105a 086241ff .........{.Z.bA. + 04d0 08101962 e1ff0811 5c240262 41ff0811 ...b....\$.bA... + 04e0 1ac4c17b 117208c4 c17b116a 10c4c17b ...{.r...{.j...{ + 04f0 116218c4 c17b115a 20c4c17b 115228c4 .b...{.Z ..{.R(. + 0500 c17b114a 30c4c17b 114238c4 c17b117a .{.J0..{.B8..{.z + 0510 40c4417b 116a48c4 417b1172 506241ff @.A{.jH.A{.rPbA. + 0520 08114a0b 6241ff08 116a0c62 c1ff0811 ..J.bA...j.b.... + 0530 4a0d62c1 ff081162 0ec4417b 115a7862 J.b....b..A{.Zxb + 0540 c1ff0811 7a10c441 7b118288 00000062 ....z..A{......b + 0550 e1ff0811 6424fb62 e1ff0811 6c240362 ....d$.b....l$.b + 0560 e1ff0811 74240449 83c120c4 417b11ba ....t$.I.. .A{.. + 0570 90000000 4883c320 4989aac8 00000049 ....H.. I......I + 0580 8982d000 00006241 ff081152 136241ff ......bA...R.bA. + 0590 08117214 62c1ff08 11521562 c1ff0811 ..r.b....R.b.... + 05a0 6a16c441 7b11a2b8 00000062 41ff0811 j..A{......bA... + 05b0 42186241 ff081162 1b62c1ff 0811421c B.bA...b.b....B. + 05c0 62c1ff08 115a1d62 c1ff0811 721ec441 b....Z.b....r..A + 05d0 7b1192f8 00000049 83c32049 83c02048 {......I.. I.. H + 05e0 83c72048 83c62048 83c12048 83c22049 .. H.. H.. H.. I + 05f0 81c20001 00004883 bc244801 0000000f ......H..$H..... + 0600 84010100 00c4417b 107808c5 7b104708 ......A{.x..{.G. + 0610 6261ff08 104e0162 61ff0810 5101c57b ba...N.ba...Q..{ + 0620 106b08c4 417b1073 08c57b10 5a08c4c1 .k..A{.s..{.Z... + 0630 7b104108 c5fb103b c4c17b10 33c4c17b {.A....;..{.3..{ + 0640 1028c5fb 1027c5fb 101ec5fb 1011c5fb .(...'.......... + 0650 100a6241 ff081021 c57b116c 24906241 ..bA...!.{.l$.bA + 0660 ff081122 c4c17b11 7a08c4c1 7b117210 ..."..{.z...{.r. + 0670 c4c17b11 6a18c4c1 7b116220 c4c17b11 ..{.j...{.b ..{. + 0680 5a28c4c1 7b115230 c4c17b11 4a38c4c1 Z(..{.R0..{.J8.. + 0690 7b114240 c4417b11 6a48c57b 11742488 {.B@.A{.jH.{.t$. + 06a0 c57b117c 24c0c57b 114424c8 6261ff08 .{.|$..{.D$.ba.. + 06b0 114c24fa 6261ff08 115424fb 4983c110 .L$.ba...T$.I... + 06c0 c4417b11 72504883 c310c441 7b117a58 .A{.rPH....A{.zX + 06d0 c4417b11 42606241 ff08114a 0d6241ff .A{.B`bA...J.bA. + 06e0 0811520e c4417b11 5a784983 c3104983 ..R..A{.ZxI...I. + 06f0 c0104883 c7104883 c6104883 c1104883 ..H...H...H...H. + 0700 c2104983 ea804883 bc245001 00000074 ..I...H..$P....t + 0710 5fc4c17b 1019c5fb 1013c4c1 7b100bc4 _..{........{... + 0720 c17b1000 c5fb1027 c5fb102e c5fb1031 .{.....'.......1 + 0730 c57b1002 4983c240 c4c17b11 5ac0c4c1 .{..I..@..{.Z... + 0740 7b1152c8 c4c17b11 4ad0c4c1 7b1142d8 {.R...{.J...{.B. + 0750 c4c17b11 62e0c4c1 7b116ae8 c4c17b11 ..{.b...{.j...{. + 0760 72f0c441 7b1142f8 0f1f8400 00000000 r..A{.B......... + 0770 4983c608 4d01e549 83c7404c 3bb424a0 I...M..I..@L;.$. + 0780 0000000f 84af0a00 004c3b74 24a80f8d .........L;t$... + 0790 9cfbffff 488b8424 e0000000 4883bc24 ....H..$....H..$ + 07a0 98000000 004a8d1c 38488b84 24180100 .....J..8H..$... + 07b0 004d89f9 4d8d1c07 488b8424 38010000 .M..M...H..$8... + 07c0 4d8d0407 488b8424 08010000 4a8d3c38 M...H..$....J.<8 + 07d0 488b8424 28010000 498d3407 488b8424 H..$(...I.4.H..$ + 07e0 20010000 498d0c07 488b8424 e8000000 ...I...H..$.... + 07f0 4a8d1438 488b4424 a80f8ea3 fbffff48 J..8H.D$.......H + 0800 89c54c89 9424b801 0000c57b 106c2488 ..L..$.....{.l$. + 0810 4c89d04c 89ac24b8 0000004d 89e24c89 L..L..$....M..L. + 0820 bc24c000 00004c89 742488c5 7b107424 .$....L.t$..{.t$ + 0830 e0c57b10 7c24c062 e1ff0810 4424fd62 ..{.|$.b....D$.b + 0840 e1ff0810 4c24fe62 e1ff0810 5424f962 ....L$.b....T$.b + 0850 e1ff0810 5c24ff62 e1ff0810 242462e1 ....\$.b....$$b. + 0860 ff08106c 240562e1 ff081074 24fa62e1 ...l$.b....t$.b. + 0870 ff08107c 24016261 ff081044 24026261 ...|$.ba...D$.ba + 0880 ff08104c 24066261 ff081054 24076261 ...L$.ba...T$.ba + 0890 ff08105c 24fb6261 ff081064 24036261 ...\$.ba...d$.ba + 08a0 ff08106c 24046261 ff081074 24084989 ...l$.ba...t$.I. + 08b0 ece9e004 0000662e 0f1f8400 00000000 ......f......... + 08c0 c4c17b10 7908c4c1 7b106110 c4c17b10 ..{.y...{.a...{. + 08d0 6918c4c1 7b107120 c4c17b10 5928c4c1 i...{.q ..{.Y(.. + 08e0 7b105130 c4c17b10 4938c5fb 104308c5 {.Q0..{.I8...C.. + 08f0 7b106b10 c57b1073 18c57b10 7b20c57b {.k..{.s..{.{ .{ + 0900 104b28c5 7b105330 c57b1063 384c8b3b .K(.{.S0.{.c8L.; + 0910 4d8b33c5 fb117c24 c0c5fb11 6424c8c5 M.3...|$....d$.. + 0920 fb116c24 d0c5fb11 7424d8c5 fb115c24 ..l$....t$....\$ + 0930 e0c5fb11 5424e8c5 fb114c24 f0c5fb11 ....T$....L$.... + 0940 442490c5 7b116c24 f8c57b11 3424c441 D$..{.l$..{.4$.A + 0950 7b106b08 c4417b10 7310c57b 117c2408 {.k..A{.s..{.|$. + 0960 c57b114c 2410c57b 11542418 c57b1164 .{.L$..{.T$..{.d /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 a5020000 00420e10 8f02420e .........B....B. + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 c41d0000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830703 6d020a0e 30410e28 ..A.8...m...0A.( - 0050 420e2042 0e18420e 10440e08 460b0000 B. B..B..D..F... + 0040 8606410e 38830747 0eb80303 86170a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0845 0b000000 D..E.... /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_SKYLAKEX.o (disasm) @@ -11,76 +11,962 @@ push %r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,-offset(%rsp) + mov %r9,offset(%rsp) + mov %rsi,offset(%rsp) mov offset(%rsp),%r14 test %rsi,%rsi jle + mov %rdi,%r11 + mov %r9,%r10 mov %rcx,%rax - imul %r9,%rax - mov %rdi,%r15 - sar %r15 - add %r8,%rax - lea (%rdx,%rax,8),%r13 - mov %rcx,%rax + mov %rdi,%rbx + and $something,%edi + mov %rcx,%rbp imul %r8,%rax + mov %rdi,offset(%rsp) + mov %r10,%rdi + imul %rbp,%rdi + mov %r8,%r12 + lea (%rax,%rcx,2),%rsi + mov %rax,%r8 + mov %rdx,%r13 + lea (%rsi,%rcx,1),%rcx + add %r12,%rdi + sub %r8,%rsi + lea (%rcx,%rbp,1),%rdx + mov %r13,%r12 + shl $something,%rsi + sub %r8,%rcx + lea offset(%r13,%rdi,8),%r13 + lea (%r10,%r8,1),%rdi + lea offset(%rbp,%rdx,1),%rax + lea (%r12,%rdi,8),%r12 + mov %rsi,offset(%rsp) + mov %r10,%rdi + lea offset(,%rcx,8),%rsi + mov offset(%rsp),%r10 + sub %r8,%rdx + lea offset(%rbp,%rax,1),%r9 + mov %rsi,offset(%rsp) + sub %r8,%rax + lea offset(,%rdx,8),%rsi + lea (%rdi,%r10,8),%r10 + mov %rsi,offset(%rsp) + lea offset(,%rax,8),%rsi + mov %r10,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rbp,%r10 + mov %r9,%rsi + lea (%r10,%r9,1),%rax + sub %r8,%rsi + mov %rbp,%r15 + lea offset(,%rsi,8),%rsi + lea offset(,%rbp,8),%rbp + sub %r8,%rax + mov %rsi,offset(%rsp) + lea offset(,%rax,8),%rsi + mov %rbp,%rax + mov %rsi,offset(%rsp) + lea offset(%rdi),%rdx + mov %rbp,%rsi + neg %rax + imul %rdi,%rax + imul %rsi,%rdx + mov %rbp,offset(%rsp) mov %rdi,%rbp - and $something,%rdi - add %r9,%rax - lea (%rdx,%rax,8),%r12 - lea (%r9,%rsi,2),%rax - mov %rax,-offset(%rsp) - lea offset(,%rcx,8),%rax - mov %rax,-offset(%rsp) - mov %rax,-offset(%rsp) - lea (%r8,%r15,2),%rax - mov %rax,-offset(%rsp) - mov %r15,%rax - mov %rdi,%r11 - mov %rcx,%r10 - shl $something,%rax - mov %rax,-offset(%rsp) - mov %r9,-offset(%rsp) - shl $something,%r10 - and $something,%ebp - add %r8,%r11 - mov %r9,%rdi - jmp - nopw offset(%rax,%rax,1) + mov %rsi,%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %rdi,%rdx + mov %rsi,offset(%rsp) + sar $something,%rbx + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %rdi,%rdx + mov %rcx,offset(%rsp) + mov %rbx,offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %rdi,%rdx + mov %rsi,offset(%rsp) + shl $something,%r15 + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %rdi,%rdx + mov %rcx,offset(%rsp) + vmovsd %xmm31,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %rdi,%rdx + mov %rsi,offset(%rsp) + vmovsd %xmm14,-offset(%rsp) + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %rdi,%rdx + mov %rcx,offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + lea (%rdx,%rax,1),%rdi + mov %r11,%rax + and $something,%rax + mov %rax,%rsi mov -offset(%rsp),%rax - mov %r13,%rsi + mov %rdi,offset(%rsp) + add %rax,%rsi + lea (%rax,%rbx,8),%rax + mov %rax,offset(%rsp) + mov %r11,%rax + and $something,%eax + mov %rax,offset(%rsp) + shl $something,%rbx + mov %r11,%rax + mov %rbx,offset(%rsp) + and $something,%eax + mov %r11,%rbx + mov %rax,offset(%rsp) + and $something,%ebx + mov %r12,%rax + and $something,%r11d + mov %rsi,-offset(%rsp) + mov %rbx,offset(%rsp) + mov %r11,offset(%rsp) + vmovsd %xmm16,-offset(%rsp) + vmovsd %xmm17,-offset(%rsp) + vmovsd %xmm18,-offset(%rsp) + vmovsd %xmm9,%xmm9,%xmm31 + vmovsd %xmm19,-offset(%rsp) + vmovsd %xmm10,%xmm10,%xmm9 + vmovsd %xmm11,-offset(%rsp) + mov %r15,%r12 + vmovsd %xmm12,%xmm12,%xmm11 + mov %r14,%r10 + vmovsd %xmm20,-offset(%rsp) + vmovsd %xmm21,(%rsp) + vmovsd %xmm22,offset(%rsp) + vmovsd %xmm23,-offset(%rsp) + vmovsd %xmm24,offset(%rsp) + vmovsd %xmm25,offset(%rsp) + vmovsd %xmm26,offset(%rsp) + vmovsd %xmm27,offset(%rsp) + vmovsd %xmm28,-offset(%rsp) + vmovsd %xmm29,offset(%rsp) + vmovsd %xmm30,offset(%rsp) + vmovsd %xmm0,%xmm0,%xmm10 + vmovsd %xmm13,%xmm13,%xmm12 + mov %rbp,%r14 + mov %rax,%r15 + jmp + cs nopw offset(%rax,%rax,1) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea offset(%r13,%rax,1),%rbx + mov offset(%rsp),%rax + mov %r13,%r9 + lea offset(%r13,%rax,1),%r11 + mov offset(%rsp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_SKYLAKEX.o (objdump) @@ -2,46 +2,480 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e04c8b 74243848 85f60f8e .H.t$.L.t$8H.... - 0030 ba010000 4889c849 0fafc149 89ff49d1 ....H..I...I..I. - 0040 ff4c01c0 4c8d2cc2 4889c849 0fafc048 .L..L.,.H..I...H - 0050 89fd4883 e7fe4c01 c84c8d24 c2498d04 ..H...L..L.$.I.. - 0060 71488944 24a8488d 04cd0000 00004889 qH.D$.H.......H. - 0070 4424b848 894424b0 4b8d0478 48894424 D$.H.D$.K..xH.D$ - 0080 c84c89f8 4989fb49 89ca48c1 e0054889 .L..I..I..H...H. - 0090 4424c04c 894c24f8 49c1e204 83e5014d D$.L.L$.I......M - 00a0 01c34c89 cfeb4f66 0f1f8400 00000000 ..L...Of........ - 00b0 488b4424 b04c89ee 498d4c05 004c89c0 H.D$.L..I.L..L.. - 00c0 4d85ff7f 4a4885ed 7416498d 56104839 M...JH..t.I.V.H9 - 00d0 c70f8fd9 0000000f 8dd30000 004989d6 .............I.. - 00e0 4883c702 4d01d549 83c41048 3b7c24a8 H...M..I...H;|$. - 00f0 0f84ea00 00004c39 c77db548 8b4424b8 ......L9.}.H.D$. - 0100 4c89e649 8d0c044c 89c04d85 ff7eb64c L..I...L..M..~.L - 0110 89c24c89 f0eb4066 0f1f8400 00000000 ..L...@f........ - 0120 c5fb101e c5fb104e 08c5fb10 11c5fb10 .......N........ - 0130 41084883 c610c5fb 1158e0c5 fb1150e8 A.H......X....P. - 0140 c5fb1148 f0c5fb11 40f84883 c1104883 ...H....@.H...H. - 0150 c2024c39 da744648 83c02048 39d77fc0 ..L9.tFH.. H9... - 0160 4e8d0c16 4a8d1c11 7c66c5fb 1016c5fb N...J...|f...... - 0170 1009c5fb 10410848 83c20248 c740f000 .....A.H...H.@.. - 0180 000000c5 fb1150e0 c5fb1148 e8c5fb11 ......P....H.... - 0190 40f84889 d94c89ce 4c39da75 ba488b44 @.H..L..L9.u.H.D - 01a0 24c84c03 7424c0e9 19ffffff 0f1f4000 $.L.t$........@. - 01b0 c5fb100e c5fb1001 c4c17b11 0ec4c17b ..........{....{ - 01c0 11460849 89d6e915 ffffff0f 1f440000 .F.I.........D.. - 01d0 4889d94c 89cee973 ffffff0f 1f440000 H..L...s.....D.. - 01e0 4c8b4c24 f8488b44 24e04d8d 0c41f644 L.L$.H.D$.M..A.D - 01f0 24d0010f 847d0000 00488b44 24d84d39 $....}...H.D$.M9 - 0200 c10f8d81 00000049 0fafc048 8b5c24f0 .......I...H.\$. - 0210 4c01c848 8d04c348 8b5c24e8 4885db7e L..H...H.\$.H..~ - 0220 55488b4c 24d84c89 c64c01c3 48f7de48 UH.L$.L..L..H..H - 0230 c1e10348 89da498d 3cf6eb1a 0f1f4000 ...H..I.<.....@. - 0240 c5fb1000 4883c008 c4a17b11 04c749ff ....H.....{...I. - 0250 c04c39c2 74204d39 c17fe548 8d34087c .L9.t M9...H.4.| - 0260 3fc5fb10 004889f0 c4a17b11 04c749ff ?....H....{...I. - 0270 c04c39c2 75e05b5d 415c415d 415e31c0 .L9.u.[]A\A]A^1. - 0280 415fc30f 1f440000 490fafc1 488b5c24 A_...D..I...H.\$ - 0290 f04c01c0 488d04c3 e97affff ff0f1f00 .L..H....z...... - 02a0 4889f0eb a9 H.... + 0000 41574156 41554154 55534881 ec800100 AWAVAUATUSH..... + 0010 004889b4 24a80000 0048c1fe 034889bc .H..$....H...H.. + 0020 24c80000 00488994 24680100 0048898c $....H..$h...H.. + 0030 24d00000 004c8944 24a84c89 8c249000 $....L.D$.L..$.. + 0040 00004889 b4247001 00004c8b b424b801 ..H..$p...L..$.. + 0050 00004885 f60f8efc 11000049 89fb4d89 ..H........I..M. + 0060 ca4889c8 4889fb83 e7074889 cd490faf .H..H.....H..I.. + 0070 c04889bc 24880000 004c89d7 480faffd .H..$....L..H... + 0080 4d89c448 8d344849 89c04989 d5488d0c M..H.4HI..I..H.. + 0090 0e4c01e7 4c29c648 8d14294d 89ec48c1 .L..L).H..)M..H. + 00a0 e6034c29 c14d8d6c fd004b8d 3c02488d ..L).M.l..K.<.H. + 00b0 4415004d 8d24fc48 89b42418 0100004c D..M.$.H..$....L + 00c0 89d7488d 34cd0000 00004c8b 94247001 ..H.4.....L..$p. + 00d0 00004c29 c24c8d4c 05004889 b4243801 ..L).L.L..H..$8. + 00e0 00004c29 c0488d34 d5000000 004e8d14 ..L).H.4.....N.. + 00f0 d74889b4 24080100 00488d34 c5000000 .H..$....H.4.... + 0100 004c8994 24a00000 004889b4 24280100 .L..$....H..$(.. + 0110 004989ea 4c89ce4b 8d040a4c 29c64989 .I..L..K...L).I. + 0120 ef488d34 f5000000 00488d2c ed000000 .H.4.....H.,.... + 0130 004c29c0 4889b424 20010000 488d34c5 .L).H..$ ...H.4. + 0140 00000000 4889e848 89b424e8 00000048 ....H..H..$....H + 0150 8d570148 89ee48f7 d8480faf c7480faf .W.H..H..H...H.. + 0160 d64889ac 24e00000 004889fd 4889f748 .H..$....H..H..H + 0170 8d340248 8d550248 0fafd748 89b42440 .4.H.U.H...H..$@ + 0180 01000048 c1fb0348 8d0c0248 8d550348 ...H...H...H.U.H + 0190 0fafd748 898c24d8 00000048 899c2498 ...H..$....H..$. + 01a0 00000048 8d340248 8d550448 0fafd748 ...H.4.H.U.H...H + 01b0 89b42410 01000049 c1e70648 8d0c0248 ..$....I...H...H + 01c0 8d550548 0fafd748 898c2430 01000062 .U.H...H..$0...b + 01d0 61ff0811 7c24f248 8d340248 8d550648 a...|$.H.4.H.U.H + 01e0 0fafd748 89b42400 010000c5 7b117424 ...H..$.....{.t$ + 01f0 88488d0c 02488d55 07480faf d748898c .H...H.U.H...H.. + 0200 24f00000 00c57b11 7c24e048 8d3c024c $.....{.|$.H.<.L + 0210 89d84883 e0f84889 c6488b44 24a84889 ..H...H..H.D$.H. + 0220 bc24f800 00004801 c6488d04 d8488984 .$....H..H...H.. + 0230 24580100 004c89d8 83e00648 89842478 $X...L.....H..$x + 0240 01000048 c1e3094c 89d84889 9c246001 ...H...L..H..$`. + 0250 000083e0 024c89db 48898424 48010000 .....L..H..$H... + 0260 83e3044c 89e04183 e3014889 7424b048 ...L..A...H.t$.H + 0270 899c24b0 0000004c 899c2450 01000062 ..$....L..$P...b + 0280 e1ff0811 4424f862 e1ff0811 4c24fd62 ....D$.b....L$.b + 0290 e1ff0811 5424fe62 41b70810 f962e1ff ....T$.bA....b.. + 02a0 08115c24 f9c4412b 10cac57b 115c2498 ..\$..A+...{.\$. + 02b0 4d89fcc4 411b10dc 4d89f262 e1ff0811 M...A...M..b.... + 02c0 6424ff62 e1ff0811 2c2462e1 ff081174 d$.b....,$b....t + 02d0 240562e1 ff08117c 24fa6261 ff081144 $.b....|$.ba...D + 02e0 24016261 ff08114c 24026261 ff081154 $.ba...L$.ba...T + 02f0 24066261 ff08115c 24076261 ff081164 $.ba...\$.ba...d + 0300 24fb6261 ff08116c 24036261 ff081174 $.ba...l$.ba...t + 0310 2404c57b 10d0c441 1310e549 89ee4989 $..{...A...I..I. + 0320 c7e96304 0000662e 0f1f8400 00000000 ..c...f......... + 0330 488b8424 40010000 4883bc24 98000000 H..$@...H..$.... + 0340 00498d5c 0500488b 8424d800 00004d89 .I.\..H..$....M. + 0350 e94d8d5c 0500488b 84241001 00004d8d .M.\..H..$....M. + 0360 44050048 8b842430 01000049 8d7c0500 D..H..$0...I.|.. + 0370 488b8424 00010000 498d7405 00488b84 H..$....I.t..H.. + 0380 24f00000 00498d4c 0500488b 8424f800 $....I.L..H..$.. + 0390 0000498d 54050048 8b4424a8 0f8f5d04 ..I.T..H.D$...]. + 03a0 00004883 bc248800 0000000f 84bf0300 ..H..$.......... + 03b0 004939c6 0f8e360e 00004883 bc24b000 .I9...6...H..$.. + 03c0 0000000f 842d0200 00c57b10 6b08c441 .....-....{.k..A + 03d0 7b107308 c4417b10 7b106241 ff081048 {.s..A{.{.bA...H + 03e0 016241ff 08105002 6241ff08 10600362 .bA...P.bA...`.b + 03f0 61ff0810 6f016261 ff081077 0262e1ff a...o.ba...w.b.. + 0400 08104703 62e1ff08 104e0162 e1ff0810 ..G.b....N.b.... + 0410 5602c4c1 7b107908 62c1ff08 10790262 V...{.y.b....y.b + 0420 41ff0810 4103c5fb 1033c57b 10431048 A...A....3.{.C.H + 0430 8b6b18c4 c17b102b 498b4318 c4c17b10 .k...{.+I.C...{. + 0440 20c5fb10 1fc5fb10 16c57b11 6c2490c5 .........{.l$.. + 0450 7b117424 88c57b11 7c24e062 61ff0811 {.t$..{.|$.ba... + 0460 4c24f862 61ff0811 5424fd62 61ff0811 L$.ba...T$.ba... + 0470 6424fe62 61ff0811 6c24f962 61ff0811 d$.ba...l$.ba... + 0480 7424ff62 e1ff0811 042462e1 ff08114c t$.b.....$b....L + 0490 24fa62e1 ff081154 240162e1 ff08105e $.b....T$.b....^ + 04a0 0362e1ff 08106902 62e1ff08 10710362 .b....i.b....q.b + 04b0 e1ff0810 6101c57b 106210c5 7b105218 ....a..{.b..{.R. + 04c0 c5fb1009 c5fb1002 c57b105a 086241ff .........{.Z.bA. + 04d0 08101962 e1ff0811 5c240262 41ff0811 ...b....\$.bA... + 04e0 1ac4c17b 117208c4 c17b116a 10c4c17b ...{.r...{.j...{ + 04f0 116218c4 c17b115a 20c4c17b 115228c4 .b...{.Z ..{.R(. + 0500 c17b114a 30c4c17b 114238c4 c17b117a .{.J0..{.B8..{.z + 0510 40c4417b 116a48c4 417b1172 506241ff @.A{.jH.A{.rPbA. + 0520 08114a0b 6241ff08 116a0c62 c1ff0811 ..J.bA...j.b.... + 0530 4a0d62c1 ff081162 0ec4417b 115a7862 J.b....b..A{.Zxb + 0540 c1ff0811 7a10c441 7b118288 00000062 ....z..A{......b + 0550 e1ff0811 6424fb62 e1ff0811 6c240362 ....d$.b....l$.b + 0560 e1ff0811 74240449 83c120c4 417b11ba ....t$.I.. .A{.. + 0570 90000000 4883c320 4989aac8 00000049 ....H.. I......I + 0580 8982d000 00006241 ff081152 136241ff ......bA...R.bA. + 0590 08117214 62c1ff08 11521562 c1ff0811 ..r.b....R.b.... + 05a0 6a16c441 7b11a2b8 00000062 41ff0811 j..A{......bA... + 05b0 42186241 ff081162 1b62c1ff 0811421c B.bA...b.b....B. + 05c0 62c1ff08 115a1d62 c1ff0811 721ec441 b....Z.b....r..A + 05d0 7b1192f8 00000049 83c32049 83c02048 {......I.. I.. H + 05e0 83c72048 83c62048 83c12048 83c22049 .. H.. H.. H.. I + 05f0 81c20001 00004883 bc244801 0000000f ......H..$H..... + 0600 84010100 00c4417b 107808c5 7b104708 ......A{.x..{.G. + 0610 6261ff08 104e0162 61ff0810 5101c57b ba...N.ba...Q..{ + 0620 106b08c4 417b1073 08c57b10 5a08c4c1 .k..A{.s..{.Z... + 0630 7b104108 c5fb103b c4c17b10 33c4c17b {.A....;..{.3..{ + 0640 1028c5fb 1027c5fb 101ec5fb 1011c5fb .(...'.......... + 0650 100a6241 ff081021 c57b116c 24906241 ..bA...!.{.l$.bA + 0660 ff081122 c4c17b11 7a08c4c1 7b117210 ..."..{.z...{.r. + 0670 c4c17b11 6a18c4c1 7b116220 c4c17b11 ..{.j...{.b ..{. + 0680 5a28c4c1 7b115230 c4c17b11 4a38c4c1 Z(..{.R0..{.J8.. + 0690 7b114240 c4417b11 6a48c57b 11742488 {.B@.A{.jH.{.t$. + 06a0 c57b117c 24c0c57b 114424c8 6261ff08 .{.|$..{.D$.ba.. + 06b0 114c24fa 6261ff08 115424fb 4983c110 .L$.ba...T$.I... + 06c0 c4417b11 72504883 c310c441 7b117a58 .A{.rPH....A{.zX + 06d0 c4417b11 42606241 ff08114a 0d6241ff .A{.B`bA...J.bA. + 06e0 0811520e c4417b11 5a784983 c3104983 ..R..A{.ZxI...I. + 06f0 c0104883 c7104883 c6104883 c1104883 ..H...H...H...H. + 0700 c2104983 ea804883 bc245001 00000074 ..I...H..$P....t + 0710 5fc4c17b 1019c5fb 1013c4c1 7b100bc4 _..{........{... + 0720 c17b1000 c5fb1027 c5fb102e c5fb1031 .{.....'.......1 + 0730 c57b1002 4983c240 c4c17b11 5ac0c4c1 .{..I..@..{.Z... + 0740 7b1152c8 c4c17b11 4ad0c4c1 7b1142d8 {.R...{.J...{.B. + 0750 c4c17b11 62e0c4c1 7b116ae8 c4c17b11 ..{.b...{.j...{. + 0760 72f0c441 7b1142f8 0f1f8400 00000000 r..A{.B......... + 0770 4983c608 4d01e549 83c7404c 3bb424a0 I...M..I..@L;.$. + 0780 0000000f 84af0a00 004c3b74 24a80f8d .........L;t$... + 0790 9cfbffff 488b8424 e0000000 4883bc24 ....H..$....H..$ + 07a0 98000000 004a8d1c 38488b84 24180100 .....J..8H..$... + 07b0 004d89f9 4d8d1c07 488b8424 38010000 .M..M...H..$8... + 07c0 4d8d0407 488b8424 08010000 4a8d3c38 M...H..$....J.<8 + 07d0 488b8424 28010000 498d3407 488b8424 H..$(...I.4.H..$ + 07e0 20010000 498d0c07 488b8424 e8000000 ...I...H..$.... + 07f0 4a8d1438 488b4424 a80f8ea3 fbffff48 J..8H.D$.......H + 0800 89c54c89 9424b801 0000c57b 106c2488 ..L..$.....{.l$. + 0810 4c89d04c 89ac24b8 0000004d 89e24c89 L..L..$....M..L. + 0820 bc24c000 00004c89 742488c5 7b107424 .$....L.t$..{.t$ + 0830 e0c57b10 7c24c062 e1ff0810 4424fd62 ..{.|$.b....D$.b + 0840 e1ff0810 4c24fe62 e1ff0810 5424f962 ....L$.b....T$.b + 0850 e1ff0810 5c24ff62 e1ff0810 242462e1 ....\$.b....$$b. + 0860 ff08106c 240562e1 ff081074 24fa62e1 ...l$.b....t$.b. + 0870 ff08107c 24016261 ff081044 24026261 ...|$.ba...D$.ba + 0880 ff08104c 24066261 ff081054 24076261 ...L$.ba...T$.ba + 0890 ff08105c 24fb6261 ff081064 24036261 ...\$.ba...d$.ba + 08a0 ff08106c 24046261 ff081074 24084989 ...l$.ba...t$.I. + 08b0 ece9e004 0000662e 0f1f8400 00000000 ......f......... + 08c0 c4c17b10 7908c4c1 7b106110 c4c17b10 ..{.y...{.a...{. + 08d0 6918c4c1 7b107120 c4c17b10 5928c4c1 i...{.q ..{.Y(.. + 08e0 7b105130 c4c17b10 4938c5fb 104308c5 {.Q0..{.I8...C.. + 08f0 7b106b10 c57b1073 18c57b10 7b20c57b {.k..{.s..{.{ .{ + 0900 104b28c5 7b105330 c57b1063 384c8b3b .K(.{.S0.{.c8L.; + 0910 4d8b33c5 fb117c24 c0c5fb11 6424c8c5 M.3...|$....d$.. + 0920 fb116c24 d0c5fb11 7424d8c5 fb115c24 ..l$....t$....\$ + 0930 e0c5fb11 5424e8c5 fb114c24 f0c5fb11 ....T$....L$.... + 0940 442490c5 7b116c24 f8c57b11 3424c441 D$..{.l$..{.4$.A + 0950 7b106b08 c4417b10 7310c57b 117c2408 {.k..A{.s..{.|$. + 0960 c57b114c 2410c57b 11542418 c57b1164 .{.L$..{.T$..{.d /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ounncopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 a5020000 00420e10 8f02420e .........B....B. + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 c41d0000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830703 6d020a0e 30410e28 ..A.8...m...0A.( - 0050 420e2042 0e18420e 10440e08 460b0000 B. B..B..D..F... + 0040 8606410e 38830747 0eb80303 86170a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0845 0b000000 D..E.... /usr/lib64/libopenblas_openmp.a/dtrmm_ounucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ounucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ounucopy_COOPERLAKE.o (disasm) @@ -11,81 +11,938 @@ push %r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,-offset(%rsp) + mov %r9,offset(%rsp) + mov %rsi,offset(%rsp) mov offset(%rsp),%r13 test %rsi,%rsi jle + mov %rdi,%r11 + mov %r9,%r10 mov %rcx,%rax - imul %r9,%rax - mov %rcx,%rbx - mov %rdi,%r14 - add %r8,%rax - lea (%rdx,%rax,8),%r12 - mov %rcx,%rax + mov %rdi,%rbx + and $something,%edi + mov %rcx,%rbp imul %r8,%rax - sar %r14 - mov %rdi,%r15 - add %r9,%rax - lea (%rdx,%rax,8),%rbp - lea offset(,%rbx,8),%rax - mov %rax,-offset(%rsp) - mov %rax,-offset(%rsp) - lea (%r8,%r14,2),%rax - and $something,%rdi - mov %rax,-offset(%rsp) - mov %r14,%rax - mov %rcx,%r10 - mov %rdi,%r11 - lea (%r9,%rsi,2),%rcx - shl $something,%rax - mov %r9,-offset(%rsp) - mov %r9,%rdi - mov %rax,-offset(%rsp) - vmovsd offset(%rip),%xmm4 # - shl $something,%r10 - and $something,%r15d - add %r8,%r11 - mov %rcx,%r9 + mov %rdi,offset(%rsp) + mov %r10,%rdi + imul %rbp,%rdi + mov %r8,%r12 + lea (%rax,%rcx,2),%rsi + mov %rax,%r8 + mov %rdx,%r15 + lea (%rsi,%rcx,1),%rcx + add %r12,%rdi + lea offset(%rbp,%rcx,1),%rdx + mov %r15,%r12 + sub %r8,%rcx + lea (%r15,%rdi,8),%r15 + lea (%r10,%r8,1),%rdi + lea offset(%rbp,%rdx,1),%rax + lea (%r12,%rdi,8),%r12 + shl $something,%rcx + mov %r10,%rdi + sub %r8,%rdx + mov offset(%rsp),%r10 + lea (%rax,%rbp,1),%r9 + mov %rcx,offset(%rsp) + sub %r8,%rax + lea offset(,%rdx,8),%rcx + lea (%rdi,%r10,8),%r10 + mov %rcx,offset(%rsp) + lea offset(,%rax,8),%rcx + mov %r10,offset(%rsp) + mov %rcx,offset(%rsp) + mov %rbp,%r10 + mov %r9,%rcx + sub %r8,%rcx + lea (%r9,%r10,1),%rax + mov %rbp,%r14 + lea offset(,%rcx,8),%rcx + lea offset(,%rbp,8),%rbp + sub %r8,%rax + sub %r8,%rsi + mov %rcx,offset(%rsp) + shl $something,%rsi + lea offset(,%rax,8),%rcx + mov %rbp,%rax + mov %rsi,offset(%rsp) + lea offset(%rdi),%rdx + mov %rbp,%rsi + neg %rax + imul %rdi,%rax + imul %rsi,%rdx + mov %rcx,offset(%rsp) + mov %rbp,offset(%rsp) + lea (%rdx,%rax,1),%rcx + lea offset(%rdi),%rdx + imul %rsi,%rdx + mov %rcx,offset(%rsp) + mov %rdi,%rbp + lea (%rdx,%rax,1),%rcx + lea offset(%rdi),%rdx + imul %rsi,%rdx + mov %rcx,offset(%rsp) + sar $something,%rbx + lea (%rdx,%rax,1),%rdi + lea offset(%rbp),%rdx + imul %rsi,%rdx + mov %rdi,offset(%rsp) + mov %rbx,offset(%rsp) + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %rsi,%rdx + mov %rcx,offset(%rsp) + shl $something,%r14 + lea (%rdx,%rax,1),%rdi + lea offset(%rbp),%rdx + imul %rsi,%rdx + mov %rdi,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %rsi,%rdx + mov %rcx,offset(%rsp) + vmovsd %xmm18,-offset(%rsp) + lea (%rdx,%rax,1),%rdi + mov %r11,%rax + and $something,%rax + mov %rax,%rcx + mov -offset(%rsp),%rax + mov %rdi,offset(%rsp) + add %rax,%rcx + lea (%rax,%rbx,8),%rax + mov %rax,offset(%rsp) + mov %r11,%rax + and $something,%eax + mov %rax,offset(%rsp) + shl $something,%rbx + mov %r11,%rax + mov %rbx,offset(%rsp) + and $something,%eax + mov %r11,%rbx + mov %rax,offset(%rsp) + and $something,%ebx + mov %r12,%rax + and $something,%r11d + mov %rcx,-offset(%rsp) + mov %rbx,offset(%rsp) + mov %r11,offset(%rsp) + vmovsd %xmm19,-offset(%rsp) + vmovsd %xmm20,-offset(%rsp) + vmovsd %xmm21,-offset(%rsp) + vmovsd %xmm22,-offset(%rsp) + mov %r14,%r12 + vmovsd %xmm23,-offset(%rsp) + mov %r15,%r14 + vmovsd %xmm30,-offset(%rsp) + vmovsd %xmm12,offset(%rsp) + mov %r13,%rdi + vmovsd %xmm13,%xmm13,%xmm12 + vmovsd %xmm24,-offset(%rsp) + vmovsd %xmm14,%xmm14,%xmm13 + vmovsd %xmm25,-offset(%rsp) + vmovsd %xmm15,%xmm15,%xmm14 + vmovsd %xmm26,-offset(%rsp) + vmovsd %xmm16,%xmm16,%xmm15 + vmovsd %xmm27,-offset(%rsp) + vmovsd %xmm28,-offset(%rsp) + vmovsd %xmm29,-offset(%rsp) + vmovsd %xmm31,(%rsp) + vmovsd %xmm11,%xmm11,%xmm30 + vmovsd %xmm17,%xmm17,%xmm16 + mov %rbp,%r13 + mov %rax,%r15 + jmp + nopl (%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%r14,%rax,1),%r11 + mov offset(%rsp),%rax + mov %r14,%rbx + lea (%r14,%rax,1),%r10 + mov offset(%rsp),%rax + lea (%r14,%rax,1),%r9 + mov offset(%rsp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_ounucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ounucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ounucopy_COOPERLAKE.o (objdump) @@ -2,48 +2,464 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_ounucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e04c8b 6c243848 85f60f8e .H.t$.L.l$8H.... - 0030 ca010000 4889c849 0fafc148 89cb4989 ....H..I...H..I. - 0040 fe4c01c0 4c8d24c2 4889c849 0fafc049 .L..L.$.H..I...I - 0050 d1fe4989 ff4c01c8 488d2cc2 488d04dd ..I..L..H.,.H... - 0060 00000000 48894424 b8488944 24b04b8d ....H.D$.H.D$.K. - 0070 04704883 e7fe4889 4424c84c 89f04989 .pH...H.D$.L..I. - 0080 ca4989fb 498d0c71 48c1e005 4c894c24 .I..I..qH...L.L$ - 0090 f84c89cf 48894424 c0c5fb10 25000000 .L..H.D$....%... - 00a0 0049c1e2 044183e7 014d01c3 4989c9eb .I...A...M..I... - 00b0 580f1f80 00000000 488b4424 b04c89e6 X.......H.D$.L.. - 00c0 498d0c04 4c89c04d 85f67f57 4d85ff74 I...L..M...WM..t - 00d0 24498d55 104839c7 0f8ee200 0000c5fb $I.U.H9......... - 00e0 100ec5fb 1001c4c1 7b114d00 c4c17b11 ........{.M...{. - 00f0 45084989 d54883c7 024d01d4 4883c510 E.I..H...M..H... - 0100 4c39cf0f 84e70000 004c39c7 7daa488b L9.......L9.}.H. - 0110 4424b848 89ee488d 4c05004c 89c04d85 D$.H..H.L..L..M. - 0120 f67ea94c 89c24c89 e8eb3c0f 1f440000 .~.L..L...<..D.. - 0130 c5fb101e c5fb104e 08c5fb10 11c5fb10 .......N........ - 0140 41084883 c610c5fb 1158e0c5 fb1150e8 A.H......X....P. - 0150 c5fb1148 f0c5fb11 40f84883 c1104883 ...H....@.H...H. - 0160 c2024c39 da743c48 83c02048 39d77fc0 ..L9.t + mov %rdi,%r11 + mov %r9,%r10 mov %rcx,%rax - imul %r9,%rax - mov %rcx,%rbx - mov %rdi,%r14 - add %r8,%rax - lea (%rdx,%rax,8),%r12 - mov %rcx,%rax + mov %rdi,%rbx + and $something,%edi + mov %rcx,%rbp imul %r8,%rax - sar %r14 - mov %rdi,%r15 - add %r9,%rax - lea (%rdx,%rax,8),%rbp - lea offset(,%rbx,8),%rax - mov %rax,-offset(%rsp) - mov %rax,-offset(%rsp) - lea (%r8,%r14,2),%rax - and $something,%rdi - mov %rax,-offset(%rsp) - mov %r14,%rax - mov %rcx,%r10 - mov %rdi,%r11 - lea (%r9,%rsi,2),%rcx - shl $something,%rax - mov %r9,-offset(%rsp) - mov %r9,%rdi - mov %rax,-offset(%rsp) - vmovsd offset(%rip),%xmm4 # - shl $something,%r10 - and $something,%r15d - add %r8,%r11 - mov %rcx,%r9 + mov %rdi,offset(%rsp) + mov %r10,%rdi + imul %rbp,%rdi + mov %r8,%r12 + lea (%rax,%rcx,2),%rsi + mov %rax,%r8 + mov %rdx,%r15 + lea (%rsi,%rcx,1),%rcx + add %r12,%rdi + lea offset(%rbp,%rcx,1),%rdx + mov %r15,%r12 + sub %r8,%rcx + lea (%r15,%rdi,8),%r15 + lea (%r10,%r8,1),%rdi + lea offset(%rbp,%rdx,1),%rax + lea (%r12,%rdi,8),%r12 + shl $something,%rcx + mov %r10,%rdi + sub %r8,%rdx + mov offset(%rsp),%r10 + lea (%rax,%rbp,1),%r9 + mov %rcx,offset(%rsp) + sub %r8,%rax + lea offset(,%rdx,8),%rcx + lea (%rdi,%r10,8),%r10 + mov %rcx,offset(%rsp) + lea offset(,%rax,8),%rcx + mov %r10,offset(%rsp) + mov %rcx,offset(%rsp) + mov %rbp,%r10 + mov %r9,%rcx + sub %r8,%rcx + lea (%r9,%r10,1),%rax + mov %rbp,%r14 + lea offset(,%rcx,8),%rcx + lea offset(,%rbp,8),%rbp + sub %r8,%rax + sub %r8,%rsi + mov %rcx,offset(%rsp) + shl $something,%rsi + lea offset(,%rax,8),%rcx + mov %rbp,%rax + mov %rsi,offset(%rsp) + lea offset(%rdi),%rdx + mov %rbp,%rsi + neg %rax + imul %rdi,%rax + imul %rsi,%rdx + mov %rcx,offset(%rsp) + mov %rbp,offset(%rsp) + lea (%rdx,%rax,1),%rcx + lea offset(%rdi),%rdx + imul %rsi,%rdx + mov %rcx,offset(%rsp) + mov %rdi,%rbp + lea (%rdx,%rax,1),%rcx + lea offset(%rdi),%rdx + imul %rsi,%rdx + mov %rcx,offset(%rsp) + sar $something,%rbx + lea (%rdx,%rax,1),%rdi + lea offset(%rbp),%rdx + imul %rsi,%rdx + mov %rdi,offset(%rsp) + mov %rbx,offset(%rsp) + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %rsi,%rdx + mov %rcx,offset(%rsp) + shl $something,%r14 + lea (%rdx,%rax,1),%rdi + lea offset(%rbp),%rdx + imul %rsi,%rdx + mov %rdi,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %rsi,%rdx + mov %rcx,offset(%rsp) + vmovsd %xmm18,-offset(%rsp) + lea (%rdx,%rax,1),%rdi + mov %r11,%rax + and $something,%rax + mov %rax,%rcx + mov -offset(%rsp),%rax + mov %rdi,offset(%rsp) + add %rax,%rcx + lea (%rax,%rbx,8),%rax + mov %rax,offset(%rsp) + mov %r11,%rax + and $something,%eax + mov %rax,offset(%rsp) + shl $something,%rbx + mov %r11,%rax + mov %rbx,offset(%rsp) + and $something,%eax + mov %r11,%rbx + mov %rax,offset(%rsp) + and $something,%ebx + mov %r12,%rax + and $something,%r11d + mov %rcx,-offset(%rsp) + mov %rbx,offset(%rsp) + mov %r11,offset(%rsp) + vmovsd %xmm19,-offset(%rsp) + vmovsd %xmm20,-offset(%rsp) + vmovsd %xmm21,-offset(%rsp) + vmovsd %xmm22,-offset(%rsp) + mov %r14,%r12 + vmovsd %xmm23,-offset(%rsp) + mov %r15,%r14 + vmovsd %xmm30,-offset(%rsp) + vmovsd %xmm12,offset(%rsp) + mov %r13,%rdi + vmovsd %xmm13,%xmm13,%xmm12 + vmovsd %xmm24,-offset(%rsp) + vmovsd %xmm14,%xmm14,%xmm13 + vmovsd %xmm25,-offset(%rsp) + vmovsd %xmm15,%xmm15,%xmm14 + vmovsd %xmm26,-offset(%rsp) + vmovsd %xmm16,%xmm16,%xmm15 + vmovsd %xmm27,-offset(%rsp) + vmovsd %xmm28,-offset(%rsp) + vmovsd %xmm29,-offset(%rsp) + vmovsd %xmm31,(%rsp) + vmovsd %xmm11,%xmm11,%xmm30 + vmovsd %xmm17,%xmm17,%xmm16 + mov %rbp,%r13 + mov %rax,%r15 + jmp + nopl (%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%r14,%rax,1),%r11 + mov offset(%rsp),%rax + mov %r14,%rbx + lea (%r14,%rax,1),%r10 + mov offset(%rsp),%rax + lea (%r14,%rax,1),%r9 + mov offset(%rsp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_ounucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_ounucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_ounucopy_SKYLAKEX.o (objdump) @@ -2,48 +2,464 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_ounucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e04c8b 6c243848 85f60f8e .H.t$.L.l$8H.... - 0030 ca010000 4889c849 0fafc148 89cb4989 ....H..I...H..I. - 0040 fe4c01c0 4c8d24c2 4889c849 0fafc049 .L..L.$.H..I...I - 0050 d1fe4989 ff4c01c8 488d2cc2 488d04dd ..I..L..H.,.H... - 0060 00000000 48894424 b8488944 24b04b8d ....H.D$.H.D$.K. - 0070 04704883 e7fe4889 4424c84c 89f04989 .pH...H.D$.L..I. - 0080 ca4989fb 498d0c71 48c1e005 4c894c24 .I..I..qH...L.L$ - 0090 f84c89cf 48894424 c0c5fb10 25000000 .L..H.D$....%... - 00a0 0049c1e2 044183e7 014d01c3 4989c9eb .I...A...M..I... - 00b0 580f1f80 00000000 488b4424 b04c89e6 X.......H.D$.L.. - 00c0 498d0c04 4c89c04d 85f67f57 4d85ff74 I...L..M...WM..t - 00d0 24498d55 104839c7 0f8ee200 0000c5fb $I.U.H9......... - 00e0 100ec5fb 1001c4c1 7b114d00 c4c17b11 ........{.M...{. - 00f0 45084989 d54883c7 024d01d4 4883c510 E.I..H...M..H... - 0100 4c39cf0f 84e70000 004c39c7 7daa488b L9.......L9.}.H. - 0110 4424b848 89ee488d 4c05004c 89c04d85 D$.H..H.L..L..M. - 0120 f67ea94c 89c24c89 e8eb3c0f 1f440000 .~.L..L...<..D.. - 0130 c5fb101e c5fb104e 08c5fb10 11c5fb10 .......N........ - 0140 41084883 c610c5fb 1158e0c5 fb1150e8 A.H......X....P. - 0150 c5fb1148 f0c5fb11 40f84883 c1104883 ...H....@.H...H. - 0160 c2024c39 da743c48 83c02048 39d77fc0 ..L9.t mov %rcx,%rax - imul %r9,%rax - mov %rdi,%r14 - sar %r14 - add %r8,%rax - lea (%rdx,%rax,8),%r12 - mov %rcx,%rax imul %r8,%rax - mov %rcx,%r10 - mov %rdi,%r15 - add %r9,%rax - lea (%rdx,%rax,8),%rbp - lea offset(,%rcx,8),%rax - mov %rax,-offset(%rsp) - mov %rdi,%rcx - mov %rax,-offset(%rsp) - lea (%r8,%r14,2),%rax - mov %rax,-offset(%rsp) - and $something,%rcx - mov %r14,%rax - lea (%r9,%rsi,2),%rsi - mov %rcx,%r11 - shl $something,%rax - mov %r9,-offset(%rsp) - mov %r9,%rdi - mov %rax,-offset(%rsp) + mov %rcx,%r15 + mov %r15,%r10 + mov %r9,%rbp + shl $something,%r10 + imul %r15,%r9 + mov %r8,%r12 + mov %r10,offset(%rsp) + lea (%rax,%rcx,2),%r8 + mov %r15,%r10 + mov %rdi,%r11 shl $something,%r10 - and $something,%r15d - add %r8,%r11 - mov %rsi,%r9 + lea (%r8,%rcx,1),%rdi + add %r12,%r9 + lea (%rdi,%rcx,1),%rsi + mov offset(%rsp),%r12 + mov %r10,offset(%rsp) + mov %r11,%r10 + lea (%rsi,%rcx,1),%rcx + and $something,%r10d + lea (%rcx,%r15,1),%rdx + sub %rax,%rdi + mov %r10,-offset(%rsp) + mov %r15,%r14 + mov %r15,%r10 + lea (%r12,%r9,8),%r15 + lea offset(%rbp,%rax,1),%r9 + shl $something,%rdi + sub %rax,%rsi + lea (%r12,%r9,8),%r12 + mov %rbp,%r9 + mov offset(%rsp),%rbp + sub %rax,%rcx + mov %rdi,offset(%rsp) + lea offset(,%rsi,8),%rdi + mov %rdi,offset(%rsp) + lea (%r9,%rbp,8),%rbp + lea offset(,%rcx,8),%rdi + mov %rdx,%rcx + sub %rax,%rcx + mov %rbp,offset(%rsp) + add %r10,%rdx + lea offset(,%r10,8),%rbp + sub %rax,%rdx + sub %rax,%r8 + mov %rdi,offset(%rsp) + mov %rbp,%rax + lea offset(,%rcx,8),%rdi + mov %rdi,offset(%rsp) + neg %rax + lea offset(,%rdx,8),%rdi + lea offset(%r9),%rdx + imul %r9,%rax + imul %rbp,%rdx + mov %rdi,offset(%rsp) + mov %r11,%rbx + lea (%rdx,%rax,1),%rdi + lea offset(%r9),%rdx + imul %rbp,%rdx + mov %rdi,offset(%rsp) + sar $something,%rbx + lea (%rdx,%rax,1),%rcx + lea offset(%r9),%rdx + imul %rbp,%rdx + mov %rcx,offset(%rsp) + mov %rbx,offset(%rsp) + lea (%rdx,%rax,1),%rdi + lea offset(%r9),%rdx + imul %rbp,%rdx + mov %rdi,offset(%rsp) + shl $something,%r14 + lea (%rdx,%rax,1),%rcx + lea offset(%r9),%rdx + imul %rbp,%rdx + mov %rcx,offset(%rsp) + shl $something,%r8 + lea (%rdx,%rax,1),%rdi + lea offset(%r9),%rdx + imul %rbp,%rdx + mov %rdi,offset(%rsp) + mov %rbp,offset(%rsp) + lea (%rdx,%rax,1),%rcx + lea offset(%r9),%rdx + imul %rbp,%rdx + vmovsd %xmm26,-offset(%rsp) + mov %r8,offset(%rsp) + lea (%rdx,%rax,1),%rdi + mov %r11,%rax + and $something,%rax + mov %rdi,offset(%rsp) + mov %rax,%rdi + mov -offset(%rsp),%rax + mov %rcx,offset(%rsp) + add %rax,%rdi + lea (%rax,%rbx,8),%rax + mov %rax,offset(%rsp) + mov %r11,%rax + shl $something,%rbx + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + mov %r11,%rbx + mov %r11,%rax + and $something,%ebx + and $something,%eax + and $something,%r11d + mov %rbx,offset(%rsp) + mov %r11,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rax,offset(%rsp) + vmovsd %xmm27,-offset(%rsp) + vmovsd %xmm28,-offset(%rsp) + mov %r15,%rbp + vmovsd %xmm29,-offset(%rsp) + mov %r14,%r11 + vmovsd %xmm17,-offset(%rsp) + mov %r9,%rbx + vmovsd %xmm18,%xmm18,%xmm17 + vmovsd %xmm30,%xmm30,%xmm26 + vmovsd %xmm19,%xmm19,%xmm18 + vmovsd %xmm31,-offset(%rsp) + vmovsd %xmm20,%xmm20,%xmm19 + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm21,%xmm21,%xmm20 + vmovsd %xmm16,-offset(%rsp) + vmovsd %xmm22,%xmm22,%xmm21 + mov %r13,%r15 + vmovsd %xmm23,%xmm23,%xmm22 + vmovsd %xmm24,%xmm24,%xmm23 + vmovsd %xmm25,%xmm25,%xmm24 jmp - nopl offset(%rax) + nopl offset(%rax,%rax,1) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea offset(%rbp,%rax,1),%rdi + mov offset(%rsp),%rax + mov %rbp,%r10 + lea offset(%rbp,%rax,1),%rsi + mov offset(%rsp),%rax + lea offset(%rbp,%rax,1),%rcx + mov offset(%rsp),%rax + lea offset(%rbp,%rax,1),%rdx + mov offset(%rsp),%rax + lea (%rax,%rbp,1),%r14 + mov offset(%rsp),%rax + lea offset(%rbp,%rax,1),%r13 + mov offset(%rsp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_outncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_outncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_outncopy_COOPERLAKE.o (objdump) @@ -2,45 +2,418 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_outncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e04c8b 6c243848 85f60f8e .H.t$.L.l$8H.... - 0030 b1010000 4889c849 0fafc149 89fe49d1 ....H..I...I..I. - 0040 fe4c01c0 4c8d24c2 4889c849 0fafc049 .L..L.$.H..I...I - 0050 89ca4989 ff4c01c8 488d2cc2 488d04cd ..I..L..H.,.H... - 0060 00000000 48894424 b04889f9 48894424 ....H.D$.H..H.D$ - 0070 b84b8d04 70488944 24c04883 e1fe4c89 .K..pH.D$.H...L. - 0080 f0498d34 714989cb 48c1e005 4c894c24 .I.4qI..H...L.L$ - 0090 f84c89cf 48894424 c849c1e2 044183e7 .L..H.D$.I...A.. - 00a0 014d01c3 4989f1eb 630f1f80 00000000 .M..I...c....... - 00b0 488b4424 b84c89e6 498d0c04 4c89c04d H.D$.L..I...L..M - 00c0 85f67f62 4d85ff74 2f498d55 104839c7 ...bM..t/I.U.H9. - 00d0 0f8fea00 0000c5fb 10060f8d 88010000 ................ - 00e0 c5fb104e 08c4c17b 114500c4 c17b114d ...N...{.E...{.M - 00f0 084989d5 0f1f4000 4883c702 4d01d448 .I....@.H...M..H - 0100 83c5104c 39cf0f84 cb000000 4c39c77d ...L9.......L9.} - 0110 9f488b44 24b04889 ee488d4c 05004c89 .H.D$.H..H.L..L. - 0120 c04d85f6 7e9e4c89 eaeb160f 1f440000 .M..~.L......D.. - 0130 4883c610 4883c110 4883c002 4939c374 H...H...H...I9.t - 0140 474883c2 204839c7 7fe6c5fb 1009c5fb GH.. H9......... - 0150 104108c5 fb10164a 8d1c164c 01d14839 .A.....J...L..H9 - 0160 c77d3dc5 fb105e08 4883c002 c5fb1152 .}=...^.H......R - 0170 e0c5fb11 5ae8c5fb 114af0c5 fb1142f8 ....Z....J....B. - 0180 4889de49 39c375b9 488b4424 c04c036c H..I9.u.H.D$.L.l - 0190 24c8e92d ffffff66 0f1f8400 00000000 $..-...f........ - 01a0 48c742e8 00000000 c5fb1152 e0c5fb11 H.B........R.... - 01b0 4af0c5fb 1142f848 89dee979 ffffff90 J....B.H...y.... - 01c0 4883c702 4989d54d 01d44883 c5104c39 H...I..M..H...L9 - 01d0 cf0f8535 ffffff4c 8b4c24f8 488b4424 ...5...L.L$.H.D$ - 01e0 e04d8d0c 41f64424 d001746a 488b4424 .M..A.D$..tjH.D$ - 01f0 d84d39c1 0f8d8600 0000490f afc0488b .M9.......I...H. - 0200 5c24f04c 01c8488d 04c3488b 5c24e848 \$.L..H...H.\$.H - 0210 85db7e42 488b4c24 d84c89c6 4c01c348 ..~BH.L$.L..L..H - 0220 f7de48c1 e1034889 da498d74 f500eb0c ..H...H..I.t.... - 0230 49ffc048 83c0084c 39c2741a 4d39c17f I..H...L9.t.M9.. - 0240 efc5fb10 004801c8 c4a17b11 04c649ff .....H....{...I. - 0250 c04c39c2 75e65b5d 415c415d 415e31c0 .L9.u.[]A\A]A^1. - 0260 415fc30f 1f440000 49c74508 00000000 A_...D..I.E..... - 0270 c4c17b11 45004989 d5e97afe ffff6690 ..{.E.I...z...f. - 0280 490fafc1 488b5c24 f04c01c0 488d04c3 I...H.\$.L..H... - 0290 e975ffff ff .u... + 0000 41574156 41554154 55534881 ec900100 AWAVAUATUSH..... + 0010 004889b4 24a80000 0048c1fe 034889bc .H..$....H...H.. + 0020 24c80000 00488994 24480100 0048898c $....H..$H...H.. + 0030 24d00000 004c8944 24884c89 8c249000 $....L.D$.L..$.. + 0040 00004889 b4247001 00004c8b ac24c801 ..H..$p...L..$.. + 0050 00004885 f60f8e4c 0f000048 89c8490f ..H....L...H..I. + 0060 afc04989 cf4d89fa 4c89cd49 c1e2054d ..I..M..L..I...M + 0070 0fafcf4d 89c44c89 94248001 00004c8d ...M..L..$....L. + 0080 04484d89 fa4989fb 49c1e204 498d3c08 .HM..I..I...I.<. + 0090 4d01e148 8d340f4c 8ba42448 0100004c M..H.4.L..$H...L + 00a0 89942488 0100004d 89da488d 0c0e4183 ..$....M..H...A. + 00b0 e2074a8d 14394829 c74c8954 24e04d89 ..J..9H).L.T$.M. + 00c0 fe4d89fa 4f8d3ccc 4c8d4c05 0048c1e7 .M..O.<.L.L..H.. + 00d0 034829c6 4f8d24cc 4989e948 8bac2470 .H).O.$.I..H..$p + 00e0 01000048 29c14889 bc240801 0000488d ...H).H..$....H. + 00f0 3cf50000 00004889 bc241801 0000498d <.....H..$....I. + 0100 2ce9488d 3ccd0000 00004889 d14829c1 ,.H.<.....H..H). + 0110 4889ac24 a0000000 4c01d24a 8d2cd500 H..$....L..J.,.. + 0120 00000048 29c24929 c04889bc 24200100 ...H).I).H..$ .. + 0130 004889e8 488d3ccd 00000000 4889bc24 .H..H.<.....H..$ + 0140 30010000 48f7d848 8d3cd500 00000049 0...H..H.<.....I + 0150 8d510149 0fafc148 0fafd548 89bc2440 .Q.I...H...H..$@ + 0160 0100004c 89db488d 3c02498d 5102480f ...L..H.<.I.Q.H. + 0170 afd54889 bc24e800 000048c1 fb03488d ..H..$....H...H. + 0180 0c02498d 5103480f afd54889 8c24f800 ..I.Q.H...H..$.. + 0190 00004889 9c249800 0000488d 3c02498d ..H..$....H.<.I. + 01a0 5104480f afd54889 bc240001 000049c1 Q.H...H..$....I. + 01b0 e606488d 0c02498d 5105480f afd54889 ..H...I.Q.H...H. + 01c0 8c241001 000049c1 e003488d 3c02498d .$....I...H.<.I. + 01d0 5106480f afd54889 bc24d800 00004889 Q.H...H..$....H. + 01e0 ac24f000 0000488d 0c02498d 5107480f .$....H...I.Q.H. + 01f0 afd56261 ff081154 24f74c89 8424e000 ..ba...T$.L..$.. + 0200 0000488d 3c024c89 d84883e0 f84889bc ..H.<.L..H...H.. + 0210 24380100 004889c7 488b4424 8848898c $8...H..H.D$.H.. + 0220 24280100 004801c7 488d04d8 48898424 $(...H..H...H..$ + 0230 68010000 4c89d848 c1e30983 e0064889 h...L..H......H. + 0240 9c246001 00004889 84247801 00004c89 .$`...H..$x...L. + 0250 db4c89d8 83e30483 e0024183 e3014889 .L........A...H. + 0260 9c24b000 00004c89 9c245801 00004889 .$....L..$X...H. + 0270 7c249048 89842450 01000062 61ff0811 |$.H..$P...ba... + 0280 5c24f862 61ff0811 6424f94c 89fd6261 \$.ba...d$.L..ba + 0290 ff08116c 24fa4d89 f362e1ff 08114c24 ...l$.M..b....L$ + 02a0 fd4c89cb 62a1ef00 10ca6201 8f0010d6 .L..b.....b..... + 02b0 62a1e700 10d36261 ff08117c 24fb62a1 b.....ba...|$.b. + 02c0 df0010dc c57b117c 24f062a1 d70010e5 .....{.|$.b..... + 02d0 62e1ff08 114424ff 62a1cf00 10ee4d89 b....D$.b.....M. + 02e0 ef62a1c7 0010f762 81bf0010 f86201b7 .b.....b.....b.. + 02f0 0010c1e9 dc000000 0f1f8400 00000000 ................ + 0300 488b8424 e8000000 4883bc24 98000000 H..$....H..$.... + 0310 00488d7c 0500488b 8424f800 00004989 .H.|..H..$....I. + 0320 ea488d74 0500488b 84240001 0000488d .H.t..H..$....H. + 0330 4c050048 8b842410 01000048 8d540500 L..H..$....H.T.. + 0340 488b8424 d8000000 4c8d3428 488b8424 H..$....L.4(H..$ + 0350 28010000 4c8d6c05 00488b84 24380100 (...L.l..H..$8.. + 0360 004c8d4c 0500488b 4424880f 8fd90000 .L.L..H.D$...... + 0370 0048837c 24e00074 424839c3 0f8ece08 .H.|$..tBH9..... + 0380 0000498d 87000100 004883bc 24b00000 ..I......H..$... + 0390 00004c0f 45f84883 bc245001 00000049 ..L.E.H..$P....I + 03a0 8d878000 00004c0f 45f84883 bc245801 ......L.E.H..$X. + 03b0 00000049 8d47404c 0f45f848 83c3084c ...I.G@L.E.H...L + 03c0 01dd4983 c4404839 9c24a000 00000f84 ..I..@H9.$...... + 03d0 ac0b0000 483b5c24 880f8d21 ffffff48 ....H;\$...!...H + 03e0 8b8424f0 00000048 83bc2498 00000000 ..$....H..$..... + 03f0 498d3c04 488b8424 e0000000 4d89e24a I.<.H..$....M..J + 0400 8d342048 8b842408 01000049 8d0c0448 .4 H..$....I...H + 0410 8b842418 01000049 8d140448 8b842420 ..$....I...H..$ + 0420 0100004d 8d340448 8b842430 0100004d ...M.4.H..$0...M + 0430 8d2c0448 8b842440 0100004d 8d0c0448 .,.H..$@...M...H + 0440 8b442488 0f8e27ff ffff4989 c04889ac .D$...'...I..H.. + 0450 24b80000 004c89a4 24c00000 004c89bc $....L..$....L.. + 0460 24c80100 00c5fb10 7c24c0c5 7b104424 $.......|$..{.D$ + 0470 b8c57b10 4c24c8c5 7b105424 d0c57b10 ..{.L$..{.T$..{. + 0480 6424d8c5 7b106c24 e8c57b10 7424f0c5 d$..{.l$..{.t$.. + 0490 7b107c24 f84c89f8 6211af00 10daeb2f {.|$.L..b....../ + 04a0 4983c008 4983c240 4883c740 4883c640 I...I..@H..@H..@ + 04b0 4883c140 4883c240 4983c640 4983c540 H..@H..@I..@I..@ + 04c0 4983c140 4c394424 900f84fc 04000048 I..@L9D$.......H + 04d0 05000200 004c39c3 7fc662c1 ff081045 .....L9...b....E + 04e0 036241ff 08104d04 6241ff08 105d05c4 .bA...M.bA...].. + 04f0 c17b1045 006241ff 08106506 4a8d2c1e .{.E.bA...e.J.,. + 0500 62e1ff08 114424f3 6261ff08 114c24f4 b....D$.ba...L$. + 0510 6261ff08 115c24f5 4f8d3c1a 4f8d241e ba...\$.O.<.O.$. + 0520 c4c17b10 32c5fb10 2fc5fb10 7f08c5fb ..{.2.../....... + 0530 1026c57b 104608c5 7b104e10 c5fb1019 .&.{.F..{.N..... + 0540 c57b1051 08c57b10 5910c57b 106118c5 .{.Q..{.Y..{.a.. + 0550 fb1012c5 7b106a08 c57b1072 10c57b10 ....{.j..{.r..{. + 0560 7a1862e1 ff08104a 04c4c17b 100e62c1 z.b....J...{..b. + 0570 ff081056 0162c1ff 08105e02 62c1ff08 ...V.b....^.b... + 0580 10660362 c1ff0810 6e0462c1 ff081076 .f.b....n.b....v + 0590 0562c1ff 08107d01 6241ff08 104502c5 .b....}.bA...E.. + 05a0 fb114424 c06261ff 08116424 f648896c ..D$.ba...d$.H.l + 05b0 24c84a8d 2c194c89 7c24d048 896c24b8 $.J.,.L.|$.H.l$. + 05c0 4c896424 d86241ff 08101962 41ff0810 L.d$.bA....bA... + 05d0 51016241 ff081049 0262c1ff 08104103 Q.bA...I.b....A. + 05e0 6241ff08 10790462 41ff0810 71056241 bA...y.bA...q.bA + 05f0 ff081069 066241ff 08106107 4e8d3c1f ...i.bA...a.N.<. + 0600 4a8d2c1a 4f8d641d 004d01d9 4c39c30f J.,.O.d..M..L9.. + 0610 8d1b0400 00c4c17b 104208c5 fb114424 .......{.B....D$ + 0620 e8c4c17b 104210c5 fb114424 f0c4c17b ...{.B....D$...{ + 0630 104218c5 fb114424 f8c4c17b 104220c5 .B....D$...{.B . + 0640 fb110424 c4c17b10 4228c5fb 11442408 ...$..{.B(...D$. + 0650 c4c17b10 42304d8b 5238c5fb 11442410 ..{.B0M.R8...D$. + 0660 c5fb1047 10c5fb11 442418c5 fb104718 ...G....D$....G. + 0670 c5fb1144 2420c5fb 104720c5 fb114424 ...D$ ...G ...D$ + 0680 28c5fb10 4728c5fb 11442430 c5fb1047 (...G(...D$0...G + 0690 30488b7f 38c5fb11 442438c5 fb104618 0H..8...D$8...F. + 06a0 c5fb1144 2440c5fb 104620c5 fb114424 ...D$@...F ...D$ + 06b0 48c5fb10 4628c5fb 11442450 c5fb1046 H...F(...D$P...F + 06c0 30c5fb11 44245848 8b7638c5 fb104120 0...D$XH.v8...A + 06d0 c5fb1144 2460c5fb 104128c5 fb114424 ...D$`...A(...D$ + 06e0 68c5fb10 4130488b 4938c5fb 11442470 h...A0H.I8...D$p + 06f0 c5fb1042 28c5fb11 442478c5 fb104230 ...B(...D$x...B0 + 0700 488b5238 c5fb1184 24800000 00c4c17b H.R8....$......{ + 0710 1046304d 8b7638c5 fb118424 88000000 .F0M.v8....$.... + 0720 c4c17b10 4538c5fb 11b000fe ffffc5fb ..{.E8.......... + 0730 1140b8c5 fb104424 e84c8990 38feffff .@....D$.L..8... + 0740 c5fb1180 08feffff c5fb1044 24f0c5fb ...........D$... + 0750 118010fe ffffc5fb 104424f8 c5fb1180 .........D$..... + 0760 18feffff c5fb1004 24c5fb11 8020feff ........$.... .. + 0770 ffc5fb10 442408c5 fb118028 feffffc5 ....D$.....(.... + 0780 fb104424 10c5fb11 8030feff ffc5fb11 ..D$.....0...... + 0790 a840feff ffc5fb10 442418c5 fb11a080 .@......D$...... + 07a0 feffffc5 fb118050 feffffc5 fb104424 .......P......D$ + 07b0 20c5fb11 98c0feff ffc5fb11 8058feff ............X.. + 07c0 ffc5fb10 44242848 89b878fe ffffc5fb ....D$(H..x..... + 07d0 118060fe ffffc5fb 10442430 4889b0b8 ..`......D$0H... + 07e0 feffffc5 fb118068 feffffc5 fb104424 .......h......D$ + 07f0 38c5fb11 b848feff ffc5fb11 8070feff 8....H.......p.. + 0800 ffc5fb10 442440c5 7b118088 feffffc5 ....D$@.{....... + 0810 fb118098 feffffc5 fb104424 48c57b11 ..........D$H.{. + 0820 8890feff ffc5fb11 80a0feff ffc5fb10 ................ + 0830 442450c5 7b1190c8 feffffc5 fb1180a8 D$P.{........... + 0840 feffffc5 fb104424 58c57b11 98d0feff ......D$X.{..... + 0850 ffc5fb11 80b0feff ffc5fb10 442460c5 ............D$`. + 0860 7b11a0d8 feffffc5 fb1180e0 feffffc5 {............... + 0870 fb104424 68c5fb11 80e8feff ffc5fb10 ..D$h........... + 0880 442470c5 fb106c24 c0c5fb11 80f0feff D$p...l$........ + 0890 ffc5fb10 442478c5 fb107424 98c5fb11 ....D$x...t$.... + 08a0 8028ffff ffc5fb10 84248000 0000c5fb .(.......$...... + 08b0 106424a0 c5fb1180 30ffffff c5fb1168 .d$.....0......h + 08c0 80c5fb10 84248800 0000c5fb 106c24a8 .....$.......l$. + 08d0 488988f8 feffff48 899038ff ffff4c89 H......H..8...L. + 08e0 b078ffff ffc5fb11 9000ffff ffc57b11 .x............{. + 08f0 a808ffff ffc57b11 b010ffff ffc57b11 ......{.......{. + 0900 b818ffff ff62e1ff 081148e4 c5fb1188 .....b....H..... + 0910 40ffffff 62e1ff08 1150e962 e1ff0811 @...b....P.b.... + 0920 58ea62e1 ff081160 eb62e1ff 081168ec X.b....`.b....h. + 0930 62e1ff08 1170edc5 fb118070 ffffff62 b....p.....p...b + 0940 e1ff0811 78f16261 ff081140 f2c5fb11 ....x.ba...@.... + 0950 7098c5fb 1160a0c5 fb1168a8 c5fb105c p....`....h....\ + 0960 24b0c5fb 1158b049 83c0084c 8b7424d8 $....X.I...L.t$. + 0970 488b4c24 b8488b74 24c84c8b 5424d062 H.L$.H.t$.L.T$.b ELF section: pipe command #0 failed with 1 for old//usr/lib64/libopenblas_openmp.a/dtrmm_outncopy_COOPERLAKE.o /usr/lib64/libopenblas_openmp.a/dtrmm_outncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_outncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_outncopy_SKYLAKEX.o (disasm) @@ -11,95 +11,839 @@ push %r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,-offset(%rsp) + mov %r9,offset(%rsp) + mov %rsi,offset(%rsp) mov offset(%rsp),%r13 test %rsi,%rsi jle mov %rcx,%rax - imul %r9,%rax - mov %rdi,%r14 - sar %r14 - add %r8,%rax - lea (%rdx,%rax,8),%r12 - mov %rcx,%rax imul %r8,%rax - mov %rcx,%r10 - mov %rdi,%r15 - add %r9,%rax - lea (%rdx,%rax,8),%rbp - lea offset(,%rcx,8),%rax - mov %rax,-offset(%rsp) - mov %rdi,%rcx - mov %rax,-offset(%rsp) - lea (%r8,%r14,2),%rax - mov %rax,-offset(%rsp) - and $something,%rcx - mov %r14,%rax - lea (%r9,%rsi,2),%rsi - mov %rcx,%r11 - shl $something,%rax - mov %r9,-offset(%rsp) - mov %r9,%rdi - mov %rax,-offset(%rsp) + mov %rcx,%r15 + mov %r15,%r10 + mov %r9,%rbp + shl $something,%r10 + imul %r15,%r9 + mov %r8,%r12 + mov %r10,offset(%rsp) + lea (%rax,%rcx,2),%r8 + mov %r15,%r10 + mov %rdi,%r11 shl $something,%r10 - and $something,%r15d - add %r8,%r11 - mov %rsi,%r9 + lea (%r8,%rcx,1),%rdi + add %r12,%r9 + lea (%rdi,%rcx,1),%rsi + mov offset(%rsp),%r12 + mov %r10,offset(%rsp) + mov %r11,%r10 + lea (%rsi,%rcx,1),%rcx + and $something,%r10d + lea (%rcx,%r15,1),%rdx + sub %rax,%rdi + mov %r10,-offset(%rsp) + mov %r15,%r14 + mov %r15,%r10 + lea (%r12,%r9,8),%r15 + lea offset(%rbp,%rax,1),%r9 + shl $something,%rdi + sub %rax,%rsi + lea (%r12,%r9,8),%r12 + mov %rbp,%r9 + mov offset(%rsp),%rbp + sub %rax,%rcx + mov %rdi,offset(%rsp) + lea offset(,%rsi,8),%rdi + mov %rdi,offset(%rsp) + lea (%r9,%rbp,8),%rbp + lea offset(,%rcx,8),%rdi + mov %rdx,%rcx + sub %rax,%rcx + mov %rbp,offset(%rsp) + add %r10,%rdx + lea offset(,%r10,8),%rbp + sub %rax,%rdx + sub %rax,%r8 + mov %rdi,offset(%rsp) + mov %rbp,%rax + lea offset(,%rcx,8),%rdi + mov %rdi,offset(%rsp) + neg %rax + lea offset(,%rdx,8),%rdi + lea offset(%r9),%rdx + imul %r9,%rax + imul %rbp,%rdx + mov %rdi,offset(%rsp) + mov %r11,%rbx + lea (%rdx,%rax,1),%rdi + lea offset(%r9),%rdx + imul %rbp,%rdx + mov %rdi,offset(%rsp) + sar $something,%rbx + lea (%rdx,%rax,1),%rcx + lea offset(%r9),%rdx + imul %rbp,%rdx + mov %rcx,offset(%rsp) + mov %rbx,offset(%rsp) + lea (%rdx,%rax,1),%rdi + lea offset(%r9),%rdx + imul %rbp,%rdx + mov %rdi,offset(%rsp) + shl $something,%r14 + lea (%rdx,%rax,1),%rcx + lea offset(%r9),%rdx + imul %rbp,%rdx + mov %rcx,offset(%rsp) + shl $something,%r8 + lea (%rdx,%rax,1),%rdi + lea offset(%r9),%rdx + imul %rbp,%rdx + mov %rdi,offset(%rsp) + mov %rbp,offset(%rsp) + lea (%rdx,%rax,1),%rcx + lea offset(%r9),%rdx + imul %rbp,%rdx + vmovsd %xmm26,-offset(%rsp) + mov %r8,offset(%rsp) + lea (%rdx,%rax,1),%rdi + mov %r11,%rax + and $something,%rax + mov %rdi,offset(%rsp) + mov %rax,%rdi + mov -offset(%rsp),%rax + mov %rcx,offset(%rsp) + add %rax,%rdi + lea (%rax,%rbx,8),%rax + mov %rax,offset(%rsp) + mov %r11,%rax + shl $something,%rbx + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + mov %r11,%rbx + mov %r11,%rax + and $something,%ebx + and $something,%eax + and $something,%r11d + mov %rbx,offset(%rsp) + mov %r11,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rax,offset(%rsp) + vmovsd %xmm27,-offset(%rsp) + vmovsd %xmm28,-offset(%rsp) + mov %r15,%rbp + vmovsd %xmm29,-offset(%rsp) + mov %r14,%r11 + vmovsd %xmm17,-offset(%rsp) + mov %r9,%rbx + vmovsd %xmm18,%xmm18,%xmm17 + vmovsd %xmm30,%xmm30,%xmm26 + vmovsd %xmm19,%xmm19,%xmm18 + vmovsd %xmm31,-offset(%rsp) + vmovsd %xmm20,%xmm20,%xmm19 + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm21,%xmm21,%xmm20 + vmovsd %xmm16,-offset(%rsp) + vmovsd %xmm22,%xmm22,%xmm21 + mov %r13,%r15 + vmovsd %xmm23,%xmm23,%xmm22 + vmovsd %xmm24,%xmm24,%xmm23 + vmovsd %xmm25,%xmm25,%xmm24 jmp - nopl offset(%rax) + nopl offset(%rax,%rax,1) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea offset(%rbp,%rax,1),%rdi + mov offset(%rsp),%rax + mov %rbp,%r10 + lea offset(%rbp,%rax,1),%rsi + mov offset(%rsp),%rax + lea offset(%rbp,%rax,1),%rcx + mov offset(%rsp),%rax + lea offset(%rbp,%rax,1),%rdx + mov offset(%rsp),%rax + lea (%rax,%rbp,1),%r14 + mov offset(%rsp),%rax + lea offset(%rbp,%rax,1),%r13 + mov offset(%rsp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_outncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_outncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_outncopy_SKYLAKEX.o (objdump) @@ -2,45 +2,418 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_outncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e04c8b 6c243848 85f60f8e .H.t$.L.l$8H.... - 0030 b1010000 4889c849 0fafc149 89fe49d1 ....H..I...I..I. - 0040 fe4c01c0 4c8d24c2 4889c849 0fafc049 .L..L.$.H..I...I - 0050 89ca4989 ff4c01c8 488d2cc2 488d04cd ..I..L..H.,.H... - 0060 00000000 48894424 b04889f9 48894424 ....H.D$.H..H.D$ - 0070 b84b8d04 70488944 24c04883 e1fe4c89 .K..pH.D$.H...L. - 0080 f0498d34 714989cb 48c1e005 4c894c24 .I.4qI..H...L.L$ - 0090 f84c89cf 48894424 c849c1e2 044183e7 .L..H.D$.I...A.. - 00a0 014d01c3 4989f1eb 630f1f80 00000000 .M..I...c....... - 00b0 488b4424 b84c89e6 498d0c04 4c89c04d H.D$.L..I...L..M - 00c0 85f67f62 4d85ff74 2f498d55 104839c7 ...bM..t/I.U.H9. - 00d0 0f8fea00 0000c5fb 10060f8d 88010000 ................ - 00e0 c5fb104e 08c4c17b 114500c4 c17b114d ...N...{.E...{.M - 00f0 084989d5 0f1f4000 4883c702 4d01d448 .I....@.H...M..H - 0100 83c5104c 39cf0f84 cb000000 4c39c77d ...L9.......L9.} - 0110 9f488b44 24b04889 ee488d4c 05004c89 .H.D$.H..H.L..L. - 0120 c04d85f6 7e9e4c89 eaeb160f 1f440000 .M..~.L......D.. - 0130 4883c610 4883c110 4883c002 4939c374 H...H...H...I9.t - 0140 474883c2 204839c7 7fe6c5fb 1009c5fb GH.. H9......... - 0150 104108c5 fb10164a 8d1c164c 01d14839 .A.....J...L..H9 - 0160 c77d3dc5 fb105e08 4883c002 c5fb1152 .}=...^.H......R - 0170 e0c5fb11 5ae8c5fb 114af0c5 fb1142f8 ....Z....J....B. - 0180 4889de49 39c375b9 488b4424 c04c036c H..I9.u.H.D$.L.l - 0190 24c8e92d ffffff66 0f1f8400 00000000 $..-...f........ - 01a0 48c742e8 00000000 c5fb1152 e0c5fb11 H.B........R.... - 01b0 4af0c5fb 1142f848 89dee979 ffffff90 J....B.H...y.... - 01c0 4883c702 4989d54d 01d44883 c5104c39 H...I..M..H...L9 - 01d0 cf0f8535 ffffff4c 8b4c24f8 488b4424 ...5...L.L$.H.D$ - 01e0 e04d8d0c 41f64424 d001746a 488b4424 .M..A.D$..tjH.D$ - 01f0 d84d39c1 0f8d8600 0000490f afc0488b .M9.......I...H. - 0200 5c24f04c 01c8488d 04c3488b 5c24e848 \$.L..H...H.\$.H - 0210 85db7e42 488b4c24 d84c89c6 4c01c348 ..~BH.L$.L..L..H - 0220 f7de48c1 e1034889 da498d74 f500eb0c ..H...H..I.t.... - 0230 49ffc048 83c0084c 39c2741a 4d39c17f I..H...L9.t.M9.. - 0240 efc5fb10 004801c8 c4a17b11 04c649ff .....H....{...I. - 0250 c04c39c2 75e65b5d 415c415d 415e31c0 .L9.u.[]A\A]A^1. - 0260 415fc30f 1f440000 49c74508 00000000 A_...D..I.E..... - 0270 c4c17b11 45004989 d5e97afe ffff6690 ..{.E.I...z...f. - 0280 490fafc1 488b5c24 f04c01c0 488d04c3 I...H.\$.L..H... - 0290 e975ffff ff .u... + 0000 41574156 41554154 55534881 ec900100 AWAVAUATUSH..... + 0010 004889b4 24a80000 0048c1fe 034889bc .H..$....H...H.. + 0020 24c80000 00488994 24480100 0048898c $....H..$H...H.. + 0030 24d00000 004c8944 24884c89 8c249000 $....L.D$.L..$.. + 0040 00004889 b4247001 00004c8b ac24c801 ..H..$p...L..$.. + 0050 00004885 f60f8e4c 0f000048 89c8490f ..H....L...H..I. + 0060 afc04989 cf4d89fa 4c89cd49 c1e2054d ..I..M..L..I...M + 0070 0fafcf4d 89c44c89 94248001 00004c8d ...M..L..$....L. + 0080 04484d89 fa4989fb 49c1e204 498d3c08 .HM..I..I...I.<. + 0090 4d01e148 8d340f4c 8ba42448 0100004c M..H.4.L..$H...L + 00a0 89942488 0100004d 89da488d 0c0e4183 ..$....M..H...A. + 00b0 e2074a8d 14394829 c74c8954 24e04d89 ..J..9H).L.T$.M. + 00c0 fe4d89fa 4f8d3ccc 4c8d4c05 0048c1e7 .M..O.<.L.L..H.. + 00d0 034829c6 4f8d24cc 4989e948 8bac2470 .H).O.$.I..H..$p + 00e0 01000048 29c14889 bc240801 0000488d ...H).H..$....H. + 00f0 3cf50000 00004889 bc241801 0000498d <.....H..$....I. + 0100 2ce9488d 3ccd0000 00004889 d14829c1 ,.H.<.....H..H). + 0110 4889ac24 a0000000 4c01d24a 8d2cd500 H..$....L..J.,.. + 0120 00000048 29c24929 c04889bc 24200100 ...H).I).H..$ .. + 0130 004889e8 488d3ccd 00000000 4889bc24 .H..H.<.....H..$ + 0140 30010000 48f7d848 8d3cd500 00000049 0...H..H.<.....I + 0150 8d510149 0fafc148 0fafd548 89bc2440 .Q.I...H...H..$@ + 0160 0100004c 89db488d 3c02498d 5102480f ...L..H.<.I.Q.H. + 0170 afd54889 bc24e800 000048c1 fb03488d ..H..$....H...H. + 0180 0c02498d 5103480f afd54889 8c24f800 ..I.Q.H...H..$.. + 0190 00004889 9c249800 0000488d 3c02498d ..H..$....H.<.I. + 01a0 5104480f afd54889 bc240001 000049c1 Q.H...H..$....I. + 01b0 e606488d 0c02498d 5105480f afd54889 ..H...I.Q.H...H. + 01c0 8c241001 000049c1 e003488d 3c02498d .$....I...H.<.I. + 01d0 5106480f afd54889 bc24d800 00004889 Q.H...H..$....H. + 01e0 ac24f000 0000488d 0c02498d 5107480f .$....H...I.Q.H. + 01f0 afd56261 ff081154 24f74c89 8424e000 ..ba...T$.L..$.. + 0200 0000488d 3c024c89 d84883e0 f84889bc ..H.<.L..H...H.. + 0210 24380100 004889c7 488b4424 8848898c $8...H..H.D$.H.. + 0220 24280100 004801c7 488d04d8 48898424 $(...H..H...H..$ + 0230 68010000 4c89d848 c1e30983 e0064889 h...L..H......H. + 0240 9c246001 00004889 84247801 00004c89 .$`...H..$x...L. + 0250 db4c89d8 83e30483 e0024183 e3014889 .L........A...H. + 0260 9c24b000 00004c89 9c245801 00004889 .$....L..$X...H. + 0270 7c249048 89842450 01000062 61ff0811 |$.H..$P...ba... + 0280 5c24f862 61ff0811 6424f94c 89fd6261 \$.ba...d$.L..ba + 0290 ff08116c 24fa4d89 f362e1ff 08114c24 ...l$.M..b....L$ + 02a0 fd4c89cb 62a1ef00 10ca6201 8f0010d6 .L..b.....b..... + 02b0 62a1e700 10d36261 ff08117c 24fb62a1 b.....ba...|$.b. + 02c0 df0010dc c57b117c 24f062a1 d70010e5 .....{.|$.b..... + 02d0 62e1ff08 114424ff 62a1cf00 10ee4d89 b....D$.b.....M. + 02e0 ef62a1c7 0010f762 81bf0010 f86201b7 .b.....b.....b.. + 02f0 0010c1e9 dc000000 0f1f8400 00000000 ................ + 0300 488b8424 e8000000 4883bc24 98000000 H..$....H..$.... + 0310 00488d7c 0500488b 8424f800 00004989 .H.|..H..$....I. + 0320 ea488d74 0500488b 84240001 0000488d .H.t..H..$....H. + 0330 4c050048 8b842410 01000048 8d540500 L..H..$....H.T.. + 0340 488b8424 d8000000 4c8d3428 488b8424 H..$....L.4(H..$ + 0350 28010000 4c8d6c05 00488b84 24380100 (...L.l..H..$8.. + 0360 004c8d4c 0500488b 4424880f 8fd90000 .L.L..H.D$...... + 0370 0048837c 24e00074 424839c3 0f8ece08 .H.|$..tBH9..... + 0380 0000498d 87000100 004883bc 24b00000 ..I......H..$... + 0390 00004c0f 45f84883 bc245001 00000049 ..L.E.H..$P....I + 03a0 8d878000 00004c0f 45f84883 bc245801 ......L.E.H..$X. + 03b0 00000049 8d47404c 0f45f848 83c3084c ...I.G@L.E.H...L + 03c0 01dd4983 c4404839 9c24a000 00000f84 ..I..@H9.$...... + 03d0 ac0b0000 483b5c24 880f8d21 ffffff48 ....H;\$...!...H + 03e0 8b8424f0 00000048 83bc2498 00000000 ..$....H..$..... + 03f0 498d3c04 488b8424 e0000000 4d89e24a I.<.H..$....M..J + 0400 8d342048 8b842408 01000049 8d0c0448 .4 H..$....I...H + 0410 8b842418 01000049 8d140448 8b842420 ..$....I...H..$ + 0420 0100004d 8d340448 8b842430 0100004d ...M.4.H..$0...M + 0430 8d2c0448 8b842440 0100004d 8d0c0448 .,.H..$@...M...H + 0440 8b442488 0f8e27ff ffff4989 c04889ac .D$...'...I..H.. + 0450 24b80000 004c89a4 24c00000 004c89bc $....L..$....L.. + 0460 24c80100 00c5fb10 7c24c0c5 7b104424 $.......|$..{.D$ + 0470 b8c57b10 4c24c8c5 7b105424 d0c57b10 ..{.L$..{.T$..{. + 0480 6424d8c5 7b106c24 e8c57b10 7424f0c5 d$..{.l$..{.t$.. + 0490 7b107c24 f84c89f8 6211af00 10daeb2f {.|$.L..b....../ + 04a0 4983c008 4983c240 4883c740 4883c640 I...I..@H..@H..@ + 04b0 4883c140 4883c240 4983c640 4983c540 H..@H..@I..@I..@ + 04c0 4983c140 4c394424 900f84fc 04000048 I..@L9D$.......H + 04d0 05000200 004c39c3 7fc662c1 ff081045 .....L9...b....E + 04e0 036241ff 08104d04 6241ff08 105d05c4 .bA...M.bA...].. + 04f0 c17b1045 006241ff 08106506 4a8d2c1e .{.E.bA...e.J.,. + 0500 62e1ff08 114424f3 6261ff08 114c24f4 b....D$.ba...L$. + 0510 6261ff08 115c24f5 4f8d3c1a 4f8d241e ba...\$.O.<.O.$. + 0520 c4c17b10 32c5fb10 2fc5fb10 7f08c5fb ..{.2.../....... + 0530 1026c57b 104608c5 7b104e10 c5fb1019 .&.{.F..{.N..... + 0540 c57b1051 08c57b10 5910c57b 106118c5 .{.Q..{.Y..{.a.. + 0550 fb1012c5 7b106a08 c57b1072 10c57b10 ....{.j..{.r..{. + 0560 7a1862e1 ff08104a 04c4c17b 100e62c1 z.b....J...{..b. + 0570 ff081056 0162c1ff 08105e02 62c1ff08 ...V.b....^.b... + 0580 10660362 c1ff0810 6e0462c1 ff081076 .f.b....n.b....v + 0590 0562c1ff 08107d01 6241ff08 104502c5 .b....}.bA...E.. + 05a0 fb114424 c06261ff 08116424 f648896c ..D$.ba...d$.H.l + 05b0 24c84a8d 2c194c89 7c24d048 896c24b8 $.J.,.L.|$.H.l$. + 05c0 4c896424 d86241ff 08101962 41ff0810 L.d$.bA....bA... + 05d0 51016241 ff081049 0262c1ff 08104103 Q.bA...I.b....A. + 05e0 6241ff08 10790462 41ff0810 71056241 bA...y.bA...q.bA + 05f0 ff081069 066241ff 08106107 4e8d3c1f ...i.bA...a.N.<. + 0600 4a8d2c1a 4f8d641d 004d01d9 4c39c30f J.,.O.d..M..L9.. + 0610 8d1b0400 00c4c17b 104208c5 fb114424 .......{.B....D$ + 0620 e8c4c17b 104210c5 fb114424 f0c4c17b ...{.B....D$...{ + 0630 104218c5 fb114424 f8c4c17b 104220c5 .B....D$...{.B . + 0640 fb110424 c4c17b10 4228c5fb 11442408 ...$..{.B(...D$. + 0650 c4c17b10 42304d8b 5238c5fb 11442410 ..{.B0M.R8...D$. + 0660 c5fb1047 10c5fb11 442418c5 fb104718 ...G....D$....G. + 0670 c5fb1144 2420c5fb 104720c5 fb114424 ...D$ ...G ...D$ + 0680 28c5fb10 4728c5fb 11442430 c5fb1047 (...G(...D$0...G + 0690 30488b7f 38c5fb11 442438c5 fb104618 0H..8...D$8...F. + 06a0 c5fb1144 2440c5fb 104620c5 fb114424 ...D$@...F ...D$ + 06b0 48c5fb10 4628c5fb 11442450 c5fb1046 H...F(...D$P...F + 06c0 30c5fb11 44245848 8b7638c5 fb104120 0...D$XH.v8...A + 06d0 c5fb1144 2460c5fb 104128c5 fb114424 ...D$`...A(...D$ + 06e0 68c5fb10 4130488b 4938c5fb 11442470 h...A0H.I8...D$p + 06f0 c5fb1042 28c5fb11 442478c5 fb104230 ...B(...D$x...B0 + 0700 488b5238 c5fb1184 24800000 00c4c17b H.R8....$......{ + 0710 1046304d 8b7638c5 fb118424 88000000 .F0M.v8....$.... + 0720 c4c17b10 4538c5fb 11b000fe ffffc5fb ..{.E8.......... + 0730 1140b8c5 fb104424 e84c8990 38feffff .@....D$.L..8... + 0740 c5fb1180 08feffff c5fb1044 24f0c5fb ...........D$... + 0750 118010fe ffffc5fb 104424f8 c5fb1180 .........D$..... + 0760 18feffff c5fb1004 24c5fb11 8020feff ........$.... .. + 0770 ffc5fb10 442408c5 fb118028 feffffc5 ....D$.....(.... + 0780 fb104424 10c5fb11 8030feff ffc5fb11 ..D$.....0...... + 0790 a840feff ffc5fb10 442418c5 fb11a080 .@......D$...... + 07a0 feffffc5 fb118050 feffffc5 fb104424 .......P......D$ + 07b0 20c5fb11 98c0feff ffc5fb11 8058feff ............X.. + 07c0 ffc5fb10 44242848 89b878fe ffffc5fb ....D$(H..x..... + 07d0 118060fe ffffc5fb 10442430 4889b0b8 ..`......D$0H... + 07e0 feffffc5 fb118068 feffffc5 fb104424 .......h......D$ + 07f0 38c5fb11 b848feff ffc5fb11 8070feff 8....H.......p.. + 0800 ffc5fb10 442440c5 7b118088 feffffc5 ....D$@.{....... + 0810 fb118098 feffffc5 fb104424 48c57b11 ..........D$H.{. + 0820 8890feff ffc5fb11 80a0feff ffc5fb10 ................ + 0830 442450c5 7b1190c8 feffffc5 fb1180a8 D$P.{........... + 0840 feffffc5 fb104424 58c57b11 98d0feff ......D$X.{..... + 0850 ffc5fb11 80b0feff ffc5fb10 442460c5 ............D$`. + 0860 7b11a0d8 feffffc5 fb1180e0 feffffc5 {............... + 0870 fb104424 68c5fb11 80e8feff ffc5fb10 ..D$h........... + 0880 442470c5 fb106c24 c0c5fb11 80f0feff D$p...l$........ + 0890 ffc5fb10 442478c5 fb107424 98c5fb11 ....D$x...t$.... + 08a0 8028ffff ffc5fb10 84248000 0000c5fb .(.......$...... + 08b0 106424a0 c5fb1180 30ffffff c5fb1168 .d$.....0......h + 08c0 80c5fb10 84248800 0000c5fb 106c24a8 .....$.......l$. + 08d0 488988f8 feffff48 899038ff ffff4c89 H......H..8...L. + 08e0 b078ffff ffc5fb11 9000ffff ffc57b11 .x............{. + 08f0 a808ffff ffc57b11 b010ffff ffc57b11 ......{.......{. + 0900 b818ffff ff62e1ff 081148e4 c5fb1188 .....b....H..... + 0910 40ffffff 62e1ff08 1150e962 e1ff0811 @...b....P.b.... + 0920 58ea62e1 ff081160 eb62e1ff 081168ec X.b....`.b....h. + 0930 62e1ff08 1170edc5 fb118070 ffffff62 b....p.....p...b + 0940 e1ff0811 78f16261 ff081140 f2c5fb11 ....x.ba...@.... + 0950 7098c5fb 1160a0c5 fb1168a8 c5fb105c p....`....h....\ + 0960 24b0c5fb 1158b049 83c0084c 8b7424d8 $....X.I...L.t$. + 0970 488b4c24 b8488b74 24c84c8b 5424d062 H.L$.H.t$.L.T$.b ELF section: pipe command #0 failed with 1 for old//usr/lib64/libopenblas_openmp.a/dtrmm_outncopy_SKYLAKEX.o /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_COOPERLAKE.o (disasm) @@ -11,95 +11,857 @@ push %r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,-offset(%rsp) + mov %r9,offset(%rsp) + mov %rsi,offset(%rsp) mov offset(%rsp),%r14 test %rsi,%rsi jle - mov %rcx,%rax - imul %r9,%rax - mov %rdi,%r15 - sar %r15 - add %r8,%rax - lea (%rdx,%rax,8),%r13 - mov %rcx,%rax - imul %r8,%rax - mov %rdi,%rbp - and $something,%rdi - add %r9,%rax - lea (%rdx,%rax,8),%r12 - lea (%r9,%rsi,2),%rax - mov %rax,-offset(%rsp) - lea offset(,%rcx,8),%rax - mov %rax,-offset(%rsp) - mov %rax,-offset(%rsp) - lea (%r8,%r15,2),%rax - mov %rax,-offset(%rsp) - mov %r15,%rax - mov %rcx,%r10 - mov %rdi,%r11 - shl $something,%rax - mov %rax,-offset(%rsp) - mov %r9,-offset(%rsp) - vmovsd offset(%rip),%xmm1 # - shl $something,%r10 - and $something,%ebp - add %r8,%r11 - mov %r9,%rsi + mov %r8,%rax + imul %rcx,%rax + mov %rcx,%rbp + mov %rbp,%r11 + shl $something,%r11 + mov %r8,%r12 + mov %r11,offset(%rsp) + lea (%rax,%rcx,2),%r8 + mov %rbp,%r11 + mov %rdi,%r10 + shl $something,%r11 + lea (%r8,%rcx,1),%rdi + mov %r9,%r13 + lea (%rdi,%rcx,1),%rsi + imul %rbp,%r9 + mov %r11,offset(%rsp) + mov %r10,%r11 + lea (%rsi,%rcx,1),%rcx + and $something,%r11d + lea (%rcx,%rbp,1),%rdx + mov %r11,-offset(%rsp) + mov %rbp,%r15 + mov %rbp,%r11 + mov offset(%rsp),%rbp + add %r12,%r9 + lea offset(%rbp,%r9,8),%r12 + mov %r13,%rbp + lea offset(%r13,%rax,1),%r9 + mov offset(%rsp),%r13 + sub %rax,%rdi + lea offset(%r13,%r9,8),%r13 + mov offset(%rsp),%r9 + sub %rax,%rsi + shl $something,%rdi + lea offset(%rbp,%r9,8),%r9 + sub %rax,%rcx + mov %r9,offset(%rsp) + mov %rdi,offset(%rsp) + mov %r11,%r9 + lea offset(,%rsi,8),%rdi + lea offset(,%r11,8),%r11 + mov %rdi,offset(%rsp) + lea offset(,%rcx,8),%rdi + mov %rdx,%rcx + add %r9,%rdx + sub %rax,%rcx + sub %rax,%rdx + sub %rax,%r8 + mov %r11,%rax + lea offset(,%rdx,8),%rsi + neg %rax + lea offset(%rbp),%rdx + imul %rbp,%rax + imul %r11,%rdx + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + lea offset(,%rcx,8),%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rcx,offset(%rsp) + mov %r10,%rbx + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + sar $something,%rbx + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rbx,offset(%rsp) + shl $something,%r15 + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + shl $something,%r8 + mov %r11,offset(%rsp) + lea (%rdx,%rax,1),%rdi + mov %r10,%rax + and $something,%rax + mov %rdi,offset(%rsp) + mov %rax,%rdi + mov -offset(%rsp),%rax + mov %r8,offset(%rsp) + add %rax,%rdi + lea (%rax,%rbx,8),%rax + mov %rax,offset(%rsp) + mov %r10,%rax + shl $something,%rbx + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + mov %r10,%rbx + mov %r10,%rax + and $something,%ebx + and $something,%eax + and $something,%r10d + mov %rbx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rax,offset(%rsp) + mov %r10,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + mov %r15,%rbx + vmovsd %xmm27,-offset(%rsp) + mov %r12,%r14 + vmovsd %xmm30,-offset(%rsp) + mov %r13,%r15 + vmovsd %xmm21,-offset(%rsp) + vmovsd %xmm22,(%rsp) + vmovsd %xmm23,%xmm23,%xmm21 + vmovsd %xmm24,%xmm24,%xmm22 + vmovsd %xmm25,%xmm25,%xmm23 + mov offset(%rsp),%r12 + vmovsd %xmm28,-offset(%rsp) + vmovsd %xmm29,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm16,-offset(%rsp) + vmovsd %xmm17,-offset(%rsp) + vmovsd %xmm18,-offset(%rsp) + vmovsd %xmm19,-offset(%rsp) + vmovsd %xmm20,-offset(%rsp) + vmovsd %xmm26,%xmm26,%xmm24 + vmovsd %xmm14,%xmm14,%xmm25 jmp - nop + nopw offset(%rax,%rax,1) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r14,1),%r8 + mov offset(%rsp),%rax + mov %r14,%r11 + lea (%r14,%rax,1),%rdi + mov offset(%rsp),%rax + lea (%rax,%r14,1),%rsi + mov offset(%rsp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_COOPERLAKE.o (objdump) @@ -2,46 +2,440 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e04c8b 74243848 85f60f8e .H.t$.L.t$8H.... - 0030 aa010000 4889c849 0fafc149 89ff49d1 ....H..I...I..I. - 0040 ff4c01c0 4c8d2cc2 4889c849 0fafc048 .L..L.,.H..I...H - 0050 89fd4883 e7fe4c01 c84c8d24 c2498d04 ..H...L..L.$.I.. - 0060 71488944 24a8488d 04cd0000 00004889 qH.D$.H.......H. - 0070 4424b848 894424b0 4b8d0478 48894424 D$.H.D$.K..xH.D$ - 0080 c04c89f8 4989ca49 89fb48c1 e0054889 .L..I..I..H...H. - 0090 4424c84c 894c24f8 c5fb100d 00000000 D$.L.L$......... - 00a0 49c1e204 83e5014d 01c34c89 ceeb5f90 I......M..L..._. - 00b0 488b4424 b04c89ef 4a8d0c28 4c89c04d H.D$.L..J..(L..M - 00c0 85ff7f63 4885ed74 2f498d56 104839c6 ...cH..t/I.V.H9. - 00d0 0f8ff200 00000f8d 94010000 c5fb1017 ................ - 00e0 c5fb1047 08c4c17b 1116c4c1 7b114608 ...G...{....{.F. - 00f0 4989d60f 1f440000 4883c602 4d01d549 I....D..H...M..I - 0100 83c41048 3b7424a8 0f84c200 00004c39 ...H;t$.......L9 - 0110 c67d9d48 8b4424b8 4c89e74a 8d0c204c .}.H.D$.L..J.. L - 0120 89c04d85 ff7e9d4c 89f2eb15 0f1f4000 ..M..~.L......@. - 0130 4883c710 4883c110 4883c002 4939c374 H...H...H...I9.t - 0140 484883c2 204839c6 7fe6c5fb 10014e8d HH.. H9.......N. - 0150 0c174a8d 1c117d48 c5fb1027 c5fb105f ..J...}H...'..._ - 0160 08c5fb10 51084883 c002c5fb 1162e0c5 ....Q.H......b.. - 0170 fb115ae8 c5fb1142 f0c5fb11 52f84889 ..Z....B....R.H. - 0180 d94c89cf 4939c375 b8488b44 24c04c03 .L..I9.u.H.D$.L. - 0190 7424c8e9 2cffffff 0f1f8400 00000000 t$..,........... - 01a0 48c742e8 00000000 c5fb114a e0c5fb11 H.B........J.... - 01b0 42f0c5fb 114af848 89d94c89 cfe976ff B....J.H..L...v. - 01c0 ffff660f 1f440000 4989d6e9 28ffffff ..f..D..I...(... - 01d0 4c8b4c24 f8488b44 24e04d8d 0c41f644 L.L$.H.D$.M..A.D - 01e0 24d00174 77488b44 24d84d39 c10f8d95 $..twH.D$.M9.... - 01f0 00000049 0fafc048 8b5c24f0 4c01c848 ...I...H.\$.L..H - 0200 8d14c348 8b4424e8 4885c07e 4f488b4c ...H.D$.H..~OH.L - 0210 24d84c89 c648f7de c5fb100d 00000000 $.L..H.......... - 0220 48c1e103 4c01c049 8d3cf6eb 0f0f1f00 H...L..I.<...... - 0230 4883c208 49ffc04c 39c07420 4d39c17f H...I..L9.t M9.. - 0240 ef488d34 0a7d59c5 fb100248 89f2c4a1 .H.4.}Y....H.... - 0250 7b1104c7 49ffc04c 39c075e0 5b5d415c {...I..L9.u.[]A\ - 0260 415d415e 31c0415f c30f1f80 00000000 A]A^1.A_........ - 0270 49c74608 00000000 c4c17b11 0e4989d6 I.F.......{..I.. - 0280 e973feff ff0f1f00 490fafc1 488b5c24 .s......I...H.\$ - 0290 f04c01c0 488d14c3 e966ffff ff0f1f00 .L..H....f...... - 02a0 c4a17b11 0cc74889 f2eb89 ..{...H.... + 0000 41574156 41554154 55534881 ec980100 AWAVAUATUSH..... + 0010 004889b4 24b00000 0048c1fe 034889bc .H..$....H...H.. + 0020 24d80000 00488994 24d00000 0048898c $....H..$....H.. + 0030 24e00000 004c8944 24904c89 8c249800 $....L.D$.L..$.. + 0040 00004889 b4247801 00004c8b b424d001 ..H..$x...L..$.. + 0050 00004885 f60f8e94 1000004c 89c0480f ..H........L..H. + 0060 afc14889 cd4989eb 49c1e305 4d89c44c ..H..I..I...M..L + 0070 899c2488 0100004c 8d044849 89eb4989 ..$....L..HI..I. + 0080 fa49c1e3 04498d3c 084d89cd 488d340f .I...I.<.M..H.4. + 0090 4c0fafcd 4c899c24 90010000 4d89d348 L...L..$....M..H + 00a0 8d0c0e41 83e30748 8d14294c 895c24d0 ...A...H..)L.\$. + 00b0 4989ef49 89eb488b ac24d000 00004d01 I..I..H..$....M. + 00c0 e14e8d64 cd004c89 ed4d8d4c 05004c8b .N.d..L..M.L..L. + 00d0 ac24d000 00004829 c74f8d6c cd004c8b .$....H).O.l..L. + 00e0 8c247801 00004829 c648c1e7 034e8d4c .$x...H).H...N.L + 00f0 cd004829 c14c898c 24a80000 004889bc ..H).L..$....H.. + 0100 24080100 004d89d9 488d3cf5 00000000 $....M..H.<..... + 0110 4e8d1cdd 00000000 4889bc24 48010000 N.......H..$H... + 0120 488d3ccd 00000000 4889d14c 01ca4829 H.<.....H..L..H) + 0130 c14829c2 4929c04c 89d8488d 34d50000 .H).I).L..H.4... + 0140 000048f7 d8488d55 01480faf c5490faf ..H..H.U.H...I.. + 0150 d34889b4 24280100 004889bc 24300100 .H..$(...H..$0.. + 0160 00488d34 02488d55 02490faf d34889b4 .H.4.H.U.I...H.. + 0170 24e80000 00488d3c cd000000 00488d34 $....H.<.....H.4 + 0180 02488d55 03490faf d34889b4 24f80000 .H.U.I...H..$... + 0190 004889bc 24380100 00488d0c 02488d55 .H..$8...H...H.U + 01a0 04490faf d348898c 24f00000 004c89d3 .I...H..$....L.. + 01b0 488d3402 488d5505 490fafd3 4889b424 H.4.H.U.I...H..$ + 01c0 10010000 48c1fb03 488d0c02 488d5506 ....H...H...H.U. + 01d0 490fafd3 48899c24 a0000000 49c1e706 I...H..$....I... + 01e0 488d3402 488d5507 490fafd3 49c1e003 H.4.H.U.I...I... + 01f0 4c899c24 20010000 488d3c02 4c89d048 L..$ ...H.<.L..H + 0200 83e0f848 89bc2450 01000048 89c7488b ...H..$P...H..H. + 0210 4424904c 89842400 01000048 01c7488d D$.L..$....H..H. + 0220 04d84889 84246801 00004c89 d048c1e3 ..H..$h...L..H.. + 0230 0983e006 48899c24 70010000 48898424 ....H..$p...H..$ + 0240 80010000 4c89d34c 89d083e3 0483e002 ....L..L........ + 0250 4183e201 48899c24 b8000000 48898c24 A...H..$....H..$ + 0260 18010000 4889b424 40010000 48897c24 ....H..$@...H.|$ + 0270 98488984 24580100 004c8994 24600100 .H..$X...L..$`.. + 0280 00c5fb10 05000000 004c89fb 6261ff08 .........L..ba.. + 0290 115c24f9 4d89e662 61ff0811 7424fb4d .\$.M..ba...t$.M + 02a0 89ef62e1 ff08116c 24ff62e1 ff081134 ..b....l$.b....4 + 02b0 2462a1c7 0010ef62 81bf0010 f06281b7 $b.....b.....b.. + 02c0 0010f94c 8ba424d0 01000062 61ff0811 ...L..$....ba... + 02d0 6424f462 61ff0811 6c24fcc5 7b117c24 d$.ba...l$..{.|$ + 02e0 a862e1ff 08114424 f662e1ff 08114c24 .b....D$.b....L$ + 02f0 f762e1ff 08115424 f862e1ff 08115c24 .b....T$.b....\$ + 0300 fd62e1ff 08116424 fe6201af 0010c262 .b....d$.b.....b + 0310 418f0810 cee9d700 0000660f 1f440000 A.........f..D.. + 0320 488b8424 e8000000 4883bc24 a0000000 H..$....H..$.... + 0330 004e8d04 30488b84 24f80000 004d89f3 .N..0H..$....M.. + 0340 498d3c06 488b8424 f0000000 4a8d3430 I.<.H..$....J.40 + 0350 488b8424 10010000 498d0c06 488b8424 H..$....I...H..$ + 0360 18010000 498d1406 488b8424 40010000 ....I...H..$@... + 0370 4d8d2c06 488b8424 50010000 4d8d1406 M.,.H..$P...M... + 0380 488b4424 900f8fdc 00000048 837c24d0 H.D$.......H.|$. + 0390 00744548 39c50f8e 94090000 498d8424 .tEH9.......I..$ + 03a0 00010000 4883bc24 b8000000 004c0f45 ....H..$.....L.E + 03b0 e04883bc 24580100 0000498d 84248000 .H..$X....I..$.. + 03c0 00004c0f 45e04883 bc246001 00000049 ..L.E.H..$`....I + 03d0 8d442440 4c0f45e0 4883c508 4901de49 .D$@L.E.H...I..I + 03e0 83c74048 39ac24a8 0000000f 84bf0c00 ..@H9.$......... + 03f0 00483b6c 24900f8d 24ffffff 488b8424 .H;l$...$...H..$ + 0400 20010000 4883bc24 a0000000 004d8d04 ...H..$.....M.. + 0410 07488b84 24000100 004d89fb 498d3c07 .H..$....M..I.<. + 0420 488b8424 08010000 498d3407 488b8424 H..$....I.4.H..$ + 0430 48010000 498d0c07 488b8424 30010000 H...I...H..$0... + 0440 498d1407 488b8424 38010000 4d8d2c07 I...H..$8...M.,. + 0450 488b8424 28010000 4d8d1407 488b4424 H..$(...M...H.D$ + 0460 900f8e24 ffffff49 89c14c89 5c24884c ...$...I..L.\$.L + 0470 89b424c0 0000004c 89bc24c8 0000004c ..$....L..$....L + 0480 89a424d0 010000c5 fb107424 a0c57b10 ..$.......t$..{. + 0490 4424a8c5 7b104c24 b0c57b10 5424b8c5 D$..{.L$..{.T$.. + 04a0 7b105c24 c0c57b10 6424e8c5 7b106c24 {.\$..{.d$..{.l$ + 04b0 f0c57b10 7424f8c5 7b103c24 4c89e062 ..{.t$..{.<$L..b + 04c0 91870010 ffeb3a66 0f1f8400 00000000 ......:f........ + 04d0 4983c108 48834424 88404983 c0404883 I...H.D$.@I..@H. + 04e0 c7404883 c6404883 c1404883 c2404983 .@H..@H..@H..@I. + 04f0 c5404983 c2404c39 4c24980f 84740500 .@I..@L9L$...t.. + 0500 00480500 0200004c 39cd7fc4 4c8b5c24 .H.....L9...L.\$ + 0510 88c4c17b 10284d8d 241b4c8d 1c1e4c89 ...{.(M.$.L...L. + 0520 5c24b84c 8d1c194c 895c24a0 4c8d1c1a \$.L...L.\$.L... + 0530 4c895c24 c04d8d5c 1d00c5fb 1027c5fb L.\$.M.\.....'.. + 0540 107708c5 fb101ec5 fb107e08 c57b1046 .w........~..{.F + 0550 10c5fb10 11c57b10 4908c57b 105110c5 ......{.I..{.Q.. + 0560 7b105918 c5fb100a c57b1062 08c57b10 {.Y......{.b..{. + 0570 6a10c57b 107218c5 7b107a20 6241ff08 j..{.r..{.z bA.. + 0580 10650062 c1ff0810 6d0162c1 ff081075 .e.b....m.b....u + 0590 0262c1ff 08107d03 6241ff08 10450462 .b....}.bA...E.b + 05a0 41ff0810 4d056241 ff08101a 6241ff08 A...M.bA....bA.. + 05b0 10520162 c1ff0810 620262c1 ff08105a .R.b....b.b....Z + 05c0 0362c1ff 08105204 62c1ff08 104a0562 .b....R.b....J.b + 05d0 c1ff0810 42064c89 5c24b04d 8d1c1a4c ....B.L.\$.M...L + 05e0 895c24a8 4d8d3418 4c8d3c1f 0f8df604 .\$.M.4.L.<..... + 05f0 00004c8b 5c248862 41ff0810 3b6241ff ..L.\$.bA...;bA. + 0600 08106b02 6261ff08 117c24f9 6241ff08 ..k.ba...|$.bA.. + 0610 107b0562 41ff0810 73016261 ff08113c .{.bA...s.ba...< + 0620 246241ff 08107803 6261ff08 116c24fd $bA...x.ba...l$. + 0630 6261ff08 117c2401 6241ff08 10780462 ba...|$.bA...x.b + 0640 41ff0810 6b046261 ff08117c 24026241 A...k.ba...|$.bA + 0650 ff081078 056261ff 08117424 f16261ff ...x.ba...t$.ba. + 0660 08117c24 036241ff 08107806 6241ff08 ..|$.bA...x.bA.. + 0670 10730362 61ff0811 7c240462 61ff0810 .s.ba...|$.ba... + 0680 7f026261 ff08116c 24ff6261 ff08117c ..ba...l$.ba...| + 0690 24fc6261 ff08107f 036241ff 08106801 $.ba.....bA...h. + 06a0 6261ff08 117c2405 6261ff08 107f0462 ba...|$.ba.....b + 06b0 61ff0811 7424fe62 61ff0811 6c24fb62 a...t$.ba...l$.b + 06c0 41ff0810 73066241 ff081068 024d8b5b A...s.bA...h.M.[ + 06d0 384d8b40 386261ff 08117c24 066261ff 8M.@8ba...|$.ba. + 06e0 08107f05 6261ff08 117c2407 6261ff08 ....ba...|$.ba.. + 06f0 107f0648 8b7f3862 61ff0811 7c240862 ...H..8ba...|$.b + 0700 61ff0810 7e036261 ff08117c 24096261 a...~.ba...|$.ba + 0710 ff08107e 046261ff 08117c24 0a6261ff ...~.ba...|$.ba. + 0720 08107e05 6261ff08 117c240b 6261ff08 ..~.ba...|$.ba.. + 0730 107e0648 8b763862 61ff0811 7c240c62 .~.H.v8ba...|$.b + 0740 61ff0810 79046261 ff08117c 240d6261 a...y.ba...|$.ba + 0750 ff081079 056261ff 08117c24 0e6261ff ...y.ba...|$.ba. + 0760 08107906 488b4938 6261ff08 117c240f ..y.H.I8ba...|$. + 0770 6261ff08 107a0562 61ff0811 7c241062 ba...z.ba...|$.b + 0780 61ff0810 7a06488b 52386261 ff08117c a...z.H.R8ba...| + 0790 24116241 ff08107d 064d8b6d 386261ff $.bA...}.M.m8ba. + 07a0 08117c24 126241ff 08107a07 6261ff08 ..|$.bA...z.ba.. + 07b0 1178ff62 61ff0810 7c24f962 61ff0811 .x.ba...|$.ba... + 07c0 78c06261 ff08107c 24f1c5fb 11a840fe x.ba...|$.....@. + 07d0 ffff6261 ff081178 c16261ff 08107c24 ..ba...x.ba...|$ + 07e0 fdc5fb10 6c24d862 61ff0811 78c26261 ....l$.ba...x.ba + 07f0 ff08107c 24fec5fb 11a848fe ffff6261 ...|$.....H...ba + 0800 ff081178 c36261ff 08107c24 ffc5fb10 ...x.ba...|$.... + 0810 6c240862 61ff0811 78c46261 ff08103c l$.ba...x.ba...< + 0820 24c5fb11 a858feff ff6261ff 081178c5 $....X...ba...x. + 0830 c5fb106c 24106261 ff08107c 24fcc5fb ...l$.ba...|$... + 0840 11a860fe ffff6261 ff081178 d2c5fb10 ..`...ba...x.... + 0850 6c241862 61ff0810 7c2405c5 fb11a868 l$.ba...|$.....h + 0860 feffff62 61ff0811 78d3c5fb 106c2420 ...ba...x....l$ + 0870 6261ff08 107c2406 4c899838 feffff4c ba...|$.L..8...L + 0880 898078fe ffff6261 ff081170 c66261ff ..x...ba...p.ba. + 0890 081168ca c5fb11a8 70feffff c5fb11a0 ..h.....p....... + 08a0 80feffff c5fb11b0 88feffff 6261ff08 ............ba.. + 08b0 1178d462 61ff0810 7c240748 89b8b8fe .x.ba...|$.H.... + 08c0 ffff6261 ff081178 d56261ff 08107c24 ..ba...x.ba...|$ + 08d0 084889b0 f8feffff 6261ff08 1178d662 .H......ba...x.b + 08e0 61ff0810 7c240948 898838ff ffff6261 a...|$.H..8...ba + 08f0 ff081178 db6261ff 08107c24 0ac5fb11 ...x.ba...|$.... + 0900 98c0feff ff6261ff 081178dc 6261ff08 .....ba...x.ba.. + 0910 107c240b c5fb11b8 c8feffff 6261ff08 .|$.........ba.. + 0920 1178dd62 61ff0810 7c240cc5 7b1180d0 .x.ba...|$..{... + 0930 feffff62 61ff0811 78de6261 ff08107c ...ba...x.ba...| + 0940 240dc5fb 119000ff ffff6261 ff081178 $.........ba...x + 0950 e46261ff 08107c24 0ec57b11 8808ffff .ba...|$..{..... + 0960 ff6261ff 081178e5 6261ff08 107c240f .ba...x.ba...|$. /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 ab020000 00420e10 8f02420e .........B....B. + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 441b0000 00420e10 8f02420e ....D....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830703 53020a0e 30410e28 ..A.8...S...0A.( - 0050 420e2042 0e18420e 10440e08 480b0000 B. B..B..D..H... + 0040 8606410e 38830747 0ed00303 8d150a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_SKYLAKEX.o (disasm) @@ -11,95 +11,857 @@ push %r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,-offset(%rsp) + mov %r9,offset(%rsp) + mov %rsi,offset(%rsp) mov offset(%rsp),%r14 test %rsi,%rsi jle - mov %rcx,%rax - imul %r9,%rax - mov %rdi,%r15 - sar %r15 - add %r8,%rax - lea (%rdx,%rax,8),%r13 - mov %rcx,%rax - imul %r8,%rax - mov %rdi,%rbp - and $something,%rdi - add %r9,%rax - lea (%rdx,%rax,8),%r12 - lea (%r9,%rsi,2),%rax - mov %rax,-offset(%rsp) - lea offset(,%rcx,8),%rax - mov %rax,-offset(%rsp) - mov %rax,-offset(%rsp) - lea (%r8,%r15,2),%rax - mov %rax,-offset(%rsp) - mov %r15,%rax - mov %rcx,%r10 - mov %rdi,%r11 - shl $something,%rax - mov %rax,-offset(%rsp) - mov %r9,-offset(%rsp) - vmovsd offset(%rip),%xmm1 # - shl $something,%r10 - and $something,%ebp - add %r8,%r11 - mov %r9,%rsi + mov %r8,%rax + imul %rcx,%rax + mov %rcx,%rbp + mov %rbp,%r11 + shl $something,%r11 + mov %r8,%r12 + mov %r11,offset(%rsp) + lea (%rax,%rcx,2),%r8 + mov %rbp,%r11 + mov %rdi,%r10 + shl $something,%r11 + lea (%r8,%rcx,1),%rdi + mov %r9,%r13 + lea (%rdi,%rcx,1),%rsi + imul %rbp,%r9 + mov %r11,offset(%rsp) + mov %r10,%r11 + lea (%rsi,%rcx,1),%rcx + and $something,%r11d + lea (%rcx,%rbp,1),%rdx + mov %r11,-offset(%rsp) + mov %rbp,%r15 + mov %rbp,%r11 + mov offset(%rsp),%rbp + add %r12,%r9 + lea offset(%rbp,%r9,8),%r12 + mov %r13,%rbp + lea offset(%r13,%rax,1),%r9 + mov offset(%rsp),%r13 + sub %rax,%rdi + lea offset(%r13,%r9,8),%r13 + mov offset(%rsp),%r9 + sub %rax,%rsi + shl $something,%rdi + lea offset(%rbp,%r9,8),%r9 + sub %rax,%rcx + mov %r9,offset(%rsp) + mov %rdi,offset(%rsp) + mov %r11,%r9 + lea offset(,%rsi,8),%rdi + lea offset(,%r11,8),%r11 + mov %rdi,offset(%rsp) + lea offset(,%rcx,8),%rdi + mov %rdx,%rcx + add %r9,%rdx + sub %rax,%rcx + sub %rax,%rdx + sub %rax,%r8 + mov %r11,%rax + lea offset(,%rdx,8),%rsi + neg %rax + lea offset(%rbp),%rdx + imul %rbp,%rax + imul %r11,%rdx + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + lea offset(,%rcx,8),%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rcx,offset(%rsp) + mov %r10,%rbx + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + sar $something,%rbx + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rbx,offset(%rsp) + shl $something,%r15 + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + shl $something,%r8 + mov %r11,offset(%rsp) + lea (%rdx,%rax,1),%rdi + mov %r10,%rax + and $something,%rax + mov %rdi,offset(%rsp) + mov %rax,%rdi + mov -offset(%rsp),%rax + mov %r8,offset(%rsp) + add %rax,%rdi + lea (%rax,%rbx,8),%rax + mov %rax,offset(%rsp) + mov %r10,%rax + shl $something,%rbx + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + mov %r10,%rbx + mov %r10,%rax + and $something,%ebx + and $something,%eax + and $something,%r10d + mov %rbx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rax,offset(%rsp) + mov %r10,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + mov %r15,%rbx + vmovsd %xmm27,-offset(%rsp) + mov %r12,%r14 + vmovsd %xmm30,-offset(%rsp) + mov %r13,%r15 + vmovsd %xmm21,-offset(%rsp) + vmovsd %xmm22,(%rsp) + vmovsd %xmm23,%xmm23,%xmm21 + vmovsd %xmm24,%xmm24,%xmm22 + vmovsd %xmm25,%xmm25,%xmm23 + mov offset(%rsp),%r12 + vmovsd %xmm28,-offset(%rsp) + vmovsd %xmm29,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm16,-offset(%rsp) + vmovsd %xmm17,-offset(%rsp) + vmovsd %xmm18,-offset(%rsp) + vmovsd %xmm19,-offset(%rsp) + vmovsd %xmm20,-offset(%rsp) + vmovsd %xmm26,%xmm26,%xmm24 + vmovsd %xmm14,%xmm14,%xmm25 jmp - nop + nopw offset(%rax,%rax,1) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r14,1),%r8 + mov offset(%rsp),%rax + mov %r14,%r11 + lea (%r14,%rax,1),%rdi + mov offset(%rsp),%rax + lea (%rax,%r14,1),%rsi + mov offset(%rsp),%rax /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_SKYLAKEX.o (objdump) @@ -2,46 +2,440 @@ /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424d048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24e848 895424f0 48894c24 ..H.|$.H.T$.H.L$ - 0020 d8488974 24e04c8b 74243848 85f60f8e .H.t$.L.t$8H.... - 0030 aa010000 4889c849 0fafc149 89ff49d1 ....H..I...I..I. - 0040 ff4c01c0 4c8d2cc2 4889c849 0fafc048 .L..L.,.H..I...H - 0050 89fd4883 e7fe4c01 c84c8d24 c2498d04 ..H...L..L.$.I.. - 0060 71488944 24a8488d 04cd0000 00004889 qH.D$.H.......H. - 0070 4424b848 894424b0 4b8d0478 48894424 D$.H.D$.K..xH.D$ - 0080 c04c89f8 4989ca49 89fb48c1 e0054889 .L..I..I..H...H. - 0090 4424c84c 894c24f8 c5fb100d 00000000 D$.L.L$......... - 00a0 49c1e204 83e5014d 01c34c89 ceeb5f90 I......M..L..._. - 00b0 488b4424 b04c89ef 4a8d0c28 4c89c04d H.D$.L..J..(L..M - 00c0 85ff7f63 4885ed74 2f498d56 104839c6 ...cH..t/I.V.H9. - 00d0 0f8ff200 00000f8d 94010000 c5fb1017 ................ - 00e0 c5fb1047 08c4c17b 1116c4c1 7b114608 ...G...{....{.F. - 00f0 4989d60f 1f440000 4883c602 4d01d549 I....D..H...M..I - 0100 83c41048 3b7424a8 0f84c200 00004c39 ...H;t$.......L9 - 0110 c67d9d48 8b4424b8 4c89e74a 8d0c204c .}.H.D$.L..J.. L - 0120 89c04d85 ff7e9d4c 89f2eb15 0f1f4000 ..M..~.L......@. - 0130 4883c710 4883c110 4883c002 4939c374 H...H...H...I9.t - 0140 484883c2 204839c6 7fe6c5fb 10014e8d HH.. H9.......N. - 0150 0c174a8d 1c117d48 c5fb1027 c5fb105f ..J...}H...'..._ - 0160 08c5fb10 51084883 c002c5fb 1162e0c5 ....Q.H......b.. - 0170 fb115ae8 c5fb1142 f0c5fb11 52f84889 ..Z....B....R.H. - 0180 d94c89cf 4939c375 b8488b44 24c04c03 .L..I9.u.H.D$.L. - 0190 7424c8e9 2cffffff 0f1f8400 00000000 t$..,........... - 01a0 48c742e8 00000000 c5fb114a e0c5fb11 H.B........J.... - 01b0 42f0c5fb 114af848 89d94c89 cfe976ff B....J.H..L...v. - 01c0 ffff660f 1f440000 4989d6e9 28ffffff ..f..D..I...(... - 01d0 4c8b4c24 f8488b44 24e04d8d 0c41f644 L.L$.H.D$.M..A.D - 01e0 24d00174 77488b44 24d84d39 c10f8d95 $..twH.D$.M9.... - 01f0 00000049 0fafc048 8b5c24f0 4c01c848 ...I...H.\$.L..H - 0200 8d14c348 8b4424e8 4885c07e 4f488b4c ...H.D$.H..~OH.L - 0210 24d84c89 c648f7de c5fb100d 00000000 $.L..H.......... - 0220 48c1e103 4c01c049 8d3cf6eb 0f0f1f00 H...L..I.<...... - 0230 4883c208 49ffc04c 39c07420 4d39c17f H...I..L9.t M9.. - 0240 ef488d34 0a7d59c5 fb100248 89f2c4a1 .H.4.}Y....H.... - 0250 7b1104c7 49ffc04c 39c075e0 5b5d415c {...I..L9.u.[]A\ - 0260 415d415e 31c0415f c30f1f80 00000000 A]A^1.A_........ - 0270 49c74608 00000000 c4c17b11 0e4989d6 I.F.......{..I.. - 0280 e973feff ff0f1f00 490fafc1 488b5c24 .s......I...H.\$ - 0290 f04c01c0 488d14c3 e966ffff ff0f1f00 .L..H....f...... - 02a0 c4a17b11 0cc74889 f2eb89 ..{...H.... + 0000 41574156 41554154 55534881 ec980100 AWAVAUATUSH..... + 0010 004889b4 24b00000 0048c1fe 034889bc .H..$....H...H.. + 0020 24d80000 00488994 24d00000 0048898c $....H..$....H.. + 0030 24e00000 004c8944 24904c89 8c249800 $....L.D$.L..$.. + 0040 00004889 b4247801 00004c8b b424d001 ..H..$x...L..$.. + 0050 00004885 f60f8e94 1000004c 89c0480f ..H........L..H. + 0060 afc14889 cd4989eb 49c1e305 4d89c44c ..H..I..I...M..L + 0070 899c2488 0100004c 8d044849 89eb4989 ..$....L..HI..I. + 0080 fa49c1e3 04498d3c 084d89cd 488d340f .I...I.<.M..H.4. + 0090 4c0fafcd 4c899c24 90010000 4d89d348 L...L..$....M..H + 00a0 8d0c0e41 83e30748 8d14294c 895c24d0 ...A...H..)L.\$. + 00b0 4989ef49 89eb488b ac24d000 00004d01 I..I..H..$....M. + 00c0 e14e8d64 cd004c89 ed4d8d4c 05004c8b .N.d..L..M.L..L. + 00d0 ac24d000 00004829 c74f8d6c cd004c8b .$....H).O.l..L. + 00e0 8c247801 00004829 c648c1e7 034e8d4c .$x...H).H...N.L + 00f0 cd004829 c14c898c 24a80000 004889bc ..H).L..$....H.. + 0100 24080100 004d89d9 488d3cf5 00000000 $....M..H.<..... + 0110 4e8d1cdd 00000000 4889bc24 48010000 N.......H..$H... + 0120 488d3ccd 00000000 4889d14c 01ca4829 H.<.....H..L..H) + 0130 c14829c2 4929c04c 89d8488d 34d50000 .H).I).L..H.4... + 0140 000048f7 d8488d55 01480faf c5490faf ..H..H.U.H...I.. + 0150 d34889b4 24280100 004889bc 24300100 .H..$(...H..$0.. + 0160 00488d34 02488d55 02490faf d34889b4 .H.4.H.U.I...H.. + 0170 24e80000 00488d3c cd000000 00488d34 $....H.<.....H.4 + 0180 02488d55 03490faf d34889b4 24f80000 .H.U.I...H..$... + 0190 004889bc 24380100 00488d0c 02488d55 .H..$8...H...H.U + 01a0 04490faf d348898c 24f00000 004c89d3 .I...H..$....L.. + 01b0 488d3402 488d5505 490fafd3 4889b424 H.4.H.U.I...H..$ + 01c0 10010000 48c1fb03 488d0c02 488d5506 ....H...H...H.U. + 01d0 490fafd3 48899c24 a0000000 49c1e706 I...H..$....I... + 01e0 488d3402 488d5507 490fafd3 49c1e003 H.4.H.U.I...I... + 01f0 4c899c24 20010000 488d3c02 4c89d048 L..$ ...H.<.L..H + 0200 83e0f848 89bc2450 01000048 89c7488b ...H..$P...H..H. + 0210 4424904c 89842400 01000048 01c7488d D$.L..$....H..H. + 0220 04d84889 84246801 00004c89 d048c1e3 ..H..$h...L..H.. + 0230 0983e006 48899c24 70010000 48898424 ....H..$p...H..$ + 0240 80010000 4c89d34c 89d083e3 0483e002 ....L..L........ + 0250 4183e201 48899c24 b8000000 48898c24 A...H..$....H..$ + 0260 18010000 4889b424 40010000 48897c24 ....H..$@...H.|$ + 0270 98488984 24580100 004c8994 24600100 .H..$X...L..$`.. + 0280 00c5fb10 05000000 004c89fb 6261ff08 .........L..ba.. + 0290 115c24f9 4d89e662 61ff0811 7424fb4d .\$.M..ba...t$.M + 02a0 89ef62e1 ff08116c 24ff62e1 ff081134 ..b....l$.b....4 + 02b0 2462a1c7 0010ef62 81bf0010 f06281b7 $b.....b.....b.. + 02c0 0010f94c 8ba424d0 01000062 61ff0811 ...L..$....ba... + 02d0 6424f462 61ff0811 6c24fcc5 7b117c24 d$.ba...l$..{.|$ + 02e0 a862e1ff 08114424 f662e1ff 08114c24 .b....D$.b....L$ + 02f0 f762e1ff 08115424 f862e1ff 08115c24 .b....T$.b....\$ + 0300 fd62e1ff 08116424 fe6201af 0010c262 .b....d$.b.....b + 0310 418f0810 cee9d700 0000660f 1f440000 A.........f..D.. + 0320 488b8424 e8000000 4883bc24 a0000000 H..$....H..$.... + 0330 004e8d04 30488b84 24f80000 004d89f3 .N..0H..$....M.. + 0340 498d3c06 488b8424 f0000000 4a8d3430 I.<.H..$....J.40 + 0350 488b8424 10010000 498d0c06 488b8424 H..$....I...H..$ + 0360 18010000 498d1406 488b8424 40010000 ....I...H..$@... + 0370 4d8d2c06 488b8424 50010000 4d8d1406 M.,.H..$P...M... + 0380 488b4424 900f8fdc 00000048 837c24d0 H.D$.......H.|$. + 0390 00744548 39c50f8e 94090000 498d8424 .tEH9.......I..$ + 03a0 00010000 4883bc24 b8000000 004c0f45 ....H..$.....L.E + 03b0 e04883bc 24580100 0000498d 84248000 .H..$X....I..$.. + 03c0 00004c0f 45e04883 bc246001 00000049 ..L.E.H..$`....I + 03d0 8d442440 4c0f45e0 4883c508 4901de49 .D$@L.E.H...I..I + 03e0 83c74048 39ac24a8 0000000f 84bf0c00 ..@H9.$......... + 03f0 00483b6c 24900f8d 24ffffff 488b8424 .H;l$...$...H..$ + 0400 20010000 4883bc24 a0000000 004d8d04 ...H..$.....M.. + 0410 07488b84 24000100 004d89fb 498d3c07 .H..$....M..I.<. + 0420 488b8424 08010000 498d3407 488b8424 H..$....I.4.H..$ + 0430 48010000 498d0c07 488b8424 30010000 H...I...H..$0... + 0440 498d1407 488b8424 38010000 4d8d2c07 I...H..$8...M.,. + 0450 488b8424 28010000 4d8d1407 488b4424 H..$(...M...H.D$ + 0460 900f8e24 ffffff49 89c14c89 5c24884c ...$...I..L.\$.L + 0470 89b424c0 0000004c 89bc24c8 0000004c ..$....L..$....L + 0480 89a424d0 010000c5 fb107424 a0c57b10 ..$.......t$..{. + 0490 4424a8c5 7b104c24 b0c57b10 5424b8c5 D$..{.L$..{.T$.. + 04a0 7b105c24 c0c57b10 6424e8c5 7b106c24 {.\$..{.d$..{.l$ + 04b0 f0c57b10 7424f8c5 7b103c24 4c89e062 ..{.t$..{.<$L..b + 04c0 91870010 ffeb3a66 0f1f8400 00000000 ......:f........ + 04d0 4983c108 48834424 88404983 c0404883 I...H.D$.@I..@H. + 04e0 c7404883 c6404883 c1404883 c2404983 .@H..@H..@H..@I. + 04f0 c5404983 c2404c39 4c24980f 84740500 .@I..@L9L$...t.. + 0500 00480500 0200004c 39cd7fc4 4c8b5c24 .H.....L9...L.\$ + 0510 88c4c17b 10284d8d 241b4c8d 1c1e4c89 ...{.(M.$.L...L. + 0520 5c24b84c 8d1c194c 895c24a0 4c8d1c1a \$.L...L.\$.L... + 0530 4c895c24 c04d8d5c 1d00c5fb 1027c5fb L.\$.M.\.....'.. + 0540 107708c5 fb101ec5 fb107e08 c57b1046 .w........~..{.F + 0550 10c5fb10 11c57b10 4908c57b 105110c5 ......{.I..{.Q.. + 0560 7b105918 c5fb100a c57b1062 08c57b10 {.Y......{.b..{. + 0570 6a10c57b 107218c5 7b107a20 6241ff08 j..{.r..{.z bA.. + 0580 10650062 c1ff0810 6d0162c1 ff081075 .e.b....m.b....u + 0590 0262c1ff 08107d03 6241ff08 10450462 .b....}.bA...E.b + 05a0 41ff0810 4d056241 ff08101a 6241ff08 A...M.bA....bA.. + 05b0 10520162 c1ff0810 620262c1 ff08105a .R.b....b.b....Z + 05c0 0362c1ff 08105204 62c1ff08 104a0562 .b....R.b....J.b + 05d0 c1ff0810 42064c89 5c24b04d 8d1c1a4c ....B.L.\$.M...L + 05e0 895c24a8 4d8d3418 4c8d3c1f 0f8df604 .\$.M.4.L.<..... + 05f0 00004c8b 5c248862 41ff0810 3b6241ff ..L.\$.bA...;bA. + 0600 08106b02 6261ff08 117c24f9 6241ff08 ..k.ba...|$.bA.. + 0610 107b0562 41ff0810 73016261 ff08113c .{.bA...s.ba...< + 0620 246241ff 08107803 6261ff08 116c24fd $bA...x.ba...l$. + 0630 6261ff08 117c2401 6241ff08 10780462 ba...|$.bA...x.b + 0640 41ff0810 6b046261 ff08117c 24026241 A...k.ba...|$.bA + 0650 ff081078 056261ff 08117424 f16261ff ...x.ba...t$.ba. + 0660 08117c24 036241ff 08107806 6241ff08 ..|$.bA...x.bA.. + 0670 10730362 61ff0811 7c240462 61ff0810 .s.ba...|$.ba... + 0680 7f026261 ff08116c 24ff6261 ff08117c ..ba...l$.ba...| + 0690 24fc6261 ff08107f 036241ff 08106801 $.ba.....bA...h. + 06a0 6261ff08 117c2405 6261ff08 107f0462 ba...|$.ba.....b + 06b0 61ff0811 7424fe62 61ff0811 6c24fb62 a...t$.ba...l$.b + 06c0 41ff0810 73066241 ff081068 024d8b5b A...s.bA...h.M.[ + 06d0 384d8b40 386261ff 08117c24 066261ff 8M.@8ba...|$.ba. + 06e0 08107f05 6261ff08 117c2407 6261ff08 ....ba...|$.ba.. + 06f0 107f0648 8b7f3862 61ff0811 7c240862 ...H..8ba...|$.b + 0700 61ff0810 7e036261 ff08117c 24096261 a...~.ba...|$.ba + 0710 ff08107e 046261ff 08117c24 0a6261ff ...~.ba...|$.ba. + 0720 08107e05 6261ff08 117c240b 6261ff08 ..~.ba...|$.ba.. + 0730 107e0648 8b763862 61ff0811 7c240c62 .~.H.v8ba...|$.b + 0740 61ff0810 79046261 ff08117c 240d6261 a...y.ba...|$.ba + 0750 ff081079 056261ff 08117c24 0e6261ff ...y.ba...|$.ba. + 0760 08107906 488b4938 6261ff08 117c240f ..y.H.I8ba...|$. + 0770 6261ff08 107a0562 61ff0811 7c241062 ba...z.ba...|$.b + 0780 61ff0810 7a06488b 52386261 ff08117c a...z.H.R8ba...| + 0790 24116241 ff08107d 064d8b6d 386261ff $.bA...}.M.m8ba. + 07a0 08117c24 126241ff 08107a07 6261ff08 ..|$.bA...z.ba.. + 07b0 1178ff62 61ff0810 7c24f962 61ff0811 .x.ba...|$.ba... + 07c0 78c06261 ff08107c 24f1c5fb 11a840fe x.ba...|$.....@. + 07d0 ffff6261 ff081178 c16261ff 08107c24 ..ba...x.ba...|$ + 07e0 fdc5fb10 6c24d862 61ff0811 78c26261 ....l$.ba...x.ba + 07f0 ff08107c 24fec5fb 11a848fe ffff6261 ...|$.....H...ba + 0800 ff081178 c36261ff 08107c24 ffc5fb10 ...x.ba...|$.... + 0810 6c240862 61ff0811 78c46261 ff08103c l$.ba...x.ba...< + 0820 24c5fb11 a858feff ff6261ff 081178c5 $....X...ba...x. + 0830 c5fb106c 24106261 ff08107c 24fcc5fb ...l$.ba...|$... + 0840 11a860fe ffff6261 ff081178 d2c5fb10 ..`...ba...x.... + 0850 6c241862 61ff0810 7c2405c5 fb11a868 l$.ba...|$.....h + 0860 feffff62 61ff0811 78d3c5fb 106c2420 ...ba...x....l$ + 0870 6261ff08 107c2406 4c899838 feffff4c ba...|$.L..8...L + 0880 898078fe ffff6261 ff081170 c66261ff ..x...ba...p.ba. + 0890 081168ca c5fb11a8 70feffff c5fb11a0 ..h.....p....... + 08a0 80feffff c5fb11b0 88feffff 6261ff08 ............ba.. + 08b0 1178d462 61ff0810 7c240748 89b8b8fe .x.ba...|$.H.... + 08c0 ffff6261 ff081178 d56261ff 08107c24 ..ba...x.ba...|$ + 08d0 084889b0 f8feffff 6261ff08 1178d662 .H......ba...x.b + 08e0 61ff0810 7c240948 898838ff ffff6261 a...|$.H..8...ba + 08f0 ff081178 db6261ff 08107c24 0ac5fb11 ...x.ba...|$.... + 0900 98c0feff ff6261ff 081178dc 6261ff08 .....ba...x.ba.. + 0910 107c240b c5fb11b8 c8feffff 6261ff08 .|$.........ba.. + 0920 1178dd62 61ff0810 7c240cc5 7b1180d0 .x.ba...|$..{... + 0930 feffff62 61ff0811 78de6261 ff08107c ...ba...x.ba...| + 0940 240dc5fb 119000ff ffff6261 ff081178 $.........ba...x + 0950 e46261ff 08107c24 0ec57b11 8808ffff .ba...|$..{..... + 0960 ff6261ff 081178e5 6261ff08 107c240f .ba...x.ba...|$. /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrmm_outucopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 ab020000 00420e10 8f02420e .........B....B. + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 441b0000 00420e10 8f02420e ....D....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830703 53020a0e 30410e28 ..A.8...S...0A.( - 0050 420e2042 0e18420e 10440e08 480b0000 B. B..B..D..H... + 0040 8606410e 38830747 0ed00303 8d150a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/dtrsm_ilnncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ilnncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ilnncopy_COOPERLAKE.o (disasm) @@ -9,439 +9,278 @@ push %r14 push %r13 push %r12 + mov %rdx,%r12 push %rbp push %rbx - sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi mov %rdi,-offset(%rsp) - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,-offset(%rsp) test %rsi,%rsi jle + mov %rdi,%r13 + sar $something,%r13 + mov %rsi,%rdx mov %rcx,%rbx - lea (%rbx,%rbx,2),%rax - mov %rdx,%r11 - mov %rsi,%r15 - lea (%rbx,%rbx,4),%rdx - lea offset(,%rax,8),%rsi - mov %rsi,offset(%rsp) - lea offset(,%rdx,8),%rsi - mov %rsi,offset(%rsp) - mov %rax,%rsi - shl $something,%rax - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - shl $something,%rsi - mov %rsi,offset(%rsp) - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - imul $something,%rbx,%rsi - lea offset(,%rcx,8),%rbp - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - shl $something,%rcx - mov %rcx,(%rsp) - mov %rax,offset(%rsp) - mov %r8,%rax - imul %rbp,%rax - mov %rbx,%rcx - shl $something,%rcx - mov %rsi,offset(%rsp) - mov %rbx,%rsi + mov %rcx,%rsi + mov %r13,%r14 + shl $something,%r14 + shl $something,%rbx shl $something,%rsi - mov %rcx,offset(%rsp) - mov %r11,%r14 - lea offset(%rbp,%rbx,1),%rcx - sub %rax,%r14 - mov %rsi,offset(%rsp) - mov %r15,%rax - lea offset(,%rcx,8),%rsi - mov %rsi,offset(%rsp) + lea (%rcx,%rcx,2),%rax shl $something,%rax - imul $something,%rbx,%rsi - add %r8,%rax - mov %rax,offset(%rsp) - shl $something,%rdx - lea offset(%rbp),%rax - shl $something,%rdi - mov %rdx,offset(%rsp) - mov %rsi,offset(%rsp) - mov %r14,offset(%rsp) - mov %rax,-offset(%rsp) - mov %rdi,offset(%rsp) + mov %rbx,-offset(%rsp) + mov %rsi,-offset(%rsp) + add %r14,%rbx + lea (%r8,%rdx,4),%rsi + lea offset(,%rcx,8),%r15 + mov %rdi,%r10 + mov %rsi,-offset(%rsp) + mov %rbx,-offset(%rsp) + lea (%r15,%r14,1),%rsi + lea (%rax,%r14,1),%rbx + and $something,%r10d + mov %rbx,-offset(%rsp) + mov %rsi,-offset(%rsp) + mov %r13,%rbx + mov %r8,-offset(%rsp) shl $something,%rbx - vmovsd offset(%rip),%xmm1 # + mov %r10,-offset(%rsp) + vmovsd offset(%rip),%xmm16 # + mov %rdi,%r10 + and $something,%rdi mov %rbx,-offset(%rsp) - mov %rbp,%rbx - mov %r8,%rbp + mov %r12,-offset(%rsp) + mov %r12,%rbx + and $something,%r10d + mov %rdi,%rbp + mov %r8,%r11 + mov %rax,%r12 nopl (%rax) - lea (%rbx,%r11,1),%rax - mov %rax,-offset(%rsp) - mov (%rsp),%rax - mov %r11,%r9 - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - lea (%rax,%r11,1),%rsi - mov offset(%rsp),%rax - lea (%r11,%rax,1),%r12 - mov offset(%rsp),%rax - lea (%rax,%r11,1),%r13 - mov offset(%rsp),%rax - lea (%rax,%r11,1),%r14 - mov offset(%rsp),%rax - lea (%rax,%r11,1),%r15 - add -offset(%rsp),%r11 - cmpq $something,-offset(%rsp) - jle - mov -offset(%rsp),%rdx - mov %rbp,%rdi - neg %rdi - mov %r11,-offset(%rsp) - mov offset(%rsp),%r10 - lea (%rdx,%rdi,8),%r8 - xor %eax,%eax - mov %rsi,%r11 - jmp - nopl offset(%rax) - cmp $something,%rdi - jle - vmovsd (%r9),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) /usr/lib64/libopenblas_openmp.a/dtrsm_ilnncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ilnncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ilnncopy_COOPERLAKE.o (objdump) @@ -2,138 +2,86 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_ilnncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ecb00000 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 0448897c .H..$....H...H.| - 0020 24884889 94249000 00004889 8c24a000 $.H..$....H..$.. - 0030 00004c89 84248800 00004c89 4c24e848 ..L..$....L.L$.H - 0040 89b424a8 00000048 85f60f8e 89030000 ..$....H........ - 0050 4889cb48 8d045b49 89d34989 f7488d14 H..H..[I..I..H.. - 0060 9b488d34 c5000000 00488974 2448488d .H.4.....H.t$HH. - 0070 34d50000 00004889 74245048 89c648c1 4.....H.t$PH..H. - 0080 e0054889 44247048 6bc36848 c1e60448 ..H.D$pHk.hH...H - 0090 89742458 48894424 28486bc3 70486bf3 .t$XH.D$(Hk.pHk. - 00a0 38488d2c cd000000 00488944 2430486b 8H.,.....H.D$0Hk - 00b0 c37848c1 e1044889 0c244889 4424384c .xH...H..$H.D$8L - 00c0 89c0480f afc54889 d948c1e1 05488974 ..H...H..H...H.t - 00d0 24104889 de48c1e6 0648894c 24084d89 $.H..H...H.L$.M. - 00e0 de488d4c 1d004929 c6488974 24184c89 .H.L..I).H.t$.L. - 00f0 f8488d34 cd000000 00488974 246048c1 .H.4.....H.t$`H. - 0100 e004486b f3584c01 c0488944 244048c1 ..Hk.XL..H.D$@H. - 0110 e204488d 450848c1 e7074889 54246848 ..H.E.H...H.T$hH - 0120 89742420 4c89b424 80000000 48894424 .t$ L..$....H.D$ - 0130 9048897c 247848c1 e307c5fb 100d0000 .H.|$xH......... - 0140 00004889 5c24f848 89eb4c89 c50f1f00 ..H.\$.H..L..... - 0150 4a8d041b 48894424 98488b04 244d89d9 J...H.D$.H..$M.. - 0160 4c01d848 894424a0 488b4424 484c01d8 L..H.D$.H.D$HL.. - 0170 48894424 a8488b44 24084c01 d8488944 H.D$.H.D$.L..H.D - 0180 24b0488b 4424504c 01d84889 4424b848 $.H.D$PL..H.D$.H - 0190 8b442458 4c01d848 894424c0 488b4424 .D$XL..H.D$.H.D$ - 01a0 104c01d8 48894424 c8488b44 24184c01 .L..H.D$.H.D$.L. - 01b0 d8488944 24d0488b 4424604c 01d84889 .H.D$.H.D$`L..H. - 01c0 4424d848 8b442468 4c01d848 894424e0 D$.H.D$hL..H.D$. - 01d0 488b4424 204a8d34 18488b44 24704d8d H.D$ J.4.H.D$pM. - 01e0 2403488b 4424284e 8d2c1848 8b442430 $.H.D$(N.,.H.D$0 - 01f0 4e8d3418 488b4424 384e8d3c 184c035c N.4.H.D$8N.<.L.\ - 0200 24f84883 7c248800 0f8e8901 0000488b $.H.|$........H. - 0210 5424e848 89ef48f7 df4c895c 24f04c8b T$.H..H..L.\$.L. - 0220 94248000 00004c8d 04fa31c0 4989f3e9 .$....L...1.I... - 0230 06010000 0f1f4000 4883ff0f 0f8e0e01 ......@.H....... - 0240 0000c4c1 7b100148 8b4c2498 c5fb1102 ....{..H.L$..... - 0250 c5fb1004 c1488b4c 24a0c5fb 114208c5 .....H.L$....B.. - 0260 fb1004c1 488b7424 a8c5fb11 4210c5fb ....H.t$....B... - 0270 1004c648 8b4c24b0 c5fb1142 18c5fb10 ...H.L$....B.... - 0280 04c1488b 7424b8c5 fb114220 c5fb1004 ..H.t$....B .... - 0290 c6488b4c 24c0c5fb 114228c5 fb1004c1 .H.L$....B(..... - 02a0 488b7424 c8c5fb11 4230c5fb 1004c648 H.t$....B0.....H - 02b0 8b4c24d0 c5fb1142 38c5fb10 04c1488b .L$....B8.....H. - 02c0 7424d8c5 fb114240 c5fb1004 c6488b4c t$....B@.....H.L - 02d0 24e0c5fb 114248c5 fb1004c1 c5fb1142 $....BH........B - 02e0 50c4c17b 1004c3c5 fb114258 c4c17b10 P..{......BX..{. - 02f0 04c4c5fb 114260c4 c17b1044 c500c5fb .....B`..{.D.... - 0300 114268c4 c17b1004 c6c5fb11 4270c4c1 .Bh..{......Bp.. - 0310 7b1004c7 c5fb1142 7848ffc0 4983c108 {......BxH..I... - 0320 4883ea80 48ffc74c 03542490 4981c088 H...H..L.T$.I... - 0330 00000048 39442488 744e4839 c50f8ef5 ...H9D$.tNH9.... - 0340 feffff48 83ff0f7e d0e9f4fe ffff6690 ...H...~......f. - 0350 4c89ce48 89d14885 ff7e1a0f 1f440000 L..H..H..~...D.. - 0360 c5fb1006 4883c108 c5fb1141 f84801de ....H......A.H.. - 0370 4c39c175 ebc4c173 5e02c4c1 7b1100eb L9.u...s^...{... - 0380 980f1f80 00000000 488b7c24 784c8b5c ........H.|$xL.\ - 0390 24f04801 7c24e848 83c51048 3b6c2440 $.H.|$.H...H;l$@ - 03a0 0f85aafd ffff488b 9c24a800 0000488b ......H..$....H. - 03b0 4424f848 0fafc348 01842490 00000048 D$.H...H..$....H - 03c0 89d8488b 9c248800 000048c1 e0044801 ..H..$....H...H. - 03d0 d8488984 24880000 00f68424 98000000 .H..$......$.... - 03e0 080f848a 01000048 8b8424a0 00000048 .......H..$....H - 03f0 8b942490 00000048 8d34c500 00000048 ..$....H.4.....H - 0400 8d2c3248 8d5c3500 4c8d1c33 4d8d1433 .,2H.\5.L..3M..3 - 0410 4d8d0c32 4d8d3c31 498d3c37 4c8b6c24 M..2M.<1I.<7L.l$ - 0420 88488d04 37488944 24a04d85 ed0f8e28 .H..7H.D$.M....( - 0430 0100004c 8bb42488 00000048 89f14c89 ...L..$....H..L. - 0440 f048f7d8 480fafc8 4c8d04c5 00000000 .H..H...L....... - 0450 4d29f548 01d1488b 5424e84c 29c74d29 M).H..H.T$.L).M) - 0460 c14c896c 24904d89 d548897c 24984c01 .L.l$.M..H.|$.L. - 0470 c24c29c5 4c29c34d 29c34d29 c54d29c7 .L).L).M).M).M). - 0480 48897424 a84c8b44 24e8c5fb 100d0000 H.t$.L.D$....... - 0490 00004c8b 94249000 0000488b bc248800 ..L..$....H..$.. - 04a0 00004c8d 66084d89 cee98700 00006690 ..L.f.M.......f. - 04b0 4883f807 0f8e2303 0000c4c1 7b100248 H.....#.....{..H - 04c0 8b742498 c4c17b11 00c5fb10 44c500c4 .t$...{.....D... - 04d0 c17b1140 08c5fb10 04c3c4c1 7b114010 .{.@........{.@. - 04e0 c4c17b10 04c3c4c1 7b114018 c4c17b10 ..{.....{.@...{. - 04f0 44c500c4 c17b1140 20c4c17b 1004c6c4 D....{.@ ..{.... - 0500 c17b1140 28c4c17b 1004c7c4 c17b1140 .{.@(..{.....{.@ - 0510 30c5fb10 04c6c4c1 7b114038 48ffc049 0.......{.@8H..I - 0520 83c20849 83c0404c 01e14883 c248483b ...I..@L..H..HH; - 0530 44249074 18488d34 384839f7 0f8e6eff D$.t.H.48H9...n. - 0540 ffff4883 f8077ed4 e96dffff ff488b44 ..H...~..m...H.D - 0550 248848c1 e0064801 4424e848 8b4424a0 $.H...H.D$.H.D$. - 0560 48838424 88000000 08488984 24900000 H..$.....H..$... - 0570 00f68424 98000000 040f84fa 00000048 ...$...........H - 0580 8b8424a0 00000048 8bbc2490 0000004c ..$....H..$....L - 0590 8d0cc500 0000004a 8d2c0f4a 8d5c0d00 .......J.,.J.\.. - 05a0 4c8b7c24 884e8d1c 0b4f8d2c 0b4d85ff L.|$.N...O.,.M.. - 05b0 0f8eb200 00004c8b 84248800 00004c89 ......L..$....L. - 05c0 ce4c89c0 48f7d848 0faff04c 8b7424e8 .L..H..H...L.t$. - 05d0 488d14c5 00000000 4d29c749 8d0c1648 H.......M).I...H - 05e0 29d54829 d34929d3 c5fb100d 00000000 ).H).I)......... - 05f0 4d8d5108 4801fe4d 89fc4c89 f2eb4a90 M.Q.H..M..L...J. - 0600 4883f803 0f8e1602 0000c5fb 1007c5fb H............... - 0610 1102c5fb 1044c500 c5fb1142 08c5fb10 .....D.....B.... - 0620 04c3c5fb 114210c4 c17b1004 c3c5fb11 .....B...{...... - 0630 421848ff c04883c7 084883c2 204c01d6 B.H..H...H.. L.. - 0640 4883c128 4c39e074 114e8d34 004d39f0 H..(L9.t.N.4.M9. - 0650 7eae4883 f8037eda ebb0488b 44248848 ~.H...~...H.D$.H - 0660 c1e00548 014424e8 48838424 88000000 ...H.D$.H..$.... - 0670 044c89ac 24900000 00f68424 98000000 .L..$......$.... - 0680 020f84ba 00000048 8b8424a0 00000048 .......H..$....H - 0690 8bac2490 00000048 c1e0034c 8b5c2488 ..$....H...L.\$. - 06a0 4c8d4c05 004d8d14 014d85db 0f8e7e00 L.L..M...M....~. - 06b0 0000488b 9c248800 00004c8d 40084889 ..H..$....L.@.H. - 06c0 de48f7de 480fafc6 488b4c24 e8c5fb10 .H..H...H.L$.... - 06d0 0d000000 004801e8 488d3cf1 31d2eb35 .....H..H.<.1..5 - 06e0 4883fe01 0f8e6501 0000c5fb 1044d500 H.....e......D.. - 06f0 c5fb1101 c4c17b10 04d1c5fb 11410848 ......{......A.H - 0700 ffc24883 c11048ff c64c01c0 4883c718 ..H...H..L..H... - 0710 4939d374 0d4839d3 7ec64883 fe017edf I9.t.H9.~.H...~. - 0720 ebc8488b 44248848 c1e00448 014424e8 ..H.D$.H...H.D$. - 0730 48838424 88000000 024c8994 24900000 H..$.....L..$... - 0740 00f68424 98000000 01747e4c 8b442488 ...$.....t~L.D$. - 0750 4d85c07e 74488bbc 24880000 004c8b54 M..~tH..$....L.T - 0760 24e84889 fa48f7da 4889f9c5 fb100d00 $.H..H..H....... - 0770 0000004c 8b8c2490 00000049 8d34d231 ...L..$....I.4.1 - 0780 c048c1e1 04eb2566 0f1f8400 00000000 .H....%f........ - 0790 4885d27e 0cc4c17b 1004c1c4 c17b1104 H..~...{.....{.. - 07a0 c248ffc0 48ffc249 39c0741d 4839c77f .H..H..I9.t.H9.. - 07b0 df75dd48 ffc0c4c1 735e04f9 48ffc2c5 .u.H....s^..H... - 07c0 fb11040e 4939c075 e34881c4 b0000000 ....I9.u.H...... - 07d0 5b5d415c 415d415e 31c0415f c34d89d1 []A\A]A^1.A_.M.. - 07e0 4c89c648 85c07e2b 48894424 b0488b44 L..H..~+H.D$.H.D - 07f0 24a8660f 1f440000 c4c17b10 014883c6 $.f..D....{..H.. - 0800 08c5fb11 46f84901 c14839d6 75ea488b ....F.I..H9.u.H. - 0810 4424b0c5 f35e01c5 fb1102e9 fcfcffff D$...^.......... - 0820 4989ff49 89d64885 c07e17c4 c17b1007 I..I..H..~...{.. - 0830 4983c608 c4c17b11 46f84d01 cf4939ce I.....{.F.M..I9. - 0840 75e9c5f3 5e06c5fb 1101e9e3 fdffff75 u...^..........u - 0850 0ac5fb10 44d500c5 fb1101c5 f35e00c5 ....D........^.. - 0860 fb1107e9 97feffff ........ + 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t + 0010 24d048c1 fe024889 7c24d848 894c24f8 $.H...H.|$.H.L$. + 0020 48897424 e04885f6 0f8e3403 00004989 H.t$.H....4...I. + 0030 fd49c1fd 024889f2 4889cb48 89ce4d89 .I...H..H..H..M. + 0040 ee49c1e6 0548c1e3 0448c1e6 05488d04 .I...H...H...H.. + 0050 4948c1e0 0348895c 24984889 7424904c IH...H.\$.H.t$.L + 0060 01f3498d 34904c8d 3ccd0000 00004989 ..I.4.L.<.....I. + 0070 fa488974 24a04889 5c24b84b 8d34374a .H.t$.H.\$.K.47J + 0080 8d1c3041 83e20248 895c24c8 48897424 ..0A...H.\$.H.t$ + 0090 c04c89eb 4c894424 f048c1e3 074c8954 .L..L.D$.H...L.T + 00a0 24a862e1 ff081005 00000000 4989fa48 $.b.........I..H + 00b0 83e7fc48 895c24b0 4c896424 e84c89e3 ...H.\$.L.d$.L.. + 00c0 4183e201 4889fd4d 89c34989 c40f1f00 A...H..M..I..... + 00d0 488b4424 98498d14 1f488d34 184a8d3c H.D$.I...H.4.J.< + 00e0 234d85ed 0f8e1604 00004889 d94c89c8 #M........H..L.. + 00f0 4531c0e9 ca000000 0f1f8400 00000000 E1.............. + 0100 0f8d9b00 0000c57b 1039c57b 105908c5 .......{.9.{.Y.. + 0110 fb107910 c5fb1059 18c57b10 32c57b10 ..y....Y..{.2.{. + 0120 5208c5fb 107210c5 fb105218 c57b102e R....r....R..{.. + 0130 c57b104e 08c5fb10 6e10c5fb 104e18c5 .{.N....n....N.. + 0140 7b1027c5 7b104708 c5fb1067 10c5fb10 {.'.{.G....g.... + 0150 4718c57b 1138c57b 117008c5 7b116810 G..{.8.{.p..{.h. + 0160 c57b1160 18c57b11 5820c57b 115028c5 .{.`..{.X .{.P(. + 0170 7b114830 c57b1140 38c5fb11 7840c5fb {.H0.{.@8...x@.. + 0180 117048c5 fb116850 c5fb1160 58c5fb11 .pH...hP...`X... + 0190 5860c5fb 115068c5 fb114870 c5fb1140 X`...Ph...Hp...@ + 01a0 784983c0 044883c1 204883c2 204883c6 xI...H.. H.. H.. + 01b0 204883c7 204883e8 804939e8 0f848e00 H.. H...I9..... + 01c0 00004d39 c30f8535 ffffffc5 fb105208 ..M9...5......R. + 01d0 c5fb104e 10c5fb10 471862f1 ff005ed2 ...N....G.b...^. + 01e0 c57b1041 08c5fb10 7910c5fb 106918c5 .{.A....y....i.. + 01f0 fb107210 c5fb1062 18c5fb10 5e186271 ..r....b....^.bq + 0200 ff005e09 c57b1140 20c57b11 08c5fb11 ..^..{.@ .{..... + 0210 7840c5fb 117048c5 fb116860 c5fb1160 x@...pH...h`...` + 0220 68c5fb11 587062f1 ff005ec9 c5fb1150 h...Xpb...^....P + 0230 2862f1ff 005ec0c5 fb114850 c5fb1140 (b...^....HP...@ + 0240 78e95bff ffff662e 0f1f8400 00000000 x.[...f......... + 0250 488b7c24 c04a8d04 33488d14 3b488b7c H.|$.J..3H..;H.| + 0260 24b84c03 4c24b048 8d343b48 8b7c24c8 $.L.L$.H.4;H.|$. + 0270 4889e948 01df4883 7c24a800 74764939 H..H..H.|$..tvI9 + 0280 cb0f8449 0200007d 53c5fb10 38c5fb10 ...I...}S...8... + 0290 5808c5fb 1032c5fb 105208c5 fb102ec5 X....2...R...... + 02a0 fb104e08 c5fb1027 c5fb1047 08c4c17b ..N....'...G...{ + 02b0 1139c4c1 7b117108 c4c17b11 6910c4c1 .9..{.q...{.i... + 02c0 7b116118 c4c17b11 5920c4c1 7b115128 {.a...{.Y ..{.Q( + 02d0 c4c17b11 4930c4c1 7b114138 4883c010 ..{.I0..{.A8H... + 02e0 4883c210 4883c610 4883c710 4983c140 H...H...H...I..@ + 02f0 4883c102 4d85d274 364c39d9 0f84be01 H...M..t6L9..... + 0300 00007e27 c5fb1018 c5fb1012 c5fb100e ..~'............ + 0310 c5fb1007 c4c17b11 19c4c17b 115108c4 ......{....{.Q.. + 0320 c17b1149 10c4c17b 11411849 83c12049 .{.I...{.A.I.. I + 0330 83c30448 035c2490 4c3b5c24 a00f858d ...H.\$.L;\$.... + 0340 fdffff48 8b5c24e0 488b4424 904c8b64 ...H.\$.H.D$.L.d + 0350 24e8480f afc34c8b 4424f049 01c44d8d $.H...L.D$.I..M. + 0360 0498f644 24d0020f 84f30000 004c8b54 ...D$........L.T + 0370 24f8488b 7c24d849 c1e20348 d1ff4b8d $.H.|$.I...H..K. + 0380 0c144885 ff0f8e97 010000c5 fb102500 ..H...........%. + 0390 00000048 8d343f4c 89ca31c0 eb3c6690 ...H.4?L..1.. + mov %rdi,%r13 + sar $something,%r13 + mov %rsi,%rdx mov %rcx,%rbx - lea (%rbx,%rbx,2),%rax - mov %rdx,%r11 - mov %rsi,%r15 - lea (%rbx,%rbx,4),%rdx - lea offset(,%rax,8),%rsi - mov %rsi,offset(%rsp) - lea offset(,%rdx,8),%rsi - mov %rsi,offset(%rsp) - mov %rax,%rsi - shl $something,%rax - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - shl $something,%rsi - mov %rsi,offset(%rsp) - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - imul $something,%rbx,%rsi - lea offset(,%rcx,8),%rbp - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - shl $something,%rcx - mov %rcx,(%rsp) - mov %rax,offset(%rsp) - mov %r8,%rax - imul %rbp,%rax - mov %rbx,%rcx - shl $something,%rcx - mov %rsi,offset(%rsp) - mov %rbx,%rsi + mov %rcx,%rsi + mov %r13,%r14 + shl $something,%r14 + shl $something,%rbx shl $something,%rsi - mov %rcx,offset(%rsp) - mov %r11,%r14 - lea offset(%rbp,%rbx,1),%rcx - sub %rax,%r14 - mov %rsi,offset(%rsp) - mov %r15,%rax - lea offset(,%rcx,8),%rsi - mov %rsi,offset(%rsp) + lea (%rcx,%rcx,2),%rax shl $something,%rax - imul $something,%rbx,%rsi - add %r8,%rax - mov %rax,offset(%rsp) - shl $something,%rdx - lea offset(%rbp),%rax - shl $something,%rdi - mov %rdx,offset(%rsp) - mov %rsi,offset(%rsp) - mov %r14,offset(%rsp) - mov %rax,-offset(%rsp) - mov %rdi,offset(%rsp) + mov %rbx,-offset(%rsp) + mov %rsi,-offset(%rsp) + add %r14,%rbx + lea (%r8,%rdx,4),%rsi + lea offset(,%rcx,8),%r15 + mov %rdi,%r10 + mov %rsi,-offset(%rsp) + mov %rbx,-offset(%rsp) + lea (%r15,%r14,1),%rsi + lea (%rax,%r14,1),%rbx + and $something,%r10d + mov %rbx,-offset(%rsp) + mov %rsi,-offset(%rsp) + mov %r13,%rbx + mov %r8,-offset(%rsp) shl $something,%rbx - vmovsd offset(%rip),%xmm1 # + mov %r10,-offset(%rsp) + vmovsd offset(%rip),%xmm16 # + mov %rdi,%r10 + and $something,%rdi mov %rbx,-offset(%rsp) - mov %rbp,%rbx - mov %r8,%rbp + mov %r12,-offset(%rsp) + mov %r12,%rbx + and $something,%r10d + mov %rdi,%rbp + mov %r8,%r11 + mov %rax,%r12 nopl (%rax) - lea (%rbx,%r11,1),%rax - mov %rax,-offset(%rsp) - mov (%rsp),%rax - mov %r11,%r9 - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - lea (%rax,%r11,1),%rsi - mov offset(%rsp),%rax - lea (%r11,%rax,1),%r12 - mov offset(%rsp),%rax - lea (%rax,%r11,1),%r13 - mov offset(%rsp),%rax - lea (%rax,%r11,1),%r14 - mov offset(%rsp),%rax - lea (%rax,%r11,1),%r15 - add -offset(%rsp),%r11 - cmpq $something,-offset(%rsp) - jle - mov -offset(%rsp),%rdx - mov %rbp,%rdi - neg %rdi - mov %r11,-offset(%rsp) - mov offset(%rsp),%r10 - lea (%rdx,%rdi,8),%r8 - xor %eax,%eax - mov %rsi,%r11 - jmp - nopl offset(%rax) - cmp $something,%rdi - jle - vmovsd (%r9),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) /usr/lib64/libopenblas_openmp.a/dtrsm_ilnncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ilnncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ilnncopy_SKYLAKEX.o (objdump) @@ -2,138 +2,86 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_ilnncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ecb00000 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 0448897c .H..$....H...H.| - 0020 24884889 94249000 00004889 8c24a000 $.H..$....H..$.. - 0030 00004c89 84248800 00004c89 4c24e848 ..L..$....L.L$.H - 0040 89b424a8 00000048 85f60f8e 89030000 ..$....H........ - 0050 4889cb48 8d045b49 89d34989 f7488d14 H..H..[I..I..H.. - 0060 9b488d34 c5000000 00488974 2448488d .H.4.....H.t$HH. - 0070 34d50000 00004889 74245048 89c648c1 4.....H.t$PH..H. - 0080 e0054889 44247048 6bc36848 c1e60448 ..H.D$pHk.hH...H - 0090 89742458 48894424 28486bc3 70486bf3 .t$XH.D$(Hk.pHk. - 00a0 38488d2c cd000000 00488944 2430486b 8H.,.....H.D$0Hk - 00b0 c37848c1 e1044889 0c244889 4424384c .xH...H..$H.D$8L - 00c0 89c0480f afc54889 d948c1e1 05488974 ..H...H..H...H.t - 00d0 24104889 de48c1e6 0648894c 24084d89 $.H..H...H.L$.M. - 00e0 de488d4c 1d004929 c6488974 24184c89 .H.L..I).H.t$.L. - 00f0 f8488d34 cd000000 00488974 246048c1 .H.4.....H.t$`H. - 0100 e004486b f3584c01 c0488944 244048c1 ..Hk.XL..H.D$@H. - 0110 e204488d 450848c1 e7074889 54246848 ..H.E.H...H.T$hH - 0120 89742420 4c89b424 80000000 48894424 .t$ L..$....H.D$ - 0130 9048897c 247848c1 e307c5fb 100d0000 .H.|$xH......... - 0140 00004889 5c24f848 89eb4c89 c50f1f00 ..H.\$.H..L..... - 0150 4a8d041b 48894424 98488b04 244d89d9 J...H.D$.H..$M.. - 0160 4c01d848 894424a0 488b4424 484c01d8 L..H.D$.H.D$HL.. - 0170 48894424 a8488b44 24084c01 d8488944 H.D$.H.D$.L..H.D - 0180 24b0488b 4424504c 01d84889 4424b848 $.H.D$PL..H.D$.H - 0190 8b442458 4c01d848 894424c0 488b4424 .D$XL..H.D$.H.D$ - 01a0 104c01d8 48894424 c8488b44 24184c01 .L..H.D$.H.D$.L. - 01b0 d8488944 24d0488b 4424604c 01d84889 .H.D$.H.D$`L..H. - 01c0 4424d848 8b442468 4c01d848 894424e0 D$.H.D$hL..H.D$. - 01d0 488b4424 204a8d34 18488b44 24704d8d H.D$ J.4.H.D$pM. - 01e0 2403488b 4424284e 8d2c1848 8b442430 $.H.D$(N.,.H.D$0 - 01f0 4e8d3418 488b4424 384e8d3c 184c035c N.4.H.D$8N.<.L.\ - 0200 24f84883 7c248800 0f8e8901 0000488b $.H.|$........H. - 0210 5424e848 89ef48f7 df4c895c 24f04c8b T$.H..H..L.\$.L. - 0220 94248000 00004c8d 04fa31c0 4989f3e9 .$....L...1.I... - 0230 06010000 0f1f4000 4883ff0f 0f8e0e01 ......@.H....... - 0240 0000c4c1 7b100148 8b4c2498 c5fb1102 ....{..H.L$..... - 0250 c5fb1004 c1488b4c 24a0c5fb 114208c5 .....H.L$....B.. - 0260 fb1004c1 488b7424 a8c5fb11 4210c5fb ....H.t$....B... - 0270 1004c648 8b4c24b0 c5fb1142 18c5fb10 ...H.L$....B.... - 0280 04c1488b 7424b8c5 fb114220 c5fb1004 ..H.t$....B .... - 0290 c6488b4c 24c0c5fb 114228c5 fb1004c1 .H.L$....B(..... - 02a0 488b7424 c8c5fb11 4230c5fb 1004c648 H.t$....B0.....H - 02b0 8b4c24d0 c5fb1142 38c5fb10 04c1488b .L$....B8.....H. - 02c0 7424d8c5 fb114240 c5fb1004 c6488b4c t$....B@.....H.L - 02d0 24e0c5fb 114248c5 fb1004c1 c5fb1142 $....BH........B - 02e0 50c4c17b 1004c3c5 fb114258 c4c17b10 P..{......BX..{. - 02f0 04c4c5fb 114260c4 c17b1044 c500c5fb .....B`..{.D.... - 0300 114268c4 c17b1004 c6c5fb11 4270c4c1 .Bh..{......Bp.. - 0310 7b1004c7 c5fb1142 7848ffc0 4983c108 {......BxH..I... - 0320 4883ea80 48ffc74c 03542490 4981c088 H...H..L.T$.I... - 0330 00000048 39442488 744e4839 c50f8ef5 ...H9D$.tNH9.... - 0340 feffff48 83ff0f7e d0e9f4fe ffff6690 ...H...~......f. - 0350 4c89ce48 89d14885 ff7e1a0f 1f440000 L..H..H..~...D.. - 0360 c5fb1006 4883c108 c5fb1141 f84801de ....H......A.H.. - 0370 4c39c175 ebc4c173 5e02c4c1 7b1100eb L9.u...s^...{... - 0380 980f1f80 00000000 488b7c24 784c8b5c ........H.|$xL.\ - 0390 24f04801 7c24e848 83c51048 3b6c2440 $.H.|$.H...H;l$@ - 03a0 0f85aafd ffff488b 9c24a800 0000488b ......H..$....H. - 03b0 4424f848 0fafc348 01842490 00000048 D$.H...H..$....H - 03c0 89d8488b 9c248800 000048c1 e0044801 ..H..$....H...H. - 03d0 d8488984 24880000 00f68424 98000000 .H..$......$.... - 03e0 080f848a 01000048 8b8424a0 00000048 .......H..$....H - 03f0 8b942490 00000048 8d34c500 00000048 ..$....H.4.....H - 0400 8d2c3248 8d5c3500 4c8d1c33 4d8d1433 .,2H.\5.L..3M..3 - 0410 4d8d0c32 4d8d3c31 498d3c37 4c8b6c24 M..2M.<1I.<7L.l$ - 0420 88488d04 37488944 24a04d85 ed0f8e28 .H..7H.D$.M....( - 0430 0100004c 8bb42488 00000048 89f14c89 ...L..$....H..L. - 0440 f048f7d8 480fafc8 4c8d04c5 00000000 .H..H...L....... - 0450 4d29f548 01d1488b 5424e84c 29c74d29 M).H..H.T$.L).M) - 0460 c14c896c 24904d89 d548897c 24984c01 .L.l$.M..H.|$.L. - 0470 c24c29c5 4c29c34d 29c34d29 c54d29c7 .L).L).M).M).M). - 0480 48897424 a84c8b44 24e8c5fb 100d0000 H.t$.L.D$....... - 0490 00004c8b 94249000 0000488b bc248800 ..L..$....H..$.. - 04a0 00004c8d 66084d89 cee98700 00006690 ..L.f.M.......f. - 04b0 4883f807 0f8e2303 0000c4c1 7b100248 H.....#.....{..H - 04c0 8b742498 c4c17b11 00c5fb10 44c500c4 .t$...{.....D... - 04d0 c17b1140 08c5fb10 04c3c4c1 7b114010 .{.@........{.@. - 04e0 c4c17b10 04c3c4c1 7b114018 c4c17b10 ..{.....{.@...{. - 04f0 44c500c4 c17b1140 20c4c17b 1004c6c4 D....{.@ ..{.... - 0500 c17b1140 28c4c17b 1004c7c4 c17b1140 .{.@(..{.....{.@ - 0510 30c5fb10 04c6c4c1 7b114038 48ffc049 0.......{.@8H..I - 0520 83c20849 83c0404c 01e14883 c248483b ...I..@L..H..HH; - 0530 44249074 18488d34 384839f7 0f8e6eff D$.t.H.48H9...n. - 0540 ffff4883 f8077ed4 e96dffff ff488b44 ..H...~..m...H.D - 0550 248848c1 e0064801 4424e848 8b4424a0 $.H...H.D$.H.D$. - 0560 48838424 88000000 08488984 24900000 H..$.....H..$... - 0570 00f68424 98000000 040f84fa 00000048 ...$...........H - 0580 8b8424a0 00000048 8bbc2490 0000004c ..$....H..$....L - 0590 8d0cc500 0000004a 8d2c0f4a 8d5c0d00 .......J.,.J.\.. - 05a0 4c8b7c24 884e8d1c 0b4f8d2c 0b4d85ff L.|$.N...O.,.M.. - 05b0 0f8eb200 00004c8b 84248800 00004c89 ......L..$....L. - 05c0 ce4c89c0 48f7d848 0faff04c 8b7424e8 .L..H..H...L.t$. - 05d0 488d14c5 00000000 4d29c749 8d0c1648 H.......M).I...H - 05e0 29d54829 d34929d3 c5fb100d 00000000 ).H).I)......... - 05f0 4d8d5108 4801fe4d 89fc4c89 f2eb4a90 M.Q.H..M..L...J. - 0600 4883f803 0f8e1602 0000c5fb 1007c5fb H............... - 0610 1102c5fb 1044c500 c5fb1142 08c5fb10 .....D.....B.... - 0620 04c3c5fb 114210c4 c17b1004 c3c5fb11 .....B...{...... - 0630 421848ff c04883c7 084883c2 204c01d6 B.H..H...H.. L.. - 0640 4883c128 4c39e074 114e8d34 004d39f0 H..(L9.t.N.4.M9. - 0650 7eae4883 f8037eda ebb0488b 44248848 ~.H...~...H.D$.H - 0660 c1e00548 014424e8 48838424 88000000 ...H.D$.H..$.... - 0670 044c89ac 24900000 00f68424 98000000 .L..$......$.... - 0680 020f84ba 00000048 8b8424a0 00000048 .......H..$....H - 0690 8bac2490 00000048 c1e0034c 8b5c2488 ..$....H...L.\$. - 06a0 4c8d4c05 004d8d14 014d85db 0f8e7e00 L.L..M...M....~. - 06b0 0000488b 9c248800 00004c8d 40084889 ..H..$....L.@.H. - 06c0 de48f7de 480fafc6 488b4c24 e8c5fb10 .H..H...H.L$.... - 06d0 0d000000 004801e8 488d3cf1 31d2eb35 .....H..H.<.1..5 - 06e0 4883fe01 0f8e6501 0000c5fb 1044d500 H.....e......D.. - 06f0 c5fb1101 c4c17b10 04d1c5fb 11410848 ......{......A.H - 0700 ffc24883 c11048ff c64c01c0 4883c718 ..H...H..L..H... - 0710 4939d374 0d4839d3 7ec64883 fe017edf I9.t.H9.~.H...~. - 0720 ebc8488b 44248848 c1e00448 014424e8 ..H.D$.H...H.D$. - 0730 48838424 88000000 024c8994 24900000 H..$.....L..$... - 0740 00f68424 98000000 01747e4c 8b442488 ...$.....t~L.D$. - 0750 4d85c07e 74488bbc 24880000 004c8b54 M..~tH..$....L.T - 0760 24e84889 fa48f7da 4889f9c5 fb100d00 $.H..H..H....... - 0770 0000004c 8b8c2490 00000049 8d34d231 ...L..$....I.4.1 - 0780 c048c1e1 04eb2566 0f1f8400 00000000 .H....%f........ - 0790 4885d27e 0cc4c17b 1004c1c4 c17b1104 H..~...{.....{.. - 07a0 c248ffc0 48ffc249 39c0741d 4839c77f .H..H..I9.t.H9.. - 07b0 df75dd48 ffc0c4c1 735e04f9 48ffc2c5 .u.H....s^..H... - 07c0 fb11040e 4939c075 e34881c4 b0000000 ....I9.u.H...... - 07d0 5b5d415c 415d415e 31c0415f c34d89d1 []A\A]A^1.A_.M.. - 07e0 4c89c648 85c07e2b 48894424 b0488b44 L..H..~+H.D$.H.D - 07f0 24a8660f 1f440000 c4c17b10 014883c6 $.f..D....{..H.. - 0800 08c5fb11 46f84901 c14839d6 75ea488b ....F.I..H9.u.H. - 0810 4424b0c5 f35e01c5 fb1102e9 fcfcffff D$...^.......... - 0820 4989ff49 89d64885 c07e17c4 c17b1007 I..I..H..~...{.. - 0830 4983c608 c4c17b11 46f84d01 cf4939ce I.....{.F.M..I9. - 0840 75e9c5f3 5e06c5fb 1101e9e3 fdffff75 u...^..........u - 0850 0ac5fb10 44d500c5 fb1101c5 f35e00c5 ....D........^.. - 0860 fb1107e9 97feffff ........ + 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t + 0010 24d048c1 fe024889 7c24d848 894c24f8 $.H...H.|$.H.L$. + 0020 48897424 e04885f6 0f8e3403 00004989 H.t$.H....4...I. + 0030 fd49c1fd 024889f2 4889cb48 89ce4d89 .I...H..H..H..M. + 0040 ee49c1e6 0548c1e3 0448c1e6 05488d04 .I...H...H...H.. + 0050 4948c1e0 0348895c 24984889 7424904c IH...H.\$.H.t$.L + 0060 01f3498d 34904c8d 3ccd0000 00004989 ..I.4.L.<.....I. + 0070 fa488974 24a04889 5c24b84b 8d34374a .H.t$.H.\$.K.47J + 0080 8d1c3041 83e20248 895c24c8 48897424 ..0A...H.\$.H.t$ + 0090 c04c89eb 4c894424 f048c1e3 074c8954 .L..L.D$.H...L.T + 00a0 24a862e1 ff081005 00000000 4989fa48 $.b.........I..H + 00b0 83e7fc48 895c24b0 4c896424 e84c89e3 ...H.\$.L.d$.L.. + 00c0 4183e201 4889fd4d 89c34989 c40f1f00 A...H..M..I..... + 00d0 488b4424 98498d14 1f488d34 184a8d3c H.D$.I...H.4.J.< + 00e0 234d85ed 0f8e1604 00004889 d94c89c8 #M........H..L.. + 00f0 4531c0e9 ca000000 0f1f8400 00000000 E1.............. + 0100 0f8d9b00 0000c57b 1039c57b 105908c5 .......{.9.{.Y.. + 0110 fb107910 c5fb1059 18c57b10 32c57b10 ..y....Y..{.2.{. + 0120 5208c5fb 107210c5 fb105218 c57b102e R....r....R..{.. + 0130 c57b104e 08c5fb10 6e10c5fb 104e18c5 .{.N....n....N.. + 0140 7b1027c5 7b104708 c5fb1067 10c5fb10 {.'.{.G....g.... + 0150 4718c57b 1138c57b 117008c5 7b116810 G..{.8.{.p..{.h. + 0160 c57b1160 18c57b11 5820c57b 115028c5 .{.`..{.X .{.P(. + 0170 7b114830 c57b1140 38c5fb11 7840c5fb {.H0.{.@8...x@.. + 0180 117048c5 fb116850 c5fb1160 58c5fb11 .pH...hP...`X... + 0190 5860c5fb 115068c5 fb114870 c5fb1140 X`...Ph...Hp...@ + 01a0 784983c0 044883c1 204883c2 204883c6 xI...H.. H.. H.. + 01b0 204883c7 204883e8 804939e8 0f848e00 H.. H...I9..... + 01c0 00004d39 c30f8535 ffffffc5 fb105208 ..M9...5......R. + 01d0 c5fb104e 10c5fb10 471862f1 ff005ed2 ...N....G.b...^. + 01e0 c57b1041 08c5fb10 7910c5fb 106918c5 .{.A....y....i.. + 01f0 fb107210 c5fb1062 18c5fb10 5e186271 ..r....b....^.bq + 0200 ff005e09 c57b1140 20c57b11 08c5fb11 ..^..{.@ .{..... + 0210 7840c5fb 117048c5 fb116860 c5fb1160 x@...pH...h`...` + 0220 68c5fb11 587062f1 ff005ec9 c5fb1150 h...Xpb...^....P + 0230 2862f1ff 005ec0c5 fb114850 c5fb1140 (b...^....HP...@ + 0240 78e95bff ffff662e 0f1f8400 00000000 x.[...f......... + 0250 488b7c24 c04a8d04 33488d14 3b488b7c H.|$.J..3H..;H.| + 0260 24b84c03 4c24b048 8d343b48 8b7c24c8 $.L.L$.H.4;H.|$. + 0270 4889e948 01df4883 7c24a800 74764939 H..H..H.|$..tvI9 + 0280 cb0f8449 0200007d 53c5fb10 38c5fb10 ...I...}S...8... + 0290 5808c5fb 1032c5fb 105208c5 fb102ec5 X....2...R...... + 02a0 fb104e08 c5fb1027 c5fb1047 08c4c17b ..N....'...G...{ + 02b0 1139c4c1 7b117108 c4c17b11 6910c4c1 .9..{.q...{.i... + 02c0 7b116118 c4c17b11 5920c4c1 7b115128 {.a...{.Y ..{.Q( + 02d0 c4c17b11 4930c4c1 7b114138 4883c010 ..{.I0..{.A8H... + 02e0 4883c210 4883c610 4883c710 4983c140 H...H...H...I..@ + 02f0 4883c102 4d85d274 364c39d9 0f84be01 H...M..t6L9..... + 0300 00007e27 c5fb1018 c5fb1012 c5fb100e ..~'............ + 0310 c5fb1007 c4c17b11 19c4c17b 115108c4 ......{....{.Q.. + 0320 c17b1149 10c4c17b 11411849 83c12049 .{.I...{.A.I.. I + 0330 83c30448 035c2490 4c3b5c24 a00f858d ...H.\$.L;\$.... + 0340 fdffff48 8b5c24e0 488b4424 904c8b64 ...H.\$.H.D$.L.d + 0350 24e8480f afc34c8b 4424f049 01c44d8d $.H...L.D$.I..M. + 0360 0498f644 24d0020f 84f30000 004c8b54 ...D$........L.T + 0370 24f8488b 7c24d849 c1e20348 d1ff4b8d $.H.|$.I...H..K. + 0380 0c144885 ff0f8e97 010000c5 fb102500 ..H...........%. + 0390 00000048 8d343f4c 89ca31c0 eb3c6690 ...H.4?L..1.. - mov %rsi,%r15 - mov %rcx,%rsi - lea offset(,%rcx,8),%rbx - lea (%rsi,%rsi,2),%rax - shl $something,%rcx - mov %rcx,-offset(%rsp) - lea offset(,%rax,8),%rcx - mov %rcx,offset(%rsp) - mov %rsi,%rcx - shl $something,%rcx - mov %rdx,%r10 - lea (%rsi,%rsi,4),%rdx - mov %rcx,(%rsp) - lea offset(,%rdx,8),%rcx - mov %rcx,offset(%rsp) - mov %rax,%rcx + mov %rdi,%r13 + sar $something,%r13 + mov %rcx,%rbx + mov %rdi,%r10 + mov %r13,%r14 + shl $something,%r14 + shl $something,%rbx + lea (%rcx,%rcx,2),%rax + and $something,%r10d + lea offset(,%rcx,8),%r15 shl $something,%rax - mov %rax,offset(%rsp) - imul $something,%rsi,%rax - shl $something,%rcx - mov %rcx,offset(%rsp) - imul $something,%rsi,%rcx - mov %rax,offset(%rsp) - imul $something,%rsi,%rax - mov %rcx,offset(%rsp) - mov %rsi,%rcx shl $something,%rcx - mov %rax,offset(%rsp) - imul $something,%rsi,%rax - mov %rcx,offset(%rsp) - lea (%rbx,%rsi,1),%rcx - shl $something,%rcx - mov %rcx,offset(%rsp) - mov %rax,offset(%rsp) - imul $something,%rsi,%rcx - mov %r15,%rax - shl $something,%rax - shl $something,%rdx - shl $something,%rsi - add %r8,%rax - shl $something,%rdi - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %rsi,-offset(%rsp) - mov %rax,offset(%rsp) - mov %rdi,offset(%rsp) - vmovsd offset(%rip),%xmm1 # - mov %rbx,%r11 - mov %r8,%rbx - nopl offset(%rax) - lea (%r11,%r10,1),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - mov %r10,%r9 - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov (%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - lea (%r10,%rax,1),%rcx - mov offset(%rsp),%rax - lea (%rax,%r10,1),%rbp - mov offset(%rsp),%rax - lea (%r10,%rax,1),%r12 - mov offset(%rsp),%rax - lea (%rax,%r10,1),%r13 - mov offset(%rsp),%rax - lea (%rax,%r10,1),%r14 - mov offset(%rsp),%rax - lea (%rax,%r10,1),%r15 - add -offset(%rsp),%r10 - cmpq $something,-offset(%rsp) - jle - mov -offset(%rsp),%rdx - mov %rbx,%rdi - neg %rdi + mov %rbx,-offset(%rsp) mov %r10,-offset(%rsp) - lea (%rdx,%rdi,8),%r8 - xor %eax,%eax - mov %rcx,%r10 - jmp - cmp $something,%rdi - jle - vmovsd (%r9),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd (%r10,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rbp,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd (%r12,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%r13,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd (%r14,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd (%r15,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - inc %rax - add $something,%r9 - sub $something,%rdx - inc %rdi - add $something,%r8 - cmp %rax,-offset(%rsp) - je - cmp %rax,%rbx - jle - cmp $something,%rdi + add %r14,%rbx + mov %rdi,%r10 + and $something,%rdi + mov %rcx,-offset(%rsp) + mov %rbx,-offset(%rsp) + lea (%r8,%rsi,4),%rcx + lea (%rax,%r14,1),%rbx + mov %rdi,%rbp + lea (%r15,%r14,1),%rdi + mov %rbx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %r13,%rbx + mov %rdi,-offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_COOPERLAKE.o (objdump) @@ -2,118 +2,82 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ec980000 AWAVAUATUSH..... - 0010 004889b4 24800000 0048c1fe 0448897c .H..$....H...H.| - 0020 24884889 54247848 898c2488 0000004c $.H.T$xH..$....L - 0030 894424f0 4c894c24 d84889b4 24900000 .D$.L.L$.H..$... - 0040 004885f6 0f8e3e03 00004989 f74889ce .H....>...I..H.. - 0050 488d1ccd 00000000 488d0476 48c1e104 H.......H..vH... - 0060 48894c24 f8488d0c c5000000 0048894c H.L$.H.......H.L - 0070 24404889 f148c1e1 054989d2 488d14b6 $@H..H...I..H... - 0080 48890c24 488d0cd5 00000000 48894c24 H..$H.......H.L$ - 0090 484889c1 48c1e005 48894424 68486bc6 HH..H...H.D$hHk. - 00a0 6848c1e1 0448894c 2450486b ce384889 hH...H.L$PHk.8H. - 00b0 44242048 6bc67048 894c2408 4889f148 D$ Hk.pH.L$.H..H - 00c0 c1e10648 89442428 486bc678 48894c24 ...H.D$(Hk.xH.L$ - 00d0 10488d0c 3348c1e1 0348894c 24584889 .H..3H...H.L$XH. - 00e0 44243048 6bce584c 89f848c1 e00448c1 D$0Hk.XL..H...H. - 00f0 e20448c1 e6074c01 c048c1e7 07488954 ..H...L..H...H.T - 0100 24604889 4c241848 897424e8 48894424 $`H.L$.H.t$.H.D$ - 0110 3848897c 2470c5fb 100d0000 00004989 8H.|$p........I. - 0120 db4c89c3 0f1f4000 4b8d0413 48894424 .L....@.K...H.D$ - 0130 90488b44 24f84d89 d14c01d0 48894424 .H.D$.M..L..H.D$ - 0140 98488b44 24404c01 d0488944 24a0488b .H.D$@L..H.D$.H. - 0150 04244c01 d0488944 24a8488b 4424484c .$L..H.D$.H.D$HL - 0160 01d04889 4424b048 8b442450 4c01d048 ..H.D$.H.D$PL..H - 0170 894424b8 488b4424 084c01d0 48894424 .D$.H.D$.L..H.D$ - 0180 c0488b44 24104c01 d0488944 24c8488b .H.D$.L..H.D$.H. - 0190 4424584c 01d04889 4424d048 8b442460 D$XL..H.D$.H.D$` - 01a0 498d0c02 488b4424 184a8d2c 10488b44 I...H.D$.J.,.H.D - 01b0 24684d8d 2402488b 4424204e 8d2c1048 $hM.$.H.D$ N.,.H - 01c0 8b442428 4e8d3410 488b4424 304e8d3c .D$(N.4.H.D$0N.< - 01d0 104c0354 24e84883 7c248800 0f8e6d01 .L.T$.H.|$....m. - 01e0 0000488b 5424d848 89df48f7 df4c8954 ..H.T$.H..H..L.T - 01f0 24e04c8d 04fa31c0 4989cae9 f9000000 $.L...1.I....... - 0200 4883ff0f 0f8e0601 0000c4c1 7b100148 H...........{..H - 0210 8b4c2490 c5fb1102 c5fb1004 c1488b74 .L$..........H.t - 0220 2498c5fb 114208c5 fb1004c6 488b4c24 $....B......H.L$ - 0230 a0c5fb11 4210c5fb 1004c148 8b7424a8 ....B......H.t$. - 0240 c5fb1142 18c5fb10 04c6488b 4c24b0c5 ...B......H.L$.. - 0250 fb114220 c5fb1004 c1488b74 24b8c5fb ..B .....H.t$... - 0260 114228c5 fb1004c6 488b4c24 c0c5fb11 .B(.....H.L$.... - 0270 4230c5fb 1004c148 8b7424c8 c5fb1142 B0.....H.t$....B - 0280 38c5fb10 04c6488b 4c24d0c5 fb114240 8.....H.L$....B@ - 0290 c5fb1004 c1c5fb11 4248c4c1 7b1004c2 ........BH..{... - 02a0 c5fb1142 50c5fb10 44c500c5 fb114258 ...BP...D.....BX - 02b0 c4c17b10 04c4c5fb 114260c4 c17b1044 ..{......B`..{.D - 02c0 c500c5fb 114268c4 c17b1004 c6c5fb11 .....Bh..{...... - 02d0 4270c4c1 7b1004c7 c5fb1142 7848ffc0 Bp..{......BxH.. - 02e0 4983c108 4883ea80 48ffc749 81c08800 I...H...H..I.... - 02f0 00004839 44248874 474839c3 0f8efefe ..H9D$.tGH9..... - 0300 ffff4883 ff0f7ed5 e9fdfeff ff0f1f00 ..H...~......... - 0310 4c89ce48 89d14885 ff7e1a0f 1f440000 L..H..H..~...D.. - 0320 c5fb1006 4883c108 c5fb1141 f84c01de ....H......A.L.. - 0330 4c39c175 ebc4c17b 1108eba1 0f1f4000 L9.u...{......@. - 0340 488b7c24 704c8b54 24e04801 7c24d848 H.|$pL.T$.H.|$.H - 0350 83c31048 3b5c2438 0f85cafd ffff488b ...H;\$8......H. - 0360 9c249000 0000488b 4424e848 0fafc348 .$....H.D$.H...H - 0370 01442478 4889d848 8b5c24f0 48c1e004 .D$xH..H.\$.H... - 0380 4801d848 894424f0 f6842480 00000008 H..H.D$...$..... - 0390 0f841001 0000488b 84248800 0000488b ......H..$....H. - 03a0 4c24784c 8d0cc500 0000004e 8d34094f L$xL.......N.4.O - 03b0 8d2c0e4f 8d640d00 4b8d2c0c 4e8d540d .,.O.d..K.,.N.T. - 03c0 004f8d1c 0a4b8d1c 0b48837c 2488004e .O...K...H.|$..N - 03d0 8d3c0b0f 8ec20000 00488b74 24f0488b .<.......H.t$.H. - 03e0 5424d848 f7de4c89 7c2490c5 fb100d00 T$.H..L.|$...... - 03f0 00000048 8d3cf231 c04989cf eb7b6690 ...H.<.1.I...{f. - 0400 4883fe07 0f8ead02 0000c4c1 7b1007c5 H...........{... - 0410 fb1102c4 c17b1004 c6c5fb11 4208c4c1 .....{......B... - 0420 7b1044c5 00c5fb11 4210c4c1 7b1004c4 {.D.....B...{... - 0430 c5fb1142 18c5fb10 44c500c5 fb114220 ...B....D.....B - 0440 c4c17b10 04c2c5fb 114228c4 c17b1004 ..{......B(..{.. - 0450 c3c5fb11 4230c5fb 1004c3c5 fb114238 ....B0........B8 - 0460 48ffc049 83c70848 83c24048 ffc64883 H..I...H..@H..H. - 0470 c7484839 44248874 0f483944 24f07e80 .HH9D$.t.H9D$.~. - 0480 4883fe07 7edaeb82 488b4424 884c8b7c H...~...H.D$.L.| - 0490 249048c1 e0064801 4424d848 834424f0 $.H...H.D$.H.D$. - 04a0 084c897c 2478f684 24800000 00040f84 .L.|$x..$....... - 04b0 cb000000 488b8424 88000000 488b7c24 ....H..$....H.|$ - 04c0 784c8d0c c5000000 004e8d14 0f4f8d1c xL.......N...O.. - 04d0 0a4c8b6c 24884b8d 1c0b4a8d 2c0b4d85 .L.l$.K...J.,.M. - 04e0 ed0f8e8d 0000004c 8b7424f0 488b5424 .......L.t$.H.T$ - 04f0 d84c89f1 48f7d9c5 fb100d00 00000048 .L..H..........H - 0500 8d34ca31 c0eb5266 0f1f8400 00000000 .4.1..Rf........ - 0510 4883f903 0f8ecd01 0000c5fb 1007c5fb H............... - 0520 1102c4c1 7b1004c2 c5fb1142 08c4c17b ....{......B...{ - 0530 1004c3c5 fb114210 c5fb1004 c3c5fb11 ......B......... - 0540 421848ff c04883c7 084883c2 2048ffc1 B.H..H...H.. H.. - 0550 4883c628 4939c574 0d4939c6 7eb24883 H..(I9.t.I9.~.H. - 0560 f9037ede ebb4488b 44248848 c1e00548 ..~...H.D$.H...H - 0570 014424d8 48834424 f0044889 6c2478f6 .D$.H.D$..H.l$x. - 0580 84248000 0000020f 849b0000 00488b84 .$...........H.. - 0590 24880000 004c8b5c 247848c1 e0034c8b $....L.\$xH...L. - 05a0 4c24884d 8d040349 8d14004d 85c97e6d L$.M...I...M..~m - 05b0 4c8b5424 f0488b4c 24d84c89 d648f7de L.T$.H.L$.L..H.. - 05c0 c5fb100d 00000000 488d3cf1 31c0eb32 ........H.<.1..2 - 05d0 4883fe01 0f8e3901 0000c4c1 7b1004c3 H.....9.....{... - 05e0 c5fb1101 c4c17b10 04c0c5fb 11410848 ......{......A.H - 05f0 ffc04883 c11048ff c64883c7 184939c1 ..H...H..H...I9. - 0600 740d4939 c27ec948 83fe017e e2ebcb48 t.I9.~.H...~...H - 0610 8b442488 48c1e004 48014424 d8488344 .D$.H...H.D$.H.D - 0620 24f00248 89542478 f6842480 00000001 $..H.T$x..$..... - 0630 7471488b 7c248848 85ff7e67 4c8b4424 tqH.|$.H..~gL.D$ - 0640 f04c8b54 24d84c89 c248f7da 4c89c1c5 .L.T$.L..H..L... - 0650 fb100d00 0000004c 8b4c2478 498d34d2 .......L.L$xI.4. - 0660 31c048c1 e104eb24 0f1f8400 00000000 1.H....$........ - 0670 4885d27e 0cc4c17b 1004c1c4 c17b1104 H..~...{.....{.. - 0680 c248ffc0 48ffc248 39c77417 4939c07f .H..H..H9.t.I9.. - 0690 df75dd48 ffc0c5fb 110c0e48 ffc24839 .u.H.......H..H9 - 06a0 c775e948 81c49800 00005b5d 415c415d .u.H......[]A\A] - 06b0 415e31c0 415fc34d 89f84889 d14885f6 A^1.A_.M..H..H.. - 06c0 7e1c660f 1f440000 c4c17b10 004883c1 ~.f..D....{..H.. - 06d0 08c5fb11 41f84d01 c84839f9 75eac5fb ....A.M..H9.u... - 06e0 110fe979 fdffff49 89fc4989 d04885c9 ...y...I..I..H.. - 06f0 7e18c4c1 7b100424 4983c008 c4c17b11 ~...{..$I.....{. - 0700 40f84d01 cc4c39c6 75e8c5fb 110ee92f @.M..L9.u....../ - 0710 feffff75 0ac4c17b 1004c3c5 fb1101c5 ...u...{........ - 0720 fb110fe9 c7feffff ........ + 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t + 0010 24d048c1 fe024889 7c24d848 894c24f8 $.H...H.|$.H.L$. + 0020 48897424 e04885f6 0f8e1003 00004989 H.t$.H........I. + 0030 fd49c1fd 024889cb 4989fa4d 89ee49c1 .I...H..I..M..I. + 0040 e60548c1 e304488d 04494183 e2024c8d ..H...H..IA...L. + 0050 3ccd0000 000048c1 e00348c1 e1054889 <.....H...H...H. + 0060 5c24984c 895424a8 4c01f349 89fa4883 \$.L.T$.L..I..H. + 0070 e7fc4889 4c249048 895c24c0 498d0cb0 ..H.L$.H.\$.I... + 0080 4a8d1c30 4889fd4b 8d3c3748 895c24b8 J..0H..K.<7H.\$. + 0090 48894c24 a04c89eb 48897c24 c8488954 H.L$.L..H.|$.H.T + 00a0 24e84c89 4424f048 c1e30762 e1ff0810 $.L.D$.H...b.... + 00b0 05000000 0048895c 24b04183 e2014d89 .....H.\$.A...M. + 00c0 c34889d3 4989c466 0f1f8400 00000000 .H..I..f........ + 00d0 488b4424 98498d0c 1f488d3c 184e8d04 H.D$.I...H.<.N.. + 00e0 234d85ed 0f8ed603 00004889 de4c89c8 #M........H..L.. + 00f0 31d2e9cb 00000066 0f1f8400 00000000 1......f........ + 0100 0f8da300 0000c57b 103ec57b 105e08c5 .......{.>.{.^.. + 0110 fb107e10 c5fb105e 18c57b10 31c57b10 ..~....^..{.1.{. + 0120 5108c5fb 107110c5 fb105118 c57b102f Q....q....Q..{./ + 0130 c57b104f 08c5fb10 6f10c5fb 104f18c4 .{.O....o....O.. + 0140 417b1024 d0c4417b 1044d008 c4c17b10 A{.$..A{.D....{. + 0150 64d010c4 c17b1044 d018c57b 1138c57b d....{.D...{.8.{ + 0160 117008c5 7b116810 c57b1160 18c57b11 .p..{.h..{.`..{. + 0170 5820c57b 115028c5 7b114830 c57b1140 X .{.P(.{.H0.{.@ + 0180 38c5fb11 7840c5fb 117048c5 fb116850 8...x@...pH...hP + 0190 c5fb1160 58c5fb11 5860c5fb 115068c5 ...`X...X`...Ph. + 01a0 fb114870 c5fb1140 784883c2 044883c6 ..Hp...@xH...H.. + 01b0 204883c1 204883c7 204883e8 804839ea H.. H.. H...H9. + 01c0 74664939 d30f8535 ffffffc5 fb106e08 tfI9...5......n. + 01d0 c5fb1066 10c5fb10 5618c5fb 105910c5 ...f....V....Y.. + 01e0 fb104918 c5fb1047 1862e1ff 081100c5 ..I....G.b...... + 01f0 fb116820 62e1ff08 114005c5 fb116040 ..h b....@....`@ + 0200 c5fb1158 4862e1ff 0811400a c5fb1150 ...XHb....@....P + 0210 60c5fb11 4868c5fb 11407062 e1ff0811 `...Hh...@pb.... + 0220 400feb85 0f1f4000 488b4424 c84a8d14 @.....@.H.D$.J.. + 0230 33488d0c 03488b44 24c04c03 4c24b048 3H...H.D$.L.L$.H + 0240 8d3c0348 8b4424b8 4c8d0403 4889e848 .<.H.D$.L...H..H + 0250 837c24a8 00747849 39c30f84 40020000 .|$..txI9...@... + 0260 7d55c5fb 103ac5fb 105a08c5 fb1031c5 }U...:...Z....1. + 0270 fb105108 c5fb102f c5fb104f 08c4c17b ..Q..../...O...{ + 0280 1020c4c1 7b104008 c4c17b11 39c4c17b . ..{.@...{.9..{ + 0290 117108c4 c17b1169 10c4c17b 116118c4 .q...{.i...{.a.. + 02a0 c17b1159 20c4c17b 115128c4 c17b1149 .{.Y ..{.Q(..{.I + 02b0 30c4c17b 11413848 83c21048 83c11048 0..{.A8H...H...H + 02c0 83c71049 83c01049 83c14048 83c0024d ...I...I..@H...M + 02d0 85d27437 4c39d80f 84b30100 007e28c5 ..t7L9.......~(. + 02e0 fb101ac5 fb1011c5 fb100fc4 c17b1000 .............{.. + 02f0 c4c17b11 19c4c17b 115108c4 c17b1149 ..{....{.Q...{.I + 0300 10c4c17b 11411849 83c12049 83c30448 ...{.A.I.. I...H + 0310 035c2490 4c3b5c24 a00f85b1 fdffff48 .\$.L;\$.......H + 0320 8b5c24e0 488b4424 904c8b64 24e8480f .\$.H.D$.L.d$.H. + 0330 afc34c8b 4424f049 01c44d8d 0498f644 ..L.D$.I..M....D + 0340 24d0020f 84e50000 004c8b54 24f8488b $........L.T$.H. + 0350 7c24d849 c1e20348 d1ff4b8d 0c144885 |$.I...H..K...H. + 0360 ff0f8e72 010000c5 fb102500 00000048 ...r......%....H + 0370 8d343f4c 89ca31c0 eb40660f 1f440000 .4?L..1..@f..D.. + 0380 7d2bc4c1 7b101cc4 c4c17b10 4cc408c5 }+..{.....{.L... + 0390 fb1014c1 c5fb1044 c108c5fb 111ac5fb .......D........ + 03a0 115208c5 fb114a10 c5fb1142 184883c0 .R....J....B.H.. + 03b0 024883c2 204839c6 74274939 c075c1c4 .H.. H9.t'I9.u.. + 03c0 817b1044 c4084883 c002c5fb 1122c5fb .{.D..H......".. + 03d0 114210c5 fb116218 4883c220 4839c675 .B....b.H.. H9.u + 03e0 d94889f8 4889fa48 c1e00448 c1e20549 .H..H..H...H...I + 03f0 01c44901 d14801c8 4801fff6 4424d801 ..I..H..H...D$.. + 0400 74244939 f80f84bf 0000007d 15c4c17b t$I9.......}...{ + 0410 100c24c5 fb1000c4 c17b1109 c4c17b11 ..$......{....{. + 0420 41084983 c1104e8d 24114983 c002f644 A.I...N.$.I....D + 0430 24d00174 44488b54 24d84885 d27e3ac5 $..tDH.T$.H..~:. + 0440 fb100d00 00000031 c0eb1b0f 1f440000 .......1.....D.. + 0450 7d0cc4c1 7b1004c4 c4c17b11 04c148ff }...{.....{...H. + 0460 c04839c2 74134939 c075e548 ffc0c481 .H9.t.I9.u.H.... + 0470 7b110cc1 4839c275 ed5b5d41 5c415d41 {...H9.u.[]A\A]A + 0480 5e31c041 5fc3662e 0f1f8400 00000000 ^1.A_.f......... + 0490 62c1ff08 1101e96c feffff0f 1f440000 b......l.....D.. + 04a0 c5fb1042 0862c1ff 081101c4 c17b1141 ...B.b.......{.A + 04b0 2062c1ff 08114105 e9fafdff ff0f1f00 b....A......... + 04c0 4889da31 c0e985fd ffff488b 05000000 H..1......H..... + 04d0 00498901 e949ffff ff4889c8 31ffe918 .I...I...H..1... + 04e0 ffffff ... /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_COOPERLAKE.o (objdump) @@ -3,9 +3,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 28070000 00420e10 8f02420e ....(....B....B. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ed00103 99060a0e ..A.8..G........ - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0010 1b0c0708 90010000 44000000 1c000000 ........D....... + 0020 00000000 e3040000 00420e10 8f02420e .........B....B. + 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 + 0040 8606410e 38830703 6d040a0e 30410e28 ..A.8...m...0A.( + 0050 420e2042 0e18420e 10440e08 4b0b0000 B. B..B..D..K... /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_SKYLAKEX.o (disasm) @@ -9,387 +9,264 @@ push %r14 push %r13 push %r12 + mov %rdx,%r12 push %rbp push %rbx - sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi mov %rdi,-offset(%rsp) - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,-offset(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,-offset(%rsp) test %rsi,%rsi jle - mov %rsi,%r15 - mov %rcx,%rsi - lea offset(,%rcx,8),%rbx - lea (%rsi,%rsi,2),%rax - shl $something,%rcx - mov %rcx,-offset(%rsp) - lea offset(,%rax,8),%rcx - mov %rcx,offset(%rsp) - mov %rsi,%rcx - shl $something,%rcx - mov %rdx,%r10 - lea (%rsi,%rsi,4),%rdx - mov %rcx,(%rsp) - lea offset(,%rdx,8),%rcx - mov %rcx,offset(%rsp) - mov %rax,%rcx + mov %rdi,%r13 + sar $something,%r13 + mov %rcx,%rbx + mov %rdi,%r10 + mov %r13,%r14 + shl $something,%r14 + shl $something,%rbx + lea (%rcx,%rcx,2),%rax + and $something,%r10d + lea offset(,%rcx,8),%r15 shl $something,%rax - mov %rax,offset(%rsp) - imul $something,%rsi,%rax - shl $something,%rcx - mov %rcx,offset(%rsp) - imul $something,%rsi,%rcx - mov %rax,offset(%rsp) - imul $something,%rsi,%rax - mov %rcx,offset(%rsp) - mov %rsi,%rcx shl $something,%rcx - mov %rax,offset(%rsp) - imul $something,%rsi,%rax - mov %rcx,offset(%rsp) - lea (%rbx,%rsi,1),%rcx - shl $something,%rcx - mov %rcx,offset(%rsp) - mov %rax,offset(%rsp) - imul $something,%rsi,%rcx - mov %r15,%rax - shl $something,%rax - shl $something,%rdx - shl $something,%rsi - add %r8,%rax - shl $something,%rdi - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %rsi,-offset(%rsp) - mov %rax,offset(%rsp) - mov %rdi,offset(%rsp) - vmovsd offset(%rip),%xmm1 # - mov %rbx,%r11 - mov %r8,%rbx - nopl offset(%rax) - lea (%r11,%r10,1),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - mov %r10,%r9 - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov (%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - lea (%r10,%rax,1),%rcx - mov offset(%rsp),%rax - lea (%rax,%r10,1),%rbp - mov offset(%rsp),%rax - lea (%r10,%rax,1),%r12 - mov offset(%rsp),%rax - lea (%rax,%r10,1),%r13 - mov offset(%rsp),%rax - lea (%rax,%r10,1),%r14 - mov offset(%rsp),%rax - lea (%rax,%r10,1),%r15 - add -offset(%rsp),%r10 - cmpq $something,-offset(%rsp) - jle - mov -offset(%rsp),%rdx - mov %rbx,%rdi - neg %rdi + mov %rbx,-offset(%rsp) mov %r10,-offset(%rsp) - lea (%rdx,%rdi,8),%r8 - xor %eax,%eax - mov %rcx,%r10 - jmp - cmp $something,%rdi - jle - vmovsd (%r9),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - mov -offset(%rsp),%rsi - vmovsd %xmm0,offset(%rdx) - vmovsd (%rsi,%rax,8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,offset(%rdx) - vmovsd (%rcx,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd (%r10,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rbp,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd (%r12,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%r13,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd (%r14,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd (%r15,%rax,8),%xmm0 - vmovsd %xmm0,offset(%rdx) - inc %rax - add $something,%r9 - sub $something,%rdx - inc %rdi - add $something,%r8 - cmp %rax,-offset(%rsp) - je - cmp %rax,%rbx - jle - cmp $something,%rdi + add %r14,%rbx + mov %rdi,%r10 + and $something,%rdi + mov %rcx,-offset(%rsp) + mov %rbx,-offset(%rsp) + lea (%r8,%rsi,4),%rcx + lea (%rax,%r14,1),%rbx + mov %rdi,%rbp + lea (%r15,%r14,1),%rdi + mov %rbx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %r13,%rbx + mov %rdi,-offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_SKYLAKEX.o (objdump) @@ -2,118 +2,82 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ec980000 AWAVAUATUSH..... - 0010 004889b4 24800000 0048c1fe 0448897c .H..$....H...H.| - 0020 24884889 54247848 898c2488 0000004c $.H.T$xH..$....L - 0030 894424f0 4c894c24 d84889b4 24900000 .D$.L.L$.H..$... - 0040 004885f6 0f8e3e03 00004989 f74889ce .H....>...I..H.. - 0050 488d1ccd 00000000 488d0476 48c1e104 H.......H..vH... - 0060 48894c24 f8488d0c c5000000 0048894c H.L$.H.......H.L - 0070 24404889 f148c1e1 054989d2 488d14b6 $@H..H...I..H... - 0080 48890c24 488d0cd5 00000000 48894c24 H..$H.......H.L$ - 0090 484889c1 48c1e005 48894424 68486bc6 HH..H...H.D$hHk. - 00a0 6848c1e1 0448894c 2450486b ce384889 hH...H.L$PHk.8H. - 00b0 44242048 6bc67048 894c2408 4889f148 D$ Hk.pH.L$.H..H - 00c0 c1e10648 89442428 486bc678 48894c24 ...H.D$(Hk.xH.L$ - 00d0 10488d0c 3348c1e1 0348894c 24584889 .H..3H...H.L$XH. - 00e0 44243048 6bce584c 89f848c1 e00448c1 D$0Hk.XL..H...H. - 00f0 e20448c1 e6074c01 c048c1e7 07488954 ..H...L..H...H.T - 0100 24604889 4c241848 897424e8 48894424 $`H.L$.H.t$.H.D$ - 0110 3848897c 2470c5fb 100d0000 00004989 8H.|$p........I. - 0120 db4c89c3 0f1f4000 4b8d0413 48894424 .L....@.K...H.D$ - 0130 90488b44 24f84d89 d14c01d0 48894424 .H.D$.M..L..H.D$ - 0140 98488b44 24404c01 d0488944 24a0488b .H.D$@L..H.D$.H. - 0150 04244c01 d0488944 24a8488b 4424484c .$L..H.D$.H.D$HL - 0160 01d04889 4424b048 8b442450 4c01d048 ..H.D$.H.D$PL..H - 0170 894424b8 488b4424 084c01d0 48894424 .D$.H.D$.L..H.D$ - 0180 c0488b44 24104c01 d0488944 24c8488b .H.D$.L..H.D$.H. - 0190 4424584c 01d04889 4424d048 8b442460 D$XL..H.D$.H.D$` - 01a0 498d0c02 488b4424 184a8d2c 10488b44 I...H.D$.J.,.H.D - 01b0 24684d8d 2402488b 4424204e 8d2c1048 $hM.$.H.D$ N.,.H - 01c0 8b442428 4e8d3410 488b4424 304e8d3c .D$(N.4.H.D$0N.< - 01d0 104c0354 24e84883 7c248800 0f8e6d01 .L.T$.H.|$....m. - 01e0 0000488b 5424d848 89df48f7 df4c8954 ..H.T$.H..H..L.T - 01f0 24e04c8d 04fa31c0 4989cae9 f9000000 $.L...1.I....... - 0200 4883ff0f 0f8e0601 0000c4c1 7b100148 H...........{..H - 0210 8b4c2490 c5fb1102 c5fb1004 c1488b74 .L$..........H.t - 0220 2498c5fb 114208c5 fb1004c6 488b4c24 $....B......H.L$ - 0230 a0c5fb11 4210c5fb 1004c148 8b7424a8 ....B......H.t$. - 0240 c5fb1142 18c5fb10 04c6488b 4c24b0c5 ...B......H.L$.. - 0250 fb114220 c5fb1004 c1488b74 24b8c5fb ..B .....H.t$... - 0260 114228c5 fb1004c6 488b4c24 c0c5fb11 .B(.....H.L$.... - 0270 4230c5fb 1004c148 8b7424c8 c5fb1142 B0.....H.t$....B - 0280 38c5fb10 04c6488b 4c24d0c5 fb114240 8.....H.L$....B@ - 0290 c5fb1004 c1c5fb11 4248c4c1 7b1004c2 ........BH..{... - 02a0 c5fb1142 50c5fb10 44c500c5 fb114258 ...BP...D.....BX - 02b0 c4c17b10 04c4c5fb 114260c4 c17b1044 ..{......B`..{.D - 02c0 c500c5fb 114268c4 c17b1004 c6c5fb11 .....Bh..{...... - 02d0 4270c4c1 7b1004c7 c5fb1142 7848ffc0 Bp..{......BxH.. - 02e0 4983c108 4883ea80 48ffc749 81c08800 I...H...H..I.... - 02f0 00004839 44248874 474839c3 0f8efefe ..H9D$.tGH9..... - 0300 ffff4883 ff0f7ed5 e9fdfeff ff0f1f00 ..H...~......... - 0310 4c89ce48 89d14885 ff7e1a0f 1f440000 L..H..H..~...D.. - 0320 c5fb1006 4883c108 c5fb1141 f84c01de ....H......A.L.. - 0330 4c39c175 ebc4c17b 1108eba1 0f1f4000 L9.u...{......@. - 0340 488b7c24 704c8b54 24e04801 7c24d848 H.|$pL.T$.H.|$.H - 0350 83c31048 3b5c2438 0f85cafd ffff488b ...H;\$8......H. - 0360 9c249000 0000488b 4424e848 0fafc348 .$....H.D$.H...H - 0370 01442478 4889d848 8b5c24f0 48c1e004 .D$xH..H.\$.H... - 0380 4801d848 894424f0 f6842480 00000008 H..H.D$...$..... - 0390 0f841001 0000488b 84248800 0000488b ......H..$....H. - 03a0 4c24784c 8d0cc500 0000004e 8d34094f L$xL.......N.4.O - 03b0 8d2c0e4f 8d640d00 4b8d2c0c 4e8d540d .,.O.d..K.,.N.T. - 03c0 004f8d1c 0a4b8d1c 0b48837c 2488004e .O...K...H.|$..N - 03d0 8d3c0b0f 8ec20000 00488b74 24f0488b .<.......H.t$.H. - 03e0 5424d848 f7de4c89 7c2490c5 fb100d00 T$.H..L.|$...... - 03f0 00000048 8d3cf231 c04989cf eb7b6690 ...H.<.1.I...{f. - 0400 4883fe07 0f8ead02 0000c4c1 7b1007c5 H...........{... - 0410 fb1102c4 c17b1004 c6c5fb11 4208c4c1 .....{......B... - 0420 7b1044c5 00c5fb11 4210c4c1 7b1004c4 {.D.....B...{... - 0430 c5fb1142 18c5fb10 44c500c5 fb114220 ...B....D.....B - 0440 c4c17b10 04c2c5fb 114228c4 c17b1004 ..{......B(..{.. - 0450 c3c5fb11 4230c5fb 1004c3c5 fb114238 ....B0........B8 - 0460 48ffc049 83c70848 83c24048 ffc64883 H..I...H..@H..H. - 0470 c7484839 44248874 0f483944 24f07e80 .HH9D$.t.H9D$.~. - 0480 4883fe07 7edaeb82 488b4424 884c8b7c H...~...H.D$.L.| - 0490 249048c1 e0064801 4424d848 834424f0 $.H...H.D$.H.D$. - 04a0 084c897c 2478f684 24800000 00040f84 .L.|$x..$....... - 04b0 cb000000 488b8424 88000000 488b7c24 ....H..$....H.|$ - 04c0 784c8d0c c5000000 004e8d14 0f4f8d1c xL.......N...O.. - 04d0 0a4c8b6c 24884b8d 1c0b4a8d 2c0b4d85 .L.l$.K...J.,.M. - 04e0 ed0f8e8d 0000004c 8b7424f0 488b5424 .......L.t$.H.T$ - 04f0 d84c89f1 48f7d9c5 fb100d00 00000048 .L..H..........H - 0500 8d34ca31 c0eb5266 0f1f8400 00000000 .4.1..Rf........ - 0510 4883f903 0f8ecd01 0000c5fb 1007c5fb H............... - 0520 1102c4c1 7b1004c2 c5fb1142 08c4c17b ....{......B...{ - 0530 1004c3c5 fb114210 c5fb1004 c3c5fb11 ......B......... - 0540 421848ff c04883c7 084883c2 2048ffc1 B.H..H...H.. H.. - 0550 4883c628 4939c574 0d4939c6 7eb24883 H..(I9.t.I9.~.H. - 0560 f9037ede ebb4488b 44248848 c1e00548 ..~...H.D$.H...H - 0570 014424d8 48834424 f0044889 6c2478f6 .D$.H.D$..H.l$x. - 0580 84248000 0000020f 849b0000 00488b84 .$...........H.. - 0590 24880000 004c8b5c 247848c1 e0034c8b $....L.\$xH...L. - 05a0 4c24884d 8d040349 8d14004d 85c97e6d L$.M...I...M..~m - 05b0 4c8b5424 f0488b4c 24d84c89 d648f7de L.T$.H.L$.L..H.. - 05c0 c5fb100d 00000000 488d3cf1 31c0eb32 ........H.<.1..2 - 05d0 4883fe01 0f8e3901 0000c4c1 7b1004c3 H.....9.....{... - 05e0 c5fb1101 c4c17b10 04c0c5fb 11410848 ......{......A.H - 05f0 ffc04883 c11048ff c64883c7 184939c1 ..H...H..H...I9. - 0600 740d4939 c27ec948 83fe017e e2ebcb48 t.I9.~.H...~...H - 0610 8b442488 48c1e004 48014424 d8488344 .D$.H...H.D$.H.D - 0620 24f00248 89542478 f6842480 00000001 $..H.T$x..$..... - 0630 7471488b 7c248848 85ff7e67 4c8b4424 tqH.|$.H..~gL.D$ - 0640 f04c8b54 24d84c89 c248f7da 4c89c1c5 .L.T$.L..H..L... - 0650 fb100d00 0000004c 8b4c2478 498d34d2 .......L.L$xI.4. - 0660 31c048c1 e104eb24 0f1f8400 00000000 1.H....$........ - 0670 4885d27e 0cc4c17b 1004c1c4 c17b1104 H..~...{.....{.. - 0680 c248ffc0 48ffc248 39c77417 4939c07f .H..H..H9.t.I9.. - 0690 df75dd48 ffc0c5fb 110c0e48 ffc24839 .u.H.......H..H9 - 06a0 c775e948 81c49800 00005b5d 415c415d .u.H......[]A\A] - 06b0 415e31c0 415fc34d 89f84889 d14885f6 A^1.A_.M..H..H.. - 06c0 7e1c660f 1f440000 c4c17b10 004883c1 ~.f..D....{..H.. - 06d0 08c5fb11 41f84d01 c84839f9 75eac5fb ....A.M..H9.u... - 06e0 110fe979 fdffff49 89fc4989 d04885c9 ...y...I..I..H.. - 06f0 7e18c4c1 7b100424 4983c008 c4c17b11 ~...{..$I.....{. - 0700 40f84d01 cc4c39c6 75e8c5fb 110ee92f @.M..L9.u....../ - 0710 feffff75 0ac4c17b 1004c3c5 fb1101c5 ...u...{........ - 0720 fb110fe9 c7feffff ........ + 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t + 0010 24d048c1 fe024889 7c24d848 894c24f8 $.H...H.|$.H.L$. + 0020 48897424 e04885f6 0f8e1003 00004989 H.t$.H........I. + 0030 fd49c1fd 024889cb 4989fa4d 89ee49c1 .I...H..I..M..I. + 0040 e60548c1 e304488d 04494183 e2024c8d ..H...H..IA...L. + 0050 3ccd0000 000048c1 e00348c1 e1054889 <.....H...H...H. + 0060 5c24984c 895424a8 4c01f349 89fa4883 \$.L.T$.L..I..H. + 0070 e7fc4889 4c249048 895c24c0 498d0cb0 ..H.L$.H.\$.I... + 0080 4a8d1c30 4889fd4b 8d3c3748 895c24b8 J..0H..K.<7H.\$. + 0090 48894c24 a04c89eb 48897c24 c8488954 H.L$.L..H.|$.H.T + 00a0 24e84c89 4424f048 c1e30762 e1ff0810 $.L.D$.H...b.... + 00b0 05000000 0048895c 24b04183 e2014d89 .....H.\$.A...M. + 00c0 c34889d3 4989c466 0f1f8400 00000000 .H..I..f........ + 00d0 488b4424 98498d0c 1f488d3c 184e8d04 H.D$.I...H.<.N.. + 00e0 234d85ed 0f8ed603 00004889 de4c89c8 #M........H..L.. + 00f0 31d2e9cb 00000066 0f1f8400 00000000 1......f........ + 0100 0f8da300 0000c57b 103ec57b 105e08c5 .......{.>.{.^.. + 0110 fb107e10 c5fb105e 18c57b10 31c57b10 ..~....^..{.1.{. + 0120 5108c5fb 107110c5 fb105118 c57b102f Q....q....Q..{./ + 0130 c57b104f 08c5fb10 6f10c5fb 104f18c4 .{.O....o....O.. + 0140 417b1024 d0c4417b 1044d008 c4c17b10 A{.$..A{.D....{. + 0150 64d010c4 c17b1044 d018c57b 1138c57b d....{.D...{.8.{ + 0160 117008c5 7b116810 c57b1160 18c57b11 .p..{.h..{.`..{. + 0170 5820c57b 115028c5 7b114830 c57b1140 X .{.P(.{.H0.{.@ + 0180 38c5fb11 7840c5fb 117048c5 fb116850 8...x@...pH...hP + 0190 c5fb1160 58c5fb11 5860c5fb 115068c5 ...`X...X`...Ph. + 01a0 fb114870 c5fb1140 784883c2 044883c6 ..Hp...@xH...H.. + 01b0 204883c1 204883c7 204883e8 804839ea H.. H.. H...H9. + 01c0 74664939 d30f8535 ffffffc5 fb106e08 tfI9...5......n. + 01d0 c5fb1066 10c5fb10 5618c5fb 105910c5 ...f....V....Y.. + 01e0 fb104918 c5fb1047 1862e1ff 081100c5 ..I....G.b...... + 01f0 fb116820 62e1ff08 114005c5 fb116040 ..h b....@....`@ + 0200 c5fb1158 4862e1ff 0811400a c5fb1150 ...XHb....@....P + 0210 60c5fb11 4868c5fb 11407062 e1ff0811 `...Hh...@pb.... + 0220 400feb85 0f1f4000 488b4424 c84a8d14 @.....@.H.D$.J.. + 0230 33488d0c 03488b44 24c04c03 4c24b048 3H...H.D$.L.L$.H + 0240 8d3c0348 8b4424b8 4c8d0403 4889e848 .<.H.D$.L...H..H + 0250 837c24a8 00747849 39c30f84 40020000 .|$..txI9...@... + 0260 7d55c5fb 103ac5fb 105a08c5 fb1031c5 }U...:...Z....1. + 0270 fb105108 c5fb102f c5fb104f 08c4c17b ..Q..../...O...{ + 0280 1020c4c1 7b104008 c4c17b11 39c4c17b . ..{.@...{.9..{ + 0290 117108c4 c17b1169 10c4c17b 116118c4 .q...{.i...{.a.. + 02a0 c17b1159 20c4c17b 115128c4 c17b1149 .{.Y ..{.Q(..{.I + 02b0 30c4c17b 11413848 83c21048 83c11048 0..{.A8H...H...H + 02c0 83c71049 83c01049 83c14048 83c0024d ...I...I..@H...M + 02d0 85d27437 4c39d80f 84b30100 007e28c5 ..t7L9.......~(. + 02e0 fb101ac5 fb1011c5 fb100fc4 c17b1000 .............{.. + 02f0 c4c17b11 19c4c17b 115108c4 c17b1149 ..{....{.Q...{.I + 0300 10c4c17b 11411849 83c12049 83c30448 ...{.A.I.. I...H + 0310 035c2490 4c3b5c24 a00f85b1 fdffff48 .\$.L;\$.......H + 0320 8b5c24e0 488b4424 904c8b64 24e8480f .\$.H.D$.L.d$.H. + 0330 afc34c8b 4424f049 01c44d8d 0498f644 ..L.D$.I..M....D + 0340 24d0020f 84e50000 004c8b54 24f8488b $........L.T$.H. + 0350 7c24d849 c1e20348 d1ff4b8d 0c144885 |$.I...H..K...H. + 0360 ff0f8e72 010000c5 fb102500 00000048 ...r......%....H + 0370 8d343f4c 89ca31c0 eb40660f 1f440000 .4?L..1..@f..D.. + 0380 7d2bc4c1 7b101cc4 c4c17b10 4cc408c5 }+..{.....{.L... + 0390 fb1014c1 c5fb1044 c108c5fb 111ac5fb .......D........ + 03a0 115208c5 fb114a10 c5fb1142 184883c0 .R....J....B.H.. + 03b0 024883c2 204839c6 74274939 c075c1c4 .H.. H9.t'I9.u.. + 03c0 817b1044 c4084883 c002c5fb 1122c5fb .{.D..H......".. + 03d0 114210c5 fb116218 4883c220 4839c675 .B....b.H.. H9.u + 03e0 d94889f8 4889fa48 c1e00448 c1e20549 .H..H..H...H...I + 03f0 01c44901 d14801c8 4801fff6 4424d801 ..I..H..H...D$.. + 0400 74244939 f80f84bf 0000007d 15c4c17b t$I9.......}...{ + 0410 100c24c5 fb1000c4 c17b1109 c4c17b11 ..$......{....{. + 0420 41084983 c1104e8d 24114983 c002f644 A.I...N.$.I....D + 0430 24d00174 44488b54 24d84885 d27e3ac5 $..tDH.T$.H..~:. + 0440 fb100d00 00000031 c0eb1b0f 1f440000 .......1.....D.. + 0450 7d0cc4c1 7b1004c4 c4c17b11 04c148ff }...{.....{...H. + 0460 c04839c2 74134939 c075e548 ffc0c481 .H9.t.I9.u.H.... + 0470 7b110cc1 4839c275 ed5b5d41 5c415d41 {...H9.u.[]A\A]A + 0480 5e31c041 5fc3662e 0f1f8400 00000000 ^1.A_.f......... + 0490 62c1ff08 1101e96c feffff0f 1f440000 b......l.....D.. + 04a0 c5fb1042 0862c1ff 081101c4 c17b1141 ...B.b.......{.A + 04b0 2062c1ff 08114105 e9fafdff ff0f1f00 b....A......... + 04c0 4889da31 c0e985fd ffff488b 05000000 H..1......H..... + 04d0 00498901 e949ffff ff4889c8 31ffe918 .I...I...H..1... + 04e0 ffffff ... /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ilnucopy_SKYLAKEX.o (objdump) @@ -3,9 +3,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 28070000 00420e10 8f02420e ....(....B....B. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ed00103 99060a0e ..A.8..G........ - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0010 1b0c0708 90010000 44000000 1c000000 ........D....... + 0020 00000000 e3040000 00420e10 8f02420e .........B....B. + 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 + 0040 8606410e 38830703 6d040a0e 30410e28 ..A.8...m...0A.( + 0050 420e2042 0e18420e 10440e08 4b0b0000 B. B..B..D..K... /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_COOPERLAKE.o (disasm) @@ -16,280 +16,287 @@ sar $something,%rsi mov %rdi,-offset(%rsp) mov %rcx,-offset(%rsp) + mov %r8,-offset(%rsp) mov %rsi,-offset(%rsp) test %rsi,%rsi jle - mov %r8,%r15 - mov %rsi,%rax - neg %r15 - shl $something,%rax - add %r8,%rax - shl $something,%r15 + mov %rcx,%rbx + lea (%rcx,%rcx,2),%rax + shl $something,%rbx + lea offset(,%rax,8),%rdx + mov %rbx,%r10 + mov %rdi,%rax mov %rdi,%rbx + sar $something,%rax + and $something,%ebx + mov %rax,%r13 + mov %rbx,-offset(%rsp) + lea (%r8,%rsi,4),%rbx mov %rax,-offset(%rsp) - mov %rdx,-offset(%rsp) - lea (%rdx,%r15,1),%rax - mov %rdi,%rbp + imul %r10,%r13 + mov %rbx,-offset(%rsp) + and $something,%edi + lea offset(,%rax,4),%rbx + shl $something,%rax + mov %rdi,-offset(%rsp) mov %rax,-offset(%rsp) - lea offset(,%rcx,8),%r13 - mov %rdi,%rax - shl $something,%rbx - vmovsd offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%rbp - mov %r8,%rdi - lea offset(%r13),%r14 - mov %rbx,%r12 - mov %rax,%r8 - nopw offset(%rax,%rax,1) - mov -offset(%rsp),%rax - sub %r15,%rax - test %r8,%r8 + mov %rcx,%r15 + vmovsd offset(%rip),%xmm16 # + mov %r12,-offset(%rsp) + add %r12,%r13 + mov %r12,%rbp + lea offset(,%rcx,8),%r14 + shl $something,%r15 + mov %r8,%r11 + mov %rdx,%r12 + nopl offset(%rax,%rax,1) + cmpq $something,-offset(%rsp) + lea (%r14,%rbp,1),%rdx + lea (%r15,%rbp,1),%rsi + lea offset(%rbp,%r12,1),%rdi jle - mov %rdi,%rsi - mov $something,%r10d - neg %rsi - lea (%rax,%r15,1),%rbx - lea (%r9,%r15,1),%r11 - sub %rdi,%r10 - mov %r9,%rdx + mov %rbp,%rcx + mov %r9,%rax + xor %r8d,%r8d jmp - nopl (%rax) - cmp $something,%rsi + nop jle - inc %rsi - sub $something,%rdx - add %r13,%rax - add %r14,%rbx - add $something,%r11 - inc %r10 - cmp %rbp,%rsi + vmovsd (%rcx),%xmm15 + vmovsd offset(%rcx),%xmm14 + vmovsd offset(%rcx),%xmm13 + vmovsd offset(%rcx),%xmm12 + vmovsd (%rdx),%xmm11 + vmovsd offset(%rdx),%xmm10 + vmovsd offset(%rdx),%xmm9 + vmovsd offset(%rdx),%xmm8 + vmovsd (%rsi),%xmm7 + vmovsd offset(%rsi),%xmm6 + vmovsd offset(%rsi),%xmm5 + vmovsd offset(%rsi),%xmm4 + vmovsd (%rdi),%xmm3 + vmovsd offset(%rdi),%xmm2 + vmovsd offset(%rdi),%xmm1 + vmovsd offset(%rdi),%xmm0 + vmovsd %xmm15,(%rax) + vmovsd %xmm14,offset(%rax) + vmovsd %xmm13,offset(%rax) + vmovsd %xmm12,offset(%rax) + vmovsd %xmm11,offset(%rax) + vmovsd %xmm10,offset(%rax) + vmovsd %xmm9,offset(%rax) + vmovsd %xmm8,offset(%rax) + vmovsd %xmm7,offset(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + add $something,%r8 + add %r10,%rcx + add %r10,%rdx + add %r10,%rsi + add %r10,%rdi + sub $something,%rax + cmp %rbx,%r8 je - lea (%rsi,%rdi,1),%rcx - cmp %rcx,%rdi - jle - test %rsi,%rsi - jns - vmovsd (%rax),%xmm0 - vmovsd %xmm0,(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - jmp - nopl offset(%rax,%rax,1) - vdivsd (%rbx),%xmm1,%xmm0 - mov %r10,%rcx - vmovsd %xmm0,(%r11) - cmp $something,%r10 - je - cs nopw offset(%rax,%rax,1) - vmovsd (%rax,%rcx,8),%xmm0 - vmovsd %xmm0,(%rdx,%rcx,8) - inc %rcx - cmp $something,%rcx + cmp %r8,%r11 jne + vmovsd offset(%rdx),%xmm2 + vmovsd offset(%rsi),%xmm1 + vmovsd offset(%rdi),%xmm0 + vdivsd %xmm2,%xmm16,%xmm2 + vmovsd offset(%rcx),%xmm8 + vmovsd offset(%rcx),%xmm7 + vmovsd offset(%rcx),%xmm6 + vmovsd offset(%rdx),%xmm5 + vmovsd offset(%rdx),%xmm4 + vmovsd offset(%rsi),%xmm3 + vdivsd (%rcx),%xmm16,%xmm9 + vmovsd %xmm8,offset(%rax) + vmovsd %xmm9,(%rax) + vmovsd %xmm7,offset(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vdivsd %xmm1,%xmm16,%xmm1 /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_COOPERLAKE.o (objdump) @@ -3,94 +3,88 @@ Contents of section .text: 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t - 0010 24d048c1 fe044889 7c24d848 894c24e0 $.H...H.|$.H.L$. - 0020 48897424 e84885f6 0f8eef01 00004d89 H.t$.H........M. - 0030 c74889f0 49f7df48 c1e0044c 01c049c1 .H..I..H...L..I. - 0040 e7034889 fb488944 24c04889 5424f04a ..H..H.D$.H.T$.J - 0050 8d043a48 89fd4889 4424c84c 8d2ccd00 ..:H..H.D$.L.,.. - 0060 00000048 89f848c1 e307c5fb 100d0000 ...H..H......... - 0070 00004c89 4424f84c 29c54c89 c74d8d75 ..L.D$.L).L..M.u - 0080 084989dc 4989c066 0f1f8400 00000000 .I..I..f........ - 0090 488b4424 c84c29f8 4d85c00f 8e420100 H.D$.L).M....B.. - 00a0 004889fe 41ba0100 000048f7 de4a8d1c .H..A.....H..J.. - 00b0 384f8d1c 394929fa 4c89caeb 2d0f1f00 8O..9I).L...-... - 00c0 4883fe0f 0f8ed600 000048ff c64883ea H.........H..H.. - 00d0 804c01e8 4c01f349 81c38800 000049ff .L..L..I......I. - 00e0 c24839ee 0f84f600 0000488d 0c3e4839 .H9.......H..>H9 - 00f0 cf7ecd48 85f679d2 c5fb1000 c5fb1102 .~.H..y......... - 0100 c5fb1040 08c5fb11 4208c5fb 104010c5 ...@....B....@.. - 0110 fb114210 c5fb1040 18c5fb11 4218c5fb ..B....@....B... - 0120 104020c5 fb114220 c5fb1040 28c5fb11 .@ ...B ...@(... - 0130 4228c5fb 104030c5 fb114230 c5fb1040 B(...@0...B0...@ - 0140 38c5fb11 4238c5fb 104040c5 fb114240 8...B8...@@...B@ - 0150 c5fb1040 48c5fb11 4248c5fb 104050c5 ...@H...BH...@P. - 0160 fb114250 c5fb1040 58c5fb11 4258c5fb ..BP...@X...BX.. - 0170 104060c5 fb114260 c5fb1040 68c5fb11 .@`...B`...@h... - 0180 4268c5fb 104070c5 fb114270 c5fb1040 Bh...@p...Bp...@ - 0190 78c5fb11 4278e92f ffffff0f 1f440000 x...Bx./.....D.. - 01a0 c5f35e03 4c89d1c4 c17b1103 4983fa10 ..^.L....{..I... - 01b0 0f8414ff ffff662e 0f1f8400 00000000 ......f......... - 01c0 c5fb1004 c8c5fb11 04ca48ff c14883f9 ..........H..H.. - 01d0 1075ede9 f2feffff 0f1f8400 00000000 .u.............. - 01e0 4d01e148 83c71048 83ed1049 83c78048 M..H...H...I...H - 01f0 3b7c24c0 0f8596fe ffff488b 5c24e84c ;|$.......H.\$.L - 0200 8b6424f0 4889d848 c1e0074c 8b4424f8 .d$.H..H...L.D$. - 0210 4901c448 89d848c1 e0044901 c0f64424 I..H..H...I...D$ - 0220 d0080f84 ff000000 488b4424 d84d8d6c ........H.D$.M.l - 0230 24404885 c00f8ee5 00000048 8b5c24e0 $@H........H.\$. - 0240 4c89c148 f7d94c8d 1cdd0000 0000488d L..H..L.......H. - 0250 3ccd0000 00004c29 c0be0100 00004d8d <.....L)......M. - 0260 143c4889 c3c5fb10 0d000000 00498d6b .J...I9.~.H..y - 03c0 d9c4c17b 100424c5 fb1101c4 c17b1044 ...{..$......{.D - 03d0 2408c5fb 114108c4 c17b1044 2410c5fb $....A...{.D$... - 03e0 114110c4 c17b1044 2418c5fb 114118eb .A...{.D$....A.. - 03f0 a9488b44 24d848c1 e0054901 c14983c0 .H.D$.H...I..I.. - 0400 044d89ec f64424d0 020f84b0 00000048 .M...D$........H - 0410 8b7c24d8 498d6c24 104885ff 0f8e9600 .|$.I.l$.H...... - 0420 0000488b 4424e04c 29c74c8d 14c50000 ..H.D$.L).L..... - 0430 00004c89 c048f7d8 488d0cc5 00000000 ..L..H..H....... - 0440 498d340c c5fb100d 00000000 498d5a08 I.4.........I.Z. - 0450 4c01c949 89fb4c89 caeb360f 1f440000 L..I..L...6..D.. - 0460 4885c079 16c4c17b 100424c5 fb1102c4 H..y...{..$..... - 0470 c17b1044 2408c5fb 11420848 ffc04883 .{.D$....B.H..H. - 0480 c2104d01 d44801de 4883c118 4c39d874 ..M..H..H...L9.t - 0490 1b498d3c 004939f8 7fc64883 f8017fdb .I.<.I9...H..... - 04a0 c5f35e06 c5fb1101 75c5ebcf 488b4424 ..^.....u...H.D$ - 04b0 d848c1e0 044901c1 4983c002 4989ecf6 .H...I..I...I... - 04c0 4424d001 75735b5d 415c415d 415e31c0 D$..us[]A\A]A^1. - 04d0 415fc3c4 c1735e02 4889f2c5 fb110748 A_...s^.H......H - 04e0 83fe080f 84a1fdff ff0f1f80 00000000 ................ - 04f0 c4c17b10 04d4c5fb 1104d048 ffc24883 ..{........H..H. - 0500 fa0875ec e981fdff ffc4c173 5e024889 ..u........s^.H. - 0510 f0c5fb11 074883fe 040f847b feffff90 .....H.....{.... - 0520 c4c17b10 04c4c5fb 1104c148 ffc04883 ..{........H..H. - 0530 f80475ec e961feff ff488b5c 24d84885 ..u..a...H.\$.H. - 0540 db7e8348 8b4c24e0 4c89c248 f7da4c8d .~.H.L$.L..H..L. - 0550 14d50000 000048c1 e1034d89 c34b8d34 ......H...M..K.4 - 0560 14c5fb10 0d000000 00488d79 084d01ca .........H.y.M.. - 0570 31c049c1 e304eb29 0f1f8400 00000000 1.I....)........ - 0580 750ac5f3 5e06c481 7b11041a 48ffc049 u...^...{...H..I - 0590 01cc48ff c24801fe 4839c30f 8425ffff ..H..H..H9...%.. - 05a0 ff4939c0 7eda4885 d279e1c4 c17b1004 .I9.~.H..y...{.. - 05b0 24c4c17b 1104c1eb d3 $..{..... + 0010 24d848c1 fe024889 7c24e048 894c24f0 $.H...H.|$.H.L$. + 0020 4c894424 d0488974 24e84885 f60f8ef1 L.D$.H.t$.H..... + 0030 02000048 89cb488d 044948c1 e305488d ...H..H..IH...H. + 0040 14c50000 00004989 da4889f8 4889fb48 ......I..H..H..H + 0050 c1f80283 e3024989 c548895c 24b8498d ......I..H.\$.I. + 0060 1cb04889 4424b04d 0fafea48 895c24a8 ..H.D$.M...H.\$. + 0070 83e70148 8d1c8500 00000048 c1e00748 ...H.......H...H + 0080 897c24c0 48894424 c84989cf 62e1ff08 .|$.H.D$.I..b... + 0090 10050000 00004c89 6424f84d 01e54c89 ......L.d$.M..L. + 00a0 e54c8d34 cd000000 0049c1e7 044d89c3 .L.4.....I...M.. + 00b0 4989d40f 1f440000 48837c24 b000498d I....D..H.|$..I. + 00c0 142e498d 342f4a8d 7c25000f 8e570400 ..I.4/J.|%...W.. + 00d0 004889e9 4c89c845 31c0e9bf 00000090 .H..L..E1....... + 00e0 0f8e9b00 0000c57b 1039c57b 107108c5 .......{.9.{.q.. + 00f0 7b106910 c57b1061 18c57b10 1ac57b10 {.i..{.a..{...{. + 0100 5208c57b 104a10c5 7b104218 c5fb103e R..{.J..{.B....> + 0110 c5fb1076 08c5fb10 6e10c5fb 106618c5 ...v....n....f.. + 0120 fb101fc5 fb105708 c5fb104f 10c5fb10 ......W....O.... + 0130 4718c57b 1138c57b 117008c5 7b116810 G..{.8.{.p..{.h. + 0140 c57b1160 18c57b11 5820c57b 115028c5 .{.`..{.X .{.P(. + 0150 7b114830 c57b1140 38c5fb11 7840c5fb {.H0.{.@8...x@.. + 0160 117048c5 fb116850 c5fb1160 58c5fb11 .pH...hP...`X... + 0170 5860c5fb 115068c5 fb114870 c5fb1140 X`...Ph...Hp...@ + 0180 784983c0 044c01d1 4c01d24c 01d64c01 xI...L..L..L..L. + 0190 d74883e8 804939d8 0f848a00 00004d39 .H...I9.......M9 + 01a0 c30f8539 ffffffc5 fb105208 c5fb104e ...9......R....N + 01b0 10c5fb10 471862f1 ff005ed2 c57b1041 ....G.b...^..{.A + 01c0 08c5fb10 7910c5fb 107118c5 fb106a10 ....y....q....j. + 01d0 c5fb1062 18c5fb10 5e186271 ff005e09 ...b....^.bq..^. + 01e0 c57b1140 08c57b11 08c5fb11 7810c5fb .{.@..{.....x... + 01f0 117018c5 fb116830 c5fb1160 38c5fb11 .p....h0...`8... + 0200 585862f1 ff005ec9 c5fb1150 2862f1ff XXb...^....P(b.. + 0210 005ec0c5 fb114850 c5fb1140 78e95fff .^....HP...@x._. + 0220 ffff660f 1f440000 4c89e84b 8d142e4c ..f..D..L..K...L + 0230 034c24c8 4889d948 837c24b8 00746b49 .L$.H..H.|$..tkI + 0240 39cb0f84 c8010000 7e55c5fb 1038c5fb 9.......~U...8.. + 0250 107008c5 fb106810 c5fb1060 18c5fb10 .p....h....`.... + 0260 1ac5fb10 5208c5fb 104a10c5 fb104218 ....R....J....B. + 0270 c4c17b11 39c4c17b 117108c4 c17b1169 ..{.9..{.q...{.i + 0280 10c4c17b 116118c4 c17b1159 20c4c17b ...{.a...{.Y ..{ + 0290 115128c4 c17b1149 30c4c17b 1141384c .Q(..{.I0..{.A8L + 02a0 01f84983 c1404883 c1024883 7c24c000 ..I..@H...H.|$.. + 02b0 74394c39 d90f841d 0100007d 2ac5fb10 t9L9.......}*... + 02c0 18c5fb10 5008c5fb 104810c5 fb104018 ....P....H....@. + 02d0 c4c17b11 19c4c17b 115108c4 c17b1149 ..{....{.Q...{.I + 02e0 10c4c17b 11411849 83c12049 83c30448 ...{.A.I.. I...H + 02f0 83c52049 83c5204c 395c24a8 0f85b6fd .. I.. L9\$..... + 0300 ffff488b 5c24e84c 8b6424f8 4889d848 ..H.\$.L.d$.H..H + 0310 c1e00549 01c4488b 4424d048 8d049848 ...I..H.D$.H...H + 0320 894424d0 f64424d8 020f8483 0100004c .D$..D$........L + 0330 8b5424e0 488b4424 f049d1fa 498d34c4 .T$.H.D$.I..I.4. + 0340 4d85d20f 8eff0100 0048c1e0 044889c7 M........H...H.. + 0350 c5fb1025 00000000 4c8b5c24 d04f8d04 ...%....L.\$.O.. + 0360 124c89e1 4c89c831 d2eb430f 1f440000 .L..L..1..C..D.. + 0370 7e25c5fb 1019c5fb 105108c5 fb100ec5 ~%.......Q...... + 0380 fb104608 c5fb1118 c5fb1150 08c5fb11 ..F........P.... + 0390 4810c5fb 11401848 83c20248 01f94801 H....@.H...H..H. + 03a0 fe4883c0 204939d0 0f84ba00 00004939 .H.. I9.......I9 + 03b0 d375bdc5 fb104608 c5fb1049 08c5db5e .u....F....I...^ + 03c0 c0c5db5e 11c5fb11 4808c5fb 1110c5fb ...^....H....... + 03d0 114018eb c20f1f00 c5fb1050 08c5fb10 .@.........P.... + 03e0 4810c5fb 10401862 f1ff005e 18c4c17b H....@.b...^...{ + 03f0 115108c4 c17b1119 c4c17b11 4910c4c1 .Q...{....{.I... + 0400 7b114118 e9defeff ff0f1f80 00000000 {.A............. + 0410 c5fb1042 08c5fb10 680862f1 ff005ec0 ...B....h.b...^. + 0420 c5fb1060 10c5fb10 5818c5fb 105210c5 ...`....X....R.. + 0430 fb104a18 62f1ff00 5e30c4c1 7b116908 ..J.b...^0..{.i. + 0440 c4c17b11 31c4c17b 116110c4 c17b1159 ..{.1..{.a...{.Y + 0450 18c4c17b 115130c4 c17b1149 38c4c17b ...{.Q0..{.I8..{ + 0460 114128e9 37feffff 490faffa 4c89d048 .A(.7...I...L..H + 0470 c1e0054c 01e74901 c14d01d2 f64424e0 ...L..I..M...D$. + 0480 0174254c 395424d0 0f84a400 00007e14 .t%L9T$.......~. + 0490 c5fb100f c5fb1047 08c4c17b 1109c4c1 .......G...{.... + 04a0 7b114108 4983c110 48834424 d0024983 {.A.I...H.D$..I. + 04b0 c410f644 24d80174 5c488b74 24e04885 ...D$..t\H.t$.H. + 04c0 f67e5248 8b5424f0 c5fb100d 00000000 .~RH.T$......... + 04d0 488b4c24 d048c1e2 0331c0eb 1c0f1f00 H.L$.H...1...... + 04e0 7e0cc4c1 7b100424 c4c17b11 04c148ff ~...{..$..{...H. + 04f0 c04901d4 4839c674 1c4839c1 75e248ff .I..H9.t.H9.u.H. + 0500 c0c4c173 5e042449 01d4c4c1 7b1104c9 ...s^.$I....{... + 0510 4839c675 e45b5d41 5c415d41 5e31c041 H9.u.[]A\A]A^1.A + 0520 5fc3660f 1f440000 4889e831 c9e905fd _.f..D..H..1.... + 0530 ffffc5fb 10050000 0000c5fb 5e07c4c1 ............^... + 0540 7b1101e9 5cffffff 4c89e745 31d2e929 {...\...L..E1..) + 0550 ffffff ... /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_COOPERLAKE.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 b9050000 00420e10 8f02420e .........B....B. + 0020 00000000 53050000 00420e10 8f02420e ....S....B....B. 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 ba040a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0040 8606410e 38830703 09050a0e 30410e28 ..A.8.......0A.( + 0050 420e2042 0e18420e 10440e08 470b0000 B. B..B..D..G... /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_SKYLAKEX.o (disasm) @@ -16,280 +16,287 @@ sar $something,%rsi mov %rdi,-offset(%rsp) mov %rcx,-offset(%rsp) + mov %r8,-offset(%rsp) mov %rsi,-offset(%rsp) test %rsi,%rsi jle - mov %r8,%r15 - mov %rsi,%rax - neg %r15 - shl $something,%rax - add %r8,%rax - shl $something,%r15 + mov %rcx,%rbx + lea (%rcx,%rcx,2),%rax + shl $something,%rbx + lea offset(,%rax,8),%rdx + mov %rbx,%r10 + mov %rdi,%rax mov %rdi,%rbx + sar $something,%rax + and $something,%ebx + mov %rax,%r13 + mov %rbx,-offset(%rsp) + lea (%r8,%rsi,4),%rbx mov %rax,-offset(%rsp) - mov %rdx,-offset(%rsp) - lea (%rdx,%r15,1),%rax - mov %rdi,%rbp + imul %r10,%r13 + mov %rbx,-offset(%rsp) + and $something,%edi + lea offset(,%rax,4),%rbx + shl $something,%rax + mov %rdi,-offset(%rsp) mov %rax,-offset(%rsp) - lea offset(,%rcx,8),%r13 - mov %rdi,%rax - shl $something,%rbx - vmovsd offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%rbp - mov %r8,%rdi - lea offset(%r13),%r14 - mov %rbx,%r12 - mov %rax,%r8 - nopw offset(%rax,%rax,1) - mov -offset(%rsp),%rax - sub %r15,%rax - test %r8,%r8 + mov %rcx,%r15 + vmovsd offset(%rip),%xmm16 # + mov %r12,-offset(%rsp) + add %r12,%r13 + mov %r12,%rbp + lea offset(,%rcx,8),%r14 + shl $something,%r15 + mov %r8,%r11 + mov %rdx,%r12 + nopl offset(%rax,%rax,1) + cmpq $something,-offset(%rsp) + lea (%r14,%rbp,1),%rdx + lea (%r15,%rbp,1),%rsi + lea offset(%rbp,%r12,1),%rdi jle - mov %rdi,%rsi - mov $something,%r10d - neg %rsi - lea (%rax,%r15,1),%rbx - lea (%r9,%r15,1),%r11 - sub %rdi,%r10 - mov %r9,%rdx + mov %rbp,%rcx + mov %r9,%rax + xor %r8d,%r8d jmp - nopl (%rax) - cmp $something,%rsi + nop jle - inc %rsi - sub $something,%rdx - add %r13,%rax - add %r14,%rbx - add $something,%r11 - inc %r10 - cmp %rbp,%rsi + vmovsd (%rcx),%xmm15 + vmovsd offset(%rcx),%xmm14 + vmovsd offset(%rcx),%xmm13 + vmovsd offset(%rcx),%xmm12 + vmovsd (%rdx),%xmm11 + vmovsd offset(%rdx),%xmm10 + vmovsd offset(%rdx),%xmm9 + vmovsd offset(%rdx),%xmm8 + vmovsd (%rsi),%xmm7 + vmovsd offset(%rsi),%xmm6 + vmovsd offset(%rsi),%xmm5 + vmovsd offset(%rsi),%xmm4 + vmovsd (%rdi),%xmm3 + vmovsd offset(%rdi),%xmm2 + vmovsd offset(%rdi),%xmm1 + vmovsd offset(%rdi),%xmm0 + vmovsd %xmm15,(%rax) + vmovsd %xmm14,offset(%rax) + vmovsd %xmm13,offset(%rax) + vmovsd %xmm12,offset(%rax) + vmovsd %xmm11,offset(%rax) + vmovsd %xmm10,offset(%rax) + vmovsd %xmm9,offset(%rax) + vmovsd %xmm8,offset(%rax) + vmovsd %xmm7,offset(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + add $something,%r8 + add %r10,%rcx + add %r10,%rdx + add %r10,%rsi + add %r10,%rdi + sub $something,%rax + cmp %rbx,%r8 je - lea (%rsi,%rdi,1),%rcx - cmp %rcx,%rdi - jle - test %rsi,%rsi - jns - vmovsd (%rax),%xmm0 - vmovsd %xmm0,(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - jmp - nopl offset(%rax,%rax,1) - vdivsd (%rbx),%xmm1,%xmm0 - mov %r10,%rcx - vmovsd %xmm0,(%r11) - cmp $something,%r10 - je - cs nopw offset(%rax,%rax,1) - vmovsd (%rax,%rcx,8),%xmm0 - vmovsd %xmm0,(%rdx,%rcx,8) - inc %rcx - cmp $something,%rcx + cmp %r8,%r11 jne + vmovsd offset(%rdx),%xmm2 + vmovsd offset(%rsi),%xmm1 + vmovsd offset(%rdi),%xmm0 + vdivsd %xmm2,%xmm16,%xmm2 + vmovsd offset(%rcx),%xmm8 + vmovsd offset(%rcx),%xmm7 + vmovsd offset(%rcx),%xmm6 + vmovsd offset(%rdx),%xmm5 + vmovsd offset(%rdx),%xmm4 + vmovsd offset(%rsi),%xmm3 + vdivsd (%rcx),%xmm16,%xmm9 + vmovsd %xmm8,offset(%rax) + vmovsd %xmm9,(%rax) + vmovsd %xmm7,offset(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vdivsd %xmm1,%xmm16,%xmm1 /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_SKYLAKEX.o (objdump) @@ -3,94 +3,88 @@ Contents of section .text: 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t - 0010 24d048c1 fe044889 7c24d848 894c24e0 $.H...H.|$.H.L$. - 0020 48897424 e84885f6 0f8eef01 00004d89 H.t$.H........M. - 0030 c74889f0 49f7df48 c1e0044c 01c049c1 .H..I..H...L..I. - 0040 e7034889 fb488944 24c04889 5424f04a ..H..H.D$.H.T$.J - 0050 8d043a48 89fd4889 4424c84c 8d2ccd00 ..:H..H.D$.L.,.. - 0060 00000048 89f848c1 e307c5fb 100d0000 ...H..H......... - 0070 00004c89 4424f84c 29c54c89 c74d8d75 ..L.D$.L).L..M.u - 0080 084989dc 4989c066 0f1f8400 00000000 .I..I..f........ - 0090 488b4424 c84c29f8 4d85c00f 8e420100 H.D$.L).M....B.. - 00a0 004889fe 41ba0100 000048f7 de4a8d1c .H..A.....H..J.. - 00b0 384f8d1c 394929fa 4c89caeb 2d0f1f00 8O..9I).L...-... - 00c0 4883fe0f 0f8ed600 000048ff c64883ea H.........H..H.. - 00d0 804c01e8 4c01f349 81c38800 000049ff .L..L..I......I. - 00e0 c24839ee 0f84f600 0000488d 0c3e4839 .H9.......H..>H9 - 00f0 cf7ecd48 85f679d2 c5fb1000 c5fb1102 .~.H..y......... - 0100 c5fb1040 08c5fb11 4208c5fb 104010c5 ...@....B....@.. - 0110 fb114210 c5fb1040 18c5fb11 4218c5fb ..B....@....B... - 0120 104020c5 fb114220 c5fb1040 28c5fb11 .@ ...B ...@(... - 0130 4228c5fb 104030c5 fb114230 c5fb1040 B(...@0...B0...@ - 0140 38c5fb11 4238c5fb 104040c5 fb114240 8...B8...@@...B@ - 0150 c5fb1040 48c5fb11 4248c5fb 104050c5 ...@H...BH...@P. - 0160 fb114250 c5fb1040 58c5fb11 4258c5fb ..BP...@X...BX.. - 0170 104060c5 fb114260 c5fb1040 68c5fb11 .@`...B`...@h... - 0180 4268c5fb 104070c5 fb114270 c5fb1040 Bh...@p...Bp...@ - 0190 78c5fb11 4278e92f ffffff0f 1f440000 x...Bx./.....D.. - 01a0 c5f35e03 4c89d1c4 c17b1103 4983fa10 ..^.L....{..I... - 01b0 0f8414ff ffff662e 0f1f8400 00000000 ......f......... - 01c0 c5fb1004 c8c5fb11 04ca48ff c14883f9 ..........H..H.. - 01d0 1075ede9 f2feffff 0f1f8400 00000000 .u.............. - 01e0 4d01e148 83c71048 83ed1049 83c78048 M..H...H...I...H - 01f0 3b7c24c0 0f8596fe ffff488b 5c24e84c ;|$.......H.\$.L - 0200 8b6424f0 4889d848 c1e0074c 8b4424f8 .d$.H..H...L.D$. - 0210 4901c448 89d848c1 e0044901 c0f64424 I..H..H...I...D$ - 0220 d0080f84 ff000000 488b4424 d84d8d6c ........H.D$.M.l - 0230 24404885 c00f8ee5 00000048 8b5c24e0 $@H........H.\$. - 0240 4c89c148 f7d94c8d 1cdd0000 0000488d L..H..L.......H. - 0250 3ccd0000 00004c29 c0be0100 00004d8d <.....L)......M. - 0260 143c4889 c3c5fb10 0d000000 00498d6b .J...I9.~.H..y - 03c0 d9c4c17b 100424c5 fb1101c4 c17b1044 ...{..$......{.D - 03d0 2408c5fb 114108c4 c17b1044 2410c5fb $....A...{.D$... - 03e0 114110c4 c17b1044 2418c5fb 114118eb .A...{.D$....A.. - 03f0 a9488b44 24d848c1 e0054901 c14983c0 .H.D$.H...I..I.. - 0400 044d89ec f64424d0 020f84b0 00000048 .M...D$........H - 0410 8b7c24d8 498d6c24 104885ff 0f8e9600 .|$.I.l$.H...... - 0420 0000488b 4424e04c 29c74c8d 14c50000 ..H.D$.L).L..... - 0430 00004c89 c048f7d8 488d0cc5 00000000 ..L..H..H....... - 0440 498d340c c5fb100d 00000000 498d5a08 I.4.........I.Z. - 0450 4c01c949 89fb4c89 caeb360f 1f440000 L..I..L...6..D.. - 0460 4885c079 16c4c17b 100424c5 fb1102c4 H..y...{..$..... - 0470 c17b1044 2408c5fb 11420848 ffc04883 .{.D$....B.H..H. - 0480 c2104d01 d44801de 4883c118 4c39d874 ..M..H..H...L9.t - 0490 1b498d3c 004939f8 7fc64883 f8017fdb .I.<.I9...H..... - 04a0 c5f35e06 c5fb1101 75c5ebcf 488b4424 ..^.....u...H.D$ - 04b0 d848c1e0 044901c1 4983c002 4989ecf6 .H...I..I...I... - 04c0 4424d001 75735b5d 415c415d 415e31c0 D$..us[]A\A]A^1. - 04d0 415fc3c4 c1735e02 4889f2c5 fb110748 A_...s^.H......H - 04e0 83fe080f 84a1fdff ff0f1f80 00000000 ................ - 04f0 c4c17b10 04d4c5fb 1104d048 ffc24883 ..{........H..H. - 0500 fa0875ec e981fdff ffc4c173 5e024889 ..u........s^.H. - 0510 f0c5fb11 074883fe 040f847b feffff90 .....H.....{.... - 0520 c4c17b10 04c4c5fb 1104c148 ffc04883 ..{........H..H. - 0530 f80475ec e961feff ff488b5c 24d84885 ..u..a...H.\$.H. - 0540 db7e8348 8b4c24e0 4c89c248 f7da4c8d .~.H.L$.L..H..L. - 0550 14d50000 000048c1 e1034d89 c34b8d34 ......H...M..K.4 - 0560 14c5fb10 0d000000 00488d79 084d01ca .........H.y.M.. - 0570 31c049c1 e304eb29 0f1f8400 00000000 1.I....)........ - 0580 750ac5f3 5e06c481 7b11041a 48ffc049 u...^...{...H..I - 0590 01cc48ff c24801fe 4839c30f 8425ffff ..H..H..H9...%.. - 05a0 ff4939c0 7eda4885 d279e1c4 c17b1004 .I9.~.H..y...{.. - 05b0 24c4c17b 1104c1eb d3 $..{..... + 0010 24d848c1 fe024889 7c24e048 894c24f0 $.H...H.|$.H.L$. + 0020 4c894424 d0488974 24e84885 f60f8ef1 L.D$.H.t$.H..... + 0030 02000048 89cb488d 044948c1 e305488d ...H..H..IH...H. + 0040 14c50000 00004989 da4889f8 4889fb48 ......I..H..H..H + 0050 c1f80283 e3024989 c548895c 24b8498d ......I..H.\$.I. + 0060 1cb04889 4424b04d 0fafea48 895c24a8 ..H.D$.M...H.\$. + 0070 83e70148 8d1c8500 00000048 c1e00748 ...H.......H...H + 0080 897c24c0 48894424 c84989cf 62e1ff08 .|$.H.D$.I..b... + 0090 10050000 00004c89 6424f84d 01e54c89 ......L.d$.M..L. + 00a0 e54c8d34 cd000000 0049c1e7 044d89c3 .L.4.....I...M.. + 00b0 4989d40f 1f440000 48837c24 b000498d I....D..H.|$..I. + 00c0 142e498d 342f4a8d 7c25000f 8e570400 ..I.4/J.|%...W.. + 00d0 004889e9 4c89c845 31c0e9bf 00000090 .H..L..E1....... + 00e0 0f8e9b00 0000c57b 1039c57b 107108c5 .......{.9.{.q.. + 00f0 7b106910 c57b1061 18c57b10 1ac57b10 {.i..{.a..{...{. + 0100 5208c57b 104a10c5 7b104218 c5fb103e R..{.J..{.B....> + 0110 c5fb1076 08c5fb10 6e10c5fb 106618c5 ...v....n....f.. + 0120 fb101fc5 fb105708 c5fb104f 10c5fb10 ......W....O.... + 0130 4718c57b 1138c57b 117008c5 7b116810 G..{.8.{.p..{.h. + 0140 c57b1160 18c57b11 5820c57b 115028c5 .{.`..{.X .{.P(. + 0150 7b114830 c57b1140 38c5fb11 7840c5fb {.H0.{.@8...x@.. + 0160 117048c5 fb116850 c5fb1160 58c5fb11 .pH...hP...`X... + 0170 5860c5fb 115068c5 fb114870 c5fb1140 X`...Ph...Hp...@ + 0180 784983c0 044c01d1 4c01d24c 01d64c01 xI...L..L..L..L. + 0190 d74883e8 804939d8 0f848a00 00004d39 .H...I9.......M9 + 01a0 c30f8539 ffffffc5 fb105208 c5fb104e ...9......R....N + 01b0 10c5fb10 471862f1 ff005ed2 c57b1041 ....G.b...^..{.A + 01c0 08c5fb10 7910c5fb 107118c5 fb106a10 ....y....q....j. + 01d0 c5fb1062 18c5fb10 5e186271 ff005e09 ...b....^.bq..^. + 01e0 c57b1140 08c57b11 08c5fb11 7810c5fb .{.@..{.....x... + 01f0 117018c5 fb116830 c5fb1160 38c5fb11 .p....h0...`8... + 0200 585862f1 ff005ec9 c5fb1150 2862f1ff XXb...^....P(b.. + 0210 005ec0c5 fb114850 c5fb1140 78e95fff .^....HP...@x._. + 0220 ffff660f 1f440000 4c89e84b 8d142e4c ..f..D..L..K...L + 0230 034c24c8 4889d948 837c24b8 00746b49 .L$.H..H.|$..tkI + 0240 39cb0f84 c8010000 7e55c5fb 1038c5fb 9.......~U...8.. + 0250 107008c5 fb106810 c5fb1060 18c5fb10 .p....h....`.... + 0260 1ac5fb10 5208c5fb 104a10c5 fb104218 ....R....J....B. + 0270 c4c17b11 39c4c17b 117108c4 c17b1169 ..{.9..{.q...{.i + 0280 10c4c17b 116118c4 c17b1159 20c4c17b ...{.a...{.Y ..{ + 0290 115128c4 c17b1149 30c4c17b 1141384c .Q(..{.I0..{.A8L + 02a0 01f84983 c1404883 c1024883 7c24c000 ..I..@H...H.|$.. + 02b0 74394c39 d90f841d 0100007d 2ac5fb10 t9L9.......}*... + 02c0 18c5fb10 5008c5fb 104810c5 fb104018 ....P....H....@. + 02d0 c4c17b11 19c4c17b 115108c4 c17b1149 ..{....{.Q...{.I + 02e0 10c4c17b 11411849 83c12049 83c30448 ...{.A.I.. I...H + 02f0 83c52049 83c5204c 395c24a8 0f85b6fd .. I.. L9\$..... + 0300 ffff488b 5c24e84c 8b6424f8 4889d848 ..H.\$.L.d$.H..H + 0310 c1e00549 01c4488b 4424d048 8d049848 ...I..H.D$.H...H + 0320 894424d0 f64424d8 020f8483 0100004c .D$..D$........L + 0330 8b5424e0 488b4424 f049d1fa 498d34c4 .T$.H.D$.I..I.4. + 0340 4d85d20f 8eff0100 0048c1e0 044889c7 M........H...H.. + 0350 c5fb1025 00000000 4c8b5c24 d04f8d04 ...%....L.\$.O.. + 0360 124c89e1 4c89c831 d2eb430f 1f440000 .L..L..1..C..D.. + 0370 7e25c5fb 1019c5fb 105108c5 fb100ec5 ~%.......Q...... + 0380 fb104608 c5fb1118 c5fb1150 08c5fb11 ..F........P.... + 0390 4810c5fb 11401848 83c20248 01f94801 H....@.H...H..H. + 03a0 fe4883c0 204939d0 0f84ba00 00004939 .H.. I9.......I9 + 03b0 d375bdc5 fb104608 c5fb1049 08c5db5e .u....F....I...^ + 03c0 c0c5db5e 11c5fb11 4808c5fb 1110c5fb ...^....H....... + 03d0 114018eb c20f1f00 c5fb1050 08c5fb10 .@.........P.... + 03e0 4810c5fb 10401862 f1ff005e 18c4c17b H....@.b...^...{ + 03f0 115108c4 c17b1119 c4c17b11 4910c4c1 .Q...{....{.I... + 0400 7b114118 e9defeff ff0f1f80 00000000 {.A............. + 0410 c5fb1042 08c5fb10 680862f1 ff005ec0 ...B....h.b...^. + 0420 c5fb1060 10c5fb10 5818c5fb 105210c5 ...`....X....R.. + 0430 fb104a18 62f1ff00 5e30c4c1 7b116908 ..J.b...^0..{.i. + 0440 c4c17b11 31c4c17b 116110c4 c17b1159 ..{.1..{.a...{.Y + 0450 18c4c17b 115130c4 c17b1149 38c4c17b ...{.Q0..{.I8..{ + 0460 114128e9 37feffff 490faffa 4c89d048 .A(.7...I...L..H + 0470 c1e0054c 01e74901 c14d01d2 f64424e0 ...L..I..M...D$. + 0480 0174254c 395424d0 0f84a400 00007e14 .t%L9T$.......~. + 0490 c5fb100f c5fb1047 08c4c17b 1109c4c1 .......G...{.... + 04a0 7b114108 4983c110 48834424 d0024983 {.A.I...H.D$..I. + 04b0 c410f644 24d80174 5c488b74 24e04885 ...D$..t\H.t$.H. + 04c0 f67e5248 8b5424f0 c5fb100d 00000000 .~RH.T$......... + 04d0 488b4c24 d048c1e2 0331c0eb 1c0f1f00 H.L$.H...1...... + 04e0 7e0cc4c1 7b100424 c4c17b11 04c148ff ~...{..$..{...H. + 04f0 c04901d4 4839c674 1c4839c1 75e248ff .I..H9.t.H9.u.H. + 0500 c0c4c173 5e042449 01d4c4c1 7b1104c9 ...s^.$I....{... + 0510 4839c675 e45b5d41 5c415d41 5e31c041 H9.u.[]A\A]A^1.A + 0520 5fc3660f 1f440000 4889e831 c9e905fd _.f..D..H..1.... + 0530 ffffc5fb 10050000 0000c5fb 5e07c4c1 ............^... + 0540 7b1101e9 5cffffff 4c89e745 31d2e929 {...\...L..E1..) + 0550 ffffff ... /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltncopy_SKYLAKEX.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 b9050000 00420e10 8f02420e .........B....B. + 0020 00000000 53050000 00420e10 8f02420e ....S....B....B. 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 ba040a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0040 8606410e 38830703 09050a0e 30410e28 ..A.8.......0A.( + 0050 420e2042 0e18420e 10440e08 470b0000 B. B..B..D..G... /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_COOPERLAKE.o (disasm) @@ -9,262 +9,278 @@ push %r14 push %r13 push %r12 - mov %rdi,%r12 + mov %rdx,%r12 push %rbp - mov %rdx,%rbp push %rbx mov %rsi,-offset(%rsp) sar $something,%rsi + mov %rdi,-offset(%rsp) mov %rcx,-offset(%rsp) + mov %r8,-offset(%rsp) mov %rsi,-offset(%rsp) test %rsi,%rsi jle - mov %r8,%rax - shl $something,%rsi - neg %rax - mov %rdx,-offset(%rsp) + mov %rcx,%rbx + lea (%rcx,%rcx,2),%rax + shl $something,%rbx + lea offset(,%rax,8),%rdx + mov %rbx,%r10 + mov %rdi,%rax mov %rdi,%rbx - mov %rdi,%r15 - lea (%rsi,%r8,1),%rsi - lea offset(%rdx,%rax,8),%rax - vmovsd offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%rbx - mov %r8,%rdi - lea offset(,%rcx,8),%r13 + sar $something,%rax + and $something,%ebx + mov %rax,%r13 + mov %rbx,-offset(%rsp) + lea (%r8,%rsi,4),%rbx + mov %rax,-offset(%rsp) + imul %r10,%r13 + mov %rbx,-offset(%rsp) + and $something,%edi + lea offset(,%rax,4),%rbx + shl $something,%rax + mov %rdi,-offset(%rsp) + mov %rax,-offset(%rsp) + mov %rcx,%r15 + vmovsd offset(%rip),%xmm16 # + mov %r12,-offset(%rsp) + add %r12,%r13 + mov %r12,%rbp + lea offset(,%rcx,8),%r14 shl $something,%r15 - mov %rdx,%r14 - mov %rsi,%r8 - mov %rax,%rbp - nopl (%rax) - mov %r14,%rax - sub $something,%r14 - test %r12,%r12 + mov %r8,%r11 + mov %rdx,%r12 + nopl offset(%rax,%rax,1) + cmpq $something,-offset(%rsp) + lea (%r14,%rbp,1),%rdx + lea (%r15,%rbp,1),%rsi + lea offset(%rbp,%r12,1),%rdi jle - mov %rbp,%r10 - mov %rdi,%rsi - sub %r14,%r10 - mov $something,%r11d - neg %rsi - add %r9,%r10 - sub %rdi,%r11 - mov %r9,%rdx + mov %rbp,%rcx + mov %r9,%rax + xor %r8d,%r8d jmp - nopl (%rax) - cmp $something,%rsi + nop jle - inc %rsi - sub $something,%rdx - add %r13,%rax - add $something,%r10 - inc %r11 - cmp %rbx,%rsi + vmovsd (%rcx),%xmm15 + vmovsd offset(%rcx),%xmm14 + vmovsd offset(%rcx),%xmm13 + vmovsd offset(%rcx),%xmm12 + vmovsd (%rdx),%xmm11 + vmovsd offset(%rdx),%xmm10 + vmovsd offset(%rdx),%xmm9 + vmovsd offset(%rdx),%xmm8 + vmovsd (%rsi),%xmm7 + vmovsd offset(%rsi),%xmm6 + vmovsd offset(%rsi),%xmm5 + vmovsd offset(%rsi),%xmm4 + vmovsd (%rdi),%xmm3 + vmovsd offset(%rdi),%xmm2 + vmovsd offset(%rdi),%xmm1 + vmovsd offset(%rdi),%xmm0 + vmovsd %xmm15,(%rax) + vmovsd %xmm14,offset(%rax) + vmovsd %xmm13,offset(%rax) + vmovsd %xmm12,offset(%rax) + vmovsd %xmm11,offset(%rax) + vmovsd %xmm10,offset(%rax) + vmovsd %xmm9,offset(%rax) + vmovsd %xmm8,offset(%rax) + vmovsd %xmm7,offset(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + add $something,%r8 + add %r10,%rcx + add %r10,%rdx + add %r10,%rsi + add %r10,%rdi + sub $something,%rax + cmp %rbx,%r8 je - lea (%rsi,%rdi,1),%rcx - cmp %rcx,%rdi - jle - test %rsi,%rsi - jns - vmovsd (%rax),%xmm0 - vmovsd %xmm0,(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - jmp - vmovsd %xmm1,(%r10) - mov %r11,%rcx - cmp $something,%r11 - je - nopw offset(%rax,%rax,1) - vmovsd (%rax,%rcx,8),%xmm0 - vmovsd %xmm0,(%rdx,%rcx,8) - inc %rcx - cmp $something,%rcx + cmp %r8,%r11 jne + vmovsd offset(%rcx),%xmm5 + vmovsd offset(%rcx),%xmm4 + vmovsd offset(%rcx),%xmm3 + vmovsd offset(%rdx),%xmm2 + vmovsd offset(%rdx),%xmm1 + vmovsd offset(%rsi),%xmm0 + vmovsd %xmm16,(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm16,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm16,offset(%rax) + vmovsd %xmm0,offset(%rax) + vmovsd %xmm16,offset(%rax) /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_COOPERLAKE.o (objdump) @@ -2,82 +2,83 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989fc55 4889d553 AWAVAUATI..UH..S - 0010 48897424 d848c1fe 0448894c 24e04889 H.t$.H...H.L$.H. - 0020 7424e848 85f60f8e bb010000 4c89c048 t$.H........L..H - 0030 c1e60448 f7d84889 5424f048 89fb4989 ...H..H.T$.H..I. - 0040 ff4a8d34 06488d84 c2800000 00c5fb10 .J.4.H.......... - 0050 0d000000 004c8944 24f84c29 c34c89c7 .....L.D$.L).L.. - 0060 4c8d2ccd 00000000 49c1e707 4989d649 L.,.....I...I..I - 0070 89f04889 c50f1f00 4c89f049 83ee804d ..H.....L..I...M - 0080 85e40f8e 2b010000 4989ea48 89fe4d29 ....+...I..H..M) - 0090 f241bb01 00000048 f7de4d01 ca4929fb .A.....H..M..I). - 00a0 4c89caeb 2a0f1f00 4883fe0f 0f8ece00 L...*...H....... - 00b0 000048ff c64883ea 804c01e8 4981c288 ..H..H...L..I... - 00c0 00000049 ffc34839 de0f84e1 00000048 ...I..H9.......H - 00d0 8d0c3e48 39cf7ed0 4885f679 d5c5fb10 ..>H9.~.H..y.... - 00e0 00c5fb11 02c5fb10 4008c5fb 114208c5 ........@....B.. - 00f0 fb104010 c5fb1142 10c5fb10 4018c5fb ..@....B....@... - 0100 114218c5 fb104020 c5fb1142 20c5fb10 .B....@ ...B ... - 0110 4028c5fb 114228c5 fb104030 c5fb1142 @(...B(...@0...B - 0120 30c5fb10 4038c5fb 114238c5 fb104040 0...@8...B8...@@ - 0130 c5fb1142 40c5fb10 4048c5fb 114248c5 ...B@...@H...BH. - 0140 fb104050 c5fb1142 50c5fb10 4058c5fb ..@P...BP...@X.. - 0150 114258c5 fb104060 c5fb1142 60c5fb10 .BX...@`...B`... - 0160 4068c5fb 114268c5 fb104070 c5fb1142 @h...Bh...@p...B - 0170 70c5fb10 4078c5fb 114278e9 32ffffff p...@x...Bx.2... - 0180 c4c17b11 0a4c89d9 4983fb10 0f8420ff ..{..L..I..... . - 0190 ffff660f 1f440000 c5fb1004 c8c5fb11 ..f..D.......... - 01a0 04ca48ff c14883f9 1075ede9 02ffffff ..H..H...u...... - 01b0 4d01f948 83c71048 83eb104c 39c70f85 M..H...H...L9... - 01c0 b4feffff 488b5c24 e8488b6c 24f04889 ....H.\$.H.l$.H. - 01d0 d848c1e0 074c8b44 24f84801 c54889d8 .H...L.D$.H..H.. - 01e0 48c1e004 4901c0f6 4424d808 0f84d600 H...I...D$...... - 01f0 00004c8d 5d404d85 e40f8ec2 00000048 ..L.]@M........H - 0200 8b4424e0 4c89c148 f7d9be01 0000004c .D$.L..H.......L - 0210 89e34c8d 14c50000 0000c5fb 100d0000 ..L............. - 0220 0000498d 3cc94c29 c64c29c3 4c89c8eb ..I.<.L).L).L... - 0230 270f1f80 00000000 4883f907 0f8ee501 '.......H....... - 0240 000048ff c14883c0 404c01d5 4883c748 ..H..H..@L..H..H - 0250 48ffc648 39d9745f 4a8d1401 4939d07e H..H9.t_J...I9.~ - 0260 d74885c9 79dcc5fb 104500c5 fb1100c5 .H..y....E...... - 0270 fb104508 c5fb1140 08c5fb10 4510c5fb ..E....@....E... - 0280 114010c5 fb104518 c5fb1140 18c5fb10 .@....E....@.... - 0290 4520c5fb 114020c5 fb104528 c5fb1140 E ...@ ...E(...@ - 02a0 28c5fb10 4530c5fb 114030c5 fb104538 (...E0...@0...E8 - 02b0 c5fb1140 38eb8b4c 89e048c1 e0064901 ...@8..L..H...I. - 02c0 c14983c0 084c89dd f64424d8 040f84ad .I...L...D$..... - 02d0 0000004c 8d5d204d 85e40f8e 99000000 ...L.] M........ - 02e0 488b4424 e04c89c2 48f7dabe 01000000 H.D$.L..H....... - 02f0 4c89e3c5 fb100d00 0000004c 8d14c500 L..........L.... - 0300 00000049 8d3cd14c 29c64c29 c34c89c9 ...I.<.L).L).L.. - 0310 eb26660f 1f440000 4883fa03 0f8e3701 .&f..D..H.....7. - 0320 000048ff c24883c1 204c01d5 4883c728 ..H..H.. L..H..( - 0330 48ffc648 39da7437 4a8d0402 4939c07e H..H9.t7J...I9.~ - 0340 d74885d2 79dcc5fb 104500c5 fb1101c5 .H..y....E...... - 0350 fb104508 c5fb1141 08c5fb10 4510c5fb ..E....A....E... - 0360 114110c5 fb104518 c5fb1141 18ebb34c .A....E....A...L - 0370 89e048c1 e0054901 c14983c0 044c89dd ..H...I..I...L.. - 0380 f64424d8 020f8488 0000004c 8d5d104d .D$........L.].M - 0390 85e47e78 488b4424 e04c89e7 4c8d14c5 ..~xH.D$.L..L... - 03a0 00000000 4c89c048 f7d8c5fb 100d0000 ....L..H........ - 03b0 0000498d 0cc14c29 c74c89ca eb2d6690 ..I...L).L...-f. - 03c0 4885c079 13c5fb10 4500c5fb 1102c5fb H..y....E....... - 03d0 104508c5 fb114208 48ffc048 83c2104c .E....B.H..H...L - 03e0 01d54883 c1184839 c7741749 8d340049 ..H...H9.t.I.4.I - 03f0 39f07fcc 4883f801 7fdec5fb 110975ce 9...H.........u. - 0400 ebd64c89 e048c1e0 044901c1 4983c002 ..L..H...I..I... - 0410 4c89ddf6 4424d801 756f5b5d 415c415d L...D$..uo[]A\A] - 0420 415e31c0 415fc3c5 fb110f48 89f24883 A^1.A_.....H..H. - 0430 fe080f84 0afeffff 0f1f8400 00000000 ................ - 0440 c5fb1044 d500c5fb 1104d048 ffc24883 ...D.......H..H. - 0450 fa0875ec e9e9fdff ffc5fb11 0f4889f0 ..u..........H.. - 0460 4883fe04 0f84b8fe ffff660f 1f440000 H.........f..D.. - 0470 c5fb1044 c500c5fb 1104c148 ffc04883 ...D.......H..H. - 0480 f80475ec e999feff ff4d85e4 7e8c488b ..u......M..~.H. - 0490 4c24e04c 89c248f7 da4c89c6 c5fb100d L$.L..H..L...... - 04a0 00000000 48c1e103 498d3cd1 31c048c1 ....H...I.<.1.H. - 04b0 e604eb1d 0f1f4000 7505c5fb 110c3748 ......@.u.....7H - 04c0 ffc04801 cd48ffc2 4939c40f 8449ffff ..H..H..I9...I.. - 04d0 ff4939c0 7ee24885 d279e4c5 fb104500 .I9.~.H..y....E. - 04e0 c4c17b11 04c1ebd7 ..{..... + 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t + 0010 24d848c1 fe024889 7c24e048 894c24f0 $.H...H.|$.H.L$. + 0020 4c894424 d0488974 24e84885 f60f8ec9 L.D$.H.t$.H..... + 0030 02000048 89cb488d 044948c1 e305488d ...H..H..IH...H. + 0040 14c50000 00004989 da4889f8 4889fb48 ......I..H..H..H + 0050 c1f80283 e3024989 c548895c 24b8498d ......I..H.\$.I. + 0060 1cb04889 4424b04d 0fafea48 895c24a8 ..H.D$.M...H.\$. + 0070 83e70148 8d1c8500 00000048 c1e00748 ...H.......H...H + 0080 897c24c0 48894424 c84989cf 62e1ff08 .|$.H.D$.I..b... + 0090 10050000 00004c89 6424f84d 01e54c89 ......L.d$.M..L. + 00a0 e54c8d34 cd000000 0049c1e7 044d89c3 .L.4.....I...M.. + 00b0 4989d40f 1f440000 48837c24 b000498d I....D..H.|$..I. + 00c0 142e498d 342f4a8d 7c25000f 8eff0300 ..I.4/J.|%...... + 00d0 004889e9 4c89c845 31c0e9bb 00000090 .H..L..E1....... + 00e0 0f8e9b00 0000c57b 1039c57b 107108c5 .......{.9.{.q.. + 00f0 7b106910 c57b1061 18c57b10 1ac57b10 {.i..{.a..{...{. + 0100 5208c57b 104a10c5 7b104218 c5fb103e R..{.J..{.B....> + 0110 c5fb1076 08c5fb10 6e10c5fb 106618c5 ...v....n....f.. + 0120 fb101fc5 fb105708 c5fb104f 10c5fb10 ......W....O.... + 0130 4718c57b 1138c57b 117008c5 7b116810 G..{.8.{.p..{.h. + 0140 c57b1160 18c57b11 5820c57b 115028c5 .{.`..{.X .{.P(. + 0150 7b114830 c57b1140 38c5fb11 7840c5fb {.H0.{.@8...x@.. + 0160 117048c5 fb116850 c5fb1160 58c5fb11 .pH...hP...`X... + 0170 5860c5fb 115068c5 fb114870 c5fb1140 X`...Ph...Hp...@ + 0180 784983c0 044c01d1 4c01d24c 01d64c01 xI...L..L..L..L. + 0190 d74883e8 804939d8 74664d39 c30f853d .H...I9.tfM9...= + 01a0 ffffffc5 fb106908 c5fb1061 10c5fb10 ......i....a.... + 01b0 5918c5fb 105210c5 fb104a18 c5fb1046 Y....R....J....F + 01c0 1862e1ff 081100c5 fb116808 c5fb1160 .b........h....` + 01d0 10c5fb11 581862e1 ff081140 05c5fb11 ....X.b....@.... + 01e0 5030c5fb 11483862 e1ff0811 400ac5fb P0...H8b....@... + 01f0 11405862 e1ff0811 400feb85 0f1f4000 .@Xb....@.....@. + 0200 4c89e84b 8d142e4c 034c24c8 4889d948 L..K...L.L$.H..H + 0210 837c24b8 00746b49 39cb0f84 b0010000 .|$..tkI9....... + 0220 7e55c5fb 1038c5fb 107008c5 fb106810 ~U...8...p....h. + 0230 c5fb1060 18c5fb10 1ac5fb10 5208c5fb ...`........R... + 0240 104a10c5 fb104218 c4c17b11 39c4c17b .J....B...{.9..{ + 0250 117108c4 c17b1169 10c4c17b 116118c4 .q...{.i...{.a.. + 0260 c17b1159 20c4c17b 115128c4 c17b1149 .{.Y ..{.Q(..{.I + 0270 30c4c17b 1141384c 01f84983 c1404883 0..{.A8L..I..@H. + 0280 c1024883 7c24c000 74394c39 d90f840d ..H.|$..t9L9.... + 0290 0100007d 2ac5fb10 18c5fb10 5008c5fb ...}*.......P... + 02a0 104810c5 fb104018 c4c17b11 19c4c17b .H....@...{....{ + 02b0 115108c4 c17b1149 10c4c17b 11411849 .Q...{.I...{.A.I + 02c0 83c12049 83c30448 83c52049 83c5204c .. I...H.. I.. L + 02d0 395c24a8 0f85defd ffff488b 5c24e84c 9\$.......H.\$.L + 02e0 8b6424f8 4889d848 c1e00549 01c4488b .d$.H..H...I..H. + 02f0 4424d048 8d049848 894424d0 f64424d8 D$.H...H.D$..D$. + 0300 020f845c 0100004c 8b5424e0 488b4424 ...\...L.T$.H.D$ + 0310 f049d1fa 498d34c4 4d85d20f 8ec80100 .I..I.4.M....... + 0320 0048c1e0 044889c7 c5fb1025 00000000 .H...H.....%.... + 0330 4c8b5c24 d04f8d04 124c89e1 4c89c831 L.\$.O...L..L..1 + 0340 d2eb430f 1f440000 7d25c5fb 1019c5fb ..C..D..}%...... + 0350 105108c5 fb100ec5 fb104608 c5fb1118 .Q........F..... + 0360 c5fb1150 08c5fb11 4810c5fb 11401848 ...P....H....@.H + 0370 83c20248 01f94801 fe4883c0 204939d0 ...H..H..H.. I9. + 0380 0f849300 00004c39 da75bdc5 fb104108 ......L9.u....A. + 0390 c5fb1120 c5fb1140 08c5fb11 6018ebcf ... ...@....`... + 03a0 c5fb1050 08c5fb10 4810c5fb 10401862 ...P....H....@.b + 03b0 c1ff0811 01c4c17b 115108c4 c17b1149 .......{.Q...{.I + 03c0 10c4c17b 114118e9 f3feffff 0f1f4000 ...{.A........@. + 03d0 c5fb1060 08c5fb10 5810c5fb 105018c5 ...`....X....P.. + 03e0 fb104a10 c5fb1042 1862c1ff 081101c4 ..J....B.b...... + 03f0 c17b1161 08c4c17b 115910c4 c17b1151 .{.a...{.Y...{.Q + 0400 1862c1ff 08114105 c4c17b11 4930c4c1 .b....A...{.I0.. + 0410 7b114138 e95efeff ff490faf fa4c89d0 {.A8.^...I...L.. + 0420 48c1e005 4c01e749 01c14d01 d2f64424 H...L..I..M...D$ + 0430 e0017425 4c3b5424 d00f849b 0000007d ..t%L;T$.......} + 0440 14c5fb10 0fc5fb10 4708c4c1 7b1109c4 ........G...{... + 0450 c17b1141 084983c1 10488344 24d00249 .{.A.I...H.D$..I + 0460 83c410f6 4424d801 7455488b 7424e048 ....D$..tUH.t$.H + 0470 85f67e4b 488b5424 f0c5fb10 0d000000 ..~KH.T$........ + 0480 00488b4c 24d048c1 e20331c0 eb1b6690 .H.L$.H...1...f. + 0490 7e0cc4c1 7b100424 c4c17b11 04c148ff ~...{..$..{...H. + 04a0 c04901d4 4839c674 164839c1 75e248ff .I..H9.t.H9.u.H. + 04b0 c0c4c17b 110cc949 01d44839 c675ea5b ...{...I..H9.u.[ + 04c0 5d415c41 5d415e31 c0415fc3 0f1f4000 ]A\A]A^1.A_...@. + 04d0 4889e831 c9e935fd ffff488b 05000000 H..1..5...H..... + 04e0 00498901 e96cffff ff4c89e7 4531d2e9 .I...l...L..E1.. + 04f0 39ffffff 9... /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_COOPERLAKE.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 e8040000 00420e10 8f02420e .........B....B. + 0020 00000000 f4040000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606440e 38830703 0b040a0e 30410e28 ..D.8.......0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0040 8606410e 38830703 b3040a0e 30410e28 ..A.8.......0A.( + 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_SKYLAKEX.o (disasm) @@ -9,262 +9,278 @@ push %r14 push %r13 push %r12 - mov %rdi,%r12 + mov %rdx,%r12 push %rbp - mov %rdx,%rbp push %rbx mov %rsi,-offset(%rsp) sar $something,%rsi + mov %rdi,-offset(%rsp) mov %rcx,-offset(%rsp) + mov %r8,-offset(%rsp) mov %rsi,-offset(%rsp) test %rsi,%rsi jle - mov %r8,%rax - shl $something,%rsi - neg %rax - mov %rdx,-offset(%rsp) + mov %rcx,%rbx + lea (%rcx,%rcx,2),%rax + shl $something,%rbx + lea offset(,%rax,8),%rdx + mov %rbx,%r10 + mov %rdi,%rax mov %rdi,%rbx - mov %rdi,%r15 - lea (%rsi,%r8,1),%rsi - lea offset(%rdx,%rax,8),%rax - vmovsd offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%rbx - mov %r8,%rdi - lea offset(,%rcx,8),%r13 + sar $something,%rax + and $something,%ebx + mov %rax,%r13 + mov %rbx,-offset(%rsp) + lea (%r8,%rsi,4),%rbx + mov %rax,-offset(%rsp) + imul %r10,%r13 + mov %rbx,-offset(%rsp) + and $something,%edi + lea offset(,%rax,4),%rbx + shl $something,%rax + mov %rdi,-offset(%rsp) + mov %rax,-offset(%rsp) + mov %rcx,%r15 + vmovsd offset(%rip),%xmm16 # + mov %r12,-offset(%rsp) + add %r12,%r13 + mov %r12,%rbp + lea offset(,%rcx,8),%r14 shl $something,%r15 - mov %rdx,%r14 - mov %rsi,%r8 - mov %rax,%rbp - nopl (%rax) - mov %r14,%rax - sub $something,%r14 - test %r12,%r12 + mov %r8,%r11 + mov %rdx,%r12 + nopl offset(%rax,%rax,1) + cmpq $something,-offset(%rsp) + lea (%r14,%rbp,1),%rdx + lea (%r15,%rbp,1),%rsi + lea offset(%rbp,%r12,1),%rdi jle - mov %rbp,%r10 - mov %rdi,%rsi - sub %r14,%r10 - mov $something,%r11d - neg %rsi - add %r9,%r10 - sub %rdi,%r11 - mov %r9,%rdx + mov %rbp,%rcx + mov %r9,%rax + xor %r8d,%r8d jmp - nopl (%rax) - cmp $something,%rsi + nop jle - inc %rsi - sub $something,%rdx - add %r13,%rax - add $something,%r10 - inc %r11 - cmp %rbx,%rsi + vmovsd (%rcx),%xmm15 + vmovsd offset(%rcx),%xmm14 + vmovsd offset(%rcx),%xmm13 + vmovsd offset(%rcx),%xmm12 + vmovsd (%rdx),%xmm11 + vmovsd offset(%rdx),%xmm10 + vmovsd offset(%rdx),%xmm9 + vmovsd offset(%rdx),%xmm8 + vmovsd (%rsi),%xmm7 + vmovsd offset(%rsi),%xmm6 + vmovsd offset(%rsi),%xmm5 + vmovsd offset(%rsi),%xmm4 + vmovsd (%rdi),%xmm3 + vmovsd offset(%rdi),%xmm2 + vmovsd offset(%rdi),%xmm1 + vmovsd offset(%rdi),%xmm0 + vmovsd %xmm15,(%rax) + vmovsd %xmm14,offset(%rax) + vmovsd %xmm13,offset(%rax) + vmovsd %xmm12,offset(%rax) + vmovsd %xmm11,offset(%rax) + vmovsd %xmm10,offset(%rax) + vmovsd %xmm9,offset(%rax) + vmovsd %xmm8,offset(%rax) + vmovsd %xmm7,offset(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + add $something,%r8 + add %r10,%rcx + add %r10,%rdx + add %r10,%rsi + add %r10,%rdi + sub $something,%rax + cmp %rbx,%r8 je - lea (%rsi,%rdi,1),%rcx - cmp %rcx,%rdi - jle - test %rsi,%rsi - jns - vmovsd (%rax),%xmm0 - vmovsd %xmm0,(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - jmp - vmovsd %xmm1,(%r10) - mov %r11,%rcx - cmp $something,%r11 - je - nopw offset(%rax,%rax,1) - vmovsd (%rax,%rcx,8),%xmm0 - vmovsd %xmm0,(%rdx,%rcx,8) - inc %rcx - cmp $something,%rcx + cmp %r8,%r11 jne + vmovsd offset(%rcx),%xmm5 + vmovsd offset(%rcx),%xmm4 + vmovsd offset(%rcx),%xmm3 + vmovsd offset(%rdx),%xmm2 + vmovsd offset(%rdx),%xmm1 + vmovsd offset(%rsi),%xmm0 + vmovsd %xmm16,(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm16,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm16,offset(%rax) + vmovsd %xmm0,offset(%rax) + vmovsd %xmm16,offset(%rax) /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_SKYLAKEX.o (objdump) @@ -2,82 +2,83 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989fc55 4889d553 AWAVAUATI..UH..S - 0010 48897424 d848c1fe 0448894c 24e04889 H.t$.H...H.L$.H. - 0020 7424e848 85f60f8e bb010000 4c89c048 t$.H........L..H - 0030 c1e60448 f7d84889 5424f048 89fb4989 ...H..H.T$.H..I. - 0040 ff4a8d34 06488d84 c2800000 00c5fb10 .J.4.H.......... - 0050 0d000000 004c8944 24f84c29 c34c89c7 .....L.D$.L).L.. - 0060 4c8d2ccd 00000000 49c1e707 4989d649 L.,.....I...I..I - 0070 89f04889 c50f1f00 4c89f049 83ee804d ..H.....L..I...M - 0080 85e40f8e 2b010000 4989ea48 89fe4d29 ....+...I..H..M) - 0090 f241bb01 00000048 f7de4d01 ca4929fb .A.....H..M..I). - 00a0 4c89caeb 2a0f1f00 4883fe0f 0f8ece00 L...*...H....... - 00b0 000048ff c64883ea 804c01e8 4981c288 ..H..H...L..I... - 00c0 00000049 ffc34839 de0f84e1 00000048 ...I..H9.......H - 00d0 8d0c3e48 39cf7ed0 4885f679 d5c5fb10 ..>H9.~.H..y.... - 00e0 00c5fb11 02c5fb10 4008c5fb 114208c5 ........@....B.. - 00f0 fb104010 c5fb1142 10c5fb10 4018c5fb ..@....B....@... - 0100 114218c5 fb104020 c5fb1142 20c5fb10 .B....@ ...B ... - 0110 4028c5fb 114228c5 fb104030 c5fb1142 @(...B(...@0...B - 0120 30c5fb10 4038c5fb 114238c5 fb104040 0...@8...B8...@@ - 0130 c5fb1142 40c5fb10 4048c5fb 114248c5 ...B@...@H...BH. - 0140 fb104050 c5fb1142 50c5fb10 4058c5fb ..@P...BP...@X.. - 0150 114258c5 fb104060 c5fb1142 60c5fb10 .BX...@`...B`... - 0160 4068c5fb 114268c5 fb104070 c5fb1142 @h...Bh...@p...B - 0170 70c5fb10 4078c5fb 114278e9 32ffffff p...@x...Bx.2... - 0180 c4c17b11 0a4c89d9 4983fb10 0f8420ff ..{..L..I..... . - 0190 ffff660f 1f440000 c5fb1004 c8c5fb11 ..f..D.......... - 01a0 04ca48ff c14883f9 1075ede9 02ffffff ..H..H...u...... - 01b0 4d01f948 83c71048 83eb104c 39c70f85 M..H...H...L9... - 01c0 b4feffff 488b5c24 e8488b6c 24f04889 ....H.\$.H.l$.H. - 01d0 d848c1e0 074c8b44 24f84801 c54889d8 .H...L.D$.H..H.. - 01e0 48c1e004 4901c0f6 4424d808 0f84d600 H...I...D$...... - 01f0 00004c8d 5d404d85 e40f8ec2 00000048 ..L.]@M........H - 0200 8b4424e0 4c89c148 f7d9be01 0000004c .D$.L..H.......L - 0210 89e34c8d 14c50000 0000c5fb 100d0000 ..L............. - 0220 0000498d 3cc94c29 c64c29c3 4c89c8eb ..I.<.L).L).L... - 0230 270f1f80 00000000 4883f907 0f8ee501 '.......H....... - 0240 000048ff c14883c0 404c01d5 4883c748 ..H..H..@L..H..H - 0250 48ffc648 39d9745f 4a8d1401 4939d07e H..H9.t_J...I9.~ - 0260 d74885c9 79dcc5fb 104500c5 fb1100c5 .H..y....E...... - 0270 fb104508 c5fb1140 08c5fb10 4510c5fb ..E....@....E... - 0280 114010c5 fb104518 c5fb1140 18c5fb10 .@....E....@.... - 0290 4520c5fb 114020c5 fb104528 c5fb1140 E ...@ ...E(...@ - 02a0 28c5fb10 4530c5fb 114030c5 fb104538 (...E0...@0...E8 - 02b0 c5fb1140 38eb8b4c 89e048c1 e0064901 ...@8..L..H...I. - 02c0 c14983c0 084c89dd f64424d8 040f84ad .I...L...D$..... - 02d0 0000004c 8d5d204d 85e40f8e 99000000 ...L.] M........ - 02e0 488b4424 e04c89c2 48f7dabe 01000000 H.D$.L..H....... - 02f0 4c89e3c5 fb100d00 0000004c 8d14c500 L..........L.... - 0300 00000049 8d3cd14c 29c64c29 c34c89c9 ...I.<.L).L).L.. - 0310 eb26660f 1f440000 4883fa03 0f8e3701 .&f..D..H.....7. - 0320 000048ff c24883c1 204c01d5 4883c728 ..H..H.. L..H..( - 0330 48ffc648 39da7437 4a8d0402 4939c07e H..H9.t7J...I9.~ - 0340 d74885d2 79dcc5fb 104500c5 fb1101c5 .H..y....E...... - 0350 fb104508 c5fb1141 08c5fb10 4510c5fb ..E....A....E... - 0360 114110c5 fb104518 c5fb1141 18ebb34c .A....E....A...L - 0370 89e048c1 e0054901 c14983c0 044c89dd ..H...I..I...L.. - 0380 f64424d8 020f8488 0000004c 8d5d104d .D$........L.].M - 0390 85e47e78 488b4424 e04c89e7 4c8d14c5 ..~xH.D$.L..L... - 03a0 00000000 4c89c048 f7d8c5fb 100d0000 ....L..H........ - 03b0 0000498d 0cc14c29 c74c89ca eb2d6690 ..I...L).L...-f. - 03c0 4885c079 13c5fb10 4500c5fb 1102c5fb H..y....E....... - 03d0 104508c5 fb114208 48ffc048 83c2104c .E....B.H..H...L - 03e0 01d54883 c1184839 c7741749 8d340049 ..H...H9.t.I.4.I - 03f0 39f07fcc 4883f801 7fdec5fb 110975ce 9...H.........u. - 0400 ebd64c89 e048c1e0 044901c1 4983c002 ..L..H...I..I... - 0410 4c89ddf6 4424d801 756f5b5d 415c415d L...D$..uo[]A\A] - 0420 415e31c0 415fc3c5 fb110f48 89f24883 A^1.A_.....H..H. - 0430 fe080f84 0afeffff 0f1f8400 00000000 ................ - 0440 c5fb1044 d500c5fb 1104d048 ffc24883 ...D.......H..H. - 0450 fa0875ec e9e9fdff ffc5fb11 0f4889f0 ..u..........H.. - 0460 4883fe04 0f84b8fe ffff660f 1f440000 H.........f..D.. - 0470 c5fb1044 c500c5fb 1104c148 ffc04883 ...D.......H..H. - 0480 f80475ec e999feff ff4d85e4 7e8c488b ..u......M..~.H. - 0490 4c24e04c 89c248f7 da4c89c6 c5fb100d L$.L..H..L...... - 04a0 00000000 48c1e103 498d3cd1 31c048c1 ....H...I.<.1.H. - 04b0 e604eb1d 0f1f4000 7505c5fb 110c3748 ......@.u.....7H - 04c0 ffc04801 cd48ffc2 4939c40f 8449ffff ..H..H..I9...I.. - 04d0 ff4939c0 7ee24885 d279e4c5 fb104500 .I9.~.H..y....E. - 04e0 c4c17b11 04c1ebd7 ..{..... + 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t + 0010 24d848c1 fe024889 7c24e048 894c24f0 $.H...H.|$.H.L$. + 0020 4c894424 d0488974 24e84885 f60f8ec9 L.D$.H.t$.H..... + 0030 02000048 89cb488d 044948c1 e305488d ...H..H..IH...H. + 0040 14c50000 00004989 da4889f8 4889fb48 ......I..H..H..H + 0050 c1f80283 e3024989 c548895c 24b8498d ......I..H.\$.I. + 0060 1cb04889 4424b04d 0fafea48 895c24a8 ..H.D$.M...H.\$. + 0070 83e70148 8d1c8500 00000048 c1e00748 ...H.......H...H + 0080 897c24c0 48894424 c84989cf 62e1ff08 .|$.H.D$.I..b... + 0090 10050000 00004c89 6424f84d 01e54c89 ......L.d$.M..L. + 00a0 e54c8d34 cd000000 0049c1e7 044d89c3 .L.4.....I...M.. + 00b0 4989d40f 1f440000 48837c24 b000498d I....D..H.|$..I. + 00c0 142e498d 342f4a8d 7c25000f 8eff0300 ..I.4/J.|%...... + 00d0 004889e9 4c89c845 31c0e9bb 00000090 .H..L..E1....... + 00e0 0f8e9b00 0000c57b 1039c57b 107108c5 .......{.9.{.q.. + 00f0 7b106910 c57b1061 18c57b10 1ac57b10 {.i..{.a..{...{. + 0100 5208c57b 104a10c5 7b104218 c5fb103e R..{.J..{.B....> + 0110 c5fb1076 08c5fb10 6e10c5fb 106618c5 ...v....n....f.. + 0120 fb101fc5 fb105708 c5fb104f 10c5fb10 ......W....O.... + 0130 4718c57b 1138c57b 117008c5 7b116810 G..{.8.{.p..{.h. + 0140 c57b1160 18c57b11 5820c57b 115028c5 .{.`..{.X .{.P(. + 0150 7b114830 c57b1140 38c5fb11 7840c5fb {.H0.{.@8...x@.. + 0160 117048c5 fb116850 c5fb1160 58c5fb11 .pH...hP...`X... + 0170 5860c5fb 115068c5 fb114870 c5fb1140 X`...Ph...Hp...@ + 0180 784983c0 044c01d1 4c01d24c 01d64c01 xI...L..L..L..L. + 0190 d74883e8 804939d8 74664d39 c30f853d .H...I9.tfM9...= + 01a0 ffffffc5 fb106908 c5fb1061 10c5fb10 ......i....a.... + 01b0 5918c5fb 105210c5 fb104a18 c5fb1046 Y....R....J....F + 01c0 1862e1ff 081100c5 fb116808 c5fb1160 .b........h....` + 01d0 10c5fb11 581862e1 ff081140 05c5fb11 ....X.b....@.... + 01e0 5030c5fb 11483862 e1ff0811 400ac5fb P0...H8b....@... + 01f0 11405862 e1ff0811 400feb85 0f1f4000 .@Xb....@.....@. + 0200 4c89e84b 8d142e4c 034c24c8 4889d948 L..K...L.L$.H..H + 0210 837c24b8 00746b49 39cb0f84 b0010000 .|$..tkI9....... + 0220 7e55c5fb 1038c5fb 107008c5 fb106810 ~U...8...p....h. + 0230 c5fb1060 18c5fb10 1ac5fb10 5208c5fb ...`........R... + 0240 104a10c5 fb104218 c4c17b11 39c4c17b .J....B...{.9..{ + 0250 117108c4 c17b1169 10c4c17b 116118c4 .q...{.i...{.a.. + 0260 c17b1159 20c4c17b 115128c4 c17b1149 .{.Y ..{.Q(..{.I + 0270 30c4c17b 1141384c 01f84983 c1404883 0..{.A8L..I..@H. + 0280 c1024883 7c24c000 74394c39 d90f840d ..H.|$..t9L9.... + 0290 0100007d 2ac5fb10 18c5fb10 5008c5fb ...}*.......P... + 02a0 104810c5 fb104018 c4c17b11 19c4c17b .H....@...{....{ + 02b0 115108c4 c17b1149 10c4c17b 11411849 .Q...{.I...{.A.I + 02c0 83c12049 83c30448 83c52049 83c5204c .. I...H.. I.. L + 02d0 395c24a8 0f85defd ffff488b 5c24e84c 9\$.......H.\$.L + 02e0 8b6424f8 4889d848 c1e00549 01c4488b .d$.H..H...I..H. + 02f0 4424d048 8d049848 894424d0 f64424d8 D$.H...H.D$..D$. + 0300 020f845c 0100004c 8b5424e0 488b4424 ...\...L.T$.H.D$ + 0310 f049d1fa 498d34c4 4d85d20f 8ec80100 .I..I.4.M....... + 0320 0048c1e0 044889c7 c5fb1025 00000000 .H...H.....%.... + 0330 4c8b5c24 d04f8d04 124c89e1 4c89c831 L.\$.O...L..L..1 + 0340 d2eb430f 1f440000 7d25c5fb 1019c5fb ..C..D..}%...... + 0350 105108c5 fb100ec5 fb104608 c5fb1118 .Q........F..... + 0360 c5fb1150 08c5fb11 4810c5fb 11401848 ...P....H....@.H + 0370 83c20248 01f94801 fe4883c0 204939d0 ...H..H..H.. I9. + 0380 0f849300 00004c39 da75bdc5 fb104108 ......L9.u....A. + 0390 c5fb1120 c5fb1140 08c5fb11 6018ebcf ... ...@....`... + 03a0 c5fb1050 08c5fb10 4810c5fb 10401862 ...P....H....@.b + 03b0 c1ff0811 01c4c17b 115108c4 c17b1149 .......{.Q...{.I + 03c0 10c4c17b 114118e9 f3feffff 0f1f4000 ...{.A........@. + 03d0 c5fb1060 08c5fb10 5810c5fb 105018c5 ...`....X....P.. + 03e0 fb104a10 c5fb1042 1862c1ff 081101c4 ..J....B.b...... + 03f0 c17b1161 08c4c17b 115910c4 c17b1151 .{.a...{.Y...{.Q + 0400 1862c1ff 08114105 c4c17b11 4930c4c1 .b....A...{.I0.. + 0410 7b114138 e95efeff ff490faf fa4c89d0 {.A8.^...I...L.. + 0420 48c1e005 4c01e749 01c14d01 d2f64424 H...L..I..M...D$ + 0430 e0017425 4c3b5424 d00f849b 0000007d ..t%L;T$.......} + 0440 14c5fb10 0fc5fb10 4708c4c1 7b1109c4 ........G...{... + 0450 c17b1141 084983c1 10488344 24d00249 .{.A.I...H.D$..I + 0460 83c410f6 4424d801 7455488b 7424e048 ....D$..tUH.t$.H + 0470 85f67e4b 488b5424 f0c5fb10 0d000000 ..~KH.T$........ + 0480 00488b4c 24d048c1 e20331c0 eb1b6690 .H.L$.H...1...f. + 0490 7e0cc4c1 7b100424 c4c17b11 04c148ff ~...{..$..{...H. + 04a0 c04901d4 4839c674 164839c1 75e248ff .I..H9.t.H9.u.H. + 04b0 c0c4c17b 110cc949 01d44839 c675ea5b ...{...I..H9.u.[ + 04c0 5d415c41 5d415e31 c0415fc3 0f1f4000 ]A\A]A^1.A_...@. + 04d0 4889e831 c9e935fd ffff488b 05000000 H..1..5...H..... + 04e0 00498901 e96cffff ff4c89e7 4531d2e9 .I...l...L..E1.. + 04f0 39ffffff 9... /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iltucopy_SKYLAKEX.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 e8040000 00420e10 8f02420e .........B....B. + 0020 00000000 f4040000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606440e 38830703 0b040a0e 30410e28 ..D.8.......0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0040 8606410e 38830703 b3040a0e 30410e28 ..A.8.......0A.( + 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_COOPERLAKE.o (disasm) @@ -6,464 +6,279 @@ dtrsm_iunncopy_COOPERLAKE: push %r15 - mov %rdi,%r15 push %r14 push %r13 push %r12 + mov %rdx,%r12 push %rbp push %rbx - sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,-offset(%rsp) test %rsi,%rsi jle + mov %rdi,%r13 + sar $something,%r13 mov %rcx,%rbx - lea (%rbx,%rbx,2),%rax - mov %rdx,%r14 - lea offset(,%rax,8),%rdi - lea (%rbx,%rbx,4),%rdx - mov %rdi,offset(%rsp) - lea offset(,%rdx,8),%rdi - mov %rdi,offset(%rsp) - mov %rax,%rdi - shl $something,%rax - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - shl $something,%rdi - mov %rdi,offset(%rsp) - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - imul $something,%rbx,%rdi - lea offset(,%rcx,8),%r13 - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - shl $something,%rcx - mov %rcx,offset(%rsp) - mov %rbx,%rcx - shl $something,%rcx - mov %rdi,offset(%rsp) - mov %rax,offset(%rsp) - mov %rbx,%rdi - mov %r8,%rax - imul %r13,%rax - shl $something,%rdi - mov %rcx,offset(%rsp) - lea offset(%r13,%rbx,1),%rcx - mov %rdi,offset(%rsp) - lea offset(,%rcx,8),%rdi - mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi + mov %r13,%r14 + shl $something,%r14 + mov %rsi,%rdx shl $something,%rbx - mov %rbx,offset(%rsp) - mov %r14,%rbx - sub %rax,%r14 - mov %rsi,%rax - shl $something,%rax - add %r8,%rax - mov %rax,offset(%rsp) - mov %r15,%rax - shl $something,%rdx + lea (%rcx,%rcx,2),%rax + mov %rcx,%rsi + lea offset(,%rcx,8),%r15 shl $something,%rax - mov %rdx,offset(%rsp) - mov %rdi,offset(%rsp) - mov %r14,offset(%rsp) - mov %rax,offset(%rsp) - mov %r15,-offset(%rsp) - vmovsd offset(%rip),%xmm1 # - lea offset(%r13),%r12 - mov %r8,%rbp - nopl offset(%rax,%rax,1) - lea offset(%r13,%rbx,1),%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - mov %rbx,%r8 - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - lea (%rax,%rbx,1),%rsi - mov offset(%rsp),%rax - lea (%rax,%rbx,1),%r14 - mov offset(%rsp),%rax - lea (%rax,%rbx,1),%r15 - add offset(%rsp),%rbx - cmpq $something,-offset(%rsp) - jle - mov -offset(%rsp),%rcx - mov offset(%rsp),%r10 - mov %rbp,%rax - neg %rax - mov $something,%edi + lea (%r8,%rdx,4),%rcx mov %rbx,-offset(%rsp) - lea (%rcx,%rax,8),%r9 - sub %rbp,%rdi - lea offset(%r13,%r10,1),%r11 - mov %rcx,%rax - xor %edx,%edx - mov %rsi,%rbx + add %r14,%rbx + mov %rdi,%r10 + mov %rcx,-offset(%rsp) + mov %rbx,-offset(%rsp) + shl $something,%rsi + lea (%rax,%r14,1),%rbx + lea (%r15,%r14,1),%rcx + and $something,%r10d + mov %rbx,-offset(%rsp) + mov %rsi,-offset(%rsp) + mov %r13,%rbx + mov %rcx,-offset(%rsp) + mov %r8,-offset(%rsp) + shl $something,%rbx + mov %r10,-offset(%rsp) + vmovsd offset(%rip),%xmm16 # + mov %rdi,%r10 + and $something,%rdi + mov %rbx,-offset(%rsp) + mov %r12,-offset(%rsp) + mov %r12,%rbx + and $something,%r10d + mov %rdi,%rbp + mov %r8,%r11 + mov %rax,%r12 + nopl (%rax) + mov -offset(%rsp),%rax + lea (%r15,%rbx,1),%rsi + lea (%rax,%rbx,1),%rcx + lea (%rbx,%r12,1),%rdx + test %r13,%r13 + jle + mov %rbx,%rdi + mov %r9,%rax + xor %r8d,%r8d jmp - xchg %ax,%ax - lea -offset(%rdi),%rcx - sub $something,%rax - cmp $something,%rcx + nopl offset(%rax,%rax,1) jle - inc %rdx + vmovsd (%rdi),%xmm15 + vmovsd offset(%rdi),%xmm11 + vmovsd offset(%rdi),%xmm7 + vmovsd offset(%rdi),%xmm3 + vmovsd (%rsi),%xmm14 + vmovsd offset(%rsi),%xmm10 + vmovsd offset(%rsi),%xmm6 + vmovsd offset(%rsi),%xmm2 /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_COOPERLAKE.o (objdump) @@ -2,141 +2,90 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574989 ff415641 55415455 534881ec AWI..AVAUATUSH.. - 0010 b8000000 4889b424 a0000000 48c1fe04 ....H..$....H... - 0020 48899424 98000000 48898c24 a8000000 H..$....H..$.... - 0030 4c890424 4c894c24 f04889b4 24b00000 L..$L.L$.H..$... - 0040 004885f6 0f8ec703 00004889 cb488d04 .H........H..H.. - 0050 5b4989d6 488d3cc5 00000000 488d149b [I..H.<.....H... - 0060 48897c24 58488d3c d5000000 0048897c H.|$XH.<.....H.| - 0070 24604889 c748c1e0 05488984 24800000 $`H..H...H..$... - 0080 00486bc3 6848c1e7 0448897c 24684889 .Hk.hH...H.|$hH. - 0090 44243848 6bc37048 6bfb384c 8d2ccd00 D$8Hk.pHk.8L.,.. - 00a0 00000048 89442440 486bc378 48c1e104 ...H.D$@Hk.xH... - 00b0 48894c24 104889d9 48c1e105 48897c24 H.L$.H..H...H.|$ - 00c0 20488944 24484889 df4c89c0 490fafc5 H.D$HH..L..I... - 00d0 48c1e706 48894c24 18498d4c 1d004889 H...H.L$.I.L..H. - 00e0 7c242848 8d3ccd00 00000048 897c2470 |$(H.<.....H.|$p - 00f0 486bfb58 48c1e307 48895c24 084c89f3 Hk.XH...H.\$.L.. - 0100 4929c648 89f048c1 e0044c01 c0488944 I).H..H...L..H.D - 0110 24504c89 f848c1e2 0448c1e0 07488954 $PL..H...H...H.T - 0120 24784889 7c24304c 89b42490 00000048 $xH.|$0L..$....H - 0130 89842488 0000004c 897c2488 c5fb100d ..$....L.|$..... - 0140 00000000 4d8d6508 4c89c50f 1f440000 ....M.e.L....D.. - 0150 498d441d 00488944 2490488b 44241049 I.D..H.D$.H.D$.I - 0160 89d84801 d8488944 2498488b 44245848 ..H..H.D$.H.D$XH - 0170 01d84889 4424a048 8b442418 4801d848 ..H.D$.H.D$.H..H - 0180 894424a8 488b4424 604801d8 48894424 .D$.H.D$`H..H.D$ - 0190 b0488b44 24684801 d8488944 24b8488b .H.D$hH..H.D$.H. - 01a0 44242048 01d84889 4424c048 8b442428 D$ H..H.D$.H.D$( - 01b0 4801d848 894424c8 488b4424 704801d8 H..H.D$.H.D$pH.. - 01c0 48894424 d0488b44 24784801 d8488944 H.D$.H.D$xH..H.D - 01d0 24d8488b 44243048 01d84889 4424e048 $.H.D$0H..H.D$.H - 01e0 8b842480 00000048 01d84889 4424e848 ..$....H..H.D$.H - 01f0 8b442438 488d3418 488b4424 404c8d34 .D$8H.4.H.D$@L.4 - 0200 18488b44 24484c8d 3c184803 5c240848 .H.D$HL.<.H.\$.H - 0210 837c2488 000f8eb7 01000048 8b4c24f0 .|$........H.L$. - 0220 4c8b9424 90000000 4889e848 f7d8bf01 L..$....H..H.... - 0230 00000048 895c24f8 4c8d0cc1 4829ef4f ...H.\$.L...H).O - 0240 8d5c1500 4889c831 d24889f3 eb366690 .\..H..1.H...6f. - 0250 488d4fff 4883e880 4883f90f 0f8e1e01 H.O.H...H....... - 0260 000048ff c24983c0 084d01e2 4981c188 ..H..I...M..I... - 0270 00000048 ffc74d01 e3483954 24880f84 ...H..M..H9T$... - 0280 3c010000 4839ea7d c74889fe 48ffce0f <...H9.}.H..H... - 0290 89dd0000 00c4c17b 1000488b 4c2490c5 .......{..H.L$.. - 02a0 fb1100c5 fb1004d1 488b7424 98c5fb11 ........H.t$.... - 02b0 4008c5fb 1004d648 8b4c24a0 c5fb1140 @......H.L$....@ - 02c0 10c5fb10 04d1488b 7424a8c5 fb114018 ......H.t$....@. - 02d0 c5fb1004 d6488b4c 24b0c5fb 114020c5 .....H.L$....@ . - 02e0 fb1004d1 488b7424 b8c5fb11 4028c5fb ....H.t$....@(.. - 02f0 1004d648 8b4c24c0 c5fb1140 30c5fb10 ...H.L$....@0... - 0300 04d1488b 7424c8c5 fb114038 c5fb1004 ..H.t$....@8.... - 0310 d6488b4c 24d0c5fb 114040c5 fb1004d1 .H.L$....@@..... - 0320 488b7424 d8c5fb11 4048c5fb 1004d6c5 H.t$....@H...... - 0330 fb114050 488b4c24 e0488b74 24e8c5fb ..@PH.L$.H.t$... - 0340 1004d1c5 fb114058 c5fb1004 d6c5fb11 ......@X........ - 0350 4060c5fb 1004d3c5 fb114068 c4c17b10 @`........@h..{. - 0360 04d6c5fb 114070c4 c17b1004 d7c5fb11 .....@p..{...... - 0370 40784883 e880e9e7 feffff0f 1f440000 @xH..........D.. - 0380 c4c1735e 02c4c17b 11014883 ff100f84 ..s^...{..H..... - 0390 cefeffff 498d4908 4c89de0f 1f440000 ....I.I.L....D.. - 03a0 c5fb1006 4883c108 c5fb1141 f84c01ee ....H......A.L.. - 03b0 4839c175 ebe9a8fe ffff660f 1f440000 H9.u......f..D.. - 03c0 488bbc24 88000000 488b5c24 f848017c H..$....H.\$.H.| - 03d0 24f04883 c510483b 6c24500f 856ffdff $.H...H;l$P..o.. - 03e0 ff488bbc 24b00000 00488b44 2408488b .H..$....H.D$.H. - 03f0 1c24480f afc74c8b 7c248848 01842498 .$H...L.|$.H..$. - 0400 00000048 89f848c1 e0044801 d8488904 ...H..H...H..H.. - 0410 24f68424 a0000000 080f8464 01000048 $..$.......d...H - 0420 8b8424a8 00000048 8bbc2498 0000004c ..$....H..$....L - 0430 8d04c500 0000004a 8d2c074a 8d440500 .......J.,.J.D.. - 0440 48894424 884c01c0 48894424 904c01c0 H.D$.L..H.D$.L.. - 0450 4e8d3400 4f8d2c06 4f8d6405 00488944 N.4.O.,.O.d..H.D - 0460 24984b8d 04044889 4424a84d 85ff0f8e $.K...H.D$.M.... - 0470 fd000000 488b0c24 be010000 004889c8 ....H..$.....H.. - 0480 48f7d849 89c24829 ce4d89c1 4d0fafd0 H..I..H).M..M... - 0490 4c0fafce 488b5424 f04c8974 24a04c8d L...H.T$.L.t$.L. - 04a0 1cc24989 eec5fb10 0d000000 00498d58 ..I..........I.X - 04b0 084901fa 4901f931 c04889fd eb2d6690 .I..I..1.H...-f. - 04c0 488d4eff 4883f907 0f8e2803 000048ff H.N.H.....(...H. - 04d0 c04883c5 084883c2 404901da 4983c348 .H...H..@I..I..H - 04e0 48ffc649 01d94939 c7747a48 3b04247d H..I..I9.tzH;.$} - 04f0 cf4889f7 48ffcf79 d5c5fb10 4500488b .H..H..y....E.H. - 0500 7c2488c5 fb1102c4 c17b1004 c6c5fb11 |$.......{...... - 0510 4208c5fb 1004c748 8b7c2490 c5fb1142 B......H.|$....B - 0520 10c5fb10 04c7488b 7c2498c5 fb114218 ......H.|$....B. - 0530 c5fb1004 c7488b7c 24a0c5fb 114220c5 .....H.|$....B . - 0540 fb1004c7 c5fb1142 28c4c17b 1044c500 .......B(..{.D.. - 0550 c5fb1142 30c4c17b 1004c4c5 fb114238 ...B0..{......B8 - 0560 e969ffff ff4c89f8 48c1e006 48014424 .i...L..H...H.D$ - 0570 f0488b44 24a84883 04240848 89842498 .H.D$.H..$.H..$. - 0580 000000f6 8424a000 0000040f 841f0100 .....$.......... - 0590 004c8b84 24a80000 00488bac 24980000 .L..$....H..$... - 05a0 004e8d0c c5000000 004a8d5c 0d004e8d .N.......J.\..N. - 05b0 1c0b4b8d 0c0b4e8d 2c094d85 ff0f8ee0 ..K...N.,.M..... - 05c0 0000004c 8b3424be 01000000 4c89f24c ...L.4$.....L..L - 05d0 29f6490f aff148f7 da488d04 d5000000 ).I...H..H...... - 05e0 004829c1 488b7c24 f04801ee 4889cd4c .H).H.|$.H..H..L - 05f0 89c14d89 fc48f7d9 4801c74d 29f44829 ..M..H..H..M).H) - 0600 c34929c3 4c896c24 9048894c 2488488b .I).L.l$.H.L$.H. - 0610 4424f0c5 fb100d00 0000004c 8b842498 D$.........L..$. - 0620 0000004c 8b34244d 8d5108eb 280f1f00 ...L.4$M.Q..(... - 0630 4c8d6a01 4883fa03 0f8e0802 00004983 L.j.H.........I. - 0640 c0084883 c0204c89 ea4883c7 284c01d6 ..H.. L..H..(L.. - 0650 4d39e574 3d498d0c 164939ce 7ed24885 M9.t=I...I9.~.H. - 0660 d27929c4 c17b1000 c5fb1100 c5fb1004 .y)..{.......... - 0670 d3c5fb11 4008c4c1 7b1004d3 c5fb1140 ....@...{......@ - 0680 10c5fb10 44d500c5 fb114018 4c8d6a01 ....D.....@.L.j. - 0690 ebac4c89 f848c1e0 05480144 24f04c8b ..L..H...H.D$.L. - 06a0 6c249048 83042404 4c89ac24 98000000 l$.H..$.L..$.... - 06b0 f68424a0 00000002 0f84b100 0000488b ..$...........H. - 06c0 8424a800 0000488b 9c249800 000048c1 .$....H..$....H. - 06d0 e0034c8d 04034d8d 14004d85 ff0f8e7f ..L...M...M..... - 06e0 0000004c 8b1c244c 8d48084c 89de48f7 ...L..$L.H.L..H. - 06f0 de480faf c6488b4c 24f0c5fb 100d0000 .H...H.L$....... - 0700 00004801 d8488d3c f131d2eb 320f1f00 ..H..H.<.1..2... - 0710 4885f679 14c5fb10 04d3c5fb 1101c4c1 H..y............ - 0720 7b1004d0 c5fb1141 0848ffc2 4883c110 {......A.H..H... - 0730 48ffc64c 01c84883 c7184939 d7741749 H..L..H...I9.t.I - 0740 39d37fcc 4883fe01 7fdfc5f3 5e00c5fb 9...H.......^... - 0750 110775ca ebd34c89 f848c1e0 04480144 ..u...L..H...H.D - 0760 24f04883 0424024c 89942498 000000f6 $.H..$.L..$..... - 0770 8424a000 00000174 694d85ff 7e64488b .$.....tiM..~dH. - 0780 3c244c8b 4c24f048 89fa48f7 da4889f9 <$L.L$.H..H..H.. - 0790 c5fb100d 00000000 4c8b8424 98000000 ........L..$.... - 07a0 498d34d1 31c048c1 e104eb15 0f1f4000 I.4.1.H.......@. - 07b0 0f84cc00 000048ff c048ffc2 4939c774 ......H..H..I9.t - 07c0 214839c7 7eea4885 d279ebc4 c17b1004 !H9.~.H..y...{.. - 07d0 c048ffc2 c4c17b11 04c148ff c04939c7 .H....{...H..I9. - 07e0 75df4881 c4b80000 005b5d41 5c415d41 u.H......[]A\A]A - 07f0 5e31c041 5fc3c4c1 735e02c4 c17b1103 ^1.A_...s^...{.. - 0800 4883fe08 0f84c4fc ffff488d 4a384889 H.........H.J8H. - 0810 4c24b048 894424b8 4c89cf48 8b4424b0 L$.H.D$.L..H.D$. - 0820 4c89d90f 1f440000 c5fb1007 4883c108 L....D......H... - 0830 c5fb1101 4c01c748 39c175ec 488b4424 ....L..H9.u.H.D$ - 0840 b8e988fc ffff488b 4c24884c 89eac5f3 ......H.L$.L.... - 0850 5e04cec5 fb110749 83fd040f 84ddfdff ^......I........ - 0860 ff4889f1 0f1f4000 c5fb1001 4c01c9c5 .H....@.....L... - 0870 fb1104d0 48ffc248 83fa0475 ebe9bcfd ....H..H...u.... - 0880 ffffc4c1 735e04f8 c5fb1104 0ee924ff ....s^........$. - 0890 ffff .. + 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t + 0010 24d048c1 fe024889 7c24d848 894c24f8 $.H...H.|$.H.L$. + 0020 48897424 e04885f6 0f8e2503 00004989 H.t$.H....%...I. + 0030 fd49c1fd 024889cb 4d89ee49 c1e60548 .I...H..M..I...H + 0040 89f248c1 e304488d 04494889 ce4c8d3c ..H...H..IH..L.< + 0050 cd000000 0048c1e0 03498d0c 9048895c .....H...I...H.\ + 0060 24984c01 f34989fa 48894c24 a048895c $.L..I..H.L$.H.\ + 0070 24c848c1 e6054a8d 1c304b8d 0c374183 $.H...J..0K..7A. + 0080 e2024889 5c24c048 89742490 4c89eb48 ..H.\$.H.t$.L..H + 0090 894c24b8 4c894424 f048c1e3 074c8954 .L$.L.D$.H...L.T + 00a0 24a862e1 ff081005 00000000 4989fa48 $.b.........I..H + 00b0 83e7fc48 895c24b0 4c896424 e84c89e3 ...H.\$.L.d$.L.. + 00c0 4183e201 4889fd4d 89c34989 c40f1f00 A...H..M..I..... + 00d0 488b4424 98498d34 1f488d0c 184a8d14 H.D$.I.4.H...J.. + 00e0 234d85ed 0f8e4e04 00004889 df4c89c8 #M....N...H..L.. + 00f0 4531c0e9 ca000000 0f1f8400 00000000 E1.............. + 0100 0f8e9b00 0000c57b 103fc57b 105f08c5 .......{.?.{._.. + 0110 fb107f10 c5fb105f 18c57b10 36c57b10 ......._..{.6.{. + 0120 5608c5fb 107610c5 fb105618 c57b1029 V....v....V..{.) + 0130 c57b1049 08c5fb10 6910c5fb 104918c5 .{.I....i....I.. + 0140 7b1022c5 7b104208 c5fb1062 10c5fb10 {.".{.B....b.... + 0150 4218c57b 1138c57b 117008c5 7b116810 B..{.8.{.p..{.h. + 0160 c57b1160 18c57b11 5820c57b 115028c5 .{.`..{.X .{.P(. + 0170 7b114830 c57b1140 38c5fb11 7840c5fb {.H0.{.@8...x@.. + 0180 117048c5 fb116850 c5fb1160 58c5fb11 .pH...hP...`X... + 0190 5860c5fb 115068c5 fb114870 c5fb1140 X`...Ph...Hp...@ + 01a0 784983c0 044883c7 204883c6 204883c1 xI...H.. H.. H.. + 01b0 204883c2 204883e8 804939e8 0f848600 H.. H...I9..... + 01c0 00004d39 c30f8535 ffffffc5 fb105608 ..M9...5......V. + 01d0 c5fb1049 10c5fb10 421862f1 ff005ed2 ...I....B.b...^. + 01e0 c57b1006 c5fb1039 c5fb1069 08c5fb10 .{.....9...i.... + 01f0 32c5fb10 6208c5fb 105a1062 71ff005e 2...b....Z.bq..^ + 0200 0fc57b11 4008c57b 1108c5fb 117810c5 ..{.@..{.....x.. + 0210 fb117018 c5fb1168 30c5fb11 6038c5fb ..p....h0...`8.. + 0220 11585862 f1ff005e c9c5fb11 502862f1 .XXb...^....P(b. + 0230 ff005ec0 c5fb1148 50c5fb11 4078e95e ..^....HP...@x.^ + 0240 ffffff0f 1f440000 488b7c24 b84a8d04 .....D..H.|$.J.. + 0250 33488d34 3b488b7c 24c84c03 4c24b048 3H.4;H.|$.L.L$.H + 0260 8d0c3b48 8b7c24c0 488d143b 4889ef48 ..;H.|$.H..;H..H + 0270 837c24a8 00746e49 39fb0f84 60020000 .|$..tnI9...`... + 0280 7e53c5fb 1038c5fb 107008c5 fb102ec5 ~S...8...p...... + 0290 fb106608 c5fb1019 c5fb1051 08c5fb10 ..f........Q.... + 02a0 0ac5fb10 4208c4c1 7b1139c4 c17b1171 ....B...{.9..{.q + 02b0 08c4c17b 116910c4 c17b1161 18c4c17b ...{.i...{.a...{ + 02c0 115920c4 c17b1151 28c4c17b 114930c4 .Y ..{.Q(..{.I0. + 02d0 c17b1141 384883c0 104883c6 104983c1 .{.A8H...H...I.. + 02e0 404883c7 024d85d2 74364c39 df0f84bd @H...M..t6L9.... + 02f0 0100007d 27c5fb10 18c5fb10 16c5fb10 ...}'........... + 0300 09c5fb10 02c4c17b 1119c4c1 7b115108 .......{....{.Q. + 0310 c4c17b11 4910c4c1 7b114118 4983c120 ..{.I...{.A.I.. + 0320 4983c304 48035c24 904c3b5c 24a00f85 I...H.\$.L;\$... + 0330 9cfdffff 488b5c24 e0488b44 24904c8b ....H.\$.H.D$.L. + 0340 6424e848 0fafc34c 8b4424f0 4901c44d d$.H...L.D$.I..M + 0350 8d0498f6 4424d002 0f84f100 00004c8b ....D$........L. + 0360 5424f848 8b7c24d8 49c1e203 48d1ff4b T$.H.|$.I...H..K + 0370 8d0c1448 85ff0f8e e8010000 c5fb1025 ...H...........% /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_COOPERLAKE.o (objdump) @@ -3,9 +3,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 92080000 00420e10 8f02450e .........B....E. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ef00103 d5070a0e ..A.8..G........ - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0010 1b0c0708 90010000 44000000 1c000000 ........D....... + 0020 00000000 6e050000 00420e10 8f02420e ....n....B....B. + 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 + 0040 8606410e 38830703 93040a0e 30410e28 ..A.8.......0A.( + 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_SKYLAKEX.o (disasm) @@ -6,464 +6,279 @@ dtrsm_iunncopy_SKYLAKEX: push %r15 - mov %rdi,%r15 push %r14 push %r13 push %r12 + mov %rdx,%r12 push %rbp push %rbx - sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,-offset(%rsp) test %rsi,%rsi jle + mov %rdi,%r13 + sar $something,%r13 mov %rcx,%rbx - lea (%rbx,%rbx,2),%rax - mov %rdx,%r14 - lea offset(,%rax,8),%rdi - lea (%rbx,%rbx,4),%rdx - mov %rdi,offset(%rsp) - lea offset(,%rdx,8),%rdi - mov %rdi,offset(%rsp) - mov %rax,%rdi - shl $something,%rax - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - shl $something,%rdi - mov %rdi,offset(%rsp) - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - imul $something,%rbx,%rdi - lea offset(,%rcx,8),%r13 - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - shl $something,%rcx - mov %rcx,offset(%rsp) - mov %rbx,%rcx - shl $something,%rcx - mov %rdi,offset(%rsp) - mov %rax,offset(%rsp) - mov %rbx,%rdi - mov %r8,%rax - imul %r13,%rax - shl $something,%rdi - mov %rcx,offset(%rsp) - lea offset(%r13,%rbx,1),%rcx - mov %rdi,offset(%rsp) - lea offset(,%rcx,8),%rdi - mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi + mov %r13,%r14 + shl $something,%r14 + mov %rsi,%rdx shl $something,%rbx - mov %rbx,offset(%rsp) - mov %r14,%rbx - sub %rax,%r14 - mov %rsi,%rax - shl $something,%rax - add %r8,%rax - mov %rax,offset(%rsp) - mov %r15,%rax - shl $something,%rdx + lea (%rcx,%rcx,2),%rax + mov %rcx,%rsi + lea offset(,%rcx,8),%r15 shl $something,%rax - mov %rdx,offset(%rsp) - mov %rdi,offset(%rsp) - mov %r14,offset(%rsp) - mov %rax,offset(%rsp) - mov %r15,-offset(%rsp) - vmovsd offset(%rip),%xmm1 # - lea offset(%r13),%r12 - mov %r8,%rbp - nopl offset(%rax,%rax,1) - lea offset(%r13,%rbx,1),%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - mov %rbx,%r8 - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - lea (%rax,%rbx,1),%rsi - mov offset(%rsp),%rax - lea (%rax,%rbx,1),%r14 - mov offset(%rsp),%rax - lea (%rax,%rbx,1),%r15 - add offset(%rsp),%rbx - cmpq $something,-offset(%rsp) - jle - mov -offset(%rsp),%rcx - mov offset(%rsp),%r10 - mov %rbp,%rax - neg %rax - mov $something,%edi + lea (%r8,%rdx,4),%rcx mov %rbx,-offset(%rsp) - lea (%rcx,%rax,8),%r9 - sub %rbp,%rdi - lea offset(%r13,%r10,1),%r11 - mov %rcx,%rax - xor %edx,%edx - mov %rsi,%rbx + add %r14,%rbx + mov %rdi,%r10 + mov %rcx,-offset(%rsp) + mov %rbx,-offset(%rsp) + shl $something,%rsi + lea (%rax,%r14,1),%rbx + lea (%r15,%r14,1),%rcx + and $something,%r10d + mov %rbx,-offset(%rsp) + mov %rsi,-offset(%rsp) + mov %r13,%rbx + mov %rcx,-offset(%rsp) + mov %r8,-offset(%rsp) + shl $something,%rbx + mov %r10,-offset(%rsp) + vmovsd offset(%rip),%xmm16 # + mov %rdi,%r10 + and $something,%rdi + mov %rbx,-offset(%rsp) + mov %r12,-offset(%rsp) + mov %r12,%rbx + and $something,%r10d + mov %rdi,%rbp + mov %r8,%r11 + mov %rax,%r12 + nopl (%rax) + mov -offset(%rsp),%rax + lea (%r15,%rbx,1),%rsi + lea (%rax,%rbx,1),%rcx + lea (%rbx,%r12,1),%rdx + test %r13,%r13 + jle + mov %rbx,%rdi + mov %r9,%rax + xor %r8d,%r8d jmp - xchg %ax,%ax - lea -offset(%rdi),%rcx - sub $something,%rax - cmp $something,%rcx + nopl offset(%rax,%rax,1) jle - inc %rdx + vmovsd (%rdi),%xmm15 + vmovsd offset(%rdi),%xmm11 + vmovsd offset(%rdi),%xmm7 + vmovsd offset(%rdi),%xmm3 + vmovsd (%rsi),%xmm14 + vmovsd offset(%rsi),%xmm10 + vmovsd offset(%rsi),%xmm6 + vmovsd offset(%rsi),%xmm2 /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_SKYLAKEX.o (objdump) @@ -2,141 +2,90 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574989 ff415641 55415455 534881ec AWI..AVAUATUSH.. - 0010 b8000000 4889b424 a0000000 48c1fe04 ....H..$....H... - 0020 48899424 98000000 48898c24 a8000000 H..$....H..$.... - 0030 4c890424 4c894c24 f04889b4 24b00000 L..$L.L$.H..$... - 0040 004885f6 0f8ec703 00004889 cb488d04 .H........H..H.. - 0050 5b4989d6 488d3cc5 00000000 488d149b [I..H.<.....H... - 0060 48897c24 58488d3c d5000000 0048897c H.|$XH.<.....H.| - 0070 24604889 c748c1e0 05488984 24800000 $`H..H...H..$... - 0080 00486bc3 6848c1e7 0448897c 24684889 .Hk.hH...H.|$hH. - 0090 44243848 6bc37048 6bfb384c 8d2ccd00 D$8Hk.pHk.8L.,.. - 00a0 00000048 89442440 486bc378 48c1e104 ...H.D$@Hk.xH... - 00b0 48894c24 104889d9 48c1e105 48897c24 H.L$.H..H...H.|$ - 00c0 20488944 24484889 df4c89c0 490fafc5 H.D$HH..L..I... - 00d0 48c1e706 48894c24 18498d4c 1d004889 H...H.L$.I.L..H. - 00e0 7c242848 8d3ccd00 00000048 897c2470 |$(H.<.....H.|$p - 00f0 486bfb58 48c1e307 48895c24 084c89f3 Hk.XH...H.\$.L.. - 0100 4929c648 89f048c1 e0044c01 c0488944 I).H..H...L..H.D - 0110 24504c89 f848c1e2 0448c1e0 07488954 $PL..H...H...H.T - 0120 24784889 7c24304c 89b42490 00000048 $xH.|$0L..$....H - 0130 89842488 0000004c 897c2488 c5fb100d ..$....L.|$..... - 0140 00000000 4d8d6508 4c89c50f 1f440000 ....M.e.L....D.. - 0150 498d441d 00488944 2490488b 44241049 I.D..H.D$.H.D$.I - 0160 89d84801 d8488944 2498488b 44245848 ..H..H.D$.H.D$XH - 0170 01d84889 4424a048 8b442418 4801d848 ..H.D$.H.D$.H..H - 0180 894424a8 488b4424 604801d8 48894424 .D$.H.D$`H..H.D$ - 0190 b0488b44 24684801 d8488944 24b8488b .H.D$hH..H.D$.H. - 01a0 44242048 01d84889 4424c048 8b442428 D$ H..H.D$.H.D$( - 01b0 4801d848 894424c8 488b4424 704801d8 H..H.D$.H.D$pH.. - 01c0 48894424 d0488b44 24784801 d8488944 H.D$.H.D$xH..H.D - 01d0 24d8488b 44243048 01d84889 4424e048 $.H.D$0H..H.D$.H - 01e0 8b842480 00000048 01d84889 4424e848 ..$....H..H.D$.H - 01f0 8b442438 488d3418 488b4424 404c8d34 .D$8H.4.H.D$@L.4 - 0200 18488b44 24484c8d 3c184803 5c240848 .H.D$HL.<.H.\$.H - 0210 837c2488 000f8eb7 01000048 8b4c24f0 .|$........H.L$. - 0220 4c8b9424 90000000 4889e848 f7d8bf01 L..$....H..H.... - 0230 00000048 895c24f8 4c8d0cc1 4829ef4f ...H.\$.L...H).O - 0240 8d5c1500 4889c831 d24889f3 eb366690 .\..H..1.H...6f. - 0250 488d4fff 4883e880 4883f90f 0f8e1e01 H.O.H...H....... - 0260 000048ff c24983c0 084d01e2 4981c188 ..H..I...M..I... - 0270 00000048 ffc74d01 e3483954 24880f84 ...H..M..H9T$... - 0280 3c010000 4839ea7d c74889fe 48ffce0f <...H9.}.H..H... - 0290 89dd0000 00c4c17b 1000488b 4c2490c5 .......{..H.L$.. - 02a0 fb1100c5 fb1004d1 488b7424 98c5fb11 ........H.t$.... - 02b0 4008c5fb 1004d648 8b4c24a0 c5fb1140 @......H.L$....@ - 02c0 10c5fb10 04d1488b 7424a8c5 fb114018 ......H.t$....@. - 02d0 c5fb1004 d6488b4c 24b0c5fb 114020c5 .....H.L$....@ . - 02e0 fb1004d1 488b7424 b8c5fb11 4028c5fb ....H.t$....@(.. - 02f0 1004d648 8b4c24c0 c5fb1140 30c5fb10 ...H.L$....@0... - 0300 04d1488b 7424c8c5 fb114038 c5fb1004 ..H.t$....@8.... - 0310 d6488b4c 24d0c5fb 114040c5 fb1004d1 .H.L$....@@..... - 0320 488b7424 d8c5fb11 4048c5fb 1004d6c5 H.t$....@H...... - 0330 fb114050 488b4c24 e0488b74 24e8c5fb ..@PH.L$.H.t$... - 0340 1004d1c5 fb114058 c5fb1004 d6c5fb11 ......@X........ - 0350 4060c5fb 1004d3c5 fb114068 c4c17b10 @`........@h..{. - 0360 04d6c5fb 114070c4 c17b1004 d7c5fb11 .....@p..{...... - 0370 40784883 e880e9e7 feffff0f 1f440000 @xH..........D.. - 0380 c4c1735e 02c4c17b 11014883 ff100f84 ..s^...{..H..... - 0390 cefeffff 498d4908 4c89de0f 1f440000 ....I.I.L....D.. - 03a0 c5fb1006 4883c108 c5fb1141 f84c01ee ....H......A.L.. - 03b0 4839c175 ebe9a8fe ffff660f 1f440000 H9.u......f..D.. - 03c0 488bbc24 88000000 488b5c24 f848017c H..$....H.\$.H.| - 03d0 24f04883 c510483b 6c24500f 856ffdff $.H...H;l$P..o.. - 03e0 ff488bbc 24b00000 00488b44 2408488b .H..$....H.D$.H. - 03f0 1c24480f afc74c8b 7c248848 01842498 .$H...L.|$.H..$. - 0400 00000048 89f848c1 e0044801 d8488904 ...H..H...H..H.. - 0410 24f68424 a0000000 080f8464 01000048 $..$.......d...H - 0420 8b8424a8 00000048 8bbc2498 0000004c ..$....H..$....L - 0430 8d04c500 0000004a 8d2c074a 8d440500 .......J.,.J.D.. - 0440 48894424 884c01c0 48894424 904c01c0 H.D$.L..H.D$.L.. - 0450 4e8d3400 4f8d2c06 4f8d6405 00488944 N.4.O.,.O.d..H.D - 0460 24984b8d 04044889 4424a84d 85ff0f8e $.K...H.D$.M.... - 0470 fd000000 488b0c24 be010000 004889c8 ....H..$.....H.. - 0480 48f7d849 89c24829 ce4d89c1 4d0fafd0 H..I..H).M..M... - 0490 4c0fafce 488b5424 f04c8974 24a04c8d L...H.T$.L.t$.L. - 04a0 1cc24989 eec5fb10 0d000000 00498d58 ..I..........I.X - 04b0 084901fa 4901f931 c04889fd eb2d6690 .I..I..1.H...-f. - 04c0 488d4eff 4883f907 0f8e2803 000048ff H.N.H.....(...H. - 04d0 c04883c5 084883c2 404901da 4983c348 .H...H..@I..I..H - 04e0 48ffc649 01d94939 c7747a48 3b04247d H..I..I9.tzH;.$} - 04f0 cf4889f7 48ffcf79 d5c5fb10 4500488b .H..H..y....E.H. - 0500 7c2488c5 fb1102c4 c17b1004 c6c5fb11 |$.......{...... - 0510 4208c5fb 1004c748 8b7c2490 c5fb1142 B......H.|$....B - 0520 10c5fb10 04c7488b 7c2498c5 fb114218 ......H.|$....B. - 0530 c5fb1004 c7488b7c 24a0c5fb 114220c5 .....H.|$....B . - 0540 fb1004c7 c5fb1142 28c4c17b 1044c500 .......B(..{.D.. - 0550 c5fb1142 30c4c17b 1004c4c5 fb114238 ...B0..{......B8 - 0560 e969ffff ff4c89f8 48c1e006 48014424 .i...L..H...H.D$ - 0570 f0488b44 24a84883 04240848 89842498 .H.D$.H..$.H..$. - 0580 000000f6 8424a000 0000040f 841f0100 .....$.......... - 0590 004c8b84 24a80000 00488bac 24980000 .L..$....H..$... - 05a0 004e8d0c c5000000 004a8d5c 0d004e8d .N.......J.\..N. - 05b0 1c0b4b8d 0c0b4e8d 2c094d85 ff0f8ee0 ..K...N.,.M..... - 05c0 0000004c 8b3424be 01000000 4c89f24c ...L.4$.....L..L - 05d0 29f6490f aff148f7 da488d04 d5000000 ).I...H..H...... - 05e0 004829c1 488b7c24 f04801ee 4889cd4c .H).H.|$.H..H..L - 05f0 89c14d89 fc48f7d9 4801c74d 29f44829 ..M..H..H..M).H) - 0600 c34929c3 4c896c24 9048894c 2488488b .I).L.l$.H.L$.H. - 0610 4424f0c5 fb100d00 0000004c 8b842498 D$.........L..$. - 0620 0000004c 8b34244d 8d5108eb 280f1f00 ...L.4$M.Q..(... - 0630 4c8d6a01 4883fa03 0f8e0802 00004983 L.j.H.........I. - 0640 c0084883 c0204c89 ea4883c7 284c01d6 ..H.. L..H..(L.. - 0650 4d39e574 3d498d0c 164939ce 7ed24885 M9.t=I...I9.~.H. - 0660 d27929c4 c17b1000 c5fb1100 c5fb1004 .y)..{.......... - 0670 d3c5fb11 4008c4c1 7b1004d3 c5fb1140 ....@...{......@ - 0680 10c5fb10 44d500c5 fb114018 4c8d6a01 ....D.....@.L.j. - 0690 ebac4c89 f848c1e0 05480144 24f04c8b ..L..H...H.D$.L. - 06a0 6c249048 83042404 4c89ac24 98000000 l$.H..$.L..$.... - 06b0 f68424a0 00000002 0f84b100 0000488b ..$...........H. - 06c0 8424a800 0000488b 9c249800 000048c1 .$....H..$....H. - 06d0 e0034c8d 04034d8d 14004d85 ff0f8e7f ..L...M...M..... - 06e0 0000004c 8b1c244c 8d48084c 89de48f7 ...L..$L.H.L..H. - 06f0 de480faf c6488b4c 24f0c5fb 100d0000 .H...H.L$....... - 0700 00004801 d8488d3c f131d2eb 320f1f00 ..H..H.<.1..2... - 0710 4885f679 14c5fb10 04d3c5fb 1101c4c1 H..y............ - 0720 7b1004d0 c5fb1141 0848ffc2 4883c110 {......A.H..H... - 0730 48ffc64c 01c84883 c7184939 d7741749 H..L..H...I9.t.I - 0740 39d37fcc 4883fe01 7fdfc5f3 5e00c5fb 9...H.......^... - 0750 110775ca ebd34c89 f848c1e0 04480144 ..u...L..H...H.D - 0760 24f04883 0424024c 89942498 000000f6 $.H..$.L..$..... - 0770 8424a000 00000174 694d85ff 7e64488b .$.....tiM..~dH. - 0780 3c244c8b 4c24f048 89fa48f7 da4889f9 <$L.L$.H..H..H.. - 0790 c5fb100d 00000000 4c8b8424 98000000 ........L..$.... - 07a0 498d34d1 31c048c1 e104eb15 0f1f4000 I.4.1.H.......@. - 07b0 0f84cc00 000048ff c048ffc2 4939c774 ......H..H..I9.t - 07c0 214839c7 7eea4885 d279ebc4 c17b1004 !H9.~.H..y...{.. - 07d0 c048ffc2 c4c17b11 04c148ff c04939c7 .H....{...H..I9. - 07e0 75df4881 c4b80000 005b5d41 5c415d41 u.H......[]A\A]A - 07f0 5e31c041 5fc3c4c1 735e02c4 c17b1103 ^1.A_...s^...{.. - 0800 4883fe08 0f84c4fc ffff488d 4a384889 H.........H.J8H. - 0810 4c24b048 894424b8 4c89cf48 8b4424b0 L$.H.D$.L..H.D$. - 0820 4c89d90f 1f440000 c5fb1007 4883c108 L....D......H... - 0830 c5fb1101 4c01c748 39c175ec 488b4424 ....L..H9.u.H.D$ - 0840 b8e988fc ffff488b 4c24884c 89eac5f3 ......H.L$.L.... - 0850 5e04cec5 fb110749 83fd040f 84ddfdff ^......I........ - 0860 ff4889f1 0f1f4000 c5fb1001 4c01c9c5 .H....@.....L... - 0870 fb1104d0 48ffc248 83fa0475 ebe9bcfd ....H..H...u.... - 0880 ffffc4c1 735e04f8 c5fb1104 0ee924ff ....s^........$. - 0890 ffff .. + 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t + 0010 24d048c1 fe024889 7c24d848 894c24f8 $.H...H.|$.H.L$. + 0020 48897424 e04885f6 0f8e2503 00004989 H.t$.H....%...I. + 0030 fd49c1fd 024889cb 4d89ee49 c1e60548 .I...H..M..I...H + 0040 89f248c1 e304488d 04494889 ce4c8d3c ..H...H..IH..L.< + 0050 cd000000 0048c1e0 03498d0c 9048895c .....H...I...H.\ + 0060 24984c01 f34989fa 48894c24 a048895c $.L..I..H.L$.H.\ + 0070 24c848c1 e6054a8d 1c304b8d 0c374183 $.H...J..0K..7A. + 0080 e2024889 5c24c048 89742490 4c89eb48 ..H.\$.H.t$.L..H + 0090 894c24b8 4c894424 f048c1e3 074c8954 .L$.L.D$.H...L.T + 00a0 24a862e1 ff081005 00000000 4989fa48 $.b.........I..H + 00b0 83e7fc48 895c24b0 4c896424 e84c89e3 ...H.\$.L.d$.L.. + 00c0 4183e201 4889fd4d 89c34989 c40f1f00 A...H..M..I..... + 00d0 488b4424 98498d34 1f488d0c 184a8d14 H.D$.I.4.H...J.. + 00e0 234d85ed 0f8e4e04 00004889 df4c89c8 #M....N...H..L.. + 00f0 4531c0e9 ca000000 0f1f8400 00000000 E1.............. + 0100 0f8e9b00 0000c57b 103fc57b 105f08c5 .......{.?.{._.. + 0110 fb107f10 c5fb105f 18c57b10 36c57b10 ......._..{.6.{. + 0120 5608c5fb 107610c5 fb105618 c57b1029 V....v....V..{.) + 0130 c57b1049 08c5fb10 6910c5fb 104918c5 .{.I....i....I.. + 0140 7b1022c5 7b104208 c5fb1062 10c5fb10 {.".{.B....b.... + 0150 4218c57b 1138c57b 117008c5 7b116810 B..{.8.{.p..{.h. + 0160 c57b1160 18c57b11 5820c57b 115028c5 .{.`..{.X .{.P(. + 0170 7b114830 c57b1140 38c5fb11 7840c5fb {.H0.{.@8...x@.. + 0180 117048c5 fb116850 c5fb1160 58c5fb11 .pH...hP...`X... + 0190 5860c5fb 115068c5 fb114870 c5fb1140 X`...Ph...Hp...@ + 01a0 784983c0 044883c7 204883c6 204883c1 xI...H.. H.. H.. + 01b0 204883c2 204883e8 804939e8 0f848600 H.. H...I9..... + 01c0 00004d39 c30f8535 ffffffc5 fb105608 ..M9...5......V. + 01d0 c5fb1049 10c5fb10 421862f1 ff005ed2 ...I....B.b...^. + 01e0 c57b1006 c5fb1039 c5fb1069 08c5fb10 .{.....9...i.... + 01f0 32c5fb10 6208c5fb 105a1062 71ff005e 2...b....Z.bq..^ + 0200 0fc57b11 4008c57b 1108c5fb 117810c5 ..{.@..{.....x.. + 0210 fb117018 c5fb1168 30c5fb11 6038c5fb ..p....h0...`8.. + 0220 11585862 f1ff005e c9c5fb11 502862f1 .XXb...^....P(b. + 0230 ff005ec0 c5fb1148 50c5fb11 4078e95e ..^....HP...@x.^ + 0240 ffffff0f 1f440000 488b7c24 b84a8d04 .....D..H.|$.J.. + 0250 33488d34 3b488b7c 24c84c03 4c24b048 3H.4;H.|$.L.L$.H + 0260 8d0c3b48 8b7c24c0 488d143b 4889ef48 ..;H.|$.H..;H..H + 0270 837c24a8 00746e49 39fb0f84 60020000 .|$..tnI9...`... + 0280 7e53c5fb 1038c5fb 107008c5 fb102ec5 ~S...8...p...... + 0290 fb106608 c5fb1019 c5fb1051 08c5fb10 ..f........Q.... + 02a0 0ac5fb10 4208c4c1 7b1139c4 c17b1171 ....B...{.9..{.q + 02b0 08c4c17b 116910c4 c17b1161 18c4c17b ...{.i...{.a...{ + 02c0 115920c4 c17b1151 28c4c17b 114930c4 .Y ..{.Q(..{.I0. + 02d0 c17b1141 384883c0 104883c6 104983c1 .{.A8H...H...I.. + 02e0 404883c7 024d85d2 74364c39 df0f84bd @H...M..t6L9.... + 02f0 0100007d 27c5fb10 18c5fb10 16c5fb10 ...}'........... + 0300 09c5fb10 02c4c17b 1119c4c1 7b115108 .......{....{.Q. + 0310 c4c17b11 4910c4c1 7b114118 4983c120 ..{.I...{.A.I.. + 0320 4983c304 48035c24 904c3b5c 24a00f85 I...H.\$.L;\$... + 0330 9cfdffff 488b5c24 e0488b44 24904c8b ....H.\$.H.D$.L. + 0340 6424e848 0fafc34c 8b4424f0 4901c44d d$.H...L.D$.I..M + 0350 8d0498f6 4424d002 0f84f100 00004c8b ....D$........L. + 0360 5424f848 8b7c24d8 49c1e203 48d1ff4b T$.H.|$.I...H..K + 0370 8d0c1448 85ff0f8e e8010000 c5fb1025 ...H...........% /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunncopy_SKYLAKEX.o (objdump) @@ -3,9 +3,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 92080000 00420e10 8f02450e .........B....E. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ef00103 d5070a0e ..A.8..G........ - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0010 1b0c0708 90010000 44000000 1c000000 ........D....... + 0020 00000000 6e050000 00420e10 8f02420e ....n....B....B. + 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 + 0040 8606410e 38830703 93040a0e 30410e28 ..A.8.......0A.( + 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_COOPERLAKE.o (disasm) @@ -7,443 +7,262 @@ dtrsm_iunucopy_COOPERLAKE: push %r15 push %r14 - mov %rdi,%r14 push %r13 push %r12 push %rbp + mov %rdx,%rbp push %rbx - sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,-offset(%rsp) test %rsi,%rsi jle + mov %rdi,%r12 mov %rcx,%rbx - lea (%rbx,%rbx,2),%rax - mov %rdx,%r15 - lea offset(,%rax,8),%rdi - lea (%rbx,%rbx,4),%rdx - mov %rdi,offset(%rsp) - lea offset(,%rdx,8),%rdi - mov %rdi,offset(%rsp) - mov %rax,%rdi - shl $something,%rax - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - lea offset(,%rcx,8),%r12 - shl $something,%rdi - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - shl $something,%rcx - mov %rcx,offset(%rsp) - mov %rax,offset(%rsp) - mov $something,%eax - sub %r8,%rax - imul %r12,%rax - mov %rbx,%rcx - shl $something,%rcx - add %r15,%rax - mov %rdi,offset(%rsp) - mov %rbx,%rdi - shl $something,%rdi - mov %rcx,offset(%rsp) - mov %rax,offset(%rsp) - lea (%r12,%rbx,1),%rcx - mov %rsi,%rax - mov %rdi,offset(%rsp) - shl $something,%rax - lea offset(,%rcx,8),%rdi - add %r8,%rax - mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi - mov %rax,offset(%rsp) - mov %r14,%rax - shl $something,%rdx - shl $something,%rax - mov %rdx,offset(%rsp) - mov %rdi,offset(%rsp) - mov %rax,offset(%rsp) - mov %r14,-offset(%rsp) + lea (%rcx,%rcx,2),%rax + sar $something,%r12 + lea offset(,%rcx,8),%r15 + mov %rcx,%r14 shl $something,%rbx - vmovsd offset(%rip),%xmm1 # + lea offset(,%rax,8),%rcx + mov %r12,%r13 + mov %rdi,%rax + shl $something,%r13 + and $something,%eax mov %rbx,-offset(%rsp) - lea offset(%r12),%rbp - mov %r8,%rbx - mov %r15,%r11 - nopl (%rax) - lea (%r12,%r11,1),%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - mov %r11,%r8 - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax + lea (%r8,%rsi,4),%rbx mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - lea (%r11,%rax,1),%rcx - mov offset(%rsp),%rax - lea (%rax,%r11,1),%r13 - mov offset(%rsp),%rax - lea (%rax,%r11,1),%r14 - mov offset(%rsp),%rax - lea (%rax,%r11,1),%r15 - add -offset(%rsp),%r11 - cmpq $something,-offset(%rsp) + mov %rbx,-offset(%rsp) + mov %rdi,%rax + mov %rdi,%rbx + shl $something,%r14 + lea (%r15,%r13,1),%rdi + mov %rdi,-offset(%rsp) + lea (%r14,%r13,1),%rdi + mov %rdi,-offset(%rsp) + lea (%rcx,%r13,1),%rdi + mov %rdi,-offset(%rsp) + mov %r12,%rdi + shl $something,%rdi + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) + and $something,%eax + vmovsd offset(%rip),%xmm16 # + mov %r8,-offset(%rsp) + mov %r8,%r11 + and $something,%rbx + mov %rdx,%r10 + mov %rax,%r8 + mov %rcx,%rbp + nopl offset(%rax,%rax,1) + lea (%r15,%r10,1),%rdi + lea (%r14,%r10,1),%rsi + lea (%r10,%rbp,1),%rcx + test %r12,%r12 jle - mov -offset(%rsp),%rsi - mov %rbx,%rax - neg %rax - mov $something,%edi - mov %r11,-offset(%rsp) - lea (%rsi,%rax,8),%r9 - mov offset(%rsp),%r10 - sub %rbx,%rdi - mov %rsi,%rax + mov %r9,%rax xor %edx,%edx - mov %rcx,%r11 jmp - nopl offset(%rax) - lea -offset(%rdi),%rcx - sub $something,%rax - cmp $something,%rcx + nop jle - inc %rdx - add $something,%r8 - add $something,%r9 - inc %rdi - add %rbp,%r10 - cmp %rdx,-offset(%rsp) - je - cmp %rbx,%rdx - jge - mov %rdi,%rsi - dec %rsi - jns - vmovsd (%r8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,(%rax) - vmovsd (%rcx,%rdx,8),%xmm0 /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_COOPERLAKE.o (objdump) @@ -2,135 +2,85 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 4989fe41 55415455 534881ec AWAVI..AUATUSH.. - 0010 b0000000 4889b424 98000000 48c1fe04 ....H..$....H... - 0020 48899424 90000000 48898c24 a0000000 H..$....H..$.... - 0030 4c890424 4c894c24 e84889b4 24a80000 L..$L.L$.H..$... - 0040 004885f6 0f8eb703 00004889 cb488d04 .H........H..H.. - 0050 5b4989d7 488d3cc5 00000000 488d149b [I..H.<.....H... - 0060 48897c24 50488d3c d5000000 0048897c H.|$PH.<.....H.| - 0070 24584889 c748c1e0 05488944 2478486b $XH..H...H.D$xHk - 0080 c3684c8d 24cd0000 000048c1 e7044889 .hL.$.....H...H. - 0090 44243048 6bc37048 897c2460 486bfb38 D$0Hk.pH.|$`Hk.8 - 00a0 48894424 38486bc3 7848c1e1 0448894c H.D$8Hk.xH...H.L - 00b0 24084889 442440b8 01000000 4c29c049 $.H.D$@.....L).I - 00c0 0fafc448 89d948c1 e1054c01 f848897c ...H..H...L..H.| - 00d0 24184889 df48c1e7 0648894c 24104889 $.H..H...H.L$.H. - 00e0 84248800 0000498d 0c1c4889 f048897c .$....I...H..H.| - 00f0 242048c1 e004488d 3ccd0000 00004c01 $ H...H.<.....L. - 0100 c048897c 2468486b fb584889 4424484c .H.|$hHk.XH.D$HL - 0110 89f048c1 e20448c1 e0074889 54247048 ..H...H...H.T$pH - 0120 897c2428 48898424 80000000 4c897424 .|$(H..$....L.t$ - 0130 8848c1e3 07c5fb10 0d000000 0048895c .H...........H.\ - 0140 24f8498d 6c24084c 89c34d89 fb0f1f00 $.I.l$.L..M..... - 0150 4b8d041c 48894424 90488b44 24084d89 K...H.D$.H.D$.M. - 0160 d84c01d8 48894424 98488b44 24504c01 .L..H.D$.H.D$PL. - 0170 d8488944 24a0488b 4424104c 01d84889 .H.D$.H.D$.L..H. - 0180 4424a848 8b442458 4c01d848 894424b0 D$.H.D$XL..H.D$. - 0190 488b4424 604c01d8 48894424 b8488b44 H.D$`L..H.D$.H.D - 01a0 24184c01 d8488944 24c0488b 4424204c $.L..H.D$.H.D$ L - 01b0 01d84889 4424c848 8b442468 4c01d848 ..H.D$.H.D$hL..H - 01c0 894424d0 488b4424 704c01d8 48894424 .D$.H.D$pL..H.D$ - 01d0 d8488b44 24284c01 d8488944 24e0488b .H.D$(L..H.D$.H. - 01e0 44247849 8d0c0348 8b442430 4e8d2c18 D$xI...H.D$0N.,. - 01f0 488b4424 384e8d34 18488b44 24404e8d H.D$8N.4.H.D$@N. - 0200 3c184c03 5c24f848 837c2488 000f8eaf <.L.\$.H.|$..... - 0210 01000048 8b7424e8 4889d848 f7d8bf01 ...H.t$.H..H.... - 0220 0000004c 895c24f0 4c8d0cc6 4c8b9424 ...L.\$.L...L..$ - 0230 88000000 4829df48 89f031d2 4989cbeb ....H).H..1.I... - 0240 380f1f80 00000000 488d4fff 4883e880 8.......H.O.H... - 0250 4883f90f 0f8e1601 000048ff c24983c0 H.........H..I.. - 0260 084981c1 88000000 48ffc749 01ea4839 .I......H..I..H9 - 0270 5424880f 84370100 004839da 7dca4889 T$...7...H9.}.H. - 0280 fe48ffce 0f89db00 0000c4c1 7b100048 .H..........{..H - 0290 8b4c2490 c5fb1100 c5fb1004 d1488b74 .L$..........H.t - 02a0 2498c5fb 114008c5 fb1004d6 488b4c24 $....@......H.L$ - 02b0 a0c5fb11 4010c5fb 1004d148 8b7424a8 ....@......H.t$. - 02c0 c5fb1140 18c5fb10 04d6488b 4c24b0c5 ...@......H.L$.. - 02d0 fb114020 c5fb1004 d1488b74 24b8c5fb ..@ .....H.t$... - 02e0 114028c5 fb1004d6 488b4c24 c0c5fb11 .@(.....H.L$.... - 02f0 4030c5fb 1004d148 8b7424c8 c5fb1140 @0.....H.t$....@ - 0300 38c5fb10 04d6488b 4c24d0c5 fb114040 8.....H.L$....@@ - 0310 c5fb1004 d1488b74 24d8c5fb 114048c5 .....H.t$....@H. - 0320 fb1004d6 c5fb1140 50488b4c 24e0c5fb .......@PH.L$... - 0330 1004d1c5 fb114058 c4c17b10 04d3c5fb ......@X..{..... - 0340 114060c4 c17b1044 d500c5fb 114068c4 .@`..{.D.....@h. - 0350 c17b1004 d6c5fb11 4070c4c1 7b1004d7 .{......@p..{... - 0360 c5fb1140 784883e8 80e9ecfe ffff6690 ...@xH........f. - 0370 c4c17b11 094883ff 100f84db feffff49 ..{..H.........I - 0380 8d49084c 89d6662e 0f1f8400 00000000 .I.L..f......... - 0390 c5fb1006 4883c108 c5fb1141 f84c01e6 ....H......A.L.. - 03a0 4839c175 ebe9b0fe ffff660f 1f440000 H9.u......f..D.. - 03b0 488bbc24 80000000 4c8b5c24 f048017c H..$....L.\$.H.| - 03c0 24e84883 c310483b 5c24480f 857ffdff $.H...H;\$H..... - 03d0 ff488b9c 24a80000 00488b44 24f84c8b .H..$....H.D$.L. - 03e0 74248848 0fafc348 01842490 00000048 t$.H...H..$....H - 03f0 89d8488b 1c2448c1 e0044801 d8488904 ..H..$H...H..H.. - 0400 24f68424 98000000 080f8455 01000048 $..$.......U...H - 0410 8b8424a0 00000048 8bbc2490 0000004c ..$....H..$....L - 0420 8d0cc500 0000004e 8d1c0f4b 8d040b4e .......N...K...N - 0430 8d3c0848 89442488 4b8d040f 4e8d2c08 .<.H.D$.K...N.,. - 0440 4f8d640d 004b8d2c 0c488944 24904a8d O.d..K.,.H.D$.J. - 0450 440d0048 894424a0 4d85f60f 8ef10000 D..H.D$.M....... - 0460 00488b1c 24be0100 00004829 de4d89c8 .H..$.....H).M.. - 0470 4c0fafc6 4889d848 8b5424e8 48f7d84c L...H..H.T$.H..L - 0480 897c2498 4c8d14c2 4d89dfc5 fb100d00 .|$.L...M....... - 0490 00000049 8d590849 01f831c0 4989fbeb ...I.Y.I..1.I... - 04a0 2f0f1f80 00000000 488d4eff 4883f907 /.......H.N.H... - 04b0 0f8e0003 000048ff c04983c3 084883c2 ......H..I...H.. - 04c0 404983c2 4848ffc6 4901d849 39c67476 @I..HH..I..I9.tv - 04d0 483b0424 7dd24889 f748ffcf 79d8c4c1 H;.$}.H..H..y... - 04e0 7b100348 8b7c2488 c5fb1102 c4c17b10 {..H.|$.......{. - 04f0 04c7c5fb 114208c5 fb1004c7 488b7c24 .....B......H.|$ - 0500 98c5fb11 4210c5fb 1004c748 8b7c2490 ....B......H.|$. - 0510 c5fb1142 18c5fb10 04c7c5fb 114220c4 ...B.........B . - 0520 c17b1044 c500c5fb 114228c4 c17b1004 .{.D.....B(..{.. - 0530 c4c5fb11 4230c5fb 1044c500 c5fb1142 ....B0...D.....B - 0540 38e970ff ffff4c89 f048c1e0 06480144 8.p...L..H...H.D - 0550 24e8488b 4424a048 83042408 48898424 $.H.D$.H..$.H..$ - 0560 90000000 f6842498 00000004 0f840e01 ......$......... - 0570 0000488b 8424a000 00004c8b 84249000 ..H..$....L..$.. - 0580 00004c8d 0cc50000 00004b8d 1c084e8d ..L.......K...N. - 0590 1c0b4b8d 0c0b4e8d 2c094d85 f60f8ed0 ..K...N.,.M..... - 05a0 0000004c 8b3c24be 01000000 4c89fa4c ...L.<$.....L..L - 05b0 29fe490f aff148f7 da488d04 d5000000 ).I...H..H...... - 05c0 00488b7c 24e84829 c14d89f4 4801c748 .H.|$.H).M..H..H - 05d0 29c34929 c34c896c 2488488b 4424e8c5 ).I).L.l$.H.D$.. - 05e0 fb100d00 0000004d 8d51084c 01c64d29 .......M.Q.L..M) - 05f0 fc4889cd eb2f662e 0f1f8400 00000000 .H.../f......... - 0600 4c8d6a01 4883fa03 0f8ef001 00004983 L.j.H.........I. - 0610 c0084883 c0204c89 ea4883c7 284c01d6 ..H.. L..H..(L.. - 0620 4d39ec74 3d498d0c 174939cf 7ed24885 M9.t=I...I9.~.H. - 0630 d27929c4 c17b1000 c5fb1100 c5fb1004 .y)..{.......... - 0640 d3c5fb11 4008c4c1 7b1004d3 c5fb1140 ....@...{......@ - 0650 10c5fb10 44d500c5 fb114018 4c8d6a01 ....D.....@.L.j. - 0660 ebac4c89 f048c1e0 05480144 24e84c8b ..L..H...H.D$.L. - 0670 6c248848 83042404 4c89ac24 90000000 l$.H..$.L..$.... - 0680 f6842498 00000002 0f849b00 0000488b ..$...........H. - 0690 8424a000 00004c8b 94249000 000048c1 .$....L..$....H. - 06a0 e0034d8d 0402498d 14004d85 f67e6d4c ..M...I...M..~mL - 06b0 8b0c2448 8b4c24e8 4c89ce48 f7dec5fb ..$H.L$.L..H.... - 06c0 100d0000 0000488d 3cf131c0 eb2f6690 ......H.<.1../f. - 06d0 4885f679 15c4c17b 1004c2c5 fb1101c4 H..y...{........ - 06e0 c17b1004 c0c5fb11 410848ff c04883c1 .{......A.H..H.. - 06f0 1048ffc6 4883c718 4939c674 134939c1 .H..H...I9.t.I9. - 0700 7fce4883 fe017fe2 c5fb110f 75d1ebda ..H.........u... - 0710 4c89f048 c1e00448 014424e8 48830424 L..H...H.D$.H..$ - 0720 02488994 24900000 00f68424 98000000 .H..$......$.... - 0730 01746f4d 85f67e6a 488b3c24 4c8b4c24 .toM..~jH.<$L.L$ - 0740 e84889fa 48f7da48 89f9c5fb 100d0000 .H..H..H........ - 0750 00004c8b 84249000 0000498d 34d131c0 ..L..$....I.4.1. - 0760 48c1e104 eb1b662e 0f1f8400 00000000 H.....f......... - 0770 0f84bc00 000048ff c048ffc2 4939c674 ......H..H..I9.t - 0780 214839c7 7eea4885 d279ebc4 c17b1004 !H9.~.H..y...{.. - 0790 c048ffc2 c4c17b11 04c148ff c04939c6 .H....{...H..I9. - 07a0 75df4881 c4b00000 005b5d41 5c415d41 u.H......[]A\A]A - 07b0 5e31c041 5fc3c4c1 7b110a48 83fe080f ^1.A_...{..H.... - 07c0 84f1fcff ff488d4a 3848894c 24a84889 .....H.J8H.L$.H. - 07d0 4424b04c 89c7488b 4424a84c 89d16690 D$.L..H.D$.L..f. - 07e0 c5fb1007 4883c108 c5fb1101 4c01cf48 ....H.......L..H - 07f0 39c175ec 488b4424 b0e9b8fc ffffc5fb 9.u.H.D$........ - 0800 110f4c89 ea4983fd 040f84ff fdffff48 ..L..I.........H - 0810 89f1660f 1f440000 c5fb1001 4c01c9c5 ..f..D......L... - 0820 fb1104d0 48ffc248 83fa0475 ebe9dcfd ....H..H...u.... - 0830 ffffc5fb 110c0ee9 3affffff ........:... + 0000 41574156 41554154 554889d5 53488974 AWAVAUATUH..SH.t + 0010 24d048c1 fe024889 7c24d848 894c24f8 $.H...H.|$.H.L$. + 0020 48897424 e04885f6 0f8ef502 00004989 H.t$.H........I. + 0030 fc4889cb 488d0449 49c1fc02 4c8d3ccd .H..H..II...L.<. + 0040 00000000 4989ce48 c1e30548 8d0cc500 ....I..H...H.... + 0050 0000004d 89e54889 f849c1e5 0583e002 ...M..H..I...... + 0060 48895c24 98498d1c b0488944 24a84889 H.\$.I...H.D$.H. + 0070 5c24a048 89f84889 fb49c1e6 044b8d3c \$.H..H..I...K.< + 0080 2f48897c 24c04b8d 3c2e4889 7c24b84a /H.|$.K.<.H.|$.J + 0090 8d3c2948 897c24c8 4c89e748 c1e70748 .<)H.|$.L..H...H + 00a0 897c24b0 48895424 e883e001 62e1ff08 .|$.H.T$....b... + 00b0 10050000 00004c89 4424f04d 89c34883 ......L.D$.M..H. + 00c0 e3fc4989 d24989c0 4889cd0f 1f440000 ..I..I..H....D.. + 00d0 4b8d3c17 4b8d3416 498d0c2a 4d85e40f K.<.K.4.I..*M... + 00e0 8e0b0400 004c89c8 31d2e9c3 00000090 .....L..1....... + 00f0 0f8ea300 0000c441 7b103cd2 c4417b10 .......A{.<..A{. + 0100 5cd208c4 c17b107c d210c4c1 7b105cd2 \....{.|....{.\. + 0110 18c57b10 37c57b10 5708c5fb 107710c5 ..{.7.{.W....w.. + 0120 fb105718 c57b102e c57b104e 08c5fb10 ..W..{...{.N.... + 0130 6e10c5fb 104e18c5 7b1021c5 7b104108 n....N..{.!.{.A. + 0140 c5fb1061 10c5fb10 4118c57b 1138c57b ...a....A..{.8.{ + 0150 117008c5 7b116810 c57b1160 18c57b11 .p..{.h..{.`..{. + 0160 5820c57b 115028c5 7b114830 c57b1140 X .{.P(.{.H0.{.@ + 0170 38c5fb11 7840c5fb 117048c5 fb116850 8...x@...pH...hP + 0180 c5fb1160 58c5fb11 5860c5fb 115068c5 ...`X...X`...Ph. + 0190 fb114870 c5fb1140 784883c2 044883c7 ..Hp...@xH...H.. + 01a0 204883c6 204883c1 204883e8 804839da H.. H.. H...H9. + 01b0 74664939 d30f8535 ffffffc5 fb102fc5 tfI9...5....../. + 01c0 fb1026c5 fb105608 c5fb1019 c5fb1049 ..&...V........I + 01d0 08c5fb10 411062e1 ff081100 c5fb1168 ....A.b........h + 01e0 08c5fb11 6010c5fb 11581862 e1ff0811 ....`....X.b.... + 01f0 4005c5fb 115030c5 fb114838 62e1ff08 @....P0...H8b... + 0200 11400ac5 fb114058 62e1ff08 11400feb .@....@Xb....@.. + 0210 880f1f80 00000000 488b4424 c04b8d14 ........H.D$.K.. + 0220 2a498d3c 02488b44 24b84c03 4c24b049 *I.<.H.D$.L.L$.I + 0230 8d340248 8b4424c8 498d0c02 4889d848 .4.H.D$.I...H..H + 0240 837c24a8 00746e49 39c30f84 50020000 .|$..tnI9...P... + 0250 7e53c5fb 103ac5fb 107208c5 fb102fc5 ~S...:...r..../. + 0260 fb106708 c5fb101e c5fb1056 08c5fb10 ..g........V.... + 0270 09c5fb10 4108c4c1 7b1139c4 c17b1171 ....A...{.9..{.q + 0280 08c4c17b 116910c4 c17b1161 18c4c17b ...{.i...{.a...{ + 0290 115920c4 c17b1151 28c4c17b 114930c4 .Y ..{.Q(..{.I0. + 02a0 c17b1141 384883c2 104883c7 104983c1 .{.A8H...H...I.. + 02b0 404883c0 024d85c0 74364c39 d80f84ad @H...M..t6L9.... + 02c0 0100007d 27c5fb10 1ac5fb10 17c5fb10 ...}'........... + 02d0 0ec5fb10 01c4c17b 1119c4c1 7b115108 .......{....{.Q. + 02e0 c4c17b11 4910c4c1 7b114118 4983c120 ..{.I...{.A.I.. + 02f0 4983c304 4c035424 984c3b5c 24a00f85 I...L.T$.L;\$... + 0300 ccfdffff 488b5c24 e0488b44 2498488b ....H.\$.H.D$.H. + 0310 6c24e848 0fafc34c 8b4424f0 4801c54d l$.H...L.D$.H..M + 0320 8d0498f6 4424d002 0f84dd00 00004c8b ....D$........L. + 0330 5424f848 8b7c24d8 49c1e203 48d1ff4a T$.H.|$.I...H..J + 0340 8d4c1500 4885ff0f 8ec60100 00c5fb10 .L..H........... + 0350 25000000 00488d34 3f4c89ca 31c0eb39 %....H.4?L..1..9 + 0360 7e2ac5fb 105cc500 c5fb104c c508c5fb ~*...\.....L.... + 0370 1014c1c5 fb1044c1 08c5fb11 1ac5fb11 ......D......... + 0380 5208c5fb 114a10c5 fb114218 4883c002 R....J....B.H... + 0390 4883c220 4839c674 264939c0 75c2c4a1 H.. H9.t&I9.u... + 03a0 7b1004c1 4883c002 c5fb1122 c5fb1142 {...H......"...B + 03b0 08c5fb11 62184883 c2204839 c675da48 ....b.H.. H9.u.H + 03c0 89f84889 fa48c1e0 0448c1e2 054801c5 ..H..H...H...H.. + 03d0 4901d148 01c84801 fff64424 d8017423 I..H..H...D$..t# /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_COOPERLAKE.o (objdump) @@ -3,9 +3,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 3c080000 00420e10 8f02420e ....<....B....B. - 0030 188e0345 0e208d04 420e288c 05410e30 ...E. ..B.(..A.0 - 0040 8606410e 38830747 0ee80103 95070a0e ..A.8..G........ - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0010 1b0c0708 90010000 44000000 1c000000 ........D....... + 0020 00000000 1d050000 00420e10 8f02420e .........B....B. + 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 + 0040 8606440e 38830703 4d040a0e 30410e28 ..D.8...M...0A.( + 0050 420e2042 0e18420e 10440e08 4b0b0000 B. B..B..D..K... /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_SKYLAKEX.o (disasm) @@ -7,443 +7,262 @@ dtrsm_iunucopy_SKYLAKEX: push %r15 push %r14 - mov %rdi,%r14 push %r13 push %r12 push %rbp + mov %rdx,%rbp push %rbx - sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,-offset(%rsp) sar $something,%rsi - mov %rdx,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r8,(%rsp) - mov %r9,-offset(%rsp) - mov %rsi,offset(%rsp) + mov %rdi,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %rsi,-offset(%rsp) test %rsi,%rsi jle + mov %rdi,%r12 mov %rcx,%rbx - lea (%rbx,%rbx,2),%rax - mov %rdx,%r15 - lea offset(,%rax,8),%rdi - lea (%rbx,%rbx,4),%rdx - mov %rdi,offset(%rsp) - lea offset(,%rdx,8),%rdi - mov %rdi,offset(%rsp) - mov %rax,%rdi - shl $something,%rax - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - lea offset(,%rcx,8),%r12 - shl $something,%rdi - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - shl $something,%rcx - mov %rcx,offset(%rsp) - mov %rax,offset(%rsp) - mov $something,%eax - sub %r8,%rax - imul %r12,%rax - mov %rbx,%rcx - shl $something,%rcx - add %r15,%rax - mov %rdi,offset(%rsp) - mov %rbx,%rdi - shl $something,%rdi - mov %rcx,offset(%rsp) - mov %rax,offset(%rsp) - lea (%r12,%rbx,1),%rcx - mov %rsi,%rax - mov %rdi,offset(%rsp) - shl $something,%rax - lea offset(,%rcx,8),%rdi - add %r8,%rax - mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi - mov %rax,offset(%rsp) - mov %r14,%rax - shl $something,%rdx - shl $something,%rax - mov %rdx,offset(%rsp) - mov %rdi,offset(%rsp) - mov %rax,offset(%rsp) - mov %r14,-offset(%rsp) + lea (%rcx,%rcx,2),%rax + sar $something,%r12 + lea offset(,%rcx,8),%r15 + mov %rcx,%r14 shl $something,%rbx - vmovsd offset(%rip),%xmm1 # + lea offset(,%rax,8),%rcx + mov %r12,%r13 + mov %rdi,%rax + shl $something,%r13 + and $something,%eax mov %rbx,-offset(%rsp) - lea offset(%r12),%rbp - mov %r8,%rbx - mov %r15,%r11 - nopl (%rax) - lea (%r12,%r11,1),%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - mov %r11,%r8 - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax + lea (%r8,%rsi,4),%rbx mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - lea (%r11,%rax,1),%rcx - mov offset(%rsp),%rax - lea (%rax,%r11,1),%r13 - mov offset(%rsp),%rax - lea (%rax,%r11,1),%r14 - mov offset(%rsp),%rax - lea (%rax,%r11,1),%r15 - add -offset(%rsp),%r11 - cmpq $something,-offset(%rsp) + mov %rbx,-offset(%rsp) + mov %rdi,%rax + mov %rdi,%rbx + shl $something,%r14 + lea (%r15,%r13,1),%rdi + mov %rdi,-offset(%rsp) + lea (%r14,%r13,1),%rdi + mov %rdi,-offset(%rsp) + lea (%rcx,%r13,1),%rdi + mov %rdi,-offset(%rsp) + mov %r12,%rdi + shl $something,%rdi + mov %rdi,-offset(%rsp) + mov %rdx,-offset(%rsp) + and $something,%eax + vmovsd offset(%rip),%xmm16 # + mov %r8,-offset(%rsp) + mov %r8,%r11 + and $something,%rbx + mov %rdx,%r10 + mov %rax,%r8 + mov %rcx,%rbp + nopl offset(%rax,%rax,1) + lea (%r15,%r10,1),%rdi + lea (%r14,%r10,1),%rsi + lea (%r10,%rbp,1),%rcx + test %r12,%r12 jle - mov -offset(%rsp),%rsi - mov %rbx,%rax - neg %rax - mov $something,%edi - mov %r11,-offset(%rsp) - lea (%rsi,%rax,8),%r9 - mov offset(%rsp),%r10 - sub %rbx,%rdi - mov %rsi,%rax + mov %r9,%rax xor %edx,%edx - mov %rcx,%r11 jmp - nopl offset(%rax) - lea -offset(%rdi),%rcx - sub $something,%rax - cmp $something,%rcx + nop jle - inc %rdx - add $something,%r8 - add $something,%r9 - inc %rdi - add %rbp,%r10 - cmp %rdx,-offset(%rsp) - je - cmp %rbx,%rdx - jge - mov %rdi,%rsi - dec %rsi - jns - vmovsd (%r8),%xmm0 - mov -offset(%rsp),%rcx - vmovsd %xmm0,(%rax) - vmovsd (%rcx,%rdx,8),%xmm0 /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_SKYLAKEX.o (objdump) @@ -2,135 +2,85 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 4989fe41 55415455 534881ec AWAVI..AUATUSH.. - 0010 b0000000 4889b424 98000000 48c1fe04 ....H..$....H... - 0020 48899424 90000000 48898c24 a0000000 H..$....H..$.... - 0030 4c890424 4c894c24 e84889b4 24a80000 L..$L.L$.H..$... - 0040 004885f6 0f8eb703 00004889 cb488d04 .H........H..H.. - 0050 5b4989d7 488d3cc5 00000000 488d149b [I..H.<.....H... - 0060 48897c24 50488d3c d5000000 0048897c H.|$PH.<.....H.| - 0070 24584889 c748c1e0 05488944 2478486b $XH..H...H.D$xHk - 0080 c3684c8d 24cd0000 000048c1 e7044889 .hL.$.....H...H. - 0090 44243048 6bc37048 897c2460 486bfb38 D$0Hk.pH.|$`Hk.8 - 00a0 48894424 38486bc3 7848c1e1 0448894c H.D$8Hk.xH...H.L - 00b0 24084889 442440b8 01000000 4c29c049 $.H.D$@.....L).I - 00c0 0fafc448 89d948c1 e1054c01 f848897c ...H..H...L..H.| - 00d0 24184889 df48c1e7 0648894c 24104889 $.H..H...H.L$.H. - 00e0 84248800 0000498d 0c1c4889 f048897c .$....I...H..H.| - 00f0 242048c1 e004488d 3ccd0000 00004c01 $ H...H.<.....L. - 0100 c048897c 2468486b fb584889 4424484c .H.|$hHk.XH.D$HL - 0110 89f048c1 e20448c1 e0074889 54247048 ..H...H...H.T$pH - 0120 897c2428 48898424 80000000 4c897424 .|$(H..$....L.t$ - 0130 8848c1e3 07c5fb10 0d000000 0048895c .H...........H.\ - 0140 24f8498d 6c24084c 89c34d89 fb0f1f00 $.I.l$.L..M..... - 0150 4b8d041c 48894424 90488b44 24084d89 K...H.D$.H.D$.M. - 0160 d84c01d8 48894424 98488b44 24504c01 .L..H.D$.H.D$PL. - 0170 d8488944 24a0488b 4424104c 01d84889 .H.D$.H.D$.L..H. - 0180 4424a848 8b442458 4c01d848 894424b0 D$.H.D$XL..H.D$. - 0190 488b4424 604c01d8 48894424 b8488b44 H.D$`L..H.D$.H.D - 01a0 24184c01 d8488944 24c0488b 4424204c $.L..H.D$.H.D$ L - 01b0 01d84889 4424c848 8b442468 4c01d848 ..H.D$.H.D$hL..H - 01c0 894424d0 488b4424 704c01d8 48894424 .D$.H.D$pL..H.D$ - 01d0 d8488b44 24284c01 d8488944 24e0488b .H.D$(L..H.D$.H. - 01e0 44247849 8d0c0348 8b442430 4e8d2c18 D$xI...H.D$0N.,. - 01f0 488b4424 384e8d34 18488b44 24404e8d H.D$8N.4.H.D$@N. - 0200 3c184c03 5c24f848 837c2488 000f8eaf <.L.\$.H.|$..... - 0210 01000048 8b7424e8 4889d848 f7d8bf01 ...H.t$.H..H.... - 0220 0000004c 895c24f0 4c8d0cc6 4c8b9424 ...L.\$.L...L..$ - 0230 88000000 4829df48 89f031d2 4989cbeb ....H).H..1.I... - 0240 380f1f80 00000000 488d4fff 4883e880 8.......H.O.H... - 0250 4883f90f 0f8e1601 000048ff c24983c0 H.........H..I.. - 0260 084981c1 88000000 48ffc749 01ea4839 .I......H..I..H9 - 0270 5424880f 84370100 004839da 7dca4889 T$...7...H9.}.H. - 0280 fe48ffce 0f89db00 0000c4c1 7b100048 .H..........{..H - 0290 8b4c2490 c5fb1100 c5fb1004 d1488b74 .L$..........H.t - 02a0 2498c5fb 114008c5 fb1004d6 488b4c24 $....@......H.L$ - 02b0 a0c5fb11 4010c5fb 1004d148 8b7424a8 ....@......H.t$. - 02c0 c5fb1140 18c5fb10 04d6488b 4c24b0c5 ...@......H.L$.. - 02d0 fb114020 c5fb1004 d1488b74 24b8c5fb ..@ .....H.t$... - 02e0 114028c5 fb1004d6 488b4c24 c0c5fb11 .@(.....H.L$.... - 02f0 4030c5fb 1004d148 8b7424c8 c5fb1140 @0.....H.t$....@ - 0300 38c5fb10 04d6488b 4c24d0c5 fb114040 8.....H.L$....@@ - 0310 c5fb1004 d1488b74 24d8c5fb 114048c5 .....H.t$....@H. - 0320 fb1004d6 c5fb1140 50488b4c 24e0c5fb .......@PH.L$... - 0330 1004d1c5 fb114058 c4c17b10 04d3c5fb ......@X..{..... - 0340 114060c4 c17b1044 d500c5fb 114068c4 .@`..{.D.....@h. - 0350 c17b1004 d6c5fb11 4070c4c1 7b1004d7 .{......@p..{... - 0360 c5fb1140 784883e8 80e9ecfe ffff6690 ...@xH........f. - 0370 c4c17b11 094883ff 100f84db feffff49 ..{..H.........I - 0380 8d49084c 89d6662e 0f1f8400 00000000 .I.L..f......... - 0390 c5fb1006 4883c108 c5fb1141 f84c01e6 ....H......A.L.. - 03a0 4839c175 ebe9b0fe ffff660f 1f440000 H9.u......f..D.. - 03b0 488bbc24 80000000 4c8b5c24 f048017c H..$....L.\$.H.| - 03c0 24e84883 c310483b 5c24480f 857ffdff $.H...H;\$H..... - 03d0 ff488b9c 24a80000 00488b44 24f84c8b .H..$....H.D$.L. - 03e0 74248848 0fafc348 01842490 00000048 t$.H...H..$....H - 03f0 89d8488b 1c2448c1 e0044801 d8488904 ..H..$H...H..H.. - 0400 24f68424 98000000 080f8455 01000048 $..$.......U...H - 0410 8b8424a0 00000048 8bbc2490 0000004c ..$....H..$....L - 0420 8d0cc500 0000004e 8d1c0f4b 8d040b4e .......N...K...N - 0430 8d3c0848 89442488 4b8d040f 4e8d2c08 .<.H.D$.K...N.,. - 0440 4f8d640d 004b8d2c 0c488944 24904a8d O.d..K.,.H.D$.J. - 0450 440d0048 894424a0 4d85f60f 8ef10000 D..H.D$.M....... - 0460 00488b1c 24be0100 00004829 de4d89c8 .H..$.....H).M.. - 0470 4c0fafc6 4889d848 8b5424e8 48f7d84c L...H..H.T$.H..L - 0480 897c2498 4c8d14c2 4d89dfc5 fb100d00 .|$.L...M....... - 0490 00000049 8d590849 01f831c0 4989fbeb ...I.Y.I..1.I... - 04a0 2f0f1f80 00000000 488d4eff 4883f907 /.......H.N.H... - 04b0 0f8e0003 000048ff c04983c3 084883c2 ......H..I...H.. - 04c0 404983c2 4848ffc6 4901d849 39c67476 @I..HH..I..I9.tv - 04d0 483b0424 7dd24889 f748ffcf 79d8c4c1 H;.$}.H..H..y... - 04e0 7b100348 8b7c2488 c5fb1102 c4c17b10 {..H.|$.......{. - 04f0 04c7c5fb 114208c5 fb1004c7 488b7c24 .....B......H.|$ - 0500 98c5fb11 4210c5fb 1004c748 8b7c2490 ....B......H.|$. - 0510 c5fb1142 18c5fb10 04c7c5fb 114220c4 ...B.........B . - 0520 c17b1044 c500c5fb 114228c4 c17b1004 .{.D.....B(..{.. - 0530 c4c5fb11 4230c5fb 1044c500 c5fb1142 ....B0...D.....B - 0540 38e970ff ffff4c89 f048c1e0 06480144 8.p...L..H...H.D - 0550 24e8488b 4424a048 83042408 48898424 $.H.D$.H..$.H..$ - 0560 90000000 f6842498 00000004 0f840e01 ......$......... - 0570 0000488b 8424a000 00004c8b 84249000 ..H..$....L..$.. - 0580 00004c8d 0cc50000 00004b8d 1c084e8d ..L.......K...N. - 0590 1c0b4b8d 0c0b4e8d 2c094d85 f60f8ed0 ..K...N.,.M..... - 05a0 0000004c 8b3c24be 01000000 4c89fa4c ...L.<$.....L..L - 05b0 29fe490f aff148f7 da488d04 d5000000 ).I...H..H...... - 05c0 00488b7c 24e84829 c14d89f4 4801c748 .H.|$.H).M..H..H - 05d0 29c34929 c34c896c 2488488b 4424e8c5 ).I).L.l$.H.D$.. - 05e0 fb100d00 0000004d 8d51084c 01c64d29 .......M.Q.L..M) - 05f0 fc4889cd eb2f662e 0f1f8400 00000000 .H.../f......... - 0600 4c8d6a01 4883fa03 0f8ef001 00004983 L.j.H.........I. - 0610 c0084883 c0204c89 ea4883c7 284c01d6 ..H.. L..H..(L.. - 0620 4d39ec74 3d498d0c 174939cf 7ed24885 M9.t=I...I9.~.H. - 0630 d27929c4 c17b1000 c5fb1100 c5fb1004 .y)..{.......... - 0640 d3c5fb11 4008c4c1 7b1004d3 c5fb1140 ....@...{......@ - 0650 10c5fb10 44d500c5 fb114018 4c8d6a01 ....D.....@.L.j. - 0660 ebac4c89 f048c1e0 05480144 24e84c8b ..L..H...H.D$.L. - 0670 6c248848 83042404 4c89ac24 90000000 l$.H..$.L..$.... - 0680 f6842498 00000002 0f849b00 0000488b ..$...........H. - 0690 8424a000 00004c8b 94249000 000048c1 .$....L..$....H. - 06a0 e0034d8d 0402498d 14004d85 f67e6d4c ..M...I...M..~mL - 06b0 8b0c2448 8b4c24e8 4c89ce48 f7dec5fb ..$H.L$.L..H.... - 06c0 100d0000 0000488d 3cf131c0 eb2f6690 ......H.<.1../f. - 06d0 4885f679 15c4c17b 1004c2c5 fb1101c4 H..y...{........ - 06e0 c17b1004 c0c5fb11 410848ff c04883c1 .{......A.H..H.. - 06f0 1048ffc6 4883c718 4939c674 134939c1 .H..H...I9.t.I9. - 0700 7fce4883 fe017fe2 c5fb110f 75d1ebda ..H.........u... - 0710 4c89f048 c1e00448 014424e8 48830424 L..H...H.D$.H..$ - 0720 02488994 24900000 00f68424 98000000 .H..$......$.... - 0730 01746f4d 85f67e6a 488b3c24 4c8b4c24 .toM..~jH.<$L.L$ - 0740 e84889fa 48f7da48 89f9c5fb 100d0000 .H..H..H........ - 0750 00004c8b 84249000 0000498d 34d131c0 ..L..$....I.4.1. - 0760 48c1e104 eb1b662e 0f1f8400 00000000 H.....f......... - 0770 0f84bc00 000048ff c048ffc2 4939c674 ......H..H..I9.t - 0780 214839c7 7eea4885 d279ebc4 c17b1004 !H9.~.H..y...{.. - 0790 c048ffc2 c4c17b11 04c148ff c04939c6 .H....{...H..I9. - 07a0 75df4881 c4b00000 005b5d41 5c415d41 u.H......[]A\A]A - 07b0 5e31c041 5fc3c4c1 7b110a48 83fe080f ^1.A_...{..H.... - 07c0 84f1fcff ff488d4a 3848894c 24a84889 .....H.J8H.L$.H. - 07d0 4424b04c 89c7488b 4424a84c 89d16690 D$.L..H.D$.L..f. - 07e0 c5fb1007 4883c108 c5fb1101 4c01cf48 ....H.......L..H - 07f0 39c175ec 488b4424 b0e9b8fc ffffc5fb 9.u.H.D$........ - 0800 110f4c89 ea4983fd 040f84ff fdffff48 ..L..I.........H - 0810 89f1660f 1f440000 c5fb1001 4c01c9c5 ..f..D......L... - 0820 fb1104d0 48ffc248 83fa0475 ebe9dcfd ....H..H...u.... - 0830 ffffc5fb 110c0ee9 3affffff ........:... + 0000 41574156 41554154 554889d5 53488974 AWAVAUATUH..SH.t + 0010 24d048c1 fe024889 7c24d848 894c24f8 $.H...H.|$.H.L$. + 0020 48897424 e04885f6 0f8ef502 00004989 H.t$.H........I. + 0030 fc4889cb 488d0449 49c1fc02 4c8d3ccd .H..H..II...L.<. + 0040 00000000 4989ce48 c1e30548 8d0cc500 ....I..H...H.... + 0050 0000004d 89e54889 f849c1e5 0583e002 ...M..H..I...... + 0060 48895c24 98498d1c b0488944 24a84889 H.\$.I...H.D$.H. + 0070 5c24a048 89f84889 fb49c1e6 044b8d3c \$.H..H..I...K.< + 0080 2f48897c 24c04b8d 3c2e4889 7c24b84a /H.|$.K.<.H.|$.J + 0090 8d3c2948 897c24c8 4c89e748 c1e70748 .<)H.|$.L..H...H + 00a0 897c24b0 48895424 e883e001 62e1ff08 .|$.H.T$....b... + 00b0 10050000 00004c89 4424f04d 89c34883 ......L.D$.M..H. + 00c0 e3fc4989 d24989c0 4889cd0f 1f440000 ..I..I..H....D.. + 00d0 4b8d3c17 4b8d3416 498d0c2a 4d85e40f K.<.K.4.I..*M... + 00e0 8e0b0400 004c89c8 31d2e9c3 00000090 .....L..1....... + 00f0 0f8ea300 0000c441 7b103cd2 c4417b10 .......A{.<..A{. + 0100 5cd208c4 c17b107c d210c4c1 7b105cd2 \....{.|....{.\. + 0110 18c57b10 37c57b10 5708c5fb 107710c5 ..{.7.{.W....w.. + 0120 fb105718 c57b102e c57b104e 08c5fb10 ..W..{...{.N.... + 0130 6e10c5fb 104e18c5 7b1021c5 7b104108 n....N..{.!.{.A. + 0140 c5fb1061 10c5fb10 4118c57b 1138c57b ...a....A..{.8.{ + 0150 117008c5 7b116810 c57b1160 18c57b11 .p..{.h..{.`..{. + 0160 5820c57b 115028c5 7b114830 c57b1140 X .{.P(.{.H0.{.@ + 0170 38c5fb11 7840c5fb 117048c5 fb116850 8...x@...pH...hP + 0180 c5fb1160 58c5fb11 5860c5fb 115068c5 ...`X...X`...Ph. + 0190 fb114870 c5fb1140 784883c2 044883c7 ..Hp...@xH...H.. + 01a0 204883c6 204883c1 204883e8 804839da H.. H.. H...H9. + 01b0 74664939 d30f8535 ffffffc5 fb102fc5 tfI9...5....../. + 01c0 fb1026c5 fb105608 c5fb1019 c5fb1049 ..&...V........I + 01d0 08c5fb10 411062e1 ff081100 c5fb1168 ....A.b........h + 01e0 08c5fb11 6010c5fb 11581862 e1ff0811 ....`....X.b.... + 01f0 4005c5fb 115030c5 fb114838 62e1ff08 @....P0...H8b... + 0200 11400ac5 fb114058 62e1ff08 11400feb .@....@Xb....@.. + 0210 880f1f80 00000000 488b4424 c04b8d14 ........H.D$.K.. + 0220 2a498d3c 02488b44 24b84c03 4c24b049 *I.<.H.D$.L.L$.I + 0230 8d340248 8b4424c8 498d0c02 4889d848 .4.H.D$.I...H..H + 0240 837c24a8 00746e49 39c30f84 50020000 .|$..tnI9...P... + 0250 7e53c5fb 103ac5fb 107208c5 fb102fc5 ~S...:...r..../. + 0260 fb106708 c5fb101e c5fb1056 08c5fb10 ..g........V.... + 0270 09c5fb10 4108c4c1 7b1139c4 c17b1171 ....A...{.9..{.q + 0280 08c4c17b 116910c4 c17b1161 18c4c17b ...{.i...{.a...{ + 0290 115920c4 c17b1151 28c4c17b 114930c4 .Y ..{.Q(..{.I0. + 02a0 c17b1141 384883c2 104883c7 104983c1 .{.A8H...H...I.. + 02b0 404883c0 024d85c0 74364c39 d80f84ad @H...M..t6L9.... + 02c0 0100007d 27c5fb10 1ac5fb10 17c5fb10 ...}'........... + 02d0 0ec5fb10 01c4c17b 1119c4c1 7b115108 .......{....{.Q. + 02e0 c4c17b11 4910c4c1 7b114118 4983c120 ..{.I...{.A.I.. + 02f0 4983c304 4c035424 984c3b5c 24a00f85 I...L.T$.L;\$... + 0300 ccfdffff 488b5c24 e0488b44 2498488b ....H.\$.H.D$.H. + 0310 6c24e848 0fafc34c 8b4424f0 4801c54d l$.H...L.D$.H..M + 0320 8d0498f6 4424d002 0f84dd00 00004c8b ....D$........L. + 0330 5424f848 8b7c24d8 49c1e203 48d1ff4a T$.H.|$.I...H..J + 0340 8d4c1500 4885ff0f 8ec60100 00c5fb10 .L..H........... + 0350 25000000 00488d34 3f4c89ca 31c0eb39 %....H.4?L..1..9 + 0360 7e2ac5fb 105cc500 c5fb104c c508c5fb ~*...\.....L.... + 0370 1014c1c5 fb1044c1 08c5fb11 1ac5fb11 ......D......... + 0380 5208c5fb 114a10c5 fb114218 4883c002 R....J....B.H... + 0390 4883c220 4839c674 264939c0 75c2c4a1 H.. H9.t&I9.u... + 03a0 7b1004c1 4883c002 c5fb1122 c5fb1142 {...H......"...B + 03b0 08c5fb11 62184883 c2204839 c675da48 ....b.H.. H9.u.H + 03c0 89f84889 fa48c1e0 0448c1e2 054801c5 ..H..H...H...H.. + 03d0 4901d148 01c84801 fff64424 d8017423 I..H..H...D$..t# /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iunucopy_SKYLAKEX.o (objdump) @@ -3,9 +3,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 3c080000 00420e10 8f02420e ....<....B....B. - 0030 188e0345 0e208d04 420e288c 05410e30 ...E. ..B.(..A.0 - 0040 8606410e 38830747 0ee80103 95070a0e ..A.8..G........ - 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0010 1b0c0708 90010000 44000000 1c000000 ........D....... + 0020 00000000 1d050000 00420e10 8f02420e .........B....B. + 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 + 0040 8606440e 38830703 4d040a0e 30410e28 ..D.8...M...0A.( + 0050 420e2042 0e18420e 10440e08 4b0b0000 B. B..B..D..K... /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_COOPERLAKE.o (disasm) @@ -9,270 +9,278 @@ push %r14 push %r13 push %r12 - mov %rdi,%r12 + mov %rdx,%r12 push %rbp - mov %rdx,%rbp push %rbx mov %rsi,-offset(%rsp) sar $something,%rsi + mov %rdi,-offset(%rsp) mov %rcx,-offset(%rsp) + mov %r8,-offset(%rsp) mov %rsi,-offset(%rsp) test %rsi,%rsi jle - mov %r8,%r15 - mov %rsi,%rax - neg %r15 + mov %rcx,%rbx + lea (%rcx,%rcx,2),%rax + shl $something,%rbx + mov %rcx,%r15 + mov %rbx,%r10 + lea offset(,%rcx,8),%r14 + mov %rdi,%rbx + lea offset(,%rax,8),%rcx + mov %rdi,%rax + sar $something,%rax + and $something,%ebx + mov %rax,%r13 + mov %rbx,-offset(%rsp) + lea (%r8,%rsi,4),%rbx + mov %rax,-offset(%rsp) + imul %r10,%r13 + mov %rbx,-offset(%rsp) + and $something,%edi + lea offset(,%rax,4),%rbx shl $something,%rax - shl $something,%r15 - lea offset(,%rcx,8),%r13 - lea (%rax,%r8,1),%rcx - lea (%rdx,%r15,1),%rax + mov %rdi,-offset(%rsp) mov %rax,-offset(%rsp) mov %rdx,-offset(%rsp) - mov %rdi,%rax - mov %rdi,%rbx - shl $something,%rax - vmovsd offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%rbx - mov %r8,%rdi - lea offset(%r13),%r14 - mov %rax,%rbp - mov %rcx,%r8 - xchg %ax,%ax - mov -offset(%rsp),%rax - sub %r15,%rax - test %r12,%r12 + vmovsd offset(%rip),%xmm16 # + shl $something,%r15 + add %rdx,%r13 + mov %r8,%r11 + mov %rdx,%rbp + mov %rcx,%r12 + nopl offset(%rax,%rax,1) + cmpq $something,-offset(%rsp) + lea (%r14,%rbp,1),%rcx + lea (%r15,%rbp,1),%rsi + lea offset(%rbp,%r12,1),%rdx jle - mov %rdi,%rcx - neg %rcx - lea (%rax,%r15,1),%r11 - lea (%r9,%r15,1),%r10 - mov %r9,%rdx + mov %rbp,%rdi + mov %r9,%rax + xor %r8d,%r8d jmp - nopw offset(%rax,%rax,1) - cmp $something,%rcx - jle - vmovsd (%rax),%xmm0 - vmovsd %xmm0,(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - inc %rcx - sub $something,%rdx - add %r13,%rax - add %r14,%r11 - add $something,%r10 - cmp %rbx,%rcx + nop + jge + vmovsd (%rdi),%xmm15 + vmovsd offset(%rdi),%xmm14 + vmovsd offset(%rdi),%xmm13 + vmovsd offset(%rdi),%xmm12 + vmovsd (%rcx),%xmm11 + vmovsd offset(%rcx),%xmm10 + vmovsd offset(%rcx),%xmm9 + vmovsd offset(%rcx),%xmm8 + vmovsd (%rsi),%xmm7 + vmovsd offset(%rsi),%xmm6 + vmovsd offset(%rsi),%xmm5 + vmovsd offset(%rsi),%xmm4 + vmovsd (%rdx),%xmm3 + vmovsd offset(%rdx),%xmm2 + vmovsd offset(%rdx),%xmm1 + vmovsd offset(%rdx),%xmm0 + vmovsd %xmm15,(%rax) + vmovsd %xmm14,offset(%rax) + vmovsd %xmm13,offset(%rax) + vmovsd %xmm12,offset(%rax) + vmovsd %xmm11,offset(%rax) + vmovsd %xmm10,offset(%rax) + vmovsd %xmm9,offset(%rax) + vmovsd %xmm8,offset(%rax) + vmovsd %xmm7,offset(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + add $something,%r8 + add %r10,%rdi + add %r10,%rcx + add %r10,%rsi + add %r10,%rdx + sub $something,%rax + cmp %rbx,%r8 je - lea (%rcx,%rdi,1),%rsi - cmp %rsi,%rdi - jle - cmp $something,%rcx - jle - jmp - nopl offset(%rax) - xor %esi,%esi - test %rcx,%rcx - jle - nopw offset(%rax,%rax,1) - vmovsd (%rax,%rsi,8),%xmm0 - vmovsd %xmm0,(%rdx,%rsi,8) - inc %rsi - cmp %rcx,%rsi + cmp %r8,%r11 jne - vdivsd (%r11),%xmm1,%xmm0 - vmovsd %xmm0,(%r10) + vmovsd offset(%rcx),%xmm2 + vmovsd offset(%rsi),%xmm1 + vmovsd offset(%rdx),%xmm0 + vdivsd %xmm2,%xmm16,%xmm2 + vmovsd (%rcx),%xmm8 + vmovsd (%rsi),%xmm7 + vmovsd offset(%rsi),%xmm6 + vmovsd (%rdx),%xmm5 + vmovsd offset(%rdx),%xmm4 + vmovsd offset(%rdx),%xmm3 + vdivsd (%rdi),%xmm16,%xmm9 + vmovsd %xmm8,offset(%rax) + vmovsd %xmm9,(%rax) + vmovsd %xmm7,offset(%rax) /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_COOPERLAKE.o (objdump) @@ -2,88 +2,83 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989fc55 4889d553 AWAVAUATI..UH..S - 0010 48897424 d848c1fe 0448894c 24e04889 H.t$.H...H.L$.H. - 0020 7424e848 85f60f8e cf010000 4d89c748 t$.H........M..H - 0030 89f049f7 df48c1e0 0449c1e7 034c8d2c ..I..H...I...L., - 0040 cd000000 004a8d0c 004a8d04 3a488944 .....J...J..:H.D - 0050 24d04889 5424f048 89f84889 fb48c1e0 $.H.T$.H..H..H.. - 0060 07c5fb10 0d000000 004c8944 24f84c29 .........L.D$.L) - 0070 c34c89c7 4d8d7508 4889c549 89c86690 .L..M.u.H..I..f. - 0080 488b4424 d04c29f8 4d85e40f 8e320100 H.D$.L).M....2.. - 0090 004889f9 48f7d94e 8d1c384f 8d14394c .H..H..N..8O..9L - 00a0 89cae9ca 00000066 0f1f8400 00000000 .......f........ - 00b0 4883f90f 0f8ed600 0000c5fb 1000c5fb H............... - 00c0 1102c5fb 104008c5 fb114208 c5fb1040 .....@....B....@ - 00d0 10c5fb11 4210c5fb 104018c5 fb114218 ....B....@....B. - 00e0 c5fb1040 20c5fb11 4220c5fb 104028c5 ...@ ...B ...@(. - 00f0 fb114228 c5fb1040 30c5fb11 4230c5fb ..B(...@0...B0.. - 0100 104038c5 fb114238 c5fb1040 40c5fb11 .@8...B8...@@... - 0110 4240c5fb 104048c5 fb114248 c5fb1040 B@...@H...BH...@ - 0120 50c5fb11 4250c5fb 104058c5 fb114258 P...BP...@X...BX - 0130 c5fb1040 60c5fb11 4260c5fb 104068c5 ...@`...B`...@h. - 0140 fb114268 c5fb1040 70c5fb11 4270c5fb ..Bh...@p...Bp.. - 0150 104078c5 fb114278 48ffc148 83ea804c .@x...BxH..H...L - 0160 01e84d01 f34981c2 88000000 4839d974 ..M..I......H9.t - 0170 4f488d34 394839f7 0f8e32ff ffff4883 OH.49H9...2...H. - 0180 f90f7ed4 e931ffff ff0f1f80 00000000 ..~..1.......... - 0190 31f64885 c97e1b66 0f1f8400 00000000 1.H..~.f........ - 01a0 c5fb1004 f0c5fb11 04f248ff c64839ce ..........H..H9. - 01b0 75eec4c1 735e03c4 c17b1102 eb9a6690 u...s^...{....f. - 01c0 4901e948 83c71048 83eb1049 83c7804c I..H...H...I...L - 01d0 39c70f85 a8feffff 488b5c24 e8488b6c 9.......H.\$.H.l - 01e0 24f04889 d848c1e0 074c8b44 24f84801 $.H..H...L.D$.H. - 01f0 c54889d8 48c1e004 4901c0f6 4424d808 .H..H...I...D$.. - 0200 0f84db00 00004c8d 6d404d85 e40f8ec7 ......L.m@M..... - 0210 00000048 8b4424e0 4c89c248 f7da4c8d ...H.D$.L..H..L. - 0220 14c50000 0000488d 34d50000 00004d89 ......H.4.....M. - 0230 e3488d7c 3500c5fb 100d0000 0000498d .H.|5.........I. - 0240 5a084c01 ce4d29c3 4c89c8eb 720f1f00 Z.L..M).L...r... - 0250 4883fa07 0f8e0702 0000c5fb 104500c5 H............E.. - 0260 fb1100c5 fb104508 c5fb1140 08c5fb10 ......E....@.... - 0270 4510c5fb 114010c5 fb104518 c5fb1140 E....@....E....@ - 0280 18c5fb10 4520c5fb 114020c5 fb104528 ....E ...@ ...E( - 0290 c5fb1140 28c5fb10 4530c5fb 114030c5 ...@(...E0...@0. - 02a0 fb104538 c5fb1140 3848ffc2 4883c040 ..E8...@8H..H..@ - 02b0 4c01d548 01df4883 c6484c39 da74114a L..H..H..HL9.t.J - 02c0 8d0c0249 39c87e88 4883fa07 7edbeb8a ...I9.~.H...~... - 02d0 4c89e048 c1e00649 01c14983 c0084c89 L..H...I..I...L. - 02e0 edf64424 d8040f84 b5000000 4c8d6d20 ..D$........L.m - 02f0 4d85e40f 8ea10000 00488b44 24e04d89 M........H.D$.M. - 0300 e34c8d14 c5000000 004c89c0 48f7d848 .L.......L..H..H - 0310 8d0cc500 00000048 8d740d00 c5fb100d .......H.t...... - 0320 00000000 498d5a08 4c01c94d 29c34c89 ....I.Z.L..M).L. - 0330 caeb4c0f 1f440000 4883f803 0f8e4e01 ..L..D..H.....N. - 0340 0000c5fb 104500c5 fb1102c5 fb104508 .....E........E. - 0350 c5fb1142 08c5fb10 4510c5fb 114210c5 ...B....E....B.. - 0360 fb104518 c5fb1142 1848ffc0 4883c220 ..E....B.H..H.. - 0370 4c01d548 01de4883 c1284c39 d874114a L..H..H..(L9.t.J - 0380 8d3c0049 39f87eb0 4883f803 7edbebb2 .<.I9.~.H...~... - 0390 4c89e048 c1e00549 01c14983 c0044c89 L..H...I..I...L. - 03a0 edf64424 d8020f84 a1000000 4c8d6d10 ..D$........L.m. - 03b0 4d85e40f 8e8d0000 00488b44 24e04d89 M........H.D$.M. - 03c0 e34c8d14 c5000000 004c89c0 48f7d848 .L.......L..H..H - 03d0 8d0cc500 00000048 8d740d00 c5fb100d .......H.t...... - 03e0 00000000 498d5a08 4c01c94d 29c34c89 ....I.Z.L..M).L. - 03f0 caeb380f 1f440000 4883f801 0f8eb500 ..8..D..H....... - 0400 0000c5fb 104500c5 fb1102c5 fb104508 .....E........E. - 0410 c5fb1142 0848ffc0 4883c210 4c01d548 ...B.H..H...L..H - 0420 01de4883 c1184c39 d874114a 8d3c0049 ..H...L9.t.J.<.I - 0430 39f87ec4 4883f801 7edbebc6 4c89e048 9.~.H...~...L..H - 0440 c1e00449 01c14983 c0024c89 edf64424 ...I..I...L...D$ - 0450 d801757b 5b5d415c 415d415e 31c0415f ..u{[]A\A]A^1.A_ - 0460 c331c948 85d27e1b 0f1f8400 00000000 .1.H..~......... - 0470 c5fb1044 cd00c5fb 1104c848 ffc14839 ...D.......H..H9 - 0480 d175edc5 f35e07c5 fb1106e9 19feffff .u...^.......... - 0490 31ff4885 c07e13c5 fb1044fd 00c5fb11 1.H..~....D..... - 04a0 04fa48ff c74839c7 75edc5f3 5e06c5fb ..H..H9.u...^... - 04b0 1101e9b2 feffff75 09c5fb10 4500c5fb .......u....E... - 04c0 1102c5f3 5e06c5fb 1101e946 ffffff4d ....^......F...M - 04d0 85e47e80 488b4c24 e04c89c2 48f7da4c ..~.H.L$.L..H..L - 04e0 8d14d500 00000048 c1e1034d 89c34a8d .......H...M..J. - 04f0 741500c5 fb100d00 00000048 8d79084d t..........H.y.M - 0500 01ca31c0 49c1e304 eb2b660f 1f440000 ..1.I....+f..D.. - 0510 4885d27e 0bc5fb10 4500c4c1 7b1104c1 H..~....E...{... - 0520 48ffc048 01cd48ff c24801fe 4939c40f H..H..H..H..I9.. - 0530 841fffff ff4939c0 7fd675d4 c5f35e06 .....I9...u...^. - 0540 c4817b11 041aebd8 ..{..... + 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t + 0010 24d848c1 fe024889 7c24e048 894c24f0 $.H...H.|$.H.L$. + 0020 4c894424 d0488974 24e84885 f60f8ee9 L.D$.H.t$.H..... + 0030 02000048 89cb488d 044948c1 e3054989 ...H..H..IH...I. + 0040 cf4989da 4c8d34cd 00000000 4889fb48 .I..L.4.....H..H + 0050 8d0cc500 00000048 89f848c1 f80283e3 .......H..H..... + 0060 024989c5 48895c24 b8498d1c b0488944 .I..H.\$.I...H.D + 0070 24b04d0f afea4889 5c24a883 e701488d $.M...H.\$....H. + 0080 1c850000 000048c1 e0074889 7c24c048 ......H...H.|$.H + 0090 894424c8 48895424 f862e1ff 08100500 .D$.H.T$.b...... + 00a0 00000049 c1e70449 01d54d89 c34889d5 ...I...I..M..H.. + 00b0 4989cc0f 1f440000 48837c24 b000498d I....D..H.|$..I. + 00c0 0c2e498d 342f4a8d 5425000f 8ef70300 ..I.4/J.T%...... + 00d0 004889ef 4c89c845 31c0e9bf 00000090 .H..L..E1....... + 00e0 0f8d9b00 0000c57b 103fc57b 107708c5 .......{.?.{.w.. + 00f0 7b106f10 c57b1067 18c57b10 19c57b10 {.o..{.g..{...{. + 0100 5108c57b 104910c5 7b104118 c5fb103e Q..{.I..{.A....> + 0110 c5fb1076 08c5fb10 6e10c5fb 106618c5 ...v....n....f.. + 0120 fb101ac5 fb105208 c5fb104a 10c5fb10 ......R....J.... + 0130 4218c57b 1138c57b 117008c5 7b116810 B..{.8.{.p..{.h. + 0140 c57b1160 18c57b11 5820c57b 115028c5 .{.`..{.X .{.P(. + 0150 7b114830 c57b1140 38c5fb11 7840c5fb {.H0.{.@8...x@.. + 0160 117048c5 fb116850 c5fb1160 58c5fb11 .pH...hP...`X... + 0170 5860c5fb 115068c5 fb114870 c5fb1140 X`...Ph...Hp...@ + 0180 784983c0 044c01d7 4c01d14c 01d64c01 xI...L..L..L..L. + 0190 d24883e8 804939d8 0f848200 00004d39 .H...I9.......M9 + 01a0 c30f8539 ffffffc5 fb105108 c5fb104e ...9......Q....N + 01b0 10c5fb10 421862f1 ff005ed2 c57b1001 ....B.b...^..{.. + 01c0 c5fb103e c5fb1076 08c5fb10 2ac5fb10 ...>...v....*... + 01d0 6208c5fb 105a1062 71ff005e 0fc57b11 b....Z.bq..^..{. + 01e0 4020c57b 1108c5fb 117840c5 fb117048 @ .{.....x@...pH + 01f0 c5fb1168 60c5fb11 6068c5fb 11587062 ...h`...`h...Xpb + 0200 f1ff005e c9c5fb11 502862f1 ff005ec0 ...^....P(b...^. + 0210 c5fb1148 50c5fb11 4078e962 ffffff90 ...HP...@x.b.... + 0220 4c89e84b 8d0c2e4c 034c24c8 4889da48 L..K...L.L$.H..H + 0230 837c24b8 00746b49 39d30f84 a0010000 .|$..tkI9....... + 0240 7d55c5fb 1038c5fb 107008c5 fb106810 }U...8...p....h. + 0250 c5fb1060 18c5fb10 19c5fb10 5108c5fb ...`........Q... + 0260 104910c5 fb104118 c4c17b11 39c4c17b .I....A...{.9..{ + 0270 117108c4 c17b1169 10c4c17b 116118c4 .q...{.i...{.a.. + 0280 c17b1159 20c4c17b 115128c4 c17b1149 .{.Y ..{.Q(..{.I + 0290 30c4c17b 1141384c 01f84983 c1404883 0..{.A8L..I..@H. + 02a0 c2024883 7c24c000 74394c39 da0f841d ..H.|$..t9L9.... + 02b0 0100007e 2ac5fb10 18c5fb10 5008c5fb ...~*.......P... + 02c0 104810c5 fb104018 c4c17b11 19c4c17b .H....@...{....{ + 02d0 115108c4 c17b1149 10c4c17b 11411849 .Q...{.I...{.A.I + 02e0 83c12049 83c30448 83c52049 83c5204c .. I...H.. I.. L + 02f0 395c24a8 0f85befd ffff488b 5c24e84c 9\$.......H.\$.L + 0300 8b6424f8 4889d848 c1e00549 01c4488b .d$.H..H...I..H. + 0310 4424d048 8d049848 894424d0 f64424d8 D$.H...H.D$..D$. + 0320 020f842e 0100004c 8b5424e0 488b4424 .......L.T$.H.D$ + 0330 f049d1fa 498d0cc4 4d85d20f 8ea70100 .I..I...M....... + 0340 0048c1e0 044889c7 c5fb1025 00000000 .H...H.....%.... + 0350 4c8b5c24 d04f8d04 124c89e6 4c89c831 L.\$.O...L..L..1 + 0360 d2eb3f0f 1f440000 7d25c5fb 101ec5fb ..?..D..}%...... + 0370 105608c5 fb1009c5 fb104108 c5fb1118 .V........A..... + 0380 c5fb1150 08c5fb11 4810c5fb 11401848 ...P....H....@.H + 0390 83c20248 01fe4801 f94883c0 204939d0 ...H..H..H.. I9. + 03a0 74694939 d375c1c5 fb104108 c5fb1009 tiI9.u....A..... + 03b0 c5db5ec0 c5db5e16 c5fb1148 10c5fb11 ..^...^....H.... + 03c0 10c5fb11 4018ebc7 0f1f8400 00000000 ....@........... + 03d0 62f1ff00 5e00c4c1 7b1101e9 fffeffff b...^...{....... + 03e0 c5fb1041 08c5fb10 0962f1ff 005ec062 ...A.....b...^.b + 03f0 f1ff005e 10c4c17b 114920c4 c17b1111 ...^...{.I ..{.. + 0400 c4c17b11 4128e98c feffff49 0faffa4c ..{.A(.....I...L + 0410 89d048c1 e0054c01 e74901c1 4d01d2f6 ..H...L..I..M... + 0420 4424e001 74254c39 5424d00f 84a10000 D$..t%L9T$...... + 0430 007d14c5 fb100fc5 fb104708 c4c17b11 .}........G...{. + 0440 09c4c17b 11410849 83c11048 834424d0 ...{.A.I...H.D$. + 0450 024983c4 10f64424 d8017459 488b7424 .I....D$..tYH.t$ + 0460 e04885f6 7e4f488b 5424f0c5 fb100d00 .H..~OH.T$...... + 0470 00000048 8b4c24d0 48c1e203 31c0eb19 ...H.L$.H...1... + 0480 7d0cc4c1 7b100424 c4c17b11 04c148ff }...{..$..{...H. + 0490 c04901d4 4839c674 1c4839c1 75e248ff .I..H9.t.H9.u.H. + 04a0 c0c4c173 5e042449 01d4c4c1 7b1104c9 ...s^.$I....{... + 04b0 4839c675 e45b5d41 5c415d41 5e31c041 H9.u.[]A\A]A^1.A + 04c0 5fc3660f 1f440000 4889e831 d2e95dfd _.f..D..H..1..]. + 04d0 ffffc5fb 10050000 0000c5fb 5e07c4c1 ............^... + 04e0 7b1101e9 5fffffff 4c89e745 31d2e92c {..._...L..E1.., + 04f0 ffffff ... /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_COOPERLAKE.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 48050000 00420e10 8f02420e ....H....B....B. + 0020 00000000 f3040000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606440e 38830703 45040a0e 30410e28 ..D.8...E...0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0040 8606410e 38830703 a9040a0e 30410e28 ..A.8.......0A.( + 0050 420e2042 0e18420e 10440e08 470b0000 B. B..B..D..G... /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_SKYLAKEX.o (disasm) @@ -9,270 +9,278 @@ push %r14 push %r13 push %r12 - mov %rdi,%r12 + mov %rdx,%r12 push %rbp - mov %rdx,%rbp push %rbx mov %rsi,-offset(%rsp) sar $something,%rsi + mov %rdi,-offset(%rsp) mov %rcx,-offset(%rsp) + mov %r8,-offset(%rsp) mov %rsi,-offset(%rsp) test %rsi,%rsi jle - mov %r8,%r15 - mov %rsi,%rax - neg %r15 + mov %rcx,%rbx + lea (%rcx,%rcx,2),%rax + shl $something,%rbx + mov %rcx,%r15 + mov %rbx,%r10 + lea offset(,%rcx,8),%r14 + mov %rdi,%rbx + lea offset(,%rax,8),%rcx + mov %rdi,%rax + sar $something,%rax + and $something,%ebx + mov %rax,%r13 + mov %rbx,-offset(%rsp) + lea (%r8,%rsi,4),%rbx + mov %rax,-offset(%rsp) + imul %r10,%r13 + mov %rbx,-offset(%rsp) + and $something,%edi + lea offset(,%rax,4),%rbx shl $something,%rax - shl $something,%r15 - lea offset(,%rcx,8),%r13 - lea (%rax,%r8,1),%rcx - lea (%rdx,%r15,1),%rax + mov %rdi,-offset(%rsp) mov %rax,-offset(%rsp) mov %rdx,-offset(%rsp) - mov %rdi,%rax - mov %rdi,%rbx - shl $something,%rax - vmovsd offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%rbx - mov %r8,%rdi - lea offset(%r13),%r14 - mov %rax,%rbp - mov %rcx,%r8 - xchg %ax,%ax - mov -offset(%rsp),%rax - sub %r15,%rax - test %r12,%r12 + vmovsd offset(%rip),%xmm16 # + shl $something,%r15 + add %rdx,%r13 + mov %r8,%r11 + mov %rdx,%rbp + mov %rcx,%r12 + nopl offset(%rax,%rax,1) + cmpq $something,-offset(%rsp) + lea (%r14,%rbp,1),%rcx + lea (%r15,%rbp,1),%rsi + lea offset(%rbp,%r12,1),%rdx jle - mov %rdi,%rcx - neg %rcx - lea (%rax,%r15,1),%r11 - lea (%r9,%r15,1),%r10 - mov %r9,%rdx + mov %rbp,%rdi + mov %r9,%rax + xor %r8d,%r8d jmp - nopw offset(%rax,%rax,1) - cmp $something,%rcx - jle - vmovsd (%rax),%xmm0 - vmovsd %xmm0,(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - inc %rcx - sub $something,%rdx - add %r13,%rax - add %r14,%r11 - add $something,%r10 - cmp %rbx,%rcx + nop + jge + vmovsd (%rdi),%xmm15 + vmovsd offset(%rdi),%xmm14 + vmovsd offset(%rdi),%xmm13 + vmovsd offset(%rdi),%xmm12 + vmovsd (%rcx),%xmm11 + vmovsd offset(%rcx),%xmm10 + vmovsd offset(%rcx),%xmm9 + vmovsd offset(%rcx),%xmm8 + vmovsd (%rsi),%xmm7 + vmovsd offset(%rsi),%xmm6 + vmovsd offset(%rsi),%xmm5 + vmovsd offset(%rsi),%xmm4 + vmovsd (%rdx),%xmm3 + vmovsd offset(%rdx),%xmm2 + vmovsd offset(%rdx),%xmm1 + vmovsd offset(%rdx),%xmm0 + vmovsd %xmm15,(%rax) + vmovsd %xmm14,offset(%rax) + vmovsd %xmm13,offset(%rax) + vmovsd %xmm12,offset(%rax) + vmovsd %xmm11,offset(%rax) + vmovsd %xmm10,offset(%rax) + vmovsd %xmm9,offset(%rax) + vmovsd %xmm8,offset(%rax) + vmovsd %xmm7,offset(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + add $something,%r8 + add %r10,%rdi + add %r10,%rcx + add %r10,%rsi + add %r10,%rdx + sub $something,%rax + cmp %rbx,%r8 je - lea (%rcx,%rdi,1),%rsi - cmp %rsi,%rdi - jle - cmp $something,%rcx - jle - jmp - nopl offset(%rax) - xor %esi,%esi - test %rcx,%rcx - jle - nopw offset(%rax,%rax,1) - vmovsd (%rax,%rsi,8),%xmm0 - vmovsd %xmm0,(%rdx,%rsi,8) - inc %rsi - cmp %rcx,%rsi + cmp %r8,%r11 jne - vdivsd (%r11),%xmm1,%xmm0 - vmovsd %xmm0,(%r10) + vmovsd offset(%rcx),%xmm2 + vmovsd offset(%rsi),%xmm1 + vmovsd offset(%rdx),%xmm0 + vdivsd %xmm2,%xmm16,%xmm2 + vmovsd (%rcx),%xmm8 + vmovsd (%rsi),%xmm7 + vmovsd offset(%rsi),%xmm6 + vmovsd (%rdx),%xmm5 + vmovsd offset(%rdx),%xmm4 + vmovsd offset(%rdx),%xmm3 + vdivsd (%rdi),%xmm16,%xmm9 + vmovsd %xmm8,offset(%rax) + vmovsd %xmm9,(%rax) + vmovsd %xmm7,offset(%rax) /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_SKYLAKEX.o (objdump) @@ -2,88 +2,83 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989fc55 4889d553 AWAVAUATI..UH..S - 0010 48897424 d848c1fe 0448894c 24e04889 H.t$.H...H.L$.H. - 0020 7424e848 85f60f8e cf010000 4d89c748 t$.H........M..H - 0030 89f049f7 df48c1e0 0449c1e7 034c8d2c ..I..H...I...L., - 0040 cd000000 004a8d0c 004a8d04 3a488944 .....J...J..:H.D - 0050 24d04889 5424f048 89f84889 fb48c1e0 $.H.T$.H..H..H.. - 0060 07c5fb10 0d000000 004c8944 24f84c29 .........L.D$.L) - 0070 c34c89c7 4d8d7508 4889c549 89c86690 .L..M.u.H..I..f. - 0080 488b4424 d04c29f8 4d85e40f 8e320100 H.D$.L).M....2.. - 0090 004889f9 48f7d94e 8d1c384f 8d14394c .H..H..N..8O..9L - 00a0 89cae9ca 00000066 0f1f8400 00000000 .......f........ - 00b0 4883f90f 0f8ed600 0000c5fb 1000c5fb H............... - 00c0 1102c5fb 104008c5 fb114208 c5fb1040 .....@....B....@ - 00d0 10c5fb11 4210c5fb 104018c5 fb114218 ....B....@....B. - 00e0 c5fb1040 20c5fb11 4220c5fb 104028c5 ...@ ...B ...@(. - 00f0 fb114228 c5fb1040 30c5fb11 4230c5fb ..B(...@0...B0.. - 0100 104038c5 fb114238 c5fb1040 40c5fb11 .@8...B8...@@... - 0110 4240c5fb 104048c5 fb114248 c5fb1040 B@...@H...BH...@ - 0120 50c5fb11 4250c5fb 104058c5 fb114258 P...BP...@X...BX - 0130 c5fb1040 60c5fb11 4260c5fb 104068c5 ...@`...B`...@h. - 0140 fb114268 c5fb1040 70c5fb11 4270c5fb ..Bh...@p...Bp.. - 0150 104078c5 fb114278 48ffc148 83ea804c .@x...BxH..H...L - 0160 01e84d01 f34981c2 88000000 4839d974 ..M..I......H9.t - 0170 4f488d34 394839f7 0f8e32ff ffff4883 OH.49H9...2...H. - 0180 f90f7ed4 e931ffff ff0f1f80 00000000 ..~..1.......... - 0190 31f64885 c97e1b66 0f1f8400 00000000 1.H..~.f........ - 01a0 c5fb1004 f0c5fb11 04f248ff c64839ce ..........H..H9. - 01b0 75eec4c1 735e03c4 c17b1102 eb9a6690 u...s^...{....f. - 01c0 4901e948 83c71048 83eb1049 83c7804c I..H...H...I...L - 01d0 39c70f85 a8feffff 488b5c24 e8488b6c 9.......H.\$.H.l - 01e0 24f04889 d848c1e0 074c8b44 24f84801 $.H..H...L.D$.H. - 01f0 c54889d8 48c1e004 4901c0f6 4424d808 .H..H...I...D$.. - 0200 0f84db00 00004c8d 6d404d85 e40f8ec7 ......L.m@M..... - 0210 00000048 8b4424e0 4c89c248 f7da4c8d ...H.D$.L..H..L. - 0220 14c50000 0000488d 34d50000 00004d89 ......H.4.....M. - 0230 e3488d7c 3500c5fb 100d0000 0000498d .H.|5.........I. - 0240 5a084c01 ce4d29c3 4c89c8eb 720f1f00 Z.L..M).L...r... - 0250 4883fa07 0f8e0702 0000c5fb 104500c5 H............E.. - 0260 fb1100c5 fb104508 c5fb1140 08c5fb10 ......E....@.... - 0270 4510c5fb 114010c5 fb104518 c5fb1140 E....@....E....@ - 0280 18c5fb10 4520c5fb 114020c5 fb104528 ....E ...@ ...E( - 0290 c5fb1140 28c5fb10 4530c5fb 114030c5 ...@(...E0...@0. - 02a0 fb104538 c5fb1140 3848ffc2 4883c040 ..E8...@8H..H..@ - 02b0 4c01d548 01df4883 c6484c39 da74114a L..H..H..HL9.t.J - 02c0 8d0c0249 39c87e88 4883fa07 7edbeb8a ...I9.~.H...~... - 02d0 4c89e048 c1e00649 01c14983 c0084c89 L..H...I..I...L. - 02e0 edf64424 d8040f84 b5000000 4c8d6d20 ..D$........L.m - 02f0 4d85e40f 8ea10000 00488b44 24e04d89 M........H.D$.M. - 0300 e34c8d14 c5000000 004c89c0 48f7d848 .L.......L..H..H - 0310 8d0cc500 00000048 8d740d00 c5fb100d .......H.t...... - 0320 00000000 498d5a08 4c01c94d 29c34c89 ....I.Z.L..M).L. - 0330 caeb4c0f 1f440000 4883f803 0f8e4e01 ..L..D..H.....N. - 0340 0000c5fb 104500c5 fb1102c5 fb104508 .....E........E. - 0350 c5fb1142 08c5fb10 4510c5fb 114210c5 ...B....E....B.. - 0360 fb104518 c5fb1142 1848ffc0 4883c220 ..E....B.H..H.. - 0370 4c01d548 01de4883 c1284c39 d874114a L..H..H..(L9.t.J - 0380 8d3c0049 39f87eb0 4883f803 7edbebb2 .<.I9.~.H...~... - 0390 4c89e048 c1e00549 01c14983 c0044c89 L..H...I..I...L. - 03a0 edf64424 d8020f84 a1000000 4c8d6d10 ..D$........L.m. - 03b0 4d85e40f 8e8d0000 00488b44 24e04d89 M........H.D$.M. - 03c0 e34c8d14 c5000000 004c89c0 48f7d848 .L.......L..H..H - 03d0 8d0cc500 00000048 8d740d00 c5fb100d .......H.t...... - 03e0 00000000 498d5a08 4c01c94d 29c34c89 ....I.Z.L..M).L. - 03f0 caeb380f 1f440000 4883f801 0f8eb500 ..8..D..H....... - 0400 0000c5fb 104500c5 fb1102c5 fb104508 .....E........E. - 0410 c5fb1142 0848ffc0 4883c210 4c01d548 ...B.H..H...L..H - 0420 01de4883 c1184c39 d874114a 8d3c0049 ..H...L9.t.J.<.I - 0430 39f87ec4 4883f801 7edbebc6 4c89e048 9.~.H...~...L..H - 0440 c1e00449 01c14983 c0024c89 edf64424 ...I..I...L...D$ - 0450 d801757b 5b5d415c 415d415e 31c0415f ..u{[]A\A]A^1.A_ - 0460 c331c948 85d27e1b 0f1f8400 00000000 .1.H..~......... - 0470 c5fb1044 cd00c5fb 1104c848 ffc14839 ...D.......H..H9 - 0480 d175edc5 f35e07c5 fb1106e9 19feffff .u...^.......... - 0490 31ff4885 c07e13c5 fb1044fd 00c5fb11 1.H..~....D..... - 04a0 04fa48ff c74839c7 75edc5f3 5e06c5fb ..H..H9.u...^... - 04b0 1101e9b2 feffff75 09c5fb10 4500c5fb .......u....E... - 04c0 1102c5f3 5e06c5fb 1101e946 ffffff4d ....^......F...M - 04d0 85e47e80 488b4c24 e04c89c2 48f7da4c ..~.H.L$.L..H..L - 04e0 8d14d500 00000048 c1e1034d 89c34a8d .......H...M..J. - 04f0 741500c5 fb100d00 00000048 8d79084d t..........H.y.M - 0500 01ca31c0 49c1e304 eb2b660f 1f440000 ..1.I....+f..D.. - 0510 4885d27e 0bc5fb10 4500c4c1 7b1104c1 H..~....E...{... - 0520 48ffc048 01cd48ff c24801fe 4939c40f H..H..H..H..I9.. - 0530 841fffff ff4939c0 7fd675d4 c5f35e06 .....I9...u...^. - 0540 c4817b11 041aebd8 ..{..... + 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t + 0010 24d848c1 fe024889 7c24e048 894c24f0 $.H...H.|$.H.L$. + 0020 4c894424 d0488974 24e84885 f60f8ee9 L.D$.H.t$.H..... + 0030 02000048 89cb488d 044948c1 e3054989 ...H..H..IH...I. + 0040 cf4989da 4c8d34cd 00000000 4889fb48 .I..L.4.....H..H + 0050 8d0cc500 00000048 89f848c1 f80283e3 .......H..H..... + 0060 024989c5 48895c24 b8498d1c b0488944 .I..H.\$.I...H.D + 0070 24b04d0f afea4889 5c24a883 e701488d $.M...H.\$....H. + 0080 1c850000 000048c1 e0074889 7c24c048 ......H...H.|$.H + 0090 894424c8 48895424 f862e1ff 08100500 .D$.H.T$.b...... + 00a0 00000049 c1e70449 01d54d89 c34889d5 ...I...I..M..H.. + 00b0 4989cc0f 1f440000 48837c24 b000498d I....D..H.|$..I. + 00c0 0c2e498d 342f4a8d 5425000f 8ef70300 ..I.4/J.T%...... + 00d0 004889ef 4c89c845 31c0e9bf 00000090 .H..L..E1....... + 00e0 0f8d9b00 0000c57b 103fc57b 107708c5 .......{.?.{.w.. + 00f0 7b106f10 c57b1067 18c57b10 19c57b10 {.o..{.g..{...{. + 0100 5108c57b 104910c5 7b104118 c5fb103e Q..{.I..{.A....> + 0110 c5fb1076 08c5fb10 6e10c5fb 106618c5 ...v....n....f.. + 0120 fb101ac5 fb105208 c5fb104a 10c5fb10 ......R....J.... + 0130 4218c57b 1138c57b 117008c5 7b116810 B..{.8.{.p..{.h. + 0140 c57b1160 18c57b11 5820c57b 115028c5 .{.`..{.X .{.P(. + 0150 7b114830 c57b1140 38c5fb11 7840c5fb {.H0.{.@8...x@.. + 0160 117048c5 fb116850 c5fb1160 58c5fb11 .pH...hP...`X... + 0170 5860c5fb 115068c5 fb114870 c5fb1140 X`...Ph...Hp...@ + 0180 784983c0 044c01d7 4c01d14c 01d64c01 xI...L..L..L..L. + 0190 d24883e8 804939d8 0f848200 00004d39 .H...I9.......M9 + 01a0 c30f8539 ffffffc5 fb105108 c5fb104e ...9......Q....N + 01b0 10c5fb10 421862f1 ff005ed2 c57b1001 ....B.b...^..{.. + 01c0 c5fb103e c5fb1076 08c5fb10 2ac5fb10 ...>...v....*... + 01d0 6208c5fb 105a1062 71ff005e 0fc57b11 b....Z.bq..^..{. + 01e0 4020c57b 1108c5fb 117840c5 fb117048 @ .{.....x@...pH + 01f0 c5fb1168 60c5fb11 6068c5fb 11587062 ...h`...`h...Xpb + 0200 f1ff005e c9c5fb11 502862f1 ff005ec0 ...^....P(b...^. + 0210 c5fb1148 50c5fb11 4078e962 ffffff90 ...HP...@x.b.... + 0220 4c89e84b 8d0c2e4c 034c24c8 4889da48 L..K...L.L$.H..H + 0230 837c24b8 00746b49 39d30f84 a0010000 .|$..tkI9....... + 0240 7d55c5fb 1038c5fb 107008c5 fb106810 }U...8...p....h. + 0250 c5fb1060 18c5fb10 19c5fb10 5108c5fb ...`........Q... + 0260 104910c5 fb104118 c4c17b11 39c4c17b .I....A...{.9..{ + 0270 117108c4 c17b1169 10c4c17b 116118c4 .q...{.i...{.a.. + 0280 c17b1159 20c4c17b 115128c4 c17b1149 .{.Y ..{.Q(..{.I + 0290 30c4c17b 1141384c 01f84983 c1404883 0..{.A8L..I..@H. + 02a0 c2024883 7c24c000 74394c39 da0f841d ..H.|$..t9L9.... + 02b0 0100007e 2ac5fb10 18c5fb10 5008c5fb ...~*.......P... + 02c0 104810c5 fb104018 c4c17b11 19c4c17b .H....@...{....{ + 02d0 115108c4 c17b1149 10c4c17b 11411849 .Q...{.I...{.A.I + 02e0 83c12049 83c30448 83c52049 83c5204c .. I...H.. I.. L + 02f0 395c24a8 0f85befd ffff488b 5c24e84c 9\$.......H.\$.L + 0300 8b6424f8 4889d848 c1e00549 01c4488b .d$.H..H...I..H. + 0310 4424d048 8d049848 894424d0 f64424d8 D$.H...H.D$..D$. + 0320 020f842e 0100004c 8b5424e0 488b4424 .......L.T$.H.D$ + 0330 f049d1fa 498d0cc4 4d85d20f 8ea70100 .I..I...M....... + 0340 0048c1e0 044889c7 c5fb1025 00000000 .H...H.....%.... + 0350 4c8b5c24 d04f8d04 124c89e6 4c89c831 L.\$.O...L..L..1 + 0360 d2eb3f0f 1f440000 7d25c5fb 101ec5fb ..?..D..}%...... + 0370 105608c5 fb1009c5 fb104108 c5fb1118 .V........A..... + 0380 c5fb1150 08c5fb11 4810c5fb 11401848 ...P....H....@.H + 0390 83c20248 01fe4801 f94883c0 204939d0 ...H..H..H.. I9. + 03a0 74694939 d375c1c5 fb104108 c5fb1009 tiI9.u....A..... + 03b0 c5db5ec0 c5db5e16 c5fb1148 10c5fb11 ..^...^....H.... + 03c0 10c5fb11 4018ebc7 0f1f8400 00000000 ....@........... + 03d0 62f1ff00 5e00c4c1 7b1101e9 fffeffff b...^...{....... + 03e0 c5fb1041 08c5fb10 0962f1ff 005ec062 ...A.....b...^.b + 03f0 f1ff005e 10c4c17b 114920c4 c17b1111 ...^...{.I ..{.. + 0400 c4c17b11 4128e98c feffff49 0faffa4c ..{.A(.....I...L + 0410 89d048c1 e0054c01 e74901c1 4d01d2f6 ..H...L..I..M... + 0420 4424e001 74254c39 5424d00f 84a10000 D$..t%L9T$...... + 0430 007d14c5 fb100fc5 fb104708 c4c17b11 .}........G...{. + 0440 09c4c17b 11410849 83c11048 834424d0 ...{.A.I...H.D$. + 0450 024983c4 10f64424 d8017459 488b7424 .I....D$..tYH.t$ + 0460 e04885f6 7e4f488b 5424f0c5 fb100d00 .H..~OH.T$...... + 0470 00000048 8b4c24d0 48c1e203 31c0eb19 ...H.L$.H...1... + 0480 7d0cc4c1 7b100424 c4c17b11 04c148ff }...{..$..{...H. + 0490 c04901d4 4839c674 1c4839c1 75e248ff .I..H9.t.H9.u.H. + 04a0 c0c4c173 5e042449 01d4c4c1 7b1104c9 ...s^.$I....{... + 04b0 4839c675 e45b5d41 5c415d41 5e31c041 H9.u.[]A\A]A^1.A + 04c0 5fc3660f 1f440000 4889e831 d2e95dfd _.f..D..H..1..]. + 04d0 ffffc5fb 10050000 0000c5fb 5e07c4c1 ............^... + 04e0 7b1101e9 5fffffff 4c89e745 31d2e92c {..._...L..E1.., + 04f0 ffffff ... /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutncopy_SKYLAKEX.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 48050000 00420e10 8f02420e ....H....B....B. + 0020 00000000 f3040000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606440e 38830703 45040a0e 30410e28 ..D.8...E...0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0040 8606410e 38830703 a9040a0e 30410e28 ..A.8.......0A.( + 0050 420e2042 0e18420e 10440e08 470b0000 B. B..B..D..G... /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_COOPERLAKE.o (disasm) @@ -9,251 +9,265 @@ push %r14 push %r13 push %r12 - mov %rdi,%r12 + mov %rdx,%r12 push %rbp push %rbx - mov %rdx,%rbx mov %rsi,-offset(%rsp) sar $something,%rsi + mov %rdi,-offset(%rsp) mov %rcx,-offset(%rsp) + mov %r8,-offset(%rsp) mov %rsi,-offset(%rsp) test %rsi,%rsi jle - mov %r8,%rax - shl $something,%rsi - neg %rax - mov %rdi,%r11 - mov %rdi,%r15 - mov %rsi,%r14 - lea offset(%rdx,%rax,8),%rax - vmovsd offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%r11 - add %r8,%r14 - mov %r8,%rdi - lea offset(,%rcx,8),%rbp + mov %rcx,%rbx + lea (%rcx,%rcx,2),%rax + shl $something,%rbx + mov %rcx,%r15 + mov %rbx,%r10 + lea offset(,%rcx,8),%r14 + mov %rdi,%rbx + lea offset(,%rax,8),%rcx + mov %rdi,%rax + sar $something,%rax + and $something,%ebx + mov %rax,%r13 + mov %rbx,-offset(%rsp) + lea (%r8,%rsi,4),%rbx + mov %rax,-offset(%rsp) + imul %r10,%r13 + mov %rbx,-offset(%rsp) + and $something,%edi + lea offset(,%rax,4),%rbx + shl $something,%rax + mov %rdi,-offset(%rsp) + mov %rax,-offset(%rsp) + mov %rdx,-offset(%rsp) + vmovsd offset(%rip),%xmm16 # shl $something,%r15 - mov %rdx,%r13 - mov %rax,%r8 - nop - mov %r13,%rax - sub $something,%r13 - test %r12,%r12 + add %rdx,%r13 + mov %r8,%r11 + mov %rdx,%rbp + mov %rcx,%r12 + nopl offset(%rax,%rax,1) + cmpq $something,-offset(%rsp) + lea (%r14,%rbp,1),%rcx + lea (%r15,%rbp,1),%rsi + lea offset(%rbp,%r12,1),%rdx jle - mov %r8,%r10 - mov %rdi,%rcx - sub %r13,%r10 - neg %rcx - add %r9,%r10 - mov %r9,%rdx + mov %rbp,%r8 + mov %r9,%rax + xor %edi,%edi jmp - nopw offset(%rax,%rax,1) - cmp $something,%rcx - jle - vmovsd (%rax),%xmm0 - vmovsd %xmm0,(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - inc %rcx - sub $something,%rdx - add %rbp,%rax - add $something,%r10 - cmp %r11,%rcx + xchg %ax,%ax + jge + vmovsd (%r8),%xmm15 + vmovsd offset(%r8),%xmm14 + vmovsd offset(%r8),%xmm13 + vmovsd offset(%r8),%xmm12 + vmovsd (%rcx),%xmm11 + vmovsd offset(%rcx),%xmm10 + vmovsd offset(%rcx),%xmm9 + vmovsd offset(%rcx),%xmm8 + vmovsd (%rsi),%xmm7 + vmovsd offset(%rsi),%xmm6 + vmovsd offset(%rsi),%xmm5 + vmovsd offset(%rsi),%xmm4 + vmovsd (%rdx),%xmm3 + vmovsd offset(%rdx),%xmm2 + vmovsd offset(%rdx),%xmm1 + vmovsd offset(%rdx),%xmm0 + vmovsd %xmm15,(%rax) + vmovsd %xmm14,offset(%rax) + vmovsd %xmm13,offset(%rax) + vmovsd %xmm12,offset(%rax) + vmovsd %xmm11,offset(%rax) + vmovsd %xmm10,offset(%rax) + vmovsd %xmm9,offset(%rax) + vmovsd %xmm8,offset(%rax) + vmovsd %xmm7,offset(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + add $something,%rdi + add %r10,%r8 + add %r10,%rcx + add %r10,%rsi + add %r10,%rdx + sub $something,%rax + cmp %rbx,%rdi je - lea (%rcx,%rdi,1),%rsi - cmp %rsi,%rdi - jle - cmp $something,%rcx - jle - jmp - cs nopw offset(%rax,%rax,1) - xor %esi,%esi - test %rcx,%rcx - jle - nopw offset(%rax,%rax,1) - vmovsd (%rax,%rsi,8),%xmm0 - vmovsd %xmm0,(%rdx,%rsi,8) - inc %rsi - cmp %rcx,%rsi + cmp %rdi,%r11 jne - vmovsd %xmm1,(%r10) + vmovsd (%rcx),%xmm5 + vmovsd (%rsi),%xmm4 + vmovsd offset(%rsi),%xmm3 + vmovsd (%rdx),%xmm2 + vmovsd offset(%rdx),%xmm1 + vmovsd offset(%rdx),%xmm0 + vmovsd %xmm16,(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm16,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm16,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + vmovsd %xmm16,offset(%rax) jmp /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_COOPERLAKE.o (objdump) @@ -2,80 +2,78 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989fc55 534889d3 AWAVAUATI..USH.. - 0010 48897424 e048c1fe 0448894c 24e84889 H.t$.H...H.L$.H. - 0020 7424f048 85f60f8e b6010000 4c89c048 t$.H........L..H - 0030 c1e60448 f7d84989 fb4989ff 4989f648 ...H..I..I..I..H - 0040 8d84c280 000000c5 fb100d00 0000004c ...............L - 0050 894424f8 4d29c34d 01c64c89 c7488d2c .D$.M).M..L..H., - 0060 cd000000 0049c1e7 074989d5 4989c090 .....I...I..I... - 0070 4c89e849 83ed804d 85e40f8e 33010000 L..I...M....3... - 0080 4d89c248 89f94d29 ea48f7d9 4d01ca4c M..H..M).H..M..L - 0090 89cae9c7 00000066 0f1f8400 00000000 .......f........ - 00a0 4883f90f 0f8ed600 0000c5fb 1000c5fb H............... - 00b0 1102c5fb 104008c5 fb114208 c5fb1040 .....@....B....@ - 00c0 10c5fb11 4210c5fb 104018c5 fb114218 ....B....@....B. - 00d0 c5fb1040 20c5fb11 4220c5fb 104028c5 ...@ ...B ...@(. - 00e0 fb114228 c5fb1040 30c5fb11 4230c5fb ..B(...@0...B0.. - 00f0 104038c5 fb114238 c5fb1040 40c5fb11 .@8...B8...@@... - 0100 4240c5fb 104048c5 fb114248 c5fb1040 B@...@H...BH...@ - 0110 50c5fb11 4250c5fb 104058c5 fb114258 P...BP...@X...BX - 0120 c5fb1040 60c5fb11 4260c5fb 104068c5 ...@`...B`...@h. - 0130 fb114268 c5fb1040 70c5fb11 4270c5fb ..Bh...@p...Bp.. - 0140 104078c5 fb114278 48ffc148 83ea8048 .@x...BxH..H...H - 0150 01e84981 c2880000 004c39d9 7452488d ..I......L9.tRH. - 0160 34394839 f70f8e35 ffffff48 83f90f7e 49H9...5...H...~ - 0170 d7e934ff ffff662e 0f1f8400 00000000 ..4...f......... - 0180 31f64885 c97e1b66 0f1f8400 00000000 1.H..~.f........ - 0190 c5fb1004 f0c5fb11 04f248ff c64839ce ..........H..H9. - 01a0 75eec4c1 7b110aeb 9f0f1f80 00000000 u...{........... - 01b0 4d01f948 83c71049 83eb104c 39f70f85 M..H...I...L9... - 01c0 acfeffff 488b7c24 f04c8b44 24f84889 ....H.|$.L.D$.H. - 01d0 f848c1e0 074801c3 4889f848 c1e00449 .H...H..H..H...I - 01e0 01c0f644 24e0080f 84c80000 004c8d5b ...D$........L.[ - 01f0 404d85e4 0f8eb400 0000488b 4424e84c @M........H.D$.L - 0200 89c248f7 da4c89e7 4c8d14c5 00000000 ..H..L..L....... - 0210 c5fb100d 00000000 498d34d1 4c29c74c ........I.4.L).L - 0220 89c8eb6f 0f1f4000 4883fa07 0f8edb01 ...o..@.H....... - 0230 0000c5fb 1003c5fb 1100c5fb 104308c5 .............C.. - 0240 fb114008 c5fb1043 10c5fb11 4010c5fb ..@....C....@... - 0250 104318c5 fb114018 c5fb1043 20c5fb11 .C....@....C ... - 0260 4020c5fb 104328c5 fb114028 c5fb1043 @ ...C(...@(...C - 0270 30c5fb11 4030c5fb 104338c5 fb114038 0...@0...C8...@8 - 0280 48ffc248 83c0404c 01d34883 c6484839 H..H..@L..H..HH9 - 0290 fa74114a 8d0c0249 39c87e8c 4883fa07 .t.J...I9.~.H... - 02a0 7edeeb8e 4c89e048 c1e00649 01c14983 ~...L..H...I..I. - 02b0 c0084c89 dbf64424 e0040f84 a5000000 ..L...D$........ - 02c0 4c8d5b20 4d85e40f 8e910000 00488b44 L.[ M........H.D - 02d0 24e84c89 e74c8d14 c5000000 004c89c0 $.L..L.......L.. - 02e0 48f7d8c5 fb100d00 00000049 8d0cc14c H..........I...L - 02f0 29c74c89 caeb4c66 0f1f8400 00000000 ).L...Lf........ - 0300 4883f803 0f8e2901 0000c5fb 1003c5fb H.....)......... - 0310 1102c5fb 104308c5 fb114208 c5fb1043 .....C....B....C - 0320 10c5fb11 4210c5fb 104318c5 fb114218 ....B....C....B. - 0330 48ffc048 83c2204c 01d34883 c1284839 H..H.. L..H..(H9 - 0340 f874114a 8d34004c 39c67db4 4883f803 .t.J.4.L9.}.H... - 0350 7edeebb6 4c89e048 c1e00549 01c14983 ~...L..H...I..I. - 0360 c0044c89 dbf64424 e0020f84 89000000 ..L...D$........ - 0370 4c8d5b10 4d85e47e 79488b44 24e84c89 L.[.M..~yH.D$.L. - 0380 e74c8d14 c5000000 004c89c0 48f7d8c5 .L.......L..H... - 0390 fb100d00 00000049 8d0cc14c 29c74c89 .......I...L).L. - 03a0 caeb340f 1f440000 4883f801 0f8ea300 ..4..D..H....... - 03b0 0000c5fb 1003c5fb 1102c5fb 104308c5 .............C.. - 03c0 fb114208 48ffc048 83c2104c 01d34883 ..B.H..H...L..H. - 03d0 c1184839 c7741149 8d340049 39f07ec8 ..H9.t.I.4.I9.~. - 03e0 4883f801 7edeebca 4c89e048 c1e00449 H...~...L..H...I - 03f0 01c14983 c0024c89 dbf64424 e0017568 ..I...L...D$..uh - 0400 5b5d415c 415d415e 31c0415f c331c948 []A\A]A^1.A_.1.H - 0410 85d27e16 0f1f4000 c5fb1004 cbc5fb11 ..~...@......... - 0420 04c848ff c14839d1 75eec5fb 110ee94d ..H..H9.u......M - 0430 feffff31 f64885c0 7e12c5fb 1004f3c5 ...1.H..~....... - 0440 fb1104f2 48ffc648 39c675ee c5fb1109 ....H..H9.u..... - 0450 e9dbfeff ff7508c5 fb1003c5 fb1102c5 .....u.......... - 0460 fb1109e9 5cffffff 4d85e47e 93488b4c ....\...M..~.H.L - 0470 24e84c89 c248f7da 4c89c6c5 fb100d00 $.L..H..L....... - 0480 00000048 c1e10349 8d3cd131 c048c1e6 ...H...I.<.1.H.. - 0490 04eb260f 1f440000 4885d27e 0ac5fb10 ..&..D..H..~.... - 04a0 03c4c17b 1104c148 ffc04801 cb48ffc2 ...{...H..H..H.. - 04b0 4939c40f 8447ffff ff4939c0 7fda75d8 I9...G...I9...u. - 04c0 c5fb110c 37ebe0 ....7.. + 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t + 0010 24d848c1 fe024889 7c24e048 894c24f0 $.H...H.|$.H.L$. + 0020 4c894424 d0488974 24e84885 f60f8ec9 L.D$.H.t$.H..... + 0030 02000048 89cb488d 044948c1 e3054989 ...H..H..IH...I. + 0040 cf4989da 4c8d34cd 00000000 4889fb48 .I..L.4.....H..H + 0050 8d0cc500 00000048 89f848c1 f80283e3 .......H..H..... + 0060 024989c5 48895c24 b8498d1c b0488944 .I..H.\$.I...H.D + 0070 24b04d0f afea4889 5c24a883 e701488d $.M...H.\$....H. + 0080 1c850000 000048c1 e0074889 7c24c048 ......H...H.|$.H + 0090 894424c8 48895424 f862e1ff 08100500 .D$.H.T$.b...... + 00a0 00000049 c1e70449 01d54d89 c34889d5 ...I...I..M..H.. + 00b0 4989cc0f 1f440000 48837c24 b000498d I....D..H.|$..I. + 00c0 0c2e498d 342f4a8d 5425000f 8eb70300 ..I.4/J.T%...... + 00d0 004989e8 4c89c831 ffe9c000 00006690 .I..L..1......f. + 00e0 0f8d9f00 0000c441 7b1038c4 417b1070 .......A{.8.A{.p + 00f0 08c4417b 106810c4 417b1060 18c57b10 ..A{.h..A{.`..{. + 0100 19c57b10 5108c57b 104910c5 7b104118 ..{.Q..{.I..{.A. + 0110 c5fb103e c5fb1076 08c5fb10 6e10c5fb ...>...v....n... + 0120 106618c5 fb101ac5 fb105208 c5fb104a .f........R....J + 0130 10c5fb10 4218c57b 1138c57b 117008c5 ....B..{.8.{.p.. + 0140 7b116810 c57b1160 18c57b11 5820c57b {.h..{.`..{.X .{ + 0150 115028c5 7b114830 c57b1140 38c5fb11 .P(.{.H0.{.@8... + 0160 7840c5fb 117048c5 fb116850 c5fb1160 x@...pH...hP...` + 0170 58c5fb11 5860c5fb 115068c5 fb114870 X...X`...Ph...Hp + 0180 c5fb1140 784883c7 044d01d0 4c01d14c ...@xH...M..L..L + 0190 01d64c01 d24883e8 804839df 74624939 ..L..H...H9.tbI9 + 01a0 fb0f8539 ffffffc5 fb1029c5 fb1026c5 ...9......)...&. + 01b0 fb105e08 c5fb1012 c5fb104a 08c5fb10 ..^........J.... + 01c0 421062e1 ff081100 c5fb1168 2062e1ff B.b........h b.. + 01d0 08114005 c5fb1160 40c5fb11 584862e1 ..@....`@...XHb. + 01e0 ff081140 0ac5fb11 5060c5fb 114868c5 ...@....P`...Hh. + 01f0 fb114070 62e1ff08 11400feb 880f1f00 ..@pb....@...... + 0200 4c89e84b 8d0c2e4c 034c24c8 4889da48 L..K...L.L$.H..H + 0210 837c24b8 00746b49 39d30f84 90010000 .|$..tkI9....... + 0220 7d55c5fb 1038c5fb 107008c5 fb106810 }U...8...p....h. + 0230 c5fb1060 18c5fb10 19c5fb10 5108c5fb ...`........Q... + 0240 104910c5 fb104118 c4c17b11 39c4c17b .I....A...{.9..{ + 0250 117108c4 c17b1169 10c4c17b 116118c4 .q...{.i...{.a.. + 0260 c17b1159 20c4c17b 115128c4 c17b1149 .{.Y ..{.Q(..{.I + 0270 30c4c17b 1141384c 01f84983 c1404883 0..{.A8L..I..@H. + 0280 c2024883 7c24c000 74394c39 da0f840d ..H.|$..t9L9.... + 0290 0100007e 2ac5fb10 18c5fb10 5008c5fb ...~*.......P... + 02a0 104810c5 fb104018 c4c17b11 19c4c17b .H....@...{....{ + 02b0 115108c4 c17b1149 10c4c17b 11411849 .Q...{.I...{.A.I + 02c0 83c12049 83c30448 83c52049 83c5204c .. I...H.. I.. L + 02d0 395c24a8 0f85defd ffff488b 5c24e84c 9\$.......H.\$.L + 02e0 8b6424f8 4889d848 c1e00549 01c4488b .d$.H..H...I..H. + 02f0 4424d048 8d049848 894424d0 f64424d8 D$.H...H.D$..D$. + 0300 020f840f 0100004c 8b5424e0 488b4424 .......L.T$.H.D$ + 0310 f049d1fa 498d0cc4 4d85d20f 8e800100 .I..I...M....... + 0320 0048c1e0 044889c7 c5fb1025 00000000 .H...H.....%.... + 0330 4c8b5c24 d04f8d04 124c89e6 4c89c831 L.\$.O...L..L..1 + 0340 d2eb3f0f 1f440000 7e25c5fb 101ec5fb ..?..D..~%...... + 0350 105608c5 fb1009c5 fb104108 c5fb1118 .V........A..... + 0360 c5fb1150 08c5fb11 4810c5fb 11401848 ...P....H....@.H + 0370 83c20248 01fe4801 f94883c0 204939d0 ...H..H..H.. I9. + 0380 744a4c39 da75c1c5 fb1001c5 fb1120c5 tJL9.u........ . + 0390 fb114010 c5fb1160 18ebd40f 1f440000 ..@....`.....D.. + 03a0 62c1ff08 1101e914 ffffff0f 1f440000 b............D.. + 03b0 c5fb1001 62c1ff08 1101c4c1 7b114120 ....b.......{.A + 03c0 62c1ff08 114105e9 abfeffff 490faffa b....A......I... + 03d0 4c89d048 c1e0054c 01e74901 c14d01d2 L..H...L..I..M.. + 03e0 f64424e0 0174254c 3b5424d0 0f84a000 .D$..t%L;T$..... + 03f0 00007e14 c5fb100f c5fb1047 08c4c17b ..~........G...{ + 0400 1109c4c1 7b114108 4983c110 48834424 ....{.A.I...H.D$ + 0410 d0024983 c410f644 24d80174 5a488b74 ..I....D$..tZH.t + 0420 24e04885 f67e5048 8b5424f0 c5fb100d $.H..~PH.T$..... + 0430 00000000 488b4c24 d048c1e2 0331c0eb ....H.L$.H...1.. + 0440 200f1f80 00000000 7d0cc4c1 7b100424 .......}...{..$ + 0450 c4c17b11 04c148ff c04901d4 4839c674 ..{...H..I..H9.t + 0460 164839c1 75e248ff c0c4c17b 110cc949 .H9.u.H....{...I + 0470 01d44839 c675ea5b 5d415c41 5d415e31 ..H9.u.[]A\A]A^1 + 0480 c0415fc3 0f1f4000 4889e831 d2e97dfd .A_...@.H..1..}. + 0490 ffff488b 05000000 00498901 e967ffff ..H......I...g.. + 04a0 ff4c89e7 4531d2e9 34ffffff .L..E1..4... /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_COOPERLAKE.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 c7040000 00420e10 8f02420e .........B....B. + 0020 00000000 ac040000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 f4030a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0040 8606410e 38830703 6b040a0e 30410e28 ..A.8...k...0A.( + 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_SKYLAKEX.o (disasm) @@ -9,251 +9,265 @@ push %r14 push %r13 push %r12 - mov %rdi,%r12 + mov %rdx,%r12 push %rbp push %rbx - mov %rdx,%rbx mov %rsi,-offset(%rsp) sar $something,%rsi + mov %rdi,-offset(%rsp) mov %rcx,-offset(%rsp) + mov %r8,-offset(%rsp) mov %rsi,-offset(%rsp) test %rsi,%rsi jle - mov %r8,%rax - shl $something,%rsi - neg %rax - mov %rdi,%r11 - mov %rdi,%r15 - mov %rsi,%r14 - lea offset(%rdx,%rax,8),%rax - vmovsd offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%r11 - add %r8,%r14 - mov %r8,%rdi - lea offset(,%rcx,8),%rbp + mov %rcx,%rbx + lea (%rcx,%rcx,2),%rax + shl $something,%rbx + mov %rcx,%r15 + mov %rbx,%r10 + lea offset(,%rcx,8),%r14 + mov %rdi,%rbx + lea offset(,%rax,8),%rcx + mov %rdi,%rax + sar $something,%rax + and $something,%ebx + mov %rax,%r13 + mov %rbx,-offset(%rsp) + lea (%r8,%rsi,4),%rbx + mov %rax,-offset(%rsp) + imul %r10,%r13 + mov %rbx,-offset(%rsp) + and $something,%edi + lea offset(,%rax,4),%rbx + shl $something,%rax + mov %rdi,-offset(%rsp) + mov %rax,-offset(%rsp) + mov %rdx,-offset(%rsp) + vmovsd offset(%rip),%xmm16 # shl $something,%r15 - mov %rdx,%r13 - mov %rax,%r8 - nop - mov %r13,%rax - sub $something,%r13 - test %r12,%r12 + add %rdx,%r13 + mov %r8,%r11 + mov %rdx,%rbp + mov %rcx,%r12 + nopl offset(%rax,%rax,1) + cmpq $something,-offset(%rsp) + lea (%r14,%rbp,1),%rcx + lea (%r15,%rbp,1),%rsi + lea offset(%rbp,%r12,1),%rdx jle - mov %r8,%r10 - mov %rdi,%rcx - sub %r13,%r10 - neg %rcx - add %r9,%r10 - mov %r9,%rdx + mov %rbp,%r8 + mov %r9,%rax + xor %edi,%edi jmp - nopw offset(%rax,%rax,1) - cmp $something,%rcx - jle - vmovsd (%rax),%xmm0 - vmovsd %xmm0,(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - vmovsd offset(%rax),%xmm0 - vmovsd %xmm0,offset(%rdx) - inc %rcx - sub $something,%rdx - add %rbp,%rax - add $something,%r10 - cmp %r11,%rcx + xchg %ax,%ax + jge + vmovsd (%r8),%xmm15 + vmovsd offset(%r8),%xmm14 + vmovsd offset(%r8),%xmm13 + vmovsd offset(%r8),%xmm12 + vmovsd (%rcx),%xmm11 + vmovsd offset(%rcx),%xmm10 + vmovsd offset(%rcx),%xmm9 + vmovsd offset(%rcx),%xmm8 + vmovsd (%rsi),%xmm7 + vmovsd offset(%rsi),%xmm6 + vmovsd offset(%rsi),%xmm5 + vmovsd offset(%rsi),%xmm4 + vmovsd (%rdx),%xmm3 + vmovsd offset(%rdx),%xmm2 + vmovsd offset(%rdx),%xmm1 + vmovsd offset(%rdx),%xmm0 + vmovsd %xmm15,(%rax) + vmovsd %xmm14,offset(%rax) + vmovsd %xmm13,offset(%rax) + vmovsd %xmm12,offset(%rax) + vmovsd %xmm11,offset(%rax) + vmovsd %xmm10,offset(%rax) + vmovsd %xmm9,offset(%rax) + vmovsd %xmm8,offset(%rax) + vmovsd %xmm7,offset(%rax) + vmovsd %xmm6,offset(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + add $something,%rdi + add %r10,%r8 + add %r10,%rcx + add %r10,%rsi + add %r10,%rdx + sub $something,%rax + cmp %rbx,%rdi je - lea (%rcx,%rdi,1),%rsi - cmp %rsi,%rdi - jle - cmp $something,%rcx - jle - jmp - cs nopw offset(%rax,%rax,1) - xor %esi,%esi - test %rcx,%rcx - jle - nopw offset(%rax,%rax,1) - vmovsd (%rax,%rsi,8),%xmm0 - vmovsd %xmm0,(%rdx,%rsi,8) - inc %rsi - cmp %rcx,%rsi + cmp %rdi,%r11 jne - vmovsd %xmm1,(%r10) + vmovsd (%rcx),%xmm5 + vmovsd (%rsi),%xmm4 + vmovsd offset(%rsi),%xmm3 + vmovsd (%rdx),%xmm2 + vmovsd offset(%rdx),%xmm1 + vmovsd offset(%rdx),%xmm0 + vmovsd %xmm16,(%rax) + vmovsd %xmm5,offset(%rax) + vmovsd %xmm16,offset(%rax) + vmovsd %xmm4,offset(%rax) + vmovsd %xmm3,offset(%rax) + vmovsd %xmm16,offset(%rax) + vmovsd %xmm2,offset(%rax) + vmovsd %xmm1,offset(%rax) + vmovsd %xmm0,offset(%rax) + vmovsd %xmm16,offset(%rax) jmp /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_SKYLAKEX.o (objdump) @@ -2,80 +2,78 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989fc55 534889d3 AWAVAUATI..USH.. - 0010 48897424 e048c1fe 0448894c 24e84889 H.t$.H...H.L$.H. - 0020 7424f048 85f60f8e b6010000 4c89c048 t$.H........L..H - 0030 c1e60448 f7d84989 fb4989ff 4989f648 ...H..I..I..I..H - 0040 8d84c280 000000c5 fb100d00 0000004c ...............L - 0050 894424f8 4d29c34d 01c64c89 c7488d2c .D$.M).M..L..H., - 0060 cd000000 0049c1e7 074989d5 4989c090 .....I...I..I... - 0070 4c89e849 83ed804d 85e40f8e 33010000 L..I...M....3... - 0080 4d89c248 89f94d29 ea48f7d9 4d01ca4c M..H..M).H..M..L - 0090 89cae9c7 00000066 0f1f8400 00000000 .......f........ - 00a0 4883f90f 0f8ed600 0000c5fb 1000c5fb H............... - 00b0 1102c5fb 104008c5 fb114208 c5fb1040 .....@....B....@ - 00c0 10c5fb11 4210c5fb 104018c5 fb114218 ....B....@....B. - 00d0 c5fb1040 20c5fb11 4220c5fb 104028c5 ...@ ...B ...@(. - 00e0 fb114228 c5fb1040 30c5fb11 4230c5fb ..B(...@0...B0.. - 00f0 104038c5 fb114238 c5fb1040 40c5fb11 .@8...B8...@@... - 0100 4240c5fb 104048c5 fb114248 c5fb1040 B@...@H...BH...@ - 0110 50c5fb11 4250c5fb 104058c5 fb114258 P...BP...@X...BX - 0120 c5fb1040 60c5fb11 4260c5fb 104068c5 ...@`...B`...@h. - 0130 fb114268 c5fb1040 70c5fb11 4270c5fb ..Bh...@p...Bp.. - 0140 104078c5 fb114278 48ffc148 83ea8048 .@x...BxH..H...H - 0150 01e84981 c2880000 004c39d9 7452488d ..I......L9.tRH. - 0160 34394839 f70f8e35 ffffff48 83f90f7e 49H9...5...H...~ - 0170 d7e934ff ffff662e 0f1f8400 00000000 ..4...f......... - 0180 31f64885 c97e1b66 0f1f8400 00000000 1.H..~.f........ - 0190 c5fb1004 f0c5fb11 04f248ff c64839ce ..........H..H9. - 01a0 75eec4c1 7b110aeb 9f0f1f80 00000000 u...{........... - 01b0 4d01f948 83c71049 83eb104c 39f70f85 M..H...I...L9... - 01c0 acfeffff 488b7c24 f04c8b44 24f84889 ....H.|$.L.D$.H. - 01d0 f848c1e0 074801c3 4889f848 c1e00449 .H...H..H..H...I - 01e0 01c0f644 24e0080f 84c80000 004c8d5b ...D$........L.[ - 01f0 404d85e4 0f8eb400 0000488b 4424e84c @M........H.D$.L - 0200 89c248f7 da4c89e7 4c8d14c5 00000000 ..H..L..L....... - 0210 c5fb100d 00000000 498d34d1 4c29c74c ........I.4.L).L - 0220 89c8eb6f 0f1f4000 4883fa07 0f8edb01 ...o..@.H....... - 0230 0000c5fb 1003c5fb 1100c5fb 104308c5 .............C.. - 0240 fb114008 c5fb1043 10c5fb11 4010c5fb ..@....C....@... - 0250 104318c5 fb114018 c5fb1043 20c5fb11 .C....@....C ... - 0260 4020c5fb 104328c5 fb114028 c5fb1043 @ ...C(...@(...C - 0270 30c5fb11 4030c5fb 104338c5 fb114038 0...@0...C8...@8 - 0280 48ffc248 83c0404c 01d34883 c6484839 H..H..@L..H..HH9 - 0290 fa74114a 8d0c0249 39c87e8c 4883fa07 .t.J...I9.~.H... - 02a0 7edeeb8e 4c89e048 c1e00649 01c14983 ~...L..H...I..I. - 02b0 c0084c89 dbf64424 e0040f84 a5000000 ..L...D$........ - 02c0 4c8d5b20 4d85e40f 8e910000 00488b44 L.[ M........H.D - 02d0 24e84c89 e74c8d14 c5000000 004c89c0 $.L..L.......L.. - 02e0 48f7d8c5 fb100d00 00000049 8d0cc14c H..........I...L - 02f0 29c74c89 caeb4c66 0f1f8400 00000000 ).L...Lf........ - 0300 4883f803 0f8e2901 0000c5fb 1003c5fb H.....)......... - 0310 1102c5fb 104308c5 fb114208 c5fb1043 .....C....B....C - 0320 10c5fb11 4210c5fb 104318c5 fb114218 ....B....C....B. - 0330 48ffc048 83c2204c 01d34883 c1284839 H..H.. L..H..(H9 - 0340 f874114a 8d34004c 39c67db4 4883f803 .t.J.4.L9.}.H... - 0350 7edeebb6 4c89e048 c1e00549 01c14983 ~...L..H...I..I. - 0360 c0044c89 dbf64424 e0020f84 89000000 ..L...D$........ - 0370 4c8d5b10 4d85e47e 79488b44 24e84c89 L.[.M..~yH.D$.L. - 0380 e74c8d14 c5000000 004c89c0 48f7d8c5 .L.......L..H... - 0390 fb100d00 00000049 8d0cc14c 29c74c89 .......I...L).L. - 03a0 caeb340f 1f440000 4883f801 0f8ea300 ..4..D..H....... - 03b0 0000c5fb 1003c5fb 1102c5fb 104308c5 .............C.. - 03c0 fb114208 48ffc048 83c2104c 01d34883 ..B.H..H...L..H. - 03d0 c1184839 c7741149 8d340049 39f07ec8 ..H9.t.I.4.I9.~. - 03e0 4883f801 7edeebca 4c89e048 c1e00449 H...~...L..H...I - 03f0 01c14983 c0024c89 dbf64424 e0017568 ..I...L...D$..uh - 0400 5b5d415c 415d415e 31c0415f c331c948 []A\A]A^1.A_.1.H - 0410 85d27e16 0f1f4000 c5fb1004 cbc5fb11 ..~...@......... - 0420 04c848ff c14839d1 75eec5fb 110ee94d ..H..H9.u......M - 0430 feffff31 f64885c0 7e12c5fb 1004f3c5 ...1.H..~....... - 0440 fb1104f2 48ffc648 39c675ee c5fb1109 ....H..H9.u..... - 0450 e9dbfeff ff7508c5 fb1003c5 fb1102c5 .....u.......... - 0460 fb1109e9 5cffffff 4d85e47e 93488b4c ....\...M..~.H.L - 0470 24e84c89 c248f7da 4c89c6c5 fb100d00 $.L..H..L....... - 0480 00000048 c1e10349 8d3cd131 c048c1e6 ...H...I.<.1.H.. - 0490 04eb260f 1f440000 4885d27e 0ac5fb10 ..&..D..H..~.... - 04a0 03c4c17b 1104c148 ffc04801 cb48ffc2 ...{...H..H..H.. - 04b0 4939c40f 8447ffff ff4939c0 7fda75d8 I9...G...I9...u. - 04c0 c5fb110c 37ebe0 ....7.. + 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t + 0010 24d848c1 fe024889 7c24e048 894c24f0 $.H...H.|$.H.L$. + 0020 4c894424 d0488974 24e84885 f60f8ec9 L.D$.H.t$.H..... + 0030 02000048 89cb488d 044948c1 e3054989 ...H..H..IH...I. + 0040 cf4989da 4c8d34cd 00000000 4889fb48 .I..L.4.....H..H + 0050 8d0cc500 00000048 89f848c1 f80283e3 .......H..H..... + 0060 024989c5 48895c24 b8498d1c b0488944 .I..H.\$.I...H.D + 0070 24b04d0f afea4889 5c24a883 e701488d $.M...H.\$....H. + 0080 1c850000 000048c1 e0074889 7c24c048 ......H...H.|$.H + 0090 894424c8 48895424 f862e1ff 08100500 .D$.H.T$.b...... + 00a0 00000049 c1e70449 01d54d89 c34889d5 ...I...I..M..H.. + 00b0 4989cc0f 1f440000 48837c24 b000498d I....D..H.|$..I. + 00c0 0c2e498d 342f4a8d 5425000f 8eb70300 ..I.4/J.T%...... + 00d0 004989e8 4c89c831 ffe9c000 00006690 .I..L..1......f. + 00e0 0f8d9f00 0000c441 7b1038c4 417b1070 .......A{.8.A{.p + 00f0 08c4417b 106810c4 417b1060 18c57b10 ..A{.h..A{.`..{. + 0100 19c57b10 5108c57b 104910c5 7b104118 ..{.Q..{.I..{.A. + 0110 c5fb103e c5fb1076 08c5fb10 6e10c5fb ...>...v....n... + 0120 106618c5 fb101ac5 fb105208 c5fb104a .f........R....J + 0130 10c5fb10 4218c57b 1138c57b 117008c5 ....B..{.8.{.p.. + 0140 7b116810 c57b1160 18c57b11 5820c57b {.h..{.`..{.X .{ + 0150 115028c5 7b114830 c57b1140 38c5fb11 .P(.{.H0.{.@8... + 0160 7840c5fb 117048c5 fb116850 c5fb1160 x@...pH...hP...` + 0170 58c5fb11 5860c5fb 115068c5 fb114870 X...X`...Ph...Hp + 0180 c5fb1140 784883c7 044d01d0 4c01d14c ...@xH...M..L..L + 0190 01d64c01 d24883e8 804839df 74624939 ..L..H...H9.tbI9 + 01a0 fb0f8539 ffffffc5 fb1029c5 fb1026c5 ...9......)...&. + 01b0 fb105e08 c5fb1012 c5fb104a 08c5fb10 ..^........J.... + 01c0 421062e1 ff081100 c5fb1168 2062e1ff B.b........h b.. + 01d0 08114005 c5fb1160 40c5fb11 584862e1 ..@....`@...XHb. + 01e0 ff081140 0ac5fb11 5060c5fb 114868c5 ...@....P`...Hh. + 01f0 fb114070 62e1ff08 11400feb 880f1f00 ..@pb....@...... + 0200 4c89e84b 8d0c2e4c 034c24c8 4889da48 L..K...L.L$.H..H + 0210 837c24b8 00746b49 39d30f84 90010000 .|$..tkI9....... + 0220 7d55c5fb 1038c5fb 107008c5 fb106810 }U...8...p....h. + 0230 c5fb1060 18c5fb10 19c5fb10 5108c5fb ...`........Q... + 0240 104910c5 fb104118 c4c17b11 39c4c17b .I....A...{.9..{ + 0250 117108c4 c17b1169 10c4c17b 116118c4 .q...{.i...{.a.. + 0260 c17b1159 20c4c17b 115128c4 c17b1149 .{.Y ..{.Q(..{.I + 0270 30c4c17b 1141384c 01f84983 c1404883 0..{.A8L..I..@H. + 0280 c2024883 7c24c000 74394c39 da0f840d ..H.|$..t9L9.... + 0290 0100007e 2ac5fb10 18c5fb10 5008c5fb ...~*.......P... + 02a0 104810c5 fb104018 c4c17b11 19c4c17b .H....@...{....{ + 02b0 115108c4 c17b1149 10c4c17b 11411849 .Q...{.I...{.A.I + 02c0 83c12049 83c30448 83c52049 83c5204c .. I...H.. I.. L + 02d0 395c24a8 0f85defd ffff488b 5c24e84c 9\$.......H.\$.L + 02e0 8b6424f8 4889d848 c1e00549 01c4488b .d$.H..H...I..H. + 02f0 4424d048 8d049848 894424d0 f64424d8 D$.H...H.D$..D$. + 0300 020f840f 0100004c 8b5424e0 488b4424 .......L.T$.H.D$ + 0310 f049d1fa 498d0cc4 4d85d20f 8e800100 .I..I...M....... + 0320 0048c1e0 044889c7 c5fb1025 00000000 .H...H.....%.... + 0330 4c8b5c24 d04f8d04 124c89e6 4c89c831 L.\$.O...L..L..1 + 0340 d2eb3f0f 1f440000 7e25c5fb 101ec5fb ..?..D..~%...... + 0350 105608c5 fb1009c5 fb104108 c5fb1118 .V........A..... + 0360 c5fb1150 08c5fb11 4810c5fb 11401848 ...P....H....@.H + 0370 83c20248 01fe4801 f94883c0 204939d0 ...H..H..H.. I9. + 0380 744a4c39 da75c1c5 fb1001c5 fb1120c5 tJL9.u........ . + 0390 fb114010 c5fb1160 18ebd40f 1f440000 ..@....`.....D.. + 03a0 62c1ff08 1101e914 ffffff0f 1f440000 b............D.. + 03b0 c5fb1001 62c1ff08 1101c4c1 7b114120 ....b.......{.A + 03c0 62c1ff08 114105e9 abfeffff 490faffa b....A......I... + 03d0 4c89d048 c1e0054c 01e74901 c14d01d2 L..H...L..I..M.. + 03e0 f64424e0 0174254c 3b5424d0 0f84a000 .D$..t%L;T$..... + 03f0 00007e14 c5fb100f c5fb1047 08c4c17b ..~........G...{ + 0400 1109c4c1 7b114108 4983c110 48834424 ....{.A.I...H.D$ + 0410 d0024983 c410f644 24d80174 5a488b74 ..I....D$..tZH.t + 0420 24e04885 f67e5048 8b5424f0 c5fb100d $.H..~PH.T$..... + 0430 00000000 488b4c24 d048c1e2 0331c0eb ....H.L$.H...1.. + 0440 200f1f80 00000000 7d0cc4c1 7b100424 .......}...{..$ + 0450 c4c17b11 04c148ff c04901d4 4839c674 ..{...H..I..H9.t + 0460 164839c1 75e248ff c0c4c17b 110cc949 .H9.u.H....{...I + 0470 01d44839 c675ea5b 5d415c41 5d415e31 ..H9.u.[]A\A]A^1 + 0480 c0415fc3 0f1f4000 4889e831 d2e97dfd .A_...@.H..1..}. + 0490 ffff488b 05000000 00498901 e967ffff ..H......I...g.. + 04a0 ff4c89e7 4531d2e9 34ffffff .L..E1..4... /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_iutucopy_SKYLAKEX.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 c7040000 00420e10 8f02420e .........B....B. + 0020 00000000 ac040000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 f4030a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0040 8606410e 38830703 6b040a0e 30410e28 ..A.8...k...0A.( + 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_COOPERLAKE.o (disasm) @@ -15,7 +15,7 @@ mov offset(%rip),%rax # mov %rsi,offset(%rsp) mov (%rax),%rax - sar %rsi + sar $something,%rsi mov %rdi,offset(%rsp) mov %rdx,offset(%rsp) mov %rcx,offset(%rsp) @@ -144,7 +144,7 @@ neg %rbp movslq %r10d,%r10 lea (%r9,%rcx,8),%rbx - nopl offset(%rax) + nopl (%rax) vmovsd (%rbx),%xmm1 test %r15,%r15 jle /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_COOPERLAKE.o (objdump) @@ -4,44 +4,44 @@ Contents of section .text: 0000 41574156 41554154 55534881 ec980000 AWAVAUATUSH..... 0010 00488b05 00000000 48897424 70488b00 .H......H.t$pH.. - 0020 48d1fe48 897c2438 48895424 2048894c H..H.|$8H.T$ H.L - 0030 24484c89 4424104c 894c2430 4889b424 $HL.D$.L.L$0H..$ - 0040 80000000 48894424 184885f6 0f8ec304 ....H.D$.H...... - 0050 00004889 f8480384 24d80000 00488984 ..H..H..$....H.. - 0060 24880000 00488b84 24d00000 0048c1ff $....H..$....H.. - 0070 04488d1c c5000000 0048897c 24684989 .H.......H.|$hI. - 0080 deeb4448 8b5c2450 488b4424 20488b74 ..DH.\$PH.D$ H.t - 0090 2410480f afc3488d 04c64889 44241048 $.H...H...H.D$.H - 00a0 8b8424d0 00000048 0fafc348 ff8c2480 ..$....H...H..$. - 00b0 00000048 8b5c2430 488d04c3 48894424 ...H.\$0H...H.D$ - 00c0 300f845d 04000048 8b442418 488b9c24 0..]...H.D$.H..$ - 00d0 88000000 8b902c05 00004889 5c24288d ......,...H.\$(. - 00e0 42ff4898 48854424 380f8537 02000048 B.H.H.D$8..7...H - 00f0 8b442418 48837c24 68004863 80300500 .D$.H.|$h.Hc.0.. - 0100 00894424 60488944 24500f8e 73ffffff ..D$`H.D$P..s... - 0110 488b4424 18488b54 24204863 982c0500 H.D$.H.T$ Hc.,.. - 0120 004c8b7c 245089d8 f7d84898 48234424 .L.|$P....H.H#D$ - 0130 384829d8 480fafd0 895c2464 48895c24 8H).H....\$dH.\$ - 0140 40488b5c 2448488d 1cd34889 5c245848 @H.\$HH...H.\$XH - 0150 8b5c2430 488d04c3 48890424 488b4424 .\$0H...H..$H.D$ - 0160 68488944 2478488b 54242048 8b5c2428 hH.D$xH.T$ H.\$( - 0170 4829da48 85d27e7d 488b7c24 404889d8 H).H..~}H.|$@H.. - 0180 4883ec08 4889d948 0fafcf48 8b5c2460 H...H..H...H.\$` - 0190 ffb424d8 00000049 0fafc748 8d0ccb48 ..$....I...H...H - 01a0 8b5c2420 4c8b4c24 104c8d04 c3488b05 .\$ L.L$.L...H.. - 01b0 00000000 4c89fec4 e1f96ec0 488b4424 ....L.....n.H.D$ - 01c0 28ff90f0 05000048 8b050000 0000488b (......H......H. - 01d0 00486398 2c050000 4c63b830 05000048 .Hc.,...Lc.0...H - 01e0 89442428 895c2474 44897c24 705f4158 .D$(.\$tD.|$p_AX - 01f0 48895c24 40488b74 2440488b 7c245848 H.\$@H.t$@H.|$XH - 0200 29742428 488d56ff 8b4c2464 4c897c24 )t$(H.V..L$dL.|$ - 0210 50488b5c 2428488d 041a480f afc64c8d PH.\$(H...H...L. - 0220 0cc7488d 041a490f afc7488b 5c241048 ..H...I...H.\$.H - 0230 8d14c348 8d04f500 00000049 89c449f7 ...H.......I..I. - 0240 dcffc90f 88b00000 0049c7c5 f8ffffff .........I...... - 0250 8b5c2464 4929c54a 8d04fd00 0000004c .\$dI).J.......L - 0260 89fd4889 44240844 8d53fe48 c1e50448 ..H.D$.D.S.H...H - 0270 63c948f7 dd4d63d2 498d1cc9 0f1f4000 c.H..Mc.I.....@. + 0020 48c1fe03 48897c24 38488954 24204889 H...H.|$8H.T$ H. + 0030 4c24484c 89442410 4c894c24 304889b4 L$HL.D$.L.L$0H.. + 0040 24800000 00488944 24184885 f60f8ec2 $....H.D$.H..... + 0050 04000048 89f84803 8424d800 00004889 ...H..H..$....H. + 0060 84248800 0000488b 8424d000 000048c1 .$....H..$....H. + 0070 ff02488d 1cc50000 00004889 7c246849 ..H.......H.|$hI + 0080 89deeb44 488b5c24 50488b44 2420488b ...DH.\$PH.D$ H. + 0090 74241048 0fafc348 8d04c648 89442410 t$.H...H...H.D$. + 00a0 488b8424 d0000000 480fafc3 48ff8c24 H..$....H...H..$ + 00b0 80000000 488b5c24 30488d04 c3488944 ....H.\$0H...H.D + 00c0 24300f84 5c040000 488b4424 18488b9c $0..\...H.D$.H.. + 00d0 24880000 008b902c 05000048 895c2428 $......,...H.\$( + 00e0 8d42ff48 98488544 24380f85 36020000 .B.H.H.D$8..6... + 00f0 488b4424 1848837c 24680048 63803005 H.D$.H.|$h.Hc.0. + 0100 00008944 24604889 4424500f 8e73ffff ...D$`H.D$P..s.. + 0110 ff488b44 2418488b 54242048 63982c05 .H.D$.H.T$ Hc.,. + 0120 00004c8b 7c245089 d8f7d848 98482344 ..L.|$P....H.H#D + 0130 24384829 d8480faf d0895c24 6448895c $8H).H....\$dH.\ + 0140 2440488b 5c244848 8d1cd348 895c2458 $@H.\$HH...H.\$X + 0150 488b5c24 30488d04 c3488904 24488b44 H.\$0H...H..$H.D + 0160 24684889 44247848 8b542420 488b5c24 $hH.D$xH.T$ H.\$ + 0170 284829da 4885d27e 7d488b7c 24404889 (H).H..~}H.|$@H. + 0180 d84883ec 084889d9 480fafcf 488b5c24 .H...H..H...H.\$ + 0190 60ffb424 d8000000 490fafc7 488d0ccb `..$....I...H... + 01a0 488b5c24 204c8b4c 24104c8d 04c3488b H.\$ L.L$.L...H. + 01b0 05000000 004c89fe c4e1f96e c0488b44 .....L.....n.H.D + 01c0 2428ff90 f0050000 488b0500 00000048 $(......H......H + 01d0 8b004863 982c0500 004c63b8 30050000 ..Hc.,...Lc.0... + 01e0 48894424 28895c24 7444897c 24705f41 H.D$(.\$tD.|$p_A + 01f0 5848895c 2440488b 74244048 8b7c2458 XH.\$@H.t$@H.|$X + 0200 48297424 28488d56 ff8b4c24 644c897c H)t$(H.V..L$dL.| + 0210 2450488b 5c242848 8d041a48 0fafc64c $PH.\$(H...H...L + 0220 8d0cc748 8d041a49 0fafc748 8b5c2410 ...H...I...H.\$. + 0230 488d14c3 488d04f5 00000000 4989c449 H...H.......I..I + 0240 f7dcffc9 0f88af00 000049c7 c5f8ffff ..........I..... + 0250 ff8b5c24 644929c5 4a8d04fd 00000000 ..\$dI).J....... + 0260 4c89fd48 89442408 448d53fe 48c1e504 L..H.D$.D.S.H... + 0270 4863c948 f7dd4d63 d2498d1c c90f1f00 Hc.H..Mc.I...... 0280 c5fb100b 4d85ff0f 8e940000 00488b74 ....M........H.t 0290 2408488b 0424488d 3c324589 d30f1f00 $.H..$H.<2E..... 02a0 c5f35904 c84883c2 0831f6c5 fb1142f8 ..Y..H...1....B. @@ -51,8 +51,8 @@ 02e0 39fa75bc 48ffc94d 01e1488d 142f49ff 9.u.H..M..H../I. 02f0 ca4c01eb 83f9ff75 87488b44 24404c01 .L.....u.H.D$@L. 0300 2424480f af442420 48c1e003 48294424 $$H..D$ H...H)D$ - 0310 5848ff4c 24780f85 4afeffff e962fdff XH.L$x..J....b.. - 0320 ff4889d7 ebbe83fa 010f8ec0 fdffff48 .H.............H + 0310 5848ff4c 24780f85 4bfeffff e963fdff XH.L$x..K....c.. + 0320 ff4889d7 ebbe83fa 010f8ec1 fdffff48 .H.............H 0330 8b5c2438 41bf0100 00004c85 fb0f84bc .\$8A.....L..... 0340 0100004c 89f8488b 74242048 f7d84821 ...L..H.t$ H..H! 0350 d84c29f8 4889f248 0fafd048 8b5c2448 .L).H..H...H.\$H @@ -80,13 +80,13 @@ 04b0 39c975e4 4c01f24c 39d675bc 488b4424 9.u.L..L9.u.H.D$ 04c0 0848ffcf 4c030424 498d3402 49ffcb48 .H..L..$I.4.I..H 04d0 036c2440 83ffff75 81488b44 24184d01 .l$@...u.H.D$.M. - 04e0 ff486380 2c050000 4c39f80f 8efefbff .Hc.,...L9...... + 04e0 ff486380 2c050000 4c39f80f 8efffbff .Hc.,...L9...... 04f0 ff488b5c 24384c85 fb0f8544 feffff48 .H.\$8L....D...H 0500 8b050000 0000488b 00488944 2418ebc9 ......H..H.D$... 0510 4989f2eb a7488b44 24188b80 30050000 I....H.D$...0... 0520 89442460 8b5c2460 8d43ff48 98488544 .D$`.\$`.C.H.H.D 0530 24700f84 53020000 89d8d1f8 4c63f885 $p..S.......Lc.. - 0540 c00f8e44 02000048 8b442438 48c1f804 ...D...H.D$8H... + 0540 c00f8e44 02000048 8b442438 48c1f802 ...D...H.D$8H... 0550 48894424 40488b84 24d00000 004c8d2c H.D$@H..$....L., 0560 c5000000 00eb3a48 8b442420 488b5c24 ......:H.D$ H.\$ 0570 10490faf c7488d04 c3488944 2410488b .I...H...H.D$.H. /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_COOPERLAKE.o (objdump) @@ -6,8 +6,8 @@ 0010 1b0c0708 90010000 94000000 1c000000 ................ 0020 00000000 14090000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ed00103 73010ed8 ..A.8..G....s... - 0050 01530ee0 0102570e d801420e d0010396 .S....W...B..... + 0040 8606410e 38830747 0ed00103 74010ed8 ..A.8..G....t... + 0050 01530ee0 0102570e d801420e d0010395 .S....W...B..... 0060 010ed801 4e0ee001 770ed801 420ed001 ....N...w...B... 0070 0386020e d801470e e0017f0e d801480e ......G.......H. 0080 d00102f1 0a0e3841 0e30410e 28420e20 ......8A.0A.(B. /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_SKYLAKEX.o (disasm) @@ -15,7 +15,7 @@ mov offset(%rip),%rax # mov %rsi,offset(%rsp) mov (%rax),%rax - sar %rsi + sar $something,%rsi mov %rdi,offset(%rsp) mov %rdx,offset(%rsp) mov %rcx,offset(%rsp) @@ -144,7 +144,7 @@ neg %rbp movslq %r10d,%r10 lea (%r9,%rcx,8),%rbx - nopl offset(%rax) + nopl (%rax) vmovsd (%rbx),%xmm1 test %r15,%r15 jle /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_SKYLAKEX.o (objdump) @@ -4,44 +4,44 @@ Contents of section .text: 0000 41574156 41554154 55534881 ec980000 AWAVAUATUSH..... 0010 00488b05 00000000 48897424 70488b00 .H......H.t$pH.. - 0020 48d1fe48 897c2438 48895424 2048894c H..H.|$8H.T$ H.L - 0030 24484c89 4424104c 894c2430 4889b424 $HL.D$.L.L$0H..$ - 0040 80000000 48894424 184885f6 0f8ec304 ....H.D$.H...... - 0050 00004889 f8480384 24d80000 00488984 ..H..H..$....H.. - 0060 24880000 00488b84 24d00000 0048c1ff $....H..$....H.. - 0070 04488d1c c5000000 0048897c 24684989 .H.......H.|$hI. - 0080 deeb4448 8b5c2450 488b4424 20488b74 ..DH.\$PH.D$ H.t - 0090 2410480f afc3488d 04c64889 44241048 $.H...H...H.D$.H - 00a0 8b8424d0 00000048 0fafc348 ff8c2480 ..$....H...H..$. - 00b0 00000048 8b5c2430 488d04c3 48894424 ...H.\$0H...H.D$ - 00c0 300f845d 04000048 8b442418 488b9c24 0..]...H.D$.H..$ - 00d0 88000000 8b902c05 00004889 5c24288d ......,...H.\$(. - 00e0 42ff4898 48854424 380f8537 02000048 B.H.H.D$8..7...H - 00f0 8b442418 48837c24 68004863 80300500 .D$.H.|$h.Hc.0.. - 0100 00894424 60488944 24500f8e 73ffffff ..D$`H.D$P..s... - 0110 488b4424 18488b54 24204863 982c0500 H.D$.H.T$ Hc.,.. - 0120 004c8b7c 245089d8 f7d84898 48234424 .L.|$P....H.H#D$ - 0130 384829d8 480fafd0 895c2464 48895c24 8H).H....\$dH.\$ - 0140 40488b5c 2448488d 1cd34889 5c245848 @H.\$HH...H.\$XH - 0150 8b5c2430 488d04c3 48890424 488b4424 .\$0H...H..$H.D$ - 0160 68488944 2478488b 54242048 8b5c2428 hH.D$xH.T$ H.\$( - 0170 4829da48 85d27e7d 488b7c24 404889d8 H).H..~}H.|$@H.. - 0180 4883ec08 4889d948 0fafcf48 8b5c2460 H...H..H...H.\$` - 0190 ffb424d8 00000049 0fafc748 8d0ccb48 ..$....I...H...H - 01a0 8b5c2420 4c8b4c24 104c8d04 c3488b05 .\$ L.L$.L...H.. - 01b0 00000000 4c89fec4 e1f96ec0 488b4424 ....L.....n.H.D$ - 01c0 28ff90f0 05000048 8b050000 0000488b (......H......H. - 01d0 00486398 2c050000 4c63b830 05000048 .Hc.,...Lc.0...H - 01e0 89442428 895c2474 44897c24 705f4158 .D$(.\$tD.|$p_AX - 01f0 48895c24 40488b74 2440488b 7c245848 H.\$@H.t$@H.|$XH - 0200 29742428 488d56ff 8b4c2464 4c897c24 )t$(H.V..L$dL.|$ - 0210 50488b5c 2428488d 041a480f afc64c8d PH.\$(H...H...L. - 0220 0cc7488d 041a490f afc7488b 5c241048 ..H...I...H.\$.H - 0230 8d14c348 8d04f500 00000049 89c449f7 ...H.......I..I. - 0240 dcffc90f 88b00000 0049c7c5 f8ffffff .........I...... - 0250 8b5c2464 4929c54a 8d04fd00 0000004c .\$dI).J.......L - 0260 89fd4889 44240844 8d53fe48 c1e50448 ..H.D$.D.S.H...H - 0270 63c948f7 dd4d63d2 498d1cc9 0f1f4000 c.H..Mc.I.....@. + 0020 48c1fe03 48897c24 38488954 24204889 H...H.|$8H.T$ H. + 0030 4c24484c 89442410 4c894c24 304889b4 L$HL.D$.L.L$0H.. + 0040 24800000 00488944 24184885 f60f8ec2 $....H.D$.H..... + 0050 04000048 89f84803 8424d800 00004889 ...H..H..$....H. + 0060 84248800 0000488b 8424d000 000048c1 .$....H..$....H. + 0070 ff02488d 1cc50000 00004889 7c246849 ..H.......H.|$hI + 0080 89deeb44 488b5c24 50488b44 2420488b ...DH.\$PH.D$ H. + 0090 74241048 0fafc348 8d04c648 89442410 t$.H...H...H.D$. + 00a0 488b8424 d0000000 480fafc3 48ff8c24 H..$....H...H..$ + 00b0 80000000 488b5c24 30488d04 c3488944 ....H.\$0H...H.D + 00c0 24300f84 5c040000 488b4424 18488b9c $0..\...H.D$.H.. + 00d0 24880000 008b902c 05000048 895c2428 $......,...H.\$( + 00e0 8d42ff48 98488544 24380f85 36020000 .B.H.H.D$8..6... + 00f0 488b4424 1848837c 24680048 63803005 H.D$.H.|$h.Hc.0. + 0100 00008944 24604889 4424500f 8e73ffff ...D$`H.D$P..s.. + 0110 ff488b44 2418488b 54242048 63982c05 .H.D$.H.T$ Hc.,. + 0120 00004c8b 7c245089 d8f7d848 98482344 ..L.|$P....H.H#D + 0130 24384829 d8480faf d0895c24 6448895c $8H).H....\$dH.\ + 0140 2440488b 5c244848 8d1cd348 895c2458 $@H.\$HH...H.\$X + 0150 488b5c24 30488d04 c3488904 24488b44 H.\$0H...H..$H.D + 0160 24684889 44247848 8b542420 488b5c24 $hH.D$xH.T$ H.\$ + 0170 284829da 4885d27e 7d488b7c 24404889 (H).H..~}H.|$@H. + 0180 d84883ec 084889d9 480fafcf 488b5c24 .H...H..H...H.\$ + 0190 60ffb424 d8000000 490fafc7 488d0ccb `..$....I...H... + 01a0 488b5c24 204c8b4c 24104c8d 04c3488b H.\$ L.L$.L...H. + 01b0 05000000 004c89fe c4e1f96e c0488b44 .....L.....n.H.D + 01c0 2428ff90 f0050000 488b0500 00000048 $(......H......H + 01d0 8b004863 982c0500 004c63b8 30050000 ..Hc.,...Lc.0... + 01e0 48894424 28895c24 7444897c 24705f41 H.D$(.\$tD.|$p_A + 01f0 5848895c 2440488b 74244048 8b7c2458 XH.\$@H.t$@H.|$X + 0200 48297424 28488d56 ff8b4c24 644c897c H)t$(H.V..L$dL.| + 0210 2450488b 5c242848 8d041a48 0fafc64c $PH.\$(H...H...L + 0220 8d0cc748 8d041a49 0fafc748 8b5c2410 ...H...I...H.\$. + 0230 488d14c3 488d04f5 00000000 4989c449 H...H.......I..I + 0240 f7dcffc9 0f88af00 000049c7 c5f8ffff ..........I..... + 0250 ff8b5c24 644929c5 4a8d04fd 00000000 ..\$dI).J....... + 0260 4c89fd48 89442408 448d53fe 48c1e504 L..H.D$.D.S.H... + 0270 4863c948 f7dd4d63 d2498d1c c90f1f00 Hc.H..Mc.I...... 0280 c5fb100b 4d85ff0f 8e940000 00488b74 ....M........H.t 0290 2408488b 0424488d 3c324589 d30f1f00 $.H..$H.<2E..... 02a0 c5f35904 c84883c2 0831f6c5 fb1142f8 ..Y..H...1....B. @@ -51,8 +51,8 @@ 02e0 39fa75bc 48ffc94d 01e1488d 142f49ff 9.u.H..M..H../I. 02f0 ca4c01eb 83f9ff75 87488b44 24404c01 .L.....u.H.D$@L. 0300 2424480f af442420 48c1e003 48294424 $$H..D$ H...H)D$ - 0310 5848ff4c 24780f85 4afeffff e962fdff XH.L$x..J....b.. - 0320 ff4889d7 ebbe83fa 010f8ec0 fdffff48 .H.............H + 0310 5848ff4c 24780f85 4bfeffff e963fdff XH.L$x..K....c.. + 0320 ff4889d7 ebbe83fa 010f8ec1 fdffff48 .H.............H 0330 8b5c2438 41bf0100 00004c85 fb0f84bc .\$8A.....L..... 0340 0100004c 89f8488b 74242048 f7d84821 ...L..H.t$ H..H! 0350 d84c29f8 4889f248 0fafd048 8b5c2448 .L).H..H...H.\$H @@ -80,13 +80,13 @@ 04b0 39c975e4 4c01f24c 39d675bc 488b4424 9.u.L..L9.u.H.D$ 04c0 0848ffcf 4c030424 498d3402 49ffcb48 .H..L..$I.4.I..H 04d0 036c2440 83ffff75 81488b44 24184d01 .l$@...u.H.D$.M. - 04e0 ff486380 2c050000 4c39f80f 8efefbff .Hc.,...L9...... + 04e0 ff486380 2c050000 4c39f80f 8efffbff .Hc.,...L9...... 04f0 ff488b5c 24384c85 fb0f8544 feffff48 .H.\$8L....D...H 0500 8b050000 0000488b 00488944 2418ebc9 ......H..H.D$... 0510 4989f2eb a7488b44 24188b80 30050000 I....H.D$...0... 0520 89442460 8b5c2460 8d43ff48 98488544 .D$`.\$`.C.H.H.D 0530 24700f84 53020000 89d8d1f8 4c63f885 $p..S.......Lc.. - 0540 c00f8e44 02000048 8b442438 48c1f804 ...D...H.D$8H... + 0540 c00f8e44 02000048 8b442438 48c1f802 ...D...H.D$8H... 0550 48894424 40488b84 24d00000 004c8d2c H.D$@H..$....L., 0560 c5000000 00eb3a48 8b442420 488b5c24 ......:H.D$ H.\$ 0570 10490faf c7488d04 c3488944 2410488b .I...H...H.D$.H. /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LN_SKYLAKEX.o (objdump) @@ -6,8 +6,8 @@ 0010 1b0c0708 90010000 94000000 1c000000 ................ 0020 00000000 14090000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ed00103 73010ed8 ..A.8..G....s... - 0050 01530ee0 0102570e d801420e d0010396 .S....W...B..... + 0040 8606410e 38830747 0ed00103 74010ed8 ..A.8..G....t... + 0050 01530ee0 0102570e d801420e d0010395 .S....W...B..... 0060 010ed801 4e0ee001 770ed801 420ed001 ....N...w...B... 0070 0386020e d801470e e0017f0e d801480e ......G.......H. 0080 d00102f1 0a0e3841 0e30410e 28420e20 ......8A.0A.(B. /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_COOPERLAKE.o (disasm) @@ -7,7 +7,7 @@ dtrsm_kernel_LT_COOPERLAKE: push %r15 mov %rsi,%rax - sar %rax + sar $something,%rax push %r14 push %r13 push %r12 @@ -82,7 +82,7 @@ mov %r10,%r11 mov $something,%r9d xor %r8d,%r8d - cs nopw offset(%rax,%rax,1) + nopw offset(%rax,%rax,1) vmovsd (%r11),%xmm2 test %r15,%r15 jle /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_COOPERLAKE.o (objdump) @@ -2,28 +2,28 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574889 f048d1f8 41564155 41545553 AWH..H..AVAUATUS - 0010 4883ec78 488b1d00 00000048 897c2430 H..xH......H.|$0 - 0020 488b1b48 89742450 48895c24 288b9b30 H..H.t$PH.\$(..0 - 0030 05000048 89542420 48894c24 384c8944 ...H.T$ H.L$8L.D - 0040 24084c89 4c241048 89442460 895c2448 $.L.L$.H.D$`.\$H - 0050 4885c00f 8eef0100 0048c1ff 04488b84 H........H...H.. - 0060 24b00000 0048897c 24584c8d 24c50000 $....H.|$XL.$... - 0070 00004c63 fb488b44 2428488b 5c24588b ..Lc.H.D$(H.\$X. - 0080 802c0500 00894424 404885db 0f8e9b04 .,....D$@H...... - 0090 0000488b 74243848 895c2468 48897424 ..H.t$8H.\$hH.t$ - 00a0 18488bac 24b80000 00488b5c 24104863 .H..$....H.\$.Hc - 00b0 f84885ed 7e5f4883 ec08ffb4 24b80000 .H..~_H.....$... - 00c0 00488b05 00000000 4989d94c 8b442418 .H......I..L.D$. - 00d0 488b4c24 28c4e1f9 6ec0488b 4424384c H.L$(...n.H.D$8L - 00e0 89fe4889 eaff90f0 05000048 8b050000 ..H........H.... - 00f0 0000488b 004c63b8 30050000 4863b82c ..H..Lc.0...Hc., - 0100 05000048 89442438 44897c24 58897c24 ...H.D$8D.|$X.|$ - 0110 50415941 5a4c89f8 480fafc5 488b7424 PAYAZL..H...H.t$ - 0120 08488b4c 2418488d 34c64889 f8480faf .H.L$.H.4.H..H.. - 0130 c54c8d2c fd000000 004c8d14 c14885ff .L.,.....L...H.. - 0140 0f8e8b00 00004d8d 75084d89 d341b901 ......M.u.M..A.. - 0150 00000045 31c0662e 0f1f8400 00000000 ...E1.f......... + 0000 41574889 f048c1f8 03415641 55415455 AWH..H...AVAUATU + 0010 534883ec 78488b1d 00000000 48897c24 SH..xH......H.|$ + 0020 30488b1b 48897424 5048895c 24288b9b 0H..H.t$PH.\$(.. + 0030 30050000 48895424 2048894c 24384c89 0...H.T$ H.L$8L. + 0040 4424084c 894c2410 48894424 60895c24 D$.L.L$.H.D$`.\$ + 0050 484885c0 0f8eee01 000048c1 ff02488b HH........H...H. + 0060 8424b000 00004889 7c24584c 8d24c500 .$....H.|$XL.$.. + 0070 0000004c 63fb488b 44242848 8b5c2458 ...Lc.H.D$(H.\$X + 0080 8b802c05 00008944 24404885 db0f8e9a ..,....D$@H..... + 0090 04000048 8b742438 48895c24 68488974 ...H.t$8H.\$hH.t + 00a0 2418488b ac24b800 0000488b 5c241048 $.H..$....H.\$.H + 00b0 63f84885 ed7e5f48 83ec08ff b424b800 c.H..~_H.....$.. + 00c0 0000488b 05000000 004989d9 4c8b4424 ..H......I..L.D$ + 00d0 18488b4c 2428c4e1 f96ec048 8b442438 .H.L$(...n.H.D$8 + 00e0 4c89fe48 89eaff90 f0050000 488b0500 L..H........H... + 00f0 00000048 8b004c63 b8300500 004863b8 ...H..Lc.0...Hc. + 0100 2c050000 48894424 3844897c 2458897c ,...H.D$8D.|$X.| + 0110 24504159 415a4c89 f8480faf c5488b74 $PAYAZL..H...H.t + 0120 2408488b 4c241848 8d34c648 89f8480f $.H.L$.H.4.H..H. + 0130 afc54c8d 2cfd0000 00004c8d 14c14885 ..L.,.....L...H. + 0140 ff0f8e8a 0000004d 8d75084d 89d341b9 .......M.u.M..A. + 0150 01000000 4531c066 0f1f8400 00000000 ....E1.f........ 0160 c4c17b10 134d85ff 7e564889 da31c990 ..{..M..~VH..1.. 0170 c4a16b59 04c24883 c60848ff c1c5fb11 ..kY..H...H..... 0180 46f8c4a1 7b1104c2 4c39cf0f 8e3f0200 F...{...L9...?.. @@ -33,15 +33,15 @@ 01c0 49ffc04d 01ea49ff c14d01f3 4939f875 I..M..I..M..I9.u 01d0 8f488b44 24204c01 eb480faf c74801fd .H.D$ L..H...H.. 01e0 48ff4c24 68488b74 2418488d 04c64889 H.L$hH.t$.H...H. - 01f0 4424180f 85b8feff ff8b4424 40ffc848 D$........D$@..H + 01f0 4424180f 85b9feff ff8b4424 40ffc848 D$........D$@..H 0200 98488544 24300f85 d2010000 488b4424 .H.D$0......H.D$ 0210 20488b5c 2408490f afc7488d 04c34889 H.\$.I...H...H. 0220 44240848 8b8424b0 00000048 8b5c2410 D$.H..$....H.\$. 0230 490fafc7 48ff4c24 60488d04 c3488944 I...H.L$`H...H.D - 0240 24100f85 2dfeffff 8b5c2448 8d43ff48 $...-....\$H.C.H + 0240 24100f85 2efeffff 8b5c2448 8d43ff48 $........\$H.C.H 0250 98488544 24500f84 ed020000 89d8d1f8 .H.D$P.......... 0260 4c63e085 c00f8ede 02000048 8b442430 Lc.........H.D$0 - 0270 48c1f804 48894424 40488b84 24b00000 H...H.D$@H..$... + 0270 48c1f802 48894424 40488b84 24b00000 H...H.D$@H..$... 0280 004c8d3c c5000000 00eb0949 d1fc0f84 .L.<.......I.... 0290 b5020000 4c856424 5074f048 8b050000 ....L.d$Pt.H.... 02a0 00004c8b 30488b44 2440458b 9e2c0500 ..L.0H.D$@E..,.. /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_COOPERLAKE.o (objdump) @@ -4,10 +4,10 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 94000000 1c000000 ................ - 0020 00000000 20070000 00420e10 8f02480e .... ....B....H. + 0020 00000000 20070000 00420e10 8f02490e .... ....B....I. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 0040 8606410e 38830744 0eb00102 a60eb801 ..A.8..D........ - 0050 470ec001 02520eb8 01420eb0 0103c801 G....R...B...... + 0050 470ec001 02520eb8 01420eb0 0103c701 G....R...B...... 0060 0eb80147 0ec0016c 0eb80144 0eb00102 ...G...l...D.... 0070 f40eb801 470ec001 02470eb8 01420eb0 ....G....G...B.. 0080 0102f50a 0e38410e 30410e28 420e2042 .....8A.0A.(B. B /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_SKYLAKEX.o (disasm) @@ -7,7 +7,7 @@ dtrsm_kernel_LT_SKYLAKEX: push %r15 mov %rsi,%rax - sar %rax + sar $something,%rax push %r14 push %r13 push %r12 @@ -82,7 +82,7 @@ mov %r10,%r11 mov $something,%r9d xor %r8d,%r8d - cs nopw offset(%rax,%rax,1) + nopw offset(%rax,%rax,1) vmovsd (%r11),%xmm2 test %r15,%r15 jle /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_SKYLAKEX.o (objdump) @@ -2,28 +2,28 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574889 f048d1f8 41564155 41545553 AWH..H..AVAUATUS - 0010 4883ec78 488b1d00 00000048 897c2430 H..xH......H.|$0 - 0020 488b1b48 89742450 48895c24 288b9b30 H..H.t$PH.\$(..0 - 0030 05000048 89542420 48894c24 384c8944 ...H.T$ H.L$8L.D - 0040 24084c89 4c241048 89442460 895c2448 $.L.L$.H.D$`.\$H - 0050 4885c00f 8eef0100 0048c1ff 04488b84 H........H...H.. - 0060 24b00000 0048897c 24584c8d 24c50000 $....H.|$XL.$... - 0070 00004c63 fb488b44 2428488b 5c24588b ..Lc.H.D$(H.\$X. - 0080 802c0500 00894424 404885db 0f8e9b04 .,....D$@H...... - 0090 0000488b 74243848 895c2468 48897424 ..H.t$8H.\$hH.t$ - 00a0 18488bac 24b80000 00488b5c 24104863 .H..$....H.\$.Hc - 00b0 f84885ed 7e5f4883 ec08ffb4 24b80000 .H..~_H.....$... - 00c0 00488b05 00000000 4989d94c 8b442418 .H......I..L.D$. - 00d0 488b4c24 28c4e1f9 6ec0488b 4424384c H.L$(...n.H.D$8L - 00e0 89fe4889 eaff90f0 05000048 8b050000 ..H........H.... - 00f0 0000488b 004c63b8 30050000 4863b82c ..H..Lc.0...Hc., - 0100 05000048 89442438 44897c24 58897c24 ...H.D$8D.|$X.|$ - 0110 50415941 5a4c89f8 480fafc5 488b7424 PAYAZL..H...H.t$ - 0120 08488b4c 2418488d 34c64889 f8480faf .H.L$.H.4.H..H.. - 0130 c54c8d2c fd000000 004c8d14 c14885ff .L.,.....L...H.. - 0140 0f8e8b00 00004d8d 75084d89 d341b901 ......M.u.M..A.. - 0150 00000045 31c0662e 0f1f8400 00000000 ...E1.f......... + 0000 41574889 f048c1f8 03415641 55415455 AWH..H...AVAUATU + 0010 534883ec 78488b1d 00000000 48897c24 SH..xH......H.|$ + 0020 30488b1b 48897424 5048895c 24288b9b 0H..H.t$PH.\$(.. + 0030 30050000 48895424 2048894c 24384c89 0...H.T$ H.L$8L. + 0040 4424084c 894c2410 48894424 60895c24 D$.L.L$.H.D$`.\$ + 0050 484885c0 0f8eee01 000048c1 ff02488b HH........H...H. + 0060 8424b000 00004889 7c24584c 8d24c500 .$....H.|$XL.$.. + 0070 0000004c 63fb488b 44242848 8b5c2458 ...Lc.H.D$(H.\$X + 0080 8b802c05 00008944 24404885 db0f8e9a ..,....D$@H..... + 0090 04000048 8b742438 48895c24 68488974 ...H.t$8H.\$hH.t + 00a0 2418488b ac24b800 0000488b 5c241048 $.H..$....H.\$.H + 00b0 63f84885 ed7e5f48 83ec08ff b424b800 c.H..~_H.....$.. + 00c0 0000488b 05000000 004989d9 4c8b4424 ..H......I..L.D$ + 00d0 18488b4c 2428c4e1 f96ec048 8b442438 .H.L$(...n.H.D$8 + 00e0 4c89fe48 89eaff90 f0050000 488b0500 L..H........H... + 00f0 00000048 8b004c63 b8300500 004863b8 ...H..Lc.0...Hc. + 0100 2c050000 48894424 3844897c 2458897c ,...H.D$8D.|$X.| + 0110 24504159 415a4c89 f8480faf c5488b74 $PAYAZL..H...H.t + 0120 2408488b 4c241848 8d34c648 89f8480f $.H.L$.H.4.H..H. + 0130 afc54c8d 2cfd0000 00004c8d 14c14885 ..L.,.....L...H. + 0140 ff0f8e8a 0000004d 8d75084d 89d341b9 .......M.u.M..A. + 0150 01000000 4531c066 0f1f8400 00000000 ....E1.f........ 0160 c4c17b10 134d85ff 7e564889 da31c990 ..{..M..~VH..1.. 0170 c4a16b59 04c24883 c60848ff c1c5fb11 ..kY..H...H..... 0180 46f8c4a1 7b1104c2 4c39cf0f 8e3f0200 F...{...L9...?.. @@ -33,15 +33,15 @@ 01c0 49ffc04d 01ea49ff c14d01f3 4939f875 I..M..I..M..I9.u 01d0 8f488b44 24204c01 eb480faf c74801fd .H.D$ L..H...H.. 01e0 48ff4c24 68488b74 2418488d 04c64889 H.L$hH.t$.H...H. - 01f0 4424180f 85b8feff ff8b4424 40ffc848 D$........D$@..H + 01f0 4424180f 85b9feff ff8b4424 40ffc848 D$........D$@..H 0200 98488544 24300f85 d2010000 488b4424 .H.D$0......H.D$ 0210 20488b5c 2408490f afc7488d 04c34889 H.\$.I...H...H. 0220 44240848 8b8424b0 00000048 8b5c2410 D$.H..$....H.\$. 0230 490fafc7 48ff4c24 60488d04 c3488944 I...H.L$`H...H.D - 0240 24100f85 2dfeffff 8b5c2448 8d43ff48 $...-....\$H.C.H + 0240 24100f85 2efeffff 8b5c2448 8d43ff48 $........\$H.C.H 0250 98488544 24500f84 ed020000 89d8d1f8 .H.D$P.......... 0260 4c63e085 c00f8ede 02000048 8b442430 Lc.........H.D$0 - 0270 48c1f804 48894424 40488b84 24b00000 H...H.D$@H..$... + 0270 48c1f802 48894424 40488b84 24b00000 H...H.D$@H..$... 0280 004c8d3c c5000000 00eb0949 d1fc0f84 .L.<.......I.... 0290 b5020000 4c856424 5074f048 8b050000 ....L.d$Pt.H.... 02a0 00004c8b 30488b44 2440458b 9e2c0500 ..L.0H.D$@E..,.. /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_LT_SKYLAKEX.o (objdump) @@ -4,10 +4,10 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 94000000 1c000000 ................ - 0020 00000000 20070000 00420e10 8f02480e .... ....B....H. + 0020 00000000 20070000 00420e10 8f02490e .... ....B....I. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 0040 8606410e 38830744 0eb00102 a60eb801 ..A.8..D........ - 0050 470ec001 02520eb8 01420eb0 0103c801 G....R...B...... + 0050 470ec001 02520eb8 01420eb0 0103c701 G....R...B...... 0060 0eb80147 0ec0016c 0eb80144 0eb00102 ...G...l...D.... 0070 f40eb801 470ec001 02470eb8 01420eb0 ....G....G...B.. 0080 0102f50a 0e38410e 30410e28 420e2042 .....8A.0A.(B. B /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_COOPERLAKE.o (disasm) @@ -7,7 +7,7 @@ dtrsm_kernel_RN_COOPERLAKE: push %r15 mov %rsi,%rax - sar %rax + sar $something,%rax push %r14 push %r13 push %r12 @@ -108,7 +108,7 @@ lea offset(%r13,%r15,1),%rbp xor %r12d,%r12d mov $something,%r8d - nopl (%rax) + xchg %ax,%ax mov %rbp,%rcx vmovsd offset(%r13),%xmm1 sub %r15,%rcx /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_COOPERLAKE.o (objdump) @@ -2,36 +2,36 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574889 f048d1f8 41564155 41545553 AWH..H..AVAUATUS - 0010 4881ec98 00000048 89742470 488bb424 H......H.t$pH..$ - 0020 d8000000 48897c24 4848f7de 48897424 ....H.|$HH..H.t$ - 0030 10488b35 00000000 48895424 38488b36 .H.5....H.T$8H.6 - 0040 48894c24 60488974 24408bb6 30050000 H.L$`H.t$@..0... - 0050 4c894424 204c894c 24304889 84248000 L.D$ L.L$0H..$.. - 0060 00008974 24584c8b bc24d000 00004885 ...t$XL..$....H. - 0070 c00f8ec4 03000048 c1ff0448 63de4889 .......H...Hc.H. - 0080 7c24684e 8d34fd00 00000049 89daeb57 |$hN.4.....I...W - 0090 8b442450 ffc84898 48854424 480f853d .D$P..H.H.D$H..= - 00a0 02000048 8b442438 488b7c24 20490faf ...H.D$8H.|$ I.. - 00b0 c24c0154 2410488d 04c74889 44242048 .L.T$.H...H.D$ H - 00c0 8b8424d0 00000048 8b7c2430 490fafc2 ..$....H.|$0I... - 00d0 48ff8c24 80000000 488d04c7 48894424 H..$....H...H.D$ - 00e0 300f844c 03000048 8b442440 48837c24 0..L...H.D$@H.|$ - 00f0 68008b80 2c050000 89442450 488b4424 h...,....D$PH.D$ - 0100 30488944 2408488b 44246048 89442428 0H.D$.H.D$`H.D$( - 0110 0f8e7aff ffff488b 4424684c 635c2450 ..z...H.D$hLc\$P - 0120 48894424 78488b54 24104885 d27e6148 H.D$xH.T$.H..~aH - 0130 83ec08ff b424d800 0000488b 05000000 .....$....H..... - 0140 004c89d6 4c8b4c24 184c8b44 2430488b .L..L.L$.L.D$0H. - 0150 4c2438c4 e1f96ec0 488b4424 504c89df L$8...n.H.D$PL.. - 0160 ff90f005 0000488b 05000000 00488b00 ......H......H.. - 0170 4c639030 0500004c 63982c05 00004889 Lc.0...Lc.,...H. - 0180 44245044 89542468 44895c24 6041595b D$PD.T$hD.\$`AY[ - 0190 488b7c24 10488b74 24204889 f8490faf H.|$.H.t$ H..I.. - 01a0 c24c8d2c c64889f8 490fafc3 488b7c24 .L.,.H..I...H.|$ - 01b0 28488d14 c74d85d2 0f8edf00 00004e8d (H...M........N. - 01c0 3cd50000 0000498d 47084889 4424184b <.....I.G.H.D$.K - 01d0 8d6c3d00 4531e441 b8010000 000f1f00 .l=.E1.A........ + 0000 41574889 f048c1f8 03415641 55415455 AWH..H...AVAUATU + 0010 534881ec 98000000 48897424 70488bb4 SH......H.t$pH.. + 0020 24d80000 0048897c 244848f7 de488974 $....H.|$HH..H.t + 0030 2410488b 35000000 00488954 2438488b $.H.5....H.T$8H. + 0040 3648894c 24604889 7424408b b6300500 6H.L$`H.t$@..0.. + 0050 004c8944 24204c89 4c243048 89842480 .L.D$ L.L$0H..$. + 0060 00000089 7424584c 8bbc24d0 00000048 ....t$XL..$....H + 0070 85c00f8e c3030000 48c1ff02 4863de48 ........H...Hc.H + 0080 897c2468 4e8d34fd 00000000 4989daeb .|$hN.4.....I... + 0090 578b4424 50ffc848 98488544 24480f85 W.D$P..H.H.D$H.. + 00a0 3c020000 488b4424 38488b7c 2420490f <...H.D$8H.|$ I. + 00b0 afc24c01 54241048 8d04c748 89442420 ..L.T$.H...H.D$ + 00c0 488b8424 d0000000 488b7c24 30490faf H..$....H.|$0I.. + 00d0 c248ff8c 24800000 00488d04 c7488944 .H..$....H...H.D + 00e0 24300f84 4b030000 488b4424 4048837c $0..K...H.D$@H.| + 00f0 2468008b 802c0500 00894424 50488b44 $h...,....D$PH.D + 0100 24304889 44240848 8b442460 48894424 $0H.D$.H.D$`H.D$ + 0110 280f8e7a ffffff48 8b442468 4c635c24 (..z...H.D$hLc\$ + 0120 50488944 2478488b 54241048 85d27e61 PH.D$xH.T$.H..~a + 0130 4883ec08 ffb424d8 00000048 8b050000 H.....$....H.... + 0140 00004c89 d64c8b4c 24184c8b 44243048 ..L..L.L$.L.D$0H + 0150 8b4c2438 c4e1f96e c0488b44 24504c89 .L$8...n.H.D$PL. + 0160 dfff90f0 05000048 8b050000 0000488b .......H......H. + 0170 004c6390 30050000 4c63982c 05000048 .Lc.0...Lc.,...H + 0180 89442450 44895424 6844895c 24604159 .D$PD.T$hD.\$`AY + 0190 5b488b7c 2410488b 74242048 89f8490f [H.|$.H.t$ H..I. + 01a0 afc24c8d 2cc64889 f8490faf c3488b7c ..L.,.H..I...H.| + 01b0 2428488d 14c74d85 d20f8ede 0000004e $(H...M........N + 01c0 8d3cd500 00000049 8d470848 89442418 .<.....I.G.H.D$. + 01d0 4b8d6c3d 004531e4 41b80100 00006690 K.l=.E1.A.....f. 01e0 4889e9c4 c17b104d 004c29f9 4d85db7e H....{.M.L).M..~ 01f0 7f4c8b8c 24d00000 00488b44 24084d0f .L..$....H.D$.M. 0200 afc84a8d 1cc14a8d 04e04d29 e149c1e1 ..J...J...M).I.. @@ -46,9 +46,9 @@ 0290 ff0f1f80 00000000 4939cb7f c1488b44 ........I9...H.D 02a0 2438488b 7c242849 0fafc348 ff4c2478 $8H.|$(I...H.L$x 02b0 488d04c7 48894424 28488b44 24084a8d H...H.D$(H.D$.J. - 02c0 04d84889 4424080f 8558feff ff8b4424 ..H.D$...X....D$ - 02d0 50ffc848 98488544 24480f84 c3fdffff P..H.H.D$H...... - 02e0 8b442450 d1f84c63 f885c00f 8eb2fdff .D$P..Lc........ + 02c0 04d84889 4424080f 8559feff ff8b4424 ..H.D$...Y....D$ + 02d0 50ffc848 98488544 24480f84 c4fdffff P..H.H.D$H...... + 02e0 8b442450 d1f84c63 f885c00f 8eb3fdff .D$P..Lc........ 02f0 ff4c857c 24480f84 45030000 488b5424 .L.|$H..E...H.T$ 0300 104885d2 7e554883 ec08ffb4 24d80000 .H..~UH.....$... 0310 00488b05 00000000 4c89d64c 8b4c2418 .H......L..L.L$. @@ -72,7 +72,7 @@ 0430 08ebad4c 8bbc24d0 0000008b 7c24588d ...L..$.....|$X. 0440 47ff4898 48854424 700f8421 02000089 G.H.H.D$p..!.... 0450 f8d1f84c 63e085c0 0f8e1202 0000488b ...Lc.........H. - 0460 4424484a 8d2cfd00 00000048 c1f80448 D$HJ.,.....H...H + 0460 4424484a 8d2cfd00 00000048 c1f80248 D$HJ.,.....H...H 0470 89442468 eb0949d1 fc0f84f1 0100004c .D$h..I........L 0480 85642470 74f0488b 05000000 00488b5c .d$pt.H......H.\ 0490 2468488b 008bb02c 05000048 89442458 $hH....,...H.D$X @@ -102,7 +102,7 @@ 0610 08ebad4c 39ff0f8c 0efeffff 488b4424 ...L9.......H.D$ 0620 38488b7c 2428490f afc7488d 04c74889 8H.|$(I...H...H. 0630 44242848 8b442408 4a8d04f8 48894424 D$(H.D$.J...H.D$ - 0640 0849d1ff 0f85a7fc ffffe954 faffff49 .I.........T...I + 0640 0849d1ff 0f85a7fc ffffe955 faffff49 .I.........U...I 0650 8d41014c 03642418 4d01e848 03ac24d0 .A.L.d$.M..H..$. 0660 0000004d 39ca74b4 4989c1e9 36fdffff ...M9.t.I...6... 0670 4881c498 0000005b 5d415c41 5d415e31 H......[]A\A]A^1 /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_COOPERLAKE.o (objdump) @@ -4,10 +4,10 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 94000000 1c000000 ................ - 0020 00000000 bd080000 00420e10 8f02480e .........B....H. + 0020 00000000 bd080000 00420e10 8f02490e .........B....I. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 0040 8606410e 38830747 0ed00103 1c010ed8 ..A.8..G........ - 0050 01470ee0 0102550e d801410e d001037a .G....U...A....z + 0050 01470ee0 0102550e d801410e d0010379 .G....U...A....y 0060 010ed801 470ee001 02480ed8 01420ed0 ....G....H...B.. 0070 0103bc01 0ed80142 0ee00102 480ed801 .......B....H... 0080 410ed001 0315010a 0e38410e 30410e28 A........8A.0A.( /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_SKYLAKEX.o (disasm) @@ -7,7 +7,7 @@ dtrsm_kernel_RN_SKYLAKEX: push %r15 mov %rsi,%rax - sar %rax + sar $something,%rax push %r14 push %r13 push %r12 @@ -108,7 +108,7 @@ lea offset(%r13,%r15,1),%rbp xor %r12d,%r12d mov $something,%r8d - nopl (%rax) + xchg %ax,%ax mov %rbp,%rcx vmovsd offset(%r13),%xmm1 sub %r15,%rcx /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_SKYLAKEX.o (objdump) @@ -2,36 +2,36 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574889 f048d1f8 41564155 41545553 AWH..H..AVAUATUS - 0010 4881ec98 00000048 89742470 488bb424 H......H.t$pH..$ - 0020 d8000000 48897c24 4848f7de 48897424 ....H.|$HH..H.t$ - 0030 10488b35 00000000 48895424 38488b36 .H.5....H.T$8H.6 - 0040 48894c24 60488974 24408bb6 30050000 H.L$`H.t$@..0... - 0050 4c894424 204c894c 24304889 84248000 L.D$ L.L$0H..$.. - 0060 00008974 24584c8b bc24d000 00004885 ...t$XL..$....H. - 0070 c00f8ec4 03000048 c1ff0448 63de4889 .......H...Hc.H. - 0080 7c24684e 8d34fd00 00000049 89daeb57 |$hN.4.....I...W - 0090 8b442450 ffc84898 48854424 480f853d .D$P..H.H.D$H..= - 00a0 02000048 8b442438 488b7c24 20490faf ...H.D$8H.|$ I.. - 00b0 c24c0154 2410488d 04c74889 44242048 .L.T$.H...H.D$ H - 00c0 8b8424d0 00000048 8b7c2430 490fafc2 ..$....H.|$0I... - 00d0 48ff8c24 80000000 488d04c7 48894424 H..$....H...H.D$ - 00e0 300f844c 03000048 8b442440 48837c24 0..L...H.D$@H.|$ - 00f0 68008b80 2c050000 89442450 488b4424 h...,....D$PH.D$ - 0100 30488944 2408488b 44246048 89442428 0H.D$.H.D$`H.D$( - 0110 0f8e7aff ffff488b 4424684c 635c2450 ..z...H.D$hLc\$P - 0120 48894424 78488b54 24104885 d27e6148 H.D$xH.T$.H..~aH - 0130 83ec08ff b424d800 0000488b 05000000 .....$....H..... - 0140 004c89d6 4c8b4c24 184c8b44 2430488b .L..L.L$.L.D$0H. - 0150 4c2438c4 e1f96ec0 488b4424 504c89df L$8...n.H.D$PL.. - 0160 ff90f005 0000488b 05000000 00488b00 ......H......H.. - 0170 4c639030 0500004c 63982c05 00004889 Lc.0...Lc.,...H. - 0180 44245044 89542468 44895c24 6041595b D$PD.T$hD.\$`AY[ - 0190 488b7c24 10488b74 24204889 f8490faf H.|$.H.t$ H..I.. - 01a0 c24c8d2c c64889f8 490fafc3 488b7c24 .L.,.H..I...H.|$ - 01b0 28488d14 c74d85d2 0f8edf00 00004e8d (H...M........N. - 01c0 3cd50000 0000498d 47084889 4424184b <.....I.G.H.D$.K - 01d0 8d6c3d00 4531e441 b8010000 000f1f00 .l=.E1.A........ + 0000 41574889 f048c1f8 03415641 55415455 AWH..H...AVAUATU + 0010 534881ec 98000000 48897424 70488bb4 SH......H.t$pH.. + 0020 24d80000 0048897c 244848f7 de488974 $....H.|$HH..H.t + 0030 2410488b 35000000 00488954 2438488b $.H.5....H.T$8H. + 0040 3648894c 24604889 7424408b b6300500 6H.L$`H.t$@..0.. + 0050 004c8944 24204c89 4c243048 89842480 .L.D$ L.L$0H..$. + 0060 00000089 7424584c 8bbc24d0 00000048 ....t$XL..$....H + 0070 85c00f8e c3030000 48c1ff02 4863de48 ........H...Hc.H + 0080 897c2468 4e8d34fd 00000000 4989daeb .|$hN.4.....I... + 0090 578b4424 50ffc848 98488544 24480f85 W.D$P..H.H.D$H.. + 00a0 3c020000 488b4424 38488b7c 2420490f <...H.D$8H.|$ I. + 00b0 afc24c01 54241048 8d04c748 89442420 ..L.T$.H...H.D$ + 00c0 488b8424 d0000000 488b7c24 30490faf H..$....H.|$0I.. + 00d0 c248ff8c 24800000 00488d04 c7488944 .H..$....H...H.D + 00e0 24300f84 4b030000 488b4424 4048837c $0..K...H.D$@H.| + 00f0 2468008b 802c0500 00894424 50488b44 $h...,....D$PH.D + 0100 24304889 44240848 8b442460 48894424 $0H.D$.H.D$`H.D$ + 0110 280f8e7a ffffff48 8b442468 4c635c24 (..z...H.D$hLc\$ + 0120 50488944 2478488b 54241048 85d27e61 PH.D$xH.T$.H..~a + 0130 4883ec08 ffb424d8 00000048 8b050000 H.....$....H.... + 0140 00004c89 d64c8b4c 24184c8b 44243048 ..L..L.L$.L.D$0H + 0150 8b4c2438 c4e1f96e c0488b44 24504c89 .L$8...n.H.D$PL. + 0160 dfff90f0 05000048 8b050000 0000488b .......H......H. + 0170 004c6390 30050000 4c63982c 05000048 .Lc.0...Lc.,...H + 0180 89442450 44895424 6844895c 24604159 .D$PD.T$hD.\$`AY + 0190 5b488b7c 2410488b 74242048 89f8490f [H.|$.H.t$ H..I. + 01a0 afc24c8d 2cc64889 f8490faf c3488b7c ..L.,.H..I...H.| + 01b0 2428488d 14c74d85 d20f8ede 0000004e $(H...M........N + 01c0 8d3cd500 00000049 8d470848 89442418 .<.....I.G.H.D$. + 01d0 4b8d6c3d 004531e4 41b80100 00006690 K.l=.E1.A.....f. 01e0 4889e9c4 c17b104d 004c29f9 4d85db7e H....{.M.L).M..~ 01f0 7f4c8b8c 24d00000 00488b44 24084d0f .L..$....H.D$.M. 0200 afc84a8d 1cc14a8d 04e04d29 e149c1e1 ..J...J...M).I.. @@ -46,9 +46,9 @@ 0290 ff0f1f80 00000000 4939cb7f c1488b44 ........I9...H.D 02a0 2438488b 7c242849 0fafc348 ff4c2478 $8H.|$(I...H.L$x 02b0 488d04c7 48894424 28488b44 24084a8d H...H.D$(H.D$.J. - 02c0 04d84889 4424080f 8558feff ff8b4424 ..H.D$...X....D$ - 02d0 50ffc848 98488544 24480f84 c3fdffff P..H.H.D$H...... - 02e0 8b442450 d1f84c63 f885c00f 8eb2fdff .D$P..Lc........ + 02c0 04d84889 4424080f 8559feff ff8b4424 ..H.D$...Y....D$ + 02d0 50ffc848 98488544 24480f84 c4fdffff P..H.H.D$H...... + 02e0 8b442450 d1f84c63 f885c00f 8eb3fdff .D$P..Lc........ 02f0 ff4c857c 24480f84 45030000 488b5424 .L.|$H..E...H.T$ 0300 104885d2 7e554883 ec08ffb4 24d80000 .H..~UH.....$... 0310 00488b05 00000000 4c89d64c 8b4c2418 .H......L..L.L$. @@ -72,7 +72,7 @@ 0430 08ebad4c 8bbc24d0 0000008b 7c24588d ...L..$.....|$X. 0440 47ff4898 48854424 700f8421 02000089 G.H.H.D$p..!.... 0450 f8d1f84c 63e085c0 0f8e1202 0000488b ...Lc.........H. - 0460 4424484a 8d2cfd00 00000048 c1f80448 D$HJ.,.....H...H + 0460 4424484a 8d2cfd00 00000048 c1f80248 D$HJ.,.....H...H 0470 89442468 eb0949d1 fc0f84f1 0100004c .D$h..I........L 0480 85642470 74f0488b 05000000 00488b5c .d$pt.H......H.\ 0490 2468488b 008bb02c 05000048 89442458 $hH....,...H.D$X @@ -102,7 +102,7 @@ 0610 08ebad4c 39ff0f8c 0efeffff 488b4424 ...L9.......H.D$ 0620 38488b7c 2428490f afc7488d 04c74889 8H.|$(I...H...H. 0630 44242848 8b442408 4a8d04f8 48894424 D$(H.D$.J...H.D$ - 0640 0849d1ff 0f85a7fc ffffe954 faffff49 .I.........T...I + 0640 0849d1ff 0f85a7fc ffffe955 faffff49 .I.........U...I 0650 8d41014c 03642418 4d01e848 03ac24d0 .A.L.d$.M..H..$. 0660 0000004d 39ca74b4 4989c1e9 36fdffff ...M9.t.I...6... 0670 4881c498 0000005b 5d415c41 5d415e31 H......[]A\A]A^1 /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RN_SKYLAKEX.o (objdump) @@ -4,10 +4,10 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 94000000 1c000000 ................ - 0020 00000000 bd080000 00420e10 8f02480e .........B....H. + 0020 00000000 bd080000 00420e10 8f02490e .........B....I. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 0040 8606410e 38830747 0ed00103 1c010ed8 ..A.8..G........ - 0050 01470ee0 0102550e d801410e d001037a .G....U...A....z + 0050 01470ee0 0102550e d801410e d0010379 .G....U...A....y 0060 010ed801 470ee001 02480ed8 01420ed0 ....G....H...B.. 0070 0103bc01 0ed80142 0ee00102 480ed801 .......B....H... 0080 410ed001 0315010a 0e38410e 30410e28 A........8A.0A.( /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_COOPERLAKE.o (disasm) @@ -341,7 +341,7 @@ jg jmp mov offset(%rsp),%rax - sar %rax + sar $something,%rax mov %rax,offset(%rsp) test %rax,%rax jle @@ -465,7 +465,7 @@ neg %r13 movslq %r11d,%r11 neg %r10 - nopl offset(%rax) + nopw offset(%rax,%rax,1) vmovsd offset(%rbp),%xmm1 test %r15,%r15 jle /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_COOPERLAKE.o (objdump) @@ -11,7 +11,7 @@ 0060 8b004889 5c24208b 90300500 00488944 ..H.\$ ..0...H.D 0070 24188d42 ff489848 85c60f84 ae050000 $..B.H.H........ 0080 83fa010f 8ea50500 00488b84 24200100 .........H..$ .. - 0090 0048c1ff 0448f7d8 488d2cc5 00000000 .H...H..H.,..... + 0090 0048c1ff 0248f7d8 488d2cc5 00000000 .H...H..H.,..... 00a0 4889e848 f7d84889 7c246048 89442470 H..H..H.|$`H.D$p 00b0 41bf0100 0000eb30 8b442458 ffc84898 A......0.D$X..H. 00c0 48854424 680f8507 0300004c 297c2420 H.D$h......L)|$ @@ -101,44 +101,44 @@ 0600 28488b5c 2408490f afc6488d 04c3488b (H.\$.I...H...H. 0610 5c244848 89442408 48015c24 1049d1fe \$HH.D$.H.\$.I.. 0620 4d85f60f 8f65feff ffe99dfa ffff488b M....e........H. - 0630 44247848 d1f84889 84249800 00004885 D$xH..H..$....H. - 0640 c00f8ef8 04000048 8b442468 48c1f804 .......H.D$hH... - 0650 48894424 78488b05 00000000 488b008b H.D$xH......H... - 0660 98300500 00488944 2460488b 84242001 .0...H.D$`H..$ . - 0670 0000895c 245848f7 d84c8d3c c5000000 ...\$XH..L.<.... - 0680 004c89f8 48f7d848 89842480 00000048 .L..H..H..$....H - 0690 63c34889 4424304d 89feeb2b 8b442470 c.H.D$0M...+.D$p - 06a0 ffc84898 48854424 680f85a4 02000048 ..H.H.D$h......H - 06b0 8b5c2430 48295c24 2048ff8c 24980000 .\$0H)\$ H..$... - 06c0 000f8478 04000048 8b5c2430 488b4424 ...x...H.\$0H.D$ - 06d0 28480faf c348c1e0 03482944 2438488b (H...H...H)D$8H. - 06e0 84242001 0000480f afc3488b 5c246048 .$ ...H...H.\$`H - 06f0 c1e00348 29442450 8b9b2c05 00004883 ...H)D$P..,...H. - 0700 7c247800 895c2470 488b4424 50488944 |$x..\$pH.D$PH.D - 0710 2448488b 84248800 00004889 4424400f $HH..$....H.D$@. - 0720 8e77ffff ff488b44 24284c63 fb482b44 .w...H.D$(Lc.H+D - 0730 24204889 8424a000 0000488b 44247848 $ H..$....H.D$xH - 0740 89842490 00000048 8bbc24a0 00000048 ..$....H..$....H - 0750 85ff0f8e 87000000 488b5c24 20488b74 ........H.\$ H.t - 0760 24304889 d8490faf df4883ec 08480faf $0H..I...H...H.. - 0770 c64889da 488b5c24 48ffb424 28010000 .H..H.\$H..$(... - 0780 488d0cd3 4889fa48 8b5c2448 4c8b4c24 H...H..H.\$HL.L$ - 0790 584c8d04 c3488b05 00000000 4c89ffc4 XL...H......L... - 07a0 e1f96ec0 488b4424 70ff90f0 05000048 ..n.H.D$p......H - 07b0 8b050000 0000488b 00486398 30050000 ......H..Hc.0... - 07c0 4c63b82c 05000048 89442470 895c2468 Lc.,...H.D$p.\$h - 07d0 4489bc24 80000000 5e5f4889 5c243048 D..$....^_H.\$0H - 07e0 8b5c2430 488b5424 20488d4b ff4829da .\$0H.T$ H.K.H). - 07f0 488d0411 490fafc7 488b7424 40448b44 H...I...H.t$@D.D - 0800 2458488d 3cc6488d 0411480f afc3488b $XH.<.H...H...H. - 0810 5c24384c 8d0cc341 ffc80f88 ed000000 \$8L...A........ - 0820 8b5c2458 488b4424 304d63d0 48c1e003 .\$XH.D$0Mc.H... - 0830 448d5bfe 4b8d2cd1 48c7c3f8 ffffff4c D.[.K.,.H......L - 0840 0faf9424 80000000 4989c548 29c34c89 ...$....I..H).L. - 0850 fa488b44 244848c1 e2044e8d 241048f7 .H.D$HH...N.$.H. - 0860 da4a8d04 fd000000 00488954 24104889 .J.......H.T$.H. - 0870 5c240848 89442418 49f7dd4d 63db49f7 \$.H.D$.I..Mc.I. - 0880 da0f1f80 00000000 c5fb104d 004d85ff ...........M.M.. + 0630 44247848 c1f80348 89842498 00000048 D$xH...H..$....H + 0640 85c00f8e f7040000 488b4424 6848c1f8 ........H.D$hH.. + 0650 02488944 2478488b 05000000 00488b00 .H.D$xH......H.. + 0660 8b983005 00004889 44246048 8b842420 ..0...H.D$`H..$ + 0670 01000089 5c245848 f7d84c8d 3cc50000 ....\$XH..L.<... + 0680 00004c89 f848f7d8 48898424 80000000 ..L..H..H..$.... + 0690 4863c348 89442430 4d89feeb 2b8b4424 Hc.H.D$0M...+.D$ + 06a0 70ffc848 98488544 24680f85 a3020000 p..H.H.D$h...... + 06b0 488b5c24 3048295c 242048ff 8c249800 H.\$0H)\$ H..$.. + 06c0 00000f84 77040000 488b5c24 30488b44 ....w...H.\$0H.D + 06d0 2428480f afc348c1 e0034829 44243848 $(H...H...H)D$8H + 06e0 8b842420 01000048 0fafc348 8b5c2460 ..$ ...H...H.\$` + 06f0 48c1e003 48294424 508b9b2c 05000048 H...H)D$P..,...H + 0700 837c2478 00895c24 70488b44 24504889 .|$x..\$pH.D$PH. + 0710 44244848 8b842488 00000048 89442440 D$HH..$....H.D$@ + 0720 0f8e77ff ffff488b 4424284c 63fb482b ..w...H.D$(Lc.H+ + 0730 44242048 898424a0 00000048 8b442478 D$ H..$....H.D$x + 0740 48898424 90000000 488bbc24 a0000000 H..$....H..$.... + 0750 4885ff0f 8e870000 00488b5c 2420488b H........H.\$ H. + 0760 74243048 89d8490f afdf4883 ec08480f t$0H..I...H...H. + 0770 afc64889 da488b5c 2448ffb4 24280100 ..H..H.\$H..$(.. + 0780 00488d0c d34889fa 488b5c24 484c8b4c .H...H..H.\$HL.L + 0790 24584c8d 04c3488b 05000000 004c89ff $XL...H......L.. + 07a0 c4e1f96e c0488b44 2470ff90 f0050000 ...n.H.D$p...... + 07b0 488b0500 00000048 8b004863 98300500 H......H..Hc.0.. + 07c0 004c63b8 2c050000 48894424 70895c24 .Lc.,...H.D$p.\$ + 07d0 684489bc 24800000 005e5f48 895c2430 hD..$....^_H.\$0 + 07e0 488b5c24 30488b54 2420488d 4bff4829 H.\$0H.T$ H.K.H) + 07f0 da488d04 11490faf c7488b74 2440448b .H...I...H.t$@D. + 0800 44245848 8d3cc648 8d041148 0fafc348 D$XH.<.H...H...H + 0810 8b5c2438 4c8d0cc3 41ffc80f 88ec0000 .\$8L...A....... + 0820 008b5c24 58488b44 24304d63 d048c1e0 ..\$XH.D$0Mc.H.. + 0830 03448d5b fe4b8d2c d148c7c3 f8ffffff .D.[.K.,.H...... + 0840 4c0faf94 24800000 004989c5 4829c34c L...$....I..H).L + 0850 89fa488b 44244848 c1e2044e 8d241048 ..H.D$HH...N.$.H + 0860 f7da4a8d 04fd0000 00004889 54241048 ..J.......H.T$.H + 0870 895c2408 48894424 1849f7dd 4d63db49 .\$.H.D$.I..Mc.I + 0880 f7da660f 1f440000 c5fb104d 004d85ff ..f..D.....M.M.. 0890 7e584489 d8498d5c c10831d2 4c89e090 ~XD..I.\..1.L... 08a0 c5f35900 498d3402 4c89c9c5 fb1104d7 ..Y.I.4.L....... 08b0 c5fb1100 4585c074 200f1f80 00000000 ....E..t ....... @@ -149,8 +149,8 @@ 0900 4d29f241 83f8ff0f 857bffff ff488b44 M).A.....{...H.D 0910 2428488b 5c244049 0fafc748 ff8c2490 $(H.\$@I...H..$. 0920 00000048 8d04c348 89442440 488b4424 ...H...H.D$@H.D$ - 0930 484a8d04 f8488944 24480f85 07feffff HJ...H.D$H...... - 0940 8b442470 ffc84898 48854424 680f845c .D$p..H.H.D$h..\ + 0930 484a8d04 f8488944 24480f85 08feffff HJ...H.D$H...... + 0940 8b442470 ffc84898 48854424 680f845d .D$p..H.H.D$h..] 0950 fdffff8b 442470d1 f84c63f8 4c857c24 ....D$p..Lc.L.|$ 0960 680f84c7 01000048 8b542428 488b5c24 h......H.T$(H.\$ 0970 204829da 4885d27e 704889d8 490fafdf H).H..~pH..I... @@ -181,6 +181,6 @@ 0b00 4d29f141 83faff75 81488b44 2428488b M).A...u.H.D$(H. 0b10 5c244049 0fafc748 8d04c348 89442440 \$@I...H...H.D$@ 0b20 488b4424 484a8d04 f8488944 244849d1 H.D$HJ...H.D$HI. - 0b30 ff4d85ff 0f8f22fe ffffe970 fbffff48 .M...."....p...H + 0b30 ff4d85ff 0f8f22fe ffffe971 fbffff48 .M...."....q...H 0b40 81c4e800 00005b5d 415c415d 415e31c0 ......[]A\A]A^1. 0b50 415fc3 A_. /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_COOPERLAKE.o (objdump) @@ -9,7 +9,7 @@ 0040 8606410e 3883074a 0ea00203 28020ea8 ..A.8..J....(... 0050 02470eb0 0202500e a802420e a0020320 .G....P...B.... 0060 020ea802 470eb002 7f0ea802 420ea002 ....G.......B... - 0070 036d020e a802530e b0020259 0ea80241 .m....S....Y...A - 0080 0ea00203 af010ea8 024f0eb0 02024b0e .........O....K. + 0070 036e020e a802530e b0020259 0ea80241 .n....S....Y...A + 0080 0ea00203 ae010ea8 024f0eb0 02024b0e .........O....K. 0090 a802410e a0020362 010e3841 0e30410e ..A....b..8A.0A. 00a0 28420e20 420e1842 0e10440e 08000000 (B. B..B..D..... /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_SKYLAKEX.o (disasm) @@ -341,7 +341,7 @@ jg jmp mov offset(%rsp),%rax - sar %rax + sar $something,%rax mov %rax,offset(%rsp) test %rax,%rax jle @@ -465,7 +465,7 @@ neg %r13 movslq %r11d,%r11 neg %r10 - nopl offset(%rax) + nopw offset(%rax,%rax,1) vmovsd offset(%rbp),%xmm1 test %r15,%r15 jle /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_SKYLAKEX.o (objdump) @@ -11,7 +11,7 @@ 0060 8b004889 5c24208b 90300500 00488944 ..H.\$ ..0...H.D 0070 24188d42 ff489848 85c60f84 ae050000 $..B.H.H........ 0080 83fa010f 8ea50500 00488b84 24200100 .........H..$ .. - 0090 0048c1ff 0448f7d8 488d2cc5 00000000 .H...H..H.,..... + 0090 0048c1ff 0248f7d8 488d2cc5 00000000 .H...H..H.,..... 00a0 4889e848 f7d84889 7c246048 89442470 H..H..H.|$`H.D$p 00b0 41bf0100 0000eb30 8b442458 ffc84898 A......0.D$X..H. 00c0 48854424 680f8507 0300004c 297c2420 H.D$h......L)|$ @@ -101,44 +101,44 @@ 0600 28488b5c 2408490f afc6488d 04c3488b (H.\$.I...H...H. 0610 5c244848 89442408 48015c24 1049d1fe \$HH.D$.H.\$.I.. 0620 4d85f60f 8f65feff ffe99dfa ffff488b M....e........H. - 0630 44247848 d1f84889 84249800 00004885 D$xH..H..$....H. - 0640 c00f8ef8 04000048 8b442468 48c1f804 .......H.D$hH... - 0650 48894424 78488b05 00000000 488b008b H.D$xH......H... - 0660 98300500 00488944 2460488b 84242001 .0...H.D$`H..$ . - 0670 0000895c 245848f7 d84c8d3c c5000000 ...\$XH..L.<.... - 0680 004c89f8 48f7d848 89842480 00000048 .L..H..H..$....H - 0690 63c34889 4424304d 89feeb2b 8b442470 c.H.D$0M...+.D$p - 06a0 ffc84898 48854424 680f85a4 02000048 ..H.H.D$h......H - 06b0 8b5c2430 48295c24 2048ff8c 24980000 .\$0H)\$ H..$... - 06c0 000f8478 04000048 8b5c2430 488b4424 ...x...H.\$0H.D$ - 06d0 28480faf c348c1e0 03482944 2438488b (H...H...H)D$8H. - 06e0 84242001 0000480f afc3488b 5c246048 .$ ...H...H.\$`H - 06f0 c1e00348 29442450 8b9b2c05 00004883 ...H)D$P..,...H. - 0700 7c247800 895c2470 488b4424 50488944 |$x..\$pH.D$PH.D - 0710 2448488b 84248800 00004889 4424400f $HH..$....H.D$@. - 0720 8e77ffff ff488b44 24284c63 fb482b44 .w...H.D$(Lc.H+D - 0730 24204889 8424a000 0000488b 44247848 $ H..$....H.D$xH - 0740 89842490 00000048 8bbc24a0 00000048 ..$....H..$....H - 0750 85ff0f8e 87000000 488b5c24 20488b74 ........H.\$ H.t - 0760 24304889 d8490faf df4883ec 08480faf $0H..I...H...H.. - 0770 c64889da 488b5c24 48ffb424 28010000 .H..H.\$H..$(... - 0780 488d0cd3 4889fa48 8b5c2448 4c8b4c24 H...H..H.\$HL.L$ - 0790 584c8d04 c3488b05 00000000 4c89ffc4 XL...H......L... - 07a0 e1f96ec0 488b4424 70ff90f0 05000048 ..n.H.D$p......H - 07b0 8b050000 0000488b 00486398 30050000 ......H..Hc.0... - 07c0 4c63b82c 05000048 89442470 895c2468 Lc.,...H.D$p.\$h - 07d0 4489bc24 80000000 5e5f4889 5c243048 D..$....^_H.\$0H - 07e0 8b5c2430 488b5424 20488d4b ff4829da .\$0H.T$ H.K.H). - 07f0 488d0411 490fafc7 488b7424 40448b44 H...I...H.t$@D.D - 0800 2458488d 3cc6488d 0411480f afc3488b $XH.<.H...H...H. - 0810 5c24384c 8d0cc341 ffc80f88 ed000000 \$8L...A........ - 0820 8b5c2458 488b4424 304d63d0 48c1e003 .\$XH.D$0Mc.H... - 0830 448d5bfe 4b8d2cd1 48c7c3f8 ffffff4c D.[.K.,.H......L - 0840 0faf9424 80000000 4989c548 29c34c89 ...$....I..H).L. - 0850 fa488b44 244848c1 e2044e8d 241048f7 .H.D$HH...N.$.H. - 0860 da4a8d04 fd000000 00488954 24104889 .J.......H.T$.H. - 0870 5c240848 89442418 49f7dd4d 63db49f7 \$.H.D$.I..Mc.I. - 0880 da0f1f80 00000000 c5fb104d 004d85ff ...........M.M.. + 0630 44247848 c1f80348 89842498 00000048 D$xH...H..$....H + 0640 85c00f8e f7040000 488b4424 6848c1f8 ........H.D$hH.. + 0650 02488944 2478488b 05000000 00488b00 .H.D$xH......H.. + 0660 8b983005 00004889 44246048 8b842420 ..0...H.D$`H..$ + 0670 01000089 5c245848 f7d84c8d 3cc50000 ....\$XH..L.<... + 0680 00004c89 f848f7d8 48898424 80000000 ..L..H..H..$.... + 0690 4863c348 89442430 4d89feeb 2b8b4424 Hc.H.D$0M...+.D$ + 06a0 70ffc848 98488544 24680f85 a3020000 p..H.H.D$h...... + 06b0 488b5c24 3048295c 242048ff 8c249800 H.\$0H)\$ H..$.. + 06c0 00000f84 77040000 488b5c24 30488b44 ....w...H.\$0H.D + 06d0 2428480f afc348c1 e0034829 44243848 $(H...H...H)D$8H + 06e0 8b842420 01000048 0fafc348 8b5c2460 ..$ ...H...H.\$` + 06f0 48c1e003 48294424 508b9b2c 05000048 H...H)D$P..,...H + 0700 837c2478 00895c24 70488b44 24504889 .|$x..\$pH.D$PH. + 0710 44244848 8b842488 00000048 89442440 D$HH..$....H.D$@ + 0720 0f8e77ff ffff488b 4424284c 63fb482b ..w...H.D$(Lc.H+ + 0730 44242048 898424a0 00000048 8b442478 D$ H..$....H.D$x + 0740 48898424 90000000 488bbc24 a0000000 H..$....H..$.... + 0750 4885ff0f 8e870000 00488b5c 2420488b H........H.\$ H. + 0760 74243048 89d8490f afdf4883 ec08480f t$0H..I...H...H. + 0770 afc64889 da488b5c 2448ffb4 24280100 ..H..H.\$H..$(.. + 0780 00488d0c d34889fa 488b5c24 484c8b4c .H...H..H.\$HL.L + 0790 24584c8d 04c3488b 05000000 004c89ff $XL...H......L.. + 07a0 c4e1f96e c0488b44 2470ff90 f0050000 ...n.H.D$p...... + 07b0 488b0500 00000048 8b004863 98300500 H......H..Hc.0.. + 07c0 004c63b8 2c050000 48894424 70895c24 .Lc.,...H.D$p.\$ + 07d0 684489bc 24800000 005e5f48 895c2430 hD..$....^_H.\$0 + 07e0 488b5c24 30488b54 2420488d 4bff4829 H.\$0H.T$ H.K.H) + 07f0 da488d04 11490faf c7488b74 2440448b .H...I...H.t$@D. + 0800 44245848 8d3cc648 8d041148 0fafc348 D$XH.<.H...H...H + 0810 8b5c2438 4c8d0cc3 41ffc80f 88ec0000 .\$8L...A....... + 0820 008b5c24 58488b44 24304d63 d048c1e0 ..\$XH.D$0Mc.H.. + 0830 03448d5b fe4b8d2c d148c7c3 f8ffffff .D.[.K.,.H...... + 0840 4c0faf94 24800000 004989c5 4829c34c L...$....I..H).L + 0850 89fa488b 44244848 c1e2044e 8d241048 ..H.D$HH...N.$.H + 0860 f7da4a8d 04fd0000 00004889 54241048 ..J.......H.T$.H + 0870 895c2408 48894424 1849f7dd 4d63db49 .\$.H.D$.I..Mc.I + 0880 f7da660f 1f440000 c5fb104d 004d85ff ..f..D.....M.M.. 0890 7e584489 d8498d5c c10831d2 4c89e090 ~XD..I.\..1.L... 08a0 c5f35900 498d3402 4c89c9c5 fb1104d7 ..Y.I.4.L....... 08b0 c5fb1100 4585c074 200f1f80 00000000 ....E..t ....... @@ -149,8 +149,8 @@ 0900 4d29f241 83f8ff0f 857bffff ff488b44 M).A.....{...H.D 0910 2428488b 5c244049 0fafc748 ff8c2490 $(H.\$@I...H..$. 0920 00000048 8d04c348 89442440 488b4424 ...H...H.D$@H.D$ - 0930 484a8d04 f8488944 24480f85 07feffff HJ...H.D$H...... - 0940 8b442470 ffc84898 48854424 680f845c .D$p..H.H.D$h..\ + 0930 484a8d04 f8488944 24480f85 08feffff HJ...H.D$H...... + 0940 8b442470 ffc84898 48854424 680f845d .D$p..H.H.D$h..] 0950 fdffff8b 442470d1 f84c63f8 4c857c24 ....D$p..Lc.L.|$ 0960 680f84c7 01000048 8b542428 488b5c24 h......H.T$(H.\$ 0970 204829da 4885d27e 704889d8 490fafdf H).H..~pH..I... @@ -181,6 +181,6 @@ 0b00 4d29f141 83faff75 81488b44 2428488b M).A...u.H.D$(H. 0b10 5c244049 0fafc748 8d04c348 89442440 \$@I...H...H.D$@ 0b20 488b4424 484a8d04 f8488944 244849d1 H.D$HJ...H.D$HI. - 0b30 ff4d85ff 0f8f22fe ffffe970 fbffff48 .M...."....p...H + 0b30 ff4d85ff 0f8f22fe ffffe971 fbffff48 .M...."....q...H 0b40 81c4e800 00005b5d 415c415d 415e31c0 ......[]A\A]A^1. 0b50 415fc3 A_. /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_kernel_RT_SKYLAKEX.o (objdump) @@ -9,7 +9,7 @@ 0040 8606410e 3883074a 0ea00203 28020ea8 ..A.8..J....(... 0050 02470eb0 0202500e a802420e a0020320 .G....P...B.... 0060 020ea802 470eb002 7f0ea802 420ea002 ....G.......B... - 0070 036d020e a802530e b0020259 0ea80241 .m....S....Y...A - 0080 0ea00203 af010ea8 024f0eb0 02024b0e .........O....K. + 0070 036e020e a802530e b0020259 0ea80241 .n....S....Y...A + 0080 0ea00203 ae010ea8 024f0eb0 02024b0e .........O....K. 0090 a802410e a0020362 010e3841 0e30410e ..A....b..8A.0A. 00a0 28420e20 420e1842 0e10440e 08000000 (B. B..B..D..... /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_COOPERLAKE.o (disasm) @@ -8,116 +8,861 @@ push %r15 push %r14 push %r13 + mov %r9,%r13 push %r12 - mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle + mov %rcx,%rbx + lea (%rbx,%rbx,2),%rax + lea offset(,%rax,8),%r15 + shl $something,%rax + mov %rsi,%r9 + lea (%rbx,%rbx,4),%rdx + mov %rbx,%rsi + mov %rax,%r10 + mov %rax,offset(%rsp) + imul $something,%rbx,%rax + shl $something,%rbx + mov %rbx,offset(%rsp) mov %rdi,%rbx - sar %rbx - mov %rbx,%r14 - mov %rbx,%rax - mov %rdx,-offset(%rsp) - mov %rcx,%r11 - lea offset(,%rcx,8),%rbp - mov %rdi,%r13 - lea (%r8,%rsi,2),%rsi + and $something,%ebx + mov %rbx,offset(%rsp) + mov %rdi,%rbx + and $something,%ebx + mov %rax,%rbp + mov %rax,offset(%rsp) + mov %rbx,offset(%rsp) + mov %rdi,%rax + mov %rdi,%rbx + sar $something,%rax + and $something,%ebx and $something,%rdi - shl $something,%r14 + mov %rdi,%r14 + mov %rbx,offset(%rsp) + mov %rax,%rdi + lea (%r8,%r9,8),%rbx + shl $something,%rdi + lea offset(,%rcx,8),%r11 + shl $something,%rsi + shl $something,%rcx + mov %rbx,offset(%rsp) + mov %rbp,%rbx + lea offset(,%rdx,8),%r12 + mov %rcx,offset(%rsp) + mov %r15,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rax,offset(%rsp) + add %rdi,%rcx + add %rdi,%r15 + add %rdi,%rsi + add %rdi,%rbx shl $something,%rax - vmovsd offset(%rip),%xmm4 # - mov %r8,-offset(%rsp) - mov %rdi,%r10 - shl $something,%r11 - mov %r8,%rdi - and $something,%r13d - lea offset(%rbp,%r14,1),%r15 - mov %rdx,%rcx - mov %rax,%r12 - mov %rsi,%r8 - lea offset(%rbp,%rcx,1),%rsi + mov %r12,offset(%rsp) + mov offset(%rsp),%rbp + add %rdi,%r12 + mov %rdi,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r15,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + add %rdi,%r10 + mov %r11,offset(%rsp) + mov %r12,offset(%rsp) + add %rdi,%r11 + mov %r8,%r12 + vmovsd offset(%rip),%xmm0 # + mov %r11,offset(%rsp) + mov %r10,offset(%rsp) + mov %rbp,%r8 + mov %r12,%r9 + mov %r14,%r10 + mov %r13,%r11 + nopw offset(%rax,%rax,1) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r8,1),%rcx + mov offset(%rsp),%rax + lea (%rax,%r8,1),%r15 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%r14 + mov offset(%rsp),%rax + lea (%rax,%r8,1),%r13 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%r12 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%rbp + mov offset(%rsp),%rax + lea (%rax,%r8,1),%rbx + jle + mov %r8,%rsi + mov %r11,%rdx + mov %r9,%rax + xor %edi,%edi + mov %r11,%r9 + mov %r8,%r11 + mov %r10,%r8 + jmp + nopl offset(%rax) + jge + vmovsd offset(%rsi),%xmm5 + vmovsd offset(%rsi),%xmm6 + vmovsd offset(%rsi),%xmm7 + vmovsd offset(%rsi),%xmm4 + vmovsd offset(%rsi),%xmm3 + vmovsd offset(%rsi),%xmm2 + vmovsd (%rcx),%xmm1 + vmovsd offset(%rcx),%xmm12 + vmovsd offset(%rcx),%xmm13 + vmovsd offset(%rcx),%xmm14 + vmovsd offset(%rcx),%xmm15 + vmovsd offset(%rcx),%xmm9 + vmovsd offset(%r15),%xmm10 + vmovsd offset(%rsi),%xmm30 + vmovsd offset(%rcx),%xmm29 + vmovsd offset(%rcx),%xmm22 + mov (%r15),%r10 + vmovsd offset(%r15),%xmm28 + vmovsd offset(%r15),%xmm21 + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd %xmm2,-offset(%rsp) + vmovsd %xmm1,-offset(%rsp) + vmovsd %xmm12,-offset(%rsp) + vmovsd %xmm13,-offset(%rsp) + vmovsd %xmm14,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm9,-offset(%rsp) + vmovsd %xmm10,-offset(%rsp) + vmovsd offset(%r15),%xmm8 + vmovsd offset(%r15),%xmm18 + vmovsd offset(%r15),%xmm19 + vmovsd offset(%r15),%xmm20 + vmovsd (%r14),%xmm24 + vmovsd offset(%r14),%xmm25 + vmovsd offset(%r14),%xmm26 + vmovsd offset(%r14),%xmm31 + vmovsd offset(%r14),%xmm16 + vmovsd offset(%r13),%xmm6 + vmovsd offset(%r13),%xmm4 + vmovsd offset(%r13),%xmm3 + vmovsd offset(%r13),%xmm11 + vmovsd offset(%r14),%xmm15 + vmovsd offset(%r13),%xmm14 + vmovsd offset(%r14),%xmm27 + vmovsd offset(%r13),%xmm10 + vmovsd %xmm8,-offset(%rsp) + vmovsd %xmm18,-offset(%rsp) + vmovsd %xmm19,(%rsp) + vmovsd %xmm20,offset(%rsp) + vmovsd offset(%r13),%xmm19 + vmovsd offset(%r14),%xmm20 + vmovsd %xmm24,offset(%rsp) + vmovsd %xmm25,offset(%rsp) + vmovsd %xmm26,offset(%rsp) + vmovsd %xmm31,offset(%rsp) + vmovsd offset(%r13),%xmm26 + vmovsd %xmm16,offset(%rsp) + vmovsd %xmm6,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_COOPERLAKE.o (objdump) @@ -2,33 +2,322 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t - 0010 24d848d1 fe48897c 24f84889 7424e048 $.H..H.|$.H.t$.H - 0020 85f60f8e 39010000 4889fb48 d1fb4989 ....9...H..H..I. - 0030 de4889d8 48895424 e84989cb 488d2ccd .H..H.T$.I..H.,. - 0040 00000000 4989fd49 8d347048 83e7fe49 ....I..I.4pH...I - 0050 c1e60448 c1e005c5 fb102500 0000004c ...H......%....L - 0060 894424f0 4989fa49 c1e3044c 89c74183 .D$.I..I...L..A. - 0070 e5014e8d 7c350048 89d14989 c44989f0 ..N.|5.H..I..I.. - 0080 488d740d 004885db 0f8e4201 00004c89 H.t..H....B...L. - 0090 ca31c0eb 3b0f1f00 7e29c5fb 101cc1c5 .1..;...~)...... - 00a0 fb104cc1 08c5fb10 14c6c5fb 1044c608 ..L..........D.. - 00b0 c5fb111a c5fb1152 08c5fb11 4a10c5fb .......R....J... - 00c0 11421848 83c00248 83c22049 39c27435 .B.H...H.. I9.t5 - 00d0 4839f875 c3c5fb10 44c608c5 fb104cc1 H9.u....D.....L. - 00e0 08c5db5e c0c5db5e 14c14883 c002c5fb ...^...^..H..... - 00f0 1112c5fb 114a1048 83c220c5 fb1142f8 .....J.H.. ...B. - 0100 4939c275 cb4a8d14 314a8d34 394d01e1 I9.u.J..1J.49M.. - 0110 4d85ed74 224839f8 0f84a200 00007e13 M..t"H9.......~. - 0120 c5fb100a c5fb1006 c4c17b11 09c4c17b ..........{....{ - 0130 11410849 83c11048 83c7024c 01d94c39 .A.I...H...L..L9 - 0140 c70f8539 ffffff48 8b4424e0 4c8b6424 ...9...H.D$.L.d$ - 0150 e84c0faf d84c8b44 24f04d01 dc4d8d04 .L...L.D$.M..M.. - 0160 40f64424 d8017447 488b5424 f84885d2 @.D$..tGH.T$.H.. - 0170 7e3dc5fb 100d0000 000031c0 eb186690 ~=........1...f. - 0180 7d0cc4c1 7b1004c4 c4c17b11 04c148ff }...{.....{...H. - 0190 c04839c2 74194939 c075e548 ffc0c481 .H9.t.I9.u.H.... - 01a0 735e04c4 c4817b11 04c14839 c275e75b s^....{...H9.u.[ - 01b0 5d415c41 5d415e31 c0415fc3 0f1f4000 ]A\A]A^1.A_...@. - 01c0 c5db5e02 c4c17b11 01e965ff ffff6690 ..^...{...e...f. - 01d0 4889ca31 c0e936ff ffff H..1..6... + 0000 41574156 41554d89 cd415455 534881ec AWAVAUM..ATUSH.. + 0010 68010000 4889b424 48010000 48c1fe03 h...H..$H...H... + 0020 4889bc24 50010000 48899424 38010000 H..$P...H..$8... + 0030 48898c24 60010000 4c898424 40010000 H..$`...L..$@... + 0040 4889b424 58010000 4885f60f 8e8e0d00 H..$X...H....... + 0050 004889cb 488d045b 4c8d3cc5 00000000 .H..H..[L.<..... + 0060 48c1e004 4989f148 8d149b48 89de4989 H...I..H...H..I. + 0070 c2488984 24e80000 00486bc3 3848c1e3 .H..$....Hk.8H.. + 0080 0648899c 24880000 004889fb 83e30448 .H..$....H.....H + 0090 899c24c0 00000048 89fb83e3 024889c5 ..$....H.....H.. + 00a0 48898424 a8000000 48899c24 c8000000 H..$....H..$.... + 00b0 4889f848 89fb48c1 f80383e3 014883e7 H..H..H......H.. + 00c0 f84989fe 48899c24 d0000000 4889c74b .I..H..$....H..K + 00d0 8d1cc848 c1e7064c 8d1ccd00 00000048 ...H...L.......H + 00e0 c1e60548 c1e10448 899c24b8 00000048 ...H...H..$....H + 00f0 89eb4c8d 24d50000 00004889 8c249800 ..L.$.....H..$.. + 0100 00004c89 bc24d800 00004889 b424a000 ..L..$....H..$.. + 0110 00004889 8424b000 00004801 f94901ff ..H..$....H..I.. + 0120 4801fe48 01fb48c1 e0094c89 a424e000 H..H..H...L..$.. + 0130 0000488b ac243801 00004901 fc4889bc ..H..$8...I..H.. + 0140 24f80000 0048898c 24080100 004c89bc $....H..$....L.. + 0150 24100100 004889b4 24180100 0048899c $....H..$....H.. + 0160 24000100 00488984 24f00000 004901fa $....H..$....I.. + 0170 4c899c24 90000000 4c89a424 28010000 L..$....L..$(... + 0180 4901fb4d 89c4c5fb 10050000 00004c89 I..M..........L. + 0190 9c243001 00004c89 94242001 00004989 .$0...L..$ ...I. + 01a0 e84d89e1 4d89f24d 89eb660f 1f440000 .M..M..M..f..D.. + 01b0 488b8424 90000000 4883bc24 b0000000 H..$....H..$.... + 01c0 004a8d0c 00488b84 24980000 004e8d3c .J...H..$....N.< + 01d0 00488b84 24d80000 004d8d34 00488b84 .H..$....M.4.H.. + 01e0 24a00000 004e8d2c 00488b84 24e00000 $....N.,.H..$... + 01f0 004d8d24 00488b84 24e80000 00498d2c .M.$.H..$....I., + 0200 00488b84 24a80000 004a8d1c 000f8e45 .H..$....J.....E + 0210 1100004c 89c64c89 da4c89c8 31ff4d89 ...L..L..L..1.M. + 0220 d94d89c3 4d89d0e9 3c050000 0f1f4000 .M..M...<.....@. + 0230 0f8dfe04 0000c5fb 106e10c5 fb107618 .........n....v. + 0240 c5fb107e 20c5fb10 6628c5fb 105e30c5 ...~ ...f(...^0. + 0250 fb105638 c5fb1009 c57b1061 18c57b10 ..V8.....{.a..{. + 0260 6920c57b 107128c5 7b107930 c57b1049 i .{.q(.{.y0.{.I + 0270 38c4417b 10571862 61ff0810 76016261 8.A{.W.ba...v.ba + 0280 ff081069 0162e1ff 08107102 4d8b1762 ...i.b....q.M..b + 0290 41ff0810 670162c1 ff08106f 02c5fb11 A...g.b....o.... + 02a0 6c2488c5 fb117424 90c5fb11 7c2498c5 l$....t$....|$.. + 02b0 fb116424 a0c5fb11 5c24a8c5 fb115424 ..d$....\$....T$ + 02c0 b0c5fb11 4c24b8c5 7b116424 c0c57b11 ....L$..{.d$..{. + 02d0 6c24c8c5 7b117424 d0c57b11 7c24d8c5 l$..{.t$..{.|$.. + 02e0 7b114c24 e0c57b11 5424e8c4 417b1047 {.L$..{.T$..A{.G + 02f0 2062c1ff 08105705 62c1ff08 105f0662 b....W.b...._.b + 0300 c1ff0810 67076241 ff081006 6241ff08 ....g.bA....bA.. + 0310 104e0462 41ff0810 56056241 ff08107e .N.bA...V.bA...~ + 0320 0662c1ff 08104607 c4c17b10 7500c4c1 .b....F...{.u... + 0330 7b106528 c4c17b10 5d30c441 7b105d38 {.e(..{.]0.A{.]8 + 0340 c4417b10 7e18c441 7b107518 6241ff08 .A{.~..A{.u.bA.. + 0350 105e01c4 417b1055 20c57b11 4424f062 .^..A{.U .{.D$.b + 0360 e1ff0811 5424ff62 e1ff0811 1c2462e1 ....T$.b.....$b. + 0370 ff081164 240162c1 ff08105d 0262c1ff ...d$.b....].b.. + 0380 08106602 6261ff08 11442402 6261ff08 ..f.ba...D$.ba.. + 0390 114c2403 6261ff08 11542404 6261ff08 .L$.ba...T$.ba.. + 03a0 117c2405 6241ff08 10550162 e1ff0811 .|$.bA...U.b.... + 03b0 442406c5 fb117424 38c5fb11 642440c5 D$....t$8...d$@. + 03c0 fb115c24 48c57b11 5c2450c5 fb104b38 ..\$H.{.\$P...K8 + 03d0 c4417b10 2424c441 7b104424 3062c1ff .A{.$$.A{.D$0b.. + 03e0 08104c24 0762e1ff 08107d00 c5fb1065 ..L$.b....}....e + 03f0 38c5fb11 8c248000 0000c5fb 100e6241 8....$........bA + 0400 ff08104c 240162c1 ff081054 2402c441 ...L$.b....T$..A + 0410 7b106c24 18c4417b 104c2420 c4c17b10 {.l$..A{.L$ ..{. + 0420 742428c5 fb106d28 6261ff08 103b62e1 t$(...m(ba...;b. + 0430 ff081043 02c57b10 5b18c5fb 107b20c5 ...C..{.[....{ . + 0440 fb105330 6261ff08 104501c5 fb105d30 ..S0ba...E....]0 + 0450 c57b1164 2458c57b 11442460 c57b1065 .{.d$X.{.D$`.{.e + 0460 18c57b10 452062e1 ff08114c 240d62e1 ..{.E b....L$.b. + 0470 ff08117c 240e62e1 ff08104d 0262e1ff ...|$.b....M.b.. + 0480 08107b01 c5fb1164 2478c5fb 106328c5 ..{....d$x...c(. + 0490 fb110ac5 fb104c24 b862e1ff 08117a0f ......L$.b....z. + 04a0 c5fb114a 08c5fb10 4c241062 e1ff0810 ...J....L$.b.... + 04b0 7c24f1c5 fb114a18 c5fb104c 243862e1 |$....J....L$8b. + 04c0 ff08114a 16c5fb11 4a20c5fb 104c2458 ...J....J ...L$X + 04d0 62e1ff08 104c24f2 c5fb114a 28c5fb10 b....L$....J(... + 04e0 4c247062 61ff0811 7a07c5fb 114a30c5 L$pba...z....J0. + 04f0 fb104c24 c06261ff 0811520c 6261ff08 ..L$.ba...R.ba.. + 0500 114a0d62 e1ff0811 621362e1 ff08115a .J.b....b.b....Z + 0510 1462e1ff 08115215 62e1ff08 11421762 .b....R.b....B.b + 0520 e1ff0811 4a184c89 52106261 ff081172 ....J.L.R.ba...r + 0530 086261ff 08116a09 6261ff08 11620a62 .ba...j.ba...b.b + 0540 61ff0811 5a0b6261 ff081142 0e62e1ff a...Z.ba...B.b.. + 0550 08117a10 62e1ff08 11721162 e1ff0811 ..z.b....r.b.... + 0560 6a12c5fb 118ac800 0000c5fb 104c24e8 j............L$. + 0570 c5fb11ba 38010000 c5fb107c 24a06261 ....8......|$.ba + 0580 ff08104c 240362e1 ff081054 24ff6261 ...L$.b....T$.ba + 0590 ff081054 2404c5fb 118ad000 0000c57b ...T$..........{ + 05a0 11b2e000 0000c5fb 104c24f0 c57b1074 .........L$..{.t + 05b0 24d0c57b 11aae800 0000c57b 119af800 $..{.......{.... + 05c0 0000c57b 106c24c8 c57b105c 2498c5fb ...{.l$..{.\$... + 05d0 11ba4001 0000c5fb 107c2440 c57b11ba ..@......|$@.{.. + 05e0 d8000000 c57b119a 00010000 c57b118a .....{.......{.. + 05f0 28010000 c57b1182 30010000 c5fb11b2 (....{..0....... + 0600 68010000 c5fb11a2 78010000 c57b11a2 h.......x....{.. + 0610 f0000000 c57b11aa 08010000 c5fb118a .....{.......... + 0620 10010000 6261ff08 114a23c5 7b119220 ....ba...J#.{.. + 0630 010000c5 7b11b248 01000062 e1ff0811 ....{..H...b.... + 0640 522a6261 ff081152 2bc5fb11 ba600100 R*ba...R+....`.. + 0650 00c5fb11 aa700100 00c5fb10 6c24a8c5 .....p......l$.. + 0660 7b107c24 d862e1ff 08101c24 6261ff08 {.|$.b.....$ba.. + 0670 107c2405 c57b1044 2460c57b 104c24e0 .|$..{.D$`.{.L$. + 0680 62e1ff08 10642401 62e1ff08 10442406 b....d$.b....D$. + 0690 c57b105c 245062e1 ff08104c 240dc5fb .{.\$Pb....L$... + 06a0 10642478 c5fb10b4 24800000 00c5fb11 .d$x....$....... + 06b0 aa800100 00c5fb11 92b80100 00c5fb10 ................ + 06c0 6c2448c5 fb105424 b0c57b11 ba880100 l$H...T$..{..... + 06d0 0062e1ff 08115a32 6261ff08 117a33c5 .b....Z2ba...z3. + 06e0 fb11aaa0 010000c5 7b1182a8 010000c5 ........{....... + 06f0 fb119ab0 010000c5 fb1192c0 010000c5 ................ + 0700 7b118ac8 01000062 e1ff0811 623a62e1 {......b....b:b. + 0710 ff081142 3bc57b11 9ae00100 0062e1ff ...B;.{......b.. + 0720 08114a3d c5fb11a2 f0010000 c5fb11b2 ..J=............ + 0730 f8010000 4883c708 4883c640 4883c140 ....H...H..@H..@ + 0740 4983c740 4983c640 4983c540 4983c440 I..@I..@I..@I..@ + 0750 4883c540 4883c340 4881c200 0200004c H..@H..@H......L + 0760 39c70f84 40020000 4839f80f 85bffaff 9...@...H9...... + 0770 ffc5fb10 7e18c4c1 7b107710 c5fb117c ....~...{.w....| + 0780 2488c5fb 107908c4 c17b106e 18c5fb5e $....y...{.n...^ + 0790 ffc4417b 105520c4 417b107c 2428c5fb ..A{.U .A{.|$(.. + 07a0 106608c5 fb105e10 c5fb1051 106261ff .f....^....Q.ba. + 07b0 08106e04 6261ff08 104e0562 e1ff0810 ..n.ba...N.b.... + 07c0 6606c57b 10763862 61ff0810 79036261 f..{.v8ba...y.ba + 07d0 ff081061 046261ff 08104105 62e1ff08 ...a.ba...A.b... + 07e0 105906c5 7b106938 6241ff08 10770362 .Y..{.i8bA...w.b + 07f0 41ff0810 5f0462c1 ff08107f 0562c1ff A..._.b......b.. + 0800 08105706 c4417b10 6738c5fb 5ef66241 ..W..A{.g8..^.bA + 0810 ff081056 0462c1ff 08107605 62c1ff08 ...V.b....v.b... + 0820 104e06c4 417b105e 3862c1ff 08106d05 .N..A{.^8b....m. + 0830 62c1ff08 104506c5 7b115424 90c4417b b....E..{.T$..A{ + 0840 105538c5 7b117c24 98c57b10 4530c5fb .U8.{.|$..{.E0.. + 0850 104b38c4 417b107c 2430c441 7b104c24 .K8.A{.|$0.A{.L$ + 0860 38c57b11 4424a0c5 fb114c24 a8c57b10 8.{.D$....L$..{. + 0870 4538c5fb 5e0ec5fb 117a48c5 fb107c24 E8..^....zH...|$ + 0880 88c5fb5e edc5fb11 0ac5fb11 6240c5fb ...^........b@.. + 0890 119a8000 0000c5fb 11928800 0000c5fb ................ + 08a0 5e642490 c5fb5e5c 2498c5fb 11bac000 ^d$...^\$....... + 08b0 0000c5fb 11b29000 00006261 ff08117a ..........ba...z + 08c0 196261ff 0811721a 6261ff08 116a2062 .ba...r.ba...j b + 08d0 61ff0811 62216261 ff08115a 226261ff a...b!ba...Z"ba. + 08e0 08115223 c5fb11a2 20010000 6261ff08 ..R#.... ...ba.. + 08f0 114a2862 61ff0811 422962e1 ff08117a .J(ba...B)b....z + 0900 2a62e1ff 0811722b 62e1ff08 116a2cc5 *b....r+b....j,. + 0910 fb119a68 010000c5 fb11aad8 00000062 ...h...........b + 0920 e1ff0811 6230c5fb 5e5424a0 c5fb5e4c ....b0..^T$...^L + 0930 24a862e1 ff08115a 3162e1ff 08115232 $.b....Z1b....R2 + 0940 62e1ff08 114a3362 e1ff0811 4234c57b b....J3b....B4.{ + 0950 11baa801 0000c5fb 1192b001 0000c57b ...............{ + 0960 11b2c001 0000c57b 11aac801 0000c57b .......{.......{ + 0970 11a2d001 0000c57b 119ad801 0000c57b .......{.......{ + 0980 1192e001 0000c57b 118ae801 0000c57b .......{.......{ + 0990 1182f001 0000c5fb 118af801 0000e991 ................ + 09a0 fdffff0f 1f440000 488bbc24 30010000 .....D..H..$0... + 09b0 4d89c24d 89d8498d 0c38488b bc240801 M..M..I..8H..$.. + 09c0 00004d89 cb4d8d3c 38488bbc 24100100 ..M..M.<8H..$... + 09d0 004989c1 4d8d3438 488bbc24 18010000 .I..M.48H..$.... + 09e0 488b8424 f8000000 4d8d2c38 488bbc24 H..$....M.,8H..$ + 09f0 28010000 4c01c04d 8d243848 8bbc2420 (...L..M.$8H..$ + 0a00 0100004c 039c24f0 00000049 8d2c3848 ...L..$....I.,8H + 0a10 8bbc2400 0100004c 89d2498d 1c384883 ..$....L..I..8H. + 0a20 bc24c000 0000000f 84f90100 004939d1 .$...........I9. + 0a30 0f84aa05 00000f8d bf010000 488b7b18 ............H.{. /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 da010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 a3010a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 ee130000 00420e10 8f02420e .........B....B. + 0030 188e0342 0e208d04 450e288c 05410e30 ...B. ..E.(..A.0 + 0040 8606410e 38830747 0ea00303 32130a0e ..A.8..G....2... + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_SKYLAKEX.o (disasm) @@ -8,116 +8,861 @@ push %r15 push %r14 push %r13 + mov %r9,%r13 push %r12 - mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle + mov %rcx,%rbx + lea (%rbx,%rbx,2),%rax + lea offset(,%rax,8),%r15 + shl $something,%rax + mov %rsi,%r9 + lea (%rbx,%rbx,4),%rdx + mov %rbx,%rsi + mov %rax,%r10 + mov %rax,offset(%rsp) + imul $something,%rbx,%rax + shl $something,%rbx + mov %rbx,offset(%rsp) mov %rdi,%rbx - sar %rbx - mov %rbx,%r14 - mov %rbx,%rax - mov %rdx,-offset(%rsp) - mov %rcx,%r11 - lea offset(,%rcx,8),%rbp - mov %rdi,%r13 - lea (%r8,%rsi,2),%rsi + and $something,%ebx + mov %rbx,offset(%rsp) + mov %rdi,%rbx + and $something,%ebx + mov %rax,%rbp + mov %rax,offset(%rsp) + mov %rbx,offset(%rsp) + mov %rdi,%rax + mov %rdi,%rbx + sar $something,%rax + and $something,%ebx and $something,%rdi - shl $something,%r14 + mov %rdi,%r14 + mov %rbx,offset(%rsp) + mov %rax,%rdi + lea (%r8,%r9,8),%rbx + shl $something,%rdi + lea offset(,%rcx,8),%r11 + shl $something,%rsi + shl $something,%rcx + mov %rbx,offset(%rsp) + mov %rbp,%rbx + lea offset(,%rdx,8),%r12 + mov %rcx,offset(%rsp) + mov %r15,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rax,offset(%rsp) + add %rdi,%rcx + add %rdi,%r15 + add %rdi,%rsi + add %rdi,%rbx shl $something,%rax - vmovsd offset(%rip),%xmm4 # - mov %r8,-offset(%rsp) - mov %rdi,%r10 - shl $something,%r11 - mov %r8,%rdi - and $something,%r13d - lea offset(%rbp,%r14,1),%r15 - mov %rdx,%rcx - mov %rax,%r12 - mov %rsi,%r8 - lea offset(%rbp,%rcx,1),%rsi + mov %r12,offset(%rsp) + mov offset(%rsp),%rbp + add %rdi,%r12 + mov %rdi,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r15,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + add %rdi,%r10 + mov %r11,offset(%rsp) + mov %r12,offset(%rsp) + add %rdi,%r11 + mov %r8,%r12 + vmovsd offset(%rip),%xmm0 # + mov %r11,offset(%rsp) + mov %r10,offset(%rsp) + mov %rbp,%r8 + mov %r12,%r9 + mov %r14,%r10 + mov %r13,%r11 + nopw offset(%rax,%rax,1) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r8,1),%rcx + mov offset(%rsp),%rax + lea (%rax,%r8,1),%r15 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%r14 + mov offset(%rsp),%rax + lea (%rax,%r8,1),%r13 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%r12 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%rbp + mov offset(%rsp),%rax + lea (%rax,%r8,1),%rbx + jle + mov %r8,%rsi + mov %r11,%rdx + mov %r9,%rax + xor %edi,%edi + mov %r11,%r9 + mov %r8,%r11 + mov %r10,%r8 + jmp + nopl offset(%rax) + jge + vmovsd offset(%rsi),%xmm5 + vmovsd offset(%rsi),%xmm6 + vmovsd offset(%rsi),%xmm7 + vmovsd offset(%rsi),%xmm4 + vmovsd offset(%rsi),%xmm3 + vmovsd offset(%rsi),%xmm2 + vmovsd (%rcx),%xmm1 + vmovsd offset(%rcx),%xmm12 + vmovsd offset(%rcx),%xmm13 + vmovsd offset(%rcx),%xmm14 + vmovsd offset(%rcx),%xmm15 + vmovsd offset(%rcx),%xmm9 + vmovsd offset(%r15),%xmm10 + vmovsd offset(%rsi),%xmm30 + vmovsd offset(%rcx),%xmm29 + vmovsd offset(%rcx),%xmm22 + mov (%r15),%r10 + vmovsd offset(%r15),%xmm28 + vmovsd offset(%r15),%xmm21 + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd %xmm2,-offset(%rsp) + vmovsd %xmm1,-offset(%rsp) + vmovsd %xmm12,-offset(%rsp) + vmovsd %xmm13,-offset(%rsp) + vmovsd %xmm14,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm9,-offset(%rsp) + vmovsd %xmm10,-offset(%rsp) + vmovsd offset(%r15),%xmm8 + vmovsd offset(%r15),%xmm18 + vmovsd offset(%r15),%xmm19 + vmovsd offset(%r15),%xmm20 + vmovsd (%r14),%xmm24 + vmovsd offset(%r14),%xmm25 + vmovsd offset(%r14),%xmm26 + vmovsd offset(%r14),%xmm31 + vmovsd offset(%r14),%xmm16 + vmovsd offset(%r13),%xmm6 + vmovsd offset(%r13),%xmm4 + vmovsd offset(%r13),%xmm3 + vmovsd offset(%r13),%xmm11 + vmovsd offset(%r14),%xmm15 + vmovsd offset(%r13),%xmm14 + vmovsd offset(%r14),%xmm27 + vmovsd offset(%r13),%xmm10 + vmovsd %xmm8,-offset(%rsp) + vmovsd %xmm18,-offset(%rsp) + vmovsd %xmm19,(%rsp) + vmovsd %xmm20,offset(%rsp) + vmovsd offset(%r13),%xmm19 + vmovsd offset(%r14),%xmm20 + vmovsd %xmm24,offset(%rsp) + vmovsd %xmm25,offset(%rsp) + vmovsd %xmm26,offset(%rsp) + vmovsd %xmm31,offset(%rsp) + vmovsd offset(%r13),%xmm26 + vmovsd %xmm16,offset(%rsp) + vmovsd %xmm6,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_SKYLAKEX.o (objdump) @@ -2,33 +2,322 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t - 0010 24d848d1 fe48897c 24f84889 7424e048 $.H..H.|$.H.t$.H - 0020 85f60f8e 39010000 4889fb48 d1fb4989 ....9...H..H..I. - 0030 de4889d8 48895424 e84989cb 488d2ccd .H..H.T$.I..H.,. - 0040 00000000 4989fd49 8d347048 83e7fe49 ....I..I.4pH...I - 0050 c1e60448 c1e005c5 fb102500 0000004c ...H......%....L - 0060 894424f0 4989fa49 c1e3044c 89c74183 .D$.I..I...L..A. - 0070 e5014e8d 7c350048 89d14989 c44989f0 ..N.|5.H..I..I.. - 0080 488d740d 004885db 0f8e4201 00004c89 H.t..H....B...L. - 0090 ca31c0eb 3b0f1f00 7e29c5fb 101cc1c5 .1..;...~)...... - 00a0 fb104cc1 08c5fb10 14c6c5fb 1044c608 ..L..........D.. - 00b0 c5fb111a c5fb1152 08c5fb11 4a10c5fb .......R....J... - 00c0 11421848 83c00248 83c22049 39c27435 .B.H...H.. I9.t5 - 00d0 4839f875 c3c5fb10 44c608c5 fb104cc1 H9.u....D.....L. - 00e0 08c5db5e c0c5db5e 14c14883 c002c5fb ...^...^..H..... - 00f0 1112c5fb 114a1048 83c220c5 fb1142f8 .....J.H.. ...B. - 0100 4939c275 cb4a8d14 314a8d34 394d01e1 I9.u.J..1J.49M.. - 0110 4d85ed74 224839f8 0f84a200 00007e13 M..t"H9.......~. - 0120 c5fb100a c5fb1006 c4c17b11 09c4c17b ..........{....{ - 0130 11410849 83c11048 83c7024c 01d94c39 .A.I...H...L..L9 - 0140 c70f8539 ffffff48 8b4424e0 4c8b6424 ...9...H.D$.L.d$ - 0150 e84c0faf d84c8b44 24f04d01 dc4d8d04 .L...L.D$.M..M.. - 0160 40f64424 d8017447 488b5424 f84885d2 @.D$..tGH.T$.H.. - 0170 7e3dc5fb 100d0000 000031c0 eb186690 ~=........1...f. - 0180 7d0cc4c1 7b1004c4 c4c17b11 04c148ff }...{.....{...H. - 0190 c04839c2 74194939 c075e548 ffc0c481 .H9.t.I9.u.H.... - 01a0 735e04c4 c4817b11 04c14839 c275e75b s^....{...H9.u.[ - 01b0 5d415c41 5d415e31 c0415fc3 0f1f4000 ]A\A]A^1.A_...@. - 01c0 c5db5e02 c4c17b11 01e965ff ffff6690 ..^...{...e...f. - 01d0 4889ca31 c0e936ff ffff H..1..6... + 0000 41574156 41554d89 cd415455 534881ec AWAVAUM..ATUSH.. + 0010 68010000 4889b424 48010000 48c1fe03 h...H..$H...H... + 0020 4889bc24 50010000 48899424 38010000 H..$P...H..$8... + 0030 48898c24 60010000 4c898424 40010000 H..$`...L..$@... + 0040 4889b424 58010000 4885f60f 8e8e0d00 H..$X...H....... + 0050 004889cb 488d045b 4c8d3cc5 00000000 .H..H..[L.<..... + 0060 48c1e004 4989f148 8d149b48 89de4989 H...I..H...H..I. + 0070 c2488984 24e80000 00486bc3 3848c1e3 .H..$....Hk.8H.. + 0080 0648899c 24880000 004889fb 83e30448 .H..$....H.....H + 0090 899c24c0 00000048 89fb83e3 024889c5 ..$....H.....H.. + 00a0 48898424 a8000000 48899c24 c8000000 H..$....H..$.... + 00b0 4889f848 89fb48c1 f80383e3 014883e7 H..H..H......H.. + 00c0 f84989fe 48899c24 d0000000 4889c74b .I..H..$....H..K + 00d0 8d1cc848 c1e7064c 8d1ccd00 00000048 ...H...L.......H + 00e0 c1e60548 c1e10448 899c24b8 00000048 ...H...H..$....H + 00f0 89eb4c8d 24d50000 00004889 8c249800 ..L.$.....H..$.. + 0100 00004c89 bc24d800 00004889 b424a000 ..L..$....H..$.. + 0110 00004889 8424b000 00004801 f94901ff ..H..$....H..I.. + 0120 4801fe48 01fb48c1 e0094c89 a424e000 H..H..H...L..$.. + 0130 0000488b ac243801 00004901 fc4889bc ..H..$8...I..H.. + 0140 24f80000 0048898c 24080100 004c89bc $....H..$....L.. + 0150 24100100 004889b4 24180100 0048899c $....H..$....H.. + 0160 24000100 00488984 24f00000 004901fa $....H..$....I.. + 0170 4c899c24 90000000 4c89a424 28010000 L..$....L..$(... + 0180 4901fb4d 89c4c5fb 10050000 00004c89 I..M..........L. + 0190 9c243001 00004c89 94242001 00004989 .$0...L..$ ...I. + 01a0 e84d89e1 4d89f24d 89eb660f 1f440000 .M..M..M..f..D.. + 01b0 488b8424 90000000 4883bc24 b0000000 H..$....H..$.... + 01c0 004a8d0c 00488b84 24980000 004e8d3c .J...H..$....N.< + 01d0 00488b84 24d80000 004d8d34 00488b84 .H..$....M.4.H.. + 01e0 24a00000 004e8d2c 00488b84 24e00000 $....N.,.H..$... + 01f0 004d8d24 00488b84 24e80000 00498d2c .M.$.H..$....I., + 0200 00488b84 24a80000 004a8d1c 000f8e45 .H..$....J.....E + 0210 1100004c 89c64c89 da4c89c8 31ff4d89 ...L..L..L..1.M. + 0220 d94d89c3 4d89d0e9 3c050000 0f1f4000 .M..M...<.....@. + 0230 0f8dfe04 0000c5fb 106e10c5 fb107618 .........n....v. + 0240 c5fb107e 20c5fb10 6628c5fb 105e30c5 ...~ ...f(...^0. + 0250 fb105638 c5fb1009 c57b1061 18c57b10 ..V8.....{.a..{. + 0260 6920c57b 107128c5 7b107930 c57b1049 i .{.q(.{.y0.{.I + 0270 38c4417b 10571862 61ff0810 76016261 8.A{.W.ba...v.ba + 0280 ff081069 0162e1ff 08107102 4d8b1762 ...i.b....q.M..b + 0290 41ff0810 670162c1 ff08106f 02c5fb11 A...g.b....o.... + 02a0 6c2488c5 fb117424 90c5fb11 7c2498c5 l$....t$....|$.. + 02b0 fb116424 a0c5fb11 5c24a8c5 fb115424 ..d$....\$....T$ + 02c0 b0c5fb11 4c24b8c5 7b116424 c0c57b11 ....L$..{.d$..{. + 02d0 6c24c8c5 7b117424 d0c57b11 7c24d8c5 l$..{.t$..{.|$.. + 02e0 7b114c24 e0c57b11 5424e8c4 417b1047 {.L$..{.T$..A{.G + 02f0 2062c1ff 08105705 62c1ff08 105f0662 b....W.b...._.b + 0300 c1ff0810 67076241 ff081006 6241ff08 ....g.bA....bA.. + 0310 104e0462 41ff0810 56056241 ff08107e .N.bA...V.bA...~ + 0320 0662c1ff 08104607 c4c17b10 7500c4c1 .b....F...{.u... + 0330 7b106528 c4c17b10 5d30c441 7b105d38 {.e(..{.]0.A{.]8 + 0340 c4417b10 7e18c441 7b107518 6241ff08 .A{.~..A{.u.bA.. + 0350 105e01c4 417b1055 20c57b11 4424f062 .^..A{.U .{.D$.b + 0360 e1ff0811 5424ff62 e1ff0811 1c2462e1 ....T$.b.....$b. + 0370 ff081164 240162c1 ff08105d 0262c1ff ...d$.b....].b.. + 0380 08106602 6261ff08 11442402 6261ff08 ..f.ba...D$.ba.. + 0390 114c2403 6261ff08 11542404 6261ff08 .L$.ba...T$.ba.. + 03a0 117c2405 6241ff08 10550162 e1ff0811 .|$.bA...U.b.... + 03b0 442406c5 fb117424 38c5fb11 642440c5 D$....t$8...d$@. + 03c0 fb115c24 48c57b11 5c2450c5 fb104b38 ..\$H.{.\$P...K8 + 03d0 c4417b10 2424c441 7b104424 3062c1ff .A{.$$.A{.D$0b.. + 03e0 08104c24 0762e1ff 08107d00 c5fb1065 ..L$.b....}....e + 03f0 38c5fb11 8c248000 0000c5fb 100e6241 8....$........bA + 0400 ff08104c 240162c1 ff081054 2402c441 ...L$.b....T$..A + 0410 7b106c24 18c4417b 104c2420 c4c17b10 {.l$..A{.L$ ..{. + 0420 742428c5 fb106d28 6261ff08 103b62e1 t$(...m(ba...;b. + 0430 ff081043 02c57b10 5b18c5fb 107b20c5 ...C..{.[....{ . + 0440 fb105330 6261ff08 104501c5 fb105d30 ..S0ba...E....]0 + 0450 c57b1164 2458c57b 11442460 c57b1065 .{.d$X.{.D$`.{.e + 0460 18c57b10 452062e1 ff08114c 240d62e1 ..{.E b....L$.b. + 0470 ff08117c 240e62e1 ff08104d 0262e1ff ...|$.b....M.b.. + 0480 08107b01 c5fb1164 2478c5fb 106328c5 ..{....d$x...c(. + 0490 fb110ac5 fb104c24 b862e1ff 08117a0f ......L$.b....z. + 04a0 c5fb114a 08c5fb10 4c241062 e1ff0810 ...J....L$.b.... + 04b0 7c24f1c5 fb114a18 c5fb104c 243862e1 |$....J....L$8b. + 04c0 ff08114a 16c5fb11 4a20c5fb 104c2458 ...J....J ...L$X + 04d0 62e1ff08 104c24f2 c5fb114a 28c5fb10 b....L$....J(... + 04e0 4c247062 61ff0811 7a07c5fb 114a30c5 L$pba...z....J0. + 04f0 fb104c24 c06261ff 0811520c 6261ff08 ..L$.ba...R.ba.. + 0500 114a0d62 e1ff0811 621362e1 ff08115a .J.b....b.b....Z + 0510 1462e1ff 08115215 62e1ff08 11421762 .b....R.b....B.b + 0520 e1ff0811 4a184c89 52106261 ff081172 ....J.L.R.ba...r + 0530 086261ff 08116a09 6261ff08 11620a62 .ba...j.ba...b.b + 0540 61ff0811 5a0b6261 ff081142 0e62e1ff a...Z.ba...B.b.. + 0550 08117a10 62e1ff08 11721162 e1ff0811 ..z.b....r.b.... + 0560 6a12c5fb 118ac800 0000c5fb 104c24e8 j............L$. + 0570 c5fb11ba 38010000 c5fb107c 24a06261 ....8......|$.ba + 0580 ff08104c 240362e1 ff081054 24ff6261 ...L$.b....T$.ba + 0590 ff081054 2404c5fb 118ad000 0000c57b ...T$..........{ + 05a0 11b2e000 0000c5fb 104c24f0 c57b1074 .........L$..{.t + 05b0 24d0c57b 11aae800 0000c57b 119af800 $..{.......{.... + 05c0 0000c57b 106c24c8 c57b105c 2498c5fb ...{.l$..{.\$... + 05d0 11ba4001 0000c5fb 107c2440 c57b11ba ..@......|$@.{.. + 05e0 d8000000 c57b119a 00010000 c57b118a .....{.......{.. + 05f0 28010000 c57b1182 30010000 c5fb11b2 (....{..0....... + 0600 68010000 c5fb11a2 78010000 c57b11a2 h.......x....{.. + 0610 f0000000 c57b11aa 08010000 c5fb118a .....{.......... + 0620 10010000 6261ff08 114a23c5 7b119220 ....ba...J#.{.. + 0630 010000c5 7b11b248 01000062 e1ff0811 ....{..H...b.... + 0640 522a6261 ff081152 2bc5fb11 ba600100 R*ba...R+....`.. + 0650 00c5fb11 aa700100 00c5fb10 6c24a8c5 .....p......l$.. + 0660 7b107c24 d862e1ff 08101c24 6261ff08 {.|$.b.....$ba.. + 0670 107c2405 c57b1044 2460c57b 104c24e0 .|$..{.D$`.{.L$. + 0680 62e1ff08 10642401 62e1ff08 10442406 b....d$.b....D$. + 0690 c57b105c 245062e1 ff08104c 240dc5fb .{.\$Pb....L$... + 06a0 10642478 c5fb10b4 24800000 00c5fb11 .d$x....$....... + 06b0 aa800100 00c5fb11 92b80100 00c5fb10 ................ + 06c0 6c2448c5 fb105424 b0c57b11 ba880100 l$H...T$..{..... + 06d0 0062e1ff 08115a32 6261ff08 117a33c5 .b....Z2ba...z3. + 06e0 fb11aaa0 010000c5 7b1182a8 010000c5 ........{....... + 06f0 fb119ab0 010000c5 fb1192c0 010000c5 ................ + 0700 7b118ac8 01000062 e1ff0811 623a62e1 {......b....b:b. + 0710 ff081142 3bc57b11 9ae00100 0062e1ff ...B;.{......b.. + 0720 08114a3d c5fb11a2 f0010000 c5fb11b2 ..J=............ + 0730 f8010000 4883c708 4883c640 4883c140 ....H...H..@H..@ + 0740 4983c740 4983c640 4983c540 4983c440 I..@I..@I..@I..@ + 0750 4883c540 4883c340 4881c200 0200004c H..@H..@H......L + 0760 39c70f84 40020000 4839f80f 85bffaff 9...@...H9...... + 0770 ffc5fb10 7e18c4c1 7b107710 c5fb117c ....~...{.w....| + 0780 2488c5fb 107908c4 c17b106e 18c5fb5e $....y...{.n...^ + 0790 ffc4417b 105520c4 417b107c 2428c5fb ..A{.U .A{.|$(.. + 07a0 106608c5 fb105e10 c5fb1051 106261ff .f....^....Q.ba. + 07b0 08106e04 6261ff08 104e0562 e1ff0810 ..n.ba...N.b.... + 07c0 6606c57b 10763862 61ff0810 79036261 f..{.v8ba...y.ba + 07d0 ff081061 046261ff 08104105 62e1ff08 ...a.ba...A.b... + 07e0 105906c5 7b106938 6241ff08 10770362 .Y..{.i8bA...w.b + 07f0 41ff0810 5f0462c1 ff08107f 0562c1ff A..._.b......b.. + 0800 08105706 c4417b10 6738c5fb 5ef66241 ..W..A{.g8..^.bA + 0810 ff081056 0462c1ff 08107605 62c1ff08 ...V.b....v.b... + 0820 104e06c4 417b105e 3862c1ff 08106d05 .N..A{.^8b....m. + 0830 62c1ff08 104506c5 7b115424 90c4417b b....E..{.T$..A{ + 0840 105538c5 7b117c24 98c57b10 4530c5fb .U8.{.|$..{.E0.. + 0850 104b38c4 417b107c 2430c441 7b104c24 .K8.A{.|$0.A{.L$ + 0860 38c57b11 4424a0c5 fb114c24 a8c57b10 8.{.D$....L$..{. + 0870 4538c5fb 5e0ec5fb 117a48c5 fb107c24 E8..^....zH...|$ + 0880 88c5fb5e edc5fb11 0ac5fb11 6240c5fb ...^........b@.. + 0890 119a8000 0000c5fb 11928800 0000c5fb ................ + 08a0 5e642490 c5fb5e5c 2498c5fb 11bac000 ^d$...^\$....... + 08b0 0000c5fb 11b29000 00006261 ff08117a ..........ba...z + 08c0 196261ff 0811721a 6261ff08 116a2062 .ba...r.ba...j b + 08d0 61ff0811 62216261 ff08115a 226261ff a...b!ba...Z"ba. + 08e0 08115223 c5fb11a2 20010000 6261ff08 ..R#.... ...ba.. + 08f0 114a2862 61ff0811 422962e1 ff08117a .J(ba...B)b....z + 0900 2a62e1ff 0811722b 62e1ff08 116a2cc5 *b....r+b....j,. + 0910 fb119a68 010000c5 fb11aad8 00000062 ...h...........b + 0920 e1ff0811 6230c5fb 5e5424a0 c5fb5e4c ....b0..^T$...^L + 0930 24a862e1 ff08115a 3162e1ff 08115232 $.b....Z1b....R2 + 0940 62e1ff08 114a3362 e1ff0811 4234c57b b....J3b....B4.{ + 0950 11baa801 0000c5fb 1192b001 0000c57b ...............{ + 0960 11b2c001 0000c57b 11aac801 0000c57b .......{.......{ + 0970 11a2d001 0000c57b 119ad801 0000c57b .......{.......{ + 0980 1192e001 0000c57b 118ae801 0000c57b .......{.......{ + 0990 1182f001 0000c5fb 118af801 0000e991 ................ + 09a0 fdffff0f 1f440000 488bbc24 30010000 .....D..H..$0... + 09b0 4d89c24d 89d8498d 0c38488b bc240801 M..M..I..8H..$.. + 09c0 00004d89 cb4d8d3c 38488bbc 24100100 ..M..M.<8H..$... + 09d0 004989c1 4d8d3438 488bbc24 18010000 .I..M.48H..$.... + 09e0 488b8424 f8000000 4d8d2c38 488bbc24 H..$....M.,8H..$ + 09f0 28010000 4c01c04d 8d243848 8bbc2420 (...L..M.$8H..$ + 0a00 0100004c 039c24f0 00000049 8d2c3848 ...L..$....I.,8H + 0a10 8bbc2400 0100004c 89d2498d 1c384883 ..$....L..I..8H. + 0a20 bc24c000 0000000f 84f90100 004939d1 .$...........I9. + 0a30 0f84aa05 00000f8d bf010000 488b7b18 ............H.{. /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnncopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 da010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 a3010a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 ee130000 00420e10 8f02420e .........B....B. + 0030 188e0342 0e208d04 450e288c 05410e30 ...B. ..E.(..A.0 + 0040 8606410e 38830747 0ea00303 32130a0e ..A.8..G....2... + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_COOPERLAKE.o (disasm) @@ -7,112 +7,806 @@ dtrsm_olnucopy_COOPERLAKE: push %r15 push %r14 + mov %r9,%r14 push %r13 push %r12 + mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rdi,%rbx - sar %rbx - mov %rbx,%r13 - mov %rcx,%r11 - lea offset(,%rcx,8),%rbp - mov %rdi,%r12 - lea (%r8,%rsi,2),%rax + lea (%rcx,%rcx,2),%rax + lea offset(,%rax,8),%r11 + lea (%rcx,%rcx,4),%rdx + shl $something,%rax + lea offset(,%rcx,8),%r10 + lea offset(,%rdx,8),%rbp + mov %rsi,%r9 + mov %rcx,%rbx + mov %rcx,%rsi + mov %rax,%rdx + mov %rax,offset(%rsp) + imul $something,%rcx,%rax + shl $something,%rcx + mov %rcx,offset(%rsp) + mov %rdi,%rcx + and $something,%ecx + mov %rcx,offset(%rsp) + mov %rdi,%rcx + mov %rax,offset(%rsp) + and $something,%ecx + mov %rdi,%rax + sar $something,%rax + mov %rcx,offset(%rsp) + mov %rdi,%rcx and $something,%rdi - shl $something,%r13 - mov %rbx,%r14 - vmovsd offset(%rip),%xmm4 # - mov %r8,-offset(%rsp) + mov %rdi,%r13 + mov %rax,%rdi + shl $something,%rdi + shl $something,%rsi + shl $something,%rbx + mov %rsi,offset(%rsp) + add %rdi,%rsi + add %rdi,%rdx + mov %r10,offset(%rsp) + mov %rbx,offset(%rsp) + add %rdi,%r10 + add %rdi,%rbx + mov %r11,offset(%rsp) + mov %rbp,offset(%rsp) + add %rdi,%r11 + add %rdi,%rbp + mov %rax,offset(%rsp) + mov %rsi,offset(%rsp) + shl $something,%rax + mov offset(%rsp),%rsi + and $something,%ecx + mov %r10,offset(%rsp) + mov %rbx,offset(%rsp) + mov %r11,offset(%rsp) + mov %rbp,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rax,offset(%rsp) + mov %r12,offset(%rsp) + add %rdi,%rsi + mov %rcx,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + lea (%r8,%r9,8),%rcx + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rsi,offset(%rsp) + mov %r12,%rcx mov %r8,%rsi - shl $something,%r11 - and $something,%r12d - mov %rdi,%r10 - lea offset(%rbp,%r13,1),%r15 - shl $something,%r14 - mov %rdx,%rcx - mov %rax,%r8 + mov %r13,%rdi + mov %r14,%r8 + nopl offset(%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%rcx,1),%r13 + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%r12 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%rbp + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%rbx + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%r11 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%r10 + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%r9 + jle + xor %r15d,%r15d + mov %rcx,%r14 + mov %rcx,%rax + mov %r8,%rdx + mov %rsi,%rcx + mov %r15,%rsi + jmp nopw offset(%rax,%rax,1) - lea offset(%rbp,%rcx,1),%rdi - test %rbx,%rbx + jge + vmovsd offset(%r14),%xmm7 + vmovsd offset(%r14),%xmm5 + vmovsd offset(%r14),%xmm6 + vmovsd offset(%r14),%xmm4 + vmovsd offset(%r14),%xmm2 + vmovsd offset(%r14),%xmm3 + vmovsd offset(%r13),%xmm1 + vmovsd offset(%r13),%xmm9 + vmovsd offset(%r13),%xmm10 + vmovsd offset(%r13),%xmm13 + vmovsd offset(%r13),%xmm14 + vmovsd (%r12),%xmm15 + vmovsd offset(%r12),%xmm8 + vmovsd offset(%r14),%xmm30 + vmovsd offset(%r13),%xmm29 + mov offset(%r13),%r15 + vmovsd offset(%r13),%xmm22 + vmovsd offset(%r12),%xmm28 + vmovsd offset(%r12),%xmm21 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm2,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd %xmm1,-offset(%rsp) + vmovsd %xmm9,-offset(%rsp) + vmovsd %xmm10,-offset(%rsp) + vmovsd %xmm13,-offset(%rsp) + vmovsd %xmm14,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm8,-offset(%rsp) + vmovsd offset(%r12),%xmm17 + vmovsd offset(%r12),%xmm18 + vmovsd offset(%r12),%xmm19 + vmovsd offset(%r12),%xmm20 + vmovsd offset(%rbp),%xmm23 + vmovsd offset(%rbp),%xmm15 + vmovsd offset(%rbp),%xmm24 + vmovsd offset(%rbp),%xmm25 + vmovsd offset(%rbp),%xmm26 + vmovsd offset(%rbp),%xmm16 + vmovsd (%rbx),%xmm6 + vmovsd offset(%rbx),%xmm4 + vmovsd offset(%rbx),%xmm2 + vmovsd offset(%rbx),%xmm14 + vmovsd offset(%rbx),%xmm10 + vmovsd offset(%rbp),%xmm27 + vmovsd %xmm17,-offset(%rsp) + vmovsd %xmm18,-offset(%rsp) + vmovsd %xmm19,(%rsp) + vmovsd %xmm20,offset(%rsp) + vmovsd offset(%rbx),%xmm19 + vmovsd offset(%rbp),%xmm20 + vmovsd %xmm23,offset(%rsp) + vmovsd %xmm15,offset(%rsp) + vmovsd %xmm24,offset(%rsp) + vmovsd %xmm25,offset(%rsp) + vmovsd %xmm26,offset(%rsp) + vmovsd %xmm16,offset(%rsp) + vmovsd offset(%rbx),%xmm26 + vmovsd %xmm6,offset(%rsp) + vmovsd %xmm4,offset(%rsp) + vmovsd %xmm2,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_COOPERLAKE.o (objdump) @@ -2,32 +2,302 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424e048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24f848 895424d8 48897424 ..H.|$.H.T$.H.t$ - 0020 e84885f6 0f8e2501 00004889 fb48d1fb .H....%...H..H.. - 0030 4989dd49 89cb488d 2ccd0000 00004989 I..I..H.,.....I. - 0040 fc498d04 704883e7 fe49c1e5 044989de .I..pH...I...I.. - 0050 c5fb1025 00000000 4c894424 f04c89c6 ...%....L.D$.L.. - 0060 49c1e304 4183e401 4989fa4e 8d7c2d00 I...A...I..N.|-. - 0070 49c1e605 4889d149 89c0660f 1f440000 I...H..I..f..D.. - 0080 488d7c0d 004885db 0f8e3201 00004c89 H.|..H....2...L. - 0090 ca31c0eb 3b0f1f00 7e29c5fb 101cc1c5 .1..;...~)...... - 00a0 fb104cc1 08c5fb10 14c7c5fb 1044c708 ..L..........D.. - 00b0 c5fb111a c5fb1152 08c5fb11 4a10c5fb .......R....J... - 00c0 11421848 83c00248 83c22049 39c27426 .B.H...H.. I9.t& - 00d0 4839f075 c3c5fb10 44c10848 83c002c5 H9.u....D..H.... - 00e0 fb1122c5 fb114210 c5fb1162 184883c2 .."...B....b.H.. - 00f0 204939c2 75da4a8d 14294a8d 3c394d01 I9.u.J..)J.<9M. - 0100 f14d85e4 74224839 c60f84a1 0000007d .M..t"H9.......} - 0110 13c5fb10 0ac5fb10 07c4c17b 1109c4c1 ...........{.... - 0120 7b114108 4983c110 4883c602 4c01d94c {.A.I...H...L..L - 0130 39c60f85 48ffffff 488b4424 e84c8b44 9...H...H.D$.L.D - 0140 24f04c0f afd84d8d 04404c01 5c24d8f6 $.L...M..@L.\$.. - 0150 4424e001 744a488b 5424f848 85d27e40 D$..tJH.T$.H..~@ - 0160 c5fb100d 00000000 488b4c24 d831c0eb ........H.L$.1.. - 0170 1c0f1f80 00000000 7e0bc5fb 1004c1c4 ........~....... - 0180 c17b1104 c148ffc0 4839c274 134c39c0 .{...H..H9.t.L9. - 0190 75e6c4c1 7b110cc1 48ffc048 39c275ed u...{...H..H9.u. - 01a0 5b5d415c 415d415e 31c0415f c30f1f00 []A\A]A^1.A_.... - 01b0 c4c17b11 21e96aff ffff660f 1f440000 ..{.!.j...f..D.. - 01c0 4889ca31 c0e937ff ffff H..1..7... + 0000 41574156 4d89ce41 55415449 89d45553 AWAVM..AUATI..US + 0010 4881ec68 01000048 89b42440 01000048 H..h...H..$@...H + 0020 c1fe0348 89bc2448 01000048 898c2458 ...H..$H...H..$X + 0030 0100004c 89842438 01000048 89b42450 ...L..$8...H..$P + 0040 01000048 85f60f8e 2b0d0000 488d0449 ...H....+...H..I + 0050 4c8d1cc5 00000000 488d1489 48c1e004 L.......H...H... + 0060 4c8d14cd 00000000 488d2cd5 00000000 L.......H.,..... + 0070 4989f148 89cb4889 ce4889c2 48898424 I..H..H..H..H..$ + 0080 e8000000 486bc138 48c1e106 48898c24 ....Hk.8H...H..$ + 0090 90000000 4889f983 e1044889 8c24c000 ....H.....H..$.. + 00a0 00004889 f9488984 24880000 0083e102 ..H..H..$....... + 00b0 4889f848 c1f80348 898c24c8 00000048 H..H...H..$....H + 00c0 89f94883 e7f84989 fd4889c7 48c1e706 ..H...I..H..H... + 00d0 48c1e605 48c1e304 4889b424 a8000000 H...H...H..$.... + 00e0 4801fe48 01fa4c89 94249800 00004889 H..H..L..$....H. + 00f0 9c24a000 00004901 fa4801fb 4c899c24 .$....I..H..L..$ + 0100 d8000000 4889ac24 e0000000 4901fb48 ....H..$....I..H + 0110 01fd4889 8424b000 00004889 b4243001 ..H..$....H..$0. + 0120 000048c1 e009488b b4248800 000083e1 ..H...H..$...... + 0130 014c8994 24280100 0048899c 24180100 .L..$(...H..$... + 0140 004c899c 24100100 004889ac 24080100 .L..$....H..$... + 0150 00488994 24000100 00488984 24f00000 .H..$....H..$... + 0160 004c89a4 24600100 004801fe 48898c24 .L..$`...H..H..$ + 0170 d0000000 c5fb1005 00000000 4b8d0cc8 ............K... + 0180 48898c24 b8000000 4889bc24 f8000000 H..$....H..$.... + 0190 4889b424 20010000 4c89e14c 89c64c89 H..$ ...L..L..L. + 01a0 ef4d89f0 0f1f4000 488b8424 98000000 .M....@.H..$.... + 01b0 4883bc24 b0000000 004c8d2c 08488b84 H..$.....L.,.H.. + 01c0 24a00000 004c8d24 08488b84 24d80000 $....L.$.H..$... + 01d0 00488d2c 01488b84 24a80000 00488d1c .H.,.H..$....H.. + 01e0 08488b84 24e00000 004c8d1c 01488b84 .H..$....L...H.. + 01f0 24e80000 004c8d14 01488b84 24880000 $....L...H..$... + 0200 004c8d0c 080f8e35 10000045 31ff4989 .L.....5...E1.I. + 0210 ce4889c8 4c89c248 89f14c89 fee94a05 .H..L..H..L...J. + 0220 0000660f 1f440000 0f8d0a05 0000c4c1 ..f..D.......... + 0230 7b107e10 c4c17b10 6e18c4c1 7b107620 {.~...{.n...{.v + 0240 c4c17b10 6628c4c1 7b105630 c4c17b10 ..{.f(..{.V0..{. + 0250 5e38c4c1 7b104d18 c4417b10 4d20c441 ^8..{.M..A{.M .A + 0260 7b105528 c4417b10 6d30c441 7b107538 {.U(.A{.m0.A{.u8 + 0270 c4417b10 3c24c441 7b104424 186241ff .A{.<$.A{.D$.bA. + 0280 08107601 6241ff08 106d014d 8b7d0062 ..v.bA...m.M.}.b + 0290 c1ff0810 75026241 ff081064 240162c1 ....u.bA...d$.b. + 02a0 ff08106c 2402c5fb 117c2488 c5fb116c ...l$....|$....l + 02b0 2490c5fb 11742498 c5fb1164 24a0c5fb $....t$....d$... + 02c0 115424a8 c5fb115c 24b0c5fb 114c24b8 .T$....\$....L$. + 02d0 c57b114c 24c0c57b 115424c8 c57b116c .{.L$..{.T$..{.l + 02e0 24d0c57b 117424d8 c57b117c 24e0c57b $..{.t$..{.|$..{ + 02f0 114424e8 62c1ff08 104c2404 62c1ff08 .D$.b....L$.b... + 0300 10542405 62c1ff08 105c2406 62c1ff08 .T$.b....\$.b... + 0310 10642407 62e1ff08 107d00c5 7b107d18 .d$.b....}..{.}. + 0320 6261ff08 10450462 61ff0810 4d056261 ba...E.ba...M.ba + 0330 ff081055 0662e1ff 08104507 c5fb1033 ...U.b....E....3 + 0340 c5fb1063 28c5fb10 5330c57b 107318c5 ...c(...S0.{.s.. + 0350 7b105320 6261ff08 105d0162 e1ff0811 {.S ba...].b.... + 0360 4c24fe62 e1ff0811 5424ff62 e1ff0811 L$.b....T$.b.... + 0370 1c2462e1 ff081164 240162e1 ff08105b .$b....d$.b....[ + 0380 0262e1ff 08106502 62e1ff08 117c2402 .b....e.b....|$. + 0390 c57b117c 24186261 ff081144 24046261 .{.|$.ba...D$.ba + 03a0 ff08114c 24056261 ff081154 240662e1 ...L$.ba...T$.b. + 03b0 ff081144 24076261 ff081053 01c5fb11 ...D$.ba...S.... + 03c0 742440c5 fb116424 48c5fb11 542450c5 t$@...d$H...T$P. + 03d0 fb104b38 c4417b10 0bc4417b 105b30c4 ..K8.A{...A{.[0. + 03e0 417b1063 38c4417b 10026241 ff08107a A{.c8.A{..bA...z + 03f0 07c4417b 103e6241 ff08104b 0162c1ff ..A{.>bA...K.b.. + 0400 08105302 c4417b10 6b18c4c1 7b107328 ..S..A{.k...{.s( + 0410 6241ff08 10420162 c1ff0810 4a02c4c1 bA...B.b....J... + 0420 7b106a28 c4c17b10 5a3062c1 ff081041 {.j(..{.Z0b....A + 0430 02c4c17b 10792062 c1ff0810 7901c4c1 ...{.y b....y... + 0440 7b106128 c4c17b10 5130c5fb 114c2458 {.a(..{.Q0...L$X + 0450 c57b114c 2460c4c1 7b104938 c4417b10 .{.L$`..{.I8.A{. + 0460 4b20c57b 115c2468 c57b1164 2470c441 K .{.\$h.{.d$p.A + 0470 7b105918 c4417b10 6218c57b 11442478 {.Y..A{.b..{.D$x + 0480 6261ff08 117c2410 c4417b10 42206241 ba...|$..A{.B bA + 0490 ff081039 c57b113a c57b107c 24e06261 ...9.{.:.{.|$.ba + 04a0 ff08117a 07c57b11 7a10c57b 107c2410 ...z..{.z..{.|$. + 04b0 6261ff08 107c24f7 c57b117a 18c57b10 ba...|$..{.z..{. + 04c0 7c244062 61ff0811 7208c57b 117a20c5 |$@ba...r..{.z . + 04d0 7b107c24 606261ff 08107424 f2c57b11 {.|$`ba...t$..{. + 04e0 7a286261 ff08116a 09c57b10 7c247862 z(ba...j..{.|$xb + 04f0 61ff0810 6c24f1c5 7b117a30 6261ff08 a...l$..{.z0ba.. + 0500 11520c62 61ff0811 4a0d6261 ff081142 .R.ba...J.ba...B + 0510 0e62e1ff 08116213 62e1ff08 115a1462 .b....b.b....Z.b + 0520 e1ff0811 521562e1 ff08114a 1662e1ff ....R.b....J.b.. + 0530 08114217 4c897a08 6261ff08 11620a62 ..B.L.z.ba...b.b + 0540 61ff0811 5a0b62e1 ff08117a 0f6261ff a...Z.b....z.ba. + 0550 08116a10 62e1ff08 11721162 e1ff0811 ..j.b....r.b.... + 0560 6a126261 ff081172 186261ff 08117a19 j.ba...r.ba...z. + 0570 c57b107c 24e8c5fb 11ba3801 0000c5fb .{.|$.....8..... + 0580 107c24a0 62e1ff08 104c24fe 6261ff08 .|$.b....L$.ba.. + 0590 10442404 62e1ff08 105424ff 6261ff08 .D$.b....T$.ba.. + 05a0 104c2405 c57b11ba d0000000 c57b11a2 .L$..{.......{.. + 05b0 f0000000 c57b107c 2418c57b 106424c0 .....{.|$..{.d$. + 05c0 c57b119a f8000000 c57b1192 20010000 .{.......{.. ... + 05d0 c57b105c 2498c57b 105424c8 c5fb11ba .{.\$..{.T$..... + 05e0 40010000 c5fb107c 2448c57b 11b2e000 @......|$H.{.... + 05f0 0000c57b 11aae800 0000c57b 119a0001 ...{.......{.... + 0600 0000c57b 11a20801 0000c5fb 11b26801 ...{..........h. + 0610 0000c5fb 11aa7001 0000c57b 11bad800 ......p....{.... + 0620 000062e1 ff08114a 226261ff 08114223 ..b....J"ba...B# + 0630 c57b118a 28010000 c57b1182 30010000 .{..(....{..0... + 0640 c57b1192 48010000 62e1ff08 11522a62 .{..H...b....R*b + 0650 61ff0811 4a2bc5fb 11ba6001 0000c5fb a...J+....`..... + 0660 11a27801 0000c5fb 106c24a8 c57b106c ..x......l$..{.l + 0670 24d062e1 ff08101c 246261ff 08105424 $.b.....$ba...T$ + 0680 06c57b10 5c2468c5 7b107424 d862e1ff ..{.\$h.{.t$.b.. + 0690 08106424 0162e1ff 08104424 07c5fb10 ..d$.b....D$.... + 06a0 742458c5 7b106424 706261ff 08107c24 t$X.{.d$pba...|$ + 06b0 10c5fb11 aa800100 00c5fb11 9ab00100 ................ + 06c0 00c5fb10 6c2450c5 fb105c24 b0c57b11 ....l$P...\$..{. + 06d0 aa880100 0062e1ff 08115a32 6261ff08 .....b....Z2ba.. + 06e0 115233c5 fb11aaa0 010000c5 7b119aa8 .R3.........{... + 06f0 010000c5 fb1192b8 010000c5 fb119ac0 ................ + 0700 010000c5 7b11b2c8 01000062 e1ff0811 ....{......b.... + 0710 623a62e1 ff081142 3bc5fb11 b2e00100 b:b....B;....... + 0720 00c57b11 a2e80100 006261ff 08117a3e ..{......ba...z> + 0730 c5fb118a f8010000 4883c608 4983c640 ........H...I..@ + 0740 4983c540 4983c440 4883c540 4883c340 I..@I..@H..@H..@ + 0750 4983c340 4983c240 4983c140 4881c200 I..@I..@I..@H... + 0760 02000048 39fe0f84 d4010000 4839f10f ...H9.......H9.. + 0770 85b3faff ff6241ff 08104e03 62c1ff08 .....bA...N.b... + 0780 10760462 c1ff0810 5605c441 7b106e30 .v.b....V..A{.n0 + 0790 c4c17b10 7e386241 ff081045 0362c1ff ..{.~8bA...E.b.. + 07a0 08106d04 62c1ff08 104d05c4 417b1065 ..m.b....M..A{.e + 07b0 30c4c17b 10753862 c1ff0810 7c240362 0..{.u8b....|$.b + 07c0 c1ff0810 64240462 c1ff0810 442405c4 ....d$.b....D$.. + 07d0 417b105c 2430c4c1 7b106c24 3862e1ff A{.\$0..{.l$8b.. + 07e0 08105d04 c57b107d 28c57b10 5530c5fb ..]..{.}(.{.U0.. + 07f0 106538c5 7b107328 c57b104b 30c5fb10 .e8.{.s(.{.K0... + 0800 5b38c441 7b104330 c4c17b10 5338c4c1 [8.A{.C0..{.S8.. + 0810 7b104a38 6241ff08 10660162 41ff0810 {.J8bA...f.bA... + 0820 5e026241 ff081055 02c5fb11 026261ff ^.bA...U.....ba. + 0830 08116208 c5fb1142 486261ff 08115a10 ..b....BHba...Z. + 0840 6261ff08 115211c5 fb118290 00000062 ba...R.........b + 0850 61ff0811 4a186261 ff081142 1962e1ff a...J.ba...B.b.. + 0860 08117a1a c5fb1182 d8000000 62e1ff08 ..z.........b... + 0870 11722062 e1ff0811 6a2162e1 ff081162 .r b....j!b....b + 0880 2262e1ff 08115a23 c5fb1182 20010000 "b....Z#.... ... + 0890 62e1ff08 11522862 e1ff0811 4a2962e1 b....R(b....J)b. + 08a0 ff081142 2ac57b11 ba580100 00c57b11 ...B*.{..X....{. + 08b0 b2600100 00c5fb11 82680100 00c57b11 .`.......h....{. + 08c0 aa800100 00c57b11 a2880100 00c57b11 ......{.......{. + 08d0 9a900100 00c57b11 92980100 00c57b11 ......{.......{. + 08e0 8aa00100 00c57b11 82a80100 00c5fb11 ......{......... + 08f0 82b00100 00c5fb11 bac00100 00c5fb11 ................ + 0900 b2c80100 00c5fb11 aad00100 00c5fb11 ................ + 0910 a2d80100 00c5fb11 9ae00100 00c5fb11 ................ + 0920 92e80100 00c5fb11 8af00100 00c5fb11 ................ + 0930 82f80100 00e9fefd ffff660f 1f440000 ..........f..D.. + 0940 488b9c24 28010000 4889ce48 89c1488b H..$(...H..H..H. + 0950 94240801 00004c8d 2c19488b 9c241801 .$....L.,.H..$.. + 0960 00004c8d 1c114c8d 2419488b 94240001 ..L...L.$.H..$.. + 0970 0000488b 9c241001 0000488b 8424f800 ..H..$....H..$.. + 0980 0000488d 2c194c8d 1411488b 9c243001 ..H.,.L...H..$0. + 0990 0000488b 94242001 00004801 c84c8d0c ..H..$ ...H..L.. + 09a0 114801cb 4c038424 f0000000 4889fa48 .H..L..$....H..H + 09b0 83bc24c0 00000000 0f84fa01 00004839 ..$...........H9 + 09c0 d60f8479 0500000f 8dc00100 004d8b79 ...y.........M.y + 09d0 18c5fb10 086261ff 08104001 62e1ff08 .....ba...@.b... + 09e0 104002c5 7b104018 6241ff08 107d0062 .@..{.@.bA...}.b + 09f0 c1ff0810 7d01c441 7b107d10 c4c17b10 ....}..A{.}...{. + 0a00 7d186241 ff081034 2462c1ff 08107424 }.bA...4$b....t$ + 0a10 01c4417b 10742410 c4c17b10 74241862 ..A{.t$...{.t$.b + 0a20 61ff0810 6d0062e1 ff08106d 01c57b10 a...m.b....m..{. + 0a30 6d10c5fb 106d1862 61ff0810 2362e1ff m....m.ba...#b.. + 0a40 08106301 c57b1063 10c5fb10 63186241 ..c..{.c....c.bA /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 ca010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830703 97010a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 440b0000 B. B..B..D..D... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 a2120000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05440e30 ...E. ..B.(..D.0 + 0040 8606410e 38830747 0ea00303 19120a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0844 0b000000 D..D.... /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_SKYLAKEX.o (disasm) @@ -7,112 +7,806 @@ dtrsm_olnucopy_SKYLAKEX: push %r15 push %r14 + mov %r9,%r14 push %r13 push %r12 + mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rdi,%rbx - sar %rbx - mov %rbx,%r13 - mov %rcx,%r11 - lea offset(,%rcx,8),%rbp - mov %rdi,%r12 - lea (%r8,%rsi,2),%rax + lea (%rcx,%rcx,2),%rax + lea offset(,%rax,8),%r11 + lea (%rcx,%rcx,4),%rdx + shl $something,%rax + lea offset(,%rcx,8),%r10 + lea offset(,%rdx,8),%rbp + mov %rsi,%r9 + mov %rcx,%rbx + mov %rcx,%rsi + mov %rax,%rdx + mov %rax,offset(%rsp) + imul $something,%rcx,%rax + shl $something,%rcx + mov %rcx,offset(%rsp) + mov %rdi,%rcx + and $something,%ecx + mov %rcx,offset(%rsp) + mov %rdi,%rcx + mov %rax,offset(%rsp) + and $something,%ecx + mov %rdi,%rax + sar $something,%rax + mov %rcx,offset(%rsp) + mov %rdi,%rcx and $something,%rdi - shl $something,%r13 - mov %rbx,%r14 - vmovsd offset(%rip),%xmm4 # - mov %r8,-offset(%rsp) + mov %rdi,%r13 + mov %rax,%rdi + shl $something,%rdi + shl $something,%rsi + shl $something,%rbx + mov %rsi,offset(%rsp) + add %rdi,%rsi + add %rdi,%rdx + mov %r10,offset(%rsp) + mov %rbx,offset(%rsp) + add %rdi,%r10 + add %rdi,%rbx + mov %r11,offset(%rsp) + mov %rbp,offset(%rsp) + add %rdi,%r11 + add %rdi,%rbp + mov %rax,offset(%rsp) + mov %rsi,offset(%rsp) + shl $something,%rax + mov offset(%rsp),%rsi + and $something,%ecx + mov %r10,offset(%rsp) + mov %rbx,offset(%rsp) + mov %r11,offset(%rsp) + mov %rbp,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rax,offset(%rsp) + mov %r12,offset(%rsp) + add %rdi,%rsi + mov %rcx,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + lea (%r8,%r9,8),%rcx + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rsi,offset(%rsp) + mov %r12,%rcx mov %r8,%rsi - shl $something,%r11 - and $something,%r12d - mov %rdi,%r10 - lea offset(%rbp,%r13,1),%r15 - shl $something,%r14 - mov %rdx,%rcx - mov %rax,%r8 + mov %r13,%rdi + mov %r14,%r8 + nopl offset(%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%rcx,1),%r13 + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%r12 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%rbp + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%rbx + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%r11 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%r10 + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%r9 + jle + xor %r15d,%r15d + mov %rcx,%r14 + mov %rcx,%rax + mov %r8,%rdx + mov %rsi,%rcx + mov %r15,%rsi + jmp nopw offset(%rax,%rax,1) - lea offset(%rbp,%rcx,1),%rdi - test %rbx,%rbx + jge + vmovsd offset(%r14),%xmm7 + vmovsd offset(%r14),%xmm5 + vmovsd offset(%r14),%xmm6 + vmovsd offset(%r14),%xmm4 + vmovsd offset(%r14),%xmm2 + vmovsd offset(%r14),%xmm3 + vmovsd offset(%r13),%xmm1 + vmovsd offset(%r13),%xmm9 + vmovsd offset(%r13),%xmm10 + vmovsd offset(%r13),%xmm13 + vmovsd offset(%r13),%xmm14 + vmovsd (%r12),%xmm15 + vmovsd offset(%r12),%xmm8 + vmovsd offset(%r14),%xmm30 + vmovsd offset(%r13),%xmm29 + mov offset(%r13),%r15 + vmovsd offset(%r13),%xmm22 + vmovsd offset(%r12),%xmm28 + vmovsd offset(%r12),%xmm21 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm2,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd %xmm1,-offset(%rsp) + vmovsd %xmm9,-offset(%rsp) + vmovsd %xmm10,-offset(%rsp) + vmovsd %xmm13,-offset(%rsp) + vmovsd %xmm14,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm8,-offset(%rsp) + vmovsd offset(%r12),%xmm17 + vmovsd offset(%r12),%xmm18 + vmovsd offset(%r12),%xmm19 + vmovsd offset(%r12),%xmm20 + vmovsd offset(%rbp),%xmm23 + vmovsd offset(%rbp),%xmm15 + vmovsd offset(%rbp),%xmm24 + vmovsd offset(%rbp),%xmm25 + vmovsd offset(%rbp),%xmm26 + vmovsd offset(%rbp),%xmm16 + vmovsd (%rbx),%xmm6 + vmovsd offset(%rbx),%xmm4 + vmovsd offset(%rbx),%xmm2 + vmovsd offset(%rbx),%xmm14 + vmovsd offset(%rbx),%xmm10 + vmovsd offset(%rbp),%xmm27 + vmovsd %xmm17,-offset(%rsp) + vmovsd %xmm18,-offset(%rsp) + vmovsd %xmm19,(%rsp) + vmovsd %xmm20,offset(%rsp) + vmovsd offset(%rbx),%xmm19 + vmovsd offset(%rbp),%xmm20 + vmovsd %xmm23,offset(%rsp) + vmovsd %xmm15,offset(%rsp) + vmovsd %xmm24,offset(%rsp) + vmovsd %xmm25,offset(%rsp) + vmovsd %xmm26,offset(%rsp) + vmovsd %xmm16,offset(%rsp) + vmovsd offset(%rbx),%xmm26 + vmovsd %xmm6,offset(%rsp) + vmovsd %xmm4,offset(%rsp) + vmovsd %xmm2,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_SKYLAKEX.o (objdump) @@ -2,32 +2,302 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424e048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24f848 895424d8 48897424 ..H.|$.H.T$.H.t$ - 0020 e84885f6 0f8e2501 00004889 fb48d1fb .H....%...H..H.. - 0030 4989dd49 89cb488d 2ccd0000 00004989 I..I..H.,.....I. - 0040 fc498d04 704883e7 fe49c1e5 044989de .I..pH...I...I.. - 0050 c5fb1025 00000000 4c894424 f04c89c6 ...%....L.D$.L.. - 0060 49c1e304 4183e401 4989fa4e 8d7c2d00 I...A...I..N.|-. - 0070 49c1e605 4889d149 89c0660f 1f440000 I...H..I..f..D.. - 0080 488d7c0d 004885db 0f8e3201 00004c89 H.|..H....2...L. - 0090 ca31c0eb 3b0f1f00 7e29c5fb 101cc1c5 .1..;...~)...... - 00a0 fb104cc1 08c5fb10 14c7c5fb 1044c708 ..L..........D.. - 00b0 c5fb111a c5fb1152 08c5fb11 4a10c5fb .......R....J... - 00c0 11421848 83c00248 83c22049 39c27426 .B.H...H.. I9.t& - 00d0 4839f075 c3c5fb10 44c10848 83c002c5 H9.u....D..H.... - 00e0 fb1122c5 fb114210 c5fb1162 184883c2 .."...B....b.H.. - 00f0 204939c2 75da4a8d 14294a8d 3c394d01 I9.u.J..)J.<9M. - 0100 f14d85e4 74224839 c60f84a1 0000007d .M..t"H9.......} - 0110 13c5fb10 0ac5fb10 07c4c17b 1109c4c1 ...........{.... - 0120 7b114108 4983c110 4883c602 4c01d94c {.A.I...H...L..L - 0130 39c60f85 48ffffff 488b4424 e84c8b44 9...H...H.D$.L.D - 0140 24f04c0f afd84d8d 04404c01 5c24d8f6 $.L...M..@L.\$.. - 0150 4424e001 744a488b 5424f848 85d27e40 D$..tJH.T$.H..~@ - 0160 c5fb100d 00000000 488b4c24 d831c0eb ........H.L$.1.. - 0170 1c0f1f80 00000000 7e0bc5fb 1004c1c4 ........~....... - 0180 c17b1104 c148ffc0 4839c274 134c39c0 .{...H..H9.t.L9. - 0190 75e6c4c1 7b110cc1 48ffc048 39c275ed u...{...H..H9.u. - 01a0 5b5d415c 415d415e 31c0415f c30f1f00 []A\A]A^1.A_.... - 01b0 c4c17b11 21e96aff ffff660f 1f440000 ..{.!.j...f..D.. - 01c0 4889ca31 c0e937ff ffff H..1..7... + 0000 41574156 4d89ce41 55415449 89d45553 AWAVM..AUATI..US + 0010 4881ec68 01000048 89b42440 01000048 H..h...H..$@...H + 0020 c1fe0348 89bc2448 01000048 898c2458 ...H..$H...H..$X + 0030 0100004c 89842438 01000048 89b42450 ...L..$8...H..$P + 0040 01000048 85f60f8e 2b0d0000 488d0449 ...H....+...H..I + 0050 4c8d1cc5 00000000 488d1489 48c1e004 L.......H...H... + 0060 4c8d14cd 00000000 488d2cd5 00000000 L.......H.,..... + 0070 4989f148 89cb4889 ce4889c2 48898424 I..H..H..H..H..$ + 0080 e8000000 486bc138 48c1e106 48898c24 ....Hk.8H...H..$ + 0090 90000000 4889f983 e1044889 8c24c000 ....H.....H..$.. + 00a0 00004889 f9488984 24880000 0083e102 ..H..H..$....... + 00b0 4889f848 c1f80348 898c24c8 00000048 H..H...H..$....H + 00c0 89f94883 e7f84989 fd4889c7 48c1e706 ..H...I..H..H... + 00d0 48c1e605 48c1e304 4889b424 a8000000 H...H...H..$.... + 00e0 4801fe48 01fa4c89 94249800 00004889 H..H..L..$....H. + 00f0 9c24a000 00004901 fa4801fb 4c899c24 .$....I..H..L..$ + 0100 d8000000 4889ac24 e0000000 4901fb48 ....H..$....I..H + 0110 01fd4889 8424b000 00004889 b4243001 ..H..$....H..$0. + 0120 000048c1 e009488b b4248800 000083e1 ..H...H..$...... + 0130 014c8994 24280100 0048899c 24180100 .L..$(...H..$... + 0140 004c899c 24100100 004889ac 24080100 .L..$....H..$... + 0150 00488994 24000100 00488984 24f00000 .H..$....H..$... + 0160 004c89a4 24600100 004801fe 48898c24 .L..$`...H..H..$ + 0170 d0000000 c5fb1005 00000000 4b8d0cc8 ............K... + 0180 48898c24 b8000000 4889bc24 f8000000 H..$....H..$.... + 0190 4889b424 20010000 4c89e14c 89c64c89 H..$ ...L..L..L. + 01a0 ef4d89f0 0f1f4000 488b8424 98000000 .M....@.H..$.... + 01b0 4883bc24 b0000000 004c8d2c 08488b84 H..$.....L.,.H.. + 01c0 24a00000 004c8d24 08488b84 24d80000 $....L.$.H..$... + 01d0 00488d2c 01488b84 24a80000 00488d1c .H.,.H..$....H.. + 01e0 08488b84 24e00000 004c8d1c 01488b84 .H..$....L...H.. + 01f0 24e80000 004c8d14 01488b84 24880000 $....L...H..$... + 0200 004c8d0c 080f8e35 10000045 31ff4989 .L.....5...E1.I. + 0210 ce4889c8 4c89c248 89f14c89 fee94a05 .H..L..H..L...J. + 0220 0000660f 1f440000 0f8d0a05 0000c4c1 ..f..D.......... + 0230 7b107e10 c4c17b10 6e18c4c1 7b107620 {.~...{.n...{.v + 0240 c4c17b10 6628c4c1 7b105630 c4c17b10 ..{.f(..{.V0..{. + 0250 5e38c4c1 7b104d18 c4417b10 4d20c441 ^8..{.M..A{.M .A + 0260 7b105528 c4417b10 6d30c441 7b107538 {.U(.A{.m0.A{.u8 + 0270 c4417b10 3c24c441 7b104424 186241ff .A{.<$.A{.D$.bA. + 0280 08107601 6241ff08 106d014d 8b7d0062 ..v.bA...m.M.}.b + 0290 c1ff0810 75026241 ff081064 240162c1 ....u.bA...d$.b. + 02a0 ff08106c 2402c5fb 117c2488 c5fb116c ...l$....|$....l + 02b0 2490c5fb 11742498 c5fb1164 24a0c5fb $....t$....d$... + 02c0 115424a8 c5fb115c 24b0c5fb 114c24b8 .T$....\$....L$. + 02d0 c57b114c 24c0c57b 115424c8 c57b116c .{.L$..{.T$..{.l + 02e0 24d0c57b 117424d8 c57b117c 24e0c57b $..{.t$..{.|$..{ + 02f0 114424e8 62c1ff08 104c2404 62c1ff08 .D$.b....L$.b... + 0300 10542405 62c1ff08 105c2406 62c1ff08 .T$.b....\$.b... + 0310 10642407 62e1ff08 107d00c5 7b107d18 .d$.b....}..{.}. + 0320 6261ff08 10450462 61ff0810 4d056261 ba...E.ba...M.ba + 0330 ff081055 0662e1ff 08104507 c5fb1033 ...U.b....E....3 + 0340 c5fb1063 28c5fb10 5330c57b 107318c5 ...c(...S0.{.s.. + 0350 7b105320 6261ff08 105d0162 e1ff0811 {.S ba...].b.... + 0360 4c24fe62 e1ff0811 5424ff62 e1ff0811 L$.b....T$.b.... + 0370 1c2462e1 ff081164 240162e1 ff08105b .$b....d$.b....[ + 0380 0262e1ff 08106502 62e1ff08 117c2402 .b....e.b....|$. + 0390 c57b117c 24186261 ff081144 24046261 .{.|$.ba...D$.ba + 03a0 ff08114c 24056261 ff081154 240662e1 ...L$.ba...T$.b. + 03b0 ff081144 24076261 ff081053 01c5fb11 ...D$.ba...S.... + 03c0 742440c5 fb116424 48c5fb11 542450c5 t$@...d$H...T$P. + 03d0 fb104b38 c4417b10 0bc4417b 105b30c4 ..K8.A{...A{.[0. + 03e0 417b1063 38c4417b 10026241 ff08107a A{.c8.A{..bA...z + 03f0 07c4417b 103e6241 ff08104b 0162c1ff ..A{.>bA...K.b.. + 0400 08105302 c4417b10 6b18c4c1 7b107328 ..S..A{.k...{.s( + 0410 6241ff08 10420162 c1ff0810 4a02c4c1 bA...B.b....J... + 0420 7b106a28 c4c17b10 5a3062c1 ff081041 {.j(..{.Z0b....A + 0430 02c4c17b 10792062 c1ff0810 7901c4c1 ...{.y b....y... + 0440 7b106128 c4c17b10 5130c5fb 114c2458 {.a(..{.Q0...L$X + 0450 c57b114c 2460c4c1 7b104938 c4417b10 .{.L$`..{.I8.A{. + 0460 4b20c57b 115c2468 c57b1164 2470c441 K .{.\$h.{.d$p.A + 0470 7b105918 c4417b10 6218c57b 11442478 {.Y..A{.b..{.D$x + 0480 6261ff08 117c2410 c4417b10 42206241 ba...|$..A{.B bA + 0490 ff081039 c57b113a c57b107c 24e06261 ...9.{.:.{.|$.ba + 04a0 ff08117a 07c57b11 7a10c57b 107c2410 ...z..{.z..{.|$. + 04b0 6261ff08 107c24f7 c57b117a 18c57b10 ba...|$..{.z..{. + 04c0 7c244062 61ff0811 7208c57b 117a20c5 |$@ba...r..{.z . + 04d0 7b107c24 606261ff 08107424 f2c57b11 {.|$`ba...t$..{. + 04e0 7a286261 ff08116a 09c57b10 7c247862 z(ba...j..{.|$xb + 04f0 61ff0810 6c24f1c5 7b117a30 6261ff08 a...l$..{.z0ba.. + 0500 11520c62 61ff0811 4a0d6261 ff081142 .R.ba...J.ba...B + 0510 0e62e1ff 08116213 62e1ff08 115a1462 .b....b.b....Z.b + 0520 e1ff0811 521562e1 ff08114a 1662e1ff ....R.b....J.b.. + 0530 08114217 4c897a08 6261ff08 11620a62 ..B.L.z.ba...b.b + 0540 61ff0811 5a0b62e1 ff08117a 0f6261ff a...Z.b....z.ba. + 0550 08116a10 62e1ff08 11721162 e1ff0811 ..j.b....r.b.... + 0560 6a126261 ff081172 186261ff 08117a19 j.ba...r.ba...z. + 0570 c57b107c 24e8c5fb 11ba3801 0000c5fb .{.|$.....8..... + 0580 107c24a0 62e1ff08 104c24fe 6261ff08 .|$.b....L$.ba.. + 0590 10442404 62e1ff08 105424ff 6261ff08 .D$.b....T$.ba.. + 05a0 104c2405 c57b11ba d0000000 c57b11a2 .L$..{.......{.. + 05b0 f0000000 c57b107c 2418c57b 106424c0 .....{.|$..{.d$. + 05c0 c57b119a f8000000 c57b1192 20010000 .{.......{.. ... + 05d0 c57b105c 2498c57b 105424c8 c5fb11ba .{.\$..{.T$..... + 05e0 40010000 c5fb107c 2448c57b 11b2e000 @......|$H.{.... + 05f0 0000c57b 11aae800 0000c57b 119a0001 ...{.......{.... + 0600 0000c57b 11a20801 0000c5fb 11b26801 ...{..........h. + 0610 0000c5fb 11aa7001 0000c57b 11bad800 ......p....{.... + 0620 000062e1 ff08114a 226261ff 08114223 ..b....J"ba...B# + 0630 c57b118a 28010000 c57b1182 30010000 .{..(....{..0... + 0640 c57b1192 48010000 62e1ff08 11522a62 .{..H...b....R*b + 0650 61ff0811 4a2bc5fb 11ba6001 0000c5fb a...J+....`..... + 0660 11a27801 0000c5fb 106c24a8 c57b106c ..x......l$..{.l + 0670 24d062e1 ff08101c 246261ff 08105424 $.b.....$ba...T$ + 0680 06c57b10 5c2468c5 7b107424 d862e1ff ..{.\$h.{.t$.b.. + 0690 08106424 0162e1ff 08104424 07c5fb10 ..d$.b....D$.... + 06a0 742458c5 7b106424 706261ff 08107c24 t$X.{.d$pba...|$ + 06b0 10c5fb11 aa800100 00c5fb11 9ab00100 ................ + 06c0 00c5fb10 6c2450c5 fb105c24 b0c57b11 ....l$P...\$..{. + 06d0 aa880100 0062e1ff 08115a32 6261ff08 .....b....Z2ba.. + 06e0 115233c5 fb11aaa0 010000c5 7b119aa8 .R3.........{... + 06f0 010000c5 fb1192b8 010000c5 fb119ac0 ................ + 0700 010000c5 7b11b2c8 01000062 e1ff0811 ....{......b.... + 0710 623a62e1 ff081142 3bc5fb11 b2e00100 b:b....B;....... + 0720 00c57b11 a2e80100 006261ff 08117a3e ..{......ba...z> + 0730 c5fb118a f8010000 4883c608 4983c640 ........H...I..@ + 0740 4983c540 4983c440 4883c540 4883c340 I..@I..@H..@H..@ + 0750 4983c340 4983c240 4983c140 4881c200 I..@I..@I..@H... + 0760 02000048 39fe0f84 d4010000 4839f10f ...H9.......H9.. + 0770 85b3faff ff6241ff 08104e03 62c1ff08 .....bA...N.b... + 0780 10760462 c1ff0810 5605c441 7b106e30 .v.b....V..A{.n0 + 0790 c4c17b10 7e386241 ff081045 0362c1ff ..{.~8bA...E.b.. + 07a0 08106d04 62c1ff08 104d05c4 417b1065 ..m.b....M..A{.e + 07b0 30c4c17b 10753862 c1ff0810 7c240362 0..{.u8b....|$.b + 07c0 c1ff0810 64240462 c1ff0810 442405c4 ....d$.b....D$.. + 07d0 417b105c 2430c4c1 7b106c24 3862e1ff A{.\$0..{.l$8b.. + 07e0 08105d04 c57b107d 28c57b10 5530c5fb ..]..{.}(.{.U0.. + 07f0 106538c5 7b107328 c57b104b 30c5fb10 .e8.{.s(.{.K0... + 0800 5b38c441 7b104330 c4c17b10 5338c4c1 [8.A{.C0..{.S8.. + 0810 7b104a38 6241ff08 10660162 41ff0810 {.J8bA...f.bA... + 0820 5e026241 ff081055 02c5fb11 026261ff ^.bA...U.....ba. + 0830 08116208 c5fb1142 486261ff 08115a10 ..b....BHba...Z. + 0840 6261ff08 115211c5 fb118290 00000062 ba...R.........b + 0850 61ff0811 4a186261 ff081142 1962e1ff a...J.ba...B.b.. + 0860 08117a1a c5fb1182 d8000000 62e1ff08 ..z.........b... + 0870 11722062 e1ff0811 6a2162e1 ff081162 .r b....j!b....b + 0880 2262e1ff 08115a23 c5fb1182 20010000 "b....Z#.... ... + 0890 62e1ff08 11522862 e1ff0811 4a2962e1 b....R(b....J)b. + 08a0 ff081142 2ac57b11 ba580100 00c57b11 ...B*.{..X....{. + 08b0 b2600100 00c5fb11 82680100 00c57b11 .`.......h....{. + 08c0 aa800100 00c57b11 a2880100 00c57b11 ......{.......{. + 08d0 9a900100 00c57b11 92980100 00c57b11 ......{.......{. + 08e0 8aa00100 00c57b11 82a80100 00c5fb11 ......{......... + 08f0 82b00100 00c5fb11 bac00100 00c5fb11 ................ + 0900 b2c80100 00c5fb11 aad00100 00c5fb11 ................ + 0910 a2d80100 00c5fb11 9ae00100 00c5fb11 ................ + 0920 92e80100 00c5fb11 8af00100 00c5fb11 ................ + 0930 82f80100 00e9fefd ffff660f 1f440000 ..........f..D.. + 0940 488b9c24 28010000 4889ce48 89c1488b H..$(...H..H..H. + 0950 94240801 00004c8d 2c19488b 9c241801 .$....L.,.H..$.. + 0960 00004c8d 1c114c8d 2419488b 94240001 ..L...L.$.H..$.. + 0970 0000488b 9c241001 0000488b 8424f800 ..H..$....H..$.. + 0980 0000488d 2c194c8d 1411488b 9c243001 ..H.,.L...H..$0. + 0990 0000488b 94242001 00004801 c84c8d0c ..H..$ ...H..L.. + 09a0 114801cb 4c038424 f0000000 4889fa48 .H..L..$....H..H + 09b0 83bc24c0 00000000 0f84fa01 00004839 ..$...........H9 + 09c0 d60f8479 0500000f 8dc00100 004d8b79 ...y.........M.y + 09d0 18c5fb10 086261ff 08104001 62e1ff08 .....ba...@.b... + 09e0 104002c5 7b104018 6241ff08 107d0062 .@..{.@.bA...}.b + 09f0 c1ff0810 7d01c441 7b107d10 c4c17b10 ....}..A{.}...{. + 0a00 7d186241 ff081034 2462c1ff 08107424 }.bA...4$b....t$ + 0a10 01c4417b 10742410 c4c17b10 74241862 ..A{.t$...{.t$.b + 0a20 61ff0810 6d0062e1 ff08106d 01c57b10 a...m.b....m..{. + 0a30 6d10c5fb 106d1862 61ff0810 2362e1ff m....m.ba...#b.. + 0a40 08106301 c57b1063 10c5fb10 63186241 ..c..{.c....c.bA /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_olnucopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 ca010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830703 97010a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 440b0000 B. B..B..D..D... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 a2120000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05440e30 ...E. ..B.(..D.0 + 0040 8606410e 38830747 0ea00303 19120a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0844 0b000000 D..D.... /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_COOPERLAKE.o (disasm) @@ -9,46 +9,798 @@ push %r14 push %r13 push %r12 + mov %r9,%r12 push %rbp - mov %rdx,%rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %r8,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle + lea offset(,%rcx,8),%rax + mov %rcx,%rbx + shl $something,%rbx + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rdx,%r10 + mov %rbx,offset(%rsp) + lea offset(,%rax,8),%rdx + mov %rcx,%rbx + shl $something,%rax + mov %rax,offset(%rsp) + mov %rbx,%rax + shl $something,%rax + mov %rdx,offset(%rsp) + lea (%rbx,%rbx,4),%rdx + imul $something,%rbx,%rbx + mov %rax,%r15 + mov %rdi,%rax + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) mov %rdi,%rbx - mov %rdi,%r12 - and $something,%ebx - lea offset(,%rcx,8),%r14 + mov %rdi,%rax + sar $something,%rbx + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + imul %r15,%rax shl $something,%rcx - sar %r12 - mov %rbx,%r13 - mov %rcx,%rbx - imul %r12,%rbx - mov %rdx,-offset(%rsp) - lea (%r8,%rsi,2),%rax - mov %r12,%r15 - vmovsd offset(%rip),%xmm4 # - mov %rcx,%rdi - add %rdx,%rbx - lea (%r12,%r12,1),%r10 - shl $something,%r15 - mov %rdx,%r11 - mov %rax,%rbp + shl $something,%rdx + add %r10,%rax + mov %rax,offset(%rsp) + and $something,%edi + lea (%r8,%rsi,8),%rax + mov %rcx,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + mov %r10,%rbp + lea offset(,%rbx,8),%r14 + mov %rbx,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + shl $something,%rbx + mov %rbx,offset(%rsp) + mov %r15,%r9 + mov %rbp,%rbx + mov %r14,%r10 + mov %r8,%rbp + nopw offset(%rax,%rax,1) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%rbx,1),%r14 + mov offset(%rsp),%rax + lea (%rax,%rbx,1),%rdx + mov offset(%rsp),%rax + lea (%rbx,%rax,1),%r15 + mov offset(%rsp),%rax + lea (%rax,%rbx,1),%rsi + mov offset(%rsp),%rax + lea (%rbx,%rax,1),%rdi + mov offset(%rsp),%rax + lea (%rbx,%rax,1),%r11 + mov offset(%rsp),%rax + lea (%rax,%rbx,1),%r8 + jle + mov %rbx,%rcx + mov %r12,%rax + xor %r13d,%r13d + jmp + nopl offset(%rax) + jle + vmovsd offset(%rcx),%xmm7 + vmovsd offset(%rcx),%xmm5 + vmovsd offset(%rcx),%xmm6 + vmovsd offset(%rcx),%xmm4 + vmovsd offset(%rcx),%xmm3 + vmovsd offset(%rcx),%xmm31 + vmovsd offset(%rcx),%xmm30 + vmovsd (%r14),%xmm29 + vmovsd offset(%r14),%xmm28 + vmovsd offset(%r14),%xmm27 + vmovsd offset(%r14),%xmm26 + vmovsd offset(%r14),%xmm25 + vmovsd offset(%r14),%xmm24 + vmovsd offset(%r14),%xmm23 + vmovsd offset(%r14),%xmm22 + vmovsd (%rdx),%xmm21 + vmovsd offset(%rdx),%xmm20 + vmovsd offset(%rdx),%xmm19 + vmovsd offset(%rdx),%xmm18 + vmovsd offset(%rdx),%xmm17 + vmovsd offset(%rdx),%xmm16 + vmovsd offset(%rdx),%xmm15 + vmovsd offset(%rdx),%xmm14 + vmovsd (%r15),%xmm13 + vmovsd offset(%r15),%xmm12 + vmovsd offset(%r15),%xmm11 + vmovsd offset(%r15),%xmm10 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd offset(%r15),%xmm9 + vmovsd offset(%r15),%xmm7 + vmovsd offset(%r15),%xmm8 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rsi),%xmm7 + vmovsd offset(%r15),%xmm6 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rsi),%xmm7 + vmovsd (%rsi),%xmm5 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rsi),%xmm7 + vmovsd offset(%rsi),%xmm4 + vmovsd %xmm7,-offset(%rsp) + vmovsd (%rdi),%xmm7 + vmovsd offset(%rsi),%xmm3 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd offset(%rsi),%xmm2 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd offset(%rsi),%xmm1 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd (%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd (%r8),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r8),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r8),%xmm7 + vmovsd %xmm7,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_COOPERLAKE.o (objdump) @@ -2,36 +2,338 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 554889d5 53488974 AWAVAUATUH..SH.t - 0010 24d848d1 fe48897c 24f04889 4c24f84c $.H..H.|$.H.L$.L - 0020 894424d0 48897424 e04885f6 0f8e3e01 .D$.H.t$.H....>. - 0030 00004889 fb4989fc 83e3014c 8d34cd00 ..H..I.....L.4.. - 0040 00000048 c1e10449 d1fc4989 dd4889cb ...H...I..I..H.. - 0050 490fafdc 48895424 e8498d04 704d89e7 I...H.T$.I..pM.. - 0060 c5fb1025 00000000 4889cf48 01d34f8d ...%....H..H..O. - 0070 142449c1 e7054989 d34889c5 0f1f4000 .$I...I..H....@. - 0080 4b8d3433 4d85e40f 8e730100 004c89d9 K.43M....s...L.. - 0090 4c89c831 d2eb4366 0f1f8400 00000000 L..1..Cf........ - 00a0 7d25c5fb 1019c5fb 105108c5 fb100ec5 }%.......Q...... - 00b0 fb104608 c5fb1118 c5fb1150 08c5fb11 ..F........P.... - 00c0 4810c5fb 11401848 83c20248 01f94801 H....@.H...H..H. - 00d0 fe4883c0 204c39d2 742e4c39 c275c1c5 .H.. L9.t.L9.u.. - 00e0 fb104608 c5fb1049 08c5db5e c0c5db5e ..F....I...^...^ - 00f0 11c5fb11 4808c5fb 1110c5fb 114018eb ....H........@.. - 0100 c60f1f80 00000000 4889d84d 01f94c89 ........H..M..L. - 0110 d24d85ed 74234c39 c20f84c1 0000007d .M..t#L9.......} - 0120 14c5fb10 08c5fb10 4008c4c1 7b1109c4 ........@...{... - 0130 c17b1141 084983c1 104983c0 024983c3 .{.A.I...I...I.. - 0140 104883c3 104939e8 0f8532ff ffff488b .H...I9...2...H. - 0150 5c24e048 8b6c24e8 4889d848 c1e00448 \$.H.l$.H..H...H - 0160 01c5488b 4424d048 8d045848 894424d0 ..H.D$.H..XH.D$. - 0170 f64424d8 01745c48 8b4c24f0 4885c97e .D$..t\H.L$.H..~ - 0180 52488b54 24f8c5fb 100d0000 0000488b RH.T$.........H. - 0190 7424d048 c1e20331 c0eb1d0f 1f440000 t$.H...1.....D.. - 01a0 7d0bc5fb 104500c4 c17b1104 c148ffc0 }....E...{...H.. - 01b0 4801d548 39c1741b 4839f075 e3c5f35e H..H9.t.H9.u...^ - 01c0 4500c4c1 7b1104c1 48ffc048 01d54839 E...{...H..H..H9 - 01d0 c175e55b 5d415c41 5d415e31 c0415fc3 .u.[]A\A]A^1.A_. - 01e0 c5fb1040 08c5db5e 08c4c17b 114108c4 ...@...^...{.A.. - 01f0 c17b1109 e93cffff ff0f1f80 00000000 .{...<.......... - 0200 4c89d831 d2e907ff ffff L..1...... + 0000 41574156 41554154 4d89cc55 534881ec AWAVAUATM..USH.. + 0010 30010000 4889b424 10010000 48c1fe03 0...H..$....H... + 0020 4889bc24 18010000 48899424 08010000 H..$....H..$.... + 0030 48898c24 20010000 4c898424 00010000 H..$ ...L..$.... + 0040 4889b424 28010000 4885f60f 8eb30c00 H..$(...H....... + 0050 00488d04 cd000000 004889cb 48c1e304 .H.......H..H... + 0060 48898424 90000000 488d0449 4989d248 H..$....H..II..H + 0070 899c24a0 00000048 8d14c500 00000048 ..$....H.......H + 0080 89cb48c1 e0044889 8424f000 00004889 ..H...H..$....H. + 0090 d848c1e0 06488994 24e00000 00488d14 .H...H..$....H.. + 00a0 9b486bdb 384989c7 4889f883 e0044889 .Hk.8I..H.....H. + 00b0 9c24b000 00004889 8424c800 00004889 .$....H..$....H. + 00c0 fb4889f8 48c1fb03 83e00248 898424d0 .H..H......H..$. + 00d0 00000048 89d8490f afc748c1 e10548c1 ...H..I...H...H. + 00e0 e2034c01 d0488984 24980000 0083e701 ..L..H..$....... + 00f0 498d04f0 48898c24 a8000000 48899424 I...H..$....H..$ + 0100 e8000000 4889bc24 d8000000 48898424 ....H..$....H..$ + 0110 b8000000 4c89d54c 8d34dd00 00000048 ....L..L.4.....H + 0120 899c24c0 000000c5 fb100500 00000048 ..$............H + 0130 c1e30948 899c24f8 0000004d 89f94889 ...H..$....M..H. + 0140 eb4d89f2 4c89c566 0f1f8400 00000000 .M..L..f........ + 0150 488b8424 90000000 4883bc24 c0000000 H..$....H..$.... + 0160 004c8d34 18488b84 24a00000 00488d14 .L.4.H..$....H.. + 0170 18488b84 24e00000 004c8d3c 03488b84 .H..$....L.<.H.. + 0180 24a80000 00488d34 18488b84 24e80000 $....H.4.H..$... + 0190 00488d3c 03488b84 24f00000 004c8d1c .H.<.H..$....L.. + 01a0 03488b84 24b00000 004c8d04 180f8e45 .H..$....L.....E + 01b0 12000048 89d94c89 e04531ed e91b0500 ...H..L..E1..... + 01c0 000f1f80 00000000 0f8ee304 0000c5fb ................ + 01d0 107908c5 fb106910 c5fb1071 18c5fb10 .y....i....q.... + 01e0 6120c5fb 10592862 61ff0810 79066261 a ...Y(ba...y.ba + 01f0 ff081071 076241ff 08102e62 41ff0810 ...q.bA....bA... + 0200 66016241 ff08105e 026241ff 08105603 f.bA...^.bA...V. + 0210 6241ff08 104e0462 41ff0810 460562c1 bA...N.bA...F.b. + 0220 ff08107e 0662c1ff 08107607 62e1ff08 ...~.b....v.b... + 0230 102a62e1 ff081062 0162e1ff 08105a02 .*b....b.b....Z. + 0240 62e1ff08 10520362 e1ff0810 4a0462e1 b....R.b....J.b. + 0250 ff081042 05c57b10 7a30c57b 107238c4 ...B..{.z0.{.r8. + 0260 417b102f c4417b10 6708c441 7b105f10 A{./.A{.g..A{._. + 0270 c4417b10 5718c5fb 117c2488 c5fb116c .A{.W....|$....l + 0280 2490c5fb 11742498 c5fb1164 24a0c5fb $....t$....d$... + 0290 115c24a8 c4417b10 4f20c4c1 7b107f30 .\$..A{.O ..{..0 + 02a0 c4417b10 4728c5fb 117c24b0 c5fb107e .A{.G(...|$....~ + 02b0 28c4c17b 107738c5 fb117c24 b8c5fb10 (..{.w8...|$.... + 02c0 7e30c5fb 102ec5fb 117c24c0 c5fb107e ~0.......|$....~ + 02d0 38c5fb10 6608c5fb 117c24c8 c5fb103f 8...f....|$....? + 02e0 c5fb105e 10c5fb11 7c24d0c5 fb107f08 ...^....|$...... + 02f0 c5fb1056 18c5fb11 7c24d8c5 fb107f10 ...V....|$...... + 0300 c5fb104e 20c5fb11 7c24e0c5 fb107f18 ...N ...|$...... + 0310 c5fb117c 24e8c5fb 107f20c5 fb117c24 ...|$..... ...|$ + 0320 f0c5fb10 7f28c5fb 117c24f8 c5fb107f .....(...|$..... + 0330 30c5fb11 3c24c5fb 107f38c5 fb117c24 0...<$....8...|$ + 0340 08c4c17b 103bc5fb 117c2410 c4c17b10 ...{.;...|$...{. + 0350 7b08c5fb 117c2418 c4c17b10 7b10c5fb {....|$...{.{... + 0360 117c2420 c4c17b10 7b18c5fb 117c2428 .|$ ..{.{....|$( + 0370 c4c17b10 7b20c5fb 117c2430 c4c17b10 ..{.{ ...|$0..{. + 0380 7b28c5fb 117c2438 c4c17b10 7b30c5fb {(...|$8..{.{0.. + 0390 117c2440 c4c17b10 7b38c5fb 117c2448 .|$@..{.{8...|$H + 03a0 c4c17b10 38c5fb11 7c2450c4 c17b1078 ..{.8...|$P..{.x + 03b0 08c5fb11 7c2458c4 c17b1078 10c5fb11 ....|$X..{.x.... + 03c0 7c2460c4 c17b1078 18c5fb11 7c2468c4 |$`..{.x....|$h. + 03d0 c17b1078 20c5fb11 7c2470c4 c17b1078 .{.x ...|$p..{.x + 03e0 28c5fb11 7c2478c4 c17b1078 30c5fb11 (...|$x..{.x0... + 03f0 bc248000 0000c4c1 7b107838 c5fb11bc .$......{.x8.... + 0400 24880000 00c5fb10 396261ff 08117806 $.......9ba...x. + 0410 c5fb1138 c5fb107c 24886261 ff081170 ...8...|$.ba...p + 0420 07c5fb11 7808c5fb 107c2490 6261ff08 ....x....|$.ba.. + 0430 116808c5 fb117810 c5fb107c 24986261 .h....x....|$.ba + 0440 ff081160 09c5fb11 7818c5fb 107c24a0 ...`....x....|$. + 0450 6261ff08 11580ac5 fb117820 c5fb107c ba...X....x ...| + 0460 24a86261 ff081150 0bc5fb11 78286261 $.ba...P....x(ba + 0470 ff081148 0c6261ff 0811400d 62e1ff08 ...H.ba...@.b... + 0480 11780e62 e1ff0811 700f62e1 ff081168 .x.b....p.b....h + 0490 1062e1ff 08116011 62e1ff08 11581262 .b....`.b....X.b + 04a0 e1ff0811 501362e1 ff081148 1462e1ff ....P.b....H.b.. + 04b0 08114015 c57b11b8 b0000000 c57b11b0 ..@..{.......{.. + 04c0 b8000000 c57b11a8 c0000000 c57b11a0 .....{.......{.. + 04d0 c8000000 c57b1198 d0000000 c5fb107c .....{.........| + 04e0 24b0c57b 1190d800 0000c5fb 11b8f000 $..{............ + 04f0 0000c5fb 107c24b8 c57b1188 e0000000 .....|$..{...... + 0500 c5fb11b8 28010000 c5fb107c 24c0c57b ....(......|$..{ + 0510 1180e800 0000c5fb 11b83001 0000c5fb ..........0..... + 0520 107c24c8 c5fb11b0 f8000000 c5fb11b8 .|$............. + 0530 38010000 c5fb107c 24d0c5fb 11a80001 8......|$....... + 0540 0000c5fb 11b84001 0000c5fb 107c24d8 ......@......|$. + 0550 c5fb11a0 08010000 c5fb11b8 48010000 ............H... + 0560 c5fb107c 24e0c5fb 11981001 0000c5fb ...|$........... + 0570 11b85001 0000c5fb 107c24e8 c5fb1190 ..P......|$..... + 0580 18010000 c5fb11b8 58010000 c5fb107c ........X......| + 0590 24f0c5fb 11882001 0000c5fb 11b86001 $..... .......`. + 05a0 0000c5fb 107c24f8 c5fb11b8 68010000 .....|$.....h... + 05b0 c5fb103c 24c5fb11 b8700100 00c5fb10 ...<$....p...... + 05c0 7c2408c5 fb11b878 010000c5 fb107c24 |$.....x......|$ + 05d0 10c5fb11 b8800100 00c5fb10 7c2418c5 ............|$.. + 05e0 fb11b888 010000c5 fb107c24 20c5fb11 ..........|$ ... + 05f0 b8900100 00c5fb10 7c2428c5 fb11b898 ........|$(..... + 0600 010000c5 fb107c24 30c5fb11 b8a00100 ......|$0....... + 0610 00c5fb10 7c2438c5 fb11b8a8 010000c5 ....|$8......... + 0620 fb107c24 40c5fb11 b8b00100 00c5fb10 ..|$@........... + 0630 7c2448c5 fb11b8b8 010000c5 fb107c24 |$H...........|$ + 0640 50c5fb11 b8c00100 00c5fb10 7c2458c5 P...........|$X. + 0650 fb11b8c8 010000c5 fb107c24 60c5fb11 ..........|$`... + 0660 b8d00100 00c5fb10 7c2468c5 fb11b8d8 ........|$h..... + 0670 010000c5 fb107c24 70c5fb11 b8e00100 ......|$p....... + 0680 00c5fb10 7c2478c5 fb11b8e8 010000c5 ....|$x......... + 0690 fb10bc24 80000000 c5fb11b8 f0010000 ...$............ + 06a0 c5fb10bc 24880000 00c5fb11 b8f80100 ....$........... + 06b0 004983c5 084c01c9 4d01ce4c 01ca4d01 .I...L..M..L..M. + 06c0 cf4c01ce 4c01cf4d 01cb4d01 c8480500 .L..L..M..M..H.. + 06d0 0200004d 39ea0f84 34020000 4c39ed0f ...M9...4...L9.. + 06e0 85e3faff ffc4c17b 107608c5 fb106a10 .......{.v....j. + 06f0 c5fb5ef6 c4c17b10 6718c5fb 107e20c5 ..^...{.g....~ . + 0700 7b104f28 c5fb1059 08c5fb10 5110c5fb {.O(...Y....Q... + 0710 10491862 61ff0810 79046261 ff081071 .I.ba...y.ba...q + 0720 056261ff 08106906 6261ff08 10610762 .ba...i.ba...a.b + 0730 41ff0810 5e026241 ff081056 036241ff A...^.bA...V.bA. + 0740 08104e04 6241ff08 10460562 c1ff0810 ..N.bA...F.b.... + 0750 7e0662c1 ff081076 0762e1ff 08106a03 ~.b....v.b....j. + 0760 62e1ff08 10620462 e1ff0810 5a05c5fb b....b.b....Z... + 0770 5eed62e1 ff081052 0662e1ff 08104a07 ^.b....R.b....J. + 0780 62c1ff08 104704c4 417b107f 28c4417b b....G..A{..(.A{ + 0790 107730c4 417b106f 38c57b10 6628c57b .w0.A{.o8.{.f(.{ + 07a0 105e30c5 7b105638 c5fb1164 2488c5fb .^0.{.V8...d$... + 07b0 117c2490 c57b114c 2498c4c1 7b107b30 .|$..{.L$...{.{0 + 07c0 c4c17b10 6038c57b 104f30c5 7b104738 ..{.`8.{.O0.{.G8 + 07d0 c5fb117c 24a0c4c1 7b107b38 c5fb1164 ...|$...{.{8...d + 07e0 24a8c5fb 5e21c5fb 115808c5 fb1120c5 $...^!...X.... . + 07f0 fb115010 c5fb1148 18c5fb5e 64248862 ..P....H...^d$.b + 0800 61ff0811 78046261 ff081170 056261ff a...x.ba...p.ba. + 0810 08116806 6261ff08 116007c5 fb117048 ..h.ba...`....pH + 0820 6261ff08 11580a62 61ff0811 500b6261 ba...X.ba...P.ba + 0830 ff081148 0c6261ff 0811400d 62e1ff08 ...H.ba...@.b... + 0840 11780e62 e1ff0811 700fc5fb 11a89000 .x.b....p....... + 0850 000062e1 ff081168 1362e1ff 08116014 ..b....h.b....`. + 0860 62e1ff08 11581562 e1ff0811 501662e1 b....X.b....P.b. + 0870 ff081148 17c5fb11 a0d80000 0062e1ff ...H.........b.. + 0880 0811401c c57b11b8 e8000000 c5fb5e4c ..@..{........^L + 0890 24a0c5fb 5e5c2490 c5fb1188 b0010000 $...^\$......... + 08a0 c5fb5e54 2498c5fb 5e4c24a8 c57b11b0 ..^T$...^L$..{.. + 08b0 f0000000 c57b11a8 f8000000 c5fb1198 .....{.......... + 08c0 20010000 c57b11a0 28010000 c57b1198 ....{..(....{.. + 08d0 30010000 c57b1190 38010000 c5fb1190 0....{..8....... + 08e0 68010000 c57b1188 70010000 c57b1180 h....{..p....{.. + 08f0 78010000 c5fb11b8 b8010000 c5fb1188 x............... + 0900 f8010000 e9a8fdff ff0f1f80 00000000 ................ + 0910 488bbc24 90000000 488bb424 98000000 H..$....H..$.... + 0920 4989fe49 01f64a8d 14374889 f04c8d3c I..I..J..7H..L.< + 0930 174c03a4 24f80000 004883bc 24c80000 .L..$....H..$... + 0940 00000f84 04020000 4c39ed0f 84670600 ........L9...g.. + 0950 000f8edc 01000049 8b7f38c5 fb100862 .......I..8....b + 0960 61ff0810 78016261 ff081070 026261ff a...x.ba...p.ba. + 0970 08106803 6261ff08 10600462 61ff0810 ..h.ba...`.ba... + 0980 58056261 ff081050 066261ff 08104807 X.ba...P.ba...H. + 0990 6241ff08 100662c1 ff08107e 0162c1ff bA....b....~.b.. + 09a0 08107602 62c1ff08 106e0362 c1ff0810 ..v.b....n.b.... + 09b0 660462c1 ff08105e 0562c1ff 08105606 f.b....^.b....V. + 09c0 62c1ff08 104e0762 e1ff0810 02c57b10 b....N.b......{. + 09d0 7a08c57b 107210c5 7b106a18 c57b1062 z..{.r..{.j..{.b + 09e0 20c57b10 5a28c57b 105230c5 7b104a38 .{.Z(.{.R0.{.J8 + 09f0 c4417b10 07c4c17b 107f08c4 c17b1077 .A{....{.....{.w + 0a00 10c4c17b 106f18c4 c17b1067 20c4c17b ...{.o...{.g ..{ /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 0a020000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606440e 38830703 c7010a0e 30410e28 ..D.8.......0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 e6140000 00420e10 8f02420e .........B....B. + 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 + 0040 8606410e 38830747 0ee80203 d4130a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0844 0b000000 D..D.... /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_SKYLAKEX.o (disasm) @@ -9,46 +9,798 @@ push %r14 push %r13 push %r12 + mov %r9,%r12 push %rbp - mov %rdx,%rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %r8,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle + lea offset(,%rcx,8),%rax + mov %rcx,%rbx + shl $something,%rbx + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rdx,%r10 + mov %rbx,offset(%rsp) + lea offset(,%rax,8),%rdx + mov %rcx,%rbx + shl $something,%rax + mov %rax,offset(%rsp) + mov %rbx,%rax + shl $something,%rax + mov %rdx,offset(%rsp) + lea (%rbx,%rbx,4),%rdx + imul $something,%rbx,%rbx + mov %rax,%r15 + mov %rdi,%rax + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) mov %rdi,%rbx - mov %rdi,%r12 - and $something,%ebx - lea offset(,%rcx,8),%r14 + mov %rdi,%rax + sar $something,%rbx + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + imul %r15,%rax shl $something,%rcx - sar %r12 - mov %rbx,%r13 - mov %rcx,%rbx - imul %r12,%rbx - mov %rdx,-offset(%rsp) - lea (%r8,%rsi,2),%rax - mov %r12,%r15 - vmovsd offset(%rip),%xmm4 # - mov %rcx,%rdi - add %rdx,%rbx - lea (%r12,%r12,1),%r10 - shl $something,%r15 - mov %rdx,%r11 - mov %rax,%rbp + shl $something,%rdx + add %r10,%rax + mov %rax,offset(%rsp) + and $something,%edi + lea (%r8,%rsi,8),%rax + mov %rcx,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + mov %r10,%rbp + lea offset(,%rbx,8),%r14 + mov %rbx,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + shl $something,%rbx + mov %rbx,offset(%rsp) + mov %r15,%r9 + mov %rbp,%rbx + mov %r14,%r10 + mov %r8,%rbp + nopw offset(%rax,%rax,1) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%rbx,1),%r14 + mov offset(%rsp),%rax + lea (%rax,%rbx,1),%rdx + mov offset(%rsp),%rax + lea (%rbx,%rax,1),%r15 + mov offset(%rsp),%rax + lea (%rax,%rbx,1),%rsi + mov offset(%rsp),%rax + lea (%rbx,%rax,1),%rdi + mov offset(%rsp),%rax + lea (%rbx,%rax,1),%r11 + mov offset(%rsp),%rax + lea (%rax,%rbx,1),%r8 + jle + mov %rbx,%rcx + mov %r12,%rax + xor %r13d,%r13d + jmp + nopl offset(%rax) + jle + vmovsd offset(%rcx),%xmm7 + vmovsd offset(%rcx),%xmm5 + vmovsd offset(%rcx),%xmm6 + vmovsd offset(%rcx),%xmm4 + vmovsd offset(%rcx),%xmm3 + vmovsd offset(%rcx),%xmm31 + vmovsd offset(%rcx),%xmm30 + vmovsd (%r14),%xmm29 + vmovsd offset(%r14),%xmm28 + vmovsd offset(%r14),%xmm27 + vmovsd offset(%r14),%xmm26 + vmovsd offset(%r14),%xmm25 + vmovsd offset(%r14),%xmm24 + vmovsd offset(%r14),%xmm23 + vmovsd offset(%r14),%xmm22 + vmovsd (%rdx),%xmm21 + vmovsd offset(%rdx),%xmm20 + vmovsd offset(%rdx),%xmm19 + vmovsd offset(%rdx),%xmm18 + vmovsd offset(%rdx),%xmm17 + vmovsd offset(%rdx),%xmm16 + vmovsd offset(%rdx),%xmm15 + vmovsd offset(%rdx),%xmm14 + vmovsd (%r15),%xmm13 + vmovsd offset(%r15),%xmm12 + vmovsd offset(%r15),%xmm11 + vmovsd offset(%r15),%xmm10 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd offset(%r15),%xmm9 + vmovsd offset(%r15),%xmm7 + vmovsd offset(%r15),%xmm8 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rsi),%xmm7 + vmovsd offset(%r15),%xmm6 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rsi),%xmm7 + vmovsd (%rsi),%xmm5 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rsi),%xmm7 + vmovsd offset(%rsi),%xmm4 + vmovsd %xmm7,-offset(%rsp) + vmovsd (%rdi),%xmm7 + vmovsd offset(%rsi),%xmm3 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd offset(%rsi),%xmm2 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd offset(%rsi),%xmm1 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd (%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r11),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd (%r8),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r8),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r8),%xmm7 + vmovsd %xmm7,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_SKYLAKEX.o (objdump) @@ -2,36 +2,338 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 554889d5 53488974 AWAVAUATUH..SH.t - 0010 24d848d1 fe48897c 24f04889 4c24f84c $.H..H.|$.H.L$.L - 0020 894424d0 48897424 e04885f6 0f8e3e01 .D$.H.t$.H....>. - 0030 00004889 fb4989fc 83e3014c 8d34cd00 ..H..I.....L.4.. - 0040 00000048 c1e10449 d1fc4989 dd4889cb ...H...I..I..H.. - 0050 490fafdc 48895424 e8498d04 704d89e7 I...H.T$.I..pM.. - 0060 c5fb1025 00000000 4889cf48 01d34f8d ...%....H..H..O. - 0070 142449c1 e7054989 d34889c5 0f1f4000 .$I...I..H....@. - 0080 4b8d3433 4d85e40f 8e730100 004c89d9 K.43M....s...L.. - 0090 4c89c831 d2eb4366 0f1f8400 00000000 L..1..Cf........ - 00a0 7d25c5fb 1019c5fb 105108c5 fb100ec5 }%.......Q...... - 00b0 fb104608 c5fb1118 c5fb1150 08c5fb11 ..F........P.... - 00c0 4810c5fb 11401848 83c20248 01f94801 H....@.H...H..H. - 00d0 fe4883c0 204c39d2 742e4c39 c275c1c5 .H.. L9.t.L9.u.. - 00e0 fb104608 c5fb1049 08c5db5e c0c5db5e ..F....I...^...^ - 00f0 11c5fb11 4808c5fb 1110c5fb 114018eb ....H........@.. - 0100 c60f1f80 00000000 4889d84d 01f94c89 ........H..M..L. - 0110 d24d85ed 74234c39 c20f84c1 0000007d .M..t#L9.......} - 0120 14c5fb10 08c5fb10 4008c4c1 7b1109c4 ........@...{... - 0130 c17b1141 084983c1 104983c0 024983c3 .{.A.I...I...I.. - 0140 104883c3 104939e8 0f8532ff ffff488b .H...I9...2...H. - 0150 5c24e048 8b6c24e8 4889d848 c1e00448 \$.H.l$.H..H...H - 0160 01c5488b 4424d048 8d045848 894424d0 ..H.D$.H..XH.D$. - 0170 f64424d8 01745c48 8b4c24f0 4885c97e .D$..t\H.L$.H..~ - 0180 52488b54 24f8c5fb 100d0000 0000488b RH.T$.........H. - 0190 7424d048 c1e20331 c0eb1d0f 1f440000 t$.H...1.....D.. - 01a0 7d0bc5fb 104500c4 c17b1104 c148ffc0 }....E...{...H.. - 01b0 4801d548 39c1741b 4839f075 e3c5f35e H..H9.t.H9.u...^ - 01c0 4500c4c1 7b1104c1 48ffc048 01d54839 E...{...H..H..H9 - 01d0 c175e55b 5d415c41 5d415e31 c0415fc3 .u.[]A\A]A^1.A_. - 01e0 c5fb1040 08c5db5e 08c4c17b 114108c4 ...@...^...{.A.. - 01f0 c17b1109 e93cffff ff0f1f80 00000000 .{...<.......... - 0200 4c89d831 d2e907ff ffff L..1...... + 0000 41574156 41554154 4d89cc55 534881ec AWAVAUATM..USH.. + 0010 30010000 4889b424 10010000 48c1fe03 0...H..$....H... + 0020 4889bc24 18010000 48899424 08010000 H..$....H..$.... + 0030 48898c24 20010000 4c898424 00010000 H..$ ...L..$.... + 0040 4889b424 28010000 4885f60f 8eb30c00 H..$(...H....... + 0050 00488d04 cd000000 004889cb 48c1e304 .H.......H..H... + 0060 48898424 90000000 488d0449 4989d248 H..$....H..II..H + 0070 899c24a0 00000048 8d14c500 00000048 ..$....H.......H + 0080 89cb48c1 e0044889 8424f000 00004889 ..H...H..$....H. + 0090 d848c1e0 06488994 24e00000 00488d14 .H...H..$....H.. + 00a0 9b486bdb 384989c7 4889f883 e0044889 .Hk.8I..H.....H. + 00b0 9c24b000 00004889 8424c800 00004889 .$....H..$....H. + 00c0 fb4889f8 48c1fb03 83e00248 898424d0 .H..H......H..$. + 00d0 00000048 89d8490f afc748c1 e10548c1 ...H..I...H...H. + 00e0 e2034c01 d0488984 24980000 0083e701 ..L..H..$....... + 00f0 498d04f0 48898c24 a8000000 48899424 I...H..$....H..$ + 0100 e8000000 4889bc24 d8000000 48898424 ....H..$....H..$ + 0110 b8000000 4c89d54c 8d34dd00 00000048 ....L..L.4.....H + 0120 899c24c0 000000c5 fb100500 00000048 ..$............H + 0130 c1e30948 899c24f8 0000004d 89f94889 ...H..$....M..H. + 0140 eb4d89f2 4c89c566 0f1f8400 00000000 .M..L..f........ + 0150 488b8424 90000000 4883bc24 c0000000 H..$....H..$.... + 0160 004c8d34 18488b84 24a00000 00488d14 .L.4.H..$....H.. + 0170 18488b84 24e00000 004c8d3c 03488b84 .H..$....L.<.H.. + 0180 24a80000 00488d34 18488b84 24e80000 $....H.4.H..$... + 0190 00488d3c 03488b84 24f00000 004c8d1c .H.<.H..$....L.. + 01a0 03488b84 24b00000 004c8d04 180f8e45 .H..$....L.....E + 01b0 12000048 89d94c89 e04531ed e91b0500 ...H..L..E1..... + 01c0 000f1f80 00000000 0f8ee304 0000c5fb ................ + 01d0 107908c5 fb106910 c5fb1071 18c5fb10 .y....i....q.... + 01e0 6120c5fb 10592862 61ff0810 79066261 a ...Y(ba...y.ba + 01f0 ff081071 076241ff 08102e62 41ff0810 ...q.bA....bA... + 0200 66016241 ff08105e 026241ff 08105603 f.bA...^.bA...V. + 0210 6241ff08 104e0462 41ff0810 460562c1 bA...N.bA...F.b. + 0220 ff08107e 0662c1ff 08107607 62e1ff08 ...~.b....v.b... + 0230 102a62e1 ff081062 0162e1ff 08105a02 .*b....b.b....Z. + 0240 62e1ff08 10520362 e1ff0810 4a0462e1 b....R.b....J.b. + 0250 ff081042 05c57b10 7a30c57b 107238c4 ...B..{.z0.{.r8. + 0260 417b102f c4417b10 6708c441 7b105f10 A{./.A{.g..A{._. + 0270 c4417b10 5718c5fb 117c2488 c5fb116c .A{.W....|$....l + 0280 2490c5fb 11742498 c5fb1164 24a0c5fb $....t$....d$... + 0290 115c24a8 c4417b10 4f20c4c1 7b107f30 .\$..A{.O ..{..0 + 02a0 c4417b10 4728c5fb 117c24b0 c5fb107e .A{.G(...|$....~ + 02b0 28c4c17b 107738c5 fb117c24 b8c5fb10 (..{.w8...|$.... + 02c0 7e30c5fb 102ec5fb 117c24c0 c5fb107e ~0.......|$....~ + 02d0 38c5fb10 6608c5fb 117c24c8 c5fb103f 8...f....|$....? + 02e0 c5fb105e 10c5fb11 7c24d0c5 fb107f08 ...^....|$...... + 02f0 c5fb1056 18c5fb11 7c24d8c5 fb107f10 ...V....|$...... + 0300 c5fb104e 20c5fb11 7c24e0c5 fb107f18 ...N ...|$...... + 0310 c5fb117c 24e8c5fb 107f20c5 fb117c24 ...|$..... ...|$ + 0320 f0c5fb10 7f28c5fb 117c24f8 c5fb107f .....(...|$..... + 0330 30c5fb11 3c24c5fb 107f38c5 fb117c24 0...<$....8...|$ + 0340 08c4c17b 103bc5fb 117c2410 c4c17b10 ...{.;...|$...{. + 0350 7b08c5fb 117c2418 c4c17b10 7b10c5fb {....|$...{.{... + 0360 117c2420 c4c17b10 7b18c5fb 117c2428 .|$ ..{.{....|$( + 0370 c4c17b10 7b20c5fb 117c2430 c4c17b10 ..{.{ ...|$0..{. + 0380 7b28c5fb 117c2438 c4c17b10 7b30c5fb {(...|$8..{.{0.. + 0390 117c2440 c4c17b10 7b38c5fb 117c2448 .|$@..{.{8...|$H + 03a0 c4c17b10 38c5fb11 7c2450c4 c17b1078 ..{.8...|$P..{.x + 03b0 08c5fb11 7c2458c4 c17b1078 10c5fb11 ....|$X..{.x.... + 03c0 7c2460c4 c17b1078 18c5fb11 7c2468c4 |$`..{.x....|$h. + 03d0 c17b1078 20c5fb11 7c2470c4 c17b1078 .{.x ...|$p..{.x + 03e0 28c5fb11 7c2478c4 c17b1078 30c5fb11 (...|$x..{.x0... + 03f0 bc248000 0000c4c1 7b107838 c5fb11bc .$......{.x8.... + 0400 24880000 00c5fb10 396261ff 08117806 $.......9ba...x. + 0410 c5fb1138 c5fb107c 24886261 ff081170 ...8...|$.ba...p + 0420 07c5fb11 7808c5fb 107c2490 6261ff08 ....x....|$.ba.. + 0430 116808c5 fb117810 c5fb107c 24986261 .h....x....|$.ba + 0440 ff081160 09c5fb11 7818c5fb 107c24a0 ...`....x....|$. + 0450 6261ff08 11580ac5 fb117820 c5fb107c ba...X....x ...| + 0460 24a86261 ff081150 0bc5fb11 78286261 $.ba...P....x(ba + 0470 ff081148 0c6261ff 0811400d 62e1ff08 ...H.ba...@.b... + 0480 11780e62 e1ff0811 700f62e1 ff081168 .x.b....p.b....h + 0490 1062e1ff 08116011 62e1ff08 11581262 .b....`.b....X.b + 04a0 e1ff0811 501362e1 ff081148 1462e1ff ....P.b....H.b.. + 04b0 08114015 c57b11b8 b0000000 c57b11b0 ..@..{.......{.. + 04c0 b8000000 c57b11a8 c0000000 c57b11a0 .....{.......{.. + 04d0 c8000000 c57b1198 d0000000 c5fb107c .....{.........| + 04e0 24b0c57b 1190d800 0000c5fb 11b8f000 $..{............ + 04f0 0000c5fb 107c24b8 c57b1188 e0000000 .....|$..{...... + 0500 c5fb11b8 28010000 c5fb107c 24c0c57b ....(......|$..{ + 0510 1180e800 0000c5fb 11b83001 0000c5fb ..........0..... + 0520 107c24c8 c5fb11b0 f8000000 c5fb11b8 .|$............. + 0530 38010000 c5fb107c 24d0c5fb 11a80001 8......|$....... + 0540 0000c5fb 11b84001 0000c5fb 107c24d8 ......@......|$. + 0550 c5fb11a0 08010000 c5fb11b8 48010000 ............H... + 0560 c5fb107c 24e0c5fb 11981001 0000c5fb ...|$........... + 0570 11b85001 0000c5fb 107c24e8 c5fb1190 ..P......|$..... + 0580 18010000 c5fb11b8 58010000 c5fb107c ........X......| + 0590 24f0c5fb 11882001 0000c5fb 11b86001 $..... .......`. + 05a0 0000c5fb 107c24f8 c5fb11b8 68010000 .....|$.....h... + 05b0 c5fb103c 24c5fb11 b8700100 00c5fb10 ...<$....p...... + 05c0 7c2408c5 fb11b878 010000c5 fb107c24 |$.....x......|$ + 05d0 10c5fb11 b8800100 00c5fb10 7c2418c5 ............|$.. + 05e0 fb11b888 010000c5 fb107c24 20c5fb11 ..........|$ ... + 05f0 b8900100 00c5fb10 7c2428c5 fb11b898 ........|$(..... + 0600 010000c5 fb107c24 30c5fb11 b8a00100 ......|$0....... + 0610 00c5fb10 7c2438c5 fb11b8a8 010000c5 ....|$8......... + 0620 fb107c24 40c5fb11 b8b00100 00c5fb10 ..|$@........... + 0630 7c2448c5 fb11b8b8 010000c5 fb107c24 |$H...........|$ + 0640 50c5fb11 b8c00100 00c5fb10 7c2458c5 P...........|$X. + 0650 fb11b8c8 010000c5 fb107c24 60c5fb11 ..........|$`... + 0660 b8d00100 00c5fb10 7c2468c5 fb11b8d8 ........|$h..... + 0670 010000c5 fb107c24 70c5fb11 b8e00100 ......|$p....... + 0680 00c5fb10 7c2478c5 fb11b8e8 010000c5 ....|$x......... + 0690 fb10bc24 80000000 c5fb11b8 f0010000 ...$............ + 06a0 c5fb10bc 24880000 00c5fb11 b8f80100 ....$........... + 06b0 004983c5 084c01c9 4d01ce4c 01ca4d01 .I...L..M..L..M. + 06c0 cf4c01ce 4c01cf4d 01cb4d01 c8480500 .L..L..M..M..H.. + 06d0 0200004d 39ea0f84 34020000 4c39ed0f ...M9...4...L9.. + 06e0 85e3faff ffc4c17b 107608c5 fb106a10 .......{.v....j. + 06f0 c5fb5ef6 c4c17b10 6718c5fb 107e20c5 ..^...{.g....~ . + 0700 7b104f28 c5fb1059 08c5fb10 5110c5fb {.O(...Y....Q... + 0710 10491862 61ff0810 79046261 ff081071 .I.ba...y.ba...q + 0720 056261ff 08106906 6261ff08 10610762 .ba...i.ba...a.b + 0730 41ff0810 5e026241 ff081056 036241ff A...^.bA...V.bA. + 0740 08104e04 6241ff08 10460562 c1ff0810 ..N.bA...F.b.... + 0750 7e0662c1 ff081076 0762e1ff 08106a03 ~.b....v.b....j. + 0760 62e1ff08 10620462 e1ff0810 5a05c5fb b....b.b....Z... + 0770 5eed62e1 ff081052 0662e1ff 08104a07 ^.b....R.b....J. + 0780 62c1ff08 104704c4 417b107f 28c4417b b....G..A{..(.A{ + 0790 107730c4 417b106f 38c57b10 6628c57b .w0.A{.o8.{.f(.{ + 07a0 105e30c5 7b105638 c5fb1164 2488c5fb .^0.{.V8...d$... + 07b0 117c2490 c57b114c 2498c4c1 7b107b30 .|$..{.L$...{.{0 + 07c0 c4c17b10 6038c57b 104f30c5 7b104738 ..{.`8.{.O0.{.G8 + 07d0 c5fb117c 24a0c4c1 7b107b38 c5fb1164 ...|$...{.{8...d + 07e0 24a8c5fb 5e21c5fb 115808c5 fb1120c5 $...^!...X.... . + 07f0 fb115010 c5fb1148 18c5fb5e 64248862 ..P....H...^d$.b + 0800 61ff0811 78046261 ff081170 056261ff a...x.ba...p.ba. + 0810 08116806 6261ff08 116007c5 fb117048 ..h.ba...`....pH + 0820 6261ff08 11580a62 61ff0811 500b6261 ba...X.ba...P.ba + 0830 ff081148 0c6261ff 0811400d 62e1ff08 ...H.ba...@.b... + 0840 11780e62 e1ff0811 700fc5fb 11a89000 .x.b....p....... + 0850 000062e1 ff081168 1362e1ff 08116014 ..b....h.b....`. + 0860 62e1ff08 11581562 e1ff0811 501662e1 b....X.b....P.b. + 0870 ff081148 17c5fb11 a0d80000 0062e1ff ...H.........b.. + 0880 0811401c c57b11b8 e8000000 c5fb5e4c ..@..{........^L + 0890 24a0c5fb 5e5c2490 c5fb1188 b0010000 $...^\$......... + 08a0 c5fb5e54 2498c5fb 5e4c24a8 c57b11b0 ..^T$...^L$..{.. + 08b0 f0000000 c57b11a8 f8000000 c5fb1198 .....{.......... + 08c0 20010000 c57b11a0 28010000 c57b1198 ....{..(....{.. + 08d0 30010000 c57b1190 38010000 c5fb1190 0....{..8....... + 08e0 68010000 c57b1188 70010000 c57b1180 h....{..p....{.. + 08f0 78010000 c5fb11b8 b8010000 c5fb1188 x............... + 0900 f8010000 e9a8fdff ff0f1f80 00000000 ................ + 0910 488bbc24 90000000 488bb424 98000000 H..$....H..$.... + 0920 4989fe49 01f64a8d 14374889 f04c8d3c I..I..J..7H..L.< + 0930 174c03a4 24f80000 004883bc 24c80000 .L..$....H..$... + 0940 00000f84 04020000 4c39ed0f 84670600 ........L9...g.. + 0950 000f8edc 01000049 8b7f38c5 fb100862 .......I..8....b + 0960 61ff0810 78016261 ff081070 026261ff a...x.ba...p.ba. + 0970 08106803 6261ff08 10600462 61ff0810 ..h.ba...`.ba... + 0980 58056261 ff081050 066261ff 08104807 X.ba...P.ba...H. + 0990 6241ff08 100662c1 ff08107e 0162c1ff bA....b....~.b.. + 09a0 08107602 62c1ff08 106e0362 c1ff0810 ..v.b....n.b.... + 09b0 660462c1 ff08105e 0562c1ff 08105606 f.b....^.b....V. + 09c0 62c1ff08 104e0762 e1ff0810 02c57b10 b....N.b......{. + 09d0 7a08c57b 107210c5 7b106a18 c57b1062 z..{.r..{.j..{.b + 09e0 20c57b10 5a28c57b 105230c5 7b104a38 .{.Z(.{.R0.{.J8 + 09f0 c4417b10 07c4c17b 107f08c4 c17b1077 .A{....{.....{.w + 0a00 10c4c17b 106f18c4 c17b1067 20c4c17b ...{.o...{.g ..{ /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltncopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 0a020000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606440e 38830703 c7010a0e 30410e28 ..D.8.......0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 e6140000 00420e10 8f02420e .........B....B. + 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 + 0040 8606410e 38830747 0ee80203 d4130a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0844 0b000000 D..D.... /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_COOPERLAKE.o (disasm) @@ -7,49 +7,771 @@ dtrsm_oltucopy_COOPERLAKE: push %r15 push %r14 + mov %r9,%r14 push %r13 push %r12 - mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rdi,%r13 - lea offset(,%rcx,8),%r15 - shl $something,%rcx - sar %r13 - mov %rcx,%rbp - imul %r13,%rbp - mov %rdi,%rbx - mov %r13,%rax - mov %rdx,-offset(%rsp) - and $something,%ebx - lea (%r8,%rsi,2),%rsi + lea offset(,%rcx,8),%rax + mov %rsi,%rbx + mov %rcx,%rsi + shl $something,%rsi + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rdx,%r11 + mov %rsi,offset(%rsp) + lea offset(,%rax,8),%rdx + mov %rcx,%rsi shl $something,%rax - vmovsd offset(%rip),%xmm4 # - mov %r8,-offset(%rsp) - mov %rbx,%r14 - mov %r8,%r10 - mov %rcx,%rdi - add %rdx,%rbp - lea offset(%r13,%r13,1),%r11 - mov %rdx,%rbx + mov %rax,offset(%rsp) + mov %rsi,%rax + shl $something,%rax + mov %rdx,offset(%rsp) + lea (%rsi,%rsi,4),%rdx + imul $something,%rsi,%rsi mov %rax,%r12 + mov %rdi,%rax + and $something,%eax + mov %rsi,offset(%rsp) + mov %rax,offset(%rsp) + mov %rdi,%rsi + mov %rdi,%rax + sar $something,%rsi + and $something,%eax + mov %rax,offset(%rsp) + mov %rsi,%rax + imul %r12,%rax + shl $something,%rdx + and $something,%edi + add %r11,%rax + mov %rax,offset(%rsp) + lea (%r8,%rbx,8),%rax + mov %rdx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + shl $something,%rcx + lea offset(,%rsi,8),%r13 + mov %r8,%r15 + mov %rsi,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + shl $something,%rsi + mov %rcx,offset(%rsp) + mov %rsi,offset(%rsp) + mov %r12,%rcx + mov %r13,%rsi + mov %r11,%r8 + mov %r15,%r9 + mov %r14,%r10 + nopl (%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r8,1),%rbx + mov offset(%rsp),%rax + lea (%rax,%r8,1),%r12 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%rbp + mov offset(%rsp),%rax + lea (%rax,%r8,1),%r14 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%r15 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%rdi + mov offset(%rsp),%rax + lea (%rax,%r8,1),%rdx + jle + mov %r10,%rax + xor %r11d,%r11d + mov %r10,-offset(%rsp) + mov %r8,%r13 + mov %r9,%r10 + mov %r8,%r9 mov %rsi,%r8 + mov %r11,%rsi + mov %rax,%r11 + jmp + nopl (%rax) + jle + vmovsd offset(%r13),%xmm7 + vmovsd offset(%r13),%xmm6 + vmovsd offset(%r13),%xmm5 + vmovsd offset(%r13),%xmm4 + vmovsd offset(%r13),%xmm3 + vmovsd offset(%r13),%xmm31 + vmovsd offset(%r13),%xmm30 + vmovsd (%rbx),%xmm29 + vmovsd offset(%rbx),%xmm28 + vmovsd offset(%rbx),%xmm27 + vmovsd offset(%rbx),%xmm26 + vmovsd offset(%rbx),%xmm25 + vmovsd offset(%rbx),%xmm24 + vmovsd offset(%rbx),%xmm23 + vmovsd offset(%rbx),%xmm22 + vmovsd (%r12),%xmm21 + vmovsd offset(%r12),%xmm20 + vmovsd offset(%r12),%xmm19 + vmovsd offset(%r12),%xmm18 + vmovsd offset(%r12),%xmm17 + vmovsd offset(%r12),%xmm16 + vmovsd offset(%r12),%xmm15 + vmovsd offset(%r12),%xmm14 + vmovsd offset(%rbp),%xmm13 + vmovsd offset(%rbp),%xmm12 + vmovsd offset(%rbp),%xmm11 + vmovsd offset(%rbp),%xmm10 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd offset(%rbp),%xmm9 + vmovsd offset(%rbp),%xmm7 + vmovsd offset(%rbp),%xmm8 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r14),%xmm7 + vmovsd offset(%rbp),%xmm6 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r14),%xmm7 + vmovsd (%r14),%xmm5 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r14),%xmm7 + vmovsd offset(%r14),%xmm4 + vmovsd %xmm7,-offset(%rsp) + vmovsd (%r15),%xmm7 + vmovsd offset(%r14),%xmm3 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd offset(%r14),%xmm2 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd offset(%r14),%xmm1 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd (%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_COOPERLAKE.o (objdump) @@ -2,34 +2,316 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t - 0010 24d048d1 fe48897c 24f04889 4c24f848 $.H..H.|$.H.L$.H - 0020 897424d8 4885f60f 8e2e0100 004989fd .t$.H........I.. - 0030 4c8d3ccd 00000000 48c1e104 49d1fd48 L.<.....H...I..H - 0040 89cd490f afed4889 fb4c89e8 48895424 ..I...H..L..H.T$ - 0050 e083e301 498d3470 48c1e005 c5fb1025 ....I.4pH......% - 0060 00000000 4c894424 e84989de 4d89c248 ....L.D$.I..M..H - 0070 89cf4801 d54f8d5c 2d004889 d34989c4 ..H..O.\-.H..I.. - 0080 4989f00f 1f440000 4a8d343b 4d85ed0f I....D..J.4;M... - 0090 8e4b0100 004889d9 4c89c831 d2eb3b90 .K...H..L..1..;. - 00a0 7e25c5fb 1019c5fb 105108c5 fb100ec5 ~%.......Q...... - 00b0 fb104608 c5fb1118 c5fb1150 08c5fb11 ..F........P.... - 00c0 4810c5fb 11401848 83c20248 01f94801 H....@.H...H..H. - 00d0 fe4883c0 204c39da 741e4939 d275c1c5 .H.. L9.t.I9.u.. - 00e0 fb104108 c5fb1120 c5fb1140 08c5fb11 ..A.... ...@.... - 00f0 6018ebd3 0f1f4000 4889e84d 01e14c89 `.....@.H..M..L. - 0100 da4d85f6 74234c39 d20f84b9 0000007d .M..t#L9.......} - 0110 14c5fb10 08c5fb10 4008c4c1 7b1109c4 ........@...{... - 0120 c17b1141 084983c1 104983c2 024883c3 .{.A.I...I...H.. - 0130 104883c5 104d39c2 0f854aff ffff488b .H...M9...J...H. - 0140 5c24d84c 8b6424e0 4c8b4424 e84889d8 \$.L.d$.L.D$.H.. - 0150 48c1e004 4901c44d 8d0458f6 4424d001 H...I..M..X.D$.. - 0160 7455488b 4c24f048 85c97e4b 488b5424 tUH.L$.H..~KH.T$ - 0170 f8c5fb10 0d000000 0048c1e2 0331c0eb .........H...1.. - 0180 200f1f80 00000000 7e0cc4c1 7b100424 .......~...{..$ - 0190 c4c17b11 04c148ff c04901d4 4839c174 ..{...H..I..H9.t - 01a0 164939c0 75e248ff c0c4817b 110cc149 .I9.u.H....{...I - 01b0 01d44839 c175ea5b 5d415c41 5d415e31 ..H9.u.[]A\A]A^1 - 01c0 c0415fc3 0f1f4000 c5fb1040 08c4c17b .A_...@....@...{ - 01d0 1121c4c1 7b114108 e948ffff ff0f1f00 .!..{.A..H...... - 01e0 4889d831 d2e917ff ffff H..1...... + 0000 41574156 4d89ce41 55415455 534881ec AWAVM..AUATUSH.. + 0010 30010000 4889b424 10010000 48c1fe03 0...H..$....H... + 0020 4889bc24 18010000 48899424 08010000 H..$....H..$.... + 0030 48898c24 20010000 4c898424 00010000 H..$ ...L..$.... + 0040 4889b424 28010000 4885f60f 8e490c00 H..$(...H....I.. + 0050 00488d04 cd000000 004889f3 4889ce48 .H.......H..H..H + 0060 c1e60448 89842490 00000048 8d044949 ...H..$....H..II + 0070 89d34889 b424a000 0000488d 14c50000 ..H..$....H..... + 0080 00004889 ce48c1e0 04488984 24f00000 ..H..H...H..$... + 0090 004889f0 48c1e006 48899424 e0000000 .H..H...H..$.... + 00a0 488d14b6 486bf638 4989c448 89f883e0 H...Hk.8I..H.... + 00b0 044889b4 24b00000 00488984 24c80000 .H..$....H..$... + 00c0 004889fe 4889f848 c1fe0383 e0024889 .H..H..H......H. + 00d0 8424d000 00004889 f0490faf c448c1e2 .$....H..I...H.. + 00e0 0383e701 4c01d848 89842498 00000049 ....L..H..$....I + 00f0 8d04d848 899424e8 00000048 89bc24d8 ...H..$....H..$. + 0100 00000048 898424b8 00000048 c1e1054c ...H..$....H...L + 0110 8d2cf500 0000004d 89c74889 b424c000 .,.....M..H..$.. + 0120 0000c5fb 10050000 000048c1 e6094889 ..........H...H. + 0130 8c24a800 00004889 b424f800 00004c89 .$....H..$....L. + 0140 e14c89ee 4d89d84d 89f94d89 f20f1f00 .L..M..M..M..... + 0150 488b8424 90000000 4883bc24 c0000000 H..$....H..$.... + 0160 004a8d1c 00488b84 24a00000 004e8d24 .J...H..$....N.$ + 0170 00488b84 24e00000 00498d2c 00488b84 .H..$....I.,.H.. + 0180 24a80000 004e8d34 00488b84 24e80000 $....N.4.H..$... + 0190 004d8d3c 00488b84 24f00000 00498d3c .M.<.H..$....I.< + 01a0 00488b84 24b00000 004a8d14 000f8e15 .H..$....J...... + 01b0 1100004c 89d04531 db4c8954 24884d89 ...L..E1.L.T$.M. + 01c0 c54d89ca 4d89c149 89f04c89 de4989c3 .M..M..I..L..I.. + 01d0 e9210500 000f1f00 0f8eed04 0000c4c1 .!.............. + 01e0 7b107d08 c4c17b10 7510c4c1 7b106d18 {.}...{.u...{.m. + 01f0 c4c17b10 6520c4c1 7b105d28 6241ff08 ..{.e ..{.](bA.. + 0200 107d0662 41ff0810 75076261 ff08102b .}.bA...u.ba...+ + 0210 6261ff08 10630162 61ff0810 5b026261 ba...c.ba...[.ba + 0220 ff081053 036261ff 08104b04 6261ff08 ...S.ba...K.ba.. + 0230 10430562 e1ff0810 7b0662e1 ff081073 .C.b....{.b....s + 0240 0762c1ff 08102c24 62c1ff08 10642401 .b....,$b....d$. + 0250 62c1ff08 105c2402 62c1ff08 10542403 b....\$.b....T$. + 0260 62c1ff08 104c2404 62c1ff08 10442405 b....L$.b....D$. + 0270 c4417b10 7c2430c4 417b1074 2438c57b .A{.|$0.A{.t$8.{ + 0280 106d00c5 7b106508 c57b105d 10c57b10 .m..{.e..{.]..{. + 0290 5518c5fb 117c2488 c5fb1174 2490c5fb U....|$....t$... + 02a0 116c2498 c5fb1164 24a0c5fb 115c24a8 .l$....d$....\$. + 02b0 c57b104d 20c5fb10 7d30c57b 104528c5 .{.M ...}0.{.E(. + 02c0 fb117c24 b0c4c17b 107e28c5 fb107538 ..|$...{.~(...u8 + 02d0 c5fb117c 24b8c4c1 7b107e30 c4c17b10 ...|$...{.~0..{. + 02e0 2ec5fb11 7c24c0c4 c17b107e 38c4c17b ....|$...{.~8..{ + 02f0 106608c5 fb117c24 c8c4c17b 103fc4c1 .f....|$...{.?.. + 0300 7b105e10 c5fb117c 24d0c4c1 7b107f08 {.^....|$...{... + 0310 c4c17b10 5618c5fb 117c24d8 c4c17b10 ..{.V....|$...{. + 0320 7f10c4c1 7b104e20 c5fb117c 24e0c4c1 ....{.N ...|$... + 0330 7b107f18 c5fb117c 24e8c4c1 7b107f20 {......|$...{.. + 0340 c5fb117c 24f0c4c1 7b107f28 c5fb117c ...|$...{..(...| + 0350 24f8c4c1 7b107f30 c5fb113c 24c4c17b $...{..0...<$..{ + 0360 107f38c5 fb117c24 08c5fb10 3fc5fb11 ..8...|$....?... + 0370 7c2410c5 fb107f08 c5fb117c 2418c5fb |$.........|$... + 0380 107f10c5 fb117c24 20c5fb10 7f18c5fb ......|$ ....... + 0390 117c2428 c5fb107f 20c5fb11 7c2430c5 .|$(.... ...|$0. + 03a0 fb107f28 c5fb117c 2438c5fb 107f30c5 ...(...|$8....0. + 03b0 fb117c24 40c5fb10 7f38c5fb 117c2448 ..|$@....8...|$H + 03c0 c5fb103a c5fb117c 2450c5fb 107a08c5 ...:...|$P...z.. + 03d0 fb117c24 58c5fb10 7a10c5fb 117c2460 ..|$X...z....|$` + 03e0 c5fb107a 18c5fb11 7c2468c5 fb107a20 ...z....|$h...z + 03f0 c5fb117c 2470c5fb 107a28c5 fb117c24 ...|$p...z(...|$ + 0400 78c5fb10 7a30c5fb 11bc2480 000000c5 x...z0....$..... + 0410 fb107a38 c5fb11bc 24880000 00c4c17b ..z8....$......{ + 0420 107d0062 61ff0811 7806c5fb 1138c5fb .}.ba...x....8.. + 0430 107c2488 6261ff08 117007c5 fb117808 .|$.ba...p....x. + 0440 c5fb107c 24906261 ff081168 08c5fb11 ...|$.ba...h.... + 0450 7810c5fb 107c2498 6261ff08 116009c5 x....|$.ba...`.. + 0460 fb117818 c5fb107c 24a06261 ff081158 ..x....|$.ba...X + 0470 0ac5fb11 7820c5fb 107c24a8 6261ff08 ....x ...|$.ba.. + 0480 11500bc5 fb117828 6261ff08 11480c62 .P....x(ba...H.b + 0490 61ff0811 400d62e1 ff081178 0e62e1ff a...@.b....x.b.. + 04a0 0811700f 62e1ff08 11681062 e1ff0811 ..p.b....h.b.... + 04b0 601162e1 ff081158 1262e1ff 08115013 `.b....X.b....P. + 04c0 62e1ff08 11481462 e1ff0811 4015c57b b....H.b....@..{ + 04d0 11b8b000 0000c57b 11b0b800 0000c57b .......{.......{ + 04e0 11a8c000 0000c57b 11a0c800 0000c57b .......{.......{ + 04f0 1198d000 0000c5fb 107c24b0 c57b1190 .........|$..{.. + 0500 d8000000 c5fb11b8 f0000000 c5fb107c ...............| + 0510 24b8c57b 1188e000 0000c5fb 11b82801 $..{..........(. + 0520 0000c5fb 107c24c0 c57b1180 e8000000 .....|$..{...... + 0530 c5fb11b8 30010000 c5fb107c 24c8c5fb ....0......|$... + 0540 11b0f800 0000c5fb 11b83801 0000c5fb ..........8..... + 0550 107c24d0 c5fb11a8 00010000 c5fb11b8 .|$............. + 0560 40010000 c5fb107c 24d8c5fb 11a00801 @......|$....... + 0570 0000c5fb 11b84801 0000c5fb 107c24e0 ......H......|$. + 0580 c5fb1198 10010000 c5fb11b8 50010000 ............P... + 0590 c5fb107c 24e8c5fb 11901801 0000c5fb ...|$........... + 05a0 11b85801 0000c5fb 107c24f0 c5fb1188 ..X......|$..... + 05b0 20010000 c5fb11b8 60010000 c5fb107c .......`......| + 05c0 24f8c5fb 11b86801 0000c5fb 103c24c5 $.....h......<$. + 05d0 fb11b870 010000c5 fb107c24 08c5fb11 ...p......|$.... + 05e0 b8780100 00c5fb10 7c2410c5 fb11b880 .x......|$...... + 05f0 010000c5 fb107c24 18c5fb11 b8880100 ......|$........ + 0600 00c5fb10 7c2420c5 fb11b890 010000c5 ....|$ ......... + 0610 fb107c24 28c5fb11 b8980100 00c5fb10 ..|$(........... + 0620 7c2430c5 fb11b8a0 010000c5 fb107c24 |$0...........|$ + 0630 38c5fb11 b8a80100 00c5fb10 7c2440c5 8...........|$@. + 0640 fb11b8b0 010000c5 fb107c24 48c5fb11 ..........|$H... + 0650 b8b80100 00c5fb10 7c2450c5 fb11b8c0 ........|$P..... + 0660 010000c5 fb107c24 58c5fb11 b8c80100 ......|$X....... + 0670 00c5fb10 7c2460c5 fb11b8d0 010000c5 ....|$`......... + 0680 fb107c24 68c5fb11 b8d80100 00c5fb10 ..|$h........... + 0690 7c2470c5 fb11b8e0 010000c5 fb107c24 |$p...........|$ + 06a0 78c5fb11 b8e80100 00c5fb10 bc248000 x............$.. + 06b0 0000c5fb 11b8f001 0000c5fb 10bc2488 ..............$. + 06c0 000000c5 fb11b8f8 01000048 83c60849 ...........H...I + 06d0 01cd4801 cb4901cc 4801cd49 01ce4901 ..H..I..H..I..I. + 06e0 cf4801cf 4801ca48 05000200 004939f0 .H..H..H.....I9. + 06f0 0f84d201 00004939 f20f85d9 faffff62 ......I9.......b + 0700 41ff0810 450562c1 ff08107d 0662c1ff A...E.b....}.b.. + 0710 08107507 62e1ff08 106b0262 e1ff0810 ..u.b....k.b.... + 0720 630362e1 ff08105b 0462e1ff 08105305 c.b....[.b....S. + 0730 62e1ff08 104b0662 e1ff0810 4307c441 b....K.b....C..A + 0740 7b107c24 18c4417b 10742420 c4417b10 {.|$..A{.t$ .A{. + 0750 6c2428c4 417b1064 2430c441 7b105c24 l$(.A{.d$0.A{.\$ + 0760 38c57b10 5520c57b 104d28c5 7b104530 8.{.U .{.M(.{.E0 + 0770 c5fb107d 38c4c17b 107628c4 c17b106e ...}8..{.v(..{.n + 0780 30c4c17b 106638c4 c17b105f 30c4c17b 0..{.f8..{._0..{ + 0790 105738c5 fb104f38 6241ff08 10650162 .W8...O8bA...e.b + 07a0 41ff0810 5d026241 ff081055 036241ff A...].bA...U.bA. + 07b0 08104d04 c5fb1100 6261ff08 11600162 ..M.....ba...`.b + 07c0 61ff0811 58026261 ff081150 036261ff a...X.ba...P.ba. + 07d0 08114804 6261ff08 11400562 e1ff0811 ..H.ba...@.b.... + 07e0 780662e1 ff081170 07c5fb11 404862e1 x.b....p....@Hb. + 07f0 ff081168 0a62e1ff 0811600b 62e1ff08 ...h.b....`.b... + 0800 11580c62 e1ff0811 500d62e1 ff081148 .X.b....P.b....H + 0810 0e62e1ff 0811400f c5fb1180 90000000 .b....@......... + 0820 c57b11b8 98000000 c57b11b0 a0000000 .{.......{...... + 0830 c57b11a8 a8000000 c57b11a0 b0000000 .{.......{...... + 0840 c57b1198 b8000000 c5fb1180 d8000000 .{.............. + 0850 c57b1190 e0000000 c57b1188 e8000000 .{.......{...... + 0860 c57b1180 f0000000 c5fb11b8 f8000000 .{.............. + 0870 c5fb1180 20010000 c5fb11b0 28010000 .... .......(... + 0880 c5fb11a8 30010000 c5fb11a0 38010000 ....0.......8... + 0890 c5fb1180 68010000 c5fb1198 70010000 ....h.......p... + 08a0 c5fb1190 78010000 c5fb1180 b0010000 ....x........... + 08b0 c5fb1188 b8010000 c5fb1180 f8010000 ................ + 08c0 e906feff ff0f1f00 488b9424 90000000 ........H..$.... + 08d0 488bbc24 98000000 4889d34c 89d84801 H..$....H..L..H. + 08e0 fb4989f3 4c8d241a 4c89c64d 89c84d89 .I..L.$.L..M..M. + 08f0 d14989c2 4a8d2c22 4889f84c 039424f8 .I..J.,"H..L..$. + 0900 00000048 83bc24c8 00000000 0f84ed01 ...H..$......... + 0910 00004d39 cb0f84d5 0500000f 8dc50100 ..M9............ + 0920 00488b55 38c5fb10 086261ff 08107801 .H.U8....ba...x. + 0930 6261ff08 10700262 61ff0810 68036261 ba...p.ba...h.ba + 0940 ff081060 046261ff 08105805 6261ff08 ...`.ba...X.ba.. + 0950 10500662 61ff0810 48076261 ff081003 .P.ba...H.ba.... + 0960 62e1ff08 107b0162 e1ff0810 730262e1 b....{.b....s.b. + 0970 ff08106b 0362e1ff 08106304 62e1ff08 ...k.b....c.b... + 0980 105b0562 e1ff0810 530662e1 ff08104b .[.b....S.b....K + 0990 0762c1ff 08100424 c4417b10 7c2408c4 .b.....$.A{.|$.. + 09a0 417b1074 2410c441 7b106c24 18c4417b A{.t$..A{.l$..A{ + 09b0 10642420 c4417b10 5c2428c4 417b1054 .d$ .A{.\$(.A{.T + 09c0 2430c441 7b104c24 38c57b10 4500c5fb $0.A{.L$8.{.E... + 09d0 107d08c5 fb107510 c5fb106d 18c5fb10 .}....u....m.... + 09e0 6520c5fb 105d28c5 fb105530 c4c17b11 e ...](...U0..{. + 09f0 0a498992 f8000000 6241ff08 117a0162 .I......bA...z.b + 0a00 41ff0811 72026241 ff08116a 036241ff A...r.bA...j.bA. + 0a10 08116204 6241ff08 115a0562 41ff0811 ..b.bA...Z.bA... + 0a20 52066241 ff08114a 076241ff 08114208 R.bA...J.bA...B. /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 ea010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 ab010a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 8c130000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05410e30 ...E. ..B.(..A.0 + 0040 8606410e 38830747 0ee80203 a0120a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0848 0b000000 D..H.... /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_SKYLAKEX.o (disasm) @@ -7,49 +7,771 @@ dtrsm_oltucopy_SKYLAKEX: push %r15 push %r14 + mov %r9,%r14 push %r13 push %r12 - mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rdi,%r13 - lea offset(,%rcx,8),%r15 - shl $something,%rcx - sar %r13 - mov %rcx,%rbp - imul %r13,%rbp - mov %rdi,%rbx - mov %r13,%rax - mov %rdx,-offset(%rsp) - and $something,%ebx - lea (%r8,%rsi,2),%rsi + lea offset(,%rcx,8),%rax + mov %rsi,%rbx + mov %rcx,%rsi + shl $something,%rsi + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rdx,%r11 + mov %rsi,offset(%rsp) + lea offset(,%rax,8),%rdx + mov %rcx,%rsi shl $something,%rax - vmovsd offset(%rip),%xmm4 # - mov %r8,-offset(%rsp) - mov %rbx,%r14 - mov %r8,%r10 - mov %rcx,%rdi - add %rdx,%rbp - lea offset(%r13,%r13,1),%r11 - mov %rdx,%rbx + mov %rax,offset(%rsp) + mov %rsi,%rax + shl $something,%rax + mov %rdx,offset(%rsp) + lea (%rsi,%rsi,4),%rdx + imul $something,%rsi,%rsi mov %rax,%r12 + mov %rdi,%rax + and $something,%eax + mov %rsi,offset(%rsp) + mov %rax,offset(%rsp) + mov %rdi,%rsi + mov %rdi,%rax + sar $something,%rsi + and $something,%eax + mov %rax,offset(%rsp) + mov %rsi,%rax + imul %r12,%rax + shl $something,%rdx + and $something,%edi + add %r11,%rax + mov %rax,offset(%rsp) + lea (%r8,%rbx,8),%rax + mov %rdx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + shl $something,%rcx + lea offset(,%rsi,8),%r13 + mov %r8,%r15 + mov %rsi,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + shl $something,%rsi + mov %rcx,offset(%rsp) + mov %rsi,offset(%rsp) + mov %r12,%rcx + mov %r13,%rsi + mov %r11,%r8 + mov %r15,%r9 + mov %r14,%r10 + nopl (%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r8,1),%rbx + mov offset(%rsp),%rax + lea (%rax,%r8,1),%r12 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%rbp + mov offset(%rsp),%rax + lea (%rax,%r8,1),%r14 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%r15 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%rdi + mov offset(%rsp),%rax + lea (%rax,%r8,1),%rdx + jle + mov %r10,%rax + xor %r11d,%r11d + mov %r10,-offset(%rsp) + mov %r8,%r13 + mov %r9,%r10 + mov %r8,%r9 mov %rsi,%r8 + mov %r11,%rsi + mov %rax,%r11 + jmp + nopl (%rax) + jle + vmovsd offset(%r13),%xmm7 + vmovsd offset(%r13),%xmm6 + vmovsd offset(%r13),%xmm5 + vmovsd offset(%r13),%xmm4 + vmovsd offset(%r13),%xmm3 + vmovsd offset(%r13),%xmm31 + vmovsd offset(%r13),%xmm30 + vmovsd (%rbx),%xmm29 + vmovsd offset(%rbx),%xmm28 + vmovsd offset(%rbx),%xmm27 + vmovsd offset(%rbx),%xmm26 + vmovsd offset(%rbx),%xmm25 + vmovsd offset(%rbx),%xmm24 + vmovsd offset(%rbx),%xmm23 + vmovsd offset(%rbx),%xmm22 + vmovsd (%r12),%xmm21 + vmovsd offset(%r12),%xmm20 + vmovsd offset(%r12),%xmm19 + vmovsd offset(%r12),%xmm18 + vmovsd offset(%r12),%xmm17 + vmovsd offset(%r12),%xmm16 + vmovsd offset(%r12),%xmm15 + vmovsd offset(%r12),%xmm14 + vmovsd offset(%rbp),%xmm13 + vmovsd offset(%rbp),%xmm12 + vmovsd offset(%rbp),%xmm11 + vmovsd offset(%rbp),%xmm10 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd offset(%rbp),%xmm9 + vmovsd offset(%rbp),%xmm7 + vmovsd offset(%rbp),%xmm8 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r14),%xmm7 + vmovsd offset(%rbp),%xmm6 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r14),%xmm7 + vmovsd (%r14),%xmm5 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r14),%xmm7 + vmovsd offset(%r14),%xmm4 + vmovsd %xmm7,-offset(%rsp) + vmovsd (%r15),%xmm7 + vmovsd offset(%r14),%xmm3 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd offset(%r14),%xmm2 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd offset(%r14),%xmm1 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd (%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_SKYLAKEX.o (objdump) @@ -2,34 +2,316 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t - 0010 24d048d1 fe48897c 24f04889 4c24f848 $.H..H.|$.H.L$.H - 0020 897424d8 4885f60f 8e2e0100 004989fd .t$.H........I.. - 0030 4c8d3ccd 00000000 48c1e104 49d1fd48 L.<.....H...I..H - 0040 89cd490f afed4889 fb4c89e8 48895424 ..I...H..L..H.T$ - 0050 e083e301 498d3470 48c1e005 c5fb1025 ....I.4pH......% - 0060 00000000 4c894424 e84989de 4d89c248 ....L.D$.I..M..H - 0070 89cf4801 d54f8d5c 2d004889 d34989c4 ..H..O.\-.H..I.. - 0080 4989f00f 1f440000 4a8d343b 4d85ed0f I....D..J.4;M... - 0090 8e4b0100 004889d9 4c89c831 d2eb3b90 .K...H..L..1..;. - 00a0 7e25c5fb 1019c5fb 105108c5 fb100ec5 ~%.......Q...... - 00b0 fb104608 c5fb1118 c5fb1150 08c5fb11 ..F........P.... - 00c0 4810c5fb 11401848 83c20248 01f94801 H....@.H...H..H. - 00d0 fe4883c0 204c39da 741e4939 d275c1c5 .H.. L9.t.I9.u.. - 00e0 fb104108 c5fb1120 c5fb1140 08c5fb11 ..A.... ...@.... - 00f0 6018ebd3 0f1f4000 4889e84d 01e14c89 `.....@.H..M..L. - 0100 da4d85f6 74234c39 d20f84b9 0000007d .M..t#L9.......} - 0110 14c5fb10 08c5fb10 4008c4c1 7b1109c4 ........@...{... - 0120 c17b1141 084983c1 104983c2 024883c3 .{.A.I...I...H.. - 0130 104883c5 104d39c2 0f854aff ffff488b .H...M9...J...H. - 0140 5c24d84c 8b6424e0 4c8b4424 e84889d8 \$.L.d$.L.D$.H.. - 0150 48c1e004 4901c44d 8d0458f6 4424d001 H...I..M..X.D$.. - 0160 7455488b 4c24f048 85c97e4b 488b5424 tUH.L$.H..~KH.T$ - 0170 f8c5fb10 0d000000 0048c1e2 0331c0eb .........H...1.. - 0180 200f1f80 00000000 7e0cc4c1 7b100424 .......~...{..$ - 0190 c4c17b11 04c148ff c04901d4 4839c174 ..{...H..I..H9.t - 01a0 164939c0 75e248ff c0c4817b 110cc149 .I9.u.H....{...I - 01b0 01d44839 c175ea5b 5d415c41 5d415e31 ..H9.u.[]A\A]A^1 - 01c0 c0415fc3 0f1f4000 c5fb1040 08c4c17b .A_...@....@...{ - 01d0 1121c4c1 7b114108 e948ffff ff0f1f00 .!..{.A..H...... - 01e0 4889d831 d2e917ff ffff H..1...... + 0000 41574156 4d89ce41 55415455 534881ec AWAVM..AUATUSH.. + 0010 30010000 4889b424 10010000 48c1fe03 0...H..$....H... + 0020 4889bc24 18010000 48899424 08010000 H..$....H..$.... + 0030 48898c24 20010000 4c898424 00010000 H..$ ...L..$.... + 0040 4889b424 28010000 4885f60f 8e490c00 H..$(...H....I.. + 0050 00488d04 cd000000 004889f3 4889ce48 .H.......H..H..H + 0060 c1e60448 89842490 00000048 8d044949 ...H..$....H..II + 0070 89d34889 b424a000 0000488d 14c50000 ..H..$....H..... + 0080 00004889 ce48c1e0 04488984 24f00000 ..H..H...H..$... + 0090 004889f0 48c1e006 48899424 e0000000 .H..H...H..$.... + 00a0 488d14b6 486bf638 4989c448 89f883e0 H...Hk.8I..H.... + 00b0 044889b4 24b00000 00488984 24c80000 .H..$....H..$... + 00c0 004889fe 4889f848 c1fe0383 e0024889 .H..H..H......H. + 00d0 8424d000 00004889 f0490faf c448c1e2 .$....H..I...H.. + 00e0 0383e701 4c01d848 89842498 00000049 ....L..H..$....I + 00f0 8d04d848 899424e8 00000048 89bc24d8 ...H..$....H..$. + 0100 00000048 898424b8 00000048 c1e1054c ...H..$....H...L + 0110 8d2cf500 0000004d 89c74889 b424c000 .,.....M..H..$.. + 0120 0000c5fb 10050000 000048c1 e6094889 ..........H...H. + 0130 8c24a800 00004889 b424f800 00004c89 .$....H..$....L. + 0140 e14c89ee 4d89d84d 89f94d89 f20f1f00 .L..M..M..M..... + 0150 488b8424 90000000 4883bc24 c0000000 H..$....H..$.... + 0160 004a8d1c 00488b84 24a00000 004e8d24 .J...H..$....N.$ + 0170 00488b84 24e00000 00498d2c 00488b84 .H..$....I.,.H.. + 0180 24a80000 004e8d34 00488b84 24e80000 $....N.4.H..$... + 0190 004d8d3c 00488b84 24f00000 00498d3c .M.<.H..$....I.< + 01a0 00488b84 24b00000 004a8d14 000f8e15 .H..$....J...... + 01b0 1100004c 89d04531 db4c8954 24884d89 ...L..E1.L.T$.M. + 01c0 c54d89ca 4d89c149 89f04c89 de4989c3 .M..M..I..L..I.. + 01d0 e9210500 000f1f00 0f8eed04 0000c4c1 .!.............. + 01e0 7b107d08 c4c17b10 7510c4c1 7b106d18 {.}...{.u...{.m. + 01f0 c4c17b10 6520c4c1 7b105d28 6241ff08 ..{.e ..{.](bA.. + 0200 107d0662 41ff0810 75076261 ff08102b .}.bA...u.ba...+ + 0210 6261ff08 10630162 61ff0810 5b026261 ba...c.ba...[.ba + 0220 ff081053 036261ff 08104b04 6261ff08 ...S.ba...K.ba.. + 0230 10430562 e1ff0810 7b0662e1 ff081073 .C.b....{.b....s + 0240 0762c1ff 08102c24 62c1ff08 10642401 .b....,$b....d$. + 0250 62c1ff08 105c2402 62c1ff08 10542403 b....\$.b....T$. + 0260 62c1ff08 104c2404 62c1ff08 10442405 b....L$.b....D$. + 0270 c4417b10 7c2430c4 417b1074 2438c57b .A{.|$0.A{.t$8.{ + 0280 106d00c5 7b106508 c57b105d 10c57b10 .m..{.e..{.]..{. + 0290 5518c5fb 117c2488 c5fb1174 2490c5fb U....|$....t$... + 02a0 116c2498 c5fb1164 24a0c5fb 115c24a8 .l$....d$....\$. + 02b0 c57b104d 20c5fb10 7d30c57b 104528c5 .{.M ...}0.{.E(. + 02c0 fb117c24 b0c4c17b 107e28c5 fb107538 ..|$...{.~(...u8 + 02d0 c5fb117c 24b8c4c1 7b107e30 c4c17b10 ...|$...{.~0..{. + 02e0 2ec5fb11 7c24c0c4 c17b107e 38c4c17b ....|$...{.~8..{ + 02f0 106608c5 fb117c24 c8c4c17b 103fc4c1 .f....|$...{.?.. + 0300 7b105e10 c5fb117c 24d0c4c1 7b107f08 {.^....|$...{... + 0310 c4c17b10 5618c5fb 117c24d8 c4c17b10 ..{.V....|$...{. + 0320 7f10c4c1 7b104e20 c5fb117c 24e0c4c1 ....{.N ...|$... + 0330 7b107f18 c5fb117c 24e8c4c1 7b107f20 {......|$...{.. + 0340 c5fb117c 24f0c4c1 7b107f28 c5fb117c ...|$...{..(...| + 0350 24f8c4c1 7b107f30 c5fb113c 24c4c17b $...{..0...<$..{ + 0360 107f38c5 fb117c24 08c5fb10 3fc5fb11 ..8...|$....?... + 0370 7c2410c5 fb107f08 c5fb117c 2418c5fb |$.........|$... + 0380 107f10c5 fb117c24 20c5fb10 7f18c5fb ......|$ ....... + 0390 117c2428 c5fb107f 20c5fb11 7c2430c5 .|$(.... ...|$0. + 03a0 fb107f28 c5fb117c 2438c5fb 107f30c5 ...(...|$8....0. + 03b0 fb117c24 40c5fb10 7f38c5fb 117c2448 ..|$@....8...|$H + 03c0 c5fb103a c5fb117c 2450c5fb 107a08c5 ...:...|$P...z.. + 03d0 fb117c24 58c5fb10 7a10c5fb 117c2460 ..|$X...z....|$` + 03e0 c5fb107a 18c5fb11 7c2468c5 fb107a20 ...z....|$h...z + 03f0 c5fb117c 2470c5fb 107a28c5 fb117c24 ...|$p...z(...|$ + 0400 78c5fb10 7a30c5fb 11bc2480 000000c5 x...z0....$..... + 0410 fb107a38 c5fb11bc 24880000 00c4c17b ..z8....$......{ + 0420 107d0062 61ff0811 7806c5fb 1138c5fb .}.ba...x....8.. + 0430 107c2488 6261ff08 117007c5 fb117808 .|$.ba...p....x. + 0440 c5fb107c 24906261 ff081168 08c5fb11 ...|$.ba...h.... + 0450 7810c5fb 107c2498 6261ff08 116009c5 x....|$.ba...`.. + 0460 fb117818 c5fb107c 24a06261 ff081158 ..x....|$.ba...X + 0470 0ac5fb11 7820c5fb 107c24a8 6261ff08 ....x ...|$.ba.. + 0480 11500bc5 fb117828 6261ff08 11480c62 .P....x(ba...H.b + 0490 61ff0811 400d62e1 ff081178 0e62e1ff a...@.b....x.b.. + 04a0 0811700f 62e1ff08 11681062 e1ff0811 ..p.b....h.b.... + 04b0 601162e1 ff081158 1262e1ff 08115013 `.b....X.b....P. + 04c0 62e1ff08 11481462 e1ff0811 4015c57b b....H.b....@..{ + 04d0 11b8b000 0000c57b 11b0b800 0000c57b .......{.......{ + 04e0 11a8c000 0000c57b 11a0c800 0000c57b .......{.......{ + 04f0 1198d000 0000c5fb 107c24b0 c57b1190 .........|$..{.. + 0500 d8000000 c5fb11b8 f0000000 c5fb107c ...............| + 0510 24b8c57b 1188e000 0000c5fb 11b82801 $..{..........(. + 0520 0000c5fb 107c24c0 c57b1180 e8000000 .....|$..{...... + 0530 c5fb11b8 30010000 c5fb107c 24c8c5fb ....0......|$... + 0540 11b0f800 0000c5fb 11b83801 0000c5fb ..........8..... + 0550 107c24d0 c5fb11a8 00010000 c5fb11b8 .|$............. + 0560 40010000 c5fb107c 24d8c5fb 11a00801 @......|$....... + 0570 0000c5fb 11b84801 0000c5fb 107c24e0 ......H......|$. + 0580 c5fb1198 10010000 c5fb11b8 50010000 ............P... + 0590 c5fb107c 24e8c5fb 11901801 0000c5fb ...|$........... + 05a0 11b85801 0000c5fb 107c24f0 c5fb1188 ..X......|$..... + 05b0 20010000 c5fb11b8 60010000 c5fb107c .......`......| + 05c0 24f8c5fb 11b86801 0000c5fb 103c24c5 $.....h......<$. + 05d0 fb11b870 010000c5 fb107c24 08c5fb11 ...p......|$.... + 05e0 b8780100 00c5fb10 7c2410c5 fb11b880 .x......|$...... + 05f0 010000c5 fb107c24 18c5fb11 b8880100 ......|$........ + 0600 00c5fb10 7c2420c5 fb11b890 010000c5 ....|$ ......... + 0610 fb107c24 28c5fb11 b8980100 00c5fb10 ..|$(........... + 0620 7c2430c5 fb11b8a0 010000c5 fb107c24 |$0...........|$ + 0630 38c5fb11 b8a80100 00c5fb10 7c2440c5 8...........|$@. + 0640 fb11b8b0 010000c5 fb107c24 48c5fb11 ..........|$H... + 0650 b8b80100 00c5fb10 7c2450c5 fb11b8c0 ........|$P..... + 0660 010000c5 fb107c24 58c5fb11 b8c80100 ......|$X....... + 0670 00c5fb10 7c2460c5 fb11b8d0 010000c5 ....|$`......... + 0680 fb107c24 68c5fb11 b8d80100 00c5fb10 ..|$h........... + 0690 7c2470c5 fb11b8e0 010000c5 fb107c24 |$p...........|$ + 06a0 78c5fb11 b8e80100 00c5fb10 bc248000 x............$.. + 06b0 0000c5fb 11b8f001 0000c5fb 10bc2488 ..............$. + 06c0 000000c5 fb11b8f8 01000048 83c60849 ...........H...I + 06d0 01cd4801 cb4901cc 4801cd49 01ce4901 ..H..I..H..I..I. + 06e0 cf4801cf 4801ca48 05000200 004939f0 .H..H..H.....I9. + 06f0 0f84d201 00004939 f20f85d9 faffff62 ......I9.......b + 0700 41ff0810 450562c1 ff08107d 0662c1ff A...E.b....}.b.. + 0710 08107507 62e1ff08 106b0262 e1ff0810 ..u.b....k.b.... + 0720 630362e1 ff08105b 0462e1ff 08105305 c.b....[.b....S. + 0730 62e1ff08 104b0662 e1ff0810 4307c441 b....K.b....C..A + 0740 7b107c24 18c4417b 10742420 c4417b10 {.|$..A{.t$ .A{. + 0750 6c2428c4 417b1064 2430c441 7b105c24 l$(.A{.d$0.A{.\$ + 0760 38c57b10 5520c57b 104d28c5 7b104530 8.{.U .{.M(.{.E0 + 0770 c5fb107d 38c4c17b 107628c4 c17b106e ...}8..{.v(..{.n + 0780 30c4c17b 106638c4 c17b105f 30c4c17b 0..{.f8..{._0..{ + 0790 105738c5 fb104f38 6241ff08 10650162 .W8...O8bA...e.b + 07a0 41ff0810 5d026241 ff081055 036241ff A...].bA...U.bA. + 07b0 08104d04 c5fb1100 6261ff08 11600162 ..M.....ba...`.b + 07c0 61ff0811 58026261 ff081150 036261ff a...X.ba...P.ba. + 07d0 08114804 6261ff08 11400562 e1ff0811 ..H.ba...@.b.... + 07e0 780662e1 ff081170 07c5fb11 404862e1 x.b....p....@Hb. + 07f0 ff081168 0a62e1ff 0811600b 62e1ff08 ...h.b....`.b... + 0800 11580c62 e1ff0811 500d62e1 ff081148 .X.b....P.b....H + 0810 0e62e1ff 0811400f c5fb1180 90000000 .b....@......... + 0820 c57b11b8 98000000 c57b11b0 a0000000 .{.......{...... + 0830 c57b11a8 a8000000 c57b11a0 b0000000 .{.......{...... + 0840 c57b1198 b8000000 c5fb1180 d8000000 .{.............. + 0850 c57b1190 e0000000 c57b1188 e8000000 .{.......{...... + 0860 c57b1180 f0000000 c5fb11b8 f8000000 .{.............. + 0870 c5fb1180 20010000 c5fb11b0 28010000 .... .......(... + 0880 c5fb11a8 30010000 c5fb11a0 38010000 ....0.......8... + 0890 c5fb1180 68010000 c5fb1198 70010000 ....h.......p... + 08a0 c5fb1190 78010000 c5fb1180 b0010000 ....x........... + 08b0 c5fb1188 b8010000 c5fb1180 f8010000 ................ + 08c0 e906feff ff0f1f00 488b9424 90000000 ........H..$.... + 08d0 488bbc24 98000000 4889d34c 89d84801 H..$....H..L..H. + 08e0 fb4989f3 4c8d241a 4c89c64d 89c84d89 .I..L.$.L..M..M. + 08f0 d14989c2 4a8d2c22 4889f84c 039424f8 .I..J.,"H..L..$. + 0900 00000048 83bc24c8 00000000 0f84ed01 ...H..$......... + 0910 00004d39 cb0f84d5 0500000f 8dc50100 ..M9............ + 0920 00488b55 38c5fb10 086261ff 08107801 .H.U8....ba...x. + 0930 6261ff08 10700262 61ff0810 68036261 ba...p.ba...h.ba + 0940 ff081060 046261ff 08105805 6261ff08 ...`.ba...X.ba.. + 0950 10500662 61ff0810 48076261 ff081003 .P.ba...H.ba.... + 0960 62e1ff08 107b0162 e1ff0810 730262e1 b....{.b....s.b. + 0970 ff08106b 0362e1ff 08106304 62e1ff08 ...k.b....c.b... + 0980 105b0562 e1ff0810 530662e1 ff08104b .[.b....S.b....K + 0990 0762c1ff 08100424 c4417b10 7c2408c4 .b.....$.A{.|$.. + 09a0 417b1074 2410c441 7b106c24 18c4417b A{.t$..A{.l$..A{ + 09b0 10642420 c4417b10 5c2428c4 417b1054 .d$ .A{.\$(.A{.T + 09c0 2430c441 7b104c24 38c57b10 4500c5fb $0.A{.L$8.{.E... + 09d0 107d08c5 fb107510 c5fb106d 18c5fb10 .}....u....m.... + 09e0 6520c5fb 105d28c5 fb105530 c4c17b11 e ...](...U0..{. + 09f0 0a498992 f8000000 6241ff08 117a0162 .I......bA...z.b + 0a00 41ff0811 72026241 ff08116a 036241ff A...r.bA...j.bA. + 0a10 08116204 6241ff08 115a0562 41ff0811 ..b.bA...Z.bA... + 0a20 52066241 ff08114a 076241ff 08114208 R.bA...J.bA...B. /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_oltucopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 ea010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 ab010a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 8c130000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05410e30 ...E. ..B.(..A.0 + 0040 8606410e 38830747 0ee80203 a0120a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0848 0b000000 D..H.... /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_COOPERLAKE.o (disasm) @@ -6,118 +6,933 @@ dtrsm_ounncopy_COOPERLAKE: push %r15 + mov %r9,%r15 push %r14 push %r13 push %r12 - mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rdi,%rbx - sar %rbx - mov %rbx,%r14 - mov %rbx,%rax - mov %rdx,-offset(%rsp) - mov %rcx,%r11 - lea offset(,%rcx,8),%rbp - mov %rdi,%r13 - lea (%r8,%rsi,2),%rsi - and $something,%rdi - shl $something,%r14 + lea (%rcx,%rcx,2),%rax + lea offset(,%rax,8),%rbp + mov %rsi,%r11 shl $something,%rax - vmovsd offset(%rip),%xmm4 # - mov %r8,-offset(%rsp) - mov %rdi,%r10 - shl $something,%r11 - mov %r8,%rdi - and $something,%r13d - lea offset(%rbp,%r14,1),%r15 - mov %rdx,%rcx + mov %rcx,%rsi + mov %rax,%r10 + mov %rax,offset(%rsp) + imul $something,%rsi,%rax + lea (%rsi,%rsi,4),%rdx + shl $something,%rsi mov %rax,%r12 - mov %rsi,%r8 - lea offset(%rbp,%rcx,1),%rsi + mov %rax,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rdi,%rax + mov %rdi,%rsi + and $something,%edi + mov %rdi,offset(%rsp) + mov %rsi,%rdi + and $something,%edi + sar $something,%rax + mov %rdi,offset(%rsp) + mov %rsi,%rdi + and $something,%rsi + mov %rcx,%rbx + mov %rsi,%r14 + mov %rax,%rsi + shl $something,%rsi + lea offset(,%rcx,8),%r9 + shl $something,%rbx + lea offset(,%rdx,8),%r13 + and $something,%edi + shl $something,%rcx + add %rsi,%r10 + mov %r9,offset(%rsp) + mov %rbx,offset(%rsp) + add %rsi,%r9 + add %rsi,%rbx + mov %rbp,offset(%rsp) + mov %r13,offset(%rsp) + add %rsi,%rbp + add %rsi,%r13 + mov %rax,offset(%rsp) + mov %rdi,offset(%rsp) + shl $something,%rax + lea (%r8,%r11,8),%rdi + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + add %rsi,%rcx + mov %r12,%rdi + mov %r9,offset(%rsp) + mov %rbx,offset(%rsp) + mov %rbp,offset(%rsp) + mov %r13,offset(%rsp) + mov %r10,offset(%rsp) + mov %rax,offset(%rsp) + add %rsi,%rdi + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + vmovsd %xmm29,%xmm29,%xmm28 + mov %r8,%rsi + vmovsd %xmm30,%xmm30,%xmm29 + mov %r14,%rdi + vmovsd %xmm31,%xmm31,%xmm30 + mov %r15,%r8 + vmovsd %xmm27,%xmm27,%xmm31 + nopl offset(%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%rcx,1),%r11 + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%r10 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%r9 + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%r13 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%r12 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%rbp + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%rbx + jle + xor %edx,%edx + mov %rdx,%rax + mov %rcx,%r15 + mov %rdi,%rdx + mov %r8,%r14 + vmovsd %xmm28,-offset(%rsp) + vmovsd %xmm29,-offset(%rsp) + vmovsd %xmm30,offset(%rsp) + vmovsd %xmm31,%xmm31,%xmm8 + mov %rsi,%rdi + jmp + nop + jle + vmovsd offset(%r15),%xmm7 + vmovsd offset(%r15),%xmm4 + vmovsd offset(%r15),%xmm2 + vmovsd offset(%r15),%xmm1 + vmovsd offset(%r15),%xmm6 + vmovsd offset(%r15),%xmm3 + vmovsd offset(%r15),%xmm13 + vmovsd (%r11),%xmm14 + vmovsd offset(%r11),%xmm15 + vmovsd offset(%r11),%xmm12 + vmovsd offset(%r11),%xmm11 + vmovsd offset(%r11),%xmm9 + vmovsd offset(%r11),%xmm10 + vmovsd offset(%r11),%xmm8 + vmovsd (%r10),%xmm24 + vmovsd offset(%r10),%xmm25 + vmovsd offset(%r11),%xmm26 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm2,-offset(%rsp) + vmovsd %xmm1,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd %xmm13,-offset(%rsp) + vmovsd %xmm14,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm12,-offset(%rsp) + vmovsd %xmm11,-offset(%rsp) + vmovsd %xmm9,-offset(%rsp) + vmovsd %xmm10,-offset(%rsp) + vmovsd %xmm8,(%rsp) + vmovsd %xmm24,offset(%rsp) + vmovsd %xmm25,offset(%rsp) + vmovsd offset(%r10),%xmm27 + vmovsd offset(%r10),%xmm17 + vmovsd offset(%r10),%xmm18 + vmovsd offset(%r10),%xmm20 + vmovsd (%r9),%xmm21 + vmovsd offset(%r9),%xmm22 + vmovsd offset(%r9),%xmm16 + vmovsd offset(%r9),%xmm28 + vmovsd offset(%r13),%xmm5 + vmovsd offset(%r13),%xmm29 + vmovsd offset(%r13),%xmm2 + vmovsd offset(%r9),%xmm13 + vmovsd offset(%r13),%xmm23 + vmovsd offset(%r10),%xmm25 + vmovsd offset(%r10),%xmm19 + vmovsd offset(%r9),%xmm31 + vmovsd offset(%r9),%xmm24 + vmovsd offset(%r13),%xmm30 + vmovsd offset(%r13),%xmm12 + vmovsd %xmm27,offset(%rsp) + vmovsd %xmm17,offset(%rsp) + vmovsd %xmm18,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_COOPERLAKE.o (objdump) @@ -2,34 +2,362 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t - 0010 24d848d1 fe48897c 24f84889 7424e048 $.H..H.|$.H.t$.H - 0020 85f60f8e 38010000 4889fb48 d1fb4989 ....8...H..H..I. - 0030 de4889d8 48895424 e84989cb 488d2ccd .H..H.T$.I..H.,. - 0040 00000000 4989fd49 8d347048 83e7fe49 ....I..I.4pH...I - 0050 c1e60448 c1e005c5 fb102500 0000004c ...H......%....L - 0060 894424f0 4989fa49 c1e3044c 89c74183 .D$.I..I...L..A. - 0070 e5014e8d 7c350048 89d14989 c44989f0 ..N.|5.H..I..I.. - 0080 488d740d 004885db 0f8e5201 00004c89 H.t..H....R...L. - 0090 ca31c0eb 3b0f1f00 7d29c5fb 101cc1c5 .1..;...})...... - 00a0 fb104cc1 08c5fb10 14c6c5fb 1044c608 ..L..........D.. - 00b0 c5fb111a c5fb1152 08c5fb11 4a10c5fb .......R....J... - 00c0 11421848 83c00248 83c22049 39c27434 .B.H...H.. I9.t4 - 00d0 4839f875 c3c5fb10 44c608c5 fb100cc6 H9.u....D....... - 00e0 c5db5ec0 c5db5e14 c14883c0 02c5fb11 ..^...^..H...... - 00f0 12c5fb11 4a084883 c220c5fb 1142f849 ....J.H.. ...B.I - 0100 39c275cc 4a8d1431 4a8d3439 4d01e14d 9.u.J..1J.49M..M - 0110 85ed7422 4839f80f 84a30000 007d13c5 ..t"H9.......}.. - 0120 fb100ac5 fb1006c4 c17b1109 c4c17b11 .........{....{. - 0130 41084983 c1104883 c7024c01 d94c39c7 A.I...H...L..L9. - 0140 0f853aff ffff488b 4424e04c 8b6424e8 ..:...H.D$.L.d$. - 0150 4c0fafd8 4c8b4424 f04d01dc 4d8d0440 L...L.D$.M..M..@ - 0160 f64424d8 01744848 8b5424f8 4885d27e .D$..tHH.T$.H..~ - 0170 3ec5fb10 0d000000 0031c0eb 190f1f00 >........1...... - 0180 7e0cc4c1 7b1004c4 c4c17b11 04c148ff ~...{.....{...H. - 0190 c04839c2 74194939 c075e548 ffc0c481 .H9.t.I9.u.H.... - 01a0 735e04c4 c4817b11 04c14839 c275e75b s^....{...H9.u.[ - 01b0 5d415c41 5d415e31 c0415fc3 0f1f4000 ]A\A]A^1.A_...@. - 01c0 c5fb1006 c5db5e0a c4c17b11 4108c4c1 ......^...{.A... - 01d0 7b1109e9 5affffff 0f1f8400 00000000 {...Z........... - 01e0 4889ca31 c0e925ff ffff H..1..%... + 0000 41574d89 cf415641 55415455 534881ec AWM..AVAUATUSH.. + 0010 68010000 4889b424 48010000 48c1fe03 h...H..$H...H... + 0020 4889bc24 50010000 48899424 38010000 H..$P...H..$8... + 0030 48898c24 60010000 4c898424 40010000 H..$`...L..$@... + 0040 4889b424 58010000 4885f60f 8e0c0e00 H..$X...H....... + 0050 00488d04 49488d2c c5000000 004989f3 .H..IH.,.....I.. + 0060 48c1e004 4889ce49 89c24889 8424e800 H...H..I..H..$.. + 0070 0000486b c638488d 14b648c1 e6064989 ..Hk.8H...H...I. + 0080 c4488984 24a80000 004889b4 24880000 .H..$....H..$... + 0090 004889f8 4889fe83 e7044889 bc24d000 .H..H.....H..$.. + 00a0 00004889 f783e702 48c1f803 4889bc24 ..H.....H...H..$ + 00b0 c8000000 4889f748 83e6f848 89cb4989 ....H..H...H..I. + 00c0 f64889c6 48c1e606 4c8d0ccd 00000000 .H..H...L....... + 00d0 48c1e304 4c8d2cd5 00000000 83e70148 H...L.,........H + 00e0 c1e10549 01f24c89 8c249000 00004889 ...I..L..$....H. + 00f0 9c249800 00004901 f14801f3 4889ac24 .$....I..H..H..$ + 0100 d8000000 4c89ac24 e0000000 4801f549 ....L..$....H..I + 0110 01f54889 8424b000 00004889 bc24c000 ..H..$....H..$.. + 0120 000048c1 e0094b8d 3cd84889 8c24a000 ..H...K.<.H..$.. + 0130 00004889 bc24b800 00004801 f14c89e7 ..H..$....H..L.. + 0140 4c898c24 20010000 48899c24 28010000 L..$ ...H..$(... + 0150 4889ac24 08010000 4c89ac24 18010000 H..$....L..$.... + 0160 4c899424 10010000 48898424 f0000000 L..$....H..$.... + 0170 4801f748 898c2400 01000048 8b8c2438 H..H..$....H..$8 + 0180 01000048 89b424f8 00000048 89bc2430 ...H..$....H..$0 + 0190 01000062 01970010 e54c89c6 62018f00 ...b.....L..b... + 01a0 10ee4c89 f7620187 0010f74d 89f86201 ..L..b.....M..b. + 01b0 a70010fb 0f1f4000 488b8424 90000000 ......@.H..$.... + 01c0 4883bc24 b0000000 004c8d1c 08488b84 H..$.....L...H.. + 01d0 24980000 004c8d14 08488b84 24d80000 $....L...H..$... + 01e0 004c8d0c 01488b84 24a00000 004c8d2c .L...H..$....L., + 01f0 08488b84 24e00000 004c8d24 01488b84 .H..$....L.$.H.. + 0200 24e80000 00488d2c 01488b84 24a80000 $....H.,.H..$... + 0210 00488d1c 080f8e5d 13000031 d24889d0 .H.....]...1.H.. + 0220 4989cf48 89fa4d89 c66261ff 08116424 I..H..M..ba...d$ + 0230 f16261ff 08116c24 f26261ff 08117424 .ba...l$.ba...t$ + 0240 10621187 0010c748 89f7e95c 05000090 .b.....H...\.... + 0250 0f8e2105 0000c4c1 7b107f08 c4c17b10 ..!.....{.....{. + 0260 6710c4c1 7b105718 c4c17b10 4f20c4c1 g...{.W...{.O .. + 0270 7b107728 c4c17b10 5f30c441 7b106f38 {.w(..{._0.A{.o8 + 0280 c4417b10 33c4417b 107b08c4 417b1063 .A{.3.A{.{..A{.c + 0290 18c4417b 105b20c4 417b104b 28c4417b ..A{.[ .A{.K(.A{ + 02a0 105330c4 417b1043 386241ff 08100262 .S0.A{.C8bA....b + 02b0 41ff0810 4a016241 ff081053 02c5fb11 A...J.bA...S.... + 02c0 7c2498c5 fb116424 a0c5fb11 5424a8c5 |$....d$....T$.. + 02d0 fb114c24 b0c5fb11 7424b8c5 fb115c24 ..L$....t$....\$ + 02e0 c0c57b11 6c24c8c5 7b117424 d0c57b11 ..{.l$..{.t$..{. + 02f0 7c24d8c5 7b116424 e0c57b11 5c24e8c5 |$..{.d$..{.\$.. + 0300 7b114c24 f0c57b11 5424f8c5 7b110424 {.L$..{.T$..{..$ + 0310 6261ff08 11442401 6261ff08 114c2402 ba...D$.ba...L$. + 0320 6241ff08 105a0462 c1ff0810 4a0562c1 bA...Z.b....J.b. + 0330 ff081052 0662c1ff 08106207 62c1ff08 ...R.b....b.b... + 0340 102962c1 ff081071 0562c1ff 08104106 .)b....q.b....A. + 0350 6241ff08 106107c4 c17b106d 006241ff bA...a...{.m.bA. + 0360 08106d05 c4c17b10 5530c441 7b106920 ..m...{.U0.A{.i + 0370 62c1ff08 107d0262 41ff0810 4a0262c1 b....}.bA...J.b. + 0380 ff08105a 036241ff 08107901 6241ff08 ...Z.bA...y.bA.. + 0390 10410262 41ff0810 7501c441 7b106520 .A.bA...u..A{.e + 03a0 6261ff08 115c2403 62e1ff08 114c2404 ba...\$.b....L$. + 03b0 62e1ff08 11542405 62c1ff08 104d0362 b....T$.b....M.b + 03c0 c1ff0810 510362e1 ff081164 240662e1 ....Q.b....d$.b. + 03d0 ff08116c 240762e1 ff081174 240862e1 ...l$.b....t$.b. + 03e0 ff081144 24096261 ff081164 240ac5fb ...D$.ba...d$... + 03f0 116c2488 6261ff08 116c240b c5fb1154 .l$.ba...l$....T + 0400 2460c4c1 7b104d38 c4c17b10 5c2438c4 $`..{.M8..{.\$8. + 0410 c17b1034 24c57b10 4538c4c1 7b102fc5 .{.4$.{.E8..{./. + 0420 fb115c24 70c5fb10 5d006241 ff08106c ..\$p...].bA...l + 0430 240162c1 ff081074 240262c1 ff081044 $.b....t$.b....D + 0440 2403c4c1 7b107c24 28c4c17b 10642430 $...{.|$(..{.d$0 + 0450 6261ff08 106501c5 7b105520 6261ff08 ba...e..{.U ba.. + 0460 105b0162 e1ff0810 6302c57b 107318c5 .[.b....c..{.s.. + 0470 7b104b20 c4417b10 5c242062 e1ff0810 {.K .A{.\$ b.... + 0480 6d02c57b 107d1848 8b7328c5 fb105330 m..{.}.H.s(...S0 + 0490 c5fb114c 2468c5fb 11742490 c5fb104b ...L$h...t$....K + 04a0 38c5fb10 7528c5e3 10c3c5fb 119c2480 8...u(........$. + 04b0 000000c5 7b114424 78c5fb10 5d30c57b ....{.D$x...]0.{ + 04c0 1003c4c1 7b112ec5 fb106c24 d06241ff ....{.....l$.bA. + 04d0 08116e0d c4c17b11 6e08c5fb 106c2408 ..n...{.n....l$. + 04e0 6241ff08 11660ec4 c17b116e 10c5fb10 bA...f...{.n.... + 04f0 6c243862 41ff0811 5e0fc4c1 7b116e18 l$8bA...^...{.n. + 0500 c5fb106c 248862c1 ff08117e 14c4c17b ...l$.b....~...{ + 0510 116e20c5 fb106c24 9062c1ff 08117615 .n ...l$.b....v. + 0520 c4c17b11 6e28c5fb 106c2498 62c1ff08 ..{.n(...l$.b... + 0530 116617c4 c17b116e 40c5fb10 6c24d8c4 .f...{.n@...l$.. + 0540 c17b1146 30c4c17b 116e48c5 fb106c24 .{.F0..{.nH...l$ + 0550 10c4417b 114638c4 c17b116e 50c5fb10 ..A{.F8..{.nP... + 0560 6c24a062 41ff0811 7e0b6241 ff081176 l$.bA...~.bA...v + 0570 0cc4c17b 11ae8000 00006241 ff081156 ...{......bA...V + 0580 116241ff 08114e12 6241ff08 11461362 .bA...N.bA...F.b + 0590 c1ff0811 6e16c5fb 106c24a8 62e1ff08 ....n....l$.b... + 05a0 107c24fc c4c17b11 aec00000 00c5fb10 .|$...{......... + 05b0 6c24b062 61ff0810 5c240362 e1ff0810 l$.ba...\$.b.... + 05c0 74240862 61ff0810 6c240b62 c1ff0811 t$.ba...l$.b.... + 05d0 4e1cc441 7b11b6f8 00000062 e1ff0810 N..A{......b.... + 05e0 4c2404c5 7b107424 e8c4c17b 11ae0001 L$..{.t$...{.... + 05f0 0000c441 7b118e38 010000c5 fb106c24 ...A{..8......l$ + 0600 b8c57b10 4c24f062 c1ff0811 561b62c1 ..{.L$.b....V.b. + 0610 ff081146 1dc4417b 11ae1801 0000c441 ...F..A{.......A + 0620 7b119630 010000c4 c17b11be 68010000 {..0.....{..h... + 0630 62c1ff08 117e1962 c1ff0811 5e1ac441 b....~.b....^..A + 0640 7b11bef0 000000c4 417b11b6 08010000 {.......A{...... + 0650 6241ff08 115e22c4 417b11a6 20010000 bA...^".A{.. ... + 0660 c4417b11 9e280100 00c4c17b 11ae4001 .A{..(.....{..@. + 0670 0000c441 7b118e48 01000062 c1ff0811 ...A{..H...b.... + 0680 4e2a62c1 ff081176 2b6241ff 08116e2c N*b....v+bA...n, + 0690 c4c17b11 b6700100 00c5fb10 7c24c0c4 ..{..p......|$.. + 06a0 c17b11a6 a8010000 c5fb1024 24c57b10 .{.........$$.{. + 06b0 5424f862 e1ff0810 54240562 e1ff0810 T$.b....T$.b.... + 06c0 442409c5 fb107424 60c57b10 6c24c862 D$....t$`.{.l$.b + 06d0 e1ff0810 64240662 61ff0810 64240ac4 ....d$.ba...d$.. + 06e0 c17b11be 80010000 c4c17b11 9eb00100 .{........{..... + 06f0 00c5fb10 7c2468c5 fb105c24 70c4c17b ....|$h...\$p..{ + 0700 11a6c801 00004989 b6780100 00c5fb10 ......I..x...... + 0710 642478c4 417b1196 88010000 62c1ff08 d$x.A{......b... + 0720 11563262 c1ff0811 4633c4c1 7b11b6a0 .V2b....F3..{... + 0730 010000c4 c17b1196 b8010000 c4417b11 .....{.......A{. + 0740 aec00100 0062c1ff 0811663a 6241ff08 .....b....f:bA.. + 0750 11663bc4 c17b11be e0010000 c4c17b11 .f;..{........{. + 0760 9ee80100 00c4c17b 11a6f001 0000c4c1 .......{........ + 0770 7b118ef8 01000048 83c00849 83c74049 {......H...I..@I + 0780 83c34049 83c24049 83c14049 83c54049 ..@I..@I..@I..@I + 0790 83c44048 83c54048 83c34049 81c60002 ..@H..@H..@I.... + 07a0 00004839 d00f8465 02000048 39c70f85 ..H9...e...H9... + 07b0 9cfaffff c57b107d 00c4c17b 105500c4 .....{.}...{.U.. + 07c0 c17b100c 24c57b10 5d30c503 11f86241 .{..$.{.]0....bA + 07d0 ff08103b c4c17b10 7b086241 ff081032 ...;..{.{.bA...2 + 07e0 6241ff08 106201c4 c17b1072 106241ff bA...b...{.r.bA. + 07f0 08102962 41ff0810 590162c1 ff081071 ..)bA...Y.b....q + 0800 02c4c17b 10691862 41ff0810 550162c1 ...{.i.bA...U.b. + 0810 ff08106d 0262c1ff 08104d03 c4c17b10 ...m.b....M...{. + 0820 65206241 ff08104c 240162c1 ff081064 e bA...L$.b....d + 0830 240262c1 ff081044 2403c441 7b106c24 $.b....D$..A{.l$ + 0840 20c4c17b 105c2428 6261ff08 10450162 ..{.\$(ba...E.b + 0850 e1ff0810 5d02c57b 106520c5 7b105528 ....]..{.e .{.U( + 0860 c57b1003 c5fb1154 2488c5fb 114c2490 .{.....T$....L$. + 0870 c57b11bc 24800000 00c57b11 5c2498c5 .{..$.....{.\$.. + 0880 7b107d18 62e1ff08 107b01c5 fb105338 {.}.b....{....S8 + 0890 c5fb104b 30c5fb11 5424a0c5 fb101500 ...K0...T$...... + 08a0 00000062 e1ff0810 5302c57b 107318c5 ...b....S..{.s.. + 08b0 7b105b20 c57b104b 28c4c16b 5e17c4c1 {.[ .{.K(..k^... + 08c0 7b114630 c5fb1005 00000000 c4c17b11 {.F0..........{. + 08d0 16c5fb5e ffc5fb10 54248862 41ff0811 ...^....T$.bA... + 08e0 7e01c4c1 7b115620 c5fb1054 24906241 ~...{.V ...T$.bA + 08f0 ff081176 02c4c17b 11562862 41ff0811 ...v...{.V(bA... + 0900 6e03c441 7b114638 6241ff08 11660a62 n..A{.F8bA...f.b + 0910 41ff0811 5e0b6241 ff081156 0c6241ff A...^.bA...V.bA. + 0920 08114e0d 6241ff08 11460e62 c1ff0811 ..N.bA...F.b.... + 0930 7e0f62c1 ff081176 1362c1ff 08116e14 ~.b....v.b....n. + 0940 62c1ff08 116615c5 fb5ef6c4 c17b117e b....f...^...{.~ + 0950 48c5fb5e edc4c17b 11b69000 000062c1 H..^...{......b. + 0960 ff08115e 16c4c17b 118eb801 0000c5fb ...^...{........ + 0970 5e542498 c5fb5e4c 24a062c1 ff081156 ^T$...^L$.b....V + 0980 1762c1ff 08114e1c 62c1ff08 11461dc4 .b....N.b....F.. + 0990 417b11be f0000000 c4417b11 b6f80000 A{.......A{..... + 09a0 00c4417b 11ae2801 0000c441 7b11a630 ..A{..(....A{..0 + 09b0 010000c5 fb5ee4c4 417b119e 38010000 .....^..A{..8... + 09c0 c4417b11 96700100 00c4417b 118e7801 .A{..p....A{..x. + 09d0 0000c4c1 7b1196b0 010000c4 c17b118e ....{........{.. + 09e0 f8010000 c4c17b11 aed80000 00c5fb5e ......{........^ + 09f0 dbc4c17b 11a62001 0000c4c1 7b119e68 ...{.. .....{..h + 0a00 010000e9 6ffdffff 0f1f8400 00000000 ....o........... + 0a10 4889fe48 89d7488b 94242001 0000488b H..H..H..$ ...H. + 0a20 8424f800 00004c8d 1c11488b 94242801 .$....L...H..$(. /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 ea010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 a3010a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 61160000 00420e10 8f02450e ....a....B....E. + 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 + 0040 8606410e 38830747 0ea00303 50150a0e ..A.8..G....P... + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0848 0b000000 D..H.... /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_SKYLAKEX.o (disasm) @@ -6,118 +6,933 @@ dtrsm_ounncopy_SKYLAKEX: push %r15 + mov %r9,%r15 push %r14 push %r13 push %r12 - mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rdi,%rbx - sar %rbx - mov %rbx,%r14 - mov %rbx,%rax - mov %rdx,-offset(%rsp) - mov %rcx,%r11 - lea offset(,%rcx,8),%rbp - mov %rdi,%r13 - lea (%r8,%rsi,2),%rsi - and $something,%rdi - shl $something,%r14 + lea (%rcx,%rcx,2),%rax + lea offset(,%rax,8),%rbp + mov %rsi,%r11 shl $something,%rax - vmovsd offset(%rip),%xmm4 # - mov %r8,-offset(%rsp) - mov %rdi,%r10 - shl $something,%r11 - mov %r8,%rdi - and $something,%r13d - lea offset(%rbp,%r14,1),%r15 - mov %rdx,%rcx + mov %rcx,%rsi + mov %rax,%r10 + mov %rax,offset(%rsp) + imul $something,%rsi,%rax + lea (%rsi,%rsi,4),%rdx + shl $something,%rsi mov %rax,%r12 - mov %rsi,%r8 - lea offset(%rbp,%rcx,1),%rsi + mov %rax,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rdi,%rax + mov %rdi,%rsi + and $something,%edi + mov %rdi,offset(%rsp) + mov %rsi,%rdi + and $something,%edi + sar $something,%rax + mov %rdi,offset(%rsp) + mov %rsi,%rdi + and $something,%rsi + mov %rcx,%rbx + mov %rsi,%r14 + mov %rax,%rsi + shl $something,%rsi + lea offset(,%rcx,8),%r9 + shl $something,%rbx + lea offset(,%rdx,8),%r13 + and $something,%edi + shl $something,%rcx + add %rsi,%r10 + mov %r9,offset(%rsp) + mov %rbx,offset(%rsp) + add %rsi,%r9 + add %rsi,%rbx + mov %rbp,offset(%rsp) + mov %r13,offset(%rsp) + add %rsi,%rbp + add %rsi,%r13 + mov %rax,offset(%rsp) + mov %rdi,offset(%rsp) + shl $something,%rax + lea (%r8,%r11,8),%rdi + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + add %rsi,%rcx + mov %r12,%rdi + mov %r9,offset(%rsp) + mov %rbx,offset(%rsp) + mov %rbp,offset(%rsp) + mov %r13,offset(%rsp) + mov %r10,offset(%rsp) + mov %rax,offset(%rsp) + add %rsi,%rdi + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + vmovsd %xmm29,%xmm29,%xmm28 + mov %r8,%rsi + vmovsd %xmm30,%xmm30,%xmm29 + mov %r14,%rdi + vmovsd %xmm31,%xmm31,%xmm30 + mov %r15,%r8 + vmovsd %xmm27,%xmm27,%xmm31 + nopl offset(%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%rcx,1),%r11 + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%r10 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%r9 + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%r13 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%r12 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%rbp + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%rbx + jle + xor %edx,%edx + mov %rdx,%rax + mov %rcx,%r15 + mov %rdi,%rdx + mov %r8,%r14 + vmovsd %xmm28,-offset(%rsp) + vmovsd %xmm29,-offset(%rsp) + vmovsd %xmm30,offset(%rsp) + vmovsd %xmm31,%xmm31,%xmm8 + mov %rsi,%rdi + jmp + nop + jle + vmovsd offset(%r15),%xmm7 + vmovsd offset(%r15),%xmm4 + vmovsd offset(%r15),%xmm2 + vmovsd offset(%r15),%xmm1 + vmovsd offset(%r15),%xmm6 + vmovsd offset(%r15),%xmm3 + vmovsd offset(%r15),%xmm13 + vmovsd (%r11),%xmm14 + vmovsd offset(%r11),%xmm15 + vmovsd offset(%r11),%xmm12 + vmovsd offset(%r11),%xmm11 + vmovsd offset(%r11),%xmm9 + vmovsd offset(%r11),%xmm10 + vmovsd offset(%r11),%xmm8 + vmovsd (%r10),%xmm24 + vmovsd offset(%r10),%xmm25 + vmovsd offset(%r11),%xmm26 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm2,-offset(%rsp) + vmovsd %xmm1,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd %xmm13,-offset(%rsp) + vmovsd %xmm14,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm12,-offset(%rsp) + vmovsd %xmm11,-offset(%rsp) + vmovsd %xmm9,-offset(%rsp) + vmovsd %xmm10,-offset(%rsp) + vmovsd %xmm8,(%rsp) + vmovsd %xmm24,offset(%rsp) + vmovsd %xmm25,offset(%rsp) + vmovsd offset(%r10),%xmm27 + vmovsd offset(%r10),%xmm17 + vmovsd offset(%r10),%xmm18 + vmovsd offset(%r10),%xmm20 + vmovsd (%r9),%xmm21 + vmovsd offset(%r9),%xmm22 + vmovsd offset(%r9),%xmm16 + vmovsd offset(%r9),%xmm28 + vmovsd offset(%r13),%xmm5 + vmovsd offset(%r13),%xmm29 + vmovsd offset(%r13),%xmm2 + vmovsd offset(%r9),%xmm13 + vmovsd offset(%r13),%xmm23 + vmovsd offset(%r10),%xmm25 + vmovsd offset(%r10),%xmm19 + vmovsd offset(%r9),%xmm31 + vmovsd offset(%r9),%xmm24 + vmovsd offset(%r13),%xmm30 + vmovsd offset(%r13),%xmm12 + vmovsd %xmm27,offset(%rsp) + vmovsd %xmm17,offset(%rsp) + vmovsd %xmm18,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_SKYLAKEX.o (objdump) @@ -2,34 +2,362 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t - 0010 24d848d1 fe48897c 24f84889 7424e048 $.H..H.|$.H.t$.H - 0020 85f60f8e 38010000 4889fb48 d1fb4989 ....8...H..H..I. - 0030 de4889d8 48895424 e84989cb 488d2ccd .H..H.T$.I..H.,. - 0040 00000000 4989fd49 8d347048 83e7fe49 ....I..I.4pH...I - 0050 c1e60448 c1e005c5 fb102500 0000004c ...H......%....L - 0060 894424f0 4989fa49 c1e3044c 89c74183 .D$.I..I...L..A. - 0070 e5014e8d 7c350048 89d14989 c44989f0 ..N.|5.H..I..I.. - 0080 488d740d 004885db 0f8e5201 00004c89 H.t..H....R...L. - 0090 ca31c0eb 3b0f1f00 7d29c5fb 101cc1c5 .1..;...})...... - 00a0 fb104cc1 08c5fb10 14c6c5fb 1044c608 ..L..........D.. - 00b0 c5fb111a c5fb1152 08c5fb11 4a10c5fb .......R....J... - 00c0 11421848 83c00248 83c22049 39c27434 .B.H...H.. I9.t4 - 00d0 4839f875 c3c5fb10 44c608c5 fb100cc6 H9.u....D....... - 00e0 c5db5ec0 c5db5e14 c14883c0 02c5fb11 ..^...^..H...... - 00f0 12c5fb11 4a084883 c220c5fb 1142f849 ....J.H.. ...B.I - 0100 39c275cc 4a8d1431 4a8d3439 4d01e14d 9.u.J..1J.49M..M - 0110 85ed7422 4839f80f 84a30000 007d13c5 ..t"H9.......}.. - 0120 fb100ac5 fb1006c4 c17b1109 c4c17b11 .........{....{. - 0130 41084983 c1104883 c7024c01 d94c39c7 A.I...H...L..L9. - 0140 0f853aff ffff488b 4424e04c 8b6424e8 ..:...H.D$.L.d$. - 0150 4c0fafd8 4c8b4424 f04d01dc 4d8d0440 L...L.D$.M..M..@ - 0160 f64424d8 01744848 8b5424f8 4885d27e .D$..tHH.T$.H..~ - 0170 3ec5fb10 0d000000 0031c0eb 190f1f00 >........1...... - 0180 7e0cc4c1 7b1004c4 c4c17b11 04c148ff ~...{.....{...H. - 0190 c04839c2 74194939 c075e548 ffc0c481 .H9.t.I9.u.H.... - 01a0 735e04c4 c4817b11 04c14839 c275e75b s^....{...H9.u.[ - 01b0 5d415c41 5d415e31 c0415fc3 0f1f4000 ]A\A]A^1.A_...@. - 01c0 c5fb1006 c5db5e0a c4c17b11 4108c4c1 ......^...{.A... - 01d0 7b1109e9 5affffff 0f1f8400 00000000 {...Z........... - 01e0 4889ca31 c0e925ff ffff H..1..%... + 0000 41574d89 cf415641 55415455 534881ec AWM..AVAUATUSH.. + 0010 68010000 4889b424 48010000 48c1fe03 h...H..$H...H... + 0020 4889bc24 50010000 48899424 38010000 H..$P...H..$8... + 0030 48898c24 60010000 4c898424 40010000 H..$`...L..$@... + 0040 4889b424 58010000 4885f60f 8e0c0e00 H..$X...H....... + 0050 00488d04 49488d2c c5000000 004989f3 .H..IH.,.....I.. + 0060 48c1e004 4889ce49 89c24889 8424e800 H...H..I..H..$.. + 0070 0000486b c638488d 14b648c1 e6064989 ..Hk.8H...H...I. + 0080 c4488984 24a80000 004889b4 24880000 .H..$....H..$... + 0090 004889f8 4889fe83 e7044889 bc24d000 .H..H.....H..$.. + 00a0 00004889 f783e702 48c1f803 4889bc24 ..H.....H...H..$ + 00b0 c8000000 4889f748 83e6f848 89cb4989 ....H..H...H..I. + 00c0 f64889c6 48c1e606 4c8d0ccd 00000000 .H..H...L....... + 00d0 48c1e304 4c8d2cd5 00000000 83e70148 H...L.,........H + 00e0 c1e10549 01f24c89 8c249000 00004889 ...I..L..$....H. + 00f0 9c249800 00004901 f14801f3 4889ac24 .$....I..H..H..$ + 0100 d8000000 4c89ac24 e0000000 4801f549 ....L..$....H..I + 0110 01f54889 8424b000 00004889 bc24c000 ..H..$....H..$.. + 0120 000048c1 e0094b8d 3cd84889 8c24a000 ..H...K.<.H..$.. + 0130 00004889 bc24b800 00004801 f14c89e7 ..H..$....H..L.. + 0140 4c898c24 20010000 48899c24 28010000 L..$ ...H..$(... + 0150 4889ac24 08010000 4c89ac24 18010000 H..$....L..$.... + 0160 4c899424 10010000 48898424 f0000000 L..$....H..$.... + 0170 4801f748 898c2400 01000048 8b8c2438 H..H..$....H..$8 + 0180 01000048 89b424f8 00000048 89bc2430 ...H..$....H..$0 + 0190 01000062 01970010 e54c89c6 62018f00 ...b.....L..b... + 01a0 10ee4c89 f7620187 0010f74d 89f86201 ..L..b.....M..b. + 01b0 a70010fb 0f1f4000 488b8424 90000000 ......@.H..$.... + 01c0 4883bc24 b0000000 004c8d1c 08488b84 H..$.....L...H.. + 01d0 24980000 004c8d14 08488b84 24d80000 $....L...H..$... + 01e0 004c8d0c 01488b84 24a00000 004c8d2c .L...H..$....L., + 01f0 08488b84 24e00000 004c8d24 01488b84 .H..$....L.$.H.. + 0200 24e80000 00488d2c 01488b84 24a80000 $....H.,.H..$... + 0210 00488d1c 080f8e5d 13000031 d24889d0 .H.....]...1.H.. + 0220 4989cf48 89fa4d89 c66261ff 08116424 I..H..M..ba...d$ + 0230 f16261ff 08116c24 f26261ff 08117424 .ba...l$.ba...t$ + 0240 10621187 0010c748 89f7e95c 05000090 .b.....H...\.... + 0250 0f8e2105 0000c4c1 7b107f08 c4c17b10 ..!.....{.....{. + 0260 6710c4c1 7b105718 c4c17b10 4f20c4c1 g...{.W...{.O .. + 0270 7b107728 c4c17b10 5f30c441 7b106f38 {.w(..{._0.A{.o8 + 0280 c4417b10 33c4417b 107b08c4 417b1063 .A{.3.A{.{..A{.c + 0290 18c4417b 105b20c4 417b104b 28c4417b ..A{.[ .A{.K(.A{ + 02a0 105330c4 417b1043 386241ff 08100262 .S0.A{.C8bA....b + 02b0 41ff0810 4a016241 ff081053 02c5fb11 A...J.bA...S.... + 02c0 7c2498c5 fb116424 a0c5fb11 5424a8c5 |$....d$....T$.. + 02d0 fb114c24 b0c5fb11 7424b8c5 fb115c24 ..L$....t$....\$ + 02e0 c0c57b11 6c24c8c5 7b117424 d0c57b11 ..{.l$..{.t$..{. + 02f0 7c24d8c5 7b116424 e0c57b11 5c24e8c5 |$..{.d$..{.\$.. + 0300 7b114c24 f0c57b11 5424f8c5 7b110424 {.L$..{.T$..{..$ + 0310 6261ff08 11442401 6261ff08 114c2402 ba...D$.ba...L$. + 0320 6241ff08 105a0462 c1ff0810 4a0562c1 bA...Z.b....J.b. + 0330 ff081052 0662c1ff 08106207 62c1ff08 ...R.b....b.b... + 0340 102962c1 ff081071 0562c1ff 08104106 .)b....q.b....A. + 0350 6241ff08 106107c4 c17b106d 006241ff bA...a...{.m.bA. + 0360 08106d05 c4c17b10 5530c441 7b106920 ..m...{.U0.A{.i + 0370 62c1ff08 107d0262 41ff0810 4a0262c1 b....}.bA...J.b. + 0380 ff08105a 036241ff 08107901 6241ff08 ...Z.bA...y.bA.. + 0390 10410262 41ff0810 7501c441 7b106520 .A.bA...u..A{.e + 03a0 6261ff08 115c2403 62e1ff08 114c2404 ba...\$.b....L$. + 03b0 62e1ff08 11542405 62c1ff08 104d0362 b....T$.b....M.b + 03c0 c1ff0810 510362e1 ff081164 240662e1 ....Q.b....d$.b. + 03d0 ff08116c 240762e1 ff081174 240862e1 ...l$.b....t$.b. + 03e0 ff081144 24096261 ff081164 240ac5fb ...D$.ba...d$... + 03f0 116c2488 6261ff08 116c240b c5fb1154 .l$.ba...l$....T + 0400 2460c4c1 7b104d38 c4c17b10 5c2438c4 $`..{.M8..{.\$8. + 0410 c17b1034 24c57b10 4538c4c1 7b102fc5 .{.4$.{.E8..{./. + 0420 fb115c24 70c5fb10 5d006241 ff08106c ..\$p...].bA...l + 0430 240162c1 ff081074 240262c1 ff081044 $.b....t$.b....D + 0440 2403c4c1 7b107c24 28c4c17b 10642430 $...{.|$(..{.d$0 + 0450 6261ff08 106501c5 7b105520 6261ff08 ba...e..{.U ba.. + 0460 105b0162 e1ff0810 6302c57b 107318c5 .[.b....c..{.s.. + 0470 7b104b20 c4417b10 5c242062 e1ff0810 {.K .A{.\$ b.... + 0480 6d02c57b 107d1848 8b7328c5 fb105330 m..{.}.H.s(...S0 + 0490 c5fb114c 2468c5fb 11742490 c5fb104b ...L$h...t$....K + 04a0 38c5fb10 7528c5e3 10c3c5fb 119c2480 8...u(........$. + 04b0 000000c5 7b114424 78c5fb10 5d30c57b ....{.D$x...]0.{ + 04c0 1003c4c1 7b112ec5 fb106c24 d06241ff ....{.....l$.bA. + 04d0 08116e0d c4c17b11 6e08c5fb 106c2408 ..n...{.n....l$. + 04e0 6241ff08 11660ec4 c17b116e 10c5fb10 bA...f...{.n.... + 04f0 6c243862 41ff0811 5e0fc4c1 7b116e18 l$8bA...^...{.n. + 0500 c5fb106c 248862c1 ff08117e 14c4c17b ...l$.b....~...{ + 0510 116e20c5 fb106c24 9062c1ff 08117615 .n ...l$.b....v. + 0520 c4c17b11 6e28c5fb 106c2498 62c1ff08 ..{.n(...l$.b... + 0530 116617c4 c17b116e 40c5fb10 6c24d8c4 .f...{.n@...l$.. + 0540 c17b1146 30c4c17b 116e48c5 fb106c24 .{.F0..{.nH...l$ + 0550 10c4417b 114638c4 c17b116e 50c5fb10 ..A{.F8..{.nP... + 0560 6c24a062 41ff0811 7e0b6241 ff081176 l$.bA...~.bA...v + 0570 0cc4c17b 11ae8000 00006241 ff081156 ...{......bA...V + 0580 116241ff 08114e12 6241ff08 11461362 .bA...N.bA...F.b + 0590 c1ff0811 6e16c5fb 106c24a8 62e1ff08 ....n....l$.b... + 05a0 107c24fc c4c17b11 aec00000 00c5fb10 .|$...{......... + 05b0 6c24b062 61ff0810 5c240362 e1ff0810 l$.ba...\$.b.... + 05c0 74240862 61ff0810 6c240b62 c1ff0811 t$.ba...l$.b.... + 05d0 4e1cc441 7b11b6f8 00000062 e1ff0810 N..A{......b.... + 05e0 4c2404c5 7b107424 e8c4c17b 11ae0001 L$..{.t$...{.... + 05f0 0000c441 7b118e38 010000c5 fb106c24 ...A{..8......l$ + 0600 b8c57b10 4c24f062 c1ff0811 561b62c1 ..{.L$.b....V.b. + 0610 ff081146 1dc4417b 11ae1801 0000c441 ...F..A{.......A + 0620 7b119630 010000c4 c17b11be 68010000 {..0.....{..h... + 0630 62c1ff08 117e1962 c1ff0811 5e1ac441 b....~.b....^..A + 0640 7b11bef0 000000c4 417b11b6 08010000 {.......A{...... + 0650 6241ff08 115e22c4 417b11a6 20010000 bA...^".A{.. ... + 0660 c4417b11 9e280100 00c4c17b 11ae4001 .A{..(.....{..@. + 0670 0000c441 7b118e48 01000062 c1ff0811 ...A{..H...b.... + 0680 4e2a62c1 ff081176 2b6241ff 08116e2c N*b....v+bA...n, + 0690 c4c17b11 b6700100 00c5fb10 7c24c0c4 ..{..p......|$.. + 06a0 c17b11a6 a8010000 c5fb1024 24c57b10 .{.........$$.{. + 06b0 5424f862 e1ff0810 54240562 e1ff0810 T$.b....T$.b.... + 06c0 442409c5 fb107424 60c57b10 6c24c862 D$....t$`.{.l$.b + 06d0 e1ff0810 64240662 61ff0810 64240ac4 ....d$.ba...d$.. + 06e0 c17b11be 80010000 c4c17b11 9eb00100 .{........{..... + 06f0 00c5fb10 7c2468c5 fb105c24 70c4c17b ....|$h...\$p..{ + 0700 11a6c801 00004989 b6780100 00c5fb10 ......I..x...... + 0710 642478c4 417b1196 88010000 62c1ff08 d$x.A{......b... + 0720 11563262 c1ff0811 4633c4c1 7b11b6a0 .V2b....F3..{... + 0730 010000c4 c17b1196 b8010000 c4417b11 .....{.......A{. + 0740 aec00100 0062c1ff 0811663a 6241ff08 .....b....f:bA.. + 0750 11663bc4 c17b11be e0010000 c4c17b11 .f;..{........{. + 0760 9ee80100 00c4c17b 11a6f001 0000c4c1 .......{........ + 0770 7b118ef8 01000048 83c00849 83c74049 {......H...I..@I + 0780 83c34049 83c24049 83c14049 83c54049 ..@I..@I..@I..@I + 0790 83c44048 83c54048 83c34049 81c60002 ..@H..@H..@I.... + 07a0 00004839 d00f8465 02000048 39c70f85 ..H9...e...H9... + 07b0 9cfaffff c57b107d 00c4c17b 105500c4 .....{.}...{.U.. + 07c0 c17b100c 24c57b10 5d30c503 11f86241 .{..$.{.]0....bA + 07d0 ff08103b c4c17b10 7b086241 ff081032 ...;..{.{.bA...2 + 07e0 6241ff08 106201c4 c17b1072 106241ff bA...b...{.r.bA. + 07f0 08102962 41ff0810 590162c1 ff081071 ..)bA...Y.b....q + 0800 02c4c17b 10691862 41ff0810 550162c1 ...{.i.bA...U.b. + 0810 ff08106d 0262c1ff 08104d03 c4c17b10 ...m.b....M...{. + 0820 65206241 ff08104c 240162c1 ff081064 e bA...L$.b....d + 0830 240262c1 ff081044 2403c441 7b106c24 $.b....D$..A{.l$ + 0840 20c4c17b 105c2428 6261ff08 10450162 ..{.\$(ba...E.b + 0850 e1ff0810 5d02c57b 106520c5 7b105528 ....]..{.e .{.U( + 0860 c57b1003 c5fb1154 2488c5fb 114c2490 .{.....T$....L$. + 0870 c57b11bc 24800000 00c57b11 5c2498c5 .{..$.....{.\$.. + 0880 7b107d18 62e1ff08 107b01c5 fb105338 {.}.b....{....S8 + 0890 c5fb104b 30c5fb11 5424a0c5 fb101500 ...K0...T$...... + 08a0 00000062 e1ff0810 5302c57b 107318c5 ...b....S..{.s.. + 08b0 7b105b20 c57b104b 28c4c16b 5e17c4c1 {.[ .{.K(..k^... + 08c0 7b114630 c5fb1005 00000000 c4c17b11 {.F0..........{. + 08d0 16c5fb5e ffc5fb10 54248862 41ff0811 ...^....T$.bA... + 08e0 7e01c4c1 7b115620 c5fb1054 24906241 ~...{.V ...T$.bA + 08f0 ff081176 02c4c17b 11562862 41ff0811 ...v...{.V(bA... + 0900 6e03c441 7b114638 6241ff08 11660a62 n..A{.F8bA...f.b + 0910 41ff0811 5e0b6241 ff081156 0c6241ff A...^.bA...V.bA. + 0920 08114e0d 6241ff08 11460e62 c1ff0811 ..N.bA...F.b.... + 0930 7e0f62c1 ff081176 1362c1ff 08116e14 ~.b....v.b....n. + 0940 62c1ff08 116615c5 fb5ef6c4 c17b117e b....f...^...{.~ + 0950 48c5fb5e edc4c17b 11b69000 000062c1 H..^...{......b. + 0960 ff08115e 16c4c17b 118eb801 0000c5fb ...^...{........ + 0970 5e542498 c5fb5e4c 24a062c1 ff081156 ^T$...^L$.b....V + 0980 1762c1ff 08114e1c 62c1ff08 11461dc4 .b....N.b....F.. + 0990 417b11be f0000000 c4417b11 b6f80000 A{.......A{..... + 09a0 00c4417b 11ae2801 0000c441 7b11a630 ..A{..(....A{..0 + 09b0 010000c5 fb5ee4c4 417b119e 38010000 .....^..A{..8... + 09c0 c4417b11 96700100 00c4417b 118e7801 .A{..p....A{..x. + 09d0 0000c4c1 7b1196b0 010000c4 c17b118e ....{........{.. + 09e0 f8010000 c4c17b11 aed80000 00c5fb5e ......{........^ + 09f0 dbc4c17b 11a62001 0000c4c1 7b119e68 ...{.. .....{..h + 0a00 010000e9 6ffdffff 0f1f8400 00000000 ....o........... + 0a10 4889fe48 89d7488b 94242001 0000488b H..H..H..$ ...H. + 0a20 8424f800 00004c8d 1c11488b 94242801 .$....L...H..$(. /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounncopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 ea010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 a3010a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 61160000 00420e10 8f02450e ....a....B....E. + 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 + 0040 8606410e 38830747 0ea00303 50150a0e ..A.8..G....P... + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0848 0b000000 D..H.... /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_COOPERLAKE.o (disasm) @@ -7,111 +7,871 @@ dtrsm_ounucopy_COOPERLAKE: push %r15 push %r14 + mov %r9,%r14 push %r13 push %r12 + mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rdi,%rbx - sar %rbx - mov %rbx,%r13 - mov %rcx,%r11 - lea offset(,%rcx,8),%rbp - mov %rdi,%r12 - lea (%r8,%rsi,2),%rax + lea (%rcx,%rcx,2),%rax + lea offset(,%rax,8),%r9 + lea (%rcx,%rcx,4),%rdx + shl $something,%rax + lea offset(,%rcx,8),%r10 + lea offset(,%rdx,8),%rbp + mov %rsi,%r11 + mov %rcx,%rbx + mov %rcx,%rsi + mov %rax,%rdx + mov %rax,offset(%rsp) + imul $something,%rcx,%rax + shl $something,%rcx + mov %rcx,offset(%rsp) + mov %rdi,%rcx + and $something,%ecx + mov %rcx,offset(%rsp) + mov %rdi,%rcx + mov %rax,offset(%rsp) + and $something,%ecx + mov %rdi,%rax + sar $something,%rax + mov %rcx,offset(%rsp) + mov %rdi,%rcx and $something,%rdi - shl $something,%r13 - mov %rbx,%r14 - vmovsd offset(%rip),%xmm4 # - mov %r8,-offset(%rsp) - mov %rdi,%r10 - shl $something,%r11 - mov %r8,%rdi - and $something,%r12d - lea offset(%rbp,%r13,1),%r15 - shl $something,%r14 - mov %rdx,%rcx - mov %rax,%r8 + mov %rdi,%r13 + mov %rax,%rdi + shl $something,%rdi + shl $something,%rsi + shl $something,%rbx + mov %rsi,offset(%rsp) + add %rdi,%rsi + add %rdi,%rdx + mov %r10,offset(%rsp) + mov %rbx,offset(%rsp) + add %rdi,%r10 + add %rdi,%rbx + mov %r9,offset(%rsp) + mov %rbp,offset(%rsp) + add %rdi,%r9 + add %rdi,%rbp + mov %rax,offset(%rsp) + mov %rsi,offset(%rsp) + shl $something,%rax + mov offset(%rsp),%rsi + and $something,%ecx + mov %r10,offset(%rsp) + mov %rbx,offset(%rsp) + mov %r9,offset(%rsp) + mov %rbp,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rax,offset(%rsp) + mov %r12,offset(%rsp) + add %rdi,%rsi + mov %rcx,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + lea (%r8,%r11,8),%rcx + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rsi,offset(%rsp) + vmovsd %xmm29,%xmm29,%xmm28 + mov %r8,%rsi + vmovsd %xmm30,%xmm30,%xmm29 + mov %r12,%rcx + vmovsd %xmm31,%xmm31,%xmm30 + mov %r13,%rdi + vmovsd %xmm27,%xmm27,%xmm31 + mov %r14,%r8 + nopl offset(%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%rcx,1),%r11 + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%r10 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%r9 + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%r13 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%r12 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%rbp + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%rbx + jle + xor %eax,%eax + mov %rax,%r15 + mov %rcx,%r14 + mov %rcx,%rax + mov %r8,%rdx + mov %rsi,%rcx + vmovsd %xmm28,%xmm28,%xmm25 + vmovsd %xmm29,%xmm29,%xmm26 + vmovsd %xmm30,%xmm30,%xmm27 + mov %r15,%rsi + jmp + xchg %ax,%ax + jle + vmovsd offset(%r14),%xmm7 + vmovsd (%r10),%xmm9 + vmovsd offset(%r14),%xmm6 + vmovsd offset(%r14),%xmm5 + vmovsd offset(%r14),%xmm4 + vmovsd offset(%r14),%xmm3 + vmovsd offset(%r14),%xmm2 + vmovsd offset(%r14),%xmm1 + vmovsd offset(%r11),%xmm13 + vmovsd offset(%r11),%xmm14 + vmovsd offset(%r11),%xmm15 + vmovsd offset(%r11),%xmm10 + vmovsd offset(%r11),%xmm11 + vmovsd offset(%r11),%xmm12 + vmovsd offset(%r11),%xmm8 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm9,%xmm9,%xmm7 + vmovsd offset(%r10),%xmm9 + mov (%r11),%r15 + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd %xmm2,-offset(%rsp) + vmovsd %xmm1,-offset(%rsp) + vmovsd %xmm13,-offset(%rsp) + vmovsd %xmm14,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm10,-offset(%rsp) + vmovsd %xmm11,-offset(%rsp) + vmovsd %xmm12,-offset(%rsp) + vmovsd %xmm8,-offset(%rsp) + vmovsd %xmm9,-offset(%rsp) + vmovsd offset(%r10),%xmm24 + vmovsd offset(%r10),%xmm20 + vmovsd offset(%r10),%xmm21 + vmovsd offset(%r10),%xmm22 + vmovsd offset(%r10),%xmm23 + vmovsd (%r9),%xmm29 + vmovsd offset(%r9),%xmm3 + vmovsd offset(%r9),%xmm16 + vmovsd offset(%r9),%xmm25 + vmovsd offset(%r9),%xmm26 + vmovsd offset(%r13),%xmm5 + vmovsd offset(%r13),%xmm27 + vmovsd offset(%r9),%xmm30 + vmovsd offset(%r9),%xmm12 + vmovsd offset(%r13),%xmm11 + vmovsd offset(%r10),%xmm18 + vmovsd %xmm20,(%rsp) + vmovsd %xmm21,offset(%rsp) + vmovsd %xmm22,offset(%rsp) + vmovsd %xmm23,offset(%rsp) + vmovsd offset(%r13),%xmm22 + vmovsd offset(%r9),%xmm23 + vmovsd %xmm29,offset(%rsp) + vmovsd %xmm3,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_COOPERLAKE.o (objdump) @@ -2,32 +2,333 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424e048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24f848 895424d8 48897424 ..H.|$.H.T$.H.t$ - 0020 e84885f6 0f8e2401 00004889 fb48d1fb .H....$...H..H.. - 0030 4989dd49 89cb488d 2ccd0000 00004989 I..I..H.,.....I. - 0040 fc498d04 704883e7 fe49c1e5 044989de .I..pH...I...I.. - 0050 c5fb1025 00000000 4c894424 f04989fa ...%....L.D$.I.. - 0060 49c1e304 4c89c741 83e4014e 8d7c2d00 I...L..A...N.|-. - 0070 49c1e605 4889d149 89c0660f 1f440000 I...H..I..f..D.. - 0080 488d740d 004885db 0f8e3201 00004c89 H.t..H....2...L. - 0090 ca31c0eb 3b0f1f00 7d29c5fb 101cc1c5 .1..;...})...... - 00a0 fb104cc1 08c5fb10 14c6c5fb 1044c608 ..L..........D.. - 00b0 c5fb111a c5fb1152 08c5fb11 4a10c5fb .......R....J... - 00c0 11421848 83c00248 83c22049 39c27425 .B.H...H.. I9.t% - 00d0 4839f875 c3c5fb10 04c64883 c002c5fb H9.u......H..... - 00e0 1122c5fb 114208c5 fb116218 4883c220 ."...B....b.H.. - 00f0 4939c275 db4a8d14 294a8d34 394d01f1 I9.u.J..)J.49M.. - 0100 4d85e474 224839c7 0f849a00 00007e13 M..t"H9.......~. - 0110 c5fb100a c5fb1006 c4c17b11 09c4c17b ..........{....{ - 0120 11410849 83c11048 83c7024c 01d94c39 .A.I...H...L..L9 - 0130 c70f8549 ffffff48 8b4424e8 4c8b4424 ...I...H.D$.L.D$ - 0140 f04c0faf d84d8d04 404c015c 24d8f644 .L...M..@L.\$..D - 0150 24e00174 43488b54 24f84885 d27e39c5 $..tCH.T$.H..~9. - 0160 fb100d00 00000048 8b4c24d8 31c0eb15 .......H.L$.1... - 0170 7e0bc5fb 1004c1c4 c17b1104 c148ffc0 ~........{...H.. - 0180 4839c274 134939c0 75e648ff c0c4817b H9.t.I9.u.H....{ - 0190 110cc148 39c275ed 5b5d415c 415d415e ...H9.u.[]A\A]A^ - 01a0 31c0415f c30f1f00 c5fb1006 c4c17b11 1.A_..........{. - 01b0 21c4c17b 114108e9 67ffffff 0f1f4000 !..{.A..g.....@. - 01c0 4889ca31 c0e936ff ffff H..1..6... + 0000 41574156 4d89ce41 55415449 89d45553 AWAVM..AUATI..US + 0010 4881ec68 01000048 89b42440 01000048 H..h...H..$@...H + 0020 c1fe0348 89bc2448 01000048 898c2458 ...H..$H...H..$X + 0030 0100004c 89842438 01000048 89b42450 ...L..$8...H..$P + 0040 01000048 85f60f8e 5c0d0000 488d0449 ...H....\...H..I + 0050 4c8d0cc5 00000000 488d1489 48c1e004 L.......H...H... + 0060 4c8d14cd 00000000 488d2cd5 00000000 L.......H.,..... + 0070 4989f348 89cb4889 ce4889c2 48898424 I..H..H..H..H..$ + 0080 e8000000 486bc138 48c1e106 48898c24 ....Hk.8H...H..$ + 0090 90000000 4889f983 e1044889 8c24d000 ....H.....H..$.. + 00a0 00004889 f9488984 24880000 0083e102 ..H..H..$....... + 00b0 4889f848 c1f80348 898c24c8 00000048 H..H...H..$....H + 00c0 89f94883 e7f84989 fd4889c7 48c1e706 ..H...I..H..H... + 00d0 48c1e605 48c1e304 4889b424 a8000000 H...H...H..$.... + 00e0 4801fe48 01fa4c89 94249800 00004889 H..H..L..$....H. + 00f0 9c24a000 00004901 fa4801fb 4c898c24 .$....I..H..L..$ + 0100 d8000000 4889ac24 e0000000 4901f948 ....H..$....I..H + 0110 01fd4889 8424b000 00004889 b4240801 ..H..$....H..$.. + 0120 000048c1 e009488b b4248800 000083e1 ..H...H..$...... + 0130 014c8994 24100100 0048899c 24280100 .L..$....H..$(.. + 0140 004c898c 24180100 004889ac 24000100 .L..$....H..$... + 0150 00488994 24300100 00488984 24f00000 .H..$0...H..$... + 0160 004c89a4 24600100 004801fe 48898c24 .L..$`...H..H..$ + 0170 c0000000 c5fb1005 00000000 4b8d0cd8 ............K... + 0180 48898c24 b8000000 4889bc24 f8000000 H..$....H..$.... + 0190 4889b424 20010000 62019700 10e54c89 H..$ ...b.....L. + 01a0 c662018f 0010ee4c 89e16201 870010f7 .b.....L..b..... + 01b0 4c89ef62 01a70010 fb4d89f0 0f1f4000 L..b.....M....@. + 01c0 488b8424 98000000 4883bc24 b0000000 H..$....H..$.... + 01d0 004c8d1c 08488b84 24a00000 004c8d14 .L...H..$....L.. + 01e0 08488b84 24d80000 004c8d0c 01488b84 .H..$....L...H.. + 01f0 24a80000 004c8d2c 08488b84 24e00000 $....L.,.H..$... + 0200 004c8d24 01488b84 24e80000 00488d2c .L.$.H..$....H., + 0210 01488b84 24880000 00488d1c 080f8ebd .H..$....H...... + 0220 11000031 c04989c7 4989ce48 89c84c89 ...1.I..I..H..L. + 0230 c24889f1 62019f00 10cc6201 970010d5 .H..b.....b..... + 0240 62018f00 10de4c89 fee94e05 00006690 b.....L...N...f. + 0250 0f8e1205 0000c4c1 7b107e08 c4417b10 ........{.~..A{. + 0260 0ac4c17b 107610c4 c17b106e 18c4c17b ...{.v...{.n...{ + 0270 106620c4 c17b105e 28c4c17b 105630c4 .f ..{.^(..{.V0. + 0280 c17b104e 38c4417b 106b08c4 417b1073 .{.N8.A{.k..A{.s + 0290 10c4417b 107b18c4 417b1053 20c4417b ..A{.{..A{.S .A{ + 02a0 105b28c4 417b1063 30c4417b 104338c5 .[(.A{.c0.A{.C8. + 02b0 fb117c24 88c53311 cfc4417b 104a084d ..|$..3...A{.J.M + 02c0 8b3bc5fb 11742490 c5fb116c 2498c5fb .;...t$....l$... + 02d0 116424a0 c5fb115c 24a8c5fb 115424b0 .d$....\$....T$. + 02e0 c5fb114c 24b8c57b 116c24c0 c57b1174 ...L$..{.l$..{.t + 02f0 24c8c57b 117c24d0 c57b1154 24d8c57b $..{.|$..{.T$..{ + 0300 115c24e0 c57b1164 24e8c57b 114424f0 .\$..{.d$..{.D$. + 0310 c57b114c 24f86241 ff081042 0262c1ff .{.L$.bA...B.b.. + 0320 08106204 62c1ff08 106a0562 c1ff0810 ..b.b....j.b.... + 0330 720662c1 ff08107a 076241ff 081029c4 r.b....z.bA...). + 0340 c17b1059 1862c1ff 08104105 6241ff08 .{.Y.b....A.bA.. + 0350 10490662 41ff0810 5107c4c1 7b106d28 .I.bA...Q...{.m( + 0360 6241ff08 105d0662 41ff0810 7101c441 bA...].bA...q..A + 0370 7b106120 c4417b10 5d2062c1 ff081052 {.a .A{.] b....R + 0380 0362e1ff 08112424 62e1ff08 116c2401 .b....$$b....l$. + 0390 62e1ff08 11742402 62e1ff08 117c2403 b....t$.b....|$. + 03a0 62c1ff08 10750262 c1ff0810 79026261 b....u.b....y.ba + 03b0 ff08116c 2404c5fb 115c2428 6241ff08 ...l$....\$(bA.. + 03c0 106d0162 e1ff0811 44240662 61ff0811 .m.b....D$.ba... + 03d0 4c240762 c1ff0810 45036241 ff08104d L$.b....E.bA...M + 03e0 006261ff 08115424 08c5fb11 6c244862 .ba...T$....l$Hb + 03f0 61ff0811 5c240a62 41ff0810 7d07c4c1 a...\$.bA...}... + 0400 7b104c24 30c4417b 10742438 c57b104d {.L$0.A{.t$8.{.M + 0410 0862e1ff 08105d07 c5fb1053 0862c1ff .b....]....S.b.. + 0420 08100e62 41ff0810 64240162 c1ff0810 ...bA...d$.b.... + 0430 6c2402c4 c17b1074 242862e1 ff081065 l$...{.t$(b....e + 0440 02c5fb10 6d28c5fb 105d30c5 7b106b18 ....m(...]0.{.k. + 0450 c57b1043 20c5fb10 63286241 ff081014 .{.C ...c(bA.... + 0460 24c4417b 107c2418 c4417b10 54242062 $.A{.|$..A{.T$ b + 0470 61ff0810 5d006261 ff08117c 240bc5fb a...].ba...|$... + 0480 114c2460 6261ff08 103bc5fb 104b38c5 .L$`ba...;...K8. + 0490 7b117424 68c57b11 4c2470c5 7b107518 {.t$h.{.L$p.{.u. + 04a0 c57b104d 2062e1ff 08115c24 0fc5fb11 .{.M b....\$.... + 04b0 94248000 000062e1 ff08105b 02c5fb10 .$....b....[.... + 04c0 533062e1 ff08110a c5fb117a 10c5fb10 S0b........z.... + 04d0 7c242062 61ff0811 720bc5fb 117a18c5 |$ ba...r....z.. + 04e0 fb107c24 886261ff 08107424 0ec5fb11 ..|$.ba...t$.... + 04f0 7a40c5fb 107c24c0 6261ff08 116a0cc5 z@...|$.ba...j.. + 0500 fb117a48 c5fb107c 24f86261 ff08106c ..zH...|$.ba...l + 0510 2410c5fb 117a50c5 fb107c24 906261ff $....zP...|$.ba. + 0520 0811620d c5fb11ba 80000000 6261ff08 ..b.........ba.. + 0530 106424f9 c5fb107c 24986261 ff081142 .d$....|$.ba...B + 0540 1262e1ff 08117a13 62e1ff08 11721462 .b....z.b....r.b + 0550 e1ff0811 6a1562e1 ff081162 1662e1ff ....j.b....b.b.. + 0560 08115a17 4c897a08 6261ff08 114a0462 ..Z.L.z.ba...J.b + 0570 61ff0811 52056261 ff08115a 066261ff a...R.ba...Z.ba. + 0580 08117a07 6261ff08 11720e62 61ff0811 ..z.ba...r.ba... + 0590 6a0f6261 ff081162 11c5fb11 bac00000 j.ba...b........ + 05a0 00c5fb10 7c24a062 e1ff0810 5c24fac5 ....|$.b....\$.. + 05b0 fb11ba00 010000c5 fb107c24 a86261ff ..........|$.ba. + 05c0 08104424 0562e1ff 08102424 62e1ff08 ..D$.b....$$b... + 05d0 106c2401 62e1ff08 11421cc5 7b11aaf8 .l$.b....B..{... + 05e0 00000062 e1ff0810 442406c5 7b106c24 ...b....D$..{.l$ + 05f0 d8c57b11 9a200100 00c5fb11 ba400100 ..{.. .......@.. + 0600 00c57b10 5c24e0c5 fb107c24 4862e1ff ..{.\$....|$Hb.. + 0610 08115a19 c57b11b2 f0000000 c57b11a2 ..Z..{.......{.. + 0620 18010000 c57b1182 38010000 c5fb11b2 .....{..8....... + 0630 68010000 c5fb11aa 70010000 62e1ff08 h.......p...b... + 0640 11521a62 61ff0811 421bc57b 11bae800 .R.ba...B..{.... + 0650 0000c57b 11aa0801 000062e1 ff081162 ...{......b....b + 0660 22c57b11 92280100 00c57b11 8a300100 ".{..(....{..0.. + 0670 00c57b11 9a480100 0062e1ff 08116a2a ..{..H...b....j* + 0680 62e1ff08 11422bc5 fb11ba60 010000c5 b....B+....`.... + 0690 fb11a278 010000c5 fb107424 b0c5fb10 ...x......t$.... + 06a0 642438c5 7b106424 e862e1ff 08107424 d$8.{.d$.b....t$ + 06b0 02c5fb10 6c24b8c5 7b104424 f062e1ff ....l$..{.D$.b.. + 06c0 08107c24 03c57b10 74246862 e1ff0810 ..|$..{.t$hb.... + 06d0 5c240fc5 fb11b280 010000c5 fb11a298 \$.............. + 06e0 010000c5 fb107424 50c5fb10 642460c5 ......t$P...d$`. + 06f0 fb119ab0 010000c5 fb1192b8 010000c5 ................ + 0700 fb105c24 40c5fb10 542458c5 7b11a288 ..\$@...T$X.{... + 0710 01000062 e1ff0811 7232c5fb 11b2a001 ...b....r2...... + 0720 0000c5fb 11a2a801 0000c5fb 11aac001 ................ + 0730 0000c57b 1182c801 000062e1 ff08117a ...{......b....z + 0740 3ac5fb11 9ad80100 00c5fb11 92e00100 :............... + 0750 00c57b11 b2e80100 0062e1ff 08115a3e ..{......b....Z> + 0760 c5fb118a f8010000 4883c608 4983c640 ........H...I..@ + 0770 4983c340 4983c240 4983c140 4983c540 I..@I..@I..@I..@ + 0780 4983c440 4883c540 4883c340 4881c200 I..@H..@H..@H... + 0790 02000048 39fe0f84 cc010000 4839f10f ...H9.......H9.. + 07a0 85abfaff ff62c1ff 08106a01 62c1ff08 .....b....j.b... + 07b0 106101c4 417b1079 1062c1ff 08105d01 .a..A{.y.b....]. + 07c0 c4417b10 7510c441 7b105518 6241ff08 .A{.u..A{.U.bA.. + 07d0 10142462 c1ff0810 542401c4 417b106c ..$b....T$..A{.l + 07e0 2410c441 7b104c24 18c4c17b 10742420 $..A{.L$...{.t$ + 07f0 6261ff08 105d0062 e1ff0810 4d01c57b ba...].b....M..{ + 0800 106510c5 7b104518 c5fb106d 20c5fb10 .e..{.E....m ... + 0810 5d286261 ff08103b 62e1ff08 104301c5 ](ba...;b....C.. + 0820 7b105b10 c5fb107b 18c5fb10 6320c5fb {.[....{....c .. + 0830 105328c5 fb104b30 6241ff08 100362c1 .S(...K0bA....b. + 0840 ff08103a 62c1ff08 10316241 ff08104d ...:b....1bA...M + 0850 00c5fb11 026261ff 08114201 62e1ff08 .....ba...B.b... + 0860 117a0262 e1ff0811 72036261 ff08114a .z.b....r.ba...J + 0870 046261ff 08115205 6261ff08 115a0662 .ba...R.ba...Z.b + 0880 61ff0811 7a07c5fb 11424862 e1ff0811 a...z....BHb.... + 0890 6a0a62e1 ff081162 0b62e1ff 08115a0c j.b....b.b....Z. + 08a0 62e1ff08 11520d62 e1ff0811 4a0e62e1 b....R.b....J.b. + 08b0 ff081142 0fc5fb11 82900000 00c57b11 ...B..........{. + 08c0 ba980000 00c57b11 b2a00000 00c57b11 ......{.......{. + 08d0 aaa80000 00c57b11 a2b00000 00c57b11 ......{.......{. + 08e0 9ab80000 00c5fb11 82d80000 00c57b11 ..............{. + 08f0 92e00000 00c57b11 8ae80000 00c57b11 ......{.......{. + 0900 82f00000 00c5fb11 baf80000 00c5fb11 ................ + 0910 82200100 00c5fb11 b2280100 00c5fb11 . .......(...... + 0920 aa300100 00c5fb11 a2380100 00c5fb11 .0.......8...... + 0930 82680100 00c5fb11 9a700100 00c5fb11 .h.......p...... + 0940 92780100 00c5fb11 82b00100 00c5fb11 .x.............. + 0950 8ab80100 00c5fb11 82f80100 00e906fe ................ + 0960 ffff660f 1f440000 488b9c24 10010000 ..f..D..H..$.... + 0970 4889ce48 89c14c8d 1c19488b 9c242801 H..H..L...H..$(. + 0980 0000488b 8424f800 00004c8d 1419488b ..H..$....L...H. + 0990 9c241801 00006201 b70010e1 4c8d0c19 .$....b.....L... + 09a0 488b9c24 08010000 6201af00 10ea4c8d H..$....b.....L. + 09b0 2c19488b 9c240001 00006201 a70010f3 ,.H..$....b..... + 09c0 4c8d2419 488b9c24 30010000 4801c848 L.$.H..$0...H..H + 09d0 8d2c1948 8b9c2420 0100004c 038424f0 .,.H..$ ...L..$. + 09e0 00000048 01cb4889 fa4883bc 24d00000 ...H..H..H..$... + 09f0 00000f84 fb010000 4839d60f 84070600 ........H9...... + 0a00 000f8ec1 0100004c 8b7b18c5 fb100862 .......L.{.....b + 0a10 61ff0810 400162e1 ff081040 02c57b10 a...@.b....@..{. + 0a20 40186241 ff08101b 62c1ff08 107b01c4 @.bA....b....{.. + 0a30 417b107b 10c4c17b 107b1862 41ff0810 A{.{...{.{.bA... + 0a40 1262c1ff 08107201 c4417b10 7210c4c1 .b....r..A{.r... /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 ca010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830703 8f010a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 440b0000 B. B..B..D..D... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 96140000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05440e30 ...E. ..B.(..D.0 + 0040 8606410e 38830747 0ea00303 b9130a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0844 0b000000 D..D.... /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_SKYLAKEX.o (disasm) @@ -7,111 +7,871 @@ dtrsm_ounucopy_SKYLAKEX: push %r15 push %r14 + mov %r9,%r14 push %r13 push %r12 + mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rdi,%rbx - sar %rbx - mov %rbx,%r13 - mov %rcx,%r11 - lea offset(,%rcx,8),%rbp - mov %rdi,%r12 - lea (%r8,%rsi,2),%rax + lea (%rcx,%rcx,2),%rax + lea offset(,%rax,8),%r9 + lea (%rcx,%rcx,4),%rdx + shl $something,%rax + lea offset(,%rcx,8),%r10 + lea offset(,%rdx,8),%rbp + mov %rsi,%r11 + mov %rcx,%rbx + mov %rcx,%rsi + mov %rax,%rdx + mov %rax,offset(%rsp) + imul $something,%rcx,%rax + shl $something,%rcx + mov %rcx,offset(%rsp) + mov %rdi,%rcx + and $something,%ecx + mov %rcx,offset(%rsp) + mov %rdi,%rcx + mov %rax,offset(%rsp) + and $something,%ecx + mov %rdi,%rax + sar $something,%rax + mov %rcx,offset(%rsp) + mov %rdi,%rcx and $something,%rdi - shl $something,%r13 - mov %rbx,%r14 - vmovsd offset(%rip),%xmm4 # - mov %r8,-offset(%rsp) - mov %rdi,%r10 - shl $something,%r11 - mov %r8,%rdi - and $something,%r12d - lea offset(%rbp,%r13,1),%r15 - shl $something,%r14 - mov %rdx,%rcx - mov %rax,%r8 + mov %rdi,%r13 + mov %rax,%rdi + shl $something,%rdi + shl $something,%rsi + shl $something,%rbx + mov %rsi,offset(%rsp) + add %rdi,%rsi + add %rdi,%rdx + mov %r10,offset(%rsp) + mov %rbx,offset(%rsp) + add %rdi,%r10 + add %rdi,%rbx + mov %r9,offset(%rsp) + mov %rbp,offset(%rsp) + add %rdi,%r9 + add %rdi,%rbp + mov %rax,offset(%rsp) + mov %rsi,offset(%rsp) + shl $something,%rax + mov offset(%rsp),%rsi + and $something,%ecx + mov %r10,offset(%rsp) + mov %rbx,offset(%rsp) + mov %r9,offset(%rsp) + mov %rbp,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rax,offset(%rsp) + mov %r12,offset(%rsp) + add %rdi,%rsi + mov %rcx,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + lea (%r8,%r11,8),%rcx + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rsi,offset(%rsp) + vmovsd %xmm29,%xmm29,%xmm28 + mov %r8,%rsi + vmovsd %xmm30,%xmm30,%xmm29 + mov %r12,%rcx + vmovsd %xmm31,%xmm31,%xmm30 + mov %r13,%rdi + vmovsd %xmm27,%xmm27,%xmm31 + mov %r14,%r8 + nopl offset(%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%rcx,1),%r11 + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%r10 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%r9 + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%r13 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%r12 + mov offset(%rsp),%rax + lea (%rcx,%rax,1),%rbp + mov offset(%rsp),%rax + lea (%rax,%rcx,1),%rbx + jle + xor %eax,%eax + mov %rax,%r15 + mov %rcx,%r14 + mov %rcx,%rax + mov %r8,%rdx + mov %rsi,%rcx + vmovsd %xmm28,%xmm28,%xmm25 + vmovsd %xmm29,%xmm29,%xmm26 + vmovsd %xmm30,%xmm30,%xmm27 + mov %r15,%rsi + jmp + xchg %ax,%ax + jle + vmovsd offset(%r14),%xmm7 + vmovsd (%r10),%xmm9 + vmovsd offset(%r14),%xmm6 + vmovsd offset(%r14),%xmm5 + vmovsd offset(%r14),%xmm4 + vmovsd offset(%r14),%xmm3 + vmovsd offset(%r14),%xmm2 + vmovsd offset(%r14),%xmm1 + vmovsd offset(%r11),%xmm13 + vmovsd offset(%r11),%xmm14 + vmovsd offset(%r11),%xmm15 + vmovsd offset(%r11),%xmm10 + vmovsd offset(%r11),%xmm11 + vmovsd offset(%r11),%xmm12 + vmovsd offset(%r11),%xmm8 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm9,%xmm9,%xmm7 + vmovsd offset(%r10),%xmm9 + mov (%r11),%r15 + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd %xmm2,-offset(%rsp) + vmovsd %xmm1,-offset(%rsp) + vmovsd %xmm13,-offset(%rsp) + vmovsd %xmm14,-offset(%rsp) + vmovsd %xmm15,-offset(%rsp) + vmovsd %xmm10,-offset(%rsp) + vmovsd %xmm11,-offset(%rsp) + vmovsd %xmm12,-offset(%rsp) + vmovsd %xmm8,-offset(%rsp) + vmovsd %xmm9,-offset(%rsp) + vmovsd offset(%r10),%xmm24 + vmovsd offset(%r10),%xmm20 + vmovsd offset(%r10),%xmm21 + vmovsd offset(%r10),%xmm22 + vmovsd offset(%r10),%xmm23 + vmovsd (%r9),%xmm29 + vmovsd offset(%r9),%xmm3 + vmovsd offset(%r9),%xmm16 + vmovsd offset(%r9),%xmm25 + vmovsd offset(%r9),%xmm26 + vmovsd offset(%r13),%xmm5 + vmovsd offset(%r13),%xmm27 + vmovsd offset(%r9),%xmm30 + vmovsd offset(%r9),%xmm12 + vmovsd offset(%r13),%xmm11 + vmovsd offset(%r10),%xmm18 + vmovsd %xmm20,(%rsp) + vmovsd %xmm21,offset(%rsp) + vmovsd %xmm22,offset(%rsp) + vmovsd %xmm23,offset(%rsp) + vmovsd offset(%r13),%xmm22 + vmovsd offset(%r9),%xmm23 + vmovsd %xmm29,offset(%rsp) + vmovsd %xmm3,offset(%rsp) /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_SKYLAKEX.o (objdump) @@ -2,32 +2,333 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534889 7424e048 AWAVAUATUSH.t$.H - 0010 d1fe4889 7c24f848 895424d8 48897424 ..H.|$.H.T$.H.t$ - 0020 e84885f6 0f8e2401 00004889 fb48d1fb .H....$...H..H.. - 0030 4989dd49 89cb488d 2ccd0000 00004989 I..I..H.,.....I. - 0040 fc498d04 704883e7 fe49c1e5 044989de .I..pH...I...I.. - 0050 c5fb1025 00000000 4c894424 f04989fa ...%....L.D$.I.. - 0060 49c1e304 4c89c741 83e4014e 8d7c2d00 I...L..A...N.|-. - 0070 49c1e605 4889d149 89c0660f 1f440000 I...H..I..f..D.. - 0080 488d740d 004885db 0f8e3201 00004c89 H.t..H....2...L. - 0090 ca31c0eb 3b0f1f00 7d29c5fb 101cc1c5 .1..;...})...... - 00a0 fb104cc1 08c5fb10 14c6c5fb 1044c608 ..L..........D.. - 00b0 c5fb111a c5fb1152 08c5fb11 4a10c5fb .......R....J... - 00c0 11421848 83c00248 83c22049 39c27425 .B.H...H.. I9.t% - 00d0 4839f875 c3c5fb10 04c64883 c002c5fb H9.u......H..... - 00e0 1122c5fb 114208c5 fb116218 4883c220 ."...B....b.H.. - 00f0 4939c275 db4a8d14 294a8d34 394d01f1 I9.u.J..)J.49M.. - 0100 4d85e474 224839c7 0f849a00 00007e13 M..t"H9.......~. - 0110 c5fb100a c5fb1006 c4c17b11 09c4c17b ..........{....{ - 0120 11410849 83c11048 83c7024c 01d94c39 .A.I...H...L..L9 - 0130 c70f8549 ffffff48 8b4424e8 4c8b4424 ...I...H.D$.L.D$ - 0140 f04c0faf d84d8d04 404c015c 24d8f644 .L...M..@L.\$..D - 0150 24e00174 43488b54 24f84885 d27e39c5 $..tCH.T$.H..~9. - 0160 fb100d00 00000048 8b4c24d8 31c0eb15 .......H.L$.1... - 0170 7e0bc5fb 1004c1c4 c17b1104 c148ffc0 ~........{...H.. - 0180 4839c274 134939c0 75e648ff c0c4817b H9.t.I9.u.H....{ - 0190 110cc148 39c275ed 5b5d415c 415d415e ...H9.u.[]A\A]A^ - 01a0 31c0415f c30f1f00 c5fb1006 c4c17b11 1.A_..........{. - 01b0 21c4c17b 114108e9 67ffffff 0f1f4000 !..{.A..g.....@. - 01c0 4889ca31 c0e936ff ffff H..1..6... + 0000 41574156 4d89ce41 55415449 89d45553 AWAVM..AUATI..US + 0010 4881ec68 01000048 89b42440 01000048 H..h...H..$@...H + 0020 c1fe0348 89bc2448 01000048 898c2458 ...H..$H...H..$X + 0030 0100004c 89842438 01000048 89b42450 ...L..$8...H..$P + 0040 01000048 85f60f8e 5c0d0000 488d0449 ...H....\...H..I + 0050 4c8d0cc5 00000000 488d1489 48c1e004 L.......H...H... + 0060 4c8d14cd 00000000 488d2cd5 00000000 L.......H.,..... + 0070 4989f348 89cb4889 ce4889c2 48898424 I..H..H..H..H..$ + 0080 e8000000 486bc138 48c1e106 48898c24 ....Hk.8H...H..$ + 0090 90000000 4889f983 e1044889 8c24d000 ....H.....H..$.. + 00a0 00004889 f9488984 24880000 0083e102 ..H..H..$....... + 00b0 4889f848 c1f80348 898c24c8 00000048 H..H...H..$....H + 00c0 89f94883 e7f84989 fd4889c7 48c1e706 ..H...I..H..H... + 00d0 48c1e605 48c1e304 4889b424 a8000000 H...H...H..$.... + 00e0 4801fe48 01fa4c89 94249800 00004889 H..H..L..$....H. + 00f0 9c24a000 00004901 fa4801fb 4c898c24 .$....I..H..L..$ + 0100 d8000000 4889ac24 e0000000 4901f948 ....H..$....I..H + 0110 01fd4889 8424b000 00004889 b4240801 ..H..$....H..$.. + 0120 000048c1 e009488b b4248800 000083e1 ..H...H..$...... + 0130 014c8994 24100100 0048899c 24280100 .L..$....H..$(.. + 0140 004c898c 24180100 004889ac 24000100 .L..$....H..$... + 0150 00488994 24300100 00488984 24f00000 .H..$0...H..$... + 0160 004c89a4 24600100 004801fe 48898c24 .L..$`...H..H..$ + 0170 c0000000 c5fb1005 00000000 4b8d0cd8 ............K... + 0180 48898c24 b8000000 4889bc24 f8000000 H..$....H..$.... + 0190 4889b424 20010000 62019700 10e54c89 H..$ ...b.....L. + 01a0 c662018f 0010ee4c 89e16201 870010f7 .b.....L..b..... + 01b0 4c89ef62 01a70010 fb4d89f0 0f1f4000 L..b.....M....@. + 01c0 488b8424 98000000 4883bc24 b0000000 H..$....H..$.... + 01d0 004c8d1c 08488b84 24a00000 004c8d14 .L...H..$....L.. + 01e0 08488b84 24d80000 004c8d0c 01488b84 .H..$....L...H.. + 01f0 24a80000 004c8d2c 08488b84 24e00000 $....L.,.H..$... + 0200 004c8d24 01488b84 24e80000 00488d2c .L.$.H..$....H., + 0210 01488b84 24880000 00488d1c 080f8ebd .H..$....H...... + 0220 11000031 c04989c7 4989ce48 89c84c89 ...1.I..I..H..L. + 0230 c24889f1 62019f00 10cc6201 970010d5 .H..b.....b..... + 0240 62018f00 10de4c89 fee94e05 00006690 b.....L...N...f. + 0250 0f8e1205 0000c4c1 7b107e08 c4417b10 ........{.~..A{. + 0260 0ac4c17b 107610c4 c17b106e 18c4c17b ...{.v...{.n...{ + 0270 106620c4 c17b105e 28c4c17b 105630c4 .f ..{.^(..{.V0. + 0280 c17b104e 38c4417b 106b08c4 417b1073 .{.N8.A{.k..A{.s + 0290 10c4417b 107b18c4 417b1053 20c4417b ..A{.{..A{.S .A{ + 02a0 105b28c4 417b1063 30c4417b 104338c5 .[(.A{.c0.A{.C8. + 02b0 fb117c24 88c53311 cfc4417b 104a084d ..|$..3...A{.J.M + 02c0 8b3bc5fb 11742490 c5fb116c 2498c5fb .;...t$....l$... + 02d0 116424a0 c5fb115c 24a8c5fb 115424b0 .d$....\$....T$. + 02e0 c5fb114c 24b8c57b 116c24c0 c57b1174 ...L$..{.l$..{.t + 02f0 24c8c57b 117c24d0 c57b1154 24d8c57b $..{.|$..{.T$..{ + 0300 115c24e0 c57b1164 24e8c57b 114424f0 .\$..{.d$..{.D$. + 0310 c57b114c 24f86241 ff081042 0262c1ff .{.L$.bA...B.b.. + 0320 08106204 62c1ff08 106a0562 c1ff0810 ..b.b....j.b.... + 0330 720662c1 ff08107a 076241ff 081029c4 r.b....z.bA...). + 0340 c17b1059 1862c1ff 08104105 6241ff08 .{.Y.b....A.bA.. + 0350 10490662 41ff0810 5107c4c1 7b106d28 .I.bA...Q...{.m( + 0360 6241ff08 105d0662 41ff0810 7101c441 bA...].bA...q..A + 0370 7b106120 c4417b10 5d2062c1 ff081052 {.a .A{.] b....R + 0380 0362e1ff 08112424 62e1ff08 116c2401 .b....$$b....l$. + 0390 62e1ff08 11742402 62e1ff08 117c2403 b....t$.b....|$. + 03a0 62c1ff08 10750262 c1ff0810 79026261 b....u.b....y.ba + 03b0 ff08116c 2404c5fb 115c2428 6241ff08 ...l$....\$(bA.. + 03c0 106d0162 e1ff0811 44240662 61ff0811 .m.b....D$.ba... + 03d0 4c240762 c1ff0810 45036241 ff08104d L$.b....E.bA...M + 03e0 006261ff 08115424 08c5fb11 6c244862 .ba...T$....l$Hb + 03f0 61ff0811 5c240a62 41ff0810 7d07c4c1 a...\$.bA...}... + 0400 7b104c24 30c4417b 10742438 c57b104d {.L$0.A{.t$8.{.M + 0410 0862e1ff 08105d07 c5fb1053 0862c1ff .b....]....S.b.. + 0420 08100e62 41ff0810 64240162 c1ff0810 ...bA...d$.b.... + 0430 6c2402c4 c17b1074 242862e1 ff081065 l$...{.t$(b....e + 0440 02c5fb10 6d28c5fb 105d30c5 7b106b18 ....m(...]0.{.k. + 0450 c57b1043 20c5fb10 63286241 ff081014 .{.C ...c(bA.... + 0460 24c4417b 107c2418 c4417b10 54242062 $.A{.|$..A{.T$ b + 0470 61ff0810 5d006261 ff08117c 240bc5fb a...].ba...|$... + 0480 114c2460 6261ff08 103bc5fb 104b38c5 .L$`ba...;...K8. + 0490 7b117424 68c57b11 4c2470c5 7b107518 {.t$h.{.L$p.{.u. + 04a0 c57b104d 2062e1ff 08115c24 0fc5fb11 .{.M b....\$.... + 04b0 94248000 000062e1 ff08105b 02c5fb10 .$....b....[.... + 04c0 533062e1 ff08110a c5fb117a 10c5fb10 S0b........z.... + 04d0 7c242062 61ff0811 720bc5fb 117a18c5 |$ ba...r....z.. + 04e0 fb107c24 886261ff 08107424 0ec5fb11 ..|$.ba...t$.... + 04f0 7a40c5fb 107c24c0 6261ff08 116a0cc5 z@...|$.ba...j.. + 0500 fb117a48 c5fb107c 24f86261 ff08106c ..zH...|$.ba...l + 0510 2410c5fb 117a50c5 fb107c24 906261ff $....zP...|$.ba. + 0520 0811620d c5fb11ba 80000000 6261ff08 ..b.........ba.. + 0530 106424f9 c5fb107c 24986261 ff081142 .d$....|$.ba...B + 0540 1262e1ff 08117a13 62e1ff08 11721462 .b....z.b....r.b + 0550 e1ff0811 6a1562e1 ff081162 1662e1ff ....j.b....b.b.. + 0560 08115a17 4c897a08 6261ff08 114a0462 ..Z.L.z.ba...J.b + 0570 61ff0811 52056261 ff08115a 066261ff a...R.ba...Z.ba. + 0580 08117a07 6261ff08 11720e62 61ff0811 ..z.ba...r.ba... + 0590 6a0f6261 ff081162 11c5fb11 bac00000 j.ba...b........ + 05a0 00c5fb10 7c24a062 e1ff0810 5c24fac5 ....|$.b....\$.. + 05b0 fb11ba00 010000c5 fb107c24 a86261ff ..........|$.ba. + 05c0 08104424 0562e1ff 08102424 62e1ff08 ..D$.b....$$b... + 05d0 106c2401 62e1ff08 11421cc5 7b11aaf8 .l$.b....B..{... + 05e0 00000062 e1ff0810 442406c5 7b106c24 ...b....D$..{.l$ + 05f0 d8c57b11 9a200100 00c5fb11 ba400100 ..{.. .......@.. + 0600 00c57b10 5c24e0c5 fb107c24 4862e1ff ..{.\$....|$Hb.. + 0610 08115a19 c57b11b2 f0000000 c57b11a2 ..Z..{.......{.. + 0620 18010000 c57b1182 38010000 c5fb11b2 .....{..8....... + 0630 68010000 c5fb11aa 70010000 62e1ff08 h.......p...b... + 0640 11521a62 61ff0811 421bc57b 11bae800 .R.ba...B..{.... + 0650 0000c57b 11aa0801 000062e1 ff081162 ...{......b....b + 0660 22c57b11 92280100 00c57b11 8a300100 ".{..(....{..0.. + 0670 00c57b11 9a480100 0062e1ff 08116a2a ..{..H...b....j* + 0680 62e1ff08 11422bc5 fb11ba60 010000c5 b....B+....`.... + 0690 fb11a278 010000c5 fb107424 b0c5fb10 ...x......t$.... + 06a0 642438c5 7b106424 e862e1ff 08107424 d$8.{.d$.b....t$ + 06b0 02c5fb10 6c24b8c5 7b104424 f062e1ff ....l$..{.D$.b.. + 06c0 08107c24 03c57b10 74246862 e1ff0810 ..|$..{.t$hb.... + 06d0 5c240fc5 fb11b280 010000c5 fb11a298 \$.............. + 06e0 010000c5 fb107424 50c5fb10 642460c5 ......t$P...d$`. + 06f0 fb119ab0 010000c5 fb1192b8 010000c5 ................ + 0700 fb105c24 40c5fb10 542458c5 7b11a288 ..\$@...T$X.{... + 0710 01000062 e1ff0811 7232c5fb 11b2a001 ...b....r2...... + 0720 0000c5fb 11a2a801 0000c5fb 11aac001 ................ + 0730 0000c57b 1182c801 000062e1 ff08117a ...{......b....z + 0740 3ac5fb11 9ad80100 00c5fb11 92e00100 :............... + 0750 00c57b11 b2e80100 0062e1ff 08115a3e ..{......b....Z> + 0760 c5fb118a f8010000 4883c608 4983c640 ........H...I..@ + 0770 4983c340 4983c240 4983c140 4983c540 I..@I..@I..@I..@ + 0780 4983c440 4883c540 4883c340 4881c200 I..@H..@H..@H... + 0790 02000048 39fe0f84 cc010000 4839f10f ...H9.......H9.. + 07a0 85abfaff ff62c1ff 08106a01 62c1ff08 .....b....j.b... + 07b0 106101c4 417b1079 1062c1ff 08105d01 .a..A{.y.b....]. + 07c0 c4417b10 7510c441 7b105518 6241ff08 .A{.u..A{.U.bA.. + 07d0 10142462 c1ff0810 542401c4 417b106c ..$b....T$..A{.l + 07e0 2410c441 7b104c24 18c4c17b 10742420 $..A{.L$...{.t$ + 07f0 6261ff08 105d0062 e1ff0810 4d01c57b ba...].b....M..{ + 0800 106510c5 7b104518 c5fb106d 20c5fb10 .e..{.E....m ... + 0810 5d286261 ff08103b 62e1ff08 104301c5 ](ba...;b....C.. + 0820 7b105b10 c5fb107b 18c5fb10 6320c5fb {.[....{....c .. + 0830 105328c5 fb104b30 6241ff08 100362c1 .S(...K0bA....b. + 0840 ff08103a 62c1ff08 10316241 ff08104d ...:b....1bA...M + 0850 00c5fb11 026261ff 08114201 62e1ff08 .....ba...B.b... + 0860 117a0262 e1ff0811 72036261 ff08114a .z.b....r.ba...J + 0870 046261ff 08115205 6261ff08 115a0662 .ba...R.ba...Z.b + 0880 61ff0811 7a07c5fb 11424862 e1ff0811 a...z....BHb.... + 0890 6a0a62e1 ff081162 0b62e1ff 08115a0c j.b....b.b....Z. + 08a0 62e1ff08 11520d62 e1ff0811 4a0e62e1 b....R.b....J.b. + 08b0 ff081142 0fc5fb11 82900000 00c57b11 ...B..........{. + 08c0 ba980000 00c57b11 b2a00000 00c57b11 ......{.......{. + 08d0 aaa80000 00c57b11 a2b00000 00c57b11 ......{.......{. + 08e0 9ab80000 00c5fb11 82d80000 00c57b11 ..............{. + 08f0 92e00000 00c57b11 8ae80000 00c57b11 ......{.......{. + 0900 82f00000 00c5fb11 baf80000 00c5fb11 ................ + 0910 82200100 00c5fb11 b2280100 00c5fb11 . .......(...... + 0920 aa300100 00c5fb11 a2380100 00c5fb11 .0.......8...... + 0930 82680100 00c5fb11 9a700100 00c5fb11 .h.......p...... + 0940 92780100 00c5fb11 82b00100 00c5fb11 .x.............. + 0950 8ab80100 00c5fb11 82f80100 00e906fe ................ + 0960 ffff660f 1f440000 488b9c24 10010000 ..f..D..H..$.... + 0970 4889ce48 89c14c8d 1c19488b 9c242801 H..H..L...H..$(. + 0980 0000488b 8424f800 00004c8d 1419488b ..H..$....L...H. + 0990 9c241801 00006201 b70010e1 4c8d0c19 .$....b.....L... + 09a0 488b9c24 08010000 6201af00 10ea4c8d H..$....b.....L. + 09b0 2c19488b 9c240001 00006201 a70010f3 ,.H..$....b..... + 09c0 4c8d2419 488b9c24 30010000 4801c848 L.$.H..$0...H..H + 09d0 8d2c1948 8b9c2420 0100004c 038424f0 .,.H..$ ...L..$. + 09e0 00000048 01cb4889 fa4883bc 24d00000 ...H..H..H..$... + 09f0 00000f84 fb010000 4839d60f 84070600 ........H9...... + 0a00 000f8ec1 0100004c 8b7b18c5 fb100862 .......L.{.....b + 0a10 61ff0810 400162e1 ff081040 02c57b10 a...@.b....@..{. + 0a20 40186241 ff08101b 62c1ff08 107b01c4 @.bA....b....{.. + 0a30 417b107b 10c4c17b 107b1862 41ff0810 A{.{...{.{.bA... + 0a40 1262c1ff 08107201 c4417b10 7210c4c1 .b....r..A{.r... /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_ounucopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 ca010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830703 8f010a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 440b0000 B. B..B..D..D... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 96140000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05440e30 ...E. ..B.(..D.0 + 0040 8606410e 38830747 0ea00303 b9130a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0844 0b000000 D..D.... /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_COOPERLAKE.o (disasm) @@ -9,46 +9,745 @@ push %r14 push %r13 push %r12 + mov %r9,%r12 push %rbp - mov %rdx,%rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %r8,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rdi,%rbx - mov %rdi,%r12 - and $something,%ebx - lea offset(,%rcx,8),%r14 - shl $something,%rcx - sar %r12 - mov %rbx,%r13 + lea offset(,%rcx,8),%rax mov %rcx,%rbx - imul %r12,%rbx - mov %rdx,-offset(%rsp) - lea (%r8,%rsi,2),%rax - mov %r12,%r15 - vmovsd offset(%rip),%xmm4 # - mov %rcx,%rdi - add %rdx,%rbx - lea (%r12,%r12,1),%r10 - shl $something,%r15 + shl $something,%rbx + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rbx,offset(%rsp) + mov %rcx,%rbx + lea offset(,%rax,8),%rcx + shl $something,%rax + mov %rax,offset(%rsp) + mov %rbx,%rax mov %rdx,%r11 - mov %rax,%rbp + shl $something,%rax + lea (%rbx,%rbx,4),%rdx + mov %rcx,offset(%rsp) + mov %rbx,%rcx + imul $something,%rbx,%rbx + mov %rax,%r15 + mov %rdi,%rax + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + mov %rdi,%rbx + mov %rdi,%rax + sar $something,%rbx + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + imul %r15,%rax + shl $something,%rcx + mov %rcx,offset(%rsp) + add %r11,%rax + mov %rax,offset(%rsp) + lea offset(,%rdx,8),%rcx + and $something,%edi + lea (%r8,%rsi,8),%rax + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + lea offset(,%rbx,8),%r14 + mov %rbx,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + shl $something,%rbx + mov %rbx,offset(%rsp) + mov %r15,%r9 + mov %r8,%rbx + mov %r14,%rbp + nopl offset(%rax,%rax,1) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r11,1),%r13 + mov offset(%rsp),%rax + lea (%rax,%r11,1),%r15 + mov offset(%rsp),%rax + lea (%r11,%rax,1),%r14 + mov offset(%rsp),%rax + lea (%rax,%r11,1),%rsi + mov offset(%rsp),%rax + lea (%r11,%rax,1),%rdi + mov offset(%rsp),%rax + lea (%r11,%rax,1),%r10 + mov offset(%rsp),%rax + lea (%rax,%r11,1),%r8 + jle + mov %r12,%rdx + xor %eax,%eax + mov %r12,-offset(%rsp) + mov %r11,%rcx + mov %r11,%r12 + mov %rax,%r11 + mov %rbx,%rax + mov %rbp,%rbx + mov %rdx,%rbp + jmp nopl offset(%rax) - lea (%r11,%r14,1),%rcx - test %r12,%r12 + jge + vmovsd offset(%rcx),%xmm7 + vmovsd offset(%rcx),%xmm5 + vmovsd offset(%rcx),%xmm6 + vmovsd offset(%rcx),%xmm4 + vmovsd offset(%rcx),%xmm3 + vmovsd offset(%rcx),%xmm31 + vmovsd offset(%rcx),%xmm30 + vmovsd offset(%r13),%xmm29 + vmovsd offset(%r13),%xmm28 + vmovsd offset(%r13),%xmm27 + vmovsd offset(%r13),%xmm26 + vmovsd offset(%r13),%xmm25 + vmovsd offset(%r13),%xmm24 + vmovsd offset(%r13),%xmm23 + vmovsd offset(%r13),%xmm22 + vmovsd (%r15),%xmm21 + vmovsd offset(%r15),%xmm20 + vmovsd offset(%r15),%xmm19 + vmovsd offset(%r15),%xmm18 + vmovsd offset(%r15),%xmm17 + vmovsd offset(%r15),%xmm16 + vmovsd offset(%r15),%xmm15 + vmovsd offset(%r15),%xmm14 + vmovsd (%r14),%xmm13 + vmovsd offset(%r14),%xmm12 + vmovsd offset(%r14),%xmm11 + vmovsd offset(%r14),%xmm10 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd offset(%r14),%xmm9 + vmovsd offset(%r14),%xmm7 + vmovsd offset(%r14),%xmm8 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rsi),%xmm7 + vmovsd offset(%r14),%xmm6 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rsi),%xmm7 + vmovsd (%rsi),%xmm5 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rsi),%xmm7 + vmovsd offset(%rsi),%xmm4 + vmovsd %xmm7,-offset(%rsp) + vmovsd (%rdi),%xmm7 + vmovsd offset(%rsi),%xmm3 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd offset(%rsi),%xmm2 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd offset(%rsi),%xmm1 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd (%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_COOPERLAKE.o (objdump) @@ -2,35 +2,305 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 554889d5 53488974 AWAVAUATUH..SH.t - 0010 24d848d1 fe48897c 24f04889 4c24f84c $.H..H.|$.H.L$.L - 0020 894424d0 48897424 e04885f6 0f8e3601 .D$.H.t$.H....6. - 0030 00004889 fb4989fc 83e3014c 8d34cd00 ..H..I.....L.4.. - 0040 00000048 c1e10449 d1fc4989 dd4889cb ...H...I..I..H.. - 0050 490fafdc 48895424 e8498d04 704d89e7 I...H.T$.I..pM.. - 0060 c5fb1025 00000000 4889cf48 01d34f8d ...%....H..H..O. - 0070 142449c1 e7054989 d34889c5 0f1f4000 .$I...I..H....@. - 0080 4b8d0c33 4d85e40f 8e630100 004c89de K..3M....c...L.. - 0090 4c89c831 d2eb4366 0f1f8400 00000000 L..1..Cf........ - 00a0 7e25c5fb 101ec5fb 105608c5 fb1009c5 ~%.......V...... - 00b0 fb104108 c5fb1118 c5fb1150 08c5fb11 ..A........P.... - 00c0 4810c5fb 11401848 83c20248 01fe4801 H....@.H...H..H. - 00d0 f94883c0 204c39d2 74264c39 c275c1c5 .H.. L9.t&L9.u.. - 00e0 fb104108 c5fb1009 c5db5ec0 c5db5e16 ..A.......^...^. - 00f0 c5fb1148 10c5fb11 10c5fb11 4018ebc7 ...H........@... - 0100 4889d84d 01f94c89 d24d85ed 74234c39 H..M..L..M..t#L9 - 0110 c20f84c9 0000007e 14c5fb10 08c5fb10 .......~........ - 0120 4008c4c1 7b1109c4 c17b1141 084983c1 @...{....{.A.I.. - 0130 104983c0 024983c3 104883c3 104939e8 .I...I...H...I9. - 0140 0f853aff ffff488b 5c24e048 8b6c24e8 ..:...H.\$.H.l$. - 0150 4889d848 c1e00448 01c5488b 4424d048 H..H...H..H.D$.H - 0160 8d045848 894424d0 f64424d8 01745c48 ..XH.D$..D$..t\H - 0170 8b4c24f0 4885c97e 52488b54 24f8c5fb .L$.H..~RH.T$... - 0180 100d0000 0000488b 7424d048 c1e20331 ......H.t$.H...1 - 0190 c0eb1d0f 1f440000 7e0bc5fb 104500c4 .....D..~....E.. - 01a0 c17b1104 c148ffc0 4801d548 39c1741b .{...H..H..H9.t. - 01b0 4839f075 e3c5f35e 4500c4c1 7b1104c1 H9.u...^E...{... - 01c0 48ffc048 01d54839 c175e55b 5d415c41 H..H..H9.u.[]A\A - 01d0 5d415e31 c0415fc3 0f1f8400 00000000 ]A^1.A_......... - 01e0 c5db5e00 c4c17b11 01e93fff ffff6690 ..^...{...?...f. - 01f0 4c89d831 d2e90fff ffff L..1...... + 0000 41574156 41554154 4d89cc55 534881ec AWAVAUATM..USH.. + 0010 30010000 4889b424 10010000 48c1fe03 0...H..$....H... + 0020 4889bc24 18010000 48899424 08010000 H..$....H..$.... + 0030 48898c24 20010000 4c898424 00010000 H..$ ...L..$.... + 0040 4889b424 28010000 4885f60f 8eeb0c00 H..$(...H....... + 0050 00488d04 cd000000 004889cb 48c1e304 .H.......H..H... + 0060 48898424 90000000 488d0449 48899c24 H..$....H..IH..$ + 0070 a0000000 4889cb48 8d0cc500 00000048 ....H..H.......H + 0080 c1e00448 898424f0 00000048 89d84989 ...H..$....H..I. + 0090 d348c1e0 06488d14 9b48898c 24e00000 .H...H...H..$... + 00a0 004889d9 486bdb38 4989c748 89f883e0 .H..Hk.8I..H.... + 00b0 0448899c 24b80000 00488984 24c80000 .H..$....H..$... + 00c0 004889fb 4889f848 c1fb0383 e0024889 .H..H..H......H. + 00d0 8424d000 00004889 d8490faf c748c1e1 .$....H..I...H.. + 00e0 0548898c 24a80000 004c01d8 48898424 .H..$....L..H..$ + 00f0 98000000 488d0cd5 00000000 83e70149 ....H..........I + 0100 8d04f048 898c24e8 00000048 89bc24d8 ...H..$....H..$. + 0110 00000048 898424b0 0000004c 8d34dd00 ...H..$....L.4.. + 0120 00000048 899c24c0 000000c5 fb100500 ...H..$......... + 0130 00000048 c1e30948 899c24f8 0000004d ...H...H..$....M + 0140 89f94c89 c34c89f5 0f1f8400 00000000 ..L..L.......... + 0150 488b8424 90000000 4883bc24 c0000000 H..$....H..$.... + 0160 004e8d2c 18488b84 24a00000 004e8d3c .N.,.H..$....N.< + 0170 18488b84 24e00000 004d8d34 03488b84 .H..$....M.4.H.. + 0180 24a80000 004a8d34 18488b84 24e80000 $....J.4.H..$... + 0190 00498d3c 03488b84 24f00000 004d8d14 .I.<.H..$....M.. + 01a0 03488b84 24b80000 004e8d04 180f8ed5 .H..$....N...... + 01b0 1000004c 89e231c0 4c896424 884c89d9 ...L..1.L.d$.L.. + 01c0 4d89dc49 89c34889 d84889eb 4889d5e9 M..I..H..H..H... + 01d0 1c050000 0f1f4000 0f8de604 0000c5fb ......@......... + 01e0 107908c5 fb106910 c5fb1071 18c5fb10 .y....i....q.... + 01f0 6120c5fb 10592862 61ff0810 79066261 a ...Y(ba...y.ba + 0200 ff081071 076241ff 08106d00 6241ff08 ...q.bA...m.bA.. + 0210 10650162 41ff0810 5d026241 ff081055 .e.bA...].bA...U + 0220 036241ff 08104d04 6241ff08 10450562 .bA...M.bA...E.b + 0230 c1ff0810 7d0662c1 ff081075 0762c1ff ....}.b....u.b.. + 0240 08102f62 c1ff0810 670162c1 ff08105f ../b....g.b...._ + 0250 0262c1ff 08105703 62c1ff08 104f0462 .b....W.b....O.b + 0260 c1ff0810 4705c441 7b107f30 c4417b10 ....G..A{..0.A{. + 0270 7738c441 7b102ec4 417b1066 08c4417b w8.A{...A{.f..A{ + 0280 105e10c4 417b1056 18c5fb11 7c2488c5 .^..A{.V....|$.. + 0290 fb116c24 90c5fb11 742498c5 fb116424 ..l$....t$....d$ + 02a0 a0c5fb11 5c24a8c4 417b104e 20c4c17b ....\$..A{.N ..{ + 02b0 107e30c4 417b1046 28c5fb11 7c24b0c5 .~0.A{.F(...|$.. + 02c0 fb107e28 c4c17b10 7638c5fb 117c24b8 ..~(..{.v8...|$. + 02d0 c5fb107e 30c5fb10 2ec5fb11 7c24c0c5 ...~0.......|$.. + 02e0 fb107e38 c5fb1066 08c5fb11 7c24c8c5 ..~8...f....|$.. + 02f0 fb103fc5 fb105e10 c5fb117c 24d0c5fb ..?...^....|$... + 0300 107f08c5 fb105618 c5fb117c 24d8c5fb ......V....|$... + 0310 107f10c5 fb104e20 c5fb117c 24e0c5fb ......N ...|$... + 0320 107f18c5 fb117c24 e8c5fb10 7f20c5fb ......|$..... .. + 0330 117c24f0 c5fb107f 28c5fb11 7c24f8c5 .|$.....(...|$.. + 0340 fb107f30 c5fb113c 24c5fb10 7f38c5fb ...0...<$....8.. + 0350 117c2408 c4c17b10 3ac5fb11 7c2410c4 .|$...{.:...|$.. + 0360 c17b107a 08c5fb11 7c2418c4 c17b107a .{.z....|$...{.z + 0370 10c5fb11 7c2420c4 c17b107a 18c5fb11 ....|$ ..{.z.... + 0380 7c2428c4 c17b107a 20c5fb11 7c2430c4 |$(..{.z ...|$0. + 0390 c17b107a 28c5fb11 7c2438c4 c17b107a .{.z(...|$8..{.z + 03a0 30c5fb11 7c2440c4 c17b107a 38c5fb11 0...|$@..{.z8... + 03b0 7c2448c4 c17b1038 c5fb117c 2450c4c1 |$H..{.8...|$P.. + 03c0 7b107808 c5fb117c 2458c4c1 7b107810 {.x....|$X..{.x. + 03d0 c5fb117c 2460c4c1 7b107818 c5fb117c ...|$`..{.x....| + 03e0 2468c4c1 7b107820 c5fb117c 2470c4c1 $h..{.x ...|$p.. + 03f0 7b107828 c5fb117c 2478c4c1 7b107830 {.x(...|$x..{.x0 + 0400 c5fb11bc 24800000 00c4c17b 107838c5 ....$......{.x8. + 0410 fb11bc24 88000000 c5fb1039 6261ff08 ...$.......9ba.. + 0420 117a06c5 fb113ac5 fb107c24 886261ff .z....:...|$.ba. + 0430 08117207 c5fb117a 08c5fb10 7c249062 ..r....z....|$.b + 0440 61ff0811 6a08c5fb 117a10c5 fb107c24 a...j....z....|$ + 0450 986261ff 08116209 c5fb117a 18c5fb10 .ba...b....z.... + 0460 7c24a062 61ff0811 5a0ac5fb 117a20c5 |$.ba...Z....z . + 0470 fb107c24 a86261ff 0811520b c5fb117a ..|$.ba...R....z + 0480 286261ff 08114a0c 6261ff08 11420d62 (ba...J.ba...B.b + 0490 e1ff0811 7a0e62e1 ff081172 0f62e1ff ....z.b....r.b.. + 04a0 08116a10 62e1ff08 11621162 e1ff0811 ..j.b....b.b.... + 04b0 5a1262e1 ff081152 1362e1ff 08114a14 Z.b....R.b....J. + 04c0 62e1ff08 114215c5 7b11bab0 000000c5 b....B..{....... + 04d0 7b11b2b8 000000c5 7b11aac0 000000c5 {.......{....... + 04e0 7b11a2c8 000000c5 7b119ad0 000000c5 {.......{....... + 04f0 fb107c24 b0c57b11 92d80000 00c5fb11 ..|$..{......... + 0500 baf00000 00c5fb10 7c24b8c5 7b118ae0 ........|$..{... + 0510 000000c5 fb11ba28 010000c5 fb107c24 .......(......|$ + 0520 c0c57b11 82e80000 00c5fb11 ba300100 ..{..........0.. + 0530 00c5fb10 7c24c8c5 fb11b2f8 000000c5 ....|$.......... + 0540 fb11ba38 010000c5 fb107c24 d0c5fb11 ...8......|$.... + 0550 aa000100 00c5fb11 ba400100 00c5fb10 .........@...... + 0560 7c24d8c5 fb11a208 010000c5 fb11ba48 |$.............H + 0570 010000c5 fb107c24 e0c5fb11 9a100100 ......|$........ + 0580 00c5fb11 ba500100 00c5fb10 7c24e8c5 .....P......|$.. + 0590 fb119218 010000c5 fb11ba58 010000c5 ...........X.... + 05a0 fb107c24 f0c5fb11 8a200100 00c5fb11 ..|$..... ...... + 05b0 ba600100 00c5fb10 7c24f8c5 fb11ba68 .`......|$.....h + 05c0 010000c5 fb103c24 c5fb11ba 70010000 ......<$....p... + 05d0 c5fb107c 2408c5fb 11ba7801 0000c5fb ...|$.....x..... + 05e0 107c2410 c5fb11ba 80010000 c5fb107c .|$............| + 05f0 2418c5fb 11ba8801 0000c5fb 107c2420 $............|$ + 0600 c5fb11ba 90010000 c5fb107c 2428c5fb ...........|$(.. + 0610 11ba9801 0000c5fb 107c2430 c5fb11ba .........|$0.... + 0620 a0010000 c5fb107c 2438c5fb 11baa801 .......|$8...... + 0630 0000c5fb 107c2440 c5fb11ba b0010000 .....|$@........ + 0640 c5fb107c 2448c5fb 11bab801 0000c5fb ...|$H.......... + 0650 107c2450 c5fb11ba c0010000 c5fb107c .|$P...........| + 0660 2458c5fb 11bac801 0000c5fb 107c2460 $X...........|$` + 0670 c5fb11ba d0010000 c5fb107c 2468c5fb ...........|$h.. + 0680 11bad801 0000c5fb 107c2470 c5fb11ba .........|$p.... + 0690 e0010000 c5fb107c 2478c5fb 11bae801 .......|$x...... + 06a0 0000c5fb 10bc2480 000000c5 fb11baf0 ......$......... + 06b0 010000c5 fb10bc24 88000000 c5fb11ba .......$........ + 06c0 f8010000 4983c308 4c01c94d 01cd4d01 ....I...L..M..M. + 06d0 cf4d01ce 4c01ce4c 01cf4d01 ca4d01c8 .M..L..L..M..M.. + 06e0 4881c200 02000049 39db0f84 40020000 H......I9...@... + 06f0 4c39d80f 85dffaff ffc4c17b 107508c4 L9.........{.u.. + 0700 c17b106f 10c5fb5e f6c4c17b 106618c5 .{.o...^...{.f.. + 0710 fb107e20 c57b105f 28c4417b 106230c4 ..~ .{._(.A{.b0. + 0720 c17b105d 00c4c17b 1017c4c1 7b104f08 .{.]...{....{.O. + 0730 6241ff08 103e6241 ff081076 016241ff bA...>bA...v.bA. + 0740 08106e02 6261ff08 10266261 ff08105e ..n.ba...&ba...^ + 0750 016261ff 08105602 6261ff08 104e0362 .ba...V.ba...N.b + 0760 61ff0810 0762e1ff 08107f01 62e1ff08 a....b......b... + 0770 10770262 e1ff0810 6f0362e1 ff081067 .w.b....o.b....g + 0780 04c5fb5e ed62c1ff 08101a62 c1ff0810 ...^.b.....b.... + 0790 520162c1 ff08104a 0262c1ff 08104203 R.b....J.b....B. + 07a0 c4417b10 7a20c441 7b107228 c4417b10 .A{.z .A{.r(.A{. + 07b0 28c5fb11 642488c5 fb117c24 90c57b11 (...d$....|$..{. + 07c0 5c2498c5 7b116424 a0c4417b 106008c4 \$..{.d$..A{.`.. + 07d0 c17b1060 38c4417b 105810c4 417b1050 .{.`8.A{.X..A{.P + 07e0 18c4417b 104820c4 417b1040 28c4c17b ..A{.H .A{.@(..{ + 07f0 107830c5 fb116424 a8c5fb5e 21c5fb11 .x0...d$...^!... + 0800 5a40c5fb 1122c5fb 11928000 0000c5fb Z@...".......... + 0810 118a8800 0000c5fb 5e642488 c5fb5e5c ........^d$...^\ + 0820 2490c5fb 117248c5 fb11aa90 00000062 $....rH........b + 0830 61ff0811 7a186261 ff081172 196261ff a...z.ba...r.ba. + 0840 08116a1a c5fb11a2 d8000000 6261ff08 ..j.........ba.. + 0850 11622062 61ff0811 5a216261 ff081152 .b ba...Z!ba...R + 0860 226261ff 08114a23 c5fb119a 20010000 "ba...J#.... ... + 0870 6261ff08 11422862 e1ff0811 7a2962e1 ba...B(b....z)b. + 0880 ff081172 2a62e1ff 08116a2b 62e1ff08 ...r*b....j+b... + 0890 11622cc5 fb5e5424 98c5fb11 92680100 .b,..^T$.....h.. + 08a0 00c5fb5e 4c24a062 e1ff0811 5a30c5fb ...^L$.b....Z0.. + 08b0 118ab001 000062e1 ff081152 31c5fb5e ......b....R1..^ + 08c0 4c24a862 e1ff0811 4a3262e1 ff081142 L$.b....J2b....B + 08d0 33c57b11 baa00100 00c57b11 b2a80100 3.{.......{..... + 08e0 00c57b11 aac00100 00c57b11 a2c80100 ..{.......{..... + 08f0 00c57b11 9ad00100 00c57b11 92d80100 ..{.......{..... + 0900 00c57b11 8ae00100 00c57b11 82e80100 ..{.......{..... + 0910 00c5fb11 baf00100 00c5fb11 8af80100 ................ + 0920 00e99efd ffff662e 0f1f8400 00000000 ......f......... + 0930 488b8c24 90000000 488bb424 98000000 H..$....H..$.... + 0940 4989cd49 01f54d89 e34e8d3c 294989ec I..I..M..N.<)I.. + 0950 4889dd4e 8d343948 89c34c03 a424f800 H..N.49H..L..$.. + 0960 00004889 f04889ea 4883bc24 c8000000 ..H..H..H..$.... + 0970 000f840c 02000048 39d30f84 c0050000 .......H9....... + 0980 0f8de401 0000498b 7e38c5fb 10086261 ......I.~8....ba + 0990 ff081078 016261ff 08107002 6261ff08 ...x.ba...p.ba.. + 09a0 10680362 61ff0810 60046261 ff081058 .h.ba...`.ba...X + 09b0 056261ff 08105006 6261ff08 10480762 .ba...P.ba...H.b + 09c0 41ff0810 450062c1 ff08107d 0162c1ff A...E.b....}.b.. + 09d0 08107502 62c1ff08 106d0362 c1ff0810 ..u.b....m.b.... + 09e0 650462c1 ff08105d 0562c1ff 08105506 e.b....].b....U. + 09f0 62c1ff08 104d0762 c1ff0810 07c4417b b....M.b......A{ + 0a00 107f08c4 417b1077 10c4417b 106f18c4 ....A{.w..A{.o.. + 0a10 417b1067 20c4417b 105f28c4 417b1057 A{.g .A{._(.A{.W /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 fa010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606440e 38830703 bf010a0e 30410e28 ..D.8.......0A.( - 0050 420e2042 0e18420e 10440e08 490b0000 B. B..B..D..I... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 df120000 00420e10 8f02420e .........B....B. + 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 + 0040 8606410e 38830747 0ee80203 64120a0e ..A.8..G....d... + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0844 0b000000 D..D.... /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_SKYLAKEX.o (disasm) @@ -9,46 +9,745 @@ push %r14 push %r13 push %r12 + mov %r9,%r12 push %rbp - mov %rdx,%rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %r8,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rdi,%rbx - mov %rdi,%r12 - and $something,%ebx - lea offset(,%rcx,8),%r14 - shl $something,%rcx - sar %r12 - mov %rbx,%r13 + lea offset(,%rcx,8),%rax mov %rcx,%rbx - imul %r12,%rbx - mov %rdx,-offset(%rsp) - lea (%r8,%rsi,2),%rax - mov %r12,%r15 - vmovsd offset(%rip),%xmm4 # - mov %rcx,%rdi - add %rdx,%rbx - lea (%r12,%r12,1),%r10 - shl $something,%r15 + shl $something,%rbx + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rbx,offset(%rsp) + mov %rcx,%rbx + lea offset(,%rax,8),%rcx + shl $something,%rax + mov %rax,offset(%rsp) + mov %rbx,%rax mov %rdx,%r11 - mov %rax,%rbp + shl $something,%rax + lea (%rbx,%rbx,4),%rdx + mov %rcx,offset(%rsp) + mov %rbx,%rcx + imul $something,%rbx,%rbx + mov %rax,%r15 + mov %rdi,%rax + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + mov %rdi,%rbx + mov %rdi,%rax + sar $something,%rbx + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + imul %r15,%rax + shl $something,%rcx + mov %rcx,offset(%rsp) + add %r11,%rax + mov %rax,offset(%rsp) + lea offset(,%rdx,8),%rcx + and $something,%edi + lea (%r8,%rsi,8),%rax + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + lea offset(,%rbx,8),%r14 + mov %rbx,offset(%rsp) + vmovsd offset(%rip),%xmm0 # + shl $something,%rbx + mov %rbx,offset(%rsp) + mov %r15,%r9 + mov %r8,%rbx + mov %r14,%rbp + nopl offset(%rax,%rax,1) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r11,1),%r13 + mov offset(%rsp),%rax + lea (%rax,%r11,1),%r15 + mov offset(%rsp),%rax + lea (%r11,%rax,1),%r14 + mov offset(%rsp),%rax + lea (%rax,%r11,1),%rsi + mov offset(%rsp),%rax + lea (%r11,%rax,1),%rdi + mov offset(%rsp),%rax + lea (%r11,%rax,1),%r10 + mov offset(%rsp),%rax + lea (%rax,%r11,1),%r8 + jle + mov %r12,%rdx + xor %eax,%eax + mov %r12,-offset(%rsp) + mov %r11,%rcx + mov %r11,%r12 + mov %rax,%r11 + mov %rbx,%rax + mov %rbp,%rbx + mov %rdx,%rbp + jmp nopl offset(%rax) - lea (%r11,%r14,1),%rcx - test %r12,%r12 + jge + vmovsd offset(%rcx),%xmm7 + vmovsd offset(%rcx),%xmm5 + vmovsd offset(%rcx),%xmm6 + vmovsd offset(%rcx),%xmm4 + vmovsd offset(%rcx),%xmm3 + vmovsd offset(%rcx),%xmm31 + vmovsd offset(%rcx),%xmm30 + vmovsd offset(%r13),%xmm29 + vmovsd offset(%r13),%xmm28 + vmovsd offset(%r13),%xmm27 + vmovsd offset(%r13),%xmm26 + vmovsd offset(%r13),%xmm25 + vmovsd offset(%r13),%xmm24 + vmovsd offset(%r13),%xmm23 + vmovsd offset(%r13),%xmm22 + vmovsd (%r15),%xmm21 + vmovsd offset(%r15),%xmm20 + vmovsd offset(%r15),%xmm19 + vmovsd offset(%r15),%xmm18 + vmovsd offset(%r15),%xmm17 + vmovsd offset(%r15),%xmm16 + vmovsd offset(%r15),%xmm15 + vmovsd offset(%r15),%xmm14 + vmovsd (%r14),%xmm13 + vmovsd offset(%r14),%xmm12 + vmovsd offset(%r14),%xmm11 + vmovsd offset(%r14),%xmm10 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm3,-offset(%rsp) + vmovsd offset(%r14),%xmm9 + vmovsd offset(%r14),%xmm7 + vmovsd offset(%r14),%xmm8 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rsi),%xmm7 + vmovsd offset(%r14),%xmm6 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rsi),%xmm7 + vmovsd (%rsi),%xmm5 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rsi),%xmm7 + vmovsd offset(%rsi),%xmm4 + vmovsd %xmm7,-offset(%rsp) + vmovsd (%rdi),%xmm7 + vmovsd offset(%rsi),%xmm3 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd offset(%rsi),%xmm2 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd offset(%rsi),%xmm1 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd (%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%r10),%xmm7 /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_SKYLAKEX.o (objdump) @@ -2,35 +2,305 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 554889d5 53488974 AWAVAUATUH..SH.t - 0010 24d848d1 fe48897c 24f04889 4c24f84c $.H..H.|$.H.L$.L - 0020 894424d0 48897424 e04885f6 0f8e3601 .D$.H.t$.H....6. - 0030 00004889 fb4989fc 83e3014c 8d34cd00 ..H..I.....L.4.. - 0040 00000048 c1e10449 d1fc4989 dd4889cb ...H...I..I..H.. - 0050 490fafdc 48895424 e8498d04 704d89e7 I...H.T$.I..pM.. - 0060 c5fb1025 00000000 4889cf48 01d34f8d ...%....H..H..O. - 0070 142449c1 e7054989 d34889c5 0f1f4000 .$I...I..H....@. - 0080 4b8d0c33 4d85e40f 8e630100 004c89de K..3M....c...L.. - 0090 4c89c831 d2eb4366 0f1f8400 00000000 L..1..Cf........ - 00a0 7e25c5fb 101ec5fb 105608c5 fb1009c5 ~%.......V...... - 00b0 fb104108 c5fb1118 c5fb1150 08c5fb11 ..A........P.... - 00c0 4810c5fb 11401848 83c20248 01fe4801 H....@.H...H..H. - 00d0 f94883c0 204c39d2 74264c39 c275c1c5 .H.. L9.t&L9.u.. - 00e0 fb104108 c5fb1009 c5db5ec0 c5db5e16 ..A.......^...^. - 00f0 c5fb1148 10c5fb11 10c5fb11 4018ebc7 ...H........@... - 0100 4889d84d 01f94c89 d24d85ed 74234c39 H..M..L..M..t#L9 - 0110 c20f84c9 0000007e 14c5fb10 08c5fb10 .......~........ - 0120 4008c4c1 7b1109c4 c17b1141 084983c1 @...{....{.A.I.. - 0130 104983c0 024983c3 104883c3 104939e8 .I...I...H...I9. - 0140 0f853aff ffff488b 5c24e048 8b6c24e8 ..:...H.\$.H.l$. - 0150 4889d848 c1e00448 01c5488b 4424d048 H..H...H..H.D$.H - 0160 8d045848 894424d0 f64424d8 01745c48 ..XH.D$..D$..t\H - 0170 8b4c24f0 4885c97e 52488b54 24f8c5fb .L$.H..~RH.T$... - 0180 100d0000 0000488b 7424d048 c1e20331 ......H.t$.H...1 - 0190 c0eb1d0f 1f440000 7e0bc5fb 104500c4 .....D..~....E.. - 01a0 c17b1104 c148ffc0 4801d548 39c1741b .{...H..H..H9.t. - 01b0 4839f075 e3c5f35e 4500c4c1 7b1104c1 H9.u...^E...{... - 01c0 48ffc048 01d54839 c175e55b 5d415c41 H..H..H9.u.[]A\A - 01d0 5d415e31 c0415fc3 0f1f8400 00000000 ]A^1.A_......... - 01e0 c5db5e00 c4c17b11 01e93fff ffff6690 ..^...{...?...f. - 01f0 4c89d831 d2e90fff ffff L..1...... + 0000 41574156 41554154 4d89cc55 534881ec AWAVAUATM..USH.. + 0010 30010000 4889b424 10010000 48c1fe03 0...H..$....H... + 0020 4889bc24 18010000 48899424 08010000 H..$....H..$.... + 0030 48898c24 20010000 4c898424 00010000 H..$ ...L..$.... + 0040 4889b424 28010000 4885f60f 8eeb0c00 H..$(...H....... + 0050 00488d04 cd000000 004889cb 48c1e304 .H.......H..H... + 0060 48898424 90000000 488d0449 48899c24 H..$....H..IH..$ + 0070 a0000000 4889cb48 8d0cc500 00000048 ....H..H.......H + 0080 c1e00448 898424f0 00000048 89d84989 ...H..$....H..I. + 0090 d348c1e0 06488d14 9b48898c 24e00000 .H...H...H..$... + 00a0 004889d9 486bdb38 4989c748 89f883e0 .H..Hk.8I..H.... + 00b0 0448899c 24b80000 00488984 24c80000 .H..$....H..$... + 00c0 004889fb 4889f848 c1fb0383 e0024889 .H..H..H......H. + 00d0 8424d000 00004889 d8490faf c748c1e1 .$....H..I...H.. + 00e0 0548898c 24a80000 004c01d8 48898424 .H..$....L..H..$ + 00f0 98000000 488d0cd5 00000000 83e70149 ....H..........I + 0100 8d04f048 898c24e8 00000048 89bc24d8 ...H..$....H..$. + 0110 00000048 898424b0 0000004c 8d34dd00 ...H..$....L.4.. + 0120 00000048 899c24c0 000000c5 fb100500 ...H..$......... + 0130 00000048 c1e30948 899c24f8 0000004d ...H...H..$....M + 0140 89f94c89 c34c89f5 0f1f8400 00000000 ..L..L.......... + 0150 488b8424 90000000 4883bc24 c0000000 H..$....H..$.... + 0160 004e8d2c 18488b84 24a00000 004e8d3c .N.,.H..$....N.< + 0170 18488b84 24e00000 004d8d34 03488b84 .H..$....M.4.H.. + 0180 24a80000 004a8d34 18488b84 24e80000 $....J.4.H..$... + 0190 00498d3c 03488b84 24f00000 004d8d14 .I.<.H..$....M.. + 01a0 03488b84 24b80000 004e8d04 180f8ed5 .H..$....N...... + 01b0 1000004c 89e231c0 4c896424 884c89d9 ...L..1.L.d$.L.. + 01c0 4d89dc49 89c34889 d84889eb 4889d5e9 M..I..H..H..H... + 01d0 1c050000 0f1f4000 0f8de604 0000c5fb ......@......... + 01e0 107908c5 fb106910 c5fb1071 18c5fb10 .y....i....q.... + 01f0 6120c5fb 10592862 61ff0810 79066261 a ...Y(ba...y.ba + 0200 ff081071 076241ff 08106d00 6241ff08 ...q.bA...m.bA.. + 0210 10650162 41ff0810 5d026241 ff081055 .e.bA...].bA...U + 0220 036241ff 08104d04 6241ff08 10450562 .bA...M.bA...E.b + 0230 c1ff0810 7d0662c1 ff081075 0762c1ff ....}.b....u.b.. + 0240 08102f62 c1ff0810 670162c1 ff08105f ../b....g.b...._ + 0250 0262c1ff 08105703 62c1ff08 104f0462 .b....W.b....O.b + 0260 c1ff0810 4705c441 7b107f30 c4417b10 ....G..A{..0.A{. + 0270 7738c441 7b102ec4 417b1066 08c4417b w8.A{...A{.f..A{ + 0280 105e10c4 417b1056 18c5fb11 7c2488c5 .^..A{.V....|$.. + 0290 fb116c24 90c5fb11 742498c5 fb116424 ..l$....t$....d$ + 02a0 a0c5fb11 5c24a8c4 417b104e 20c4c17b ....\$..A{.N ..{ + 02b0 107e30c4 417b1046 28c5fb11 7c24b0c5 .~0.A{.F(...|$.. + 02c0 fb107e28 c4c17b10 7638c5fb 117c24b8 ..~(..{.v8...|$. + 02d0 c5fb107e 30c5fb10 2ec5fb11 7c24c0c5 ...~0.......|$.. + 02e0 fb107e38 c5fb1066 08c5fb11 7c24c8c5 ..~8...f....|$.. + 02f0 fb103fc5 fb105e10 c5fb117c 24d0c5fb ..?...^....|$... + 0300 107f08c5 fb105618 c5fb117c 24d8c5fb ......V....|$... + 0310 107f10c5 fb104e20 c5fb117c 24e0c5fb ......N ...|$... + 0320 107f18c5 fb117c24 e8c5fb10 7f20c5fb ......|$..... .. + 0330 117c24f0 c5fb107f 28c5fb11 7c24f8c5 .|$.....(...|$.. + 0340 fb107f30 c5fb113c 24c5fb10 7f38c5fb ...0...<$....8.. + 0350 117c2408 c4c17b10 3ac5fb11 7c2410c4 .|$...{.:...|$.. + 0360 c17b107a 08c5fb11 7c2418c4 c17b107a .{.z....|$...{.z + 0370 10c5fb11 7c2420c4 c17b107a 18c5fb11 ....|$ ..{.z.... + 0380 7c2428c4 c17b107a 20c5fb11 7c2430c4 |$(..{.z ...|$0. + 0390 c17b107a 28c5fb11 7c2438c4 c17b107a .{.z(...|$8..{.z + 03a0 30c5fb11 7c2440c4 c17b107a 38c5fb11 0...|$@..{.z8... + 03b0 7c2448c4 c17b1038 c5fb117c 2450c4c1 |$H..{.8...|$P.. + 03c0 7b107808 c5fb117c 2458c4c1 7b107810 {.x....|$X..{.x. + 03d0 c5fb117c 2460c4c1 7b107818 c5fb117c ...|$`..{.x....| + 03e0 2468c4c1 7b107820 c5fb117c 2470c4c1 $h..{.x ...|$p.. + 03f0 7b107828 c5fb117c 2478c4c1 7b107830 {.x(...|$x..{.x0 + 0400 c5fb11bc 24800000 00c4c17b 107838c5 ....$......{.x8. + 0410 fb11bc24 88000000 c5fb1039 6261ff08 ...$.......9ba.. + 0420 117a06c5 fb113ac5 fb107c24 886261ff .z....:...|$.ba. + 0430 08117207 c5fb117a 08c5fb10 7c249062 ..r....z....|$.b + 0440 61ff0811 6a08c5fb 117a10c5 fb107c24 a...j....z....|$ + 0450 986261ff 08116209 c5fb117a 18c5fb10 .ba...b....z.... + 0460 7c24a062 61ff0811 5a0ac5fb 117a20c5 |$.ba...Z....z . + 0470 fb107c24 a86261ff 0811520b c5fb117a ..|$.ba...R....z + 0480 286261ff 08114a0c 6261ff08 11420d62 (ba...J.ba...B.b + 0490 e1ff0811 7a0e62e1 ff081172 0f62e1ff ....z.b....r.b.. + 04a0 08116a10 62e1ff08 11621162 e1ff0811 ..j.b....b.b.... + 04b0 5a1262e1 ff081152 1362e1ff 08114a14 Z.b....R.b....J. + 04c0 62e1ff08 114215c5 7b11bab0 000000c5 b....B..{....... + 04d0 7b11b2b8 000000c5 7b11aac0 000000c5 {.......{....... + 04e0 7b11a2c8 000000c5 7b119ad0 000000c5 {.......{....... + 04f0 fb107c24 b0c57b11 92d80000 00c5fb11 ..|$..{......... + 0500 baf00000 00c5fb10 7c24b8c5 7b118ae0 ........|$..{... + 0510 000000c5 fb11ba28 010000c5 fb107c24 .......(......|$ + 0520 c0c57b11 82e80000 00c5fb11 ba300100 ..{..........0.. + 0530 00c5fb10 7c24c8c5 fb11b2f8 000000c5 ....|$.......... + 0540 fb11ba38 010000c5 fb107c24 d0c5fb11 ...8......|$.... + 0550 aa000100 00c5fb11 ba400100 00c5fb10 .........@...... + 0560 7c24d8c5 fb11a208 010000c5 fb11ba48 |$.............H + 0570 010000c5 fb107c24 e0c5fb11 9a100100 ......|$........ + 0580 00c5fb11 ba500100 00c5fb10 7c24e8c5 .....P......|$.. + 0590 fb119218 010000c5 fb11ba58 010000c5 ...........X.... + 05a0 fb107c24 f0c5fb11 8a200100 00c5fb11 ..|$..... ...... + 05b0 ba600100 00c5fb10 7c24f8c5 fb11ba68 .`......|$.....h + 05c0 010000c5 fb103c24 c5fb11ba 70010000 ......<$....p... + 05d0 c5fb107c 2408c5fb 11ba7801 0000c5fb ...|$.....x..... + 05e0 107c2410 c5fb11ba 80010000 c5fb107c .|$............| + 05f0 2418c5fb 11ba8801 0000c5fb 107c2420 $............|$ + 0600 c5fb11ba 90010000 c5fb107c 2428c5fb ...........|$(.. + 0610 11ba9801 0000c5fb 107c2430 c5fb11ba .........|$0.... + 0620 a0010000 c5fb107c 2438c5fb 11baa801 .......|$8...... + 0630 0000c5fb 107c2440 c5fb11ba b0010000 .....|$@........ + 0640 c5fb107c 2448c5fb 11bab801 0000c5fb ...|$H.......... + 0650 107c2450 c5fb11ba c0010000 c5fb107c .|$P...........| + 0660 2458c5fb 11bac801 0000c5fb 107c2460 $X...........|$` + 0670 c5fb11ba d0010000 c5fb107c 2468c5fb ...........|$h.. + 0680 11bad801 0000c5fb 107c2470 c5fb11ba .........|$p.... + 0690 e0010000 c5fb107c 2478c5fb 11bae801 .......|$x...... + 06a0 0000c5fb 10bc2480 000000c5 fb11baf0 ......$......... + 06b0 010000c5 fb10bc24 88000000 c5fb11ba .......$........ + 06c0 f8010000 4983c308 4c01c94d 01cd4d01 ....I...L..M..M. + 06d0 cf4d01ce 4c01ce4c 01cf4d01 ca4d01c8 .M..L..L..M..M.. + 06e0 4881c200 02000049 39db0f84 40020000 H......I9...@... + 06f0 4c39d80f 85dffaff ffc4c17b 107508c4 L9.........{.u.. + 0700 c17b106f 10c5fb5e f6c4c17b 106618c5 .{.o...^...{.f.. + 0710 fb107e20 c57b105f 28c4417b 106230c4 ..~ .{._(.A{.b0. + 0720 c17b105d 00c4c17b 1017c4c1 7b104f08 .{.]...{....{.O. + 0730 6241ff08 103e6241 ff081076 016241ff bA...>bA...v.bA. + 0740 08106e02 6261ff08 10266261 ff08105e ..n.ba...&ba...^ + 0750 016261ff 08105602 6261ff08 104e0362 .ba...V.ba...N.b + 0760 61ff0810 0762e1ff 08107f01 62e1ff08 a....b......b... + 0770 10770262 e1ff0810 6f0362e1 ff081067 .w.b....o.b....g + 0780 04c5fb5e ed62c1ff 08101a62 c1ff0810 ...^.b.....b.... + 0790 520162c1 ff08104a 0262c1ff 08104203 R.b....J.b....B. + 07a0 c4417b10 7a20c441 7b107228 c4417b10 .A{.z .A{.r(.A{. + 07b0 28c5fb11 642488c5 fb117c24 90c57b11 (...d$....|$..{. + 07c0 5c2498c5 7b116424 a0c4417b 106008c4 \$..{.d$..A{.`.. + 07d0 c17b1060 38c4417b 105810c4 417b1050 .{.`8.A{.X..A{.P + 07e0 18c4417b 104820c4 417b1040 28c4c17b ..A{.H .A{.@(..{ + 07f0 107830c5 fb116424 a8c5fb5e 21c5fb11 .x0...d$...^!... + 0800 5a40c5fb 1122c5fb 11928000 0000c5fb Z@...".......... + 0810 118a8800 0000c5fb 5e642488 c5fb5e5c ........^d$...^\ + 0820 2490c5fb 117248c5 fb11aa90 00000062 $....rH........b + 0830 61ff0811 7a186261 ff081172 196261ff a...z.ba...r.ba. + 0840 08116a1a c5fb11a2 d8000000 6261ff08 ..j.........ba.. + 0850 11622062 61ff0811 5a216261 ff081152 .b ba...Z!ba...R + 0860 226261ff 08114a23 c5fb119a 20010000 "ba...J#.... ... + 0870 6261ff08 11422862 e1ff0811 7a2962e1 ba...B(b....z)b. + 0880 ff081172 2a62e1ff 08116a2b 62e1ff08 ...r*b....j+b... + 0890 11622cc5 fb5e5424 98c5fb11 92680100 .b,..^T$.....h.. + 08a0 00c5fb5e 4c24a062 e1ff0811 5a30c5fb ...^L$.b....Z0.. + 08b0 118ab001 000062e1 ff081152 31c5fb5e ......b....R1..^ + 08c0 4c24a862 e1ff0811 4a3262e1 ff081142 L$.b....J2b....B + 08d0 33c57b11 baa00100 00c57b11 b2a80100 3.{.......{..... + 08e0 00c57b11 aac00100 00c57b11 a2c80100 ..{.......{..... + 08f0 00c57b11 9ad00100 00c57b11 92d80100 ..{.......{..... + 0900 00c57b11 8ae00100 00c57b11 82e80100 ..{.......{..... + 0910 00c5fb11 baf00100 00c5fb11 8af80100 ................ + 0920 00e99efd ffff662e 0f1f8400 00000000 ......f......... + 0930 488b8c24 90000000 488bb424 98000000 H..$....H..$.... + 0940 4989cd49 01f54d89 e34e8d3c 294989ec I..I..M..N.<)I.. + 0950 4889dd4e 8d343948 89c34c03 a424f800 H..N.49H..L..$.. + 0960 00004889 f04889ea 4883bc24 c8000000 ..H..H..H..$.... + 0970 000f840c 02000048 39d30f84 c0050000 .......H9....... + 0980 0f8de401 0000498b 7e38c5fb 10086261 ......I.~8....ba + 0990 ff081078 016261ff 08107002 6261ff08 ...x.ba...p.ba.. + 09a0 10680362 61ff0810 60046261 ff081058 .h.ba...`.ba...X + 09b0 056261ff 08105006 6261ff08 10480762 .ba...P.ba...H.b + 09c0 41ff0810 450062c1 ff08107d 0162c1ff A...E.b....}.b.. + 09d0 08107502 62c1ff08 106d0362 c1ff0810 ..u.b....m.b.... + 09e0 650462c1 ff08105d 0562c1ff 08105506 e.b....].b....U. + 09f0 62c1ff08 104d0762 c1ff0810 07c4417b b....M.b......A{ + 0a00 107f08c4 417b1077 10c4417b 106f18c4 ....A{.w..A{.o.. + 0a10 417b1067 20c4417b 105f28c4 417b1057 A{.g .A{._(.A{.W /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outncopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 fa010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606440e 38830703 bf010a0e 30410e28 ..D.8.......0A.( - 0050 420e2042 0e18420e 10440e08 490b0000 B. B..B..D..I... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 df120000 00420e10 8f02420e .........B....B. + 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 + 0040 8606410e 38830747 0ee80203 64120a0e ..A.8..G....d... + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0844 0b000000 D..D.... /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_COOPERLAKE.o (disasm) @@ -7,49 +7,708 @@ dtrsm_outucopy_COOPERLAKE: push %r15 push %r14 + mov %r9,%r14 push %r13 push %r12 - mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rdi,%r13 - lea offset(,%rcx,8),%r15 + lea offset(,%rcx,8),%rax + mov %rcx,%rbx + shl $something,%rbx + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rbx,offset(%rsp) + mov %rcx,%rbx + lea offset(,%rax,8),%rcx + shl $something,%rax + mov %rax,offset(%rsp) + mov %rbx,%rax + mov %rdx,%r10 + shl $something,%rax + lea (%rbx,%rbx,4),%rdx + mov %rcx,offset(%rsp) + mov %rbx,%rcx + imul $something,%rbx,%rbx + mov %rax,%r12 + mov %rdi,%rax + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + mov %rdi,%rbx + mov %rdi,%rax + sar $something,%rbx + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + imul %r12,%rax shl $something,%rcx - sar %r13 - mov %rcx,%rbp - imul %r13,%rbp + lea offset(,%rbx,8),%r13 + add %r10,%rax + mov %rcx,offset(%rsp) + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + lea offset(,%rdx,8),%rcx + lea (%r8,%rsi,8),%rax + and $something,%edi + shl $something,%rbx + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + mov %rbx,offset(%rsp) + mov %r8,%r15 + vmovsd offset(%rip),%xmm0 # + mov %r10,%r8 + mov %r12,%rsi + mov %r15,%r9 + mov %r13,%r10 + mov %r14,%r11 + nopl offset(%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r8,1),%rbx + mov offset(%rsp),%rax + lea (%rax,%r8,1),%r12 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%rbp + mov offset(%rsp),%rax + lea (%rax,%r8,1),%r14 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%r15 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%rdi + mov offset(%rsp),%rax + lea (%rax,%r8,1),%rcx + jle + xor %eax,%eax + mov %rax,-offset(%rsp) + mov %r8,%r13 + mov %r8,%rax + mov %r11,%rdx + mov %r9,%r8 + xor %r9d,%r9d + jmp + cs nopw offset(%rax,%rax,1) + jge + vmovsd offset(%r13),%xmm7 + vmovsd offset(%r13),%xmm5 + vmovsd offset(%r13),%xmm6 + vmovsd offset(%r13),%xmm4 + vmovsd offset(%r13),%xmm2 + vmovsd offset(%r13),%xmm31 + vmovsd offset(%r13),%xmm30 + vmovsd (%rbx),%xmm29 + vmovsd offset(%rbx),%xmm28 + vmovsd offset(%rbx),%xmm27 + vmovsd offset(%rbx),%xmm26 + vmovsd offset(%rbx),%xmm25 + vmovsd offset(%rbx),%xmm24 + vmovsd offset(%rbx),%xmm23 + vmovsd offset(%rbx),%xmm22 + vmovsd (%r12),%xmm21 + vmovsd offset(%r12),%xmm20 + vmovsd offset(%r12),%xmm19 + vmovsd offset(%r12),%xmm18 + vmovsd offset(%r12),%xmm17 + vmovsd offset(%r12),%xmm16 + vmovsd offset(%r12),%xmm15 + vmovsd offset(%r12),%xmm14 + vmovsd offset(%rbp),%xmm13 + vmovsd offset(%rbp),%xmm12 + vmovsd offset(%rbp),%xmm11 + vmovsd offset(%rbp),%xmm10 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm2,-offset(%rsp) + vmovsd offset(%rbp),%xmm9 + vmovsd offset(%rbp),%xmm7 + vmovsd offset(%rbp),%xmm8 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r14),%xmm7 + vmovsd offset(%rbp),%xmm6 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r14),%xmm7 + vmovsd (%r14),%xmm5 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r14),%xmm7 + vmovsd offset(%r14),%xmm4 + vmovsd %xmm7,-offset(%rsp) + vmovsd (%r15),%xmm7 + vmovsd offset(%r14),%xmm3 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd offset(%r14),%xmm2 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd offset(%r14),%xmm1 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd (%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd (%rcx),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rcx),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rcx),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rcx),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rcx),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rcx),%xmm7 /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_COOPERLAKE.o (objdump) @@ -2,34 +2,285 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t - 0010 24d048d1 fe48897c 24f04889 4c24f848 $.H..H.|$.H.L$.H - 0020 897424d8 4885f60f 8e2e0100 004989fd .t$.H........I.. - 0030 4c8d3ccd 00000000 48c1e104 49d1fd48 L.<.....H...I..H - 0040 89cd490f afed4889 fb4c89e8 48895424 ..I...H..L..H.T$ - 0050 e083e301 498d3470 48c1e005 c5fb1025 ....I.4pH......% - 0060 00000000 4c894424 e84989de 4d89c248 ....L.D$.I..M..H - 0070 89cf4801 d54f8d5c 2d004889 d34989c4 ..H..O.\-.H..I.. - 0080 4989f00f 1f440000 4a8d0c3b 4d85ed0f I....D..J..;M... - 0090 8e430100 004889de 4c89c831 d2eb3b90 .C...H..L..1..;. - 00a0 7d25c5fb 101ec5fb 105608c5 fb1009c5 }%.......V...... - 00b0 fb104108 c5fb1118 c5fb1150 08c5fb11 ..A........P.... - 00c0 4810c5fb 11401848 83c20248 01fe4801 H....@.H...H..H. - 00d0 f94883c0 204c39da 741e4939 d275c1c5 .H.. L9.t.I9.u.. - 00e0 fb1001c5 fb1120c5 fb114010 c5fb1160 ...... ...@....` - 00f0 18ebd40f 1f440000 4889ea4d 01e14c89 .....D..H..M..L. - 0100 d84d85f6 74234c39 d00f84b9 0000007e .M..t#L9.......~ - 0110 14c5fb10 0ac5fb10 4208c4c1 7b1109c4 ........B...{... - 0120 c17b1141 084983c1 104983c2 024883c3 .{.A.I...I...H.. - 0130 104883c5 104d39c2 0f854aff ffff488b .H...M9...J...H. - 0140 5c24d84c 8b6424e0 4c8b4424 e84889d8 \$.L.d$.L.D$.H.. - 0150 48c1e004 4901c44d 8d0458f6 4424d001 H...I..M..X.D$.. - 0160 7455488b 4c24f048 85c97e4b 488b5424 tUH.L$.H..~KH.T$ - 0170 f8c5fb10 0d000000 0048c1e2 0331c0eb .........H...1.. - 0180 200f1f80 00000000 7d0cc4c1 7b100424 .......}...{..$ - 0190 c4c17b11 04c148ff c04901d4 4839c174 ..{...H..I..H9.t - 01a0 164939c0 75e248ff c0c4817b 110cc149 .I9.u.H....{...I - 01b0 01d44839 c175ea5b 5d415c41 5d415e31 ..H9.u.[]A\A]A^1 - 01c0 c0415fc3 0f1f4000 c4c17b11 21e953ff .A_...@...{.!.S. - 01d0 ffff660f 1f440000 4889da31 c0e91fff ..f..D..H..1.... - 01e0 ffff .. + 0000 41574156 4d89ce41 55415455 534881ec AWAVM..AUATUSH.. + 0010 30010000 4889b424 10010000 48c1fe03 0...H..$....H... + 0020 4889bc24 18010000 48899424 08010000 H..$....H..$.... + 0030 48898c24 20010000 4c898424 00010000 H..$ ...L..$.... + 0040 4889b424 28010000 4885f60f 8e380c00 H..$(...H....8.. + 0050 00488d04 cd000000 004889cb 48c1e304 .H.......H..H... + 0060 48898424 90000000 488d0449 48899c24 H..$....H..IH..$ + 0070 a0000000 4889cb48 8d0cc500 00000048 ....H..H.......H + 0080 c1e00448 898424f0 00000048 89d84989 ...H..$....H..I. + 0090 d248c1e0 06488d14 9b48898c 24e00000 .H...H...H..$... + 00a0 004889d9 486bdb38 4989c448 89f883e0 .H..Hk.8I..H.... + 00b0 0448899c 24b80000 00488984 24c80000 .H..$....H..$... + 00c0 004889fb 4889f848 c1fb0383 e0024889 .H..H..H......H. + 00d0 8424d000 00004889 d8490faf c448c1e1 .$....H..I...H.. + 00e0 054c8d2c dd000000 004c01d0 48898c24 .L.,.....L..H..$ + 00f0 a8000000 48899c24 c0000000 48898424 ....H..$....H..$ + 0100 98000000 488d0cd5 00000000 498d04f0 ....H.......I... + 0110 83e70148 c1e30948 898c24e8 00000048 ...H...H..$....H + 0120 89bc24d8 00000048 898424b0 00000048 ..$....H..$....H + 0130 899c24f8 0000004d 89c7c5fb 10050000 ..$....M........ + 0140 00004d89 d04c89e6 4d89f94d 89ea4d89 ..M..L..M..M..M. + 0150 f30f1f80 00000000 488b8424 90000000 ........H..$.... + 0160 4883bc24 c0000000 004a8d1c 00488b84 H..$.....J...H.. + 0170 24a00000 004e8d24 00488b84 24e00000 $....N.$.H..$... + 0180 00498d2c 00488b84 24a80000 004e8d34 .I.,.H..$....N.4 + 0190 00488b84 24e80000 004d8d3c 00488b84 .H..$....M.<.H.. + 01a0 24f00000 00498d3c 00488b84 24b80000 $....I.<.H..$... + 01b0 004a8d0c 000f8e9d 0f000031 c0488944 .J.........1.H.D + 01c0 24884d89 c54c89c0 4c89da4d 89c84531 $.M..L..L..M..E1 + 01d0 c9e92905 0000662e 0f1f8400 00000000 ..)...f......... + 01e0 0f8ded04 0000c4c1 7b107d08 c4c17b10 ........{.}...{. + 01f0 6d10c4c1 7b107518 c4c17b10 6520c4c1 m...{.u...{.e .. + 0200 7b105528 6241ff08 107d0662 41ff0810 {.U(bA...}.bA... + 0210 75076261 ff08102b 6261ff08 10630162 u.ba...+ba...c.b + 0220 61ff0810 5b026261 ff081053 036261ff a...[.ba...S.ba. + 0230 08104b04 6261ff08 10430562 e1ff0810 ..K.ba...C.b.... + 0240 7b0662e1 ff081073 0762c1ff 08102c24 {.b....s.b....,$ + 0250 62c1ff08 10642401 62c1ff08 105c2402 b....d$.b....\$. + 0260 62c1ff08 10542403 62c1ff08 104c2404 b....T$.b....L$. + 0270 62c1ff08 10442405 c4417b10 7c2430c4 b....D$..A{.|$0. + 0280 417b1074 2438c57b 106d00c5 7b106508 A{.t$8.{.m..{.e. + 0290 c57b105d 10c57b10 5518c5fb 117c2488 .{.]..{.U....|$. + 02a0 c5fb116c 2490c5fb 11742498 c5fb1164 ...l$....t$....d + 02b0 24a0c5fb 115424a8 c57b104d 20c5fb10 $....T$..{.M ... + 02c0 7d30c57b 104528c5 fb117c24 b0c4c17b }0.{.E(...|$...{ + 02d0 107e28c5 fb107538 c5fb117c 24b8c4c1 .~(...u8...|$... + 02e0 7b107e30 c4c17b10 2ec5fb11 7c24c0c4 {.~0..{.....|$.. + 02f0 c17b107e 38c4c17b 106608c5 fb117c24 .{.~8..{.f....|$ + 0300 c8c4c17b 103fc4c1 7b105e10 c5fb117c ...{.?..{.^....| + 0310 24d0c4c1 7b107f08 c4c17b10 5618c5fb $...{.....{.V... + 0320 117c24d8 c4c17b10 7f10c4c1 7b104e20 .|$...{.....{.N + 0330 c5fb117c 24e0c4c1 7b107f18 c5fb117c ...|$...{......| + 0340 24e8c4c1 7b107f20 c5fb117c 24f0c4c1 $...{.. ...|$... + 0350 7b107f28 c5fb117c 24f8c4c1 7b107f30 {..(...|$...{..0 + 0360 c5fb113c 24c4c17b 107f38c5 fb117c24 ...<$..{..8...|$ + 0370 08c5fb10 3fc5fb11 7c2410c5 fb107f08 ....?...|$...... + 0380 c5fb117c 2418c5fb 107f10c5 fb117c24 ...|$.........|$ + 0390 20c5fb10 7f18c5fb 117c2428 c5fb107f ........|$(.... + 03a0 20c5fb11 7c2430c5 fb107f28 c5fb117c ...|$0....(...| + 03b0 2438c5fb 107f30c5 fb117c24 40c5fb10 $8....0...|$@... + 03c0 7f38c5fb 117c2448 c5fb1039 c5fb117c .8...|$H...9...| + 03d0 2450c5fb 107908c5 fb117c24 58c5fb10 $P...y....|$X... + 03e0 7910c5fb 117c2460 c5fb1079 18c5fb11 y....|$`...y.... + 03f0 7c2468c5 fb107920 c5fb117c 2470c5fb |$h...y ...|$p.. + 0400 107928c5 fb117c24 78c5fb10 7930c5fb .y(...|$x...y0.. + 0410 11bc2480 000000c5 fb107938 c5fb11bc ..$.......y8.... + 0420 24880000 00c4c17b 107d0062 61ff0811 $......{.}.ba... + 0430 7a06c5fb 113ac5fb 107c2488 6261ff08 z....:...|$.ba.. + 0440 117207c5 fb117a08 c5fb107c 24906261 .r....z....|$.ba + 0450 ff08116a 08c5fb11 7a10c5fb 107c2498 ...j....z....|$. + 0460 6261ff08 116209c5 fb117a18 c5fb107c ba...b....z....| + 0470 24a06261 ff08115a 0ac5fb11 7a20c5fb $.ba...Z....z .. + 0480 107c24a8 6261ff08 11520bc5 fb117a28 .|$.ba...R....z( + 0490 6261ff08 114a0c62 61ff0811 420d62e1 ba...J.ba...B.b. + 04a0 ff08117a 0e62e1ff 0811720f 62e1ff08 ...z.b....r.b... + 04b0 116a1062 e1ff0811 621162e1 ff08115a .j.b....b.b....Z + 04c0 1262e1ff 08115213 62e1ff08 114a1462 .b....R.b....J.b + 04d0 e1ff0811 4215c57b 11bab000 0000c57b ....B..{.......{ + 04e0 11b2b800 0000c57b 11aac000 0000c57b .......{.......{ + 04f0 11a2c800 0000c57b 119ad000 0000c5fb .......{........ + 0500 107c24b0 c57b1192 d8000000 c5fb11ba .|$..{.......... + 0510 f0000000 c5fb107c 24b8c57b 118ae000 .......|$..{.... + 0520 0000c5fb 11ba2801 0000c5fb 107c24c0 ......(......|$. + 0530 c57b1182 e8000000 c5fb11ba 30010000 .{..........0... + 0540 c5fb107c 24c8c5fb 11b2f800 0000c5fb ...|$........... + 0550 11ba3801 0000c5fb 107c24d0 c5fb11aa ..8......|$..... + 0560 00010000 c5fb11ba 40010000 c5fb107c ........@......| + 0570 24d8c5fb 11a20801 0000c5fb 11ba4801 $.............H. + 0580 0000c5fb 107c24e0 c5fb119a 10010000 .....|$......... + 0590 c5fb11ba 50010000 c5fb107c 24e8c5fb ....P......|$... + 05a0 11921801 0000c5fb 11ba5801 0000c5fb ..........X..... + 05b0 107c24f0 c5fb118a 20010000 c5fb11ba .|$..... ....... + 05c0 60010000 c5fb107c 24f8c5fb 11ba6801 `......|$.....h. + 05d0 0000c5fb 103c24c5 fb11ba70 010000c5 .....<$....p.... + 05e0 fb107c24 08c5fb11 ba780100 00c5fb10 ..|$.....x...... + 05f0 7c2410c5 fb11ba80 010000c5 fb107c24 |$............|$ + 0600 18c5fb11 ba880100 00c5fb10 7c2420c5 ............|$ . + 0610 fb11ba90 010000c5 fb107c24 28c5fb11 ..........|$(... + 0620 ba980100 00c5fb10 7c2430c5 fb11baa0 ........|$0..... + 0630 010000c5 fb107c24 38c5fb11 baa80100 ......|$8....... + 0640 00c5fb10 7c2440c5 fb11bab0 010000c5 ....|$@......... + 0650 fb107c24 48c5fb11 bab80100 00c5fb10 ..|$H........... + 0660 7c2450c5 fb11bac0 010000c5 fb107c24 |$P...........|$ + 0670 58c5fb11 bac80100 00c5fb10 7c2460c5 X...........|$`. + 0680 fb11bad0 010000c5 fb107c24 68c5fb11 ..........|$h... + 0690 bad80100 00c5fb10 7c2470c5 fb11bae0 ........|$p..... + 06a0 010000c5 fb107c24 78c5fb11 bae80100 ......|$x....... + 06b0 00c5fb10 bc248000 0000c5fb 11baf001 .....$.......... + 06c0 0000c5fb 10bc2488 000000c5 fb11baf8 ......$......... + 06d0 01000049 83c10849 01f54801 f34901f4 ...I...I..H..I.. + 06e0 4801f549 01f64901 f74801f7 4801f148 H..I..I..H..H..H + 06f0 81c20002 00004d39 d10f84c1 0100004d ......M9.......M + 0700 39c80f85 d8faffff 6261ff08 104d0062 9.......ba...M.b + 0710 61ff0810 450162e1 ff08107d 0262c1ff a...E.b....}.b.. + 0720 08103662 c1ff0810 6e0162c1 ff081066 ..6b....n.b....f + 0730 0262c1ff 08105e03 62c1ff08 101762c1 .b....^.b.....b. + 0740 ff08104f 0162c1ff 08104702 c4417b10 ...O.b....G..A{. + 0750 7f18c441 7b107720 c57b102f c57b1067 ...A{.w .{./.{.g + 0760 08c57b10 5f10c57b 105718c5 7b104f20 ..{._..{.W..{.O + 0770 c57b1047 28c5fb10 39c5fb10 7108c5fb .{.G(...9...q... + 0780 106910c5 fb106118 c5fb1059 20c5fb10 .i....a....Y ... + 0790 5128c5fb 10493062 61ff0810 236241ff Q(...I0ba...#bA. + 07a0 08101c24 6241ff08 10542401 c5fb1102 ...$bA...T$..... + 07b0 6261ff08 116208c5 fb114248 6261ff08 ba...b....BHba.. + 07c0 115a1062 61ff0811 5211c5fb 11829000 .Z.ba...R....... + 07d0 00006261 ff08114a 186261ff 08114219 ..ba...J.ba...B. + 07e0 62e1ff08 117a1ac5 fb1182d8 00000062 b....z.........b + 07f0 e1ff0811 722062e1 ff08116a 2162e1ff ....r b....j!b.. + 0800 08116222 62e1ff08 115a23c5 fb118220 ..b"b....Z#.... + 0810 01000062 e1ff0811 522862e1 ff08114a ...b....R(b....J + 0820 2962e1ff 0811422a c57b11ba 58010000 )b....B*.{..X... + 0830 c57b11b2 60010000 c5fb1182 68010000 .{..`.......h... + 0840 c57b11aa 80010000 c57b11a2 88010000 .{.......{...... + 0850 c57b119a 90010000 c57b1192 98010000 .{.......{...... + 0860 c57b118a a0010000 c57b1182 a8010000 .{.......{...... + 0870 c5fb1182 b0010000 c5fb11ba c0010000 ................ + 0880 c5fb11b2 c8010000 c5fb11aa d0010000 ................ + 0890 c5fb11a2 d8010000 c5fb119a e0010000 ................ + 08a0 c5fb1192 e8010000 c5fb118a f0010000 ................ + 08b0 c5fb1182 f8010000 e916feff ff0f1f00 ................ + 08c0 488bbc24 90000000 488b8c24 98000000 H..$....H..$.... + 08d0 4889fb48 01cb4c8d 241f4d89 c14a8d2c H..H..L.$.M..J., + 08e0 274989c0 4c039c24 f8000000 4889c84c 'I..L..$....H..L + 08f0 89d24883 bc24c800 0000000f 84ed0100 ..H..$.......... + 0900 004939d1 0f844e05 00000f8d c5010000 .I9...N......... + 0910 488b7d38 c5fb1008 6261ff08 10780162 H.}8....ba...x.b + 0920 61ff0810 70026261 ff081068 036261ff a...p.ba...h.ba. + 0930 08106004 6261ff08 10580562 61ff0810 ..`.ba...X.ba... + 0940 50066261 ff081048 076261ff 08100362 P.ba...H.ba....b + 0950 e1ff0810 7b0162e1 ff081073 0262e1ff ....{.b....s.b.. + 0960 08106b03 62e1ff08 10630462 e1ff0810 ..k.b....c.b.... + 0970 5b0562e1 ff081053 0662e1ff 08104b07 [.b....S.b....K. + 0980 62c1ff08 100424c4 417b107c 2408c441 b.....$.A{.|$..A + 0990 7b107424 10c4417b 106c2418 c4417b10 {.t$..A{.l$..A{. + 09a0 642420c4 417b105c 2428c441 7b105424 d$ .A{.\$(.A{.T$ + 09b0 30c4417b 104c2438 c57b1045 00c5fb10 0.A{.L$8.{.E.... + 09c0 7d08c5fb 107510c5 fb106d18 c5fb1065 }....u....m....e + 09d0 20c5fb10 5d28c5fb 105530c4 c17b110b ...](...U0..{.. + 09e0 4989bbf8 00000062 41ff0811 7b016241 I......bA...{.bA + 09f0 ff081173 026241ff 08116b03 6241ff08 ...s.bA...k.bA.. + 0a00 11630462 41ff0811 5b056241 ff081153 .c.bA...[.bA...S + 0a10 066241ff 08114b07 6241ff08 11430862 .bA...K.bA...C.b + 0a20 c1ff0811 7b0962c1 ff081173 0a62c1ff ....{.b....s.b.. /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 e2010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 ab010a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 a0110000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05410e30 ...E. ..B.(..A.0 + 0040 8606410e 38830747 0ee80203 30110a0e ..A.8..G....0... + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0848 0b000000 D..H.... /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_SKYLAKEX.o (disasm) @@ -7,49 +7,708 @@ dtrsm_outucopy_SKYLAKEX: push %r15 push %r14 + mov %r9,%r14 push %r13 push %r12 - mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) - sar %rsi - mov %rdi,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) + sar $something,%rsi + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rdi,%r13 - lea offset(,%rcx,8),%r15 + lea offset(,%rcx,8),%rax + mov %rcx,%rbx + shl $something,%rbx + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rbx,offset(%rsp) + mov %rcx,%rbx + lea offset(,%rax,8),%rcx + shl $something,%rax + mov %rax,offset(%rsp) + mov %rbx,%rax + mov %rdx,%r10 + shl $something,%rax + lea (%rbx,%rbx,4),%rdx + mov %rcx,offset(%rsp) + mov %rbx,%rcx + imul $something,%rbx,%rbx + mov %rax,%r12 + mov %rdi,%rax + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + mov %rdi,%rbx + mov %rdi,%rax + sar $something,%rbx + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + imul %r12,%rax shl $something,%rcx - sar %r13 - mov %rcx,%rbp - imul %r13,%rbp + lea offset(,%rbx,8),%r13 + add %r10,%rax + mov %rcx,offset(%rsp) + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + lea offset(,%rdx,8),%rcx + lea (%r8,%rsi,8),%rax + and $something,%edi + shl $something,%rbx + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + mov %rbx,offset(%rsp) + mov %r8,%r15 + vmovsd offset(%rip),%xmm0 # + mov %r10,%r8 + mov %r12,%rsi + mov %r15,%r9 + mov %r13,%r10 + mov %r14,%r11 + nopl offset(%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r8,1),%rbx + mov offset(%rsp),%rax + lea (%rax,%r8,1),%r12 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%rbp + mov offset(%rsp),%rax + lea (%rax,%r8,1),%r14 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%r15 + mov offset(%rsp),%rax + lea (%r8,%rax,1),%rdi + mov offset(%rsp),%rax + lea (%rax,%r8,1),%rcx + jle + xor %eax,%eax + mov %rax,-offset(%rsp) + mov %r8,%r13 + mov %r8,%rax + mov %r11,%rdx + mov %r9,%r8 + xor %r9d,%r9d + jmp + cs nopw offset(%rax,%rax,1) + jge + vmovsd offset(%r13),%xmm7 + vmovsd offset(%r13),%xmm5 + vmovsd offset(%r13),%xmm6 + vmovsd offset(%r13),%xmm4 + vmovsd offset(%r13),%xmm2 + vmovsd offset(%r13),%xmm31 + vmovsd offset(%r13),%xmm30 + vmovsd (%rbx),%xmm29 + vmovsd offset(%rbx),%xmm28 + vmovsd offset(%rbx),%xmm27 + vmovsd offset(%rbx),%xmm26 + vmovsd offset(%rbx),%xmm25 + vmovsd offset(%rbx),%xmm24 + vmovsd offset(%rbx),%xmm23 + vmovsd offset(%rbx),%xmm22 + vmovsd (%r12),%xmm21 + vmovsd offset(%r12),%xmm20 + vmovsd offset(%r12),%xmm19 + vmovsd offset(%r12),%xmm18 + vmovsd offset(%r12),%xmm17 + vmovsd offset(%r12),%xmm16 + vmovsd offset(%r12),%xmm15 + vmovsd offset(%r12),%xmm14 + vmovsd offset(%rbp),%xmm13 + vmovsd offset(%rbp),%xmm12 + vmovsd offset(%rbp),%xmm11 + vmovsd offset(%rbp),%xmm10 + vmovsd %xmm7,-offset(%rsp) + vmovsd %xmm5,-offset(%rsp) + vmovsd %xmm6,-offset(%rsp) + vmovsd %xmm4,-offset(%rsp) + vmovsd %xmm2,-offset(%rsp) + vmovsd offset(%rbp),%xmm9 + vmovsd offset(%rbp),%xmm7 + vmovsd offset(%rbp),%xmm8 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r14),%xmm7 + vmovsd offset(%rbp),%xmm6 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r14),%xmm7 + vmovsd (%r14),%xmm5 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r14),%xmm7 + vmovsd offset(%r14),%xmm4 + vmovsd %xmm7,-offset(%rsp) + vmovsd (%r15),%xmm7 + vmovsd offset(%r14),%xmm3 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd offset(%r14),%xmm2 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd offset(%r14),%xmm1 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,-offset(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,(%rsp) + vmovsd offset(%r15),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd (%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rdi),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd (%rcx),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rcx),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rcx),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rcx),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rcx),%xmm7 + vmovsd %xmm7,offset(%rsp) + vmovsd offset(%rcx),%xmm7 /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_SKYLAKEX.o (objdump) @@ -2,34 +2,285 @@ /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t - 0010 24d048d1 fe48897c 24f04889 4c24f848 $.H..H.|$.H.L$.H - 0020 897424d8 4885f60f 8e2e0100 004989fd .t$.H........I.. - 0030 4c8d3ccd 00000000 48c1e104 49d1fd48 L.<.....H...I..H - 0040 89cd490f afed4889 fb4c89e8 48895424 ..I...H..L..H.T$ - 0050 e083e301 498d3470 48c1e005 c5fb1025 ....I.4pH......% - 0060 00000000 4c894424 e84989de 4d89c248 ....L.D$.I..M..H - 0070 89cf4801 d54f8d5c 2d004889 d34989c4 ..H..O.\-.H..I.. - 0080 4989f00f 1f440000 4a8d0c3b 4d85ed0f I....D..J..;M... - 0090 8e430100 004889de 4c89c831 d2eb3b90 .C...H..L..1..;. - 00a0 7d25c5fb 101ec5fb 105608c5 fb1009c5 }%.......V...... - 00b0 fb104108 c5fb1118 c5fb1150 08c5fb11 ..A........P.... - 00c0 4810c5fb 11401848 83c20248 01fe4801 H....@.H...H..H. - 00d0 f94883c0 204c39da 741e4939 d275c1c5 .H.. L9.t.I9.u.. - 00e0 fb1001c5 fb1120c5 fb114010 c5fb1160 ...... ...@....` - 00f0 18ebd40f 1f440000 4889ea4d 01e14c89 .....D..H..M..L. - 0100 d84d85f6 74234c39 d00f84b9 0000007e .M..t#L9.......~ - 0110 14c5fb10 0ac5fb10 4208c4c1 7b1109c4 ........B...{... - 0120 c17b1141 084983c1 104983c2 024883c3 .{.A.I...I...H.. - 0130 104883c5 104d39c2 0f854aff ffff488b .H...M9...J...H. - 0140 5c24d84c 8b6424e0 4c8b4424 e84889d8 \$.L.d$.L.D$.H.. - 0150 48c1e004 4901c44d 8d0458f6 4424d001 H...I..M..X.D$.. - 0160 7455488b 4c24f048 85c97e4b 488b5424 tUH.L$.H..~KH.T$ - 0170 f8c5fb10 0d000000 0048c1e2 0331c0eb .........H...1.. - 0180 200f1f80 00000000 7d0cc4c1 7b100424 .......}...{..$ - 0190 c4c17b11 04c148ff c04901d4 4839c174 ..{...H..I..H9.t - 01a0 164939c0 75e248ff c0c4817b 110cc149 .I9.u.H....{...I - 01b0 01d44839 c175ea5b 5d415c41 5d415e31 ..H9.u.[]A\A]A^1 - 01c0 c0415fc3 0f1f4000 c4c17b11 21e953ff .A_...@...{.!.S. - 01d0 ffff660f 1f440000 4889da31 c0e91fff ..f..D..H..1.... - 01e0 ffff .. + 0000 41574156 4d89ce41 55415455 534881ec AWAVM..AUATUSH.. + 0010 30010000 4889b424 10010000 48c1fe03 0...H..$....H... + 0020 4889bc24 18010000 48899424 08010000 H..$....H..$.... + 0030 48898c24 20010000 4c898424 00010000 H..$ ...L..$.... + 0040 4889b424 28010000 4885f60f 8e380c00 H..$(...H....8.. + 0050 00488d04 cd000000 004889cb 48c1e304 .H.......H..H... + 0060 48898424 90000000 488d0449 48899c24 H..$....H..IH..$ + 0070 a0000000 4889cb48 8d0cc500 00000048 ....H..H.......H + 0080 c1e00448 898424f0 00000048 89d84989 ...H..$....H..I. + 0090 d248c1e0 06488d14 9b48898c 24e00000 .H...H...H..$... + 00a0 004889d9 486bdb38 4989c448 89f883e0 .H..Hk.8I..H.... + 00b0 0448899c 24b80000 00488984 24c80000 .H..$....H..$... + 00c0 004889fb 4889f848 c1fb0383 e0024889 .H..H..H......H. + 00d0 8424d000 00004889 d8490faf c448c1e1 .$....H..I...H.. + 00e0 054c8d2c dd000000 004c01d0 48898c24 .L.,.....L..H..$ + 00f0 a8000000 48899c24 c0000000 48898424 ....H..$....H..$ + 0100 98000000 488d0cd5 00000000 498d04f0 ....H.......I... + 0110 83e70148 c1e30948 898c24e8 00000048 ...H...H..$....H + 0120 89bc24d8 00000048 898424b0 00000048 ..$....H..$....H + 0130 899c24f8 0000004d 89c7c5fb 10050000 ..$....M........ + 0140 00004d89 d04c89e6 4d89f94d 89ea4d89 ..M..L..M..M..M. + 0150 f30f1f80 00000000 488b8424 90000000 ........H..$.... + 0160 4883bc24 c0000000 004a8d1c 00488b84 H..$.....J...H.. + 0170 24a00000 004e8d24 00488b84 24e00000 $....N.$.H..$... + 0180 00498d2c 00488b84 24a80000 004e8d34 .I.,.H..$....N.4 + 0190 00488b84 24e80000 004d8d3c 00488b84 .H..$....M.<.H.. + 01a0 24f00000 00498d3c 00488b84 24b80000 $....I.<.H..$... + 01b0 004a8d0c 000f8e9d 0f000031 c0488944 .J.........1.H.D + 01c0 24884d89 c54c89c0 4c89da4d 89c84531 $.M..L..L..M..E1 + 01d0 c9e92905 0000662e 0f1f8400 00000000 ..)...f......... + 01e0 0f8ded04 0000c4c1 7b107d08 c4c17b10 ........{.}...{. + 01f0 6d10c4c1 7b107518 c4c17b10 6520c4c1 m...{.u...{.e .. + 0200 7b105528 6241ff08 107d0662 41ff0810 {.U(bA...}.bA... + 0210 75076261 ff08102b 6261ff08 10630162 u.ba...+ba...c.b + 0220 61ff0810 5b026261 ff081053 036261ff a...[.ba...S.ba. + 0230 08104b04 6261ff08 10430562 e1ff0810 ..K.ba...C.b.... + 0240 7b0662e1 ff081073 0762c1ff 08102c24 {.b....s.b....,$ + 0250 62c1ff08 10642401 62c1ff08 105c2402 b....d$.b....\$. + 0260 62c1ff08 10542403 62c1ff08 104c2404 b....T$.b....L$. + 0270 62c1ff08 10442405 c4417b10 7c2430c4 b....D$..A{.|$0. + 0280 417b1074 2438c57b 106d00c5 7b106508 A{.t$8.{.m..{.e. + 0290 c57b105d 10c57b10 5518c5fb 117c2488 .{.]..{.U....|$. + 02a0 c5fb116c 2490c5fb 11742498 c5fb1164 ...l$....t$....d + 02b0 24a0c5fb 115424a8 c57b104d 20c5fb10 $....T$..{.M ... + 02c0 7d30c57b 104528c5 fb117c24 b0c4c17b }0.{.E(...|$...{ + 02d0 107e28c5 fb107538 c5fb117c 24b8c4c1 .~(...u8...|$... + 02e0 7b107e30 c4c17b10 2ec5fb11 7c24c0c4 {.~0..{.....|$.. + 02f0 c17b107e 38c4c17b 106608c5 fb117c24 .{.~8..{.f....|$ + 0300 c8c4c17b 103fc4c1 7b105e10 c5fb117c ...{.?..{.^....| + 0310 24d0c4c1 7b107f08 c4c17b10 5618c5fb $...{.....{.V... + 0320 117c24d8 c4c17b10 7f10c4c1 7b104e20 .|$...{.....{.N + 0330 c5fb117c 24e0c4c1 7b107f18 c5fb117c ...|$...{......| + 0340 24e8c4c1 7b107f20 c5fb117c 24f0c4c1 $...{.. ...|$... + 0350 7b107f28 c5fb117c 24f8c4c1 7b107f30 {..(...|$...{..0 + 0360 c5fb113c 24c4c17b 107f38c5 fb117c24 ...<$..{..8...|$ + 0370 08c5fb10 3fc5fb11 7c2410c5 fb107f08 ....?...|$...... + 0380 c5fb117c 2418c5fb 107f10c5 fb117c24 ...|$.........|$ + 0390 20c5fb10 7f18c5fb 117c2428 c5fb107f ........|$(.... + 03a0 20c5fb11 7c2430c5 fb107f28 c5fb117c ...|$0....(...| + 03b0 2438c5fb 107f30c5 fb117c24 40c5fb10 $8....0...|$@... + 03c0 7f38c5fb 117c2448 c5fb1039 c5fb117c .8...|$H...9...| + 03d0 2450c5fb 107908c5 fb117c24 58c5fb10 $P...y....|$X... + 03e0 7910c5fb 117c2460 c5fb1079 18c5fb11 y....|$`...y.... + 03f0 7c2468c5 fb107920 c5fb117c 2470c5fb |$h...y ...|$p.. + 0400 107928c5 fb117c24 78c5fb10 7930c5fb .y(...|$x...y0.. + 0410 11bc2480 000000c5 fb107938 c5fb11bc ..$.......y8.... + 0420 24880000 00c4c17b 107d0062 61ff0811 $......{.}.ba... + 0430 7a06c5fb 113ac5fb 107c2488 6261ff08 z....:...|$.ba.. + 0440 117207c5 fb117a08 c5fb107c 24906261 .r....z....|$.ba + 0450 ff08116a 08c5fb11 7a10c5fb 107c2498 ...j....z....|$. + 0460 6261ff08 116209c5 fb117a18 c5fb107c ba...b....z....| + 0470 24a06261 ff08115a 0ac5fb11 7a20c5fb $.ba...Z....z .. + 0480 107c24a8 6261ff08 11520bc5 fb117a28 .|$.ba...R....z( + 0490 6261ff08 114a0c62 61ff0811 420d62e1 ba...J.ba...B.b. + 04a0 ff08117a 0e62e1ff 0811720f 62e1ff08 ...z.b....r.b... + 04b0 116a1062 e1ff0811 621162e1 ff08115a .j.b....b.b....Z + 04c0 1262e1ff 08115213 62e1ff08 114a1462 .b....R.b....J.b + 04d0 e1ff0811 4215c57b 11bab000 0000c57b ....B..{.......{ + 04e0 11b2b800 0000c57b 11aac000 0000c57b .......{.......{ + 04f0 11a2c800 0000c57b 119ad000 0000c5fb .......{........ + 0500 107c24b0 c57b1192 d8000000 c5fb11ba .|$..{.......... + 0510 f0000000 c5fb107c 24b8c57b 118ae000 .......|$..{.... + 0520 0000c5fb 11ba2801 0000c5fb 107c24c0 ......(......|$. + 0530 c57b1182 e8000000 c5fb11ba 30010000 .{..........0... + 0540 c5fb107c 24c8c5fb 11b2f800 0000c5fb ...|$........... + 0550 11ba3801 0000c5fb 107c24d0 c5fb11aa ..8......|$..... + 0560 00010000 c5fb11ba 40010000 c5fb107c ........@......| + 0570 24d8c5fb 11a20801 0000c5fb 11ba4801 $.............H. + 0580 0000c5fb 107c24e0 c5fb119a 10010000 .....|$......... + 0590 c5fb11ba 50010000 c5fb107c 24e8c5fb ....P......|$... + 05a0 11921801 0000c5fb 11ba5801 0000c5fb ..........X..... + 05b0 107c24f0 c5fb118a 20010000 c5fb11ba .|$..... ....... + 05c0 60010000 c5fb107c 24f8c5fb 11ba6801 `......|$.....h. + 05d0 0000c5fb 103c24c5 fb11ba70 010000c5 .....<$....p.... + 05e0 fb107c24 08c5fb11 ba780100 00c5fb10 ..|$.....x...... + 05f0 7c2410c5 fb11ba80 010000c5 fb107c24 |$............|$ + 0600 18c5fb11 ba880100 00c5fb10 7c2420c5 ............|$ . + 0610 fb11ba90 010000c5 fb107c24 28c5fb11 ..........|$(... + 0620 ba980100 00c5fb10 7c2430c5 fb11baa0 ........|$0..... + 0630 010000c5 fb107c24 38c5fb11 baa80100 ......|$8....... + 0640 00c5fb10 7c2440c5 fb11bab0 010000c5 ....|$@......... + 0650 fb107c24 48c5fb11 bab80100 00c5fb10 ..|$H........... + 0660 7c2450c5 fb11bac0 010000c5 fb107c24 |$P...........|$ + 0670 58c5fb11 bac80100 00c5fb10 7c2460c5 X...........|$`. + 0680 fb11bad0 010000c5 fb107c24 68c5fb11 ..........|$h... + 0690 bad80100 00c5fb10 7c2470c5 fb11bae0 ........|$p..... + 06a0 010000c5 fb107c24 78c5fb11 bae80100 ......|$x....... + 06b0 00c5fb10 bc248000 0000c5fb 11baf001 .....$.......... + 06c0 0000c5fb 10bc2488 000000c5 fb11baf8 ......$......... + 06d0 01000049 83c10849 01f54801 f34901f4 ...I...I..H..I.. + 06e0 4801f549 01f64901 f74801f7 4801f148 H..I..I..H..H..H + 06f0 81c20002 00004d39 d10f84c1 0100004d ......M9.......M + 0700 39c80f85 d8faffff 6261ff08 104d0062 9.......ba...M.b + 0710 61ff0810 450162e1 ff08107d 0262c1ff a...E.b....}.b.. + 0720 08103662 c1ff0810 6e0162c1 ff081066 ..6b....n.b....f + 0730 0262c1ff 08105e03 62c1ff08 101762c1 .b....^.b.....b. + 0740 ff08104f 0162c1ff 08104702 c4417b10 ...O.b....G..A{. + 0750 7f18c441 7b107720 c57b102f c57b1067 ...A{.w .{./.{.g + 0760 08c57b10 5f10c57b 105718c5 7b104f20 ..{._..{.W..{.O + 0770 c57b1047 28c5fb10 39c5fb10 7108c5fb .{.G(...9...q... + 0780 106910c5 fb106118 c5fb1059 20c5fb10 .i....a....Y ... + 0790 5128c5fb 10493062 61ff0810 236241ff Q(...I0ba...#bA. + 07a0 08101c24 6241ff08 10542401 c5fb1102 ...$bA...T$..... + 07b0 6261ff08 116208c5 fb114248 6261ff08 ba...b....BHba.. + 07c0 115a1062 61ff0811 5211c5fb 11829000 .Z.ba...R....... + 07d0 00006261 ff08114a 186261ff 08114219 ..ba...J.ba...B. + 07e0 62e1ff08 117a1ac5 fb1182d8 00000062 b....z.........b + 07f0 e1ff0811 722062e1 ff08116a 2162e1ff ....r b....j!b.. + 0800 08116222 62e1ff08 115a23c5 fb118220 ..b"b....Z#.... + 0810 01000062 e1ff0811 522862e1 ff08114a ...b....R(b....J + 0820 2962e1ff 0811422a c57b11ba 58010000 )b....B*.{..X... + 0830 c57b11b2 60010000 c5fb1182 68010000 .{..`.......h... + 0840 c57b11aa 80010000 c57b11a2 88010000 .{.......{...... + 0850 c57b119a 90010000 c57b1192 98010000 .{.......{...... + 0860 c57b118a a0010000 c57b1182 a8010000 .{.......{...... + 0870 c5fb1182 b0010000 c5fb11ba c0010000 ................ + 0880 c5fb11b2 c8010000 c5fb11aa d0010000 ................ + 0890 c5fb11a2 d8010000 c5fb119a e0010000 ................ + 08a0 c5fb1192 e8010000 c5fb118a f0010000 ................ + 08b0 c5fb1182 f8010000 e916feff ff0f1f00 ................ + 08c0 488bbc24 90000000 488b8c24 98000000 H..$....H..$.... + 08d0 4889fb48 01cb4c8d 241f4d89 c14a8d2c H..H..L.$.M..J., + 08e0 274989c0 4c039c24 f8000000 4889c84c 'I..L..$....H..L + 08f0 89d24883 bc24c800 0000000f 84ed0100 ..H..$.......... + 0900 004939d1 0f844e05 00000f8d c5010000 .I9...N......... + 0910 488b7d38 c5fb1008 6261ff08 10780162 H.}8....ba...x.b + 0920 61ff0810 70026261 ff081068 036261ff a...p.ba...h.ba. + 0930 08106004 6261ff08 10580562 61ff0810 ..`.ba...X.ba... + 0940 50066261 ff081048 076261ff 08100362 P.ba...H.ba....b + 0950 e1ff0810 7b0162e1 ff081073 0262e1ff ....{.b....s.b.. + 0960 08106b03 62e1ff08 10630462 e1ff0810 ..k.b....c.b.... + 0970 5b0562e1 ff081053 0662e1ff 08104b07 [.b....S.b....K. + 0980 62c1ff08 100424c4 417b107c 2408c441 b.....$.A{.|$..A + 0990 7b107424 10c4417b 106c2418 c4417b10 {.t$..A{.l$..A{. + 09a0 642420c4 417b105c 2428c441 7b105424 d$ .A{.\$(.A{.T$ + 09b0 30c4417b 104c2438 c57b1045 00c5fb10 0.A{.L$8.{.E.... + 09c0 7d08c5fb 107510c5 fb106d18 c5fb1065 }....u....m....e + 09d0 20c5fb10 5d28c5fb 105530c4 c17b110b ...](...U0..{.. + 09e0 4989bbf8 00000062 41ff0811 7b016241 I......bA...{.bA + 09f0 ff081173 026241ff 08116b03 6241ff08 ...s.bA...k.bA.. + 0a00 11630462 41ff0811 5b056241 ff081153 .c.bA...[.bA...S + 0a10 066241ff 08114b07 6241ff08 11430862 .bA...K.bA...C.b + 0a20 c1ff0811 7b0962c1 ff081173 0a62c1ff ....{.b....s.b.. /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/dtrsm_outucopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 e2010000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 ab010a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 450b0000 B. B..B..D..E... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 a0110000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05410e30 ...E. ..B.(..A.0 + 0040 8606410e 38830747 0ee80203 30110a0e ..A.8..G....0... + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0848 0b000000 D..H.... /usr/lib64/libopenblas_openmp.a/sasum_k_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sasum_k_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sasum_k_COOPERLAKE.o (disasm) @@ -13,139 +13,161 @@ cmp $something,%rdx je imul %rdx,%rdi - vxorps %xmm1,%xmm1,%xmm1 - vmovaps %xmm1,%xmm7 + vxorps %xmm2,%xmm2,%xmm2 + vmovaps %xmm2,%xmm1 + mov %rdi,%rsi xor %eax,%eax vmovss offset(%rip),%xmm5 # nopl offset(%rax) vmovss (%rcx,%rax,4),%xmm0 add %rdx,%rax - vmovaps %xmm0,%xmm2 - vxorps %xmm5,%xmm0,%xmm3 - vcmpnltss %xmm0,%xmm1,%xmm0 - vblendvps %xmm0,%xmm3,%xmm2,%xmm0 - vaddss %xmm0,%xmm7,%xmm7 - cmp %rax,%rdi + vmovaps %xmm0,%xmm3 + vxorps %xmm5,%xmm0,%xmm4 + vcmpnltss %xmm0,%xmm2,%xmm0 + vblendvps %xmm0,%xmm4,%xmm3,%xmm0 + vaddss %xmm0,%xmm1,%xmm1 + cmp %rax,%rsi jg - vmovaps %xmm7,%xmm0 + vmovaps %xmm1,%xmm0 + ret + nopl offset(%rax) + cmp $something,%rdi + jg + mov %rdi,%rsi + and $something,%rsi + cmp $something,%rdi + jg + vxorps %xmm2,%xmm2,%xmm2 + vmovaps %xmm2,%xmm1 + cmp %rdi,%rsi + jge + lea (%rcx,%rsi,4),%rax + lea (%rcx,%rdi,4),%rdx + vmovss offset(%rip),%xmm5 # + nop + vmovss (%rax),%xmm0 + add $something,%rax + vmovaps %xmm0,%xmm3 + vxorps %xmm5,%xmm0,%xmm4 + vcmpnltss %xmm0,%xmm2,%xmm0 + vblendvps %xmm0,%xmm4,%xmm3,%xmm0 + vaddss %xmm0,%xmm1,%xmm1 + cmp %rax,%rdx + jne + vmovaps %xmm1,%xmm0 ret nopl offset(%rax) - mov %rdi,%rdx - and $something,%rdx - je - vmovss offset(%rip),%xmm13 # vxorps %xmm1,%xmm1,%xmm1 + vmovaps %xmm1,%xmm0 + ret + nopl offset(%rax) mov %rsi,%rax - vmovaps %xmm1,%xmm11 - xor %esi,%esi - vmovaps %xmm1,%xmm12 - vmovaps %xmm1,%xmm5 - vmovaps %xmm1,%xmm7 - vmovaps %xmm13,%xmm20 - vmovaps %xmm13,%xmm19 - vmovaps %xmm13,%xmm18 - vmovaps %xmm13,%xmm17 - vmovaps %xmm13,%xmm16 - vmovaps %xmm13,%xmm23 - vmovaps %xmm13,%xmm24 - vmovss (%rax),%xmm4 - vmovss offset(%rax),%xmm3 - vmovaps %xmm4,%xmm0 - vxorps %xmm13,%xmm4,%xmm2 - vcmpnltss %xmm4,%xmm1,%xmm4 - vmovss offset(%rax),%xmm10 - vmovss offset(%rax),%xmm9 - vblendvps %xmm4,%xmm2,%xmm0,%xmm4 - vmovaps %xmm3,%xmm0 - vxorps %xmm20,%xmm3,%xmm2 - vcmpnltss %xmm3,%xmm1,%xmm3 - vaddss %xmm7,%xmm4,%xmm7 - add $something,%rsi - vblendvps %xmm3,%xmm2,%xmm0,%xmm3 - vmovss offset(%rax),%xmm2 - vaddss %xmm5,%xmm3,%xmm5 - vmovaps %xmm2,%xmm0 - vxorps %xmm19,%xmm2,%xmm6 - vcmpnltss %xmm2,%xmm1,%xmm2 - add $something,%rax - vblendvps %xmm2,%xmm6,%xmm0,%xmm2 - vmovss -offset(%rax),%xmm0 - vaddss %xmm12,%xmm2,%xmm12 - vmovaps %xmm0,%xmm6 - vxorps %xmm18,%xmm0,%xmm8 - vcmpnltss %xmm0,%xmm1,%xmm0 - vblendvps %xmm0,%xmm8,%xmm6,%xmm0 - vmovaps %xmm10,%xmm6 - vxorps %xmm17,%xmm10,%xmm8 - vcmpnltss %xmm10,%xmm1,%xmm10 - vaddss %xmm0,%xmm11,%xmm11 - vblendvps %xmm10,%xmm8,%xmm6,%xmm10 - vmovaps %xmm9,%xmm6 - vxorps %xmm16,%xmm9,%xmm8 - vcmpnltss %xmm9,%xmm1,%xmm9 - vaddss %xmm10,%xmm7,%xmm7 - vblendvps %xmm9,%xmm8,%xmm6,%xmm9 - vmovss -offset(%rax),%xmm8 - vaddss %xmm9,%xmm5,%xmm5 - vmovaps %xmm8,%xmm6 - vxorps %xmm23,%xmm8,%xmm21 - vcmpnltss %xmm8,%xmm1,%xmm8 - vmovaps %xmm21,%xmm14 - vblendvps %xmm8,%xmm14,%xmm6,%xmm8 - vmovss -offset(%rax),%xmm6 - vaddss %xmm8,%xmm12,%xmm12 - vmovaps %xmm6,%xmm21 - vxorps %xmm24,%xmm6,%xmm22 - vcmpnltss %xmm6,%xmm1,%xmm6 - vmovaps %xmm21,%xmm14 - vmovaps %xmm22,%xmm15 - vblendvps %xmm6,%xmm15,%xmm14,%xmm6 - vaddss %xmm6,%xmm11,%xmm11 - cmp %rsi,%rdx - jg - vaddss %xmm5,%xmm7,%xmm7 - dec %rdx + mov $something,%edx + and $something,%esi + sub %rsi,%rdx shr $something,%rdx - vaddss %xmm12,%xmm7,%xmm7 - lea offset(,%rdx,8),%rdx - vaddss %xmm11,%xmm7,%xmm7 - cmp %rdx,%rdi + and $something,%edx + je + vxorps %xmm2,%xmm2,%xmm2 + lea (%rcx,%rdx,4),%rsi + vmovaps %xmm2,%xmm3 + vmovss offset(%rip),%xmm5 # + nop + vmovss (%rax),%xmm0 + add $something,%rax + vmovaps %xmm0,%xmm1 + vxorps %xmm5,%xmm0,%xmm4 + vcmpnltss %xmm0,%xmm2,%xmm0 + vblendvps %xmm0,%xmm4,%xmm1,%xmm0 + vaddss %xmm0,%xmm3,%xmm3 + cmp %rax,%rsi + jne + sub %rdx,%rdi + mov %rdi,%rsi + mov %rdi,%r8 + lea (%rcx,%rdx,4),%rcx + and $something,%rsi + xor %r8b,%r8b + cmp $something,%rdi jle + test %r8,%r8 + je + vxorps %xmm4,%xmm4,%xmm4 + vpbroadcastq offset(%rip),%ymm0 # + mov %rcx,%rax + lea (%rcx,%r8,4),%rdx + vmovaps %ymm4,%ymm5 + vmovaps %ymm4,%ymm6 + vmovaps %ymm4,%ymm1 + xchg %ax,%ax + vpand (%rax),%ymm0,%ymm7 + sub $something,%rax + vaddps %ymm7,%ymm1,%ymm1 + vpand -offset(%rax),%ymm0,%ymm7 + vaddps %ymm7,%ymm6,%ymm6 + vpand -offset(%rax),%ymm0,%ymm7 + vaddps %ymm7,%ymm5,%ymm5 + vpand -offset(%rax),%ymm0,%ymm7 + vaddps %ymm7,%ymm4,%ymm4 + cmp %rax,%rdx + jne + vaddps %ymm6,%ymm1,%ymm0 + vaddps %ymm5,%ymm0,%ymm0 + vaddps %ymm4,%ymm0,%ymm0 + vextractf128 $something,%ymm0,%xmm1 + vaddps %xmm0,%xmm1,%xmm0 + vhaddps %xmm0,%xmm0,%xmm0 + vhaddps %xmm0,%xmm0,%xmm0 + vaddss %xmm0,%xmm3,%xmm3 + vzeroupper + cmp %rsi,%r8 /usr/lib64/libopenblas_openmp.a/sasum_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sasum_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sasum_k_COOPERLAKE.o (objdump) @@ -2,46 +2,46 @@ /usr/lib64/libopenblas_openmp.a/sasum_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 4889f148 85ff0f8e 34020000 4885d20f H..H....4...H... - 0010 8e2b0200 004883fa 01744d48 0faffac5 .+...H...tMH.... - 0020 f057c9c5 f828f931 c0c5fa10 2d000000 .W...(.1....-... - 0030 000f1f80 00000000 c5fa1004 814801d0 .............H.. - 0040 c5f828d0 c5f857dd c5f2c2c0 05c4e369 ..(...W........i - 0050 4ac300c5 c258f848 39c77fdc c5f828c7 J....X.H9.....(. - 0060 c30f1f80 00000000 4889fa48 83e2f80f ........H..H.... - 0070 84d40100 00c57a10 2d000000 00c5f057 ......z.-......W - 0080 c94889f0 c57828d9 31f6c578 28e1c5f8 .H...x(.1..x(... - 0090 28e9c5f8 28f962c1 7c0828e5 62c17c08 (...(.b.|.(.b.|. - 00a0 28dd62c1 7c0828d5 62c17c08 28cd62c1 (.b.|.(.b.|.(.b. - 00b0 7c0828c5 62c17c08 28fd6241 7c0828c5 |.(.b.|.(.bA|.(. - 00c0 c5fa1020 c5fa1058 04c5f828 c4c4c158 ... ...X...(...X - 00d0 57d5c5f2 c2e405c5 7a105010 c57a1048 W.......z.P..z.H - 00e0 14c4e379 4ae240c5 f828c362 b1640857 ...yJ.@..(.b.d.W - 00f0 d4c5f2c2 db05c5da 58ff4883 c608c4e3 ........X.H..... - 0100 794ada30 c5fa1050 08c5e258 edc5f828 yJ.0...P...X...( - 0110 c262b16c 0857f3c5 f2c2d205 4883c020 .b.l.W......H.. - 0120 c4e3794a d620c5fa 1040ecc4 416a58e4 ..yJ. ...@..AjX. - 0130 c5f828f0 62317c08 57c2c5f2 c2c005c4 ..(.b1|.W....... - 0140 c3494ac0 00c57829 d662312c 0857c1c4 .IJ...x).b1,.W.. - 0150 4172c2d2 05c52258 d8c44349 4ad0a0c5 Ar...."X..CIJ... - 0160 7829ce62 31340857 c0c44172 c2c905c4 x).b14.W..Ar.... - 0170 c14258fa c443494a c890c57a 1040f8c4 .BX..CIJ...z.@.. - 0180 c15258e9 c57829c6 62a13c08 57efc441 .RX..x).b.<.W..A - 0190 72c2c005 62317c08 28f5c443 494ac680 r...b1|.(..CIJ.. - 01a0 c5fa1070 fcc4411a 58e062e1 7c0828ee ...p..A.X.b.|.(. - 01b0 62814c08 57f0c5f2 c2f60562 317c0828 b.L.W......b1|.( - 01c0 f562317c 0828fec4 c3094af7 60c52258 .b1|.(....J.`."X - 01d0 de4839f2 0f8fe6fe ffffc5c2 58fd48ff .H9.........X.H. - 01e0 ca48c1ea 03c4c142 58fc488d 14d50800 .H.....BX.H..... - 01f0 0000c4c1 4258fb48 39d77e57 c5f828c1 ....BX.H9.~W..(. - 0200 c5fa102d 00000000 0f1f8400 00000000 ...-............ - 0210 c5fa1014 9148ffc2 c5f828da c5e857e5 .....H....(...W. - 0220 c5f2c2d2 05c4e361 4ad420c5 fa58c248 .......aJ. ..X.H - 0230 39d77fdc c5fa58ff c5f828c7 c30f1f00 9.....X...(..... - 0240 c5c057ff c5f828c7 c3c5f057 c9c5f828 ..W...(....W...( - 0250 f9eba9c5 f828c1eb db0f1f80 00000000 .....(.......... - 0260 4889ce4c 89c2e895 fdffff48 8b442410 H..L.......H.D$. - 0270 c5fa1100 31c0c366 0f1f8400 00000000 ....1..f........ + 0000 4889f148 85ff0f8e c4000000 4885d20f H..H........H... + 0010 8ebb0000 004883fa 01744d48 0faffac5 .....H...tMH.... + 0020 e857d2c5 f828ca48 89fe31c0 c5fa102d .W...(.H..1....- + 0030 00000000 0f1f4000 c5fa1004 814801d0 ......@......H.. + 0040 c5f828d8 c5f857e5 c5eac2c0 05c4e361 ..(...W........a + 0050 4ac400c5 f258c848 39c67fdc c5f828c1 J....X.H9.....(. + 0060 c30f1f80 00000000 4881ffff 0000007f ........H....... + 0070 6f4889fe 4883e6f8 4883ff07 0f8fc901 oH..H...H....... + 0080 0000c5e8 57d2c5f8 28ca4839 fe7dcd48 ....W...(.H9.}.H + 0090 8d04b148 8d14b9c5 fa102d00 00000090 ...H......-..... + 00a0 c5fa1000 4883c004 c5f828d8 c5f857e5 ....H.....(...W. + 00b0 c5eac2c0 05c4e361 4ac400c5 f258c848 .......aJ....X.H + 00c0 39c275dc c5f828c1 c30f1f80 00000000 9.u...(......... + 00d0 c5f057c9 c5f828c1 c30f1f80 00000000 ..W...(......... + 00e0 4889f0ba 20000000 83e61f48 29f248c1 H... ......H).H. + 00f0 ea0283e2 070f8434 010000c5 e857d248 .......4.....W.H + 0100 8d3491c5 f828dac5 fa102d00 00000090 .4...(....-..... + 0110 c5fa1000 4883c004 c5f828c8 c5f857e5 ....H.....(...W. + 0120 c5eac2c0 05c4e371 4ac400c5 e258d848 .......qJ....X.H + 0130 39c675dc 4829d748 89fe4989 f8488d0c 9.u.H).H..I..H.. + 0140 914883e6 f84530c0 4881ffff 0000000f .H...E0.H....... + 0150 8e7c0000 004d85c0 0f84e400 0000c5d8 .|...M.......... + 0160 57e4c4e2 7d590500 00000048 89c84a8d W...}Y.....H..J. + 0170 1481c5fc 28ecc5fc 28f4c5fc 28cc6690 ....(...(...(.f. + 0180 c5fddb38 4883e880 c5f458cf c5fddb78 ...8H.....X....x + 0190 a0c5cc58 f7c5fddb 78c0c5d4 58efc5fd ...X....x...X... + 01a0 db78e0c5 dc58e748 39c275d4 c5f458c6 .x...X.H9.u...X. + 01b0 c5fc58c5 c5fc58c4 c4e37d19 c101c5f0 ..X...X...}..... + 01c0 58c0c5fb 7cc0c5fb 7cc0c5e2 58d8c5f8 X...|...|...X... + 01d0 774939f0 7d66488d 56ff4c29 c24883e2 wI9.}fH.V.L).H.. + 01e0 f84c01c2 c5f057c9 c4e27959 25000000 .L....W...yY%... + 01f0 004a8d04 81488d54 9120c5f8 28c16690 .J...H.T. ..(.f. + 0200 c5d9db28 4883c020 c5f858c5 c5d9db68 ...(H.. ..X....h + 0210 f0c5f058 cd4839c2 75e6c5f8 58c1c5fb ...X.H9.u...X... + 0220 7cc0c5fb 7cc0c5fa 58cbe95b feffffc5 |...|...X..[.... + 0230 e857d2c5 f828dae9 f8feffff c5f857c0 .W...(........W. + 0240 ebdcc5f8 57c0e96d ffffffc5 e857d245 ....W..m.....W.E + 0250 31c0c5f8 28dae976 ffffff0f 1f440000 1...(..v.....D.. + 0260 4883ec08 4889ce4c 89c2e891 fdffff48 H...H..L.......H + 0270 8b442418 c5fa1100 31c04883 c408c390 .D$.....1.H..... 0280 41564989 f6415549 89d54154 4989fc55 AVI..AUI..ATI..U 0290 534881ec 20040000 64488b04 25280000 SH.. ...dH..%(.. 02a0 00488984 24180400 0031c0e8 00000000 .H..$....1...... ELF section: pipe command #0 failed with 1 for old//usr/lib64/libopenblas_openmp.a/sasum_k_COOPERLAKE.o /usr/lib64/libopenblas_openmp.a/sasum_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sasum_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sasum_k_SKYLAKEX.o (disasm) @@ -93,36 +93,31 @@ test %r8,%r8 je vxorps %xmm4,%xmm4,%xmm4 - vpbroadcastd offset(%rip),%zmm0 # + vpbroadcastq offset(%rip),%ymm0 # mov %rcx,%rax lea (%rcx,%r8,4),%rdx - vmovaps %zmm4,%zmm5 - vmovaps %zmm4,%zmm6 - vmovaps %zmm4,%zmm1 - nopl (%rax) - vpandd (%rax),%zmm0,%zmm7 - add $something,%rax - vaddps %zmm7,%zmm1,%zmm1 - vpandd -offset(%rax),%zmm0,%zmm7 - vaddps %zmm7,%zmm6,%zmm6 - vpandd -offset(%rax),%zmm0,%zmm7 - vaddps %zmm7,%zmm5,%zmm5 - vpandd -offset(%rax),%zmm0,%zmm7 - vaddps %zmm7,%zmm4,%zmm4 + vmovaps %ymm4,%ymm5 + vmovaps %ymm4,%ymm6 + vmovaps %ymm4,%ymm1 + xchg %ax,%ax + vpand (%rax),%ymm0,%ymm7 + sub $something,%rax + vaddps %ymm7,%ymm1,%ymm1 + vpand -offset(%rax),%ymm0,%ymm7 + vaddps %ymm7,%ymm6,%ymm6 + vpand -offset(%rax),%ymm0,%ymm7 + vaddps %ymm7,%ymm5,%ymm5 + vpand -offset(%rax),%ymm0,%ymm7 + vaddps %ymm7,%ymm4,%ymm4 cmp %rax,%rdx jne - vaddps %zmm6,%zmm1,%zmm0 - vaddps %zmm5,%zmm0,%zmm0 - vaddps %zmm4,%zmm0,%zmm0 - vextractf64x4 $something,%zmm0,%ymm1 - vaddps %ymm0,%ymm1,%ymm0 + vaddps %ymm6,%ymm1,%ymm0 + vaddps %ymm5,%ymm0,%ymm0 + vaddps %ymm4,%ymm0,%ymm0 vextractf128 $something,%ymm0,%xmm1 - vaddps %xmm0,%xmm1,%xmm1 - vpermilps $something,%xmm1,%xmm0 - vaddps %xmm1,%xmm0,%xmm0 - vmovaps %xmm0,%xmm1 - vshufps $something,%xmm0,%xmm0,%xmm0 - vaddss %xmm0,%xmm1,%xmm0 + vaddps %xmm0,%xmm1,%xmm0 + vhaddps %xmm0,%xmm0,%xmm0 + vhaddps %xmm0,%xmm0,%xmm0 vaddss %xmm0,%xmm3,%xmm3 vzeroupper cmp %rsi,%r8 @@ -136,7 +131,7 @@ lea (%rcx,%r8,4),%rax lea offset(%rcx,%rdx,4),%rdx vmovaps %xmm1,%xmm0 - nopl offset(%rax,%rax,1) + xchg %ax,%ax vpand (%rax),%xmm4,%xmm5 add $something,%rax vaddps %xmm5,%xmm0,%xmm0 @@ -154,7 +149,7 @@ jmp vxorps %xmm0,%xmm0,%xmm0 jmp - vxorpd %xmm0,%xmm0,%xmm0 + vxorps %xmm0,%xmm0,%xmm0 jmp vxorps %xmm2,%xmm2,%xmm2 xor %r8d,%r8d /usr/lib64/libopenblas_openmp.a/sasum_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sasum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sasum_k_SKYLAKEX.o (objdump) @@ -9,62 +9,58 @@ 0040 c5f828d8 c5f857e5 c5eac2c0 05c4e361 ..(...W........a 0050 4ac400c5 f258c848 39c67fdc c5f828c1 J....X.H9.....(. 0060 c30f1f80 00000000 4881ffff 0000007f ........H....... - 0070 6f4889fe 4883e6f8 4883ff07 0f8f0902 oH..H...H....... + 0070 6f4889fe 4883e6f8 4883ff07 0f8fc901 oH..H...H....... 0080 0000c5e8 57d2c5f8 28ca4839 fe7dcd48 ....W...(.H9.}.H 0090 8d04b148 8d14b9c5 fa102d00 00000090 ...H......-..... 00a0 c5fa1000 4883c004 c5f828d8 c5f857e5 ....H.....(...W. 00b0 c5eac2c0 05c4e361 4ac400c5 f258c848 .......aJ....X.H 00c0 39c275dc c5f828c1 c30f1f80 00000000 9.u...(......... 00d0 c5f057c9 c5f828c1 c30f1f80 00000000 ..W...(......... - 00e0 4889f0ba 40000000 83e63f48 29f248c1 H...@.....?H).H. - 00f0 ea0283e2 0f0f8474 010000c5 e857d248 .......t.....W.H + 00e0 4889f0ba 20000000 83e61f48 29f248c1 H... ......H).H. + 00f0 ea0283e2 070f8434 010000c5 e857d248 .......4.....W.H 0100 8d3491c5 f828dac5 fa102d00 00000090 .4...(....-..... 0110 c5fa1000 4883c004 c5f828c8 c5f857e5 ....H.....(...W. 0120 c5eac2c0 05c4e371 4ac400c5 e258d848 .......qJ....X.H 0130 39c675dc 4829d748 89fe4989 f8488d0c 9.u.H).H..I..H.. 0140 914883e6 f84530c0 4881ffff 0000000f .H...E0.H....... - 0150 8eb60000 004d85c0 0f842401 0000c5d8 .....M....$..... - 0160 57e462f2 7d485805 00000000 4889c84a W.b.}HX.....H..J - 0170 8d148162 f17c4828 ec62f17c 4828f462 ...b.|H(.b.|H(.b - 0180 f17c4828 cc0f1f00 62f17d48 db384805 .|H(....b.}H.8H. - 0190 00010000 62f17448 58cf62f1 7d48db78 ....b.tHX.b.}H.x - 01a0 fd62f14c 4858f762 f17d48db 78fe62f1 .b.LHX.b.}H.x.b. - 01b0 544858ef 62f17d48 db78ff62 f15c4858 THX.b.}H.x.b.\HX - 01c0 e74839c2 75c262f1 744858c6 62f17c48 .H9.u.b.tHX.b.|H - 01d0 58c562f1 7c4858c4 62f3fd48 1bc101c5 X.b.|HX.b..H.... - 01e0 f458c0c4 e37d19c1 01c5f058 c8c4e379 .X...}.....X...y - 01f0 04c14ec5 f858c1c5 f828c8c5 f8c6c055 ..N..X...(.....U - 0200 c5f258c0 c5e258d8 c5f87749 39f07d6c ..X...X...wI9.}l - 0210 488d56ff 4c29c248 83e2f84c 01c2c5f0 H.V.L).H...L.... - 0220 57c9c4e2 79592500 0000004a 8d048148 W...yY%....J...H - 0230 8d549120 c5f828c1 0f1f8400 00000000 .T. ..(......... - 0240 c5d9db28 4883c020 c5f858c5 c5d9db68 ...(H.. ..X....h - 0250 f0c5f058 cd4839c2 75e6c5f8 58c1c5fb ...X.H9.u...X... - 0260 7cc0c5fb 7cc0c5fa 58cbe91b feffffc5 |...|...X....... - 0270 e857d2c5 f828dae9 b8feffff c5f857c0 .W...(........W. - 0280 ebdcc5f9 57c0e94d ffffffc5 e857d245 ....W..M.....W.E - 0290 31c0c5f8 28dae970 ffffff0f 1f440000 1...(..p.....D.. - 02a0 4883ec08 4889ce4c 89c2e851 fdffff48 H...H..L...Q...H - 02b0 8b442418 c5fa1100 31c04883 c408c390 .D$.....1.H..... - 02c0 41564989 f6415549 89d54154 4989fc55 AVI..AUI..ATI..U - 02d0 534881ec 20040000 64488b04 25280000 SH.. ...dH..%(.. - 02e0 00488984 24180400 0031c0e8 00000000 .H..$....1...... - 02f0 83f8010f 84e70000 0089c5e8 00000000 ................ - 0300 85c00f85 d8000000 488b1d00 00000048 ........H......H - 0310 630b39cd 740a89ef e8000000 0048630b c.9.t........Hc. - 0320 4981fca0 8601000f 8eb30000 004d85ed I............M.. - 0330 0f8eaa00 00004c89 e048ba09 e1d1c611 ......L..H...... - 0340 6bf12948 f7ea4c89 e048c1f8 3f48c1fa k.)H..L..H..?H.. - 0350 0e4829c2 4839ca48 0f4eca48 89cd4883 .H).H9.H.N.H..H. - 0360 f901747c 4883ec08 51488d05 30ffffff ..t|H...QH..0... - 0370 4d89f150 31c931d2 6a004c89 e6bf0200 M..P1.1.j.L..... - 0380 0000488d 5c243053 6a006a00 41554c8d ..H.\$0Sj.j.AUL. - 0390 44244ce8 00000000 4883c440 4885ed7e D$L.....H..@H..~ - 03a0 6f48c1e5 04488d14 2b4889d8 c5f857c0 oH...H..+H....W. - 03b0 c5fa5800 4883c010 4839d075 f3488b84 ..X.H...H9.u.H.. - 03c0 24180400 0064482b 04252800 00007546 $....dH+.%(...uF - 03d0 4881c420 0400005b 5d415c41 5d415ec3 H.. ...[]A\A]A^. - 03e0 488b8424 18040000 64482b04 25280000 H..$....dH+.%(.. - 03f0 00752348 81c42004 00005b5d 4c89e741 .u#H.. ...[]L..A - 0400 5c4c89ea 415d4c89 f6415ee9 f0fbffff \L..A]L..A^..... - 0410 c5f857c0 eba7e800 000000 ..W........ + 0150 8e7c0000 004d85c0 0f84e400 0000c5d8 .|...M.......... + 0160 57e4c4e2 7d590500 00000048 89c84a8d W...}Y.....H..J. + 0170 1481c5fc 28ecc5fc 28f4c5fc 28cc6690 ....(...(...(.f. + 0180 c5fddb38 4883e880 c5f458cf c5fddb78 ...8H.....X....x + 0190 a0c5cc58 f7c5fddb 78c0c5d4 58efc5fd ...X....x...X... + 01a0 db78e0c5 dc58e748 39c275d4 c5f458c6 .x...X.H9.u...X. + 01b0 c5fc58c5 c5fc58c4 c4e37d19 c101c5f0 ..X...X...}..... + 01c0 58c0c5fb 7cc0c5fb 7cc0c5e2 58d8c5f8 X...|...|...X... + 01d0 774939f0 7d66488d 56ff4c29 c24883e2 wI9.}fH.V.L).H.. + 01e0 f84c01c2 c5f057c9 c4e27959 25000000 .L....W...yY%... + 01f0 004a8d04 81488d54 9120c5f8 28c16690 .J...H.T. ..(.f. + 0200 c5d9db28 4883c020 c5f858c5 c5d9db68 ...(H.. ..X....h + 0210 f0c5f058 cd4839c2 75e6c5f8 58c1c5fb ...X.H9.u...X... + 0220 7cc0c5fb 7cc0c5fa 58cbe95b feffffc5 |...|...X..[.... + 0230 e857d2c5 f828dae9 f8feffff c5f857c0 .W...(........W. + 0240 ebdcc5f8 57c0e96d ffffffc5 e857d245 ....W..m.....W.E + 0250 31c0c5f8 28dae976 ffffff0f 1f440000 1...(..v.....D.. + 0260 4883ec08 4889ce4c 89c2e891 fdffff48 H...H..L.......H + 0270 8b442418 c5fa1100 31c04883 c408c390 .D$.....1.H..... + 0280 41564989 f6415549 89d54154 4989fc55 AVI..AUI..ATI..U + 0290 534881ec 20040000 64488b04 25280000 SH.. ...dH..%(.. + 02a0 00488984 24180400 0031c0e8 00000000 .H..$....1...... + 02b0 83f8010f 84e70000 0089c5e8 00000000 ................ + 02c0 85c00f85 d8000000 488b1d00 00000048 ........H......H + 02d0 630b39cd 740a89ef e8000000 0048630b c.9.t........Hc. + 02e0 4981fca0 8601000f 8eb30000 004d85ed I............M.. + 02f0 0f8eaa00 00004c89 e048ba09 e1d1c611 ......L..H...... + 0300 6bf12948 f7ea4c89 e048c1f8 3f48c1fa k.)H..L..H..?H.. + 0310 0e4829c2 4839ca48 0f4eca48 89cd4883 .H).H9.H.N.H..H. + 0320 f901747c 4883ec08 51488d05 30ffffff ..t|H...QH..0... + 0330 4d89f150 31c931d2 6a004c89 e6bf0200 M..P1.1.j.L..... + 0340 0000488d 5c243053 6a006a00 41554c8d ..H.\$0Sj.j.AUL. + 0350 44244ce8 00000000 4883c440 4885ed7e D$L.....H..@H..~ + 0360 6f48c1e5 04488d14 2b4889d8 c5f857c0 oH...H..+H....W. + 0370 c5fa5800 4883c010 4839d075 f3488b84 ..X.H...H9.u.H.. + 0380 24180400 0064482b 04252800 00007546 $....dH+.%(...uF + 0390 4881c420 0400005b 5d415c41 5d415ec3 H.. ...[]A\A]A^. + 03a0 488b8424 18040000 64482b04 25280000 H..$....dH+.%(.. + 03b0 00752348 81c42004 00005b5d 4c89e741 .u#H.. ...[]L..A + 03c0 5c4c89ea 415d4c89 f6415ee9 30fcffff \L..A]L..A^.0... + 03d0 c5f857c0 eba7e800 000000 ..W........ /usr/lib64/libopenblas_openmp.a/sasum_k_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/sasum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sasum_k_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39000000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/sasum_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/sasum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sasum_k_SKYLAKEX.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 10000000 1c000000 ................ - 0020 00000000 9b020000 00000000 14000000 ................ + 0020 00000000 5b020000 00000000 14000000 ....[........... 0030 30000000 00000000 1f000000 00440e10 0............D.. 0040 5a0e0800 80000000 48000000 00000000 Z.......H....... 0050 5b010000 00420e10 8e02450e 188d0345 [....B....E....E /usr/lib64/libopenblas_openmp.a/saxpy_k_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/saxpy_k_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/saxpy_k_COOPERLAKE.o (disasm) @@ -4,70 +4,93 @@ Disassembly of section .text: +saxpy_kernel_16: + xor %eax,%eax + vbroadcastss (%rcx),%ymm0 + nopw offset(%rax,%rax,1) + vmovups (%rdx,%rax,4),%ymm12 + vmovups offset(%rdx,%rax,4),%ymm13 + vmovups offset(%rdx,%rax,4),%ymm14 + vmovups offset(%rdx,%rax,4),%ymm15 + vfmadd231ps (%rsi,%rax,4),%ymm0,%ymm12 + vfmadd231ps offset(%rsi,%rax,4),%ymm0,%ymm13 + vfmadd231ps offset(%rsi,%rax,4),%ymm0,%ymm14 + vfmadd231ps offset(%rsi,%rax,4),%ymm0,%ymm15 + vmovups %ymm12,(%rdx,%rax,4) + vmovups %ymm13,offset(%rdx,%rax,4) + vmovups %ymm14,offset(%rdx,%rax,4) + vmovups %ymm15,offset(%rdx,%rax,4) + add $something,%rax + sub $something,%rdi + jne + vzeroupper + vzeroupper + ret + nopw offset(%rax,%rax,1) + saxpy_k_COOPERLAKE: - push %rbp - mov %rsp,%rbp push %r15 push %r14 push %r13 push %r12 + push %rbp push %rbx - and $something,%rsp - mov offset(%rbp),%rsi + sub $something,%rsp + mov offset(%rsp),%rsi + vmovss %xmm0,offset(%rsp) test %rdi,%rdi jle mov %rdi,%r10 - mov %rcx,%rbx + mov %rcx,%rbp cmp $something,%r8 jne cmp $something,%rsi jne - mov %rdi,%rax - and $something,%rax + mov %rdi,%r8 + and $something,%r8 jne - nopl offset(%rax) - vmovss (%rbx,%rax,4),%xmm1 - vfmadd213ss (%r9,%rax,4),%xmm0,%xmm1 - vmovss %xmm1,(%r9,%rax,4) - inc %rax - cmp %rax,%r10 + vmovss offset(%rsp),%xmm1 + nopl offset(%rax,%rax,1) + vmovss offset(%rbp,%r8,4),%xmm0 + vfmadd213ss (%r9,%r8,4),%xmm1,%xmm0 + vmovss %xmm0,(%r9,%r8,4) + inc %r8 + cmp %r8,%r10 jg - lea -offset(%rbp),%rsp - xor %eax,%eax + add $something,%rsp pop %rbx + pop %rbp pop %r12 pop %r13 pop %r14 + xor %eax,%eax pop %r15 - pop %rbp ret - nopw offset(%rax,%rax,1) + nopl offset(%rax) mov %r10,%rcx + vmovss offset(%rsp),%xmm0 and $something,%rcx je lea offset(,%r8,4),%rax + lea (%r8,%r8,1),%r12 + lea (%rsi,%rsi,1),%r11 + mov %r8,%r14 + mov %rsi,%r13 kmovq %rax,%k0 lea offset(,%rsi,4),%rax kmovq %rax,%k1 - mov %rsi,%rax - shl $something,%rax - mov %rax,-offset(%rsp) - mov %r10,-offset(%rsp) - lea (%r8,%r8,1),%r13 - lea (%rsi,%rsi,1),%r11 - mov %r8,%r14 - mov -offset(%rsp),%r10 - lea offset(%r13,%r8,1),%r15 - lea (%r11,%rsi,1),%r12 + lea (%r12,%r8,1),%r15 + lea (%r11,%rsi,1),%rbx shl $something,%r14 - mov %rbx,%rdx + mov %rbp,%rdx + shl $something,%r13 mov %r9,%rax xor %edi,%edi - nopl (%rax) + nopl offset(%rax,%rax,1) vmovss (%rdx),%xmm4 vmovss (%rdx,%r8,4),%xmm3 vfmadd213ss (%rax),%xmm0,%xmm4 - vmovss (%rdx,%r13,4),%xmm2 + vmovss (%rdx,%r12,4),%xmm2 vmovss (%rdx,%r15,4),%xmm1 add $something,%rdi add %r14,%rdx @@ -76,15 +99,14 @@ vmovss %xmm3,(%rax,%rsi,4) vfmadd213ss (%rax,%r11,4),%xmm0,%xmm2 vmovss %xmm2,(%rax,%r11,4) - vfmadd213ss (%rax,%r12,4),%xmm0,%xmm1 - vmovss %xmm1,(%rax,%r12,4) - add %r10,%rax + vfmadd213ss (%rax,%rbx,4),%xmm0,%xmm1 + vmovss %xmm1,(%rax,%rbx,4) + add %r13,%rax cmp %rdi,%rcx jg dec %rcx shr $something,%rcx inc %rcx - mov -offset(%rsp),%r10 kmovq %k0,%rdx kmovq %k1,%rax imul %rcx,%rdx @@ -95,8 +117,8 @@ shl $something,%rsi lea (%r9,%rax,4),%rax shl $something,%r8 - lea (%rbx,%rdx,4),%rdx - nop + lea offset(%rbp,%rdx,4),%rdx + nopw offset(%rax,%rax,1) vmovss (%rdx),%xmm1 inc %rcx vfmadd213ss (%rax),%xmm0,%xmm1 @@ -106,64 +128,15 @@ cmp %rcx,%r10 jg jmp - mov %rdi,%rcx - vbroadcastss %xmm0,%ymm1 - vbroadcastss %xmm0,%zmm2 - and $something,%rcx - je - dec %rcx - shr $something,%rcx - mov %rcx,%rdi - shl $something,%rdi + lea offset(%rsp),%rcx mov %r9,%rdx - mov %rbx,%rsi - lea offset(%r9,%rdi,1),%rdi - nopl offset(%rax) - vmovups (%rsi),%zmm3 - add $something,%rdx - vfmadd213ps -offset(%rdx),%zmm2,%zmm3 - add $something,%rsi - vmovups %zmm3,-offset(%rdx) - vmovups -offset(%rsi),%zmm3 - vfmadd213ps -offset(%rdx),%zmm2,%zmm3 - vmovups %zmm3,-offset(%rdx) - vmovups -offset(%rsi),%zmm3 - vfmadd213ps -offset(%rdx),%zmm2,%zmm3 - vmovups %zmm3,-offset(%rdx) - vmovups -offset(%rsi),%zmm3 - vfmadd213ps -offset(%rdx),%zmm2,%zmm3 - vmovups %zmm3,-offset(%rdx) - cmp %rdx,%rdi - jne - inc %rcx - shl $something,%rcx - cmp %rcx,%rax - jle - lea (%r9,%rcx,4),%rdx - xchg %ax,%ax - vmovups (%rbx,%rcx,4),%ymm2 - sub $something,%rdx - vfmadd213ps -offset(%rdx),%ymm1,%ymm2 - vmovups %ymm2,-offset(%rdx) /usr/lib64/libopenblas_openmp.a/saxpy_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/saxpy_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/saxpy_k_COOPERLAKE.o (objdump) @@ -2,46 +2,37 @@ /usr/lib64/libopenblas_openmp.a/saxpy_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 554889e5 41574156 41554154 534883e4 UH..AWAVAUATSH.. - 0010 c0488b75 104885ff 7e3f4989 fa4889cb .H.u.H..~?I..H.. - 0020 4983f801 754a4883 fe017544 4889f848 I...uJH...uDH..H - 0030 83e0e00f 85470100 000f1f80 00000000 .....G.......... - 0040 c5fa100c 83c4c279 a90c81c4 c17a110c .......y.....z.. - 0050 8148ffc0 4939c27f e7488d65 d831c05b .H..I9...H.e.1.[ - 0060 415c415d 415e415f 5dc3660f 1f440000 A\A]A^A_].f..D.. - 0070 4c89d148 83e1fc0f 84130200 004a8d04 L..H.........J.. - 0080 85000000 00c4e1fb 92c0488d 04b50000 ..........H..... - 0090 0000c4e1 fb92c848 89f048c1 e0044889 .......H..H...H. - 00a0 4424f84c 895424f0 4f8d2c00 4c8d1c36 D$.L.T$.O.,.L..6 - 00b0 4d89c64c 8b5424f8 4f8d7c05 004d8d24 M..L.T$.O.|..M.$ - 00c0 3349c1e6 044889da 4c89c831 ff0f1f00 3I...H..L..1.... - 00d0 c5fa1022 c4a17a10 1c82c4e2 79a920c4 ..."..z.....y. . - 00e0 a17a1014 aac4a17a 100cba48 83c7044c .z.....z...H...L - 00f0 01f2c5fa 1120c4e2 79a91cb0 c5fa111c ..... ..y....... - 0100 b0c4a279 a91498c4 a17a1114 98c4a279 ...y.....z.....y - 0110 a90ca0c4 a17a110c a04c01d0 4839f97f .....z...L..H9.. - 0120 af48ffc9 48c1e902 48ffc14c 8b5424f0 .H..H...H..L.T$. - 0130 c4e1fb93 d0c4e1fb 93c1480f afd1480f ..........H...H. - 0140 afc148c1 e1024939 ca0f8e0a ffffff48 ..H...I9.......H - 0150 c1e60249 8d048149 c1e00248 8d149390 ...I...I...H.... - 0160 c5fa100a 48ffc1c4 e279a908 4c01c2c5 ....H....y..L... - 0170 fa110848 01f04939 ca7fe5e9 d9feffff ...H..I9........ - 0180 4889f9c4 e27d18c8 62f27d48 18d04883 H....}..b.}H..H. - 0190 e1c00f84 92000000 48ffc948 c1e90648 ........H..H...H - 01a0 89cf48c1 e7084c89 ca4889de 498dbc39 ..H...L..H..I..9 - 01b0 00010000 0f1f4000 62f17c48 101e4881 ......@.b.|H..H. - 01c0 c2000100 0062f26d 48a85afc 4881c600 .....b.mH.Z.H... - 01d0 01000062 f17c4811 5afc62f1 7c48105e ...b.|H.Z.b.|H.^ - 01e0 fd62f26d 48a85afd 62f17c48 115afd62 .b.mH.Z.b.|H.Z.b - 01f0 f17c4810 5efe62f2 6d48a85a fe62f17c .|H.^.b.mH.Z.b.| - 0200 48115afe 62f17c48 105eff62 f26d48a8 H.Z.b.|H.^.b.mH. - 0210 5aff62f1 7c48115a ff4839d7 759a48ff Z.b.|H.Z.H9.u.H. - 0220 c148c1e1 064839c8 7e56498d 14896690 .H...H9.~VI...f. - 0230 c5fc1014 8b4883ea 80c4e275 a85280c5 .....H.....u.R.. - 0240 fc115280 c5fc1054 8b20c4e2 75a852a0 ..R....T. ..u.R. - 0250 c5fc1152 a0c5fc10 548b40c4 e275a852 ...R....T.@..u.R - 0260 c0c5fc11 52c0c5fc 10548b60 4883c120 ....R....T.`H.. - 0270 c4e275a8 52e0c5fc 1152e048 39c87fb0 ..u.R....R.H9... - 0280 4939c27e 14c5f877 e9b3fdff ff0f1f00 I9.~...w........ - 0290 31c031d2 e9b6feff ffc5f877 e9b8fdff 1.1........w.... - 02a0 ff . + 0000 31c0c4e2 7d180166 0f1f8400 00000000 1...}..f........ + 0010 c57c1024 82c57c10 6c8220c5 7c107482 .|.$..|.l. .|.t. + 0020 40c57c10 7c8260c4 627db824 86c4627d @.|.|.`.b}.$..b} + 0030 b86c8620 c4627db8 748640c4 627db87c .l. .b}.t.@.b}.| + 0040 8660c57c 112482c5 7c116c82 20c57c11 .`.|.$..|.l. .|. + 0050 748240c5 7c117c82 604883c0 204883ef t.@.|.|.`H.. H.. + 0060 2075adc5 f877c5f8 77c3660f 1f440000 u...w..w.f..D.. + 0070 41574156 41554154 55534883 ec08488b AWAVAUATUSH...H. + 0080 742440c5 fa114424 044885ff 7e454989 t$@...D$.H..~EI. + 0090 fa4889cd 4983f801 754e4883 fe017548 .H..I...uNH...uH + 00a0 4989f849 83e0e00f 85430100 00c5fa10 I..I.....C...... + 00b0 4c24040f 1f440000 c4a17a10 448500c4 L$...D....z.D... + 00c0 8271a904 81c4817a 11048149 ffc04d39 .q.....z...I..M9 + 00d0 c27fe548 83c4085b 5d415c41 5d415e31 ...H...[]A\A]A^1 + 00e0 c0415fc3 0f1f4000 4c89d1c5 fa104424 .A_...@.L.....D$ + 00f0 044883e1 fc0f841d 0100004a 8d048500 .H.........J.... + 0100 0000004f 8d24004c 8d1c364d 89c64989 ...O.$.L..6M..I. + 0110 f5c4e1fb 92c0488d 04b50000 0000c4e1 ......H......... + 0120 fb92c84f 8d3c0449 8d1c3349 c1e60448 ...O.<.I..3I...H + 0130 89ea49c1 e5044c89 c831ff0f 1f440000 ..I...L..1...D.. + 0140 c5fa1022 c4a17a10 1c82c4e2 79a920c4 ..."..z.....y. . + 0150 a17a1014 a2c4a17a 100cba48 83c7044c .z.....z...H...L + 0160 01f2c5fa 1120c4e2 79a91cb0 c5fa111c ..... ..y....... + 0170 b0c4a279 a91498c4 a17a1114 98c4e279 ...y.....z.....y + 0180 a90c98c5 fa110c98 4c01e848 39f97fb0 ........L..H9... + 0190 48ffc948 c1e90248 ffc1c4e1 fb93d0c4 H..H...H........ + 01a0 e1fb93c1 480fafd1 480fafc1 48c1e102 ....H...H...H... + 01b0 4939ca0f 8e1affff ff48c1e6 02498d04 I9.......H...I.. + 01c0 8149c1e0 02488d54 9500660f 1f440000 .I...H.T..f..D.. + 01d0 c5fa100a 48ffc1c4 e279a908 4c01c2c5 ....H....y..L... + 01e0 fa110848 01f04939 ca7fe5e9 e3feffff ...H..I9........ + 01f0 488d4c24 044c89ca 4889ee4c 89c7e8fd H.L$.L..H..L.... + 0200 fdffff4d 39c20f8f a1feffff e9c2feff ...M9........... + 0210 ff0f1f80 00000000 31c031d2 eb9b ........1.1... /usr/lib64/libopenblas_openmp.a/saxpy_k_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/saxpy_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/saxpy_k_COOPERLAKE.o (objdump) @@ -4,4 +4,4 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0020 010001c0 04000000 19080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/saxpy_k_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/saxpy_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/saxpy_k_COOPERLAKE.o (objdump) @@ -3,7 +3,10 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 2c000000 1c000000 ........,....... - 0020 00000000 a1020000 00410e10 8602430d .........A....C. - 0030 064d8f03 8e048d05 8c068307 02580a0c .M...........X.. - 0040 0708470b 00000000 ..G..... + 0010 1b0c0708 90010000 10000000 1c000000 ................ + 0020 00000000 6a000000 00000000 48000000 ....j.......H... + 0030 30000000 00000000 ae010000 00420e10 0............B.. + 0040 8f02420e 188e0342 0e208d04 420e288c ..B....B. ..B.(. + 0050 05410e30 8606410e 38830744 0e400259 .A.0..A.8..D.@.Y + 0060 0a0e3841 0e30410e 28420e20 420e1842 ..8A.0A.(B. B..B + 0070 0e10440e 08450b00 ..D..E.. /usr/lib64/libopenblas_openmp.a/saxpy_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/saxpy_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/saxpy_k_SKYLAKEX.o (disasm) @@ -4,70 +4,93 @@ Disassembly of section .text: +saxpy_kernel_16: + xor %eax,%eax + vbroadcastss (%rcx),%ymm0 + nopw offset(%rax,%rax,1) + vmovups (%rdx,%rax,4),%ymm12 + vmovups offset(%rdx,%rax,4),%ymm13 + vmovups offset(%rdx,%rax,4),%ymm14 + vmovups offset(%rdx,%rax,4),%ymm15 + vfmadd231ps (%rsi,%rax,4),%ymm0,%ymm12 + vfmadd231ps offset(%rsi,%rax,4),%ymm0,%ymm13 + vfmadd231ps offset(%rsi,%rax,4),%ymm0,%ymm14 + vfmadd231ps offset(%rsi,%rax,4),%ymm0,%ymm15 + vmovups %ymm12,(%rdx,%rax,4) + vmovups %ymm13,offset(%rdx,%rax,4) + vmovups %ymm14,offset(%rdx,%rax,4) + vmovups %ymm15,offset(%rdx,%rax,4) + add $something,%rax + sub $something,%rdi + jne + vzeroupper + vzeroupper + ret + nopw offset(%rax,%rax,1) + saxpy_k_SKYLAKEX: - push %rbp - mov %rsp,%rbp push %r15 push %r14 push %r13 push %r12 + push %rbp push %rbx - and $something,%rsp - mov offset(%rbp),%rsi + sub $something,%rsp + mov offset(%rsp),%rsi + vmovss %xmm0,offset(%rsp) test %rdi,%rdi jle mov %rdi,%r10 - mov %rcx,%rbx + mov %rcx,%rbp cmp $something,%r8 jne cmp $something,%rsi jne - mov %rdi,%rax - and $something,%rax + mov %rdi,%r8 + and $something,%r8 jne - nopl offset(%rax) - vmovss (%rbx,%rax,4),%xmm1 - vfmadd213ss (%r9,%rax,4),%xmm0,%xmm1 - vmovss %xmm1,(%r9,%rax,4) - inc %rax - cmp %rax,%r10 + vmovss offset(%rsp),%xmm1 + nopl offset(%rax,%rax,1) + vmovss offset(%rbp,%r8,4),%xmm0 + vfmadd213ss (%r9,%r8,4),%xmm1,%xmm0 + vmovss %xmm0,(%r9,%r8,4) + inc %r8 + cmp %r8,%r10 jg - lea -offset(%rbp),%rsp - xor %eax,%eax + add $something,%rsp pop %rbx + pop %rbp pop %r12 pop %r13 pop %r14 + xor %eax,%eax pop %r15 - pop %rbp ret - nopw offset(%rax,%rax,1) + nopl offset(%rax) mov %r10,%rcx + vmovss offset(%rsp),%xmm0 and $something,%rcx je lea offset(,%r8,4),%rax + lea (%r8,%r8,1),%r12 + lea (%rsi,%rsi,1),%r11 + mov %r8,%r14 + mov %rsi,%r13 kmovq %rax,%k0 lea offset(,%rsi,4),%rax kmovq %rax,%k1 - mov %rsi,%rax - shl $something,%rax - mov %rax,-offset(%rsp) - mov %r10,-offset(%rsp) - lea (%r8,%r8,1),%r13 - lea (%rsi,%rsi,1),%r11 - mov %r8,%r14 - mov -offset(%rsp),%r10 - lea offset(%r13,%r8,1),%r15 - lea (%r11,%rsi,1),%r12 + lea (%r12,%r8,1),%r15 + lea (%r11,%rsi,1),%rbx shl $something,%r14 - mov %rbx,%rdx + mov %rbp,%rdx + shl $something,%r13 mov %r9,%rax xor %edi,%edi - nopl (%rax) + nopl offset(%rax,%rax,1) vmovss (%rdx),%xmm4 vmovss (%rdx,%r8,4),%xmm3 vfmadd213ss (%rax),%xmm0,%xmm4 - vmovss (%rdx,%r13,4),%xmm2 + vmovss (%rdx,%r12,4),%xmm2 vmovss (%rdx,%r15,4),%xmm1 add $something,%rdi add %r14,%rdx @@ -76,15 +99,14 @@ vmovss %xmm3,(%rax,%rsi,4) vfmadd213ss (%rax,%r11,4),%xmm0,%xmm2 vmovss %xmm2,(%rax,%r11,4) - vfmadd213ss (%rax,%r12,4),%xmm0,%xmm1 - vmovss %xmm1,(%rax,%r12,4) - add %r10,%rax + vfmadd213ss (%rax,%rbx,4),%xmm0,%xmm1 + vmovss %xmm1,(%rax,%rbx,4) + add %r13,%rax cmp %rdi,%rcx jg dec %rcx shr $something,%rcx inc %rcx - mov -offset(%rsp),%r10 kmovq %k0,%rdx kmovq %k1,%rax imul %rcx,%rdx @@ -95,8 +117,8 @@ shl $something,%rsi lea (%r9,%rax,4),%rax shl $something,%r8 - lea (%rbx,%rdx,4),%rdx - nop + lea offset(%rbp,%rdx,4),%rdx + nopw offset(%rax,%rax,1) vmovss (%rdx),%xmm1 inc %rcx vfmadd213ss (%rax),%xmm0,%xmm1 @@ -106,64 +128,15 @@ cmp %rcx,%r10 jg jmp - mov %rdi,%rcx - vbroadcastss %xmm0,%ymm1 - vbroadcastss %xmm0,%zmm2 - and $something,%rcx - je - dec %rcx - shr $something,%rcx - mov %rcx,%rdi - shl $something,%rdi + lea offset(%rsp),%rcx mov %r9,%rdx - mov %rbx,%rsi - lea offset(%r9,%rdi,1),%rdi - nopl offset(%rax) - vmovups (%rsi),%zmm3 - add $something,%rdx - vfmadd213ps -offset(%rdx),%zmm2,%zmm3 - add $something,%rsi - vmovups %zmm3,-offset(%rdx) - vmovups -offset(%rsi),%zmm3 - vfmadd213ps -offset(%rdx),%zmm2,%zmm3 - vmovups %zmm3,-offset(%rdx) - vmovups -offset(%rsi),%zmm3 - vfmadd213ps -offset(%rdx),%zmm2,%zmm3 - vmovups %zmm3,-offset(%rdx) - vmovups -offset(%rsi),%zmm3 - vfmadd213ps -offset(%rdx),%zmm2,%zmm3 - vmovups %zmm3,-offset(%rdx) - cmp %rdx,%rdi - jne - inc %rcx - shl $something,%rcx - cmp %rcx,%rax - jle - lea (%r9,%rcx,4),%rdx - xchg %ax,%ax - vmovups (%rbx,%rcx,4),%ymm2 - sub $something,%rdx - vfmadd213ps -offset(%rdx),%ymm1,%ymm2 - vmovups %ymm2,-offset(%rdx) /usr/lib64/libopenblas_openmp.a/saxpy_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/saxpy_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/saxpy_k_SKYLAKEX.o (objdump) @@ -2,46 +2,37 @@ /usr/lib64/libopenblas_openmp.a/saxpy_k_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 554889e5 41574156 41554154 534883e4 UH..AWAVAUATSH.. - 0010 c0488b75 104885ff 7e3f4989 fa4889cb .H.u.H..~?I..H.. - 0020 4983f801 754a4883 fe017544 4889f848 I...uJH...uDH..H - 0030 83e0e00f 85470100 000f1f80 00000000 .....G.......... - 0040 c5fa100c 83c4c279 a90c81c4 c17a110c .......y.....z.. - 0050 8148ffc0 4939c27f e7488d65 d831c05b .H..I9...H.e.1.[ - 0060 415c415d 415e415f 5dc3660f 1f440000 A\A]A^A_].f..D.. - 0070 4c89d148 83e1fc0f 84130200 004a8d04 L..H.........J.. - 0080 85000000 00c4e1fb 92c0488d 04b50000 ..........H..... - 0090 0000c4e1 fb92c848 89f048c1 e0044889 .......H..H...H. - 00a0 4424f84c 895424f0 4f8d2c00 4c8d1c36 D$.L.T$.O.,.L..6 - 00b0 4d89c64c 8b5424f8 4f8d7c05 004d8d24 M..L.T$.O.|..M.$ - 00c0 3349c1e6 044889da 4c89c831 ff0f1f00 3I...H..L..1.... - 00d0 c5fa1022 c4a17a10 1c82c4e2 79a920c4 ..."..z.....y. . - 00e0 a17a1014 aac4a17a 100cba48 83c7044c .z.....z...H...L - 00f0 01f2c5fa 1120c4e2 79a91cb0 c5fa111c ..... ..y....... - 0100 b0c4a279 a91498c4 a17a1114 98c4a279 ...y.....z.....y - 0110 a90ca0c4 a17a110c a04c01d0 4839f97f .....z...L..H9.. - 0120 af48ffc9 48c1e902 48ffc14c 8b5424f0 .H..H...H..L.T$. - 0130 c4e1fb93 d0c4e1fb 93c1480f afd1480f ..........H...H. - 0140 afc148c1 e1024939 ca0f8e0a ffffff48 ..H...I9.......H - 0150 c1e60249 8d048149 c1e00248 8d149390 ...I...I...H.... - 0160 c5fa100a 48ffc1c4 e279a908 4c01c2c5 ....H....y..L... - 0170 fa110848 01f04939 ca7fe5e9 d9feffff ...H..I9........ - 0180 4889f9c4 e27d18c8 62f27d48 18d04883 H....}..b.}H..H. - 0190 e1c00f84 92000000 48ffc948 c1e90648 ........H..H...H - 01a0 89cf48c1 e7084c89 ca4889de 498dbc39 ..H...L..H..I..9 - 01b0 00010000 0f1f4000 62f17c48 101e4881 ......@.b.|H..H. - 01c0 c2000100 0062f26d 48a85afc 4881c600 .....b.mH.Z.H... - 01d0 01000062 f17c4811 5afc62f1 7c48105e ...b.|H.Z.b.|H.^ - 01e0 fd62f26d 48a85afd 62f17c48 115afd62 .b.mH.Z.b.|H.Z.b - 01f0 f17c4810 5efe62f2 6d48a85a fe62f17c .|H.^.b.mH.Z.b.| - 0200 48115afe 62f17c48 105eff62 f26d48a8 H.Z.b.|H.^.b.mH. - 0210 5aff62f1 7c48115a ff4839d7 759a48ff Z.b.|H.Z.H9.u.H. - 0220 c148c1e1 064839c8 7e56498d 14896690 .H...H9.~VI...f. - 0230 c5fc1014 8b4883ea 80c4e275 a85280c5 .....H.....u.R.. - 0240 fc115280 c5fc1054 8b20c4e2 75a852a0 ..R....T. ..u.R. - 0250 c5fc1152 a0c5fc10 548b40c4 e275a852 ...R....T.@..u.R - 0260 c0c5fc11 52c0c5fc 10548b60 4883c120 ....R....T.`H.. - 0270 c4e275a8 52e0c5fc 1152e048 39c87fb0 ..u.R....R.H9... - 0280 4939c27e 14c5f877 e9b3fdff ff0f1f00 I9.~...w........ - 0290 31c031d2 e9b6feff ffc5f877 e9b8fdff 1.1........w.... - 02a0 ff . + 0000 31c0c4e2 7d180166 0f1f8400 00000000 1...}..f........ + 0010 c57c1024 82c57c10 6c8220c5 7c107482 .|.$..|.l. .|.t. + 0020 40c57c10 7c8260c4 627db824 86c4627d @.|.|.`.b}.$..b} + 0030 b86c8620 c4627db8 748640c4 627db87c .l. .b}.t.@.b}.| + 0040 8660c57c 112482c5 7c116c82 20c57c11 .`.|.$..|.l. .|. + 0050 748240c5 7c117c82 604883c0 204883ef t.@.|.|.`H.. H.. + 0060 2075adc5 f877c5f8 77c3660f 1f440000 u...w..w.f..D.. + 0070 41574156 41554154 55534883 ec08488b AWAVAUATUSH...H. + 0080 742440c5 fa114424 044885ff 7e454989 t$@...D$.H..~EI. + 0090 fa4889cd 4983f801 754e4883 fe017548 .H..I...uNH...uH + 00a0 4989f849 83e0e00f 85430100 00c5fa10 I..I.....C...... + 00b0 4c24040f 1f440000 c4a17a10 448500c4 L$...D....z.D... + 00c0 8271a904 81c4817a 11048149 ffc04d39 .q.....z...I..M9 + 00d0 c27fe548 83c4085b 5d415c41 5d415e31 ...H...[]A\A]A^1 + 00e0 c0415fc3 0f1f4000 4c89d1c5 fa104424 .A_...@.L.....D$ + 00f0 044883e1 fc0f841d 0100004a 8d048500 .H.........J.... + 0100 0000004f 8d24004c 8d1c364d 89c64989 ...O.$.L..6M..I. + 0110 f5c4e1fb 92c0488d 04b50000 0000c4e1 ......H......... + 0120 fb92c84f 8d3c0449 8d1c3349 c1e60448 ...O.<.I..3I...H + 0130 89ea49c1 e5044c89 c831ff0f 1f440000 ..I...L..1...D.. + 0140 c5fa1022 c4a17a10 1c82c4e2 79a920c4 ..."..z.....y. . + 0150 a17a1014 a2c4a17a 100cba48 83c7044c .z.....z...H...L + 0160 01f2c5fa 1120c4e2 79a91cb0 c5fa111c ..... ..y....... + 0170 b0c4a279 a91498c4 a17a1114 98c4e279 ...y.....z.....y + 0180 a90c98c5 fa110c98 4c01e848 39f97fb0 ........L..H9... + 0190 48ffc948 c1e90248 ffc1c4e1 fb93d0c4 H..H...H........ + 01a0 e1fb93c1 480fafd1 480fafc1 48c1e102 ....H...H...H... + 01b0 4939ca0f 8e1affff ff48c1e6 02498d04 I9.......H...I.. + 01c0 8149c1e0 02488d54 9500660f 1f440000 .I...H.T..f..D.. + 01d0 c5fa100a 48ffc1c4 e279a908 4c01c2c5 ....H....y..L... + 01e0 fa110848 01f04939 ca7fe5e9 e3feffff ...H..I9........ + 01f0 488d4c24 044c89ca 4889ee4c 89c7e8fd H.L$.L..H..L.... + 0200 fdffff4d 39c20f8f a1feffff e9c2feff ...M9........... + 0210 ff0f1f80 00000000 31c031d2 eb9b ........1.1... /usr/lib64/libopenblas_openmp.a/saxpy_k_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/saxpy_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/saxpy_k_SKYLAKEX.o (objdump) @@ -4,4 +4,4 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0020 010001c0 04000000 19080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/saxpy_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/saxpy_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/saxpy_k_SKYLAKEX.o (objdump) @@ -3,7 +3,10 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 2c000000 1c000000 ........,....... - 0020 00000000 a1020000 00410e10 8602430d .........A....C. - 0030 064d8f03 8e048d05 8c068307 02580a0c .M...........X.. - 0040 0708470b 00000000 ..G..... + 0010 1b0c0708 90010000 10000000 1c000000 ................ + 0020 00000000 6a000000 00000000 48000000 ....j.......H... + 0030 30000000 00000000 ae010000 00420e10 0............B.. + 0040 8f02420e 188e0342 0e208d04 420e288c ..B....B. ..B.(. + 0050 05410e30 8606410e 38830744 0e400259 .A.0..A.8..D.@.Y + 0060 0a0e3841 0e30410e 28420e20 420e1842 ..8A.0A.(B. B..B + 0070 0e10440e 08450b00 ..D..E.. /usr/lib64/libopenblas_openmp.a/sbdot_k_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sbdot_k_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sbdot_k_COOPERLAKE.o (disasm) @@ -4,181 +4,7 @@ Disassembly of section .text: -sbdot_accl_kernel: - mov %rsi,%r10 - mov %rdx,%rsi - cmp $something,%rdi - jle - mov %rdi,%rcx - vxorps %xmm3,%xmm3,%xmm3 - mov %rdi,%r8 - and $something,%rcx - mov %rdx,%rax - and $something,%r8 - mov %r10,%rdx - lea (%rsi,%rcx,2),%r9 - vmovaps %zmm3,%zmm1 - vmovaps %zmm3,%zmm2 - vmovaps %zmm3,%zmm0 - xchg %ax,%ax - vmovdqu16 (%rdx),%zmm6 - vmovdqu16 (%rax),%zmm7 - vmovdqu16 offset(%rdx),%zmm4 - vmovdqu16 offset(%rax),%zmm5 - vdpbf16ps %zmm7,%zmm6,%zmm0 - vdpbf16ps %zmm5,%zmm4,%zmm2 - vmovdqu16 offset(%rdx),%zmm6 - vmovdqu16 offset(%rax),%zmm7 - vmovdqu16 offset(%rdx),%zmm4 - vmovdqu16 offset(%rax),%zmm5 - add $something,%rax - vdpbf16ps %zmm7,%zmm6,%zmm1 - vdpbf16ps %zmm5,%zmm4,%zmm3 - add $something,%rdx - cmp %rax,%r9 - jne - cmp %rcx,%r8 - jle - nopl (%rax) - vmovdqu16 (%r10,%rcx,2),%zmm6 - vmovdqu16 (%rsi,%rcx,2),%zmm7 - add $something,%rcx - vdpbf16ps %zmm7,%zmm6,%zmm0 - cmp %rcx,%r8 - jg - and $something,%edi - jne - vaddps %zmm2,%zmm0,%zmm0 - vaddps %zmm3,%zmm1,%zmm1 - vaddps %zmm0,%zmm1,%zmm1 - vextractf32x8 $something,%zmm1,%ymm0 - vaddps %ymm1,%ymm0,%ymm1 - vextractf128 $something,%ymm1,%xmm0 - vaddps %xmm1,%xmm0,%xmm0 - vzeroupper - vshufps $something,%xmm0,%xmm0,%xmm1 - vaddps %xmm1,%xmm0,%xmm0 - vshufps $something,%xmm0,%xmm0,%xmm1 - vaddps %xmm0,%xmm1,%xmm0 - ret - nopl offset(%rax,%rax,1) - cmp $something,%rdi - jle - mov %edi,%edx - vxorps %xmm1,%xmm1,%xmm1 - and $something,%edx - xor %eax,%eax - vmovaps %ymm1,%ymm0 - vmovdqu16 (%r10,%rax,2),%ymm3 - vmovdqu16 (%rsi,%rax,2),%ymm2 - vdpbf16ps %ymm2,%ymm3,%ymm0 - vmovdqu16 offset(%r10,%rax,2),%ymm3 - vmovdqu16 offset(%rsi,%rax,2),%ymm2 - add $something,%rax - vdpbf16ps %ymm2,%ymm3,%ymm1 - cmp %eax,%edx - jg - vaddps %ymm1,%ymm0,%ymm1 - test $something,%dil - je - movslq %edx,%rdx - vmovdqu (%r10,%rdx,2),%ymm0 - vmovdqu (%rsi,%rdx,2),%ymm2 - vdpbf16ps %ymm2,%ymm0,%ymm1 - vextractf128 $something,%ymm1,%xmm0 - vaddps %xmm1,%xmm0,%xmm0 - test $something,%dil - je - mov %edi,%eax - and $something,%eax - cltq - vmovdqu (%r10,%rax,2),%xmm1 - vmovdqu (%rsi,%rax,2),%xmm2 - vdpbf16ps %xmm2,%xmm1,%xmm0 - mov %rdi,%rcx - and $something,%ecx - je - mov $something,%eax - sub %ecx,%eax - mov %eax,%edx - and $something,%edi - mov $something,%eax - sarx %edx,%eax,%eax - kmovd %eax,%k1 - movslq %edi,%rax - add %rax,%rax - vmovdqu16 (%rsi,%rax,1),%xmm2{%k1}{z} - vmovdqu16 (%r10,%rax,1),%xmm1{%k1}{z} - vdpbf16ps %xmm2,%xmm1,%xmm0 - vzeroupper - jmp - nopl offset(%rax) - cmp $something,%rdi - jle - vmovdqu16 (%r10),%ymm3 - vmovdqu16 (%rdx),%ymm2 - vxorps %xmm1,%xmm1,%xmm1 - vdpbf16ps %ymm2,%ymm3,%ymm1 - vextractf128 $something,%ymm1,%xmm0 - vaddps %xmm1,%xmm0,%xmm0 - vxorps %xmm1,%xmm1,%xmm1 - vaddps %xmm1,%xmm0,%xmm0 - test $something,%dil - je - vmovdqu16 offset(%r10),%xmm3 - vmovdqu16 offset(%rdx),%xmm2 - vdpbf16ps %xmm2,%xmm3,%xmm0 - jmp - nopl (%rax) - mov $something,%eax - sub %edi,%eax - mov %eax,%edx - add %r8,%r8 - mov $something,%eax - shrx %edx,%eax,%eax - kmovd %eax,%k1 - vmovdqu16 (%rsi,%r8,1),%zmm5{%k1}{z} - vmovdqu16 (%r10,%r8,1),%zmm4{%k1}{z} - vdpbf16ps %zmm5,%zmm4,%zmm1 - jmp - nopl offset(%rax,%rax,1) - vzeroupper - jmp - nopl offset(%rax,%rax,1) - cmp $something,%rdi - jle - vmovdqu16 (%r10),%xmm3 - vmovdqu16 (%rdx),%xmm2 - vxorps %xmm0,%xmm0,%xmm0 - vdpbf16ps %xmm2,%xmm3,%xmm0 - and $something,%edi - je - mov $something,%eax - sub %edi,%eax - mov %eax,%edx - mov $something,%eax - sarx %edx,%eax,%eax - kmovd %eax,%k1 - vmovdqu16 offset(%rsi),%xmm2{%k1}{z} - vmovdqu16 offset(%r10),%xmm1{%k1}{z} - vdpbf16ps %xmm2,%xmm1,%xmm0 - jmp - nopl (%rax) - and $something,%edi - mov $something,%eax - sub %edi,%eax - mov %eax,%edx - mov $something,%eax - sarx %edx,%eax,%eax - kmovd %eax,%k1 - vmovdqu16 (%rsi),%xmm2{%k1}{z} - vmovdqu16 (%r10),%xmm1{%k1}{z} - vxorps %xmm0,%xmm0,%xmm0 - vdpbf16ps %xmm2,%xmm1,%xmm0 - jmp - nopl (%rax) - -sbdot_compute.part.0: +sbdot_compute: push %r15 mov %r8,%r15 push %r14 @@ -193,11 +19,11 @@ sub $something,%rsp mov %rsi,offset(%rsp) mov %rdx,(%rsp) - call + call mov %r12,%rdi mov %rax,%r13 - call - mov offset(%rip),%rbx # + call + mov offset(%rip),%rbx # mov %rax,%r12 mov (%rsp),%rdx mov (%rbx),%rax /usr/lib64/libopenblas_openmp.a/sbdot_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sbdot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sbdot_k_COOPERLAKE.o (objdump) @@ -2,101 +2,45 @@ /usr/lib64/libopenblas_openmp.a/sbdot_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 4989f248 89d64883 ff7f0f8e 00010000 I..H..H......... - 0010 4889f9c5 e057db49 89f84883 e1804889 H....W.I..H...H. - 0020 d04983e0 e04c89d2 4c8d0c4e 62f17c48 .I...L..L..Nb.|H - 0030 28cb62f1 7c4828d3 62f17c48 28c36690 (.b.|H(.b.|H(.f. - 0040 62f1ff48 6f3262f1 ff486f38 62f1ff48 b..Ho2b..Ho8b..H - 0050 6f620162 f1ff486f 680162f2 4e4852c7 ob.b..Hoh.b.NHR. - 0060 62f25e48 52d562f1 ff486f72 0262f1ff b.^HR.b..Hor.b.. - 0070 486f7802 62f1ff48 6f620362 f1ff486f Hox.b..Hob.b..Ho - 0080 68034805 00010000 62f24e48 52cf62f2 h.H.....b.NHR.b. - 0090 5e4852dd 4881c200 01000049 39c175a0 ^HR.H......I9.u. - 00a0 4939c87e 200f1f00 62d1ff48 6f344a62 I9.~ ...b..Ho4Jb - 00b0 f1ff486f 3c4e4883 c12062f2 4e4852c7 ..Ho nopl (%rax) -tobf16_accl_kernel: - mov %rsi,%rcx - mov %rdx,%rsi - mov %rcx,%rdx - and $something,%edx - mov $something,%eax - sub %rdx,%rax - shr $something,%rax - mov %eax,%edx - and $something,%eax - and $something,%edx - cmp %rdi,%rax - jle - mov %edi,%edx - movslq %edi,%rax - test %edx,%edx - je - mov $something,%r9d - sub %edx,%r9d - mov $something,%r8d - sarx %r9d,%r8d,%r11d - kmovd %r11d,%k1 - vmovupd (%rcx),%zmm0{%k1}{z} - vcvtpd2ps %zmm0,%ymm0 - vcvtneps2bf16 %ymm0,%xmm0 - vmovdqu16 %xmm0,(%rsi){%k1} - cmp %rax,%rdi - je - sub %rax,%rdi - movslq %edx,%rdx - mov %edi,%r8d - mov %edi,%r9d - mov %edi,%r11d - lea (%rcx,%rdx,8),%rcx - lea (%rsi,%rdx,2),%rsi - and $something,%r8d - and $something,%r9d - and $something,%r11d - jle - lea -offset(%r11),%r10d - shr $something,%r10d - shl $something,%r10 - mov %rcx,%rax - mov %rsi,%rdx - lea offset(%rcx,%r10,1),%r10 - nopl offset(%rax,%rax,1) - vcvtpd2ps offset(%rax),%ymm0 - vcvtpd2ps offset(%rax),%ymm2 - vcvtpd2ps (%rax),%ymm1 - vinsertf64x4 $something,%ymm0,%zmm1,%zmm1 - vcvtpd2ps offset(%rax),%ymm0 - vinsertf64x4 $something,%ymm2,%zmm0,%zmm0 - vcvtne2ps2bf16 %zmm1,%zmm0,%zmm0 - add $something,%rax - add $something,%rdx - vmovdqu64 %zmm0,-offset(%rdx) - vcvtpd2ps -offset(%rax),%ymm0 - vcvtpd2ps -offset(%rax),%ymm2 - vcvtpd2ps -offset(%rax),%ymm1 - vinsertf64x4 $something,%ymm0,%zmm1,%zmm1 - vcvtpd2ps -offset(%rax),%ymm0 - vinsertf64x4 $something,%ymm2,%zmm0,%zmm0 - vcvtne2ps2bf16 %zmm1,%zmm0,%zmm0 - vmovdqu64 %zmm0,-offset(%rdx) - vcvtpd2ps -offset(%rax),%ymm0 - vcvtpd2ps -offset(%rax),%ymm2 - vcvtpd2ps -offset(%rax),%ymm1 - vinsertf64x4 $something,%ymm0,%zmm1,%zmm1 - vcvtpd2ps -offset(%rax),%ymm0 - vinsertf64x4 $something,%ymm2,%zmm0,%zmm0 - vcvtne2ps2bf16 %zmm1,%zmm0,%zmm0 - vmovdqu64 %zmm0,-offset(%rdx) - vcvtpd2ps -offset(%rax),%ymm0 - vcvtpd2ps -offset(%rax),%ymm1 - vcvtpd2ps -offset(%rax),%ymm2 - vinsertf64x4 $something,%ymm0,%zmm1,%zmm1 - vcvtpd2ps -offset(%rax),%ymm0 - vinsertf64x4 $something,%ymm2,%zmm0,%zmm0 - vcvtne2ps2bf16 %zmm1,%zmm0,%zmm0 - vmovdqu64 %zmm0,-offset(%rdx) - cmp %rax,%r10 - jne - movslq %r11d,%rax - cmp %r11d,%r9d - jle - nopl offset(%rax) - vcvtpd2ps offset(%rcx,%rax,8),%ymm0 - vcvtpd2ps (%rcx,%rax,8),%ymm1 - vcvtpd2ps offset(%rcx,%rax,8),%ymm2 - vinsertf64x4 $something,%ymm0,%zmm1,%zmm1 - vcvtpd2ps offset(%rcx,%rax,8),%ymm0 - vinsertf64x4 $something,%ymm2,%zmm0,%zmm0 - vcvtne2ps2bf16 %zmm1,%zmm0,%zmm0 - vmovdqu64 %zmm0,(%rsi,%rax,2) - add $something,%rax - cmp %eax,%r9d - jg - movslq %r9d,%rax - cmp %r9d,%r8d - jle - nopl offset(%rax,%rax,1) - vcvtpd2ps (%rcx,%rax,8),%ymm0 - vcvtneps2bf16 %ymm0,%xmm0 - vmovdqu %xmm0,(%rsi,%rax,2) - add $something,%rax - cmp %eax,%r8d - jg - and $something,%edi - je - mov $something,%eax - sub %edi,%eax - mov %eax,%edx - movslq %r8d,%r8 - mov $something,%eax - sarx %edx,%eax,%eax - kmovd %eax,%k1 - vmovapd (%rcx,%r8,8),%zmm0{%k1}{z} - vcvtpd2ps %zmm0,%ymm0 - vcvtneps2bf16 %ymm0,%xmm0 - vmovdqu16 %xmm0,(%rsi,%r8,2){%k1} - vzeroupper - ret - nopl offset(%rax,%rax,1) - tobf16_thread_func: - sub $something,%rsp mov %rcx,%rsi mov %r8,%rdx + mov %r9,%rcx cmp $something,%r8 jne cmpq $something,offset(%rsp) jne - mov %r9,%rdx - call + mov $something,%r8d + call xor %eax,%eax - add $something,%rsp ret - nopw offset(%rax,%rax,1) + nopl (%rax) mov offset(%rsp),%r8 - mov %r9,%rcx call xor %eax,%eax - add $something,%rsp ret data16 cs nopw offset(%rax,%rax,1) - nop sbdtobf16_k_COOPERLAKE: sub $something,%rsp @@ -258,9 +130,11 @@ mov offset(%rsp),%rax sub %fs:0x28,%rax jne - mov %rcx,%rdx + mov $something,%r8d + mov $something,%edx add $something,%rsp - jmp + jmp + nopl offset(%rax,%rax,1) mov offset(%rsp),%rax sub %fs:0x28,%rax jne /usr/lib64/libopenblas_openmp.a/sbdtobf16_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sbdtobf16_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sbdtobf16_k_COOPERLAKE.o (objdump) @@ -14,60 +14,22 @@ 0090 4489c0c1 e81083e0 01418d84 00ff7f00 D........A...... 00a0 00c1e810 668901e9 79ffffff 0f1f4000 ....f...y.....@. 00b0 b80080ff ff668901 e968ffff ff0f1f00 .....f...h...... - 00c0 4889f148 89d64889 ca83e23f b8400000 H..H..H....?.@.. - 00d0 004829d0 48c1e803 89c283e0 0783e207 .H).H........... - 00e0 4839f87e 0589fa48 63c785d2 743141b9 H9.~...Hc...t1A. - 00f0 08000000 4129d141 b8ff0000 00c44232 ....A).A......B2 - 0100 f7d8c4c1 7b92cb62 f1fdc910 0162f1fd ....{..b.....b.. - 0110 485ac062 f27e2872 c062f1ff 097f0648 HZ.b.~(r.b.....H - 0120 39c70f84 ec010000 4829c748 63d24189 9.......H).Hc.A. - 0130 f84189f9 4189fb48 8d0cd148 8d345641 .A..A..H...H.4VA - 0140 83e0f841 83e1e041 83e3800f 8e100100 ...A...A........ - 0150 00458d53 ff41c1ea 0749c1e2 0a4889c8 .E.S.A...I...H.. - 0160 4889f24e 8d941100 0400000f 1f440000 H..N.........D.. - 0170 62f1fd48 5a400162 f1fd485a 500362f1 b..HZ@.b..HZP.b. - 0180 fd485a08 62f3f548 1ac80162 f1fd485a .HZ.b..H...b..HZ - 0190 400262f3 fd481ac2 0162f27f 4872c148 @.b..H...b..Hr.H - 01a0 05000400 004881c2 00010000 62f1fe48 .....H......b..H - 01b0 7f42fc62 f1fd485a 40f562f1 fd485a50 .B.b..HZ@.b..HZP - 01c0 f762f1fd 485a48f4 62f3f548 1ac80162 .b..HZH.b..H...b - 01d0 f1fd485a 40f662f3 fd481ac2 0162f27f ..HZ@.b..H...b.. - 01e0 4872c162 f1fe487f 42fd62f1 fd485a40 Hr.b..H.B.b..HZ@ - 01f0 f962f1fd 485a50fb 62f1fd48 5a48f862 .b..HZP.b..HZH.b - 0200 f3f5481a c80162f1 fd485a40 fa62f3fd ..H...b..HZ@.b.. - 0210 481ac201 62f27f48 72c162f1 fe487f42 H...b..Hr.b..H.B - 0220 fe62f1fd 485a40fd 62f1fd48 5a48fc62 .b..HZ@.b..HZH.b - 0230 f1fd485a 50ff62f3 f5481ac8 0162f1fd ..HZP.b..H...b.. - 0240 485a40fe 62f3fd48 1ac20162 f27f4872 HZ@.b..H...b..Hr - 0250 c162f1fe 487f42ff 4939c20f 850fffff .b..H.B.I9...... - 0260 ff4963c3 4539d97e 4a0f1f80 00000000 .Ic.E9.~J....... - 0270 62f1fd48 5a44c101 62f1fd48 5a0cc162 b..HZD..b..HZ..b - 0280 f1fd485a 54c10362 f3f5481a c80162f1 ..HZT..b..H...b. - 0290 fd485a44 c10262f3 fd481ac2 0162f27f .HZD..b..H...b.. - 02a0 4872c162 f1fe487f 04464883 c0204139 Hr.b..H..FH.. A9 - 02b0 c17fbd49 63c14539 c87e200f 1f440000 ...Ic.E9.~ ..D.. - 02c0 62f1fd48 5a04c162 f27e2872 c0c5fa7f b..HZ..b.~(r.... - 02d0 04464883 c0084139 c07fe583 e7077434 .FH...A9......t4 - 02e0 b8080000 0029f889 c24d63c0 b8ff0000 .....)...Mc..... - 02f0 00c4e26a f7c0c5fb 92c862b1 fdc92804 ...j......b...(. - 0300 c162f1fd 485ac062 f27e2872 c062b1ff .b..HZ.b.~(r.b.. - 0310 097f0446 c5f877c3 0f1f8400 00000000 ...F..w......... - 0320 4883ec08 4889ce4c 89c24983 f8017520 H...H..L..I...u - 0330 48837c24 10017518 4c89cae8 80fdffff H.|$..u.L....... - 0340 31c04883 c408c366 0f1f8400 00000000 1.H....f........ - 0350 4c8b4424 104c89c9 e8a3fcff ff31c048 L.D$.L.......1.H - 0360 83c408c3 66662e0f 1f840000 00000090 ....ff.......... - 0370 4883ec28 64488b04 25280000 00488944 H..(dH..%(...H.D - 0380 241831c0 4885ff7e 674885d2 0f94c04d $.1.H..~gH.....M - 0390 85c0410f 94c14408 c8756d48 81ffa086 ..A...D..umH.... - 03a0 01007e64 4881ff7f 96980041 b9040000 ..~dH......A.... - 03b0 00b81000 0000410f 4ec14883 ec085048 ......A.N.H...PH - 03c0 8d055aff ffff4989 f1504889 febf0900 ..Z...I..PH..... - 03d0 00006a00 488d4424 30504150 5131c952 ..j.H.D$0PAPQ1.R - 03e0 31d24c8d 442448e8 00000000 4883c440 1.L.D$H.....H..@ - 03f0 488b4424 1864482b 04252800 00007549 H.D$.dH+.%(...uI - 0400 4883c428 c30f1f00 4883fa01 75224983 H..(....H...u"I. - 0410 f801751c 488b4424 1864482b 04252800 ..u.H.D$.dH+.%(. - 0420 00007525 4889ca48 83c428e9 90fcffff ..u%H..H..(..... - 0430 488b4424 1864482b 04252800 00007509 H.D$.dH+.%(...u. - 0440 4883c428 e9b7fbff ffe80000 0000 H..(.......... + 00c0 4889ce4c 89c24c89 c94983f8 01751948 H..L..L..I...u.H + 00d0 837c2408 01751141 b8010000 00e81eff .|$..u.A........ + 00e0 ffff31c0 c30f1f00 4c8b4424 08e80eff ..1.....L.D$.... + 00f0 ffff31c0 c366662e 0f1f8400 00000000 ..1..ff......... + 0100 4883ec28 64488b04 25280000 00488944 H..(dH..%(...H.D + 0110 241831c0 4885ff7e 674885d2 0f94c04d $.1.H..~gH.....M + 0120 85c0410f 94c14408 c8756d48 81ffa086 ..A...D..umH.... + 0130 01007e64 4881ff7f 96980041 b9040000 ..~dH......A.... + 0140 00b81000 0000410f 4ec14883 ec085048 ......A.N.H...PH + 0150 8d056aff ffff4989 f1504889 febf0900 ..j...I..PH..... + 0160 00006a00 488d4424 30504150 5131c952 ..j.H.D$0PAPQ1.R + 0170 31d24c8d 442448e8 00000000 4883c440 1.L.D$H.....H..@ + 0180 488b4424 1864482b 04252800 00007559 H.D$.dH+.%(...uY + 0190 4883c428 c30f1f00 4883fa01 75324983 H..(....H...u2I. + 01a0 f801752c 488b4424 1864482b 04252800 ..u,H.D$.dH+.%(. + 01b0 00007535 41b80100 0000ba01 00000048 ..u5A..........H + 01c0 83c428e9 38feffff 0f1f8400 00000000 ..(.8........... + 01d0 488b4424 1864482b 04252800 00007509 H.D$.dH+.%(...u. + 01e0 4883c428 e917feff ffe80000 0000 H..(.......... /usr/lib64/libopenblas_openmp.a/sbdtobf16_k_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/sbdtobf16_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sbdtobf16_k_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/sbdtobf16_k_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/sbdtobf16_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sbdtobf16_k_COOPERLAKE.o (objdump) @@ -5,11 +5,9 @@ 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 10000000 1c000000 ................ 0020 00000000 bd000000 00000000 10000000 ................ - 0030 30000000 00000000 58020000 00000000 0.......X....... - 0040 1c000000 44000000 00000000 44000000 ....D.......D... - 0050 00440e10 620a0e08 4a0b530e 08000000 .D..b...J.S..... - 0060 44000000 64000000 00000000 de000000 D...d........... - 0070 00440e30 024a0e38 410e404b 0e484a0e .D.0.J.8A.@K.HJ. - 0080 50460e58 420e6041 0e68430e 70500e30 PF.XB.`A.hC.pP.0 - 0090 540a0e08 440b630a 0e08450b 540a0e08 T...D.c...E.T... - 00a0 450b0000 00000000 E....... + 0030 30000000 00000000 35000000 00000000 0.......5....... + 0040 44000000 44000000 00000000 ee000000 D...D........... + 0050 00440e30 024a0e38 410e404b 0e484a0e .D.0.J.8A.@K.HJ. + 0060 50460e58 420e6041 0e68430e 70500e30 PF.XB.`A.hC.pP.0 + 0070 540a0e08 440b6b0a 0e084d0b 540a0e08 T...D.k...M.T... + 0080 450b0000 00000000 E....... /usr/lib64/libopenblas_openmp.a/sbgemv_n_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sbgemv_n_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sbgemv_n_COOPERLAKE.o (disasm) @@ -5,864 +5,203 @@ Disassembly of section .text: sbgemv_n_COOPERLAKE: - push %rbp - mov %rsp,%rbp push %r15 push %r14 push %r13 push %r12 + push %rbp push %rbx - and $something,%rsp sub $something,%rsp + mov %r8,offset(%rsp) mov %r9,offset(%rsp) + vmovss %xmm0,offset(%rsp) + vmovss %xmm1,offset(%rsp) test %rdi,%rdi jle - mov %rsi,%r12 + mov %rsi,%r15 test %rsi,%rsi jle movq $something,offset(%rsp) - mov %rdi,%r13 - mov %rdx,%r14 - mov %rcx,%r15 - mov %r8,%rbx + mov %rdi,%rbp + mov %rdx,%rbx + mov %rcx,%r14 cmp $something,%r9 jne - cmpq $something,offset(%rbp) + cmpq $something,offset(%rsp) jne - vucomiss offset(%rip),%xmm1 # movq $something,offset(%rsp) - mov offset(%rbp),%rcx - jp - jne - mov %r13,%r8 - mov %r13,%rsi - and $something,%r8 - and $something,%rsi - vucomiss offset(%rip),%xmm0 # - jp - jne - test %rsi,%rsi - je - mov $something,%eax - vmovdqa32 offset(%rip),%zmm5 # - vmovdqa32 offset(%rip),%zmm4 # - kmovd %eax,%k2 - mov %rcx,%rdi - mov $something,%eax - mov %r14,%r11 - lea (%r15,%r15,1),%r9 - xor %r10d,%r10d - kmovd %eax,%k1 - nopl offset(%rax,%rax,1) - vxorps %xmm8,%xmm8,%xmm8 - mov %r11,%rax - vmovaps %zmm8,%zmm2 - vmovaps %zmm8,%zmm9 - vmovaps %zmm8,%zmm3 - vmovaps %zmm8,%zmm10 - vmovaps %zmm8,%zmm6 - vmovaps %zmm8,%zmm11 - vmovaps %zmm8,%zmm7 - xor %edx,%edx - nopl offset(%rax) - vmovdqu64 (%rax),%zmm1 - vpbroadcastw (%rbx,%rdx,2),%zmm0 - vmovdqu16 %zmm1,%zmm19{%k2}{z} - vmovdqu16 %zmm1,%zmm18{%k1}{z} - vmovdqu64 offset(%rax),%zmm1 - inc %rdx - vmovdqu16 %zmm1,%zmm17{%k2}{z} - vmovdqu16 %zmm1,%zmm16{%k1}{z} - vmovdqu64 offset(%rax),%zmm1 - vdpbf16ps %zmm0,%zmm19,%zmm7 - vmovdqu16 %zmm1,%zmm15{%k2}{z} - vmovdqu16 %zmm1,%zmm14{%k1}{z} - vmovdqu64 offset(%rax),%zmm1 - vdpbf16ps %zmm0,%zmm18,%zmm11 - vmovdqu16 %zmm1,%zmm13{%k2}{z} - vmovdqu16 %zmm1,%zmm12{%k1}{z} - vdpbf16ps %zmm0,%zmm17,%zmm6 - vdpbf16ps %zmm0,%zmm16,%zmm10 - vdpbf16ps %zmm0,%zmm15,%zmm3 - vdpbf16ps %zmm0,%zmm14,%zmm9 - vdpbf16ps %zmm0,%zmm13,%zmm2 - vdpbf16ps %zmm0,%zmm12,%zmm8 - add %r9,%rax - cmp %rdx,%r12 - jg - vmovaps %zmm7,%zmm12 - vpermt2ps %zmm11,%zmm5,%zmm12 - vpermt2ps %zmm11,%zmm4,%zmm7 - vmovaps %zmm3,%zmm1 - vmovaps %zmm6,%zmm11 - vmovaps %zmm2,%zmm0 - vpermt2ps %zmm10,%zmm5,%zmm11 - vpermt2ps %zmm10,%zmm4,%zmm6 - vpermt2ps %zmm9,%zmm5,%zmm1 - vpermt2ps %zmm9,%zmm4,%zmm3 - vpermt2ps %zmm8,%zmm5,%zmm0 - vpermt2ps %zmm8,%zmm4,%zmm2 - sub $something,%r10 - vmovups %zmm12,(%rdi) - vmovups %zmm7,offset(%rdi) - vmovups %zmm11,offset(%rdi) - vmovups %zmm6,offset(%rdi) - vmovups %zmm1,offset(%rdi) - vmovups %zmm3,offset(%rdi) - vmovups %zmm0,offset(%rdi) - vmovups %zmm2,offset(%rdi) - add $something,%r11 - add $something,%rdi - cmp %rsi,%r10 - jl - cmp %rsi,%r8 - jle - mov $something,%eax - vmovdqa32 offset(%rip),%zmm5 # - vmovdqa32 offset(%rip),%zmm4 # - kmovd %eax,%k2 - lea (%r14,%rsi,2),%r9 + vxorps %xmm6,%xmm6,%xmm6 + mov offset(%rsp),%r12 + vmovss %xmm6,offset(%rsp) + mov %rbp,%r13 + imul %r15,%r13 + lea offset(%r13,%r13,1),%rdi + call + lea offset(,%r13,4),%rdi + mov %rax,offset(%rsp) + call + lea offset(,%r15,4),%rdi + mov %rax,offset(%rsp) + call + mov %rax,%r13 + lea offset(%rbp,%rbp,1),%rsi + test %rbp,%rbp mov $something,%eax - lea (%r15,%r15,1),%rdi - kmovd %eax,%k1 + cmovg %rsi,%rax + lea (%r14,%r14,1),%rcx + mov offset(%rsp),%rdi + xor %r14d,%r14d + mov %r12,offset(%rsp) + mov %r13,offset(%rsp) + mov %rbp,offset(%rsp) + mov %rbx,%r13 + mov %r14,%rbp + mov %rcx,%r12 + mov %rsi,%rbx + mov %rax,%r14 nopw offset(%rax,%rax,1) - vxorps %xmm3,%xmm3,%xmm3 - mov %r9,%rdx - vmovaps %zmm3,%zmm2 + mov %r13,%rsi + mov %r14,%rdx + call + mov %rax,%rdi + inc %rbp + add %rbx,%rdi + add %r12,%r13 + cmp %rbp,%r15 + jg + mov offset(%rip),%rbx # + mov offset(%rsp),%r13 + mov offset(%rsp),%rbp + mov (%rbx),%rax + mov offset(%rsp),%rsi + mov $something,%r8d + mov %r13,%rcx + mov $something,%edx + mov %r15,%rdi + mov offset(%rsp),%r12 + call *offset(%rax) + mov %rbp,%rdi + imul %r15,%rdi + mov (%rbx),%rax + mov offset(%rsp),%rbx + mov offset(%rsp),%rsi + mov %rbx,%rcx + mov $something,%r8d + mov $something,%edx + call *offset(%rax) + vmovss offset(%rsp),%xmm1 + mov %rbx,%rdi + lea offset(,%rbp,4),%rcx + xor %esi,%esi /usr/lib64/libopenblas_openmp.a/sbgemv_n_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sbgemv_n_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sbgemv_n_COOPERLAKE.o (objdump) @@ -2,278 +2,56 @@ /usr/lib64/libopenblas_openmp.a/sbgemv_n_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 554889e5 41574156 41554154 534883e4 UH..AWAVAUATSH.. - 0010 c04883ec 404c894c 24304885 ff0f8e18 .H..@L.L$0H..... - 0020 04000049 89f44885 f60f8e0c 04000048 ...I..H........H - 0030 c7442428 00000000 4989fd49 89d64989 .D$(....I..I..I. - 0040 cf4c89c3 4983f901 0f855208 00004883 .L..I.....R...H. - 0050 7d18010f 85f70300 00c5f82e 0d000000 }............... - 0060 0048c744 24200000 0000488b 4d100f8a .H.D$ ....H.M... - 0070 58040000 0f855204 00004d89 e84c89ee X.....R...M..L.. - 0080 4983e0e0 4883e680 c5f82e05 00000000 I...H........... - 0090 0f8a8a0c 00000f85 840c0000 4885f60f ............H... - 00a0 849e0100 00b85555 555562f1 7d486f2d ......UUUUb.}Ho- - 00b0 00000000 62f17d48 6f250000 0000c5fb ....b.}Ho%...... - 00c0 92d04889 cfb8aaaa aaaa4d89 f34f8d0c ..H.......M..O.. - 00d0 3f4531d2 c5fb92c8 0f1f8400 00000000 ?E1............. - 00e0 c4413857 c04c89d8 62d17c48 28d06251 .A8W.L..b.|H(.bQ - 00f0 7c4828c8 62d17c48 28d86251 7c4828d0 |H(.b.|H(.bQ|H(. - 0100 62d17c48 28f06251 7c4828d8 62d17c48 b.|H(.bQ|H(.b.|H - 0110 28f831d2 0f1f4000 62f1fe48 6f0862f2 (.1...@.b..Ho.b. - 0120 7d487904 5362e1ff ca6fd962 e1ffc96f }Hy.Sb...o.b...o - 0130 d162f1fe 486f4801 48ffc262 e1ffca6f .b..HoH.H..b...o - 0140 c962e1ff c96fc162 f1fe486f 480262f2 .b...o.b..HoH.b. - 0150 664052f8 6271ffca 6ff96271 ffc96ff1 f@R.bq..o.bq..o. - 0160 62f1fe48 6f480362 726e4052 d86271ff b..HoH.brn@R.bq. - 0170 ca6fe962 71ffc96f e162f276 4052f062 .o.bq..o.b.v@R.b - 0180 727e4052 d062f206 4852d862 720e4852 r~@R.b..HR.br.HR - 0190 c862f216 4852d062 721e4852 c04c01c8 .b..HR.br.HR.L.. - 01a0 4939d40f 8f6fffff ff62717c 4828e762 I9...o...bq|H(.b - 01b0 5255487f e362d25d 487ffb62 f17c4828 RUH..b.]H..b.|H( - 01c0 cb62717c 4828de62 f17c4828 c2625255 .bq|H(.b.|H(.bRU - 01d0 487fda62 d25d487f f262d255 487fc962 H..b.]H..b.UH..b - 01e0 d25d487f d962d255 487fc062 d25d487f .]H..b.UH..b.]H. - 01f0 d04983ea 8062717c 48112762 f17c4811 .I...bq|H.'b.|H. - 0200 7f016271 7c48115f 0262f17c 48117703 ..bq|H._.b.|H.w. - 0210 62f17c48 114f0462 f17c4811 5f0562f1 b.|H.O.b.|H._.b. - 0220 7c481147 0662f17c 48115707 4981c300 |H.G.b.|H.W.I... - 0230 01000048 81c70002 00004939 f20f8c9d ...H......I9.... - 0240 feffff49 39f00f8e a2000000 b8555555 ...I9........UUU - 0250 5562f17d 486f2d00 00000062 f17d486f Ub.}Ho-....b.}Ho - 0260 25000000 00c5fb92 d04d8d0c 76b8aaaa %........M..v... - 0270 aaaa4b8d 3c3fc5fb 92c8660f 1f440000 ..K..UUUU..W..t$>. - 0340 fb92df4d 01ffbfaa aaaaaa4b 8d144662 ...M.......K..Fb - 0350 f17c4828 d331c0c5 fb92d70f 1f440000 .|H(.1.......D.. - 0360 62f1ffc9 6f0a62f2 7d487904 4362f1ff b...o.b.}Hy.Cb.. - 0370 cb6fe962 f1ffca6f e148ffc0 62f25648 .o.b...o.H..b.VH - 0380 52d062f2 5e4852d8 4c01fa49 39c47fd0 R.b.^HR.L..I9... - 0390 62f17d48 6f050000 00004c89 ef4a8d04 b.}Ho.....L..J.. - 03a0 85000000 004c29c7 62f26d48 77c30fb7 .....L).b.mHw... - 03b0 f6488d14 014883ff 100f8e09 0d000062 .H...H.........b - 03c0 f17c4811 0262f17d 486f0500 000000c5 .|H..b.}Ho...... - 03d0 f892e662 f26d4877 c362f17c 4c114401 ...b.mHw.b.|L.D. - 03e0 010f1f80 00000000 48837d18 010f84cd ........H.}..... - 03f0 0c000048 8b451848 8b551048 8d348500 ...H.E.H.U.H.4.. - 0400 00000031 c00f1f00 c5fa1004 8148ffc0 ...1.........H.. - 0410 c5fa1102 4801f249 39c57fec 488b7c24 ....H..I9...H.|$ - 0420 20c5f877 e8000000 0048837c 24300174 ..w.....H.|$0.t - 0430 0a488b7c 2428e800 00000048 8d65d85b .H.|$(.....H.e.[ - 0440 415c415d 415e415f 31c05dc3 0f1f4000 A\A]A^A_1.]...@. - 0450 4a8d3cad 3f000000 c5fa114c 2418c5fa J.<.?......L$... - 0460 1144241c e8000000 00488944 24204889 .D$......H.D$ H. - 0470 c783e03f c5fa1044 241cc5fa 104c2418 ...?...D$....L$. - 0480 0f849e0c 0000b940 00000029 c14863c9 .......@...).Hc. - 0490 4801f9c5 f82e0d00 0000007a 060f84d7 H..........z.... - 04a0 fbffff48 8b451848 8b551048 8d348500 ...H.E.H.U.H.4.. - 04b0 00000031 c00f1f00 c5fa1012 4801f2c5 ...1........H... - 04c0 fa111481 48ffc049 39c57fec 4d89e84c ....H..I9...M..L - 04d0 89ef4983 e0e04883 e780c5f8 2e0d0000 ..I...H......... - 04e0 000062f2 7d4818c0 0f8a2a04 00000f85 ..b.}H....*..... - 04f0 24040000 4885ff0f 84d30100 00b85555 $...H.........UU - 0500 555562f1 7d486f2d 00000000 62f17d48 UUb.}Ho-....b.}H - 0510 6f250000 0000c5fb 92d04889 ceb8aaaa o%........H..... - 0520 aaaa4d89 f34f8d0c 3f4531d2 c5fb92c8 ..M..O..?E1..... - 0530 c4413057 c94c89d8 62d17c48 28d96251 .A0W.L..b.|H(.bQ - 0540 7c4828d1 62d17c48 28f16251 7c4828d9 |H(.b.|H(.bQ|H(. - 0550 62d17c48 28f96251 7c4828e1 62517c48 b.|H(.bQ|H(.bQ|H - 0560 28c131d2 0f1f4000 62f1fe48 6f1062f2 (.1...@.b..Ho.b. - 0570 7d48790c 5362e1ff ca6fe262 e1ffc96f }Hy.Sb...o.b...o - 0580 da62f1fe 486f5001 48ffc262 e1ffca6f .b..HoP.H..b...o - 0590 d262e1ff c96fca62 f1fe486f 50026272 .b...o.b..HoP.br - 05a0 5e4052c1 62e1ffca 6fc26271 ffc96ffa ^@R.b...o.bq..o. - 05b0 62f1fe48 6f500362 72664052 e16271ff b..HoP.brf@R.bq. - 05c0 ca6ff262 71ffc96f ea62f26e 4052f962 .o.bq..o.b.n@R.b - 05d0 72764052 d962f27e 4052f162 72064852 rv@R.b.~@R.br.HR - 05e0 d162f20e 4852d962 72164852 c94c01c8 .b..HR.br.HR.L.. - 05f0 4939d40f 8f6fffff ff62517c 4828e862 I9...o...bQ|H(.b - 0600 5255487f ec62525d 487fc462 f17c4828 RUH..bR]H..b.|H( - 0610 d662717c 4828e762 f17c4828 cb62d255 .bq|H(.b.|H(.b.U - 0620 487fc962 d25d487f d9625255 487fe362 H..b.]H..bRUH..b - 0630 d25d487f fb62d255 487fd262 d25d487f .]H..b.UH..b.]H. - 0640 f262517c 4828cd62 727d48a8 0e62727d .bQ|H(.br}H..br} - 0650 48a84601 62727d48 a8660262 f27d48a8 H.F.br}H.f.b.}H. - 0660 7e0362f2 7d48a856 0462f27d 48a87605 ~.b.}H.V.b.}H.v. - 0670 62f27d48 a84e0662 f27d48a8 5e074983 b.}H.N.b.}H.^.I. - 0680 ea806271 7c48110e 62717c48 11460162 ..bq|H..bq|H.F.b - 0690 717c4811 660262f1 7c48117e 0362f17c q|H.f.b.|H.~.b.| - 06a0 48115604 62f17c48 11760562 f17c4811 H.V.b.|H.v.b.|H. - 06b0 4e0662f1 7c48115e 074981c3 00010000 N.b.|H.^.I...... - 06c0 4881c600 02000049 39fa0f8c 60feffff H......I9...`... - 06d0 4939f80f 8eb80000 00b85555 555562f1 I9........UUUUb. - 06e0 7d486f2d 00000000 62f17d48 6f250000 }Ho-....b.}Ho%.. - 06f0 0000c5fb 92d04d8d 0c7eb8aa aaaaaa4b ......M..~.....K - 0700 8d343fc5 fb92c866 0f1f8400 00000000 .4?....f........ - 0710 c5c857f6 4c89ca62 f17c4828 de31c090 ..W.L..b.|H(.1.. - 0720 62f1fe48 6f1262f2 7d48790c 436271ff b..Ho.b.}Hy.Cbq. - 0730 ca6fc262 f1ffc96f fa48ffc0 62f23e48 .o.b...o.H..b.>H - 0740 52d962f2 464852f1 4801f249 39c47fd0 R.b.FHR.H..I9... - 0750 62f17c48 28cb62f2 55487fce 62f25d48 b.|H(.b.UH..b.]H - 0760 7fde62f2 7d48a80c b962f27d 48a85cb9 ..b.}H...b.}H.\. - 0770 014983c1 4062f17c 48110cb9 62f17c48 .I..@b.|H...b.|H - 0780 115cb901 4883c720 4c39c70f 8c7fffff .\..H.. L9...... - 0790 ff4d39c5 0f844efc ffff4489 ee83e61f .M9...N...D..... - 07a0 b8200000 0029f089 c2b8ffff ffffc4e2 . ...).......... - 07b0 6bf7c044 89ea83e2 0fc5fb92 c8b81000 k..D............ - 07c0 000029d0 89c6b8ff ff0000c4 e24bf7c0 ..)..........K.. - 07d0 66894424 3ebf5555 5555c5d8 57e48b74 f.D$>.UUUU..W..t - 07e0 243ec5fb 92df4d01 ffbfaaaa aaaa4b8d $>....M.......K. - 07f0 144662f1 7c4828dc 31c0c5fb 92d76690 .Fb.|H(.1.....f. - 0800 62f1ffc9 6f1262f2 7d48790c 4362f1ff b...o.b.}Hy.Cb.. - 0810 cb6ff262 f1ffca6f ea48ffc0 62f24e48 .o.b...o.H..b.NH - 0820 52d962f2 564852e1 4c01fa49 39c47fd0 R.b.VHR.L..I9... - 0830 0fb7fe62 f17d486f 0d000000 004c89ee ...b.}Ho.....L.. - 0840 4a8d1485 00000000 4c29c662 f2654877 J.......L).b.eHw - 0850 cc488d04 11c5fb92 cf4883fe 100f8e83 .H.......H...... - 0860 08000062 f27d48a8 0862f17c 48110848 ...b.}H..b.|H..H - 0870 8d441140 62f17d48 6f0d0000 000062f1 .D.@b.}Ho.....b. - 0880 7cc91010 62f26548 77cc62f2 6d4898c1 |...b.eHw.b.mH.. - 0890 62f17c49 1100e94d fbffff0f 1f440000 b.|I...M.....D.. - 08a0 488d7c36 3fc5fa11 4c241cc5 fa114424 H.|6?...L$....D$ - 08b0 20e80000 00004889 44242848 89c783e0 .....H.D$(H.... - 08c0 3fc5fa10 442420c5 fa104c24 1c0f8447 ?...D$ ...L$...G - 08d0 080000b9 40000000 29c14863 c94801f9 ....@...).Hc.H.. - 08e0 488b4424 30488d34 0031c00f 1f440000 H.D$0H.4.1...D.. - 08f0 0fb71348 01f36689 144148ff c04939c4 ...H..f..AH..I9. - 0900 7fee4883 7d180148 89cb0f84 49f7ffff ..H.}..H....I... - 0910 e93bfbff ff0f1f00 62727d48 18e94885 .;......br}H..H. - 0920 ff0f8403 020000b8 55555555 62f17d48 ........UUUUb.}H - 0930 6f2d0000 000062f1 7d486f25 00000000 o-....b.}Ho%.... - 0940 c5fb92d0 4889ceb8 aaaaaaaa 4d89f34f ....H.......M..O - 0950 8d0c3f45 31d2c5fb 92c8660f 1f440000 ..?E1.....f..D.. - 0960 c4413057 c94c89d8 62d17c48 28d96251 .A0W.L..b.|H(.bQ - 0970 7c4828d1 62d17c48 28f16251 7c4828d9 |H(.b.|H(.bQ|H(. - 0980 62d17c48 28f96251 7c4828e1 62517c48 b.|H(.bQ|H(.bQ|H - 0990 28c131d2 0f1f4000 62f1fe48 6f1062f2 (.1...@.b..Ho.b. - 09a0 7d48790c 5362e1ff ca6fea62 e1ffc96f }Hy.Sb...o.b...o - 09b0 e262f1fe 486f5001 48ffc262 e1ffca6f .b..HoP.H..b...o - 09c0 da62e1ff c96fd262 f1fe486f 50026272 .b...o.b..HoP.br - 09d0 564052c1 62e1ffca 6fca62e1 ffc96fc2 V@R.b...o.b...o. - 09e0 62f1fe48 6f500362 725e4052 e16271ff b..HoP.br^@R.bq. - 09f0 ca6ffa62 71ffc96f f262f266 4052f962 .o.bq..o.b.f@R.b - 0a00 726e4052 d962f276 4052f162 727e4052 rn@R.b.v@R.br~@R - 0a10 d162f206 4852d962 720e4852 c94c01c8 .b..HR.br.HR.L.. - 0a20 4939d40f 8f6fffff ff62f17c 4828cb62 I9...o...b.|H(.b - 0a30 d255487f c962d25d 487fd962 71144859 .UH..b.]H..bq.HY - 0a40 0e62517c 4828f062 5255487f f462525d .bQ|H(.bRUH..bR] - 0a50 487fc462 717c4828 e762527d 48b8ce62 H..bq|H(.bR}H..b - 0a60 5255487f e362d25d 487ffb62 f17c4828 RUH..b.]H..b.|H( - 0a70 d662d255 487fd262 717c4811 0e627114 .b.UH..bq|H..bq. - 0a80 48594e01 62d25d48 7ff24983 ea804881 HYN.b.]H..I...H. - 0a90 c6000200 004981c3 00010000 62723548 .....I......br5H - 0aa0 98c06271 7c481146 f9627114 485946fa ..bq|H.F.bq.HYF. - 0ab0 62527d48 b8c46271 7c481146 fa627114 bR}H..bq|H.F.bq. - 0ac0 485946fb 62f23d48 98f862f1 7c48117e HYF.b.=H..b.|H.~ - 0ad0 fb62f114 48597efc 62f24548 98d062f1 .b..HY~.b.EH..b. - 0ae0 7c481156 fc62f114 485956fd 62f26d48 |H.V.b..HYV.b.mH - 0af0 98f062f1 14485956 fe62f17c 481176fd ..b..HYV.b.|H.v. - 0b00 62f26d48 98c862f1 7c48114e fe62f114 b.mH..b.|H.N.b.. - 0b10 48594eff 62f27548 98d862f1 7c48115e HYN.b.uH..b.|H.^ - 0b20 ff4939fa 0f8c36fe ffff4939 f80f8eca .I9...6...I9.... - 0b30 000000b8 55555555 62f17d48 6f2d0000 ....UUUUb.}Ho-.. - 0b40 000062f1 7d486f25 00000000 c5fb92d0 ..b.}Ho%........ - 0b50 4d8d0c7e b8aaaaaa aa4b8d34 3fc5fb92 M..~.....K.4?... - 0b60 c80f1f80 00000000 c5c857f6 4c89ca62 ..........W.L..b - 0b70 f17c4828 de31c066 0f1f8400 00000000 .|H(.1.f........ - 0b80 62f1fe48 6f1262f2 7d48790c 436271ff b..Ho.b.}Hy.Cbq. - 0b90 ca6fc262 f1ffc96f fa48ffc0 62f23e48 .o.b...o.H..b.>H - 0ba0 52d962f2 464852f1 4801f249 39c47fd0 R.b.FHR.H..I9... - 0bb0 62f11448 5914b962 f17c4828 cb62f255 b..HY..b.|H(.b.U - 0bc0 487fce62 f25d487f de4983c1 4062f26d H..b.]H..I..@b.m - 0bd0 4898c862 f17c4811 0cb962f1 1448594c H..b.|H...b..HYL - 0be0 b90162f2 754898d8 62f17c48 115cb901 ..b.uH..b.|H.\.. - 0bf0 4883c720 4c39c70f 8c6bffff ff4d39c5 H.. L9...k...M9. - 0c00 0f84e2f7 ffff4489 ee83e61f b8200000 ......D...... .. - 0c10 0029f089 c2b8ffff ffffc4e2 6bf7c044 .)..........k..D /usr/lib64/libopenblas_openmp.a/sbgemv_n_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/sbgemv_n_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sbgemv_n_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/sbgemv_n_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/sbgemv_n_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sbgemv_n_COOPERLAKE.o (objdump) @@ -3,7 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 2c000000 1c000000 ........,....... - 0020 00000000 2e110000 00410e10 8602430d .........A....C. - 0030 06518f03 8e048d05 8c068307 0336040a .Q...........6.. - 0040 0c070845 0b000000 ...E.... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 4e030000 00420e10 8f02420e ....N....B....B. + 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 + 0040 8606410e 38830744 0ea00103 37020a0e ..A.8..D....7... + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0841 0b000000 D..A.... /usr/lib64/libopenblas_openmp.a/sbgemv_t_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sbgemv_t_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sbgemv_t_COOPERLAKE.o (disasm) @@ -4,13550 +4,140 @@ Disassembly of section .text: -sbgemv_kernel_32x1_alpha_one.constprop.0.isra.0: - mov %edx,%r8d - mov $something,%eax - mov %rcx,%rdx - mov %rdi,%rcx - kmovd %eax,%k2 - vbroadcastss %xmm0,%zmm3 - vpbroadcastw %r8d,%zmm4{%k2}{z} - and $something,%rcx - jle - vmovdqa64 offset(%rip),%zmm7 # - vmovdqa64 offset(%rip),%zmm6 # - xor %eax,%eax - vxorps %xmm5,%xmm5,%xmm5 - xchg %ax,%ax - vmovdqu64 (%rsi,%rax,2),%zmm0 - vmovaps %zmm5,%zmm2 - vpermw %zmm0,%zmm7,%zmm1 - vdpbf16ps %zmm4,%zmm1,%zmm2 - vpermw %zmm0,%zmm6,%zmm0 - vmovaps %zmm5,%zmm1 - vdpbf16ps %zmm4,%zmm0,%zmm1 - vfmadd213ps (%rdx,%rax,4),%zmm3,%zmm2 - vfmadd213ps offset(%rdx,%rax,4),%zmm3,%zmm1 - vmovups %zmm2,(%rdx,%rax,4) - vmovups %zmm1,offset(%rdx,%rax,4) - add $something,%rax - cmp %rax,%rcx - jg - sub %rcx,%rdi - lea (%rsi,%rcx,2),%r9 - shl $something,%rcx - lea (%rdx,%rcx,1),%r8 - cmp $something,%rdi - jle - mov $something,%esi - sub %edi,%esi - mov $something,%eax - shrx %esi,%eax,%eax - vmovdqa64 offset(%rip),%zmm5 # - kmovd %eax,%k3 - vmovdqa64 offset(%rip),%zmm1 # - vmovdqu16 (%r9),%zmm0{%k3}{z} - mov $something,%eax - vpermw %zmm0,%zmm5,%zmm5 - vpermw %zmm0,%zmm1,%zmm1 - vxorps %xmm0,%xmm0,%xmm0 - vmovaps %zmm0,%zmm2 - vdpbf16ps %zmm4,%zmm5,%zmm2 - vdpbf16ps %zmm4,%zmm1,%zmm0 - sarx %esi,%eax,%eax - kmovd %eax,%k1 - lea offset(%rdx,%rcx,1),%rax - vfmadd213ps (%r8),%zmm3,%zmm2 - vmovups %zmm2,(%r8) - vmovups (%rax),%zmm1{%k1}{z} - vfmadd132ps %zmm3,%zmm1,%zmm0 - vmovups %zmm0,(%rax){%k1} - vzeroupper - ret - nopl offset(%rax) - cmp $something,%rdi - jle - mov $something,%esi - sub %edi,%esi - vmovdqa32 offset(%rip),%zmm1 # - mov $something,%eax - sarx %esi,%eax,%eax - vmovapd offset(%rip),%ymm5 # - kmovw %eax,%k4 - vmovdqu16 (%r9),%ymm0{%k4}{z} - vextracti32x8 $something,%zmm1,%ymm1 - vpermw %ymm0,%ymm5,%ymm5 - vpermw %ymm0,%ymm1,%ymm1 - vxorps %xmm0,%xmm0,%xmm0 - vmovaps %ymm0,%ymm2 - vdpbf16ps %ymm4,%ymm5,%ymm2 - vdpbf16ps %ymm4,%ymm1,%ymm0 - mov $something,%eax - sarx %esi,%eax,%eax - kmovd %eax,%k1 - lea offset(%rdx,%rcx,1),%rax - vfmadd213ps (%r8),%ymm3,%ymm2 - vmovups %ymm2,(%r8) - vmovups (%rax),%ymm1{%k1}{z} - vfmadd132ps %ymm3,%ymm1,%ymm0 - vmovups %ymm0,(%rax){%k1} - vzeroupper - ret - nopl offset(%rax,%rax,1) - mov $something,%eax - sub %edi,%eax - mov $something,%esi - vmovdqa offset(%rip),%xmm0 # - sarx %eax,%esi,%esi - kmovb %esi,%k5 - vmovdqu16 (%r9),%xmm2{%k5}{z} - vxorps %xmm1,%xmm1,%xmm1 - vpermw %xmm2,%xmm0,%xmm0 - vmovaps %xmm1,%xmm5 - vdpbf16ps %xmm4,%xmm0,%xmm5 - cmp $something,%rdi - jle - vfmadd213ps (%r8),%xmm3,%xmm5 - mov $something,%esi - sarx %eax,%esi,%eax - kmovd %eax,%k1 - lea offset(%rdx,%rcx,1),%rax - vmovups %xmm5,(%r8) - vmovdqa offset(%rip),%xmm5 # - vmovups (%rax),%xmm0{%k1}{z} - vpermw %xmm2,%xmm5,%xmm2 - vdpbf16ps %xmm4,%xmm2,%xmm1 - vfmadd132ps %xmm1,%xmm0,%xmm3 - vmovups %xmm3,(%rax){%k1} - vzeroupper - ret - nopl offset(%rax,%rax,1) - mov $something,%eax - sub %edi,%eax - mov %eax,%edx - mov $something,%eax - sarx %edx,%eax,%eax - kmovd %eax,%k1 - vmovups (%r8),%xmm0{%k1}{z} - vfmadd132ps %xmm5,%xmm0,%xmm3 - vmovups %xmm3,(%r8){%k1} - vzeroupper - ret - data16 cs nopw offset(%rax,%rax,1) - nop - -sbgemv_kernel_32x2_alpha_one.constprop.0.isra.0: - mov $something,%eax - kmovb %eax,%k2 - vmovdqu16 (%rdx),%xmm5{%k2}{z} - mov %rdi,%rdx - vpbroadcastd %xmm5,%zmm5 - vbroadcastss %xmm0,%zmm0 - vmovdqa64 %zmm5,%zmm4 - xor %eax,%eax - vxorps %xmm3,%xmm3,%xmm3 - and $something,%rdx - jle - vmovdqu16 (%rsi,%rax,4),%zmm6 - vmovdqu16 offset(%rsi,%rax,4),%zmm7 - vmovaps %zmm3,%zmm2 - vmovaps %zmm3,%zmm1 - vdpbf16ps %zmm4,%zmm6,%zmm2 - vdpbf16ps %zmm4,%zmm7,%zmm1 - vfmadd213ps (%rcx,%rax,4),%zmm0,%zmm2 - vfmadd213ps offset(%rcx,%rax,4),%zmm0,%zmm1 - vmovups %zmm2,(%rcx,%rax,4) - vmovups %zmm1,offset(%rcx,%rax,4) - add $something,%rax - cmp %rax,%rdx - jg - mov %rdi,%rax - sub %rdx,%rax - cmp $something,%rax - jle - vmovdqu16 (%rsi,%rdx,4),%zmm6 - vxorps %xmm1,%xmm1,%xmm1 - vdpbf16ps %zmm5,%zmm6,%zmm1 - lea (%rcx,%rdx,4),%rax - add $something,%rdx - vfmadd213ps (%rax),%zmm0,%zmm1 - vmovups %zmm1,(%rax) - mov %rdi,%rax - sub %rdx,%rax - shl $something,%rdx - add %rdx,%rsi - add %rdx,%rcx - cmp $something,%rax - jle - and $something,%edi - mov $something,%eax - sub %edi,%eax - mov %eax,%edx - mov $something,%eax - sarx %edx,%eax,%eax - kmovd %eax,%k1 - vmovdqu32 (%rsi),%zmm2{%k1}{z} - vxorps %xmm1,%xmm1,%xmm1 - vdpbf16ps %zmm5,%zmm2,%zmm1 - vmovups (%rcx),%zmm2{%k1}{z} - vfmadd132ps %zmm1,%zmm2,%zmm0 - vmovups %zmm0,(%rcx){%k1} - vzeroupper - ret - nopl (%rax) - je - and $something,%edi - mov $something,%eax /usr/lib64/libopenblas_openmp.a/sbgemv_t_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sbgemv_t_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sbgemv_t_COOPERLAKE.o (objdump) @@ -2,4384 +2,56 @@ /usr/lib64/libopenblas_openmp.a/sbgemv_t_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 00000 4189d0b8 55555555 4889ca48 89f9c5fb A...UUUUH..H.... - 00010 92d062f2 7d4818d8 62d27dca 7be04883 ..b.}H..b.}.{.H. - 00020 e1e07e6e 62f1fd48 6f3d0000 000062f1 ..~nb..Ho=....b. - 00030 fd486f35 00000000 31c0c5d0 57ed6690 .Ho5....1...W.f. - 00040 62f1fe48 6f044662 f17c4828 d562f2c5 b..Ho.Fb.|H(.b.. - 00050 488dc862 f2764852 d462f2cd 488dc062 H..b.vHR.b..H..b - 00060 f17c4828 cd62f27e 4852cc62 f26548a8 .|H(.b.~HR.b.eH. - 00070 148262f2 6548a84c 820162f1 7c481114 ..b.eH.L..b.|H.. - 00080 8262f17c 48114c82 014883c0 204839c1 .b.|H.L..H.. H9. - 00090 7fae4829 cf4c8d0c 4e48c1e1 024c8d04 ..H).L..NH...L.. - 000a0 0a4883ff 100f8e8d 000000be 20000000 .H.......... ... - 000b0 29feb8ff ffffffc4 e24bf7c0 62f1fd48 )........K..b..H - 000c0 6f2d0000 0000c5fb 92d862f1 fd486f0d o-........b..Ho. - 000d0 00000000 62d1ffcb 6f01b8ff ff000062 ....b...o......b - 000e0 f2d5488d e862f2f5 488dc8c5 f857c062 ..H..b..H....W.b - 000f0 f17c4828 d062f256 4852d462 f2764852 .|H(.b.VHR.b.vHR - 00100 c4c4e24a f7c0c5fb 92c8488d 440a4062 ...J......H.D.@b - 00110 d26548a8 1062d17c 48111062 f17cc910 .eH..b.|H..b.|.. - 00120 0862f275 4898c362 f17c4911 00c5f877 .b.uH..b.|I....w - 00130 c30f1f80 00000000 4883ff08 0f8e8e00 ........H....... - 00140 0000be10 00000029 fe62f17d 486f0d00 .......).b.}Ho.. - 00150 000000b8 ffff0000 c4e24af7 c0c5fd28 ..........J....( - 00160 2d000000 00c5f892 e062d1ff ac6f0162 -........b...o.b - 00170 f37d483b c90162f2 d5288de8 62f2f528 .}H;..b..(..b..( - 00180 8dc8c5f8 57c0c5fc 28d062f2 562852d4 ....W...(.b.V(R. - 00190 62f27628 52c4b8ff 000000c4 e24af7c0 b.v(R........J.. - 001a0 c5fb92c8 488d440a 20c4c265 a810c4c1 ....H.D. ..e.... - 001b0 7c111062 f17ca910 08c4e275 98c362f1 |..b.|.....u..b. - 001c0 7c291100 c5f877c3 0f1f8400 00000000 |)....w......... - 001d0 b8080000 0029f8be ff000000 c5f96f05 .....)........o. - 001e0 00000000 c4e27af7 f6c5f992 ee62d1ff ......z......b.. - 001f0 8d6f11c5 f057c962 f2fd088d c2c5f828 .o...W.b.......( - 00200 e962f27e 0852ec48 83ff047e 4bc4c261 .b.~.R.H...~K..a - 00210 a828be0f 000000c4 e27af7c6 c5fb92c8 .(.......z...... - 00220 488d440a 10c4c178 1128c5f9 6f2d0000 H.D....x.(..o-.. - 00230 000062f1 7c891000 62f2d508 8dd262f2 ..b.|...b.....b. - 00240 6e0852cc c4e27998 d962f17c 091118c5 n.R...y..b.|.... - 00250 f877c30f 1f440000 b8040000 0029f889 .w...D.......).. - 00260 c2b80f00 0000c4e2 6af7c0c5 fb92c862 ........j......b - 00270 d17c8910 00c4e279 98dd62d1 7c091118 .|.....y..b.|... - 00280 c5f877c3 66662e0f 1f840000 00000090 ..w.ff.......... - 00290 b8030000 00c5f992 d062f1ff 8a6f2a48 .........b...o*H - 002a0 89fa62f2 7d4858ed 62f27d48 18c062f1 ..b.}HX.b.}H..b. - 002b0 fd486fe5 31c0c5e0 57db4883 e2e07e4e .Ho.1...W.H...~N - 002c0 62f1ff48 6f348662 f1ff486f 7c860162 b..Ho4.b..Ho|..b - 002d0 f17c4828 d362f17c 4828cb62 f24e4852 .|H(.b.|H(.b.NHR - 002e0 d462f246 4852cc62 f27d48a8 148162f2 .b.FHR.b.}H...b. - 002f0 7d48a84c 810162f1 7c481114 8162f17c }H.L..b.|H...b.| - 00300 48114c81 014883c0 204839c2 7fb24889 H.L..H.. H9...H. - 00310 f84829d0 4883f80f 7e2b62f1 ff486f34 .H).H...~+b..Ho4 - 00320 96c5f057 c962f24e 4852cd48 8d049148 ...W.b.NHR.H...H - 00330 83c21062 f27d48a8 0862f17c 48110848 ...b.}H..b.|H..H - 00340 89f84829 d048c1e2 024801d6 4801d148 ..H).H...H..H..H - 00350 83f8087e 4383e70f b8100000 0029f889 ...~C........).. - 00360 c2b8ffff 0000c4e2 6af7c0c5 fb92c862 ........j......b - 00370 f17ec96f 16c5f057 c962f26e 4852cd62 .~.o...W.b.nHR.b - 00380 f17cc910 1162f26d 4898c162 f17c4911 .|...b.mH..b.|I. - 00390 01c5f877 c30f1f00 744683e7 07b80800 ...w....tF...... - 003a0 000029f8 89c2b8ff 000000c4 e26af7c0 ..)..........j.. - 003b0 c5fb92c8 62f17ea9 6f16c5f0 57c962f2 ....b.~.o...W.b. - 003c0 6e2852cd 62f17ca9 1011c4e2 6d98c162 n(R.b.|.....m..b - 003d0 f17c2911 01c5f877 c30f1f80 00000000 .|)....w........ - 003e0 c5fe6f16 c5f057c9 62f26e28 52cdc4e2 ..o...W.b.n(R... - 003f0 75a801c5 fc1101c5 f877c30f 1f440000 u........w...D.. - 00400 b8070000 0062f27d 4818d8c5 f992d062 .....b.}H......b - 00410 f1ff8a6f 024989f8 62727d48 58f0c5f9 ...o.I..br}HX... - 00420 70c00149 89c96272 7d4858e8 4983e0e0 p..I..br}HX.I... - 00430 0f8ef600 0000b800 000080c5 fb92e048 ...............H - 00440 89c8498d 48ff48c1 e90562f1 fd486f35 ..I.H.H...b..Ho5 - 00450 00000000 488d0c49 c44131ef c948c1e1 ....H..I.A1..H.. - 00460 066271fd 486f2500 00000062 71fd486f .bq.Ho%....bq.Ho - 00470 1d000000 006271fd 486f1500 00000062 .....bq.Ho.....b - 00480 52cd4c66 c962d1fd 486fed62 d1fd486f R.Lf.b..Ho.b..Ho - 00490 f64889f2 488d8c0e c0000000 c5d857e4 .H..H.........W. - 004a0 62f1fe48 6f420162 f1fe486f 0a62f1fe b..HoB.b..Ho.b.. - 004b0 486f5202 6271fd48 6fc162f1 fd486ff8 HoR.bq.Ho.b..Ho. - 004c0 62f2ad48 7dc86272 9d487dc0 62f2a548 b..H}.br.H}.b..H - 004d0 7dfa62f2 b5487dc2 62f17c48 28d462f2 }.b..H}.b.|H(.b. - 004e0 3e4852d6 4881c2c0 00000048 83e88062 >HR.H......H...b - 004f0 f2764852 d562f17c 4828cc62 f2464852 .vHR.b.|H(.b.FHR - 00500 ce62f265 48a850fe 62f27e48 52cd62f1 .b.eH.P.b.~HR.b. - 00510 7c481150 fe62f265 48a848ff 62f17c48 |H.P.b.eH.H.b.|H - 00520 1148ff48 39d10f85 74ffffff 4c39c70f .H.H9...t...L9.. - 00530 840a0100 00c5fd28 0d000000 0062f2fd .......(.....b.. - 00540 48190500 000000b8 0080ffff c575fdc0 H............u.. - 00550 62f2fd48 19050000 0000c5f8 92d84889 b..H..........H. - 00560 f8c575fd c8c5e9ef d2c5bdfd c04c29c0 ..u..........L). - 00570 62f1ff2b 6fc2c5fd 6ff14883 f80f0f8f b..+o...o.H..... - 00580 c4000000 4b8d1440 4801d289 c1488d3c ....K..@H....H.< - 00590 164883f8 0a0f8e4d 01000048 83e80bc5 .H.....M...H.... - 005a0 fe6f0f8d 3c850000 000029f8 83c00fbf .o..<.....)..... - 005b0 ffff0000 c4e27af7 ffc5fe6f 641620c5 ......z....od. . - 005c0 f892ef62 f1ffad6f 7c160262 f2f52875 ...b...o|..b..(u - 005d0 f4c5fd6f e9c57d7f c2c5f057 c962f2dd ...o..}....W.b.. - 005e0 2875d762 f2b5287d ec62f2fd 287de7c5 (u.b..(}.b..(}.. - 005f0 fc28c162 d24e2852 c662d26e 2852ce62 .(.b.N(R.b.n(R.b - 00600 d2562852 c562d25e 2852cdb8 10000000 .V(R.b.^(R...... - 00610 29c889c2 b8ffff00 00c4e26a f7c0c5fb )..........j.... - 00620 92c84b8d 048162f3 fd481ac1 0162f17c ..K...b..H...b.| - 00630 c9100862 f2754898 d862f17c 491118c5 ...b.uH..b.|I... - 00640 f877c30f 1f440000 4b8d0440 4801c0c5 .w...D..K..@H... - 00650 fe6f2406 c5fe6f54 0620c5fe 6f6c0640 .o$...oT. ..ol.@ - 00660 c5fd6ffc 62f2dd28 75cac57d 6fd262f2 ..o.b..(u..}o.b. - 00670 b5287dfa c5fd6fe2 c5e857d2 6272bd28 .(}...o...W.br.( - 00680 7dd562f2 fd287de5 c5fc28ea 62d27628 }.b..(}...(.b.v( - 00690 52ee62d2 2e2852d6 4a8d1485 00000000 R.b..(R.J....... - 006a0 498d0c11 498d4411 204983c0 1062d246 I...I.D. I...b.F - 006b0 2852ed62 d25e2852 d5c5fc28 cdc4e265 (R.b.^(R...(...e - 006c0 a809c5fc 1109c4e2 65a810c5 fc11104c ........e......L - 006d0 39c70f84 67ffffff 4889f84c 29c0e9a1 9...g...H..L)... - 006e0 feffff0f 1f440000 4883f805 7e3a4883 .....D..H...~:H. - 006f0 e806c5fe 6f0f8d3c 85000000 0029f883 ....o..<.....).. - 00700 c00ebfff ff0000c4 e27af7ff c5c1efff .........z...... - 00710 c5f892f7 62f1ffae 6f641601 e9aafeff ....b...od...... - 00720 ff0f1f80 00000000 8d148500 00000029 ...............) - 00730 d08d5010 b8ffff00 00c4e26a f7c0c5f8 ..P........j.... - 00740 92f862f1 ffaf6f07 c5e9efd2 62f2fd28 ..b...o.....b..( - 00750 75f262f2 b5287dc2 c5fd6fc8 c5f857c0 u.b..(}...o...W. - 00760 62d24e28 52c662d2 762852c5 c5f057c9 b.N(R.b.v(R...W. - 00770 e996feff ff66662e 0f1f8400 00000000 .....ff......... - 00780 554889f8 4989ca48 89e54154 4989d448 UH..I..H..ATI..H - 00790 ba898888 88888888 8848f7ea 4889f848 .........H..H..H - 007a0 c1f83f4c 8d0c3a49 c1f90449 29c1b81f ..?L..:I...I)... - 007b0 00000049 6bc91ec5 f992e862 51ff8d6f ...Ik......bQ..o - 007c0 24244989 f962c17d 0870c401 c4417970 $$I..b.}.p...Ayp - 007d0 fc024989 f862617c 0828e049 89f34929 ..I..ba|.(.I..I) - 007e0 c962f27d 4818f062 c27d4858 cc62a27d .b.}H..b.}HX.b.} - 007f0 4858c062 527d4858 ff4885c9 0f8eca01 HX.bR}HX.H...... - 00800 000062f1 7d486f05 00000000 baffffff ..b.}Ho......... - 00810 3f62e27d 48792500 00000062 e27d4879 ?b.}Hy%....b.}Hy - 00820 1d000000 00c5fb92 caba00f0 ffff62e3 ..............b. - 00830 7d4843d0 39c5f892 da62f37d 4843c04f }HC.9....b.}HC.O - 00840 ba003f00 006271fd 486f3500 00000062 ..?..bq.Ho5....b - 00850 71fd486f 2d000000 006271fd 486f1d00 q.Ho-....bq.Ho.. - 00860 00000062 a15d40fd ea62a1fd 486ffa48 ...b.]@..b..Ho.H - 00870 89f762a1 6540fdd2 c5f892d2 62e1fd48 ..b.e@......b..H - 00880 6ff0baff 3f000062 31fd486f d162e15d o...?..b1.Ho.b.] - 00890 40fde062 31fd486f c862e165 40fdd862 @..b1.Ho.b.e@..b - 008a0 51fd486f c7498d72 4031c0c5 c057ffc5 Q.Ho.I.r@1...W.. - 008b0 f892e20f 1f440000 62f1ffc9 6f2762f1 .....D..b...o'b. - 008c0 ffc96f87 78000000 6261ffc9 6f973c00 ..o.x...ba..o.<. - 008d0 00006261 ffc96f8f b4000000 62f1ffc9 ..ba..o.....b... - 008e0 6faff000 000062f1 fd486fd4 62f1fd48 o.....b..Ho.b..H - 008f0 6fc86292 c5407dc9 62f2cd40 8ddd6292 o.b..@}.b..@..b. - 00900 8d487dd2 6262754a 64c362f1 7d4b6fd1 .H}.bbuJd.b.}Ko. - 00910 62f17c48 28cf62d2 3e4052ca 62f17c48 b.|H(.b.>@R.b.|H - 00920 28df62d2 6e4852da 6261fd48 6fdc6261 (.b.nHR.ba.Ho.ba - 00930 fd486fc0 62f2dd40 8dd56202 d5407dc1 .Ho.b..@..b..@}. - 00940 62029548 7dda6201 7d4b6fd8 62617d4a b..H}.b.}Ko.ba}J - 00950 6fc262f1 7c4828d1 62d22640 52d962d2 o.b.|H(.b.&@R.b. - 00960 3e4052d1 6292a548 7de26292 ed407dc1 >@R.b..H}.b..@}. - 00970 62f1fd48 6fcc62f2 e5408ded 62f17d4b b..Ho.b..@..b.}K - 00980 6fc862f1 7d4a6fc5 62d27e48 52d062d2 o.b.}Jo.b.~HR.b. - 00990 764852d8 62f17ccc 10064883 c01e4881 vHR.b.|...H...H. - 009a0 c72c0100 0062f24d 48b8c262 f24d48a8 .,...b.MH..b.MH. - 009b0 5eff62f1 7c4c1106 62f17c48 115eff48 ^.b.|L..b.|H.^.H - 009c0 83c67848 39c10f8f ecfeffff 4983f90b ..xH9.......I... - 009d0 0f8eff00 00004c89 c848baab aaaaaaaa ......L..H...... - 009e0 aaaa2a48 f7ea4c89 c848c1f8 3f48d1fa ..*H..L..H..?H.. - 009f0 4829c248 8d045248 c1e00248 8d148d00 H).H..RH...H.... - 00a00 00000049 29c1bfff ffff3f48 8d040a4c ...I).....?H...L - 00a10 89c66271 fd486f35 00000000 6271fd48 ..bq.Ho5....bq.H - 00a20 6f2d0000 00006271 fd486f1d 00000000 o-....bq.Ho..... - 00a30 c5fb92d7 4c29cebf ff0f0000 6231fd48 ....L)......b1.H - 00a40 6fc96231 fd486fc0 62d1fd48 6fff498d o.b1.Ho.b..Ho.I. - 00a50 04434c01 d2c5d057 edc5f892 cf0f1f00 .CL....W........ - 00a60 62f1ffca 6f0062f1 ffca6f90 3c000000 b...o.b...o.<... - 00a70 62f1fd48 6fe062f1 fd486fd8 62f1fd48 b..Ho.b..Ho.b..H - 00a80 6fc862f2 8d487de2 62f17c48 28c562d2 o.b..H}.b.|H(.b. - 00a90 5e4852c1 62f29548 7dda62f2 a5487dca ^HR.b..H}.b..H}. - 00aa0 4883c10c 4883c078 62d26648 52c062f2 H...H..xb.fHR.b. - 00ab0 764852c7 62f17cc9 100a62f2 754898c6 vHR.b.|...b.uH.. - 00ac0 62f17c49 11024883 c2304839 ce7f914d b.|I..H..0H9...M - 00ad0 89c14929 c94983f9 067f6549 39c87e53 ..I).I....eI9.~S - 00ae0 488d0489 ba1f0000 00498d04 43c5e857 H........I..C..W - 00af0 d2c5f992 ca0f1f00 62f1ff89 6f08c5f8 ........b...o... - 00b00 28c262d2 760852c4 4883c00a c5f8c6c8 (.b.v.R.H....... - 00b10 0ec5f858 c1c5f8c6 c801c5f8 58c162d2 ...X........X.b. - 00b20 1d00a904 8ac4c17a 11048a48 ffc14939 .......z...H..I9 - 00b30 c875c5c5 f8774c8b 65f8c9c3 0f1f4000 .u...wL.e.....@. - 00b40 b8100000 004429c8 89c2b8ff ff0000c4 .....D)......... - 00b50 e26af7c0 baffffff 3fc5fb92 c8c5fb92 .j......?....... - 00b60 f2488d04 8d000000 00ba0c00 00004801 .H............H. - 00b70 c14c29ca 4801c98d 749202ba ffffffff .L).H...t....... - 00b80 62d1ffce 6f040b62 f1fd486f 1d000000 b...o..b..Ho.... - 00b90 0062f1fd 486f1500 00000062 f1fd486f .b..Ho.....b..Ho - 00ba0 0d000000 00c4e24b f7d2c5fb 92fa62d1 .......K......b. - 00bb0 ffcf6fa4 0b3c0000 004c01d0 62f2fd48 ..o..<...L..b..H - 00bc0 75cc62f2 fd4875dc 62f2fd48 75d4c5f8 u.b..Hu.b..Hu... - 00bd0 57c062b2 664852c1 62b26e48 52c062d2 W.b.fHR.b.nHR.b. - 00be0 764852c7 62f17cc9 100862f2 754898f0 vHR.b.|...b.uH.. - 00bf0 62f17c49 1130c5f8 774c8b65 f8c9c390 b.|I.0..wL.e.... - 00c00 b83f0000 00c5f992 d84889f8 4989f062 .?.......H..I..b - 00c10 f1ff8b6f 32c5f828 e84889ce 4883e0f0 ...o2..(.H..H... /usr/lib64/libopenblas_openmp.a/sbgemv_t_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/sbgemv_t_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sbgemv_t_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/sbgemv_t_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/sbgemv_t_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sbgemv_t_COOPERLAKE.o (objdump) @@ -3,120 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 10000000 1c000000 ................ - 0020 00000000 84020000 00000000 10000000 ................ - 0030 30000000 00000000 6b010000 00000000 0.......k....... - 0040 10000000 44000000 00000000 75030000 ....D.......u... - 0050 00000000 28000000 58000000 00000000 ....(...X....... - 0060 7f040000 00410e10 8602490d 06428c03 .....A....I..B.. - 0070 03af030a 0c070845 0b02be0c 07080000 .......E........ - 0080 10000000 84000000 00000000 a5020000 ................ - 0090 00000000 10000000 98000000 00000000 ................ - 00a0 0b030000 00000000 10000000 ac000000 ................ - 00b0 00000000 8b020000 00000000 10000000 ................ - 00c0 c0000000 00000000 71020000 00000000 ........q....... - 00d0 10000000 d4000000 00000000 79020000 ............y... - 00e0 00000000 10000000 e8000000 00000000 ................ - 00f0 49030000 00000000 10000000 fc000000 I............... - 0100 00000000 39030000 00000000 10000000 ....9........... - 0110 10010000 00000000 c9040000 00000000 ................ - 0120 10000000 24010000 00000000 39040000 ....$.......9... - 0130 00000000 10000000 38010000 00000000 ........8....... - 0140 c9040000 00000000 10000000 4c010000 ............L... - 0150 00000000 b8030000 00000000 24000000 ............$... - 0160 60010000 00000000 0b030000 00410e10 `............A.. - 0170 86024b0d 06418303 034b020a 0c070848 ..K..A...K.....H - 0180 0b000000 2c000000 88010000 00000000 ....,........... - 0190 9e050000 00410e10 8602470d 06488f03 .....A....G..H.. - 01a0 8e048d05 8c064f83 07033d05 0a0c0708 ......O...=..... - 01b0 440b0000 28000000 b8010000 00000000 D...(........... - 01c0 e9030000 00410e10 86024a0d 06428f03 .....A....J..B.. - 01d0 4e8e048d 058c0683 0703cd03 0c070800 N............... - 01e0 30000000 e4010000 00000000 27040000 0...........'... - 01f0 00410e10 8602490d 065a8e03 8d048c05 .A....I..Z...... - 0200 830603fa 010a0c07 08420b03 06020c07 .........B...... - 0210 08000000 10000000 18020000 00000000 ................ - 0220 19020000 00000000 10000000 2c020000 ............,... - 0230 00000000 65030000 00000000 28000000 ....e.......(... - 0240 40020000 00000000 39040000 00410e10 @.......9....A.. - 0250 8602490d 06428c03 0378030a 0c070844 ..I..B...x.....D - 0260 0b02b00c 07080000 10000000 6c020000 ............l... - 0270 00000000 5d020000 00000000 10000000 ....]........... - 0280 80020000 00000000 c4020000 00000000 ................ - 0290 10000000 94020000 00000000 55020000 ............U... - 02a0 00000000 10000000 a8020000 00000000 ................ - 02b0 62020000 00000000 10000000 bc020000 b............... - 02c0 00000000 52020000 00000000 10000000 ....R........... - 02d0 d0020000 00000000 22030000 00000000 ........"....... - 02e0 10000000 e4020000 00000000 1a030000 ................ - 02f0 00000000 10000000 f8020000 00000000 ................ - 0300 89040000 00000000 10000000 0c030000 ................ - 0310 00000000 11040000 00000000 10000000 ................ - 0320 20030000 00000000 89040000 00000000 ............... - 0330 10000000 34030000 00000000 88030000 ....4........... - 0340 00000000 24000000 48030000 00000000 ....$...H....... - 0350 dc020000 00410e10 86024a0d 06418303 .....A....J..A.. - 0360 0326020a 0c070846 0b000000 2c000000 .&.....F....,... - 0370 70030000 00000000 8e050000 00410e10 p............A.. - 0380 8602430d 06488f03 8e048d05 8c064f83 ..C..H........O. - 0390 07033005 0a0c0708 450b0000 28000000 ..0.....E...(... - 03a0 a0030000 00000000 cf030000 00410e10 .............A.. - 03b0 86024a0d 06428f03 4a8e048d 058c0683 ..J..B..J....... - 03c0 0703b703 0c070800 30000000 cc030000 ........0....... - 03d0 00000000 07040000 00410e10 8602490d .........A....I. - 03e0 06518e03 8d048c05 830603e5 010a0c07 .Q.............. - 03f0 08480b03 fe010c07 08000000 30000000 .H..........0... - 0400 00040000 00000000 27040000 00410e10 ........'....A.. - 0410 8602490d 065a8e03 8d048c05 830603f9 ..I..Z.......... - 0420 010a0c07 08430b03 06020c07 08000000 .....C.......... - 0430 28000000 34040000 00000000 e8030000 (...4........... - 0440 00410e10 86024a0d 06428f03 4e8e048d .A....J..B..N... - 0450 058c0683 0703cc03 0c070800 2c000000 ............,... - 0460 60040000 00000000 8e050000 00410e10 `............A.. - 0470 8602470d 06488f03 8e048d05 8c064f83 ..G..H........O. - 0480 07033005 0a0c0708 410b0000 24000000 ..0.....A...$... - 0490 90040000 00000000 09030000 00410e10 .............A.. - 04a0 86024b0d 06418303 0349020a 0c07084a ..K..A...I.....J - 04b0 0b000000 10000000 b8040000 00000000 ................ - 04c0 ad030000 00000000 10000000 cc040000 ................ - 04d0 00000000 a6040000 00000000 10000000 ................ - 04e0 e0040000 00000000 27040000 00000000 ........'....... - 04f0 10000000 f4040000 00000000 a6040000 ................ - 0500 00000000 10000000 08050000 00000000 ................ - 0510 27030000 00000000 10000000 1c050000 '............... - 0520 00000000 37030000 00000000 10000000 ....7........... - 0530 30050000 00000000 67020000 00000000 0.......g....... - 0540 10000000 44050000 00000000 67020000 ....D.......g... - 0550 00000000 10000000 58050000 00000000 ........X....... - 0560 7a020000 00000000 10000000 6c050000 z...........l... - 0570 00000000 da020000 00000000 10000000 ................ - 0580 80050000 00000000 75020000 00000000 ........u....... - 0590 28000000 94050000 00000000 5f040000 (..........._... - 05a0 00410e10 8602490d 06428c03 0395030a .A....I..B...... - 05b0 0c070847 0b02b60c 07080000 10000000 ...G............ - 05c0 c0050000 00000000 5d030000 00000000 ........]....... - 05d0 10000000 d4050000 00000000 5a010000 ............Z... - 05e0 00000000 30000000 e8050000 00000000 ....0........... - 05f0 4f040000 00410e10 8602490d 065f8e03 O....A....I.._.. - 0600 8d048c05 8306030a 020a0c07 08450b03 .............E.. - 0610 16020c07 08000000 28000000 1c060000 ........(....... - 0620 00000000 f6030000 00410e10 86024a0d .........A....J. - 0630 06428f03 4e8e048d 058c0683 0703da03 .B..N........... - 0640 0c070800 2c000000 48060000 00000000 ....,...H....... - 0650 b6050000 00410e10 8602470d 06488f03 .....A....G..H.. - 0660 8e048d05 8c064f83 07035205 0a0c0708 ......O...R..... - 0670 470b0000 24000000 78060000 00000000 G...$...x....... - 0680 24030000 00410e10 86024b0d 06418303 $....A....K..A.. - 0690 0360020a 0c070843 0b000000 10000000 .`.....C........ - 06a0 a0060000 00000000 c4030000 00000000 ................ - 06b0 10000000 b4060000 00000000 dd040000 ................ - 06c0 00000000 10000000 c8060000 00000000 ................ - 06d0 4d040000 00000000 10000000 dc060000 M............... - 06e0 00000000 38330000 00000000 68000000 ....83......h... - 06f0 f0060000 00000000 0b020000 004b0e10 .............K.. - 0700 8f02420e 188e0342 0e208d04 420e288c ..B....B. ..B.(. - 0710 05440e30 8606410e 38830744 0e600241 .D.0..A.8..D.`.A - 0720 0a0e3841 0e30410e 28420e20 420e1842 ..8A.0A.(B. B..B - 0730 0e10440e 08490b03 88010e08 c3c6cccd ..D..I.......... - 0740 cecf430e 60830786 068c058d 048e038f ..C.`........... - 0750 02000000 00000000 ........ + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 4c030000 00420e10 8f02420e ....L....B....B. + 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 + 0040 8606410e 38830744 0ea00103 37020a0e ..A.8..D....7... + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0841 0b000000 D..A.... /usr/lib64/libopenblas_openmp.a/sbstobf16_k_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sbstobf16_k_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sbstobf16_k_COOPERLAKE.o (disasm) @@ -59,140 +59,24 @@ jmp nopl (%rax) -tobf16_accl_kernel: - mov %rdx,%r8 - mov %rsi,%rdx - and $something,%edx - mov $something,%eax - sub %rdx,%rax - shr $something,%rax - mov %eax,%edx - mov %rdi,%rcx - and $something,%eax - mov %rsi,%rdi - and $something,%edx - cmp %rcx,%rax - jle - mov %ecx,%edx - movslq %ecx,%rax - test %edx,%edx - je - mov $something,%esi - sub %edx,%esi - mov %esi,%r9d - mov $something,%esi - sarx %r9d,%esi,%esi - kmovd %esi,%k1 - vmovups (%rdi),%zmm0{%k1}{z} - vcvtneps2bf16 %zmm0,%ymm0 - vmovdqu16 %ymm0,(%r8){%k1} - cmp %rax,%rcx - je - mov %rcx,%rsi - sub %rax,%rsi - movslq %edx,%rdx - lea (%rdi,%rdx,4),%rcx - lea (%r8,%rdx,2),%r8 - mov %esi,%edx - and $something,%edx - mov $something,%eax - sub %edx,%eax - mov %esi,%edi - mov $something,%edx - mov %esi,%r11d - and $something,%edi - sarx %eax,%edx,%r10d - and $something,%r11d - jle - lea -offset(%r11),%r9d - shr $something,%r9d - shl $something,%r9 - mov %rcx,%rax - mov %r8,%rdx - lea offset(%rcx,%r9,1),%r9 - nopw offset(%rax,%rax,1) - vmovaps offset(%rax),%zmm2 - vmovaps (%rax),%zmm3 - add $something,%rax - vcvtne2ps2bf16 %zmm3,%zmm2,%zmm0 - add $something,%rdx - vmovdqu64 %zmm0,-offset(%rdx) - vmovaps -offset(%rax),%zmm4 - vmovaps -offset(%rax),%zmm5 - vcvtne2ps2bf16 %zmm5,%zmm4,%zmm0 - vmovdqu64 %zmm0,-offset(%rdx) - vmovaps -offset(%rax),%zmm6 - vmovaps -offset(%rax),%zmm7 - vcvtne2ps2bf16 %zmm7,%zmm6,%zmm0 - vmovdqu64 %zmm0,-offset(%rdx) - vmovaps -offset(%rax),%zmm1 - vmovaps -offset(%rax),%zmm2 - vcvtne2ps2bf16 %zmm2,%zmm1,%zmm0 - vmovdqu64 %zmm0,-offset(%rdx) - cmp %rax,%r9 - jne - movslq %r11d,%rax - cmp %r11d,%edi - jle - nopl (%rax) - vmovaps offset(%rcx,%rax,4),%zmm3 - vmovaps (%rcx,%rax,4),%zmm4 - vcvtne2ps2bf16 %zmm4,%zmm3,%zmm0 - vmovdqu64 %zmm0,(%r8,%rax,2) - add $something,%rax - cmp %eax,%edi - jg - test $something,%sil - je - movslq %edi,%rdi - vmovaps (%rcx,%rdi,4),%zmm1 - kmovw %r10d,%k2 - vmovaps offset(%rcx,%rdi,4),%zmm0{%k2}{z} - and $something,%esi - vcvtne2ps2bf16 %zmm1,%zmm0,%zmm0 - mov $something,%eax - sub %esi,%eax - mov %eax,%edx - mov $something,%eax - shrx %edx,%eax,%eax - kmovd %eax,%k3 - vmovdqu16 %zmm0,(%r8,%rdi,2){%k3} - vzeroupper - ret - nopl offset(%rax) - and $something,%esi - je - movslq %edi,%rdi - kmovw %r10d,%k4 - vmovaps (%rcx,%rdi,4),%zmm0{%k4}{z} - vcvtneps2bf16 %zmm0,%ymm0 - vmovdqu16 %ymm0,(%r8,%rdi,2){%k4} - vzeroupper - ret - nopl (%rax) - tobf16_thread_func: - sub $something,%rsp mov %rcx,%rsi mov %r8,%rdx + mov %r9,%rcx cmp $something,%r8 jne cmpq $something,offset(%rsp) jne - mov %r9,%rdx - call + mov $something,%r8d + call xor %eax,%eax - add $something,%rsp ret - nopw offset(%rax,%rax,1) + nopl (%rax) mov offset(%rsp),%r8 - mov %r9,%rcx call xor %eax,%eax - add $something,%rsp ret data16 cs nopw offset(%rax,%rax,1) - nop sbstobf16_k_COOPERLAKE: sub $something,%rsp @@ -244,9 +128,11 @@ mov offset(%rsp),%rax sub %fs:0x28,%rax jne - mov %rcx,%rdx + mov $something,%r8d + mov $something,%edx add $something,%rsp - jmp + jmp + nopl offset(%rax,%rax,1) mov offset(%rsp),%rax sub %fs:0x28,%rax jne /usr/lib64/libopenblas_openmp.a/sbstobf16_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sbstobf16_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sbstobf16_k_COOPERLAKE.o (objdump) @@ -13,52 +13,22 @@ 0080 89c0c1e8 1083e001 418d8400 ff7f0000 ........A....... 0090 c1e81066 8901eb8d 0f1f8400 00000000 ...f............ 00a0 b80080ff ff668901 e978ffff ff0f1f00 .....f...x...... - 00b0 4989d048 89f283e2 3fb84000 00004829 I..H....?.@...H) - 00c0 d048c1e8 0289c248 89f983e0 0f4889f7 .H.....H.....H.. - 00d0 83e20f48 39c87e05 89ca4863 c185d274 ...H9.~...Hc...t - 00e0 2abe1000 000029d6 4189f1be ffff0000 *.....).A....... - 00f0 c4e232f7 f6c5fb92 ce62f17c c9100762 ..2......b.|...b - 0100 f27e4872 c062d1ff 297f0048 39c10f84 .~Hr.b..)..H9... - 0110 4c010000 4889ce48 29c64863 d2488d0c L...H..H).Hc.H.. - 0120 974d8d04 5089f283 e20fb810 00000029 .M..P..........) - 0130 d089f7ba ffff0000 4189f383 e7e0c462 ........A......b - 0140 7af7d241 83e3800f 8ea00000 00458d4b z..A.........E.K - 0150 ff41c1e9 0749c1e1 094889c8 4c89c24e .A...I...H..L..N - 0160 8d8c0900 02000066 0f1f8400 00000000 .......f........ - 0170 62f17c48 28500162 f17c4828 18480500 b.|H(P.b.|H(.H.. - 0180 02000062 f26f4872 c34881c2 00010000 ...b.oHr.H...... - 0190 62f1fe48 7f42fc62 f17c4828 60fb62f1 b..H.B.b.|H(`.b. - 01a0 7c482868 fa62f25f 4872c562 f1fe487f |H(h.b._Hr.b..H. - 01b0 42fd62f1 7c482870 fd62f17c 482878fc B.b.|H(p.b.|H(x. - 01c0 62f24f48 72c762f1 fe487f42 fe62f17c b.OHr.b..H.B.b.| - 01d0 482848ff 62f17c48 2850fe62 f2774872 H(H.b.|H(P.b.wHr - 01e0 c262f1fe 487f42ff 4939c175 834963c3 .b..H.B.I9.u.Ic. - 01f0 4439df7e 270f1f00 62f17c48 285c8101 D9.~'...b.|H(\.. - 0200 62f17c48 28248162 f2674872 c462d1fe b.|H($.b.gHr.b.. - 0210 487f0440 4883c020 39c77fdc 40f6c610 H..@H.. 9...@... - 0220 74464863 ff62f17c 48280cb9 c4c17892 tFHc.b.|H(....x. - 0230 d262f17c ca2844b9 0183e61f 62f27f48 .b.|.(D.....b..H - 0240 72c1b820 00000029 f089c2b8 ffffffff r.. ...)........ - 0250 c4e26bf7 c0c5fb92 d862d1ff 4b7f0478 ..k......b..K..x - 0260 c5f877c3 0f1f4000 83e61f74 f34863ff ..w...@....t.Hc. - 0270 c4c17892 e262f17c cc2804b9 62f27e48 ..x..b.|.(..b.~H - 0280 72c062d1 ff2c7f04 78c5f877 c30f1f00 r.b..,..x..w.... - 0290 4883ec08 4889ce4c 89c24983 f8017520 H...H..L..I...u - 02a0 48837c24 10017518 4c89cae8 00feffff H.|$..u.L....... - 02b0 31c04883 c408c366 0f1f8400 00000000 1.H....f........ - 02c0 4c8b4424 104c89c9 e833fdff ff31c048 L.D$.L...3...1.H - 02d0 83c408c3 66662e0f 1f840000 00000090 ....ff.......... - 02e0 4883ec18 64488b04 25280000 00488944 H...dH..%(...H.D - 02f0 240831c0 4885ff7e 674885d2 0f94c04d $.1.H..~gH.....M - 0300 85c0410f 94c14408 c8756d48 81ffa086 ..A...D..umH.... - 0310 01007e64 4881ff7f 96980041 b9040000 ..~dH......A.... - 0320 00b81000 0000410f 4ec14883 ec085048 ......A.N.H...PH - 0330 8d055aff ffff4989 f1504889 febf0800 ..Z...I..PH..... - 0340 00006a00 488d4424 24504150 5131c952 ..j.H.D$$PAPQ1.R - 0350 31d24c8d 442440e8 00000000 4883c440 1.L.D$@.....H..@ - 0360 488b4424 0864482b 04252800 00007549 H.D$.dH+.%(...uI - 0370 4883c418 c30f1f00 4883fa01 75224983 H.......H...u"I. - 0380 f801751c 488b4424 0864482b 04252800 ..u.H.D$.dH+.%(. - 0390 00007525 4889ca48 83c418e9 10fdffff ..u%H..H........ - 03a0 488b4424 0864482b 04252800 00007509 H.D$.dH+.%(...u. - 03b0 4883c418 e947fcff ffe80000 0000 H....G........ + 00b0 4889ce4c 89c24c89 c94983f8 01751948 H..L..L..I...u.H + 00c0 837c2408 01751141 b8010000 00e82eff .|$..u.A........ + 00d0 ffff31c0 c30f1f00 4c8b4424 08e81eff ..1.....L.D$.... + 00e0 ffff31c0 c366662e 0f1f8400 00000000 ..1..ff......... + 00f0 4883ec18 64488b04 25280000 00488944 H...dH..%(...H.D + 0100 240831c0 4885ff7e 674885d2 0f94c04d $.1.H..~gH.....M + 0110 85c0410f 94c14408 c8756d48 81ffa086 ..A...D..umH.... + 0120 01007e64 4881ff7f 96980041 b9040000 ..~dH......A.... + 0130 00b81000 0000410f 4ec14883 ec085048 ......A.N.H...PH + 0140 8d056aff ffff4989 f1504889 febf0800 ..j...I..PH..... + 0150 00006a00 488d4424 24504150 5131c952 ..j.H.D$$PAPQ1.R + 0160 31d24c8d 442440e8 00000000 4883c440 1.L.D$@.....H..@ + 0170 488b4424 0864482b 04252800 00007559 H.D$.dH+.%(...uY + 0180 4883c418 c30f1f00 4883fa01 75324983 H.......H...u2I. + 0190 f801752c 488b4424 0864482b 04252800 ..u,H.D$.dH+.%(. + 01a0 00007535 41b80100 0000ba01 00000048 ..u5A..........H + 01b0 83c418e9 48feffff 0f1f8400 00000000 ....H........... + 01c0 488b4424 0864482b 04252800 00007509 H.D$.dH+.%(...u. + 01d0 4883c418 e927feff ffe80000 0000 H....'........ /usr/lib64/libopenblas_openmp.a/sbstobf16_k_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/sbstobf16_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sbstobf16_k_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0010 020001c0 04000000 01000000 00000000 ................ + 0020 010001c0 04000000 01000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/sbstobf16_k_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/sbstobf16_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sbstobf16_k_COOPERLAKE.o (objdump) @@ -5,11 +5,9 @@ 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 10000000 1c000000 ................ 0020 00000000 ad000000 00000000 10000000 ................ - 0030 30000000 00000000 dd010000 00000000 0............... - 0040 1c000000 44000000 00000000 44000000 ....D.......D... - 0050 00440e10 620a0e08 4a0b530e 08000000 .D..b...J.S..... - 0060 44000000 64000000 00000000 de000000 D...d........... - 0070 00440e20 024a0e28 410e304b 0e384a0e .D. .J.(A.0K.8J. - 0080 40460e48 420e5041 0e58430e 60500e20 @F.HB.PA.XC.`P. - 0090 540a0e08 440b630a 0e08450b 540a0e08 T...D.c...E.T... - 00a0 450b0000 00000000 E....... + 0030 30000000 00000000 35000000 00000000 0.......5....... + 0040 44000000 44000000 00000000 ee000000 D...D........... + 0050 00440e20 024a0e28 410e304b 0e384a0e .D. .J.(A.0K.8J. + 0060 40460e48 420e5041 0e58430e 60500e20 @F.HB.PA.XC.`P. + 0070 540a0e08 440b6b0a 0e084d0b 540a0e08 T...D.k...M.T... + 0080 450b0000 00000000 E....... /usr/lib64/libopenblas_openmp.a/sdot_k_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sdot_k_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sdot_k_COOPERLAKE.o (disasm) @@ -4,176 +4,151 @@ Disassembly of section .text: +sdot_kernel_16.constprop.0: + xor %eax,%eax + vxorps %ymm4,%ymm4,%ymm4 + vxorps %ymm5,%ymm5,%ymm5 + vxorps %ymm6,%ymm6,%ymm6 + vxorps %ymm7,%ymm7,%ymm7 + data16 cs nopw offset(%rax,%rax,1) + nopl (%rax) + vmovups (%rsi,%rax,4),%ymm12 + vmovups offset(%rsi,%rax,4),%ymm13 + vmovups offset(%rsi,%rax,4),%ymm14 + vmovups offset(%rsi,%rax,4),%ymm15 + vfmadd231ps (%rdx,%rax,4),%ymm12,%ymm4 + vfmadd231ps offset(%rdx,%rax,4),%ymm13,%ymm5 + vfmadd231ps offset(%rdx,%rax,4),%ymm14,%ymm6 + vfmadd231ps offset(%rdx,%rax,4),%ymm15,%ymm7 + add $something,%rax + sub $something,%rdi + jne + vextractf128 $something,%ymm4,%xmm12 + vextractf128 $something,%ymm5,%xmm13 + vextractf128 $something,%ymm6,%xmm14 + vextractf128 $something,%ymm7,%xmm15 + vaddps %xmm4,%xmm12,%xmm4 + vaddps %xmm5,%xmm13,%xmm5 + vaddps %xmm6,%xmm14,%xmm6 + vaddps %xmm7,%xmm15,%xmm7 + vaddps %xmm4,%xmm5,%xmm4 + vaddps %xmm6,%xmm7,%xmm6 + vaddps %xmm4,%xmm6,%xmm4 + vhaddps %xmm4,%xmm4,%xmm4 + vhaddps %xmm4,%xmm4,%xmm4 + vmovss %xmm4,(%rcx) + vzeroupper + vzeroupper + ret + data16 cs nopw offset(%rax,%rax,1) + xchg %ax,%ax + sdot_k_COOPERLAKE: + push %r13 + vxorps %xmm0,%xmm0,%xmm0 + push %r12 + push %rbp + push %rbx + sub $something,%rsp + mov %fs:0x28,%rax + mov %rax,offset(%rsp) + xor %eax,%eax + movl $something,offset(%rsp) test %rdi,%rdi jle - mov %rsi,%r10 + mov %rdx,%r10 mov %rdi,%r9 - mov %rdx,%rsi - mov %rcx,%r11 - cmp $something,%rdx + mov %rcx,%rdx + cmp $something,%r10 jne cmp $something,%r8 jne - vxorpd %xmm0,%xmm0,%xmm0 - mov %rdi,%rax - vmovsd %xmm0,%xmm0,%xmm2 - and $something,%rax + vxorpd %xmm2,%xmm2,%xmm2 + mov %rdi,%r8 + vmovq %xmm2,%r10 + and $something,%r8 jne - cs nopw offset(%rax,%rax,1) - vmovss (%r11,%rax,4),%xmm1 - vmulss (%r10,%rax,4),%xmm1,%xmm1 - inc %rax + vmovq %r10,%xmm0 + nopl offset(%rax,%rax,1) + vmovss (%rdx,%r8,4),%xmm1 + vmulss (%rsi,%r8,4),%xmm1,%xmm1 + inc %r8 vcvtss2sd %xmm1,%xmm1,%xmm1 vaddsd %xmm1,%xmm0,%xmm0 - cmp %rax,%r9 + cmp %r8,%r9 jg vaddsd %xmm2,%xmm0,%xmm0 vcvtsd2ss %xmm0,%xmm0,%xmm0 + mov offset(%rsp),%rax + sub %fs:0x28,%rax + jne + add $something,%rsp + pop %rbx + pop %rbp + pop %r12 + pop %r13 ret - nopl (%rax) - push %rbp + nopl offset(%rax,%rax,1) mov %r9,%rax - mov %rsp,%rbp - push %r14 - push %r13 - push %r12 - push %rbx and $something,%rax je - lea (%rsi,%rsi,1),%r13 - lea (%r8,%r8,1),%r14 - lea offset(,%r8,8),%r12 - mov %r11,%rcx - lea offset(,%rsi,8),%rbx - mov %r10,%rdx + lea (%r10,%r10,1),%r12 + lea (%r8,%r8,1),%r13 + lea offset(,%r8,8),%rbp + mov %rdx,%rdi + lea offset(,%r10,8),%rbx + mov %rsi,%rcx vxorpd %xmm0,%xmm0,%xmm0 - xor %edi,%edi - nopl offset(%rax) - vmovss (%rcx,%r8,4),%xmm1 - vmovss (%rcx),%xmm5 - vmulss (%rdx,%rsi,4),%xmm1,%xmm1 - add $something,%rdi - add %r12,%rcx - vfmadd231ss (%rdx),%xmm5,%xmm1 - add %rbx,%rdx + xor %r11d,%r11d + nopw offset(%rax,%rax,1) + vmovss (%rdi,%r8,4),%xmm1 + vmovss (%rdi),%xmm3 + vmulss (%rcx,%r10,4),%xmm1,%xmm1 + add $something,%r11 + add %rbp,%rdi + vfmadd231ss (%rcx),%xmm3,%xmm1 + add %rbx,%rcx vcvtss2sd %xmm1,%xmm1,%xmm1 vaddsd %xmm1,%xmm0,%xmm0 - cmp %rdi,%rax + cmp %r11,%rax jg dec %rax shr %rax inc %rax + imul %rax,%r12 imul %rax,%r13 - imul %rax,%r14 add %rax,%rax cmp %rax,%r9 jle + lea (%rdx,%r13,4),%rcx shl $something,%r8 - lea (%r11,%r14,4),%rcx - shl $something,%rsi - lea (%r10,%r13,4),%rdx - nopl offset(%rax) + shl $something,%r10 + lea (%rsi,%r12,4),%rdx + nopl (%rax) vmovss (%rcx),%xmm1 inc %rax vmulss (%rdx),%xmm1,%xmm1 add %r8,%rcx - add %rsi,%rdx + add %r10,%rdx vcvtss2sd %xmm1,%xmm1,%xmm1 vaddsd %xmm1,%xmm0,%xmm0 cmp %rax,%r9 jg - pop %rbx - pop %r12 - pop %r13 - pop %r14 vcvtsd2ss %xmm0,%xmm0,%xmm0 - pop %rbp - ret - nopl offset(%rax,%rax,1) - vxorps %xmm0,%xmm0,%xmm0 - ret - nopl (%rax) - mov %eax,%edx - and $something,%edx - jle - dec %edx - shr $something,%edx - mov %edx,%edi - vxorps %xmm1,%xmm1,%xmm1 - shl $something,%rdi - mov %r10,%rcx - mov %r11,%rsi - lea offset(%r10,%rdi,1),%rdi /usr/lib64/libopenblas_openmp.a/sdot_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sdot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sdot_k_COOPERLAKE.o (objdump) @@ -2,47 +2,41 @@ /usr/lib64/libopenblas_openmp.a/sdot_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 4885ff0f 8e270100 004989f2 4989f948 H....'...I..I..H - 0010 89d64989 cb4883fa 01754d49 83f80175 ..I..H...uMI...u - 0020 47c5f957 c04889f8 c5fb10d0 4883e0e0 G..W.H......H... - 0030 0f850201 0000662e 0f1f8400 00000000 ......f......... - 0040 c4c17a10 0c83c4c1 72590c82 48ffc0c5 ..z.....rY..H... - 0050 f25ac9c5 fb58c149 39c17fe4 c5fb58c2 .Z...X.I9.....X. - 0060 c5fb5ac0 c30f1f00 554c89c8 4889e541 ..Z.....UL..H..A - 0070 56415541 54534883 e0fe0f84 10020000 VAUATSH......... - 0080 4c8d2c36 4f8d3400 4e8d24c5 00000000 L.,6O.4.N.$..... - 0090 4c89d948 8d1cf500 0000004c 89d2c5f9 L..H.......L.... - 00a0 57c031ff 0f1f4000 c4a17a10 0c81c5fa W.1...@...z..... - 00b0 1029c5f2 590cb248 83c7024c 01e1c4e2 .)..Y..H...L.... - 00c0 51b90a48 01dac5f2 5ac9c5fb 58c14839 Q..H....Z...X.H9 - 00d0 f87fd548 ffc848d1 e848ffc0 4c0fafe8 ...H..H..H..L... - 00e0 4c0faff0 4801c049 39c17e32 49c1e002 L...H..I9.~2I... - 00f0 4b8d0cb3 48c1e602 4b8d14aa 0f1f4000 K...H...K.....@. - 0100 c5fa1009 48ffc0c5 f2590a4c 01c14801 ....H....Y.L..H. - 0110 f2c5f25a c9c5fb58 c14939c1 7fe25b41 ...Z...X.I9...[A - 0120 5c415d41 5ec5fb5a c05dc30f 1f440000 \A]A^..Z.]...D.. - 0130 c5f857c0 c30f1f00 89c283e2 c00f8e64 ..W............d - 0140 010000ff cac1ea06 89d7c5f0 57c948c1 ............W.H. - 0150 e7084c89 d14c89de 498dbc3a 00010000 ..L..L..I..:.... - 0160 62f17c48 28d162f1 7c4828d9 62f17c48 b.|H(.b.|H(.b.|H - 0170 28e1660f 1f440000 62f17c48 103162f1 (.f..D..b.|H.1b. - 0180 7c481079 0162f24d 48b82662 f24548b8 |H.y.b.MH.&b.EH. - 0190 5e0162f1 7c481071 0262f17c 48107903 ^.b.|H.q.b.|H.y. - 01a0 4881c100 01000062 f24d48b8 560262f2 H......b.MH.V.b. - 01b0 4548b84e 034881c6 00010000 4839cf75 EH.N.H......H9.u - 01c0 b7c5fc28 c462f37d 481be401 c5fc58c4 ...(.b.}H.....X. - 01d0 ffc2c5fc 28e362f3 7d481bdb 01c5dc58 ....(.b.}H.....X - 01e0 dbc1e206 c5fc28e2 62f37d48 1bd201c5 ......(.b.}H.... - 01f0 dc58d248 63d2c5fc 28e162f3 7d481bc9 .X.Hc...(.b.}H.. - 0200 01c5dc58 e14839d0 7e45660f 1f440000 ...X.H9.~Ef..D.. - 0210 c4c17c10 3492c4c1 7c107c92 20c4c24d ..|.4...|.|. ..M - 0220 b80493c4 c245b85c 9320c4c1 7c107492 .....E.\. ..|.t. - 0230 40c4c17c 107c9260 c4c24db8 549340c4 @..|.|.`..M.T.@. - 0240 c245b864 93604883 c2204839 d07fc1c5 .E.d.`H.. H9.... - 0250 fc58cbc5 f458cac5 f458ccc5 f828c1c4 .X...X...X...(.. - 0260 e37d19c9 01c5f858 c1c5fb7c c0c5fb7c .}.....X...|...| - 0270 c0c5fa5a d0c5f957 c04939c1 7e21c5f8 ...Z...W.I9.~!.. - 0280 77e9bafd ffff662e 0f1f8400 00000000 w.....f......... - 0290 4531f645 31edc5f9 57c0e94d feffffc5 E1.E1...W..M.... - 02a0 f877e9b5 fdffffc5 f857c0c5 fc28e0c5 .w.......W...(.. - 02b0 fc28d0c5 fc28d831 d2e952ff ffff .(...(.1..R... + 0000 31c0c5dc 57e4c5d4 57edc5cc 57f6c5c4 1...W...W...W... + 0010 57ff6666 2e0f1f84 00000000 000f1f00 W.ff............ + 0020 c57c1024 86c57c10 6c8620c5 7c107486 .|.$..|.l. .|.t. + 0030 40c57c10 7c8660c4 e21db824 82c4e215 @.|.|.`....$.... + 0040 b86c8220 c4e20db8 748240c4 e205b87c .l. ....t.@....| + 0050 82604883 c0204883 ef2075c4 c4c37d19 .`H.. H.. u...}. + 0060 e401c4c3 7d19ed01 c4c37d19 f601c4c3 ....}.....}..... + 0070 7d19ff01 c59858e4 c59058ed c58858f6 }.....X...X...X. + 0080 c58058ff c5d058e4 c5c058f6 c5c858e4 ..X...X...X...X. + 0090 c5db7ce4 c5db7ce4 c5fa1121 c5f877c5 ..|...|....!..w. + 00a0 f877c366 662e0f1f 84000000 00006690 .w.ff.........f. + 00b0 4155c5f8 57c04154 55534883 ec186448 AU..W.ATUSH...dH + 00c0 8b042528 00000048 89442408 31c0c744 ..%(...H.D$.1..D + 00d0 24040000 00004885 ff7e5949 89d24989 $.....H..~YI..I. + 00e0 f94889ca 4983fa01 756e4983 f8017568 .H..I...unI...uh + 00f0 c5e957d2 4989f8c4 c1f97ed2 4983e0e0 ..W.I.....~.I... + 0100 0f850a01 0000c4c1 f96ec20f 1f440000 .........n...D.. + 0110 c4a17a10 0c82c4a1 72590c86 49ffc0c5 ..z.....rY..I... + 0120 f25ac9c5 fb58c14d 39c17fe4 c5fb58c2 .Z...X.M9.....X. + 0130 c5fb5ac0 488b4424 0864482b 04252800 ..Z.H.D$.dH+.%(. + 0140 00000f85 04010000 4883c418 5b5d415c ........H...[]A\ + 0150 415dc30f 1f440000 4c89c848 83e0fe0f A]...D..L..H.... + 0160 84db0000 004f8d24 124f8d2c 004a8d2c .....O.$.O.,.J., + 0170 c5000000 004889d7 4a8d1cd5 00000000 .....H..J....... + 0180 4889f1c5 f957c045 31db660f 1f440000 H....W.E1.f..D.. + 0190 c4a17a10 0c87c5fa 101fc4a1 72590c91 ..z.........rY.. + 01a0 4983c302 4801efc4 e261b909 4801d9c5 I...H....a..H... + 01b0 f25ac9c5 fb58c14c 39d87fd4 48ffc848 .Z...X.L9...H..H + 01c0 d1e848ff c04c0faf e04c0faf e84801c0 ..H..L...L...H.. + 01d0 4939c17e 314a8d0c aa49c1e0 0249c1e2 I9.~1J...I...I.. + 01e0 024a8d14 a60f1f00 c5fa1009 48ffc0c5 .J..........H... + 01f0 f2590a4c 01c14c01 d2c5f25a c9c5fb58 .Y.L..L....Z...X + 0200 c14939c1 7fe2c5fb 5ac0e925 ffffff90 .I9.....Z..%.... + 0210 62a17c00 57c0488d 4c24044c 89c7e8dd b.|.W.H.L$.L.... + 0220 fdffffc4 c1f96ec2 62f17e00 5a542401 ......n.b.~.ZT$. + 0230 4d39c10f 8fcdfeff ffe9eefe ffff6690 M9............f. + 0240 4531ed45 31e4c5f9 57c0eb89 e8000000 E1.E1...W....... + 0250 00 . /usr/lib64/libopenblas_openmp.a/sdot_k_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/sdot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sdot_k_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 be020000 0002690e 10860246 ..........i....F - 0030 0d06478e 038d048c 05830602 b40c0708 ..G............. - 0040 46c3c6cc cdce0360 010c0610 83068602 F......`........ - 0050 8c058d04 8e034f0c 0708c3c6 cccdce00 ......O......... + 0010 1b0c0708 90010000 10000000 1c000000 ................ + 0020 00000000 a3000000 00000000 38000000 ............8... + 0030 30000000 00000000 a1010000 00420e10 0............B.. + 0040 8d02460e 188c0341 0e208604 410e2883 ..F....A. ..A.(. + 0050 05440e40 028e0a0e 28410e20 410e1842 .D.@....(A. A..B + 0060 0e10420e 08460b00 ..B..F.. /usr/lib64/libopenblas_openmp.a/sdot_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sdot_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sdot_k_SKYLAKEX.o (disasm) @@ -4,176 +4,151 @@ Disassembly of section .text: +sdot_kernel_16.constprop.0: + xor %eax,%eax + vxorps %ymm4,%ymm4,%ymm4 + vxorps %ymm5,%ymm5,%ymm5 + vxorps %ymm6,%ymm6,%ymm6 + vxorps %ymm7,%ymm7,%ymm7 + data16 cs nopw offset(%rax,%rax,1) + nopl (%rax) + vmovups (%rsi,%rax,4),%ymm12 + vmovups offset(%rsi,%rax,4),%ymm13 + vmovups offset(%rsi,%rax,4),%ymm14 + vmovups offset(%rsi,%rax,4),%ymm15 + vfmadd231ps (%rdx,%rax,4),%ymm12,%ymm4 + vfmadd231ps offset(%rdx,%rax,4),%ymm13,%ymm5 + vfmadd231ps offset(%rdx,%rax,4),%ymm14,%ymm6 + vfmadd231ps offset(%rdx,%rax,4),%ymm15,%ymm7 + add $something,%rax + sub $something,%rdi + jne + vextractf128 $something,%ymm4,%xmm12 + vextractf128 $something,%ymm5,%xmm13 + vextractf128 $something,%ymm6,%xmm14 + vextractf128 $something,%ymm7,%xmm15 + vaddps %xmm4,%xmm12,%xmm4 + vaddps %xmm5,%xmm13,%xmm5 + vaddps %xmm6,%xmm14,%xmm6 + vaddps %xmm7,%xmm15,%xmm7 + vaddps %xmm4,%xmm5,%xmm4 + vaddps %xmm6,%xmm7,%xmm6 + vaddps %xmm4,%xmm6,%xmm4 + vhaddps %xmm4,%xmm4,%xmm4 + vhaddps %xmm4,%xmm4,%xmm4 + vmovss %xmm4,(%rcx) + vzeroupper + vzeroupper + ret + data16 cs nopw offset(%rax,%rax,1) + xchg %ax,%ax + sdot_k_SKYLAKEX: + push %r13 + vxorps %xmm0,%xmm0,%xmm0 + push %r12 + push %rbp + push %rbx + sub $something,%rsp + mov %fs:0x28,%rax + mov %rax,offset(%rsp) + xor %eax,%eax + movl $something,offset(%rsp) test %rdi,%rdi jle - mov %rsi,%r10 + mov %rdx,%r10 mov %rdi,%r9 - mov %rdx,%rsi - mov %rcx,%r11 - cmp $something,%rdx + mov %rcx,%rdx + cmp $something,%r10 jne cmp $something,%r8 jne - vxorpd %xmm0,%xmm0,%xmm0 - mov %rdi,%rax - vmovsd %xmm0,%xmm0,%xmm2 - and $something,%rax + vxorpd %xmm2,%xmm2,%xmm2 + mov %rdi,%r8 + vmovq %xmm2,%r10 + and $something,%r8 jne - cs nopw offset(%rax,%rax,1) - vmovss (%r11,%rax,4),%xmm1 - vmulss (%r10,%rax,4),%xmm1,%xmm1 - inc %rax + vmovq %r10,%xmm0 + nopl offset(%rax,%rax,1) + vmovss (%rdx,%r8,4),%xmm1 + vmulss (%rsi,%r8,4),%xmm1,%xmm1 + inc %r8 vcvtss2sd %xmm1,%xmm1,%xmm1 vaddsd %xmm1,%xmm0,%xmm0 - cmp %rax,%r9 + cmp %r8,%r9 jg vaddsd %xmm2,%xmm0,%xmm0 vcvtsd2ss %xmm0,%xmm0,%xmm0 + mov offset(%rsp),%rax + sub %fs:0x28,%rax + jne + add $something,%rsp + pop %rbx + pop %rbp + pop %r12 + pop %r13 ret - nopl (%rax) - push %rbp + nopl offset(%rax,%rax,1) mov %r9,%rax - mov %rsp,%rbp - push %r14 - push %r13 - push %r12 - push %rbx and $something,%rax je - lea (%rsi,%rsi,1),%r13 - lea (%r8,%r8,1),%r14 - lea offset(,%r8,8),%r12 - mov %r11,%rcx - lea offset(,%rsi,8),%rbx - mov %r10,%rdx + lea (%r10,%r10,1),%r12 + lea (%r8,%r8,1),%r13 + lea offset(,%r8,8),%rbp + mov %rdx,%rdi + lea offset(,%r10,8),%rbx + mov %rsi,%rcx vxorpd %xmm0,%xmm0,%xmm0 - xor %edi,%edi - nopl offset(%rax) - vmovss (%rcx,%r8,4),%xmm1 - vmovss (%rcx),%xmm5 - vmulss (%rdx,%rsi,4),%xmm1,%xmm1 - add $something,%rdi - add %r12,%rcx - vfmadd231ss (%rdx),%xmm5,%xmm1 - add %rbx,%rdx + xor %r11d,%r11d + nopw offset(%rax,%rax,1) + vmovss (%rdi,%r8,4),%xmm1 + vmovss (%rdi),%xmm3 + vmulss (%rcx,%r10,4),%xmm1,%xmm1 + add $something,%r11 + add %rbp,%rdi + vfmadd231ss (%rcx),%xmm3,%xmm1 + add %rbx,%rcx vcvtss2sd %xmm1,%xmm1,%xmm1 vaddsd %xmm1,%xmm0,%xmm0 - cmp %rdi,%rax + cmp %r11,%rax jg dec %rax shr %rax inc %rax + imul %rax,%r12 imul %rax,%r13 - imul %rax,%r14 add %rax,%rax cmp %rax,%r9 jle + lea (%rdx,%r13,4),%rcx shl $something,%r8 - lea (%r11,%r14,4),%rcx - shl $something,%rsi - lea (%r10,%r13,4),%rdx - nopl offset(%rax) + shl $something,%r10 + lea (%rsi,%r12,4),%rdx + nopl (%rax) vmovss (%rcx),%xmm1 inc %rax vmulss (%rdx),%xmm1,%xmm1 add %r8,%rcx - add %rsi,%rdx + add %r10,%rdx vcvtss2sd %xmm1,%xmm1,%xmm1 vaddsd %xmm1,%xmm0,%xmm0 cmp %rax,%r9 jg - pop %rbx - pop %r12 - pop %r13 - pop %r14 vcvtsd2ss %xmm0,%xmm0,%xmm0 - pop %rbp - ret - nopl offset(%rax,%rax,1) - vxorps %xmm0,%xmm0,%xmm0 - ret - nopl (%rax) - mov %eax,%edx - and $something,%edx - jle - dec %edx - shr $something,%edx - mov %edx,%edi - vxorps %xmm1,%xmm1,%xmm1 - shl $something,%rdi - mov %r10,%rcx - mov %r11,%rsi - lea offset(%r10,%rdi,1),%rdi /usr/lib64/libopenblas_openmp.a/sdot_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sdot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sdot_k_SKYLAKEX.o (objdump) @@ -2,47 +2,41 @@ /usr/lib64/libopenblas_openmp.a/sdot_k_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 4885ff0f 8e270100 004989f2 4989f948 H....'...I..I..H - 0010 89d64989 cb4883fa 01754d49 83f80175 ..I..H...uMI...u - 0020 47c5f957 c04889f8 c5fb10d0 4883e0e0 G..W.H......H... - 0030 0f850201 0000662e 0f1f8400 00000000 ......f......... - 0040 c4c17a10 0c83c4c1 72590c82 48ffc0c5 ..z.....rY..H... - 0050 f25ac9c5 fb58c149 39c17fe4 c5fb58c2 .Z...X.I9.....X. - 0060 c5fb5ac0 c30f1f00 554c89c8 4889e541 ..Z.....UL..H..A - 0070 56415541 54534883 e0fe0f84 10020000 VAUATSH......... - 0080 4c8d2c36 4f8d3400 4e8d24c5 00000000 L.,6O.4.N.$..... - 0090 4c89d948 8d1cf500 0000004c 89d2c5f9 L..H.......L.... - 00a0 57c031ff 0f1f4000 c4a17a10 0c81c5fa W.1...@...z..... - 00b0 1029c5f2 590cb248 83c7024c 01e1c4e2 .)..Y..H...L.... - 00c0 51b90a48 01dac5f2 5ac9c5fb 58c14839 Q..H....Z...X.H9 - 00d0 f87fd548 ffc848d1 e848ffc0 4c0fafe8 ...H..H..H..L... - 00e0 4c0faff0 4801c049 39c17e32 49c1e002 L...H..I9.~2I... - 00f0 4b8d0cb3 48c1e602 4b8d14aa 0f1f4000 K...H...K.....@. - 0100 c5fa1009 48ffc0c5 f2590a4c 01c14801 ....H....Y.L..H. - 0110 f2c5f25a c9c5fb58 c14939c1 7fe25b41 ...Z...X.I9...[A - 0120 5c415d41 5ec5fb5a c05dc30f 1f440000 \A]A^..Z.]...D.. - 0130 c5f857c0 c30f1f00 89c283e2 c00f8e64 ..W............d - 0140 010000ff cac1ea06 89d7c5f0 57c948c1 ............W.H. - 0150 e7084c89 d14c89de 498dbc3a 00010000 ..L..L..I..:.... - 0160 62f17c48 28d162f1 7c4828d9 62f17c48 b.|H(.b.|H(.b.|H - 0170 28e1660f 1f440000 62f17c48 103162f1 (.f..D..b.|H.1b. - 0180 7c481079 0162f24d 48b82662 f24548b8 |H.y.b.MH.&b.EH. - 0190 5e0162f1 7c481071 0262f17c 48107903 ^.b.|H.q.b.|H.y. - 01a0 4881c100 01000062 f24d48b8 560262f2 H......b.MH.V.b. - 01b0 4548b84e 034881c6 00010000 4839cf75 EH.N.H......H9.u - 01c0 b7c5fc28 c462f37d 481be401 c5fc58c4 ...(.b.}H.....X. - 01d0 ffc2c5fc 28e362f3 7d481bdb 01c5dc58 ....(.b.}H.....X - 01e0 dbc1e206 c5fc28e2 62f37d48 1bd201c5 ......(.b.}H.... - 01f0 dc58d248 63d2c5fc 28e162f3 7d481bc9 .X.Hc...(.b.}H.. - 0200 01c5dc58 e14839d0 7e45660f 1f440000 ...X.H9.~Ef..D.. - 0210 c4c17c10 3492c4c1 7c107c92 20c4c24d ..|.4...|.|. ..M - 0220 b80493c4 c245b85c 9320c4c1 7c107492 .....E.\. ..|.t. - 0230 40c4c17c 107c9260 c4c24db8 549340c4 @..|.|.`..M.T.@. - 0240 c245b864 93604883 c2204839 d07fc1c5 .E.d.`H.. H9.... - 0250 fc58cbc5 f458cac5 f458ccc5 f828c1c4 .X...X...X...(.. - 0260 e37d19c9 01c5f858 c1c5fb7c c0c5fb7c .}.....X...|...| - 0270 c0c5fa5a d0c5f957 c04939c1 7e21c5f8 ...Z...W.I9.~!.. - 0280 77e9bafd ffff662e 0f1f8400 00000000 w.....f......... - 0290 4531f645 31edc5f9 57c0e94d feffffc5 E1.E1...W..M.... - 02a0 f877e9b5 fdffffc5 f857c0c5 fc28e0c5 .w.......W...(.. - 02b0 fc28d0c5 fc28d831 d2e952ff ffff .(...(.1..R... + 0000 31c0c5dc 57e4c5d4 57edc5cc 57f6c5c4 1...W...W...W... + 0010 57ff6666 2e0f1f84 00000000 000f1f00 W.ff............ + 0020 c57c1024 86c57c10 6c8620c5 7c107486 .|.$..|.l. .|.t. + 0030 40c57c10 7c8660c4 e21db824 82c4e215 @.|.|.`....$.... + 0040 b86c8220 c4e20db8 748240c4 e205b87c .l. ....t.@....| + 0050 82604883 c0204883 ef2075c4 c4c37d19 .`H.. H.. u...}. + 0060 e401c4c3 7d19ed01 c4c37d19 f601c4c3 ....}.....}..... + 0070 7d19ff01 c59858e4 c59058ed c58858f6 }.....X...X...X. + 0080 c58058ff c5d058e4 c5c058f6 c5c858e4 ..X...X...X...X. + 0090 c5db7ce4 c5db7ce4 c5fa1121 c5f877c5 ..|...|....!..w. + 00a0 f877c366 662e0f1f 84000000 00006690 .w.ff.........f. + 00b0 4155c5f8 57c04154 55534883 ec186448 AU..W.ATUSH...dH + 00c0 8b042528 00000048 89442408 31c0c744 ..%(...H.D$.1..D + 00d0 24040000 00004885 ff7e5949 89d24989 $.....H..~YI..I. + 00e0 f94889ca 4983fa01 756e4983 f8017568 .H..I...unI...uh + 00f0 c5e957d2 4989f8c4 c1f97ed2 4983e0e0 ..W.I.....~.I... + 0100 0f850a01 0000c4c1 f96ec20f 1f440000 .........n...D.. + 0110 c4a17a10 0c82c4a1 72590c86 49ffc0c5 ..z.....rY..I... + 0120 f25ac9c5 fb58c14d 39c17fe4 c5fb58c2 .Z...X.M9.....X. + 0130 c5fb5ac0 488b4424 0864482b 04252800 ..Z.H.D$.dH+.%(. + 0140 00000f85 04010000 4883c418 5b5d415c ........H...[]A\ + 0150 415dc30f 1f440000 4c89c848 83e0fe0f A]...D..L..H.... + 0160 84db0000 004f8d24 124f8d2c 004a8d2c .....O.$.O.,.J., + 0170 c5000000 004889d7 4a8d1cd5 00000000 .....H..J....... + 0180 4889f1c5 f957c045 31db660f 1f440000 H....W.E1.f..D.. + 0190 c4a17a10 0c87c5fa 101fc4a1 72590c91 ..z.........rY.. + 01a0 4983c302 4801efc4 e261b909 4801d9c5 I...H....a..H... + 01b0 f25ac9c5 fb58c14c 39d87fd4 48ffc848 .Z...X.L9...H..H + 01c0 d1e848ff c04c0faf e04c0faf e84801c0 ..H..L...L...H.. + 01d0 4939c17e 314a8d0c aa49c1e0 0249c1e2 I9.~1J...I...I.. + 01e0 024a8d14 a60f1f00 c5fa1009 48ffc0c5 .J..........H... + 01f0 f2590a4c 01c14c01 d2c5f25a c9c5fb58 .Y.L..L....Z...X + 0200 c14939c1 7fe2c5fb 5ac0e925 ffffff90 .I9.....Z..%.... + 0210 62a17c00 57c0488d 4c24044c 89c7e8dd b.|.W.H.L$.L.... + 0220 fdffffc4 c1f96ec2 62f17e00 5a542401 ......n.b.~.ZT$. + 0230 4d39c10f 8fcdfeff ffe9eefe ffff6690 M9............f. + 0240 4531ed45 31e4c5f9 57c0eb89 e8000000 E1.E1...W....... + 0250 00 . /usr/lib64/libopenblas_openmp.a/sdot_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/sdot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sdot_k_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 be020000 0002690e 10860246 ..........i....F - 0030 0d06478e 038d048c 05830602 b40c0708 ..G............. - 0040 46c3c6cc cdce0360 010c0610 83068602 F......`........ - 0050 8c058d04 8e034f0c 0708c3c6 cccdce00 ......O......... + 0010 1b0c0708 90010000 10000000 1c000000 ................ + 0020 00000000 a3000000 00000000 38000000 ............8... + 0030 30000000 00000000 a1010000 00420e10 0............B.. + 0040 8d02460e 188c0341 0e208604 410e2883 ..F....A. ..A.(. + 0050 05440e40 028e0a0e 28410e20 410e1842 .D.@....(A. A..B + 0060 0e10420e 08460b00 ..B..F.. /usr/lib64/libopenblas_openmp.a/sdsdot_k_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sdsdot_k_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sdsdot_k_COOPERLAKE.o (disasm) @@ -4,134 +4,163 @@ Disassembly of section .text: +sdot_kernel_16.constprop.0: + mov %rdx,%r8 + xor %eax,%eax + mov $something,%edx + vxorps %ymm4,%ymm4,%ymm4 + vxorps %ymm5,%ymm5,%ymm5 + vxorps %ymm6,%ymm6,%ymm6 + vxorps %ymm7,%ymm7,%ymm7 + nopw offset(%rax,%rax,1) + vmovups (%rdi,%rax,4),%ymm12 + vmovups offset(%rdi,%rax,4),%ymm13 + vmovups offset(%rdi,%rax,4),%ymm14 + vmovups offset(%rdi,%rax,4),%ymm15 + vfmadd231ps (%rsi,%rax,4),%ymm12,%ymm4 + vfmadd231ps offset(%rsi,%rax,4),%ymm13,%ymm5 + vfmadd231ps offset(%rsi,%rax,4),%ymm14,%ymm6 + vfmadd231ps offset(%rsi,%rax,4),%ymm15,%ymm7 + vextractf128 $something,%ymm4,%xmm12 + vextractf128 $something,%ymm5,%xmm13 + vextractf128 $something,%ymm6,%xmm14 + vextractf128 $something,%ymm7,%xmm15 + vaddps %xmm4,%xmm12,%xmm4 + vaddps %xmm5,%xmm13,%xmm5 + vaddps %xmm6,%xmm14,%xmm6 + vaddps %xmm7,%xmm15,%xmm7 + vaddps %xmm4,%xmm5,%xmm4 + vaddps %xmm6,%xmm7,%xmm6 + vaddps %xmm4,%xmm6,%xmm4 + vhaddps %xmm4,%xmm4,%xmm4 + vhaddps %xmm4,%xmm4,%xmm4 + vmovss %xmm4,(%r8) + vzeroupper + vzeroupper + ret + nopw offset(%rax,%rax,1) + sdsdot_k_COOPERLAKE: + push %r13 + vxorpd %xmm2,%xmm2,%xmm2 + push %r12 + push %rbp + push %rbx + sub $something,%rsp + mov %fs:0x28,%rax + mov %rax,offset(%rsp) + xor %eax,%eax + movl $something,offset(%rsp) test %rdi,%rdi jle - mov %rsi,%r9 - mov %rcx,%r10 + mov %rsi,%r10 + mov %rdi,%r9 mov %rdx,%rsi - vxorps %xmm1,%xmm1,%xmm1 + mov %rcx,%r11 + vxorps %xmm16,%xmm16,%xmm16 cmp $something,%rdx jne cmp $something,%r8 jne - mov %rdi,%rax - and $something,%rax + mov %rdi,%rcx + and $something,%rcx jne - vxorpd %xmm7,%xmm7,%xmm7 - vmovsd %xmm7,%xmm7,%xmm3 - vmovsd %xmm7,%xmm7,%xmm4 + vxorpd %xmm18,%xmm18,%xmm18 + vmovsd %xmm18,%xmm18,%xmm17 + vmovsd %xmm18,%xmm18,%xmm2 nopl offset(%rax,%rax,1) - vcvtss2sd (%r10,%rax,4),%xmm1,%xmm0 - vmovsd %xmm0,%xmm0,%xmm2 - vcvtss2sd (%r9,%rax,4),%xmm1,%xmm0 - inc %rax - vfmadd231sd %xmm0,%xmm2,%xmm4 - cmp %rax,%rdi + vcvtss2sd (%r11,%rcx,4),%xmm16,%xmm0 + vmovsd %xmm0,%xmm0,%xmm1 + vcvtss2sd (%r10,%rcx,4),%xmm16,%xmm0 + inc %rcx + vfmadd231sd %xmm0,%xmm1,%xmm2 + cmp %rcx,%r9 jg - vaddsd %xmm4,%xmm3,%xmm3 - vmovsd %xmm3,%xmm3,%xmm0 + vaddsd %xmm2,%xmm17,%xmm2 + mov offset(%rsp),%rax + sub %fs:0x28,%rax + jne + add $something,%rsp + pop %rbx + pop %rbp + pop %r12 + vmovsd %xmm2,%xmm2,%xmm0 + pop %r13 ret - cs nopw offset(%rax,%rax,1) - push %rbp - mov %rdi,%rax - mov %rsp,%rbp - push %r14 - push %r13 - push %r12 - push %rbx + nopl offset(%rax,%rax,1) + mov %r9,%rax and $something,%rax je - lea (%rsi,%rsi,1),%r13 - lea (%r8,%r8,1),%r14 - lea offset(,%r8,8),%r12 - mov %r10,%rcx + lea (%rsi,%rsi,1),%r12 + lea (%r8,%r8,1),%r13 + lea offset(,%r8,8),%rbp + mov %r11,%rcx lea offset(,%rsi,8),%rbx - mov %r9,%rdx - vxorpd %xmm3,%xmm3,%xmm3 - xor %r11d,%r11d - nopl (%rax) - vcvtss2sd (%rdx),%xmm1,%xmm2 - vcvtss2sd (%rdx,%rsi,4),%xmm1,%xmm5 - vmovsd %xmm2,%xmm2,%xmm4 - vcvtss2sd (%rcx,%r8,4),%xmm1,%xmm2 - vmulsd %xmm5,%xmm2,%xmm2 - vcvtss2sd (%rcx),%xmm1,%xmm0 - add $something,%r11 - add %r12,%rcx + mov %r10,%rdx + vxorpd %xmm2,%xmm2,%xmm2 + xor %edi,%edi + nopl offset(%rax) + vcvtss2sd (%rdx),%xmm16,%xmm1 + vcvtss2sd (%rdx,%rsi,4),%xmm16,%xmm4 + vmovsd %xmm1,%xmm1,%xmm3 + vcvtss2sd (%rcx,%r8,4),%xmm16,%xmm1 + vmulsd %xmm4,%xmm1,%xmm1 + vcvtss2sd (%rcx),%xmm16,%xmm0 + add $something,%rdi + add %rbp,%rcx add %rbx,%rdx - vfmadd132sd %xmm4,%xmm2,%xmm0 - vaddsd %xmm0,%xmm3,%xmm3 - cmp %r11,%rax + vfmadd132sd %xmm3,%xmm1,%xmm0 + vaddsd %xmm0,%xmm2,%xmm2 + cmp %rdi,%rax jg dec %rax shr %rax inc %rax + imul %rax,%r12 imul %rax,%r13 - imul %rax,%r14 add %rax,%rax - cmp %rax,%rdi + cmp %rax,%r9 jle shl $something,%r8 - lea (%r10,%r14,4),%rcx + lea (%r11,%r13,4),%rcx shl $something,%rsi - lea (%r9,%r13,4),%rdx - nopl offset(%rax) - vcvtss2sd (%rcx),%xmm1,%xmm0 + lea (%r10,%r12,4),%rdx + nop + vcvtss2sd (%rcx),%xmm16,%xmm0 inc %rax - vmovsd %xmm0,%xmm0,%xmm2 + vmovsd %xmm0,%xmm0,%xmm1 add %r8,%rcx - vcvtss2sd (%rdx),%xmm1,%xmm0 + vcvtss2sd (%rdx),%xmm16,%xmm0 add %rsi,%rdx - vfmadd231sd %xmm0,%xmm2,%xmm3 - cmp %rax,%rdi + vfmadd231sd %xmm0,%xmm1,%xmm2 + cmp %rax,%r9 jg - pop %rbx - pop %r12 - pop %r13 - pop %r14 - vmovsd %xmm3,%xmm3,%xmm0 - pop %rbp - ret - nopl offset(%rax) - vxorpd %xmm3,%xmm3,%xmm3 - vmovsd %xmm3,%xmm3,%xmm0 /usr/lib64/libopenblas_openmp.a/sdsdot_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sdsdot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sdsdot_k_COOPERLAKE.o (objdump) @@ -2,35 +2,46 @@ /usr/lib64/libopenblas_openmp.a/sdsdot_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 4885ff0f 8e370100 004989f1 4989ca48 H....7...I..I..H - 0010 89d6c5f0 57c94883 fa017554 4983f801 ....W.H...uTI... - 0020 754e4889 f84883e0 e00f8521 010000c5 uNH..H.....!.... - 0030 c157ffc5 c310dfc5 c310e70f 1f440000 .W...........D.. - 0040 c4c1725a 0482c5fb 10d0c4c1 725a0481 ..rZ........rZ.. - 0050 48ffc0c4 e2e9b9e0 4839c77f e3c5e358 H.......H9.....X - 0060 dcc5e310 c3c3662e 0f1f8400 00000000 ......f......... - 0070 554889f8 4889e541 56415541 54534883 UH..H..AVAUATSH. - 0080 e0fe0f84 52010000 4c8d2c36 4f8d3400 ....R...L.,6O.4. - 0090 4e8d24c5 00000000 4c89d148 8d1cf500 N.$.....L..H.... - 00a0 0000004c 89cac5e1 57db4531 db0f1f00 ...L....W.E1.... - 00b0 c5f25a12 c5f25a2c b2c5eb10 e2c4a172 ..Z...Z,.......r - 00c0 5a1481c5 eb59d5c5 f25a0149 83c3024c Z....Y...Z.I...L - 00d0 01e14801 dac4e2e9 99c4c5e3 58d84c39 ..H.........X.L9 - 00e0 d87fcd48 ffc848d1 e848ffc0 4c0fafe8 ...H..H..H..L... - 00f0 4c0faff0 4801c048 39c77e33 49c1e002 L...H..H9.~3I... - 0100 4b8d0cb2 48c1e602 4b8d14a9 0f1f4000 K...H...K.....@. - 0110 c5f25a01 48ffc0c5 fb10d04c 01c1c5f2 ..Z.H......L.... - 0120 5a024801 f2c4e2e9 b9d84839 c77fe15b Z.H.......H9...[ - 0130 415c415d 415ec5e3 10c35dc3 0f1f4000 A\A]A^....]...@. - 0140 c5e157db c5e310c3 c30f1f80 00000000 ..W............. - 0150 c5c157ff c5d857e4 c5c310df 31d26690 ..W...W.....1.f. - 0160 c4c17c10 1491c4c1 7c107491 20c4c25d ..|.....|.t. ..] - 0170 981492c4 c25d9874 9220c4c1 7c106c91 .....].t. ..|.l. - 0180 40c4c17c 10449260 c4c25d98 6c9240c4 @..|.D.`..].l.@. - 0190 c25d9844 9160c5ec 58d64883 c220c5ec .].D.`..X.H.. .. - 01a0 58d5c5fc 58c2c5f8 28d0c4e3 7d19c001 X...X...(...}... - 01b0 c5e858d0 c5eb7cd2 c5eb7cd2 c5ea5ad2 ..X...|...|...Z. - 01c0 c5e358da 4839d07f 97c5c310 e74839c7 ..X.H9.......H9. - 01d0 7e17c5f8 77e95dfe ffff4531 f64531ed ~...w.]...E1.E1. - 01e0 c5e157db e913ffff ffc5f877 e96cfeff ..W........w.l.. - 01f0 ff . + 0000 4989d031 c0ba2000 0000c5dc 57e4c5d4 I..1.. .....W... + 0010 57edc5cc 57f6c5c4 57ff660f 1f440000 W...W...W.f..D.. + 0020 c57c1024 87c57c10 6c8720c5 7c107487 .|.$..|.l. .|.t. + 0030 40c57c10 7c8760c4 e21db824 86c4e215 @.|.|.`....$.... + 0040 b86c8620 c4e20db8 748640c4 e205b87c .l. ....t.@....| + 0050 8660c4c3 7d19e401 c4c37d19 ed01c4c3 .`..}.....}..... + 0060 7d19f601 c4c37d19 ff01c598 58e4c590 }.....}.....X... + 0070 58edc588 58f6c580 58ffc5d0 58e4c5c0 X...X...X...X... + 0080 58f6c5c8 58e4c5db 7ce4c5db 7ce4c4c1 X...X...|...|... + 0090 7a1120c5 f877c5f8 77c3660f 1f440000 z. ..w..w.f..D.. + 00a0 4155c5e9 57d24154 55534883 ec186448 AU..W.ATUSH...dH + 00b0 8b042528 00000048 89442408 31c0c744 ..%(...H.D$.1..D + 00c0 24040000 00004885 ff7e6a49 89f24989 $.....H..~jI..I. + 00d0 f94889d6 4989cb62 a17c0057 c04883fa .H..I..b.|.W.H.. + 00e0 01757d49 83f80175 774889f9 4883e1e0 .u}I...uwH..H... + 00f0 0f853a01 000062a1 ed0057d2 62a1ef00 ..:...b...W.b... + 0100 10ca62b1 ef0010d2 0f1f8400 00000000 ..b............. + 0110 62d17e00 5a048bc5 fb10c862 d17e005a b.~.Z......b.~.Z + 0120 048a48ff c1c4e2f1 b9d04939 c97fe162 ..H.......I9...b + 0130 f1f70058 d2488b44 24086448 2b042528 ...X.H.D$.dH+.%( + 0140 0000000f 855e0100 004883c4 185b5d41 .....^...H...[]A + 0150 5cc5eb10 c2415dc3 0f1f8400 00000000 \....A]......... + 0160 4c89c848 83e0fe0f 842b0100 004c8d24 L..H.....+...L.$ + 0170 364f8d2c 004a8d2c c5000000 004c89d9 6O.,.J.,.....L.. + 0180 488d1cf5 00000000 4c89d2c5 e957d231 H.......L....W.1 + 0190 ff0f1f80 00000000 62f17e00 5a0a62f1 ........b.~.Z.b. + 01a0 7e005a24 b2c5f310 d962b17e 005a0c81 ~.Z$.....b.~.Z.. + 01b0 c5f359cc 62f17e00 5a014883 c7024801 ..Y.b.~.Z.H...H. + 01c0 e94801da c4e2f199 c3c5eb58 d04839f8 .H.........X.H9. + 01d0 7fc648ff c848d1e8 48ffc04c 0fafe04c ..H..H..H..L...L + 01e0 0fafe848 01c04939 c10f8e46 ffffff49 ...H..I9...F...I + 01f0 c1e0024b 8d0cab48 c1e6024b 8d14a290 ...K...H...K.... + 0200 62f17e00 5a0148ff c0c5fb10 c84c01c1 b.~.Z.H......L.. + 0210 62f17e00 5a024801 f2c4e2f1 b9d04939 b.~.Z.H.......I9 + 0220 c17fdde9 0dffffff 0f1f8400 00000000 ................ + 0230 62a1ed00 57d24c89 de4c89d7 62a1ef00 b...W.L..L..b... + 0240 10ca31db 488d6c24 040f1f80 00000000 ..1.H.l$........ + 0250 4889ea48 83c320e8 a4fdffff 62f17e00 H..H.. .....b.~. + 0260 5a442401 4883ef80 62e1f700 58c8c744 ZD$.H...b...X..D + 0270 24040000 00004883 ee804839 d97fd162 $.....H...H9...b + 0280 b1ef0010 d24939c9 0f8f74fe ffffe99c .....I9...t..... + 0290 feffff0f 1f440000 4531ed45 31e4c5e9 .....D..E1.E1... + 02a0 57d2e948 ffffffe8 00000000 W..H........ /usr/lib64/libopenblas_openmp.a/sdsdot_k_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/sdsdot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sdsdot_k_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 19000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39000000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/sdsdot_k_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/sdsdot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sdsdot_k_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 f1010000 0002710e 10860246 ..........q....F - 0030 0d06478e 038d048c 05830602 bd0c0708 ..G............. - 0040 45c3c6cc cdce029a 0c061083 0686028c E............... - 0050 058d048e 034f0c07 08c3c6cc cdce0000 .....O.......... + 0010 1b0c0708 90010000 10000000 1c000000 ................ + 0020 00000000 9a000000 00000000 38000000 ............8... + 0030 30000000 00000000 0c020000 00420e10 0............B.. + 0040 8d02460e 188c0341 0e208604 410e2883 ..F....A. ..A.(. + 0050 05440e40 029f0a0e 28410e20 410e1842 .D.@....(A. A..B + 0060 0e10460e 08490b00 ..F..I.. /usr/lib64/libopenblas_openmp.a/sdsdot_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sdsdot_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sdsdot_k_SKYLAKEX.o (disasm) @@ -4,134 +4,163 @@ Disassembly of section .text: +sdot_kernel_16.constprop.0: + mov %rdx,%r8 + xor %eax,%eax + mov $something,%edx + vxorps %ymm4,%ymm4,%ymm4 + vxorps %ymm5,%ymm5,%ymm5 + vxorps %ymm6,%ymm6,%ymm6 + vxorps %ymm7,%ymm7,%ymm7 + nopw offset(%rax,%rax,1) + vmovups (%rdi,%rax,4),%ymm12 + vmovups offset(%rdi,%rax,4),%ymm13 + vmovups offset(%rdi,%rax,4),%ymm14 + vmovups offset(%rdi,%rax,4),%ymm15 + vfmadd231ps (%rsi,%rax,4),%ymm12,%ymm4 + vfmadd231ps offset(%rsi,%rax,4),%ymm13,%ymm5 + vfmadd231ps offset(%rsi,%rax,4),%ymm14,%ymm6 + vfmadd231ps offset(%rsi,%rax,4),%ymm15,%ymm7 + vextractf128 $something,%ymm4,%xmm12 + vextractf128 $something,%ymm5,%xmm13 + vextractf128 $something,%ymm6,%xmm14 + vextractf128 $something,%ymm7,%xmm15 + vaddps %xmm4,%xmm12,%xmm4 + vaddps %xmm5,%xmm13,%xmm5 + vaddps %xmm6,%xmm14,%xmm6 + vaddps %xmm7,%xmm15,%xmm7 + vaddps %xmm4,%xmm5,%xmm4 + vaddps %xmm6,%xmm7,%xmm6 + vaddps %xmm4,%xmm6,%xmm4 + vhaddps %xmm4,%xmm4,%xmm4 + vhaddps %xmm4,%xmm4,%xmm4 + vmovss %xmm4,(%r8) + vzeroupper + vzeroupper + ret + nopw offset(%rax,%rax,1) + sdsdot_k_SKYLAKEX: + push %r13 + vxorpd %xmm2,%xmm2,%xmm2 + push %r12 + push %rbp + push %rbx + sub $something,%rsp + mov %fs:0x28,%rax + mov %rax,offset(%rsp) + xor %eax,%eax + movl $something,offset(%rsp) test %rdi,%rdi jle - mov %rsi,%r9 - mov %rcx,%r10 + mov %rsi,%r10 + mov %rdi,%r9 mov %rdx,%rsi - vxorps %xmm1,%xmm1,%xmm1 + mov %rcx,%r11 + vxorps %xmm16,%xmm16,%xmm16 cmp $something,%rdx jne cmp $something,%r8 jne - mov %rdi,%rax - and $something,%rax + mov %rdi,%rcx + and $something,%rcx jne - vxorpd %xmm7,%xmm7,%xmm7 - vmovsd %xmm7,%xmm7,%xmm3 - vmovsd %xmm7,%xmm7,%xmm4 + vxorpd %xmm18,%xmm18,%xmm18 + vmovsd %xmm18,%xmm18,%xmm17 + vmovsd %xmm18,%xmm18,%xmm2 nopl offset(%rax,%rax,1) - vcvtss2sd (%r10,%rax,4),%xmm1,%xmm0 - vmovsd %xmm0,%xmm0,%xmm2 - vcvtss2sd (%r9,%rax,4),%xmm1,%xmm0 - inc %rax - vfmadd231sd %xmm0,%xmm2,%xmm4 - cmp %rax,%rdi + vcvtss2sd (%r11,%rcx,4),%xmm16,%xmm0 + vmovsd %xmm0,%xmm0,%xmm1 + vcvtss2sd (%r10,%rcx,4),%xmm16,%xmm0 + inc %rcx + vfmadd231sd %xmm0,%xmm1,%xmm2 + cmp %rcx,%r9 jg - vaddsd %xmm4,%xmm3,%xmm3 - vmovsd %xmm3,%xmm3,%xmm0 + vaddsd %xmm2,%xmm17,%xmm2 + mov offset(%rsp),%rax + sub %fs:0x28,%rax + jne + add $something,%rsp + pop %rbx + pop %rbp + pop %r12 + vmovsd %xmm2,%xmm2,%xmm0 + pop %r13 ret - cs nopw offset(%rax,%rax,1) - push %rbp - mov %rdi,%rax - mov %rsp,%rbp - push %r14 - push %r13 - push %r12 - push %rbx + nopl offset(%rax,%rax,1) + mov %r9,%rax and $something,%rax je - lea (%rsi,%rsi,1),%r13 - lea (%r8,%r8,1),%r14 - lea offset(,%r8,8),%r12 - mov %r10,%rcx + lea (%rsi,%rsi,1),%r12 + lea (%r8,%r8,1),%r13 + lea offset(,%r8,8),%rbp + mov %r11,%rcx lea offset(,%rsi,8),%rbx - mov %r9,%rdx - vxorpd %xmm3,%xmm3,%xmm3 - xor %r11d,%r11d - nopl (%rax) - vcvtss2sd (%rdx),%xmm1,%xmm2 - vcvtss2sd (%rdx,%rsi,4),%xmm1,%xmm5 - vmovsd %xmm2,%xmm2,%xmm4 - vcvtss2sd (%rcx,%r8,4),%xmm1,%xmm2 - vmulsd %xmm5,%xmm2,%xmm2 - vcvtss2sd (%rcx),%xmm1,%xmm0 - add $something,%r11 - add %r12,%rcx + mov %r10,%rdx + vxorpd %xmm2,%xmm2,%xmm2 + xor %edi,%edi + nopl offset(%rax) + vcvtss2sd (%rdx),%xmm16,%xmm1 + vcvtss2sd (%rdx,%rsi,4),%xmm16,%xmm4 + vmovsd %xmm1,%xmm1,%xmm3 + vcvtss2sd (%rcx,%r8,4),%xmm16,%xmm1 + vmulsd %xmm4,%xmm1,%xmm1 + vcvtss2sd (%rcx),%xmm16,%xmm0 + add $something,%rdi + add %rbp,%rcx add %rbx,%rdx - vfmadd132sd %xmm4,%xmm2,%xmm0 - vaddsd %xmm0,%xmm3,%xmm3 - cmp %r11,%rax + vfmadd132sd %xmm3,%xmm1,%xmm0 + vaddsd %xmm0,%xmm2,%xmm2 + cmp %rdi,%rax jg dec %rax shr %rax inc %rax + imul %rax,%r12 imul %rax,%r13 - imul %rax,%r14 add %rax,%rax - cmp %rax,%rdi + cmp %rax,%r9 jle shl $something,%r8 - lea (%r10,%r14,4),%rcx + lea (%r11,%r13,4),%rcx shl $something,%rsi - lea (%r9,%r13,4),%rdx - nopl offset(%rax) - vcvtss2sd (%rcx),%xmm1,%xmm0 + lea (%r10,%r12,4),%rdx + nop + vcvtss2sd (%rcx),%xmm16,%xmm0 inc %rax - vmovsd %xmm0,%xmm0,%xmm2 + vmovsd %xmm0,%xmm0,%xmm1 add %r8,%rcx - vcvtss2sd (%rdx),%xmm1,%xmm0 + vcvtss2sd (%rdx),%xmm16,%xmm0 add %rsi,%rdx - vfmadd231sd %xmm0,%xmm2,%xmm3 - cmp %rax,%rdi + vfmadd231sd %xmm0,%xmm1,%xmm2 + cmp %rax,%r9 jg - pop %rbx - pop %r12 - pop %r13 - pop %r14 - vmovsd %xmm3,%xmm3,%xmm0 - pop %rbp - ret - nopl offset(%rax) - vxorpd %xmm3,%xmm3,%xmm3 - vmovsd %xmm3,%xmm3,%xmm0 /usr/lib64/libopenblas_openmp.a/sdsdot_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sdsdot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sdsdot_k_SKYLAKEX.o (objdump) @@ -2,35 +2,46 @@ /usr/lib64/libopenblas_openmp.a/sdsdot_k_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 4885ff0f 8e370100 004989f1 4989ca48 H....7...I..I..H - 0010 89d6c5f0 57c94883 fa017554 4983f801 ....W.H...uTI... - 0020 754e4889 f84883e0 e00f8521 010000c5 uNH..H.....!.... - 0030 c157ffc5 c310dfc5 c310e70f 1f440000 .W...........D.. - 0040 c4c1725a 0482c5fb 10d0c4c1 725a0481 ..rZ........rZ.. - 0050 48ffc0c4 e2e9b9e0 4839c77f e3c5e358 H.......H9.....X - 0060 dcc5e310 c3c3662e 0f1f8400 00000000 ......f......... - 0070 554889f8 4889e541 56415541 54534883 UH..H..AVAUATSH. - 0080 e0fe0f84 52010000 4c8d2c36 4f8d3400 ....R...L.,6O.4. - 0090 4e8d24c5 00000000 4c89d148 8d1cf500 N.$.....L..H.... - 00a0 0000004c 89cac5e1 57db4531 db0f1f00 ...L....W.E1.... - 00b0 c5f25a12 c5f25a2c b2c5eb10 e2c4a172 ..Z...Z,.......r - 00c0 5a1481c5 eb59d5c5 f25a0149 83c3024c Z....Y...Z.I...L - 00d0 01e14801 dac4e2e9 99c4c5e3 58d84c39 ..H.........X.L9 - 00e0 d87fcd48 ffc848d1 e848ffc0 4c0fafe8 ...H..H..H..L... - 00f0 4c0faff0 4801c048 39c77e33 49c1e002 L...H..H9.~3I... - 0100 4b8d0cb2 48c1e602 4b8d14a9 0f1f4000 K...H...K.....@. - 0110 c5f25a01 48ffc0c5 fb10d04c 01c1c5f2 ..Z.H......L.... - 0120 5a024801 f2c4e2e9 b9d84839 c77fe15b Z.H.......H9...[ - 0130 415c415d 415ec5e3 10c35dc3 0f1f4000 A\A]A^....]...@. - 0140 c5e157db c5e310c3 c30f1f80 00000000 ..W............. - 0150 c5c157ff c5d857e4 c5c310df 31d26690 ..W...W.....1.f. - 0160 c4c17c10 1491c4c1 7c107491 20c4c25d ..|.....|.t. ..] - 0170 981492c4 c25d9874 9220c4c1 7c106c91 .....].t. ..|.l. - 0180 40c4c17c 10449260 c4c25d98 6c9240c4 @..|.D.`..].l.@. - 0190 c25d9844 9160c5ec 58d64883 c220c5ec .].D.`..X.H.. .. - 01a0 58d5c5fc 58c2c5f8 28d0c4e3 7d19c001 X...X...(...}... - 01b0 c5e858d0 c5eb7cd2 c5eb7cd2 c5ea5ad2 ..X...|...|...Z. - 01c0 c5e358da 4839d07f 97c5c310 e74839c7 ..X.H9.......H9. - 01d0 7e17c5f8 77e95dfe ffff4531 f64531ed ~...w.]...E1.E1. - 01e0 c5e157db e913ffff ffc5f877 e96cfeff ..W........w.l.. - 01f0 ff . + 0000 4989d031 c0ba2000 0000c5dc 57e4c5d4 I..1.. .....W... + 0010 57edc5cc 57f6c5c4 57ff660f 1f440000 W...W...W.f..D.. + 0020 c57c1024 87c57c10 6c8720c5 7c107487 .|.$..|.l. .|.t. + 0030 40c57c10 7c8760c4 e21db824 86c4e215 @.|.|.`....$.... + 0040 b86c8620 c4e20db8 748640c4 e205b87c .l. ....t.@....| + 0050 8660c4c3 7d19e401 c4c37d19 ed01c4c3 .`..}.....}..... + 0060 7d19f601 c4c37d19 ff01c598 58e4c590 }.....}.....X... + 0070 58edc588 58f6c580 58ffc5d0 58e4c5c0 X...X...X...X... + 0080 58f6c5c8 58e4c5db 7ce4c5db 7ce4c4c1 X...X...|...|... + 0090 7a1120c5 f877c5f8 77c3660f 1f440000 z. ..w..w.f..D.. + 00a0 4155c5e9 57d24154 55534883 ec186448 AU..W.ATUSH...dH + 00b0 8b042528 00000048 89442408 31c0c744 ..%(...H.D$.1..D + 00c0 24040000 00004885 ff7e6a49 89f24989 $.....H..~jI..I. + 00d0 f94889d6 4989cb62 a17c0057 c04883fa .H..I..b.|.W.H.. + 00e0 01757d49 83f80175 774889f9 4883e1e0 .u}I...uwH..H... + 00f0 0f853a01 000062a1 ed0057d2 62a1ef00 ..:...b...W.b... + 0100 10ca62b1 ef0010d2 0f1f8400 00000000 ..b............. + 0110 62d17e00 5a048bc5 fb10c862 d17e005a b.~.Z......b.~.Z + 0120 048a48ff c1c4e2f1 b9d04939 c97fe162 ..H.......I9...b + 0130 f1f70058 d2488b44 24086448 2b042528 ...X.H.D$.dH+.%( + 0140 0000000f 855e0100 004883c4 185b5d41 .....^...H...[]A + 0150 5cc5eb10 c2415dc3 0f1f8400 00000000 \....A]......... + 0160 4c89c848 83e0fe0f 842b0100 004c8d24 L..H.....+...L.$ + 0170 364f8d2c 004a8d2c c5000000 004c89d9 6O.,.J.,.....L.. + 0180 488d1cf5 00000000 4c89d2c5 e957d231 H.......L....W.1 + 0190 ff0f1f80 00000000 62f17e00 5a0a62f1 ........b.~.Z.b. + 01a0 7e005a24 b2c5f310 d962b17e 005a0c81 ~.Z$.....b.~.Z.. + 01b0 c5f359cc 62f17e00 5a014883 c7024801 ..Y.b.~.Z.H...H. + 01c0 e94801da c4e2f199 c3c5eb58 d04839f8 .H.........X.H9. + 01d0 7fc648ff c848d1e8 48ffc04c 0fafe04c ..H..H..H..L...L + 01e0 0fafe848 01c04939 c10f8e46 ffffff49 ...H..I9...F...I + 01f0 c1e0024b 8d0cab48 c1e6024b 8d14a290 ...K...H...K.... + 0200 62f17e00 5a0148ff c0c5fb10 c84c01c1 b.~.Z.H......L.. + 0210 62f17e00 5a024801 f2c4e2f1 b9d04939 b.~.Z.H.......I9 + 0220 c17fdde9 0dffffff 0f1f8400 00000000 ................ + 0230 62a1ed00 57d24c89 de4c89d7 62a1ef00 b...W.L..L..b... + 0240 10ca31db 488d6c24 040f1f80 00000000 ..1.H.l$........ + 0250 4889ea48 83c320e8 a4fdffff 62f17e00 H..H.. .....b.~. + 0260 5a442401 4883ef80 62e1f700 58c8c744 ZD$.H...b...X..D + 0270 24040000 00004883 ee804839 d97fd162 $.....H...H9...b + 0280 b1ef0010 d24939c9 0f8f74fe ffffe99c .....I9...t..... + 0290 feffff0f 1f440000 4531ed45 31e4c5e9 .....D..E1.E1... + 02a0 57d2e948 ffffffe8 00000000 W..H........ /usr/lib64/libopenblas_openmp.a/sdsdot_k_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/sdsdot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sdsdot_k_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 19000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39000000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/sdsdot_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/sdsdot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sdsdot_k_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 f1010000 0002710e 10860246 ..........q....F - 0030 0d06478e 038d048c 05830602 bd0c0708 ..G............. - 0040 45c3c6cc cdce029a 0c061083 0686028c E............... - 0050 058d048e 034f0c07 08c3c6cc cdce0000 .....O.......... + 0010 1b0c0708 90010000 10000000 1c000000 ................ + 0020 00000000 9a000000 00000000 38000000 ............8... + 0030 30000000 00000000 0c020000 00420e10 0............B.. + 0040 8d02460e 188c0341 0e208604 410e2883 ..F....A. ..A.(. + 0050 05440e40 029f0a0e 28410e20 410e1842 .D.@....(A. A..B + 0060 0e10460e 08490b00 ..F..I.. /usr/lib64/libopenblas_openmp.a/setparam_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/setparam_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/setparam_COOPERLAKE.o (disasm) @@ -12,84 +12,88 @@ shr $something,%ecx je mov offset(%rip),%rax # - movabs $something,%rdi - mov %rdi,offset(%rax) - movabs $something,%rdi - mov %rdi,offset(%rax) - movabs $something,%rdi - mov %rdi,offset(%rax) + movabs $something,%rdx mov offset(%rax),%edi mov offset(%rax),%r9d - movabs $something,%rsi - movabs $something,%rdx - mov %rsi,offset(%rax) + movabs $something,%rcx mov %edi,%r8d - movabs $something,%rsi not %r8d mov %rdx,offset(%rax) - mov %rsi,offset(%rax) + mov %rcx,offset(%rax) + mov %rdx,offset(%rax) + mov %rcx,offset(%rax) mov %rdx,offset(%rax) - mov $something,%esi + mov $something,%ecx + lea offset(%r9,%rdi,1),%edx + and %r8d,%edx + mov %ecx,%esi + sub %edx,%esi + movslq %esi,%rdx + imul $something,%rdx,%rdx + sar $something,%esi + mov %ecx,%r10d + sar $something,%rdx + sub %esi,%edx + sub $something,%edx + and $something,%edx + mov %edx,offset(%rax) + lea offset(%r9,%rdi,1),%edx + and %r8d,%edx + mov %ecx,%esi + sub %edx,%esi + lea offset(%rsi),%edx + cmovns %esi,%edx + movabs $something,%rbx + sar $something,%edx + sub $something,%edx + and $something,%edx + mov %edx,offset(%rax) + lea offset(%r9,%rdi,1),%edx + and %r8d,%edx + sub %edx,%r10d + lea offset(%r10),%edx + cmovns %r10d,%edx + mov %ecx,%r10d + sar $something,%edx + sub $something,%edx + and $something,%edx + mov %edx,offset(%rax) lea offset(%r9,%rdi,1),%edx and %r8d,%edx - mov %esi,%r10d sub %edx,%r10d movslq %r10d,%rdx imul $something,%rdx,%rdx sar $something,%r10d - movl $something,offset(%rax) - mov %rdx,%rbx - sar $something,%rbx - mov %rbx,%rcx - sub %r10d,%ecx - sub $something,%ecx - and $something,%ecx - mov %ecx,offset(%rax) - lea offset(%r9,%rdi,1),%ecx - and %r8d,%ecx - mov %esi,%ebx - sub %ecx,%ebx - movslq %ebx,%rcx - imul $something,%rcx,%rcx - sar $something,%ebx - mov %rcx,%r11 - sar $something,%rcx - sub %ebx,%ecx - sar $something,%r11 - sub %ebx,%r11d - sub $something,%ecx - and $something,%ecx - sub $something,%r11d - and $something,%r11d - mov %ecx,offset(%rax) - lea offset(%r9,%rdi,1),%ecx - mov %r11d,offset(%rax) - and %r8d,%ecx - mov %esi,%r11d - sub %ecx,%r11d - lea offset(%r11),%ecx - cmovns %r11d,%ecx + mov %rbx,offset(%rax) sar $something,%rdx sub %r10d,%edx sub $something,%edx and $something,%edx mov %edx,offset(%rax) - sar $something,%ecx lea offset(%r9,%rdi,1),%edx - sub $something,%ecx and %r8d,%edx - and $something,%ecx - sub %edx,%esi + sub %edx,%ecx + movslq %ecx,%rdx + imul $something,%rdx,%rdx + sar $something,%ecx + movabs $something,%rbx + sar $something,%rdx + sub %ecx,%edx + sub $something,%edx + and $something,%edx + mov %edx,offset(%rax) + test %esi,%esi lea offset(%rsi),%edx cmovns %esi,%edx - mov %ecx,offset(%rax) + movl $something,offset(%rax) sar $something,%edx sub $something,%edx and $something,%edx + mov %rbx,offset(%rax) mov %edx,offset(%rax) pop %rbx ret - nopl offset(%rax) + cs nopw offset(%rax,%rax,1) mov offset(%rip),%rax # mov $something,%edx mov (%rax),%rcx /usr/lib64/libopenblas_openmp.a/setparam_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/setparam_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/setparam_COOPERLAKE.o (objdump) @@ -3,29 +3,30 @@ Contents of section .text: 0000 53b80600 0080b900 0000000f a2c1e910 S............... - 0010 0f847201 0000488b 05000000 0048bf80 ..r...H......H.. - 0020 02000040 01000048 89b8a002 000048bf ...@...H......H. - 0030 c0000000 80010000 4889b820 05000048 ........H.. ...H - 0040 bf000100 00800000 004889b8 080c0000 .........H...... - 0050 8b780c44 8b480448 be800100 00c00000 .x.D.H.H........ - 0060 0048ba00 01000000 01000048 89b09007 .H.........H.... - 0070 00004189 f848be40 01000040 01000041 ..A..H.@...@...A - 0080 f7d04889 50104889 b0b80a00 00488990 ..H.P.H......H.. - 0090 300f0000 be000000 08418d94 3900800c 0........A..9... - 00a0 004421c2 4189f241 29d24963 d24869d2 .D!.A..A).Ic.Hi. - 00b0 67666666 41c1fa1f c7401800 01000048 gfffA....@.....H - 00c0 89d348c1 fb294889 d94429d1 83e90f83 ..H..)H..D)..... - 00d0 e1f08988 a8020000 418d8c39 00000900 ........A..9.... - 00e0 4421c189 f329cb48 63cb4869 c9abaaaa D!...).Hc.Hi.... - 00f0 2ac1fb1f 4989cb48 c1f92829 d949c1fb *...I..H..().I.. - 0100 294129db 83e90f83 e1f04183 eb0f4183 )A).......A...A. - 0110 e3f08988 98070000 418d8c39 00000800 ........A..9.... - 0120 44899828 05000044 21c14189 f34129cb D..(...D!.A..A). - 0130 418d8bff 07000041 0f49cb48 c1fa2a44 A......A.I.H..*D - 0140 29d283ea 0f83e2f0 8990c00a 0000c1f9 )............... - 0150 0b418d94 39000010 0083e90f 4421c283 .A..9.......D!.. - 0160 e1f029d6 8d96ff0f 00000f49 d6898810 ..)........I.... - 0170 0c0000c1 fa0c83ea 0f83e2f0 8990380f ..............8. - 0180 00005bc3 0f1f4000 488b0500 000000ba ..[...@.H....... - 0190 57000000 488b08be 01000000 488d3d00 W...H.......H.=. - 01a0 000000e8 00000000 e969feff ff .........i... + 0010 0f847a01 0000488b 05000000 0048ba00 ..z...H......H.. + 0020 01000000 0100008b 780c448b 480448b9 ........x.D.H.H. + 0030 40010000 40010000 4189f841 f7d04889 @...@...A..A..H. + 0040 50104889 88a00200 00488990 90070000 P.H......H...... + 0050 488988b8 0a000048 8990300f 0000b900 H......H..0..... + 0060 00000841 8d943900 40060044 21c289ce ...A..9.@..D!... + 0070 29d64863 d64869d2 67666666 c1fe1f41 ).Hc.Hi.gfff...A + 0080 89ca48c1 fa2929f2 83ea0f83 e2f08990 ..H..))......... + 0090 a8020000 418d9439 00001000 4421c289 ....A..9....D!.. + 00a0 ce29d68d 96ff0700 000f49d6 48bb0002 .)........I.H... + 00b0 00000001 0000c1fa 0b83ea0f 83e2f089 ................ + 00c0 90280500 00418d94 39000008 004421c2 .(...A..9....D!. + 00d0 4129d241 8d92ff07 0000410f 49d24189 A).A......A.I.A. + 00e0 cac1fa0b 83ea0f83 e2f08990 98070000 ................ + 00f0 418d9439 00000900 4421c241 29d24963 A..9....D!.A).Ic + 0100 d24869d2 abaaaa2a 41c1fa1f 48899820 .Hi....*A...H.. + 0110 05000048 c1fa2944 29d283ea 0f83e2f0 ...H..)D)....... + 0120 8990100c 0000418d 94390080 0c004421 ......A..9....D! + 0130 c229d148 63d14869 d2676666 66c1f91f .).Hc.Hi.gfff... + 0140 48bbc000 0000c000 000048c1 fa2a29ca H.........H..*). + 0150 83ea0f83 e2f08990 c00a0000 85f68d96 ................ + 0160 ff0f0000 0f49d6c7 40180001 0000c1fa .....I..@....... + 0170 0c83ea0f 83e2f048 8998080c 00008990 .......H........ + 0180 380f0000 5bc3662e 0f1f8400 00000000 8...[.f......... + 0190 488b0500 000000ba 57000000 488b08be H.......W...H... + 01a0 01000000 488d3d00 000000e8 00000000 ....H.=......... + 01b0 e961feff ff .a... /usr/lib64/libopenblas_openmp.a/setparam_COOPERLAKE.o differs in ELF section .data.rel --- old /usr/lib64/libopenblas_openmp.a/setparam_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/setparam_COOPERLAKE.o (objdump) @@ -44,8 +44,8 @@ 0270 00000000 00000000 00000000 00000000 ................ 0280 00000000 00000000 00000000 00000000 ................ 0290 00000000 00000000 00000000 00000000 ................ - 02a0 00000000 00000000 00000000 10000000 ................ - 02b0 04000000 20000000 00000000 00000000 .... ........... + 02a0 00000000 00000000 00000000 08000000 ................ + 02b0 04000000 08000000 00000000 00000000 ................ 02c0 00000000 00000000 00000000 00000000 ................ 02d0 00000000 00000000 00000000 00000000 ................ 02e0 00000000 00000000 00000000 00000000 ................ @@ -84,8 +84,8 @@ 04f0 00000000 00000000 00000000 00000000 ................ 0500 00000000 00000000 00000000 00000000 ................ 0510 00000000 00000000 00000000 00000000 ................ - 0520 00000000 00000000 00000000 10000000 ................ - 0530 02000000 20000000 00000000 00000000 .... ........... + 0520 00000000 00000000 00000000 04000000 ................ + 0530 08000000 08000000 00000000 00000000 ................ 0540 00000000 00000000 00000000 00000000 ................ 0550 00000000 00000000 00000000 00000000 ................ 0560 00000000 00000000 00000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/setparam_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/setparam_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/setparam_COOPERLAKE.o (objdump) @@ -4,5 +4,5 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 1c000000 1c000000 ................ - 0020 00000000 ad010000 00410e10 83020382 .........A...... - 0030 010a0e08 450b0000 ....E... + 0020 00000000 b5010000 00410e10 83020384 .........A...... + 0030 010a0e08 4b0b0000 ....K... /usr/lib64/libopenblas_openmp.a/setparam_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/setparam_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/setparam_SKYLAKEX.o (disasm) @@ -12,92 +12,88 @@ shr $something,%ecx je mov offset(%rip),%rax # - movabs $something,%rsi - mov %rsi,offset(%rax) - movabs $something,%rsi - mov %rsi,offset(%rax) - mov offset(%rax),%esi - mov offset(%rax),%r8d movabs $something,%rdx - mov %esi,%edi - not %edi - mov $something,%ecx + mov offset(%rax),%edi + mov offset(%rax),%r9d + movabs $something,%rcx + mov %edi,%r8d + not %r8d + mov %rdx,offset(%rax) + mov %rcx,offset(%rax) mov %rdx,offset(%rax) + mov %rcx,offset(%rax) mov %rdx,offset(%rax) - lea offset(%r8,%rsi,1),%edx - and %edi,%edx - mov %ecx,%r9d - sub %edx,%r9d - movslq %r9d,%rdx + mov $something,%ecx + lea offset(%r9,%rdi,1),%edx + and %r8d,%edx + mov %ecx,%esi + sub %edx,%esi + movslq %esi,%rdx imul $something,%rdx,%rdx + sar $something,%esi mov %ecx,%r10d + sar $something,%rdx + sub %esi,%edx + sub $something,%edx + and $something,%edx + mov %edx,offset(%rax) + lea offset(%r9,%rdi,1),%edx + and %r8d,%edx + mov %ecx,%esi + sub %edx,%esi + lea offset(%rsi),%edx + cmovns %esi,%edx movabs $something,%rbx - shr $something,%rdx - add %r9d,%edx sar $something,%edx - sar $something,%r9d - sub %r9d,%edx sub $something,%edx and $something,%edx mov %edx,offset(%rax) - lea offset(%r8,%rsi,1),%edx - and %edi,%edx + lea offset(%r9,%rdi,1),%edx + and %r8d,%edx + sub %edx,%r10d + lea offset(%r10),%edx + cmovns %r10d,%edx + mov %ecx,%r10d + sar $something,%edx + sub $something,%edx + and $something,%edx + mov %edx,offset(%rax) + lea offset(%r9,%rdi,1),%edx + and %r8d,%edx sub %edx,%r10d movslq %r10d,%rdx imul $something,%rdx,%rdx - mov %rbx,offset(%rax) - movabs $something,%rbx - mov %rbx,offset(%rax) - movabs $something,%rbx - mov %rbx,offset(%rax) - mov %rdx,%rbx - sar $something,%rbx sar $something,%r10d + mov %rbx,offset(%rax) sar $something,%rdx - mov %rbx,%r9 sub %r10d,%edx - sub %r10d,%r9d - sub $something,%edx - and $something,%edx - sub $something,%r9d - and $something,%r9d - mov %edx,offset(%rax) - lea offset(%r8,%rsi,1),%edx - mov %r9d,offset(%rax) - and %edi,%edx - mov %ecx,%r9d - sub %edx,%r9d - lea offset(%r9),%edx - cmovns %r9d,%edx - mov %ecx,%r9d - sar $something,%edx sub $something,%edx and $something,%edx mov %edx,offset(%rax) - lea offset(%r8,%rsi,1),%edx - and %edi,%edx - sub %edx,%r9d - movslq %r9d,%rdx + lea offset(%r9,%rdi,1),%edx + and %r8d,%edx + sub %edx,%ecx + movslq %ecx,%rdx imul $something,%rdx,%rdx - sar $something,%r9d - movl $something,offset(%rax) + sar $something,%ecx + movabs $something,%rbx sar $something,%rdx - sub %r9d,%edx + sub %ecx,%edx sub $something,%edx and $something,%edx mov %edx,offset(%rax) - lea offset(%r8,%rsi,1),%edx - and %edi,%edx - sub %edx,%ecx - lea offset(%rcx),%edx - cmovns %ecx,%edx + test %esi,%esi + lea offset(%rsi),%edx + cmovns %esi,%edx + movl $something,offset(%rax) sar $something,%edx sub $something,%edx and $something,%edx + mov %rbx,offset(%rax) mov %edx,offset(%rax) pop %rbx ret - nopl offset(%rax,%rax,1) + cs nopw offset(%rax,%rax,1) mov offset(%rip),%rax # mov $something,%edx mov (%rax),%rcx /usr/lib64/libopenblas_openmp.a/setparam_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/setparam_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/setparam_SKYLAKEX.o (objdump) @@ -3,31 +3,30 @@ Contents of section .text: 0000 53b80600 0080b900 0000000f a2c1e910 S............... - 0010 0f849201 0000488b 05000000 0048be80 ......H......H.. - 0020 010000c0 00000048 89b09007 000048be .......H......H. - 0030 40010000 40010000 4889b0b8 0a00008b @...@...H....... - 0040 700c448b 400448ba 00010000 00010000 p.D.@.H......... - 0050 89f7f7d7 b9000000 08488950 10488990 .........H.P.H.. - 0060 300f0000 418d9430 00400c00 21fa4189 0...A..0.@..!.A. - 0070 c94129d1 4963d148 69d29324 49924189 .A).Ic.Hi..$I.A. - 0080 ca48bbc0 010000c0 01000048 c1ea2044 .H.........H.. D - 0090 01cac1fa 0a41c1f9 1f4429ca 83ea0f83 .....A...D)..... - 00a0 e2f08990 a8020000 418d9430 00000900 ........A..0.... - 00b0 21fa4129 d24963d2 4869d2ab aaaa2a48 !.A).Ic.Hi....*H - 00c0 8998a002 000048bb c0000000 80010000 ......H......... - 00d0 48899820 05000048 bb000100 00800000 H.. ...H........ - 00e0 00488998 080c0000 4889d348 c1fb2941 .H......H..H..)A - 00f0 c1fa1f48 c1fa2849 89d94429 d24529d1 ...H..(I..D).E). - 0100 83ea0f83 e2f04183 e90f4183 e1f08990 ......A...A..... - 0110 98070000 418d9430 00000800 44898828 ....A..0....D..( - 0120 05000021 fa4189c9 4129d141 8d91ff07 ...!.A..A).A.... - 0130 0000410f 49d14189 c9c1fa0b 83ea0f83 ..A.I.A......... - 0140 e2f08990 100c0000 418d9430 00800c00 ........A..0.... - 0150 21fa4129 d14963d1 4869d267 66666641 !.A).Ic.Hi.gfffA - 0160 c1f91fc7 40180001 000048c1 fa2a4429 ....@.....H..*D) - 0170 ca83ea0f 83e2f089 90c00a00 00418d94 .............A.. - 0180 30000010 0021fa29 d18d91ff 0f00000f 0....!.)........ - 0190 49d1c1fa 0c83ea0f 83e2f089 90380f00 I............8.. - 01a0 005bc30f 1f440000 488b0500 000000ba .[...D..H....... - 01b0 57000000 488b08be 01000000 488d3d00 W...H.......H.=. - 01c0 000000e8 00000000 e949feff ff .........I... + 0010 0f847a01 0000488b 05000000 0048ba00 ..z...H......H.. + 0020 01000000 0100008b 780c448b 480448b9 ........x.D.H.H. + 0030 40010000 40010000 4189f841 f7d04889 @...@...A..A..H. + 0040 50104889 88a00200 00488990 90070000 P.H......H...... + 0050 488988b8 0a000048 8990300f 0000b900 H......H..0..... + 0060 00000841 8d943900 40060044 21c289ce ...A..9.@..D!... + 0070 29d64863 d64869d2 67666666 c1fe1f41 ).Hc.Hi.gfff...A + 0080 89ca48c1 fa2929f2 83ea0f83 e2f08990 ..H..))......... + 0090 a8020000 418d9439 00001000 4421c289 ....A..9....D!.. + 00a0 ce29d68d 96ff0700 000f49d6 48bb0002 .)........I.H... + 00b0 00000001 0000c1fa 0b83ea0f 83e2f089 ................ + 00c0 90280500 00418d94 39000008 004421c2 .(...A..9....D!. + 00d0 4129d241 8d92ff07 0000410f 49d24189 A).A......A.I.A. + 00e0 cac1fa0b 83ea0f83 e2f08990 98070000 ................ + 00f0 418d9439 00000900 4421c241 29d24963 A..9....D!.A).Ic + 0100 d24869d2 abaaaa2a 41c1fa1f 48899820 .Hi....*A...H.. + 0110 05000048 c1fa2944 29d283ea 0f83e2f0 ...H..)D)....... + 0120 8990100c 0000418d 94390080 0c004421 ......A..9....D! + 0130 c229d148 63d14869 d2676666 66c1f91f .).Hc.Hi.gfff... + 0140 48bbc000 0000c000 000048c1 fa2a29ca H.........H..*). + 0150 83ea0f83 e2f08990 c00a0000 85f68d96 ................ + 0160 ff0f0000 0f49d6c7 40180001 0000c1fa .....I..@....... + 0170 0c83ea0f 83e2f048 8998080c 00008990 .......H........ + 0180 380f0000 5bc3662e 0f1f8400 00000000 8...[.f......... + 0190 488b0500 000000ba 57000000 488b08be H.......W...H... + 01a0 01000000 488d3d00 000000e8 00000000 ....H.=......... + 01b0 e961feff ff .a... /usr/lib64/libopenblas_openmp.a/setparam_SKYLAKEX.o differs in ELF section .data.rel --- old /usr/lib64/libopenblas_openmp.a/setparam_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/setparam_SKYLAKEX.o (objdump) @@ -44,8 +44,8 @@ 0270 00000000 00000000 00000000 00000000 ................ 0280 00000000 00000000 00000000 00000000 ................ 0290 00000000 00000000 00000000 00000000 ................ - 02a0 00000000 00000000 00000000 10000000 ................ - 02b0 04000000 20000000 00000000 00000000 .... ........... + 02a0 00000000 00000000 00000000 08000000 ................ + 02b0 04000000 08000000 00000000 00000000 ................ 02c0 00000000 00000000 00000000 00000000 ................ 02d0 00000000 00000000 00000000 00000000 ................ 02e0 00000000 00000000 00000000 00000000 ................ @@ -84,8 +84,8 @@ 04f0 00000000 00000000 00000000 00000000 ................ 0500 00000000 00000000 00000000 00000000 ................ 0510 00000000 00000000 00000000 00000000 ................ - 0520 00000000 00000000 00000000 10000000 ................ - 0530 02000000 20000000 00000000 00000000 .... ........... + 0520 00000000 00000000 00000000 04000000 ................ + 0530 08000000 08000000 00000000 00000000 ................ 0540 00000000 00000000 00000000 00000000 ................ 0550 00000000 00000000 00000000 00000000 ................ 0560 00000000 00000000 00000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/setparam_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/setparam_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/setparam_SKYLAKEX.o (objdump) @@ -4,5 +4,5 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 1c000000 1c000000 ................ - 0020 00000000 cd010000 00410e10 830203a1 .........A...... - 0030 010a0e08 460b0000 ....F... + 0020 00000000 b5010000 00410e10 83020384 .........A...... + 0030 010a0e08 4b0b0000 ....K... /usr/lib64/libopenblas_openmp.a/sgemm_direct_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sgemm_direct_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sgemm_direct_COOPERLAKE.o (disasm) @@ -5,1291 +5,4 @@ Disassembly of section .text: sgemm_direct_COOPERLAKE: - push %rbp - mov %rdi,%rax - mov %esi,%r10d - mov %rsp,%rbp - push %r15 - and $something,%r10d - push %r14 - mov %r9,%r14 - mov %esi,%r9d - push %r13 - and $something,%r9d - push %r12 - mov %esi,%r12d - and $something,%r12d - push %rbx - mov %esi,%ebx - and $something,%ebx - and $something,%rsp - sub $something,%rsp - mov %rdi,-offset(%rsp) - mov %rdx,%rdi - mov %rax,%rdx - and $something,%eax - mov %rsi,offset(%rsp) - mov %eax,-offset(%rsp) - mov %esi,%eax - and $something,%esi - mov %esi,offset(%rsp) - mov %edx,%esi - and $something,%eax - and $something,%esi - mov %rcx,-offset(%rsp) - mov %r8,offset(%rsp) - mov %ebx,offset(%rsp) - mov %r9d,offset(%rsp) - mov %r10d,offset(%rsp) - mov %r12d,offset(%rsp) - mov %eax,offset(%rsp) - mov %esi,offset(%rsp) - mov offset(%rbp),%r15 - jle - mov offset(%rbp),%rdx - mov %r8,%rax - add %rdx,%rdx - mov %rdx,offset(%rsp) - add offset(%rbp),%rdx - mov %rdx,offset(%rsp) - lea offset(,%rax,4),%rdx - mov offset(%rbp),%rsi - mov %rdx,(%rsp) - mov %ebx,-offset(%rsp) - lea (%rax,%rax,1),%rdx - movslq %ebx,%rbx - mov %rdx,offset(%rsp) - mov %rbx,-offset(%rsp) - add %rax,%rdx - lea -offset(%r9),%ebx - mov offset(%rsp),%eax - mov %rsi,offset(%rsp) - mov %ebx,-offset(%rsp) - shl $something,%rsi - lea -offset(%r10),%ebx - lea (%r15,%rsi,1),%r11 - mov %r8,offset(%rsp) - mov %rcx,offset(%rsp) - mov %rdx,offset(%rsp) - mov %ebx,-offset(%rsp) - shl $something,%r8 - lea -offset(%r12),%ebx - lea (%rcx,%rdi,4),%rdx - dec %eax - mov $something,%ecx - shlx %rcx,offset(%rbp),%rcx - lea (%r11,%rsi,1),%r13 - mov %rcx,offset(%rsp) - mov %r8,-offset(%rsp) - mov offset(%rbp),%rcx - movq $something,offset(%rsp) - movq $something,offset(%rsp) - movl $something,offset(%rsp) - mov %ebx,-offset(%rsp) - mov %eax,-offset(%rsp) - mov %rsi,-offset(%rsp) - add %r13,%rsi - mov %r14,offset(%rsp) - mov %r15,%r12 - shl $something,%rcx - vxorps %xmm9,%xmm9,%xmm9 - mov %rdi,%r14 - mov %rsi,%r15 - nopl offset(%rax,%rax,1) - mov offset(%rsp),%eax - xor %edi,%edi - xor %ebx,%ebx - test %eax,%eax - jle - mov offset(%rsp),%rax - mov offset(%rsp),%r9 - mov offset(%rsp),%r8 - mov offset(%rsp),%rdi - mov %r13,offset(%rsp) - mov %r13,offset(%rsp) - mov %r12,offset(%rsp) - mov %r12,%r10 - xor %esi,%esi - mov offset(%rsp),%r12 - mov %r15,offset(%rsp) - mov %r15,offset(%rsp) - mov %r11,offset(%rsp) - mov %r11,%rbx - sub %rax,%r9 - mov %r15,%r11 - sub %rax,%r8 - sub %rax,%rdi - mov %rsi,%r15 - nop - test %r14,%r14 - jle - vxorps %xmm24,%xmm24,%xmm24 - mov offset(%rsp),%rax - lea (%r12,%r15,4),%rsi - vmovaps %zmm24,%zmm23 - vmovaps %zmm24,%zmm22 - vmovaps %zmm24,%zmm21 - vmovaps %zmm24,%zmm20 - vmovaps %zmm24,%zmm19 - vmovaps %zmm24,%zmm18 - vmovaps %zmm24,%zmm17 - vmovaps %zmm24,%zmm16 - vmovaps %zmm24,%zmm15 - vmovaps %zmm24,%zmm14 - vmovaps %zmm24,%zmm13 - vmovaps %zmm24,%zmm12 - vmovaps %zmm24,%zmm11 - vmovaps %zmm24,%zmm10 - vmovaps %zmm24,%zmm8 - nopl (%rax) - vbroadcastss (%rax),%zmm7 - vbroadcastss (%rax,%r9,4),%zmm6 - vbroadcastss (%rax,%r8,4),%zmm5 - vbroadcastss (%rax,%rdi,4),%zmm1 - vmovups (%rsi),%zmm4 - vmovups offset(%rsi),%zmm3 - vmovups offset(%rsi),%zmm2 - vmovups offset(%rsi),%zmm0 - add $something,%rax - vfmadd231ps %zmm4,%zmm7,%zmm8 - vfmadd231ps %zmm3,%zmm7,%zmm10 - vfmadd231ps %zmm2,%zmm7,%zmm11 - vfmadd231ps %zmm0,%zmm7,%zmm12 - vfmadd231ps %zmm4,%zmm6,%zmm13 - vfmadd231ps %zmm3,%zmm6,%zmm14 - vfmadd231ps %zmm2,%zmm6,%zmm15 - vfmadd231ps %zmm0,%zmm6,%zmm16 - vfmadd231ps %zmm4,%zmm5,%zmm17 - vfmadd231ps %zmm3,%zmm5,%zmm18 - vfmadd231ps %zmm2,%zmm5,%zmm19 - vfmadd231ps %zmm0,%zmm5,%zmm20 - vfmadd231ps %zmm4,%zmm1,%zmm21 - vfmadd231ps %zmm3,%zmm1,%zmm22 - vfmadd231ps %zmm2,%zmm1,%zmm23 - vfmadd231ps %zmm0,%zmm1,%zmm24 - add %rcx,%rsi - cmp %rax,%rdx - jne - add $something,%r15 - vmovups %zmm8,(%r10) - vmovups %zmm10,offset(%r10) - vmovups %zmm11,offset(%r10) - vmovups %zmm12,offset(%r10) - add $something,%rbx - vmovups %zmm13,-offset(%rbx) - vmovups %zmm14,-offset(%rbx) - vmovups %zmm15,-offset(%rbx) - vmovups %zmm16,-offset(%rbx) - add $something,%r10 - vmovups %zmm17,offset(%r13) - vmovups %zmm18,offset(%r13) - vmovups %zmm19,offset(%r13) - vmovups %zmm20,offset(%r13) - add $something,%r11 - vmovups %zmm21,-offset(%r11) - vmovups %zmm22,-offset(%r11) - vmovups %zmm23,-offset(%r11) - vmovups %zmm24,-offset(%r11) - add $something,%r13 - cmp %r15d,offset(%rsp) - jg - mov offset(%rsp),%r15 - mov offset(%rsp),%r13 - mov offset(%rsp),%r11 - mov offset(%rsp),%r12 - mov -offset(%rsp),%rdi - mov -offset(%rsp),%ebx /usr/lib64/libopenblas_openmp.a/sgemm_direct_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sgemm_direct_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sgemm_direct_COOPERLAKE.o (objdump) @@ -2,390 +2,4 @@ /usr/lib64/libopenblas_openmp.a/sgemm_direct_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 554889f8 4189f248 89e54157 4183e2f0 UH..A..H..AWA... - 0010 41564d89 ce4189f1 41554183 e1e04154 AVM..A..AUA...AT - 0020 4189f441 83e4f853 89f383e3 c04883e4 A..A...S.....H.. - 0030 c04881ec c8000000 48897c24 c04889d7 .H......H.|$.H.. - 0040 4889c283 e0fe4889 b4249000 00008944 H.....H..$.....D - 0050 24d089f0 83e6fe89 b424b000 000089d6 $........$...... - 0060 83e0fc83 e6fc4889 4c24c84c 89442460 ......H.L$.L.D$` - 0070 899c24a8 00000044 898c24a4 00000044 ..$....D..$....D - 0080 899424a0 00000044 89a4249c 00000089 ..$....D..$..... - 0090 8424ac00 000089b4 24980000 004c8b7d .$......$....L.} - 00a0 180f8e6b 17000048 8b55204c 89c04801 ...k...H.U L..H. - 00b0 d2488954 24484803 55204889 54245048 .H.T$HH.U H.T$PH - 00c0 8d148500 00000048 8b752048 89142489 .......H.u H..$. - 00d0 5c24ec48 8d140048 63db4889 54247848 \$.H...Hc.H.T$xH - 00e0 895c24e0 4801c241 8d59ff8b 8424ac00 .\$.H..A.Y...$.. - 00f0 00004889 74244089 5c24e848 c1e60241 ..H.t$@.\$.H...A - 0100 8d5aff4d 8d1c374c 89442470 48898c24 .Z.M..7L.D$pH..$ - 0110 c0000000 48899424 80000000 895c24dc ....H..$.....\$. - 0120 49c1e004 418d5c24 ff488d14 b9ffc8b9 I...A.\$.H...... - 0130 04000000 c4e2f1f7 4d204d8d 2c334889 ........M M.,3H. - 0140 4c24084c 894424f8 488b4d10 48c74424 L$.L.D$.H.M.H.D$ - 0150 68000000 0048c784 24880000 00000000 h....H..$....... - 0160 00c74424 58000000 00895c24 d8894424 ..D$X.....\$..D$ - 0170 d4488974 24f04c01 ee4c89b4 24b80000 .H.t$.L..L..$... - 0180 004d89fc 48c1e102 c4413057 c94989fe .M..H....A0W.I.. - 0190 4989f70f 1f440000 8b8424a8 00000031 I....D....$....1 - 01a0 ff31db85 c00f8e2d 02000048 8b442468 .1.....-...H.D$h - 01b0 4c8b4c24 704c8b44 2478488b bc248000 L.L$pL.D$xH..$.. - 01c0 00004c89 6c24304c 896c2420 4c896424 ..L.l$0L.l$ L.d$ - 01d0 104d89e2 31f64c8b a424b800 00004c89 .M..1.L..$....L. - 01e0 7c24384c 897c2428 4c895c24 184c89db |$8L.|$(L.\$.L.. - 01f0 4929c14d 89fb4929 c04829c7 4989f790 I).M..I).H).I... - 0200 4d85f60f 8e8f1500 0062013c 0057c048 M........b.<.W.H - 0210 8b8424c0 0000004b 8d34bc62 817c4828 ..$....K.4.b.|H( - 0220 f862817c 4828f062 817c4828 e862817c .b.|H(.b.|H(.b.| - 0230 4828e062 817c4828 d862817c 4828d062 H(.b.|H(.b.|H(.b - 0240 817c4828 c862817c 4828c062 117c4828 .|H(.b.|H(.b.|H( - 0250 f862117c 4828f062 117c4828 e862117c .b.|H(.b.|H(.b.| - 0260 4828e062 117c4828 d862117c 4828d062 H(.b.|H(.b.|H(.b - 0270 117c4828 c00f1f00 62f27d48 183862b2 .|H(....b.}H.8b. - 0280 7d481834 8862b27d 48182c80 62f27d48 }H.4.b.}H.,.b.}H - 0290 180cb862 f17c4810 2662f17c 48105e01 ...b.|H.&b.|H.^. - 02a0 62f17c48 10560262 f17c4810 46034883 b.|H.V.b.|H.F.H. - 02b0 c0046272 4548b8c4 62724548 b8d36272 ..brEH..brEH..br - 02c0 4548b8da 62724548 b8e06272 4d48b8ec EH..brEH..brMH.. - 02d0 62724d48 b8f36272 4d48b8fa 62e24d48 brMH..brMH..b.MH - 02e0 b8c062e2 5548b8cc 62e25548 b8d362e2 ..b.UH..b.UH..b. - 02f0 5548b8da 62e25548 b8e062e2 7548b8ec UH..b.UH..b.uH.. - 0300 62e27548 b8f362e2 7548b8fa 62627548 b.uH..b.uH..bbuH - 0310 b8c04801 ce4839c2 0f855aff ffff4983 ..H..H9...Z...I. - 0320 c7406251 7c481102 62517c48 11520162 .@bQ|H..bQ|H.R.b - 0330 517c4811 5a026251 7c481162 034881c3 Q|H.Z.bQ|H.b.H.. - 0340 00010000 62717c48 116bfc62 717c4811 ....bq|H.k.bq|H. - 0350 73fd6271 7c48117b fe62e17c 481143ff s.bq|H.{.b.|H.C. - 0360 4981c200 01000062 c17c4811 4d0062c1 I......b.|H.M.b. - 0370 7c481155 0162c17c 48115d02 62c17c48 |H.U.b.|H.].b.|H - 0380 11650349 81c30001 000062c1 7c48116b .e.I......b.|H.k - 0390 fc62c17c 481173fd 62c17c48 117bfe62 .b.|H.s.b.|H.{.b - 03a0 417c4811 43ff4981 c5000100 004439bc A|H.C.I......D9. - 03b0 24a80000 000f8f45 feffff4c 8b7c2428 $......E...L.|$( - 03c0 4c8b6c24 204c8b5c 24184c8b 64241048 L.l$ L.\$.L.d$.H - 03d0 8b7c24e0 8b5c24ec 399c24a4 0000000f .|$..\$.9.$..... - 03e0 8e410100 00488b44 24684c8b 5424704c .A...H.D$hL.T$pL - 03f0 8b4c2478 4c8b8424 80000000 895c2438 .L$xL..$.....\$8 - 0400 4863fb48 8b9c24b8 00000049 29c24929 Hc.H..$....I).I) - 0410 c14929c0 0f1f4000 4d85f60f 8e3f1300 .I)...@.M....?.. - 0420 00c44108 57f6488b 8424c000 0000488d ..A.W.H..$....H. - 0430 34bb6251 7c4828ee 62517c48 28e66251 4.bQ|H(.bQ|H(.bQ - 0440 7c4828de 62517c48 28d66251 7c4828c6 |H(.bQ|H(.bQ|H(. - 0450 62d17c48 28fe62d1 7c4828f6 0f1f4000 b.|H(.b.|H(...@. - 0460 62f17c48 100e62f1 7c481046 0162f27d b.|H..b.|H.F.b.} - 0470 48182862 b27d4818 249062b2 7d48181c H.(b.}H.$.b.}H.. - 0480 8862b27d 48181480 4883c004 62f25548 .b.}H...H...b.UH - 0490 b8f162f2 5548b8f8 62725d48 b8c16272 ..b.UH..br]H..br - 04a0 5d48b8d0 62726548 b8d96272 6548b8e0 ]H..breH..breH.. - 04b0 62726d48 b8e96272 6d48b8f0 4801ce48 brmH..brmH..H..H - 04c0 39c2759c 62d17c48 1134bc62 d17c4811 9.u.b.|H.4.b.|H. - 04d0 7cbc0162 517c4811 04bb6251 7c481154 |..bQ|H...bQ|H.T - 04e0 bb016251 7c48115c bd006251 7c481164 ..bQ|H.\..bQ|H.d - 04f0 bd016251 7c48112c bf62517c 481174bf ..bQ|H.,.bQ|H.t. - 0500 014883c7 2039bc24 a4000000 0f8f06ff .H.. 9.$........ - 0510 ffff8b5c 24388b44 24e829d8 83e0e08d ...\$8.D$.)..... - 0520 5c032048 63fb399c 24a00000 000f8ed5 \. Hc.9.$....... - 0530 00000048 8b442468 4c8b4c24 704c8b44 ...H.D$hL.L$pL.D - 0540 2478488b bc248000 0000895c 24384c63 $xH..$.....\$8Lc - 0550 d3488b9c 24b80000 004929c1 4929c048 .H..$....I).I).H - 0560 29c7660f 1f440000 4d85f60f 8ecf1100 ).f..D..M....... - 0570 00c5d857 e4488b84 24c00000 004a8d34 ...W.H..$....J.4 - 0580 9362f17c 4828dc62 f17c4828 d462f17c .b.|H(.b.|H(.b.| - 0590 4828cc0f 1f440000 62f17c48 10064801 H(...D..b.|H..H. - 05a0 ce62f27d 58b80862 b27d58b8 148862b2 .b.}X..b.}X...b. - 05b0 7d58b81c 8062f27d 58b824b8 4883c004 }X...b.}X.$.H... - 05c0 4839c275 d362917c 48110c94 62917c48 H9.u.b.|H...b.|H - 05d0 11149362 917c4811 5c950062 917c4811 ...b.|H.\..b.|H. - 05e0 24974983 c2104439 9424a000 00000f8f $.I...D9.$...... - 05f0 74ffffff 8b5c2438 8b4424dc 29d883e0 t....\$8.D$.)... - 0600 f08d5c03 104863fb 399c249c 0000000f ..\..Hc.9.$..... - 0610 8ec10000 00488b44 24684c8b 4c24704c .....H.D$hL.L$pL - 0620 8b442478 488bbc24 80000000 895c2438 .D$xH..$.....\$8 - 0630 4c63d348 8b9c24b8 00000049 29c14929 Lc.H..$....I).I) - 0640 c04829c7 0f1f4000 4d85f60f 8ed71000 .H)...@.M....... - 0650 00c5d857 e4488b84 24c00000 004a8d34 ...W.H..$....J.4 - 0660 93c5fc28 dcc5fc28 d4c5fc28 cc0f1f00 ...(...(...(.... - 0670 c5fc1006 4801ce62 f27d38b8 0862b27d ....H..b.}8..b.} - 0680 38b81488 62b27d38 b81c8062 f27d38b8 8...b.}8...b.}8. - 0690 24b84883 c0044839 c275d5c4 817c110c $.H...H9.u...|.. - 06a0 94c4817c 111493c4 817c115c 9500c481 ...|.....|.\.... - 06b0 7c112497 4983c208 44399424 9c000000 |.$.I...D9.$.... - 06c0 7f868b5c 24388b44 24d829d8 83e0f88d ...\$8.D$.)..... - 06d0 5c030848 63fb399c 24ac0000 000f8ec3 \..Hc.9.$....... - 06e0 00000048 8b442468 4c8b4c24 704c8b44 ...H.D$hL.L$pL.D - 06f0 2478488b bc248000 0000895c 24384c63 $xH..$.....\$8Lc - 0700 d3488b9c 24b80000 004929c1 4929c048 .H..$....I).I).H - 0710 29c7660f 1f440000 4d85f60f 8e7f0f00 ).f..D..M....... - 0720 00c5d857 e4488b84 24c00000 004a8d34 ...W.H..$....J.4 - 0730 93c5f828 dcc5f828 d4c5f828 cc0f1f00 ...(...(...(.... - 0740 c5f81006 4801ce62 f27d18b8 0862b27d ....H..b.}...b.} - 0750 18b81488 62b27d18 b81c8062 f27d18b8 ....b.}....b.}.. - 0760 24b84883 c0044839 c275d5c4 8178110c $.H...H9.u...x.. - 0770 94c48178 111493c4 8178115c 9500c481 ...x.....x.\.... - 0780 78112497 4983c204 44399424 ac000000 x.$.I...D9.$.... - 0790 7f868b5c 24388b44 24d429d8 83e0fc8d ...\$8.D$.)..... - 07a0 5c030448 63fb399c 24b00000 000f8e27 \..Hc.9.$......' - 07b0 01000048 8b442468 4c8b5424 704c8b4c ...H.D$hL.T$pL.L - 07c0 24784c8b 84248000 0000895c 24384863 $xL..$.....\$8Hc - 07d0 fb488b9c 24b80000 004929c2 4929c149 .H..$....I).I).I - 07e0 29c0660f 1f440000 4d85f60f 8e7f0e00 ).f..D..M....... - 07f0 00488b84 24c00000 00488d34 bbc44178 .H..$....H.4..Ax - 0800 28f1c441 7828e9c4 417828e1 c4417828 (..Ax(..Ax(..Ax( - 0810 d9c44178 28d1c441 7828c1c5 7829cfc5 ..Ax(..Ax(..x).. - 0820 7829ce0f 1f440000 c5fa100e c5fa1046 x)...D.........F - 0830 04c5fa10 28c4a17a 102490c4 a17a101c ....(..z.$...z.. - 0840 88c4a17a 10148048 83c004c4 e251b9f1 ...z...H.....Q.. - 0850 c4e251b9 f8c46259 b9c1c462 59b9d0c4 ..Q...bY...bY... - 0860 6261b9d9 c46261b9 e0c46269 b9e9c462 ba...ba...bi...b - 0870 69b9f048 01ce4839 c275adc4 c17a1134 i..H..H9.u...z.4 - 0880 bcc4c17a 117cbc04 c4417a11 04bbc441 ...z.|...Az....A - 0890 7a1154bb 04c4417a 115cbd00 c4417a11 z.T...Az.\...Az. - 08a0 64bd04c4 417a112c bfc4417a 1174bf04 d...Az.,..Az.t.. - 08b0 4883c702 39bc24b0 0000000f 8f27ffff H...9.$......'.. - 08c0 ff8b8424 b0000000 8b5c2438 ffc829d8 ...$.....\$8..). - 08d0 83e0fe8d 5c030248 63fb4839 bc249000 ....\..Hc.H9.$.. - 08e0 00000f8e fe000000 488b4424 684c8b54 ........H.D$hL.T - 08f0 24704c8b 4c24784c 8b842480 0000004c $pL.L$xL..$....L - 0900 897c2438 4c896c24 304c895c 24284c89 .|$8L.l$0L.\$(L. - 0910 64242048 63db4c8b 6424504c 8b6c2448 d$ Hc.L.d$PL.l$H - 0920 4c8b5c24 404c8b7d 1848ffc3 4929c249 L.\$@L.}.H..I).I - 0930 29c14929 c00f1f00 4d85f60f 8e170d00 ).I)....M....... - 0940 00488b84 24b80000 00c57829 cc488d34 .H..$.....x).H.4 - 0950 b8488b84 24c00000 00c57829 cbc57829 .H..$.....x)..x) - 0960 cac57829 c90f1f00 c5fa1006 4801cec4 ..x)........H... - 0970 e279b908 c4a279b9 1490c4a2 79b91c88 .y....y.....y... - 0980 c4a279b9 24804883 c0044839 c275d948 ..y.$.H...H9.u.H - 0990 8b842488 00000048 01f8c4c1 7a110c87 ..$....H....z... - 09a0 498d043b c4c17a11 1487498d 443d004c I..;..z...I.D=.L - 09b0 01e7c4c1 7a111c87 c4c17a11 24bf4889 ....z.....z.$.H. - 09c0 df48ffc3 483bbc24 90000000 0f8c66ff .H..H;.$......f. - 09d0 ffff4c8b 7c24384c 8b6c2430 4c8b5c24 ..L.|$8L.l$0L.\$ - 09e0 284c8b64 2420488b 4424f083 44245804 (L.d$ H.D$..D$X. - 09f0 48018424 88000000 48014424 40480144 H..$....H.D$@H.D - 0a00 24484801 44245048 8b042448 8b5c24f8 $HH.D$PH..$H.\$. - 0a10 48014424 68480144 24704801 44247848 H.D$hH.D$pH.D$xH - 0a20 01842480 0000008b 7c245848 8b442408 ..$.....|$XH.D$. - 0a30 48019c24 c0000000 4801da49 01c44901 H..$....H..I..I. - 0a40 c34901c5 4901c739 bc249800 00000f8f .I..I..9.$...... - 0a50 44f7ffff 8b842498 0000004c 89f78984 D.....$....L.... - 0a60 24880000 004c8bb4 24b80000 004c8b7d $....L..$....L.} - 0a70 188b5424 d08b9c24 88000000 39da0f8e ..T$...$....9... - 0a80 23070000 488b4520 ffca29da 4801c089 #...H.E ..).H... - 0a90 54241883 e2fe8d73 01488944 24504863 T$.....s.H.D$PHc - 0aa0 c38d5c13 03895c24 78488b5d 1089b424 ..\...\$xH.]...$ - 0ab0 c0000000 488d149d 00000000 48639c24 ....H.......Hc.$ - 0ac0 a8000000 488b7424 60895c24 4848895c ....H.t$`.\$HH.\ - 0ad0 24408b9c 24a40000 004c8b6d 20ffcb89 $@..$....L.m ... - 0ae0 5c24388b 9c24a000 0000488d 0cf50000 \$8..$....H..... - 0af0 0000ffcb 895c2430 8b9c249c 0000004c .....\$0..$....L - 0b00 0fafe8ff cb895c24 288b9c24 ac000000 ......\$(..$.... - 0b10 480fafc6 4801f648 894c2458 48897424 H...H..H.L$XH.t$ - 0b20 68488b4c 24c8488b 7520ffcb 895c2420 hH.L$.H.u ...\$ - 0b30 48c1e603 48898424 b8000000 4c8d0481 H...H..$....L... - 0b40 4801f848 89742470 488d0481 4b8d34af H..H.t$pH...K.4. - 0b50 c4413857 c00f1f00 448b8c24 a8000000 .A8W....D..$.... - 0b60 4585c90f 8e9e0c00 0048638c 24c00000 E........Hc.$... - 0b70 004c8b54 24604889 b4248000 00004c0f .L.T$`H..$....L. - 0b80 afd1480f af4d2049 89f34531 e4498d1c ..H..M I..E1.I.. - 0b90 8f4c2b94 24b80000 004489ce 0f1f4000 .L+.$....D....@. - 0ba0 4885ff0f 8e470b00 00c44108 57f64b8d H....G....A.W.K. - 0bb0 0ca64d89 c162517c 4828ee62 517c4828 ..M..bQ|H(.bQ|H( - 0bc0 e662517c 4828de62 517c4828 d662517c .bQ|H(.bQ|H(.bQ| - 0bd0 4828ce62 d17c4828 fe62d17c 4828f690 H(.b.|H(.b.|H(.. - 0be0 62d27d48 18096292 7d481804 9162f17c b.}H..b.}H...b.| - 0bf0 48102962 f17c4810 610162f1 7c481059 H.)b.|H.a.b.|H.Y - 0c00 0262f17c 48105103 4983c104 62f27548 .b.|H.Q.I...b.uH - 0c10 b8f562f2 7548b8fc 62727548 b8cb6272 ..b.uH..bruH..br /usr/lib64/libopenblas_openmp.a/sgemm_direct_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/sgemm_direct_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sgemm_direct_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39000000 00000000 ........9....... + 0010 020001c0 04000000 00000000 00000000 ................ + 0020 010001c0 04000000 01000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/sgemm_direct_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/sgemm_direct_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sgemm_direct_COOPERLAKE.o (objdump) @@ -3,7 +3,5 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 2c000000 1c000000 ........,....... - 0020 00000000 22180000 00410e10 8602490d ...."....A....I. - 0030 06488f03 8e044e8d 058c0648 8307030c .H....N....H.... - 0040 160a0c07 08440b00 .....D.. + 0010 1b0c0708 90010000 14000000 1c000000 ................ + 0020 00000000 01000000 00000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/sgemm_direct_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sgemm_direct_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sgemm_direct_SKYLAKEX.o (disasm) @@ -5,1291 +5,4 @@ Disassembly of section .text: sgemm_direct_SKYLAKEX: - push %rbp - mov %rdi,%rax - mov %esi,%r10d - mov %rsp,%rbp - push %r15 - and $something,%r10d - push %r14 - mov %r9,%r14 - mov %esi,%r9d - push %r13 - and $something,%r9d - push %r12 - mov %esi,%r12d - and $something,%r12d - push %rbx - mov %esi,%ebx - and $something,%ebx - and $something,%rsp - sub $something,%rsp - mov %rdi,-offset(%rsp) - mov %rdx,%rdi - mov %rax,%rdx - and $something,%eax - mov %rsi,offset(%rsp) - mov %eax,-offset(%rsp) - mov %esi,%eax - and $something,%esi - mov %esi,offset(%rsp) - mov %edx,%esi - and $something,%eax - and $something,%esi - mov %rcx,-offset(%rsp) - mov %r8,offset(%rsp) - mov %ebx,offset(%rsp) - mov %r9d,offset(%rsp) - mov %r10d,offset(%rsp) - mov %r12d,offset(%rsp) - mov %eax,offset(%rsp) - mov %esi,offset(%rsp) - mov offset(%rbp),%r15 - jle - mov offset(%rbp),%rdx - mov %r8,%rax - add %rdx,%rdx - mov %rdx,offset(%rsp) - add offset(%rbp),%rdx - mov %rdx,offset(%rsp) - lea offset(,%rax,4),%rdx - mov offset(%rbp),%rsi - mov %rdx,(%rsp) - mov %ebx,-offset(%rsp) - lea (%rax,%rax,1),%rdx - movslq %ebx,%rbx - mov %rdx,offset(%rsp) - mov %rbx,-offset(%rsp) - add %rax,%rdx - lea -offset(%r9),%ebx - mov offset(%rsp),%eax - mov %rsi,offset(%rsp) - mov %ebx,-offset(%rsp) - shl $something,%rsi - lea -offset(%r10),%ebx - lea (%r15,%rsi,1),%r11 - mov %r8,offset(%rsp) - mov %rcx,offset(%rsp) - mov %rdx,offset(%rsp) - mov %ebx,-offset(%rsp) - shl $something,%r8 - lea -offset(%r12),%ebx - lea (%rcx,%rdi,4),%rdx - dec %eax - mov $something,%ecx - shlx %rcx,offset(%rbp),%rcx - lea (%r11,%rsi,1),%r13 - mov %rcx,offset(%rsp) - mov %r8,-offset(%rsp) - mov offset(%rbp),%rcx - movq $something,offset(%rsp) - movq $something,offset(%rsp) - movl $something,offset(%rsp) - mov %ebx,-offset(%rsp) - mov %eax,-offset(%rsp) - mov %rsi,-offset(%rsp) - add %r13,%rsi - mov %r14,offset(%rsp) - mov %r15,%r12 - shl $something,%rcx - vxorps %xmm9,%xmm9,%xmm9 - mov %rdi,%r14 - mov %rsi,%r15 - nopl offset(%rax,%rax,1) - mov offset(%rsp),%eax - xor %edi,%edi - xor %ebx,%ebx - test %eax,%eax - jle - mov offset(%rsp),%rax - mov offset(%rsp),%r9 - mov offset(%rsp),%r8 - mov offset(%rsp),%rdi - mov %r13,offset(%rsp) - mov %r13,offset(%rsp) - mov %r12,offset(%rsp) - mov %r12,%r10 - xor %esi,%esi - mov offset(%rsp),%r12 - mov %r15,offset(%rsp) - mov %r15,offset(%rsp) - mov %r11,offset(%rsp) - mov %r11,%rbx - sub %rax,%r9 - mov %r15,%r11 - sub %rax,%r8 - sub %rax,%rdi - mov %rsi,%r15 - nop - test %r14,%r14 - jle - vxorps %xmm24,%xmm24,%xmm24 - mov offset(%rsp),%rax - lea (%r12,%r15,4),%rsi - vmovaps %zmm24,%zmm23 - vmovaps %zmm24,%zmm22 - vmovaps %zmm24,%zmm21 - vmovaps %zmm24,%zmm20 - vmovaps %zmm24,%zmm19 - vmovaps %zmm24,%zmm18 - vmovaps %zmm24,%zmm17 - vmovaps %zmm24,%zmm16 - vmovaps %zmm24,%zmm15 - vmovaps %zmm24,%zmm14 - vmovaps %zmm24,%zmm13 - vmovaps %zmm24,%zmm12 - vmovaps %zmm24,%zmm11 - vmovaps %zmm24,%zmm10 - vmovaps %zmm24,%zmm8 - nopl (%rax) - vbroadcastss (%rax),%zmm7 - vbroadcastss (%rax,%r9,4),%zmm6 - vbroadcastss (%rax,%r8,4),%zmm5 - vbroadcastss (%rax,%rdi,4),%zmm1 - vmovups (%rsi),%zmm4 - vmovups offset(%rsi),%zmm3 - vmovups offset(%rsi),%zmm2 - vmovups offset(%rsi),%zmm0 - add $something,%rax - vfmadd231ps %zmm4,%zmm7,%zmm8 - vfmadd231ps %zmm3,%zmm7,%zmm10 - vfmadd231ps %zmm2,%zmm7,%zmm11 - vfmadd231ps %zmm0,%zmm7,%zmm12 - vfmadd231ps %zmm4,%zmm6,%zmm13 - vfmadd231ps %zmm3,%zmm6,%zmm14 - vfmadd231ps %zmm2,%zmm6,%zmm15 - vfmadd231ps %zmm0,%zmm6,%zmm16 - vfmadd231ps %zmm4,%zmm5,%zmm17 - vfmadd231ps %zmm3,%zmm5,%zmm18 - vfmadd231ps %zmm2,%zmm5,%zmm19 - vfmadd231ps %zmm0,%zmm5,%zmm20 - vfmadd231ps %zmm4,%zmm1,%zmm21 - vfmadd231ps %zmm3,%zmm1,%zmm22 - vfmadd231ps %zmm2,%zmm1,%zmm23 - vfmadd231ps %zmm0,%zmm1,%zmm24 - add %rcx,%rsi - cmp %rax,%rdx - jne - add $something,%r15 - vmovups %zmm8,(%r10) - vmovups %zmm10,offset(%r10) - vmovups %zmm11,offset(%r10) - vmovups %zmm12,offset(%r10) - add $something,%rbx - vmovups %zmm13,-offset(%rbx) - vmovups %zmm14,-offset(%rbx) - vmovups %zmm15,-offset(%rbx) - vmovups %zmm16,-offset(%rbx) - add $something,%r10 - vmovups %zmm17,offset(%r13) - vmovups %zmm18,offset(%r13) - vmovups %zmm19,offset(%r13) - vmovups %zmm20,offset(%r13) - add $something,%r11 - vmovups %zmm21,-offset(%r11) - vmovups %zmm22,-offset(%r11) - vmovups %zmm23,-offset(%r11) - vmovups %zmm24,-offset(%r11) - add $something,%r13 - cmp %r15d,offset(%rsp) - jg - mov offset(%rsp),%r15 - mov offset(%rsp),%r13 - mov offset(%rsp),%r11 - mov offset(%rsp),%r12 - mov -offset(%rsp),%rdi - mov -offset(%rsp),%ebx /usr/lib64/libopenblas_openmp.a/sgemm_direct_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sgemm_direct_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sgemm_direct_SKYLAKEX.o (objdump) @@ -2,390 +2,4 @@ /usr/lib64/libopenblas_openmp.a/sgemm_direct_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 554889f8 4189f248 89e54157 4183e2f0 UH..A..H..AWA... - 0010 41564d89 ce4189f1 41554183 e1e04154 AVM..A..AUA...AT - 0020 4189f441 83e4f853 89f383e3 c04883e4 A..A...S.....H.. - 0030 c04881ec c8000000 48897c24 c04889d7 .H......H.|$.H.. - 0040 4889c283 e0fe4889 b4249000 00008944 H.....H..$.....D - 0050 24d089f0 83e6fe89 b424b000 000089d6 $........$...... - 0060 83e0fc83 e6fc4889 4c24c84c 89442460 ......H.L$.L.D$` - 0070 899c24a8 00000044 898c24a4 00000044 ..$....D..$....D - 0080 899424a0 00000044 89a4249c 00000089 ..$....D..$..... - 0090 8424ac00 000089b4 24980000 004c8b7d .$......$....L.} - 00a0 180f8e6b 17000048 8b55204c 89c04801 ...k...H.U L..H. - 00b0 d2488954 24484803 55204889 54245048 .H.T$HH.U H.T$PH - 00c0 8d148500 00000048 8b752048 89142489 .......H.u H..$. - 00d0 5c24ec48 8d140048 63db4889 54247848 \$.H...Hc.H.T$xH - 00e0 895c24e0 4801c241 8d59ff8b 8424ac00 .\$.H..A.Y...$.. - 00f0 00004889 74244089 5c24e848 c1e60241 ..H.t$@.\$.H...A - 0100 8d5aff4d 8d1c374c 89442470 48898c24 .Z.M..7L.D$pH..$ - 0110 c0000000 48899424 80000000 895c24dc ....H..$.....\$. - 0120 49c1e004 418d5c24 ff488d14 b9ffc8b9 I...A.\$.H...... - 0130 04000000 c4e2f1f7 4d204d8d 2c334889 ........M M.,3H. - 0140 4c24084c 894424f8 488b4d10 48c74424 L$.L.D$.H.M.H.D$ - 0150 68000000 0048c784 24880000 00000000 h....H..$....... - 0160 00c74424 58000000 00895c24 d8894424 ..D$X.....\$..D$ - 0170 d4488974 24f04c01 ee4c89b4 24b80000 .H.t$.L..L..$... - 0180 004d89fc 48c1e102 c4413057 c94989fe .M..H....A0W.I.. - 0190 4989f70f 1f440000 8b8424a8 00000031 I....D....$....1 - 01a0 ff31db85 c00f8e2d 02000048 8b442468 .1.....-...H.D$h - 01b0 4c8b4c24 704c8b44 2478488b bc248000 L.L$pL.D$xH..$.. - 01c0 00004c89 6c24304c 896c2420 4c896424 ..L.l$0L.l$ L.d$ - 01d0 104d89e2 31f64c8b a424b800 00004c89 .M..1.L..$....L. - 01e0 7c24384c 897c2428 4c895c24 184c89db |$8L.|$(L.\$.L.. - 01f0 4929c14d 89fb4929 c04829c7 4989f790 I).M..I).H).I... - 0200 4d85f60f 8e8f1500 0062013c 0057c048 M........b.<.W.H - 0210 8b8424c0 0000004b 8d34bc62 817c4828 ..$....K.4.b.|H( - 0220 f862817c 4828f062 817c4828 e862817c .b.|H(.b.|H(.b.| - 0230 4828e062 817c4828 d862817c 4828d062 H(.b.|H(.b.|H(.b - 0240 817c4828 c862817c 4828c062 117c4828 .|H(.b.|H(.b.|H( - 0250 f862117c 4828f062 117c4828 e862117c .b.|H(.b.|H(.b.| - 0260 4828e062 117c4828 d862117c 4828d062 H(.b.|H(.b.|H(.b - 0270 117c4828 c00f1f00 62f27d48 183862b2 .|H(....b.}H.8b. - 0280 7d481834 8862b27d 48182c80 62f27d48 }H.4.b.}H.,.b.}H - 0290 180cb862 f17c4810 2662f17c 48105e01 ...b.|H.&b.|H.^. - 02a0 62f17c48 10560262 f17c4810 46034883 b.|H.V.b.|H.F.H. - 02b0 c0046272 4548b8c4 62724548 b8d36272 ..brEH..brEH..br - 02c0 4548b8da 62724548 b8e06272 4d48b8ec EH..brEH..brMH.. - 02d0 62724d48 b8f36272 4d48b8fa 62e24d48 brMH..brMH..b.MH - 02e0 b8c062e2 5548b8cc 62e25548 b8d362e2 ..b.UH..b.UH..b. - 02f0 5548b8da 62e25548 b8e062e2 7548b8ec UH..b.UH..b.uH.. - 0300 62e27548 b8f362e2 7548b8fa 62627548 b.uH..b.uH..bbuH - 0310 b8c04801 ce4839c2 0f855aff ffff4983 ..H..H9...Z...I. - 0320 c7406251 7c481102 62517c48 11520162 .@bQ|H..bQ|H.R.b - 0330 517c4811 5a026251 7c481162 034881c3 Q|H.Z.bQ|H.b.H.. - 0340 00010000 62717c48 116bfc62 717c4811 ....bq|H.k.bq|H. - 0350 73fd6271 7c48117b fe62e17c 481143ff s.bq|H.{.b.|H.C. - 0360 4981c200 01000062 c17c4811 4d0062c1 I......b.|H.M.b. - 0370 7c481155 0162c17c 48115d02 62c17c48 |H.U.b.|H.].b.|H - 0380 11650349 81c30001 000062c1 7c48116b .e.I......b.|H.k - 0390 fc62c17c 481173fd 62c17c48 117bfe62 .b.|H.s.b.|H.{.b - 03a0 417c4811 43ff4981 c5000100 004439bc A|H.C.I......D9. - 03b0 24a80000 000f8f45 feffff4c 8b7c2428 $......E...L.|$( - 03c0 4c8b6c24 204c8b5c 24184c8b 64241048 L.l$ L.\$.L.d$.H - 03d0 8b7c24e0 8b5c24ec 399c24a4 0000000f .|$..\$.9.$..... - 03e0 8e410100 00488b44 24684c8b 5424704c .A...H.D$hL.T$pL - 03f0 8b4c2478 4c8b8424 80000000 895c2438 .L$xL..$.....\$8 - 0400 4863fb48 8b9c24b8 00000049 29c24929 Hc.H..$....I).I) - 0410 c14929c0 0f1f4000 4d85f60f 8e3f1300 .I)...@.M....?.. - 0420 00c44108 57f6488b 8424c000 0000488d ..A.W.H..$....H. - 0430 34bb6251 7c4828ee 62517c48 28e66251 4.bQ|H(.bQ|H(.bQ - 0440 7c4828de 62517c48 28d66251 7c4828c6 |H(.bQ|H(.bQ|H(. - 0450 62d17c48 28fe62d1 7c4828f6 0f1f4000 b.|H(.b.|H(...@. - 0460 62f17c48 100e62f1 7c481046 0162f27d b.|H..b.|H.F.b.} - 0470 48182862 b27d4818 249062b2 7d48181c H.(b.}H.$.b.}H.. - 0480 8862b27d 48181480 4883c004 62f25548 .b.}H...H...b.UH - 0490 b8f162f2 5548b8f8 62725d48 b8c16272 ..b.UH..br]H..br - 04a0 5d48b8d0 62726548 b8d96272 6548b8e0 ]H..breH..breH.. - 04b0 62726d48 b8e96272 6d48b8f0 4801ce48 brmH..brmH..H..H - 04c0 39c2759c 62d17c48 1134bc62 d17c4811 9.u.b.|H.4.b.|H. - 04d0 7cbc0162 517c4811 04bb6251 7c481154 |..bQ|H...bQ|H.T - 04e0 bb016251 7c48115c bd006251 7c481164 ..bQ|H.\..bQ|H.d - 04f0 bd016251 7c48112c bf62517c 481174bf ..bQ|H.,.bQ|H.t. - 0500 014883c7 2039bc24 a4000000 0f8f06ff .H.. 9.$........ - 0510 ffff8b5c 24388b44 24e829d8 83e0e08d ...\$8.D$.)..... - 0520 5c032048 63fb399c 24a00000 000f8ed5 \. Hc.9.$....... - 0530 00000048 8b442468 4c8b4c24 704c8b44 ...H.D$hL.L$pL.D - 0540 2478488b bc248000 0000895c 24384c63 $xH..$.....\$8Lc - 0550 d3488b9c 24b80000 004929c1 4929c048 .H..$....I).I).H - 0560 29c7660f 1f440000 4d85f60f 8ecf1100 ).f..D..M....... - 0570 00c5d857 e4488b84 24c00000 004a8d34 ...W.H..$....J.4 - 0580 9362f17c 4828dc62 f17c4828 d462f17c .b.|H(.b.|H(.b.| - 0590 4828cc0f 1f440000 62f17c48 10064801 H(...D..b.|H..H. - 05a0 ce62f27d 58b80862 b27d58b8 148862b2 .b.}X..b.}X...b. - 05b0 7d58b81c 8062f27d 58b824b8 4883c004 }X...b.}X.$.H... - 05c0 4839c275 d362917c 48110c94 62917c48 H9.u.b.|H...b.|H - 05d0 11149362 917c4811 5c950062 917c4811 ...b.|H.\..b.|H. - 05e0 24974983 c2104439 9424a000 00000f8f $.I...D9.$...... - 05f0 74ffffff 8b5c2438 8b4424dc 29d883e0 t....\$8.D$.)... - 0600 f08d5c03 104863fb 399c249c 0000000f ..\..Hc.9.$..... - 0610 8ec10000 00488b44 24684c8b 4c24704c .....H.D$hL.L$pL - 0620 8b442478 488bbc24 80000000 895c2438 .D$xH..$.....\$8 - 0630 4c63d348 8b9c24b8 00000049 29c14929 Lc.H..$....I).I) - 0640 c04829c7 0f1f4000 4d85f60f 8ed71000 .H)...@.M....... - 0650 00c5d857 e4488b84 24c00000 004a8d34 ...W.H..$....J.4 - 0660 93c5fc28 dcc5fc28 d4c5fc28 cc0f1f00 ...(...(...(.... - 0670 c5fc1006 4801ce62 f27d38b8 0862b27d ....H..b.}8..b.} - 0680 38b81488 62b27d38 b81c8062 f27d38b8 8...b.}8...b.}8. - 0690 24b84883 c0044839 c275d5c4 817c110c $.H...H9.u...|.. - 06a0 94c4817c 111493c4 817c115c 9500c481 ...|.....|.\.... - 06b0 7c112497 4983c208 44399424 9c000000 |.$.I...D9.$.... - 06c0 7f868b5c 24388b44 24d829d8 83e0f88d ...\$8.D$.)..... - 06d0 5c030848 63fb399c 24ac0000 000f8ec3 \..Hc.9.$....... - 06e0 00000048 8b442468 4c8b4c24 704c8b44 ...H.D$hL.L$pL.D - 06f0 2478488b bc248000 0000895c 24384c63 $xH..$.....\$8Lc - 0700 d3488b9c 24b80000 004929c1 4929c048 .H..$....I).I).H - 0710 29c7660f 1f440000 4d85f60f 8e7f0f00 ).f..D..M....... - 0720 00c5d857 e4488b84 24c00000 004a8d34 ...W.H..$....J.4 - 0730 93c5f828 dcc5f828 d4c5f828 cc0f1f00 ...(...(...(.... - 0740 c5f81006 4801ce62 f27d18b8 0862b27d ....H..b.}...b.} - 0750 18b81488 62b27d18 b81c8062 f27d18b8 ....b.}....b.}.. - 0760 24b84883 c0044839 c275d5c4 8178110c $.H...H9.u...x.. - 0770 94c48178 111493c4 8178115c 9500c481 ...x.....x.\.... - 0780 78112497 4983c204 44399424 ac000000 x.$.I...D9.$.... - 0790 7f868b5c 24388b44 24d429d8 83e0fc8d ...\$8.D$.)..... - 07a0 5c030448 63fb399c 24b00000 000f8e27 \..Hc.9.$......' - 07b0 01000048 8b442468 4c8b5424 704c8b4c ...H.D$hL.T$pL.L - 07c0 24784c8b 84248000 0000895c 24384863 $xL..$.....\$8Hc - 07d0 fb488b9c 24b80000 004929c2 4929c149 .H..$....I).I).I - 07e0 29c0660f 1f440000 4d85f60f 8e7f0e00 ).f..D..M....... - 07f0 00488b84 24c00000 00488d34 bbc44178 .H..$....H.4..Ax - 0800 28f1c441 7828e9c4 417828e1 c4417828 (..Ax(..Ax(..Ax( - 0810 d9c44178 28d1c441 7828c1c5 7829cfc5 ..Ax(..Ax(..x).. - 0820 7829ce0f 1f440000 c5fa100e c5fa1046 x)...D.........F - 0830 04c5fa10 28c4a17a 102490c4 a17a101c ....(..z.$...z.. - 0840 88c4a17a 10148048 83c004c4 e251b9f1 ...z...H.....Q.. - 0850 c4e251b9 f8c46259 b9c1c462 59b9d0c4 ..Q...bY...bY... - 0860 6261b9d9 c46261b9 e0c46269 b9e9c462 ba...ba...bi...b - 0870 69b9f048 01ce4839 c275adc4 c17a1134 i..H..H9.u...z.4 - 0880 bcc4c17a 117cbc04 c4417a11 04bbc441 ...z.|...Az....A - 0890 7a1154bb 04c4417a 115cbd00 c4417a11 z.T...Az.\...Az. - 08a0 64bd04c4 417a112c bfc4417a 1174bf04 d...Az.,..Az.t.. - 08b0 4883c702 39bc24b0 0000000f 8f27ffff H...9.$......'.. - 08c0 ff8b8424 b0000000 8b5c2438 ffc829d8 ...$.....\$8..). - 08d0 83e0fe8d 5c030248 63fb4839 bc249000 ....\..Hc.H9.$.. - 08e0 00000f8e fe000000 488b4424 684c8b54 ........H.D$hL.T - 08f0 24704c8b 4c24784c 8b842480 0000004c $pL.L$xL..$....L - 0900 897c2438 4c896c24 304c895c 24284c89 .|$8L.l$0L.\$(L. - 0910 64242048 63db4c8b 6424504c 8b6c2448 d$ Hc.L.d$PL.l$H - 0920 4c8b5c24 404c8b7d 1848ffc3 4929c249 L.\$@L.}.H..I).I - 0930 29c14929 c00f1f00 4d85f60f 8e170d00 ).I)....M....... - 0940 00488b84 24b80000 00c57829 cc488d34 .H..$.....x).H.4 - 0950 b8488b84 24c00000 00c57829 cbc57829 .H..$.....x)..x) - 0960 cac57829 c90f1f00 c5fa1006 4801cec4 ..x)........H... - 0970 e279b908 c4a279b9 1490c4a2 79b91c88 .y....y.....y... - 0980 c4a279b9 24804883 c0044839 c275d948 ..y.$.H...H9.u.H - 0990 8b842488 00000048 01f8c4c1 7a110c87 ..$....H....z... - 09a0 498d043b c4c17a11 1487498d 443d004c I..;..z...I.D=.L - 09b0 01e7c4c1 7a111c87 c4c17a11 24bf4889 ....z.....z.$.H. - 09c0 df48ffc3 483bbc24 90000000 0f8c66ff .H..H;.$......f. - 09d0 ffff4c8b 7c24384c 8b6c2430 4c8b5c24 ..L.|$8L.l$0L.\$ - 09e0 284c8b64 2420488b 4424f083 44245804 (L.d$ H.D$..D$X. - 09f0 48018424 88000000 48014424 40480144 H..$....H.D$@H.D - 0a00 24484801 44245048 8b042448 8b5c24f8 $HH.D$PH..$H.\$. - 0a10 48014424 68480144 24704801 44247848 H.D$hH.D$pH.D$xH - 0a20 01842480 0000008b 7c245848 8b442408 ..$.....|$XH.D$. - 0a30 48019c24 c0000000 4801da49 01c44901 H..$....H..I..I. - 0a40 c34901c5 4901c739 bc249800 00000f8f .I..I..9.$...... - 0a50 44f7ffff 8b842498 0000004c 89f78984 D.....$....L.... - 0a60 24880000 004c8bb4 24b80000 004c8b7d $....L..$....L.} - 0a70 188b5424 d08b9c24 88000000 39da0f8e ..T$...$....9... - 0a80 23070000 488b4520 ffca29da 4801c089 #...H.E ..).H... - 0a90 54241883 e2fe8d73 01488944 24504863 T$.....s.H.D$PHc - 0aa0 c38d5c13 03895c24 78488b5d 1089b424 ..\...\$xH.]...$ - 0ab0 c0000000 488d149d 00000000 48639c24 ....H.......Hc.$ - 0ac0 a8000000 488b7424 60895c24 4848895c ....H.t$`.\$HH.\ - 0ad0 24408b9c 24a40000 004c8b6d 20ffcb89 $@..$....L.m ... - 0ae0 5c24388b 9c24a000 0000488d 0cf50000 \$8..$....H..... - 0af0 0000ffcb 895c2430 8b9c249c 0000004c .....\$0..$....L - 0b00 0fafe8ff cb895c24 288b9c24 ac000000 ......\$(..$.... - 0b10 480fafc6 4801f648 894c2458 48897424 H...H..H.L$XH.t$ - 0b20 68488b4c 24c8488b 7520ffcb 895c2420 hH.L$.H.u ...\$ - 0b30 48c1e603 48898424 b8000000 4c8d0481 H...H..$....L... - 0b40 4801f848 89742470 488d0481 4b8d34af H..H.t$pH...K.4. - 0b50 c4413857 c00f1f00 448b8c24 a8000000 .A8W....D..$.... - 0b60 4585c90f 8e9e0c00 0048638c 24c00000 E........Hc.$... - 0b70 004c8b54 24604889 b4248000 00004c0f .L.T$`H..$....L. - 0b80 afd1480f af4d2049 89f34531 e4498d1c ..H..M I..E1.I.. - 0b90 8f4c2b94 24b80000 004489ce 0f1f4000 .L+.$....D....@. - 0ba0 4885ff0f 8e470b00 00c44108 57f64b8d H....G....A.W.K. - 0bb0 0ca64d89 c162517c 4828ee62 517c4828 ..M..bQ|H(.bQ|H( - 0bc0 e662517c 4828de62 517c4828 d662517c .bQ|H(.bQ|H(.bQ| - 0bd0 4828ce62 d17c4828 fe62d17c 4828f690 H(.b.|H(.b.|H(.. - 0be0 62d27d48 18096292 7d481804 9162f17c b.}H..b.}H...b.| - 0bf0 48102962 f17c4810 610162f1 7c481059 H.)b.|H.a.b.|H.Y - 0c00 0262f17c 48105103 4983c104 62f27548 .b.|H.Q.I...b.uH - 0c10 b8f562f2 7548b8fc 62727548 b8cb6272 ..b.uH..bruH..br /usr/lib64/libopenblas_openmp.a/sgemm_direct_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/sgemm_direct_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sgemm_direct_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39000000 00000000 ........9....... + 0010 020001c0 04000000 00000000 00000000 ................ + 0020 010001c0 04000000 01000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/sgemm_direct_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/sgemm_direct_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sgemm_direct_SKYLAKEX.o (objdump) @@ -3,7 +3,5 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 2c000000 1c000000 ........,....... - 0020 00000000 22180000 00410e10 8602490d ...."....A....I. - 0030 06488f03 8e044e8d 058c0648 8307030c .H....N....H.... - 0040 160a0c07 08440b00 .....D.. + 0010 1b0c0708 90010000 14000000 1c000000 ................ + 0020 00000000 01000000 00000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/sgemv_n_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sgemv_n_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sgemv_n_COOPERLAKE.o (disasm) @@ -167,6 +167,32 @@ data16 cs nopw offset(%rax,%rax,1) nopl offset(%rax) +sgemv_kernel_4x2: + mov (%rsi),%r9 + xor %eax,%eax + mov offset(%rsi),%rsi + movss (%rdx),%xmm12 + movss (%r8),%xmm4 + movss offset(%rdx),%xmm13 + mulss %xmm4,%xmm12 + mulss %xmm4,%xmm13 + shufps $something,%xmm12,%xmm12 + shufps $something,%xmm13,%xmm13 + movups (%rcx,%rax,4),%xmm4 + movups (%r9,%rax,4),%xmm8 + movups (%rsi,%rax,4),%xmm9 + mulps %xmm12,%xmm8 + mulps %xmm13,%xmm9 + addps %xmm8,%xmm4 + add $something,%rax + addps %xmm9,%xmm4 + movups %xmm4,-offset(%rcx,%rax,4) + sub $something,%rdi + jne + vzeroupper + ret + xchg %ax,%ax + sgemv_kernel_4x1: mov %rdi,%rax mov %rdx,%r9 @@ -233,525 +259,376 @@ ret nopl offset(%rax) -sgemv_kernel_n_64.isra.0: - push %rbp - mov %rdi,%r10 - mov %rdx,%r11 - mov %rsp,%rbp - push %r14 - vbroadcastss %xmm0,%ymm5 - push %r13 - push %r12 - mov %rdi,%r12 - push %rbx - mov %rcx,%rbx - and $something,%r12 - jle - mov %r9,%rcx - mov %rdx,%r14 - lea offset(,%rbx,4),%rdi - xor %r13d,%r13d - nopw offset(%rax,%rax,1) - vxorps %xmm1,%xmm1,%xmm1 - mov %r14,%rax - vmovaps %ymm1,%ymm2 - vmovaps %ymm1,%ymm3 - vmovaps %ymm1,%ymm4 - xor %edx,%edx - nopl (%rax) - vbroadcastss (%r8,%rdx,4),%ymm0 - inc %rdx - vfmadd231ps (%rax),%ymm0,%ymm4 - vfmadd231ps offset(%rax),%ymm0,%ymm3 - vfmadd231ps offset(%rax),%ymm0,%ymm2 - vfmadd231ps offset(%rax),%ymm0,%ymm1 - add %rdi,%rax - cmp %rsi,%rdx - jne - vfmadd213ps (%rcx),%ymm5,%ymm4 - vfmadd213ps offset(%rcx),%ymm5,%ymm3 - vfmadd213ps offset(%rcx),%ymm5,%ymm2 - vfmadd213ps offset(%rcx),%ymm5,%ymm1 - add $something,%r13 - vmovups %ymm4,(%rcx) - vmovups %ymm3,offset(%rcx) - vmovups %ymm2,offset(%rcx) - vmovups %ymm1,offset(%rcx) - sub $something,%r14 - sub $something,%rcx - cmp %r13,%r12 - jg - cmp %r12,%r10 - je - mov %r10,%r14 - and $something,%r14 - cmp %r14,%r12 - jge - lea offset(,%r12,4),%r13 - lea (%r9,%r13,1),%rdi - lea offset(,%rbx,4),%rcx - add %r11,%r13 - nopw offset(%rax,%rax,1) - vxorps %xmm1,%xmm1,%xmm1 - mov %r13,%rdx - vmovaps %ymm1,%ymm2 - xor %eax,%eax - nopl (%rax) - vbroadcastss (%r8,%rax,4),%ymm0 - inc %rax - vfmadd231ps (%rdx),%ymm0,%ymm2 - vfmadd231ps offset(%rdx),%ymm0,%ymm1 - add %rcx,%rdx - cmp %rax,%rsi - jne - vfmadd213ps (%rdi),%ymm5,%ymm2 - vfmadd213ps offset(%rdi),%ymm5,%ymm1 - add $something,%r12 - add $something,%rdi - add $something,%r13 - vmovups %ymm2,-offset(%rdi) - vmovups %ymm1,-offset(%rdi) - cmp %r12,%r14 - jg - cmp %r14,%r10 - je - mov %r10,%r12 - and $something,%r12 - cmp %r12,%r14 - jge - lea -offset(%r12),%rcx - sub %r14,%rcx - and $something,%rcx - lea offset(,%r14,4),%rdx - add %r14,%rcx - lea (%r11,%rdx,1),%rax - lea offset(%r11,%rcx,4),%rcx - add %r9,%rdx - lea offset(,%rbx,4),%rdi - vxorps %xmm1,%xmm1,%xmm1 - cs nopw offset(%rax,%rax,1) - vbroadcastss (%r8),%ymm0 - vfmadd132ps (%rax),%ymm1,%ymm0 - cmp $something,%rsi - jne - vbroadcastss offset(%r8),%ymm6 - vfmadd231ps (%rdi,%rax,1),%ymm6,%ymm0 - vfmadd213ps (%rdx),%ymm5,%ymm0 - add $something,%rax - add $something,%rdx - vmovups %ymm0,-offset(%rdx) - cmp %rax,%rcx - jne - cmp %r12,%r10 - je - and $something,%r10d - mov $something,%eax - sub %r10d,%eax - mov %eax,%edx - mov $something,%eax - sarx %edx,%eax,%eax - kmovd %eax,%k1 - lea offset(,%r12,4),%rax - vmovups (%r11,%rax,1),%ymm0{%k1}{z} - vxorps %xmm1,%xmm1,%xmm1 - vfmadd132ps (%r8){1to8},%ymm1,%ymm0{%k1}{z} - cmp $something,%rsi - jne - add %rbx,%r12 - vmovups (%r11,%r12,4),%ymm1{%k1}{z} - vfmadd231ps offset(%r8){1to8},%ymm1,%ymm0{%k1}{z} - add %rax,%r9 - vmovups (%r9),%ymm1{%k1}{z} - vfmadd132ps %ymm5,%ymm1,%ymm0{%k1}{z} - vmovups %ymm0,(%r9){%k1} - vzeroupper - pop %rbx - pop %r12 - pop %r13 - pop %r14 - pop %rbp - ret - data16 cs nopw offset(%rax,%rax,1) - sgemv_n_COOPERLAKE: - lea offset(%rsp),%r10 - and $something,%rsp - push -offset(%r10) - push %rbp - mov %rsp,%rbp push %r15 push %r14 push %r13 push %r12 - push %r10 + push %rbp push %rbx sub $something,%rsp - mov offset(%r10),%rax - mov %rcx,-offset(%rbp) - mov %rax,-offset(%rbp) - mov (%r10),%rcx - mov offset(%r10),%rax - mov %rsi,-offset(%rbp) - mov %r8,-offset(%rbp) /usr/lib64/libopenblas_openmp.a/sgemv_n_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sgemv_n_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sgemv_n_COOPERLAKE.o (objdump) @@ -51,302 +51,194 @@ 02e0 c46255b8 cec57c11 0481c57c 114c8120 .bU...|....|.L. 02f0 4883c010 4883ef10 759ac5f8 77c5f877 H...H...u...w..w 0300 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. - 0310 4889f849 89d14883 e0f883e7 0431d2f3 H..I..H......1.. - 0320 450f1021 f3450f59 20450fc6 e4004883 E..!.E.Y E....H. - 0330 f800743a 0f102491 0f106c91 10440f10 ..t:..$...l..D.. - 0340 0496440f 104c9610 450f59c4 450f59cc ..D..L..E.Y.E.Y. - 0350 440f58c4 440f58cd 4883c208 440f1144 D.X.D.X.H...D..D - 0360 91e0440f 114c91f0 4883e808 75c648f7 ..D..L..H...u.H. - 0370 c7040000 00741d0f 10249144 0f100496 .....t...$.D.... - 0380 450f59c4 410f58e0 0f112491 4883c204 E.Y.A.X...$.H... - 0390 4883e804 c5f877c3 0f1f8400 00000000 H.....w......... - 03a0 4883f901 743248c1 e102488d 04be4885 H...t2H...H...H. - 03b0 ff7e480f 1f440000 c5fa1002 4883c604 .~H..D......H... - 03c0 c5fa5846 fcc5fa11 024801ca 4839f075 ..XF.....H..H9.u - 03d0 e7c3660f 1f440000 31c0440f 10248644 ..f..D..1.D..$.D - 03e0 0f101c82 450f58dc 4883c004 440f115c ....E.X.H...D..\ - 03f0 82f04883 ef0475e2 c5f877c3 0f1f4000 ..H...u...w...@. - 0400 554989fa 4989d348 89e54156 c4e27d18 UI..I..H..AV..}. - 0410 e8415541 544989fc 534889cb 4983e4e0 .AUATI..SH..I... - 0420 0f8e9500 00004c89 c94989d6 488d3c9d ......L..I..H.<. - 0430 00000000 4531ed66 0f1f8400 00000000 ....E1.f........ - 0440 c5f057c9 4c89f0c5 fc28d1c5 fc28d9c5 ..W.L....(...(.. - 0450 fc28e131 d20f1f00 c4c27d18 049048ff .(.1......}...H. - 0460 c2c4e27d b820c4e2 7db85820 c4e27db8 ...}. ..}.X ..}. - 0470 5040c4e2 7db84860 4801f848 39f275d8 P@..}.H`H..H9.u. - 0480 c4e255a8 21c4e255 a85920c4 e255a851 ..U.!..U.Y ..U.Q - 0490 40c4e255 a8496049 83c520c5 fc1121c5 @..U.I`I.. ...!. - 04a0 fc115920 c5fc1151 40c5fc11 49604983 ..Y ...Q@...I`I. - 04b0 ee804883 e9804d39 ec7f854d 39e20f84 ..H...M9...M9... - 04c0 65010000 4d89d649 83e6f04d 39f47d72 e...M..I...M9.}r - 04d0 4e8d2ca5 00000000 4b8d3c29 488d0c9d N.,.....K.<)H... - 04e0 00000000 4d01dd66 0f1f8400 00000000 ....M..f........ - 04f0 c5f057c9 4c89eac5 fc28d131 c00f1f00 ..W.L....(.1.... - 0500 c4c27d18 048048ff c0c4e27d b812c4e2 ..}...H....}.... - 0510 7db84a20 4801ca48 39c675e4 c4e255a8 }.J H..H9.u...U. - 0520 17c4e255 a84f2049 83c41048 83c74049 ...U.O I...H..@I - 0530 83c540c5 fc1157c0 c5fc114f e04d39e6 ..@...W....O.M9. - 0540 7fae4d39 f20f84de 0000004d 89d44983 ..M9.......M..I. - 0550 e4f84d39 e67d6c49 8d4c24ff 4c29f148 ..M9.}lI.L$.L).H - 0560 83e1f84a 8d14b500 0000004c 01f1498d ...J.......L..I. - 0570 0413498d 4c8b204c 01ca488d 3c9d0000 ..I.L. L..H.<... - 0580 0000c5f0 57c9662e 0f1f8400 00000000 ....W.f......... - 0590 c4c27d18 00c4e275 98004883 fe02750c ..}....u..H...u. - 05a0 c4c27d18 7004c4e2 4db80407 c4e255a8 ..}.p...M.....U. - 05b0 024883c0 204883c2 20c5fc11 42e04839 .H.. H.. ...B.H9 - 05c0 c175cd4d 39e27461 4183e207 b8080000 .u.M9.taA....... - 05d0 004429d0 89c2b8ff 000000c4 e26af7c0 .D)..........j.. - 05e0 c5fb92c8 4a8d04a5 00000000 62d17ca9 ....J.......b.|. - 05f0 100403c5 f057c962 d275b998 004883fe .....W.b.u...H.. - 0600 02751149 01dc6291 7ca9100c a362d275 .u.I..b.|....b.u - 0610 b9b84001 4901c162 d17ca910 0962f275 ..@.I..b.|...b.u - 0620 a998c562 d17c2911 01c5f877 5b415c41 ...b.|)....w[A\A - 0630 5d415e5d c366662e 0f1f8400 00000000 ]A^].ff......... - 0640 4c8d5424 084883e4 c041ff72 f8554889 L.T$.H...A.r.UH. - 0650 e5415741 56415541 54415253 4881ec40 .AWAVAUATARSH..@ - 0660 01000049 8b420848 898d48ff ffff4889 ...I.B.H..H...H. - 0670 8530ffff ff498b0a 498b4210 4889b5c8 .0...I..I.B.H... - 0680 feffff4c 8985e0fe ffff4c89 8d18ffff ...L......L..... - 0690 ff48898d 10ffffff 48898528 ffffffc5 .H......H..(.... - 06a0 fa11857c ffffff4d 8b721864 488b0425 ...|...M.r.dH..% - 06b0 28000000 488945c8 31c04885 ff0f8e95 (...H.E.1.H..... - 06c0 04000048 85f60f8e 8c040000 4883fe30 ...H........H..0 - 06d0 0f9ec248 83fe040f 95c084c2 740d4881 ...H........t.H. - 06e0 ff004000 000f8eb3 07000048 8b85e0fe ..@........H.... - 06f0 ffff488d 0c850000 00004889 8d38ffff ..H.......H..8.. - 0700 ff488b8d c8feffff 48c1e003 4889ce48 .H......H...H..H - 0710 c1fe0283 e1034883 bd10ffff ff014889 ......H.......H. - 0720 b568ffff ff48898d 58ffffff 751f488b .h...H..X...u.H. - 0730 8dc8feff ff4889ce 48c1fe03 83e10748 .....H..H......H - 0740 89b568ff ffff4889 8d58ffff ff4889f9 ..h...H..X...H.. - 0750 83e10348 8b9de0fe ffff4889 fe81e7ff ...H......H..... - 0760 0f000048 29cf488d 14850000 00004889 ...H).H.......H. - 0770 8da8feff ff488d04 dd000000 004889f9 .....H.......H.. - 0780 4889bdd8 feffff48 8d3c9d00 00000048 H......H.<.....H - 0790 89bd20ff ffff4889 85a0feff ff488bbd .. ...H......H.. - 07a0 10ffffff 488d048d 00000000 488b8d18 ....H.......H... - 07b0 ffffff48 8985d0fe ffff4c8d 3cbd0000 ...H......L.<... - 07c0 00004889 f8488d3c f94889bd f0feffff ..H..H.<.H...... - 07d0 488bbd68 ffffff48 83e6fc48 c1e00448 H..h...H...H...H - 07e0 89b508ff ffff4889 8570ffff ff488bb5 ......H..p...H.. - 07f0 38ffffff 480fafc7 48c1e602 4889b500 8...H...H...H... - 0800 ffffff48 01c8480f aff74889 95c0feff ...H..H...H..... - 0810 ff480faf d748c1e7 05488985 f8feffff .H...H...H...... - 0820 4889f848 01c84889 b5e8feff ff488995 H..H..H......H.. - 0830 b8feffff 488985b0 feffff0f 1f440000 ....H........D.. - 0840 4881ad08 ffffff00 10000048 c78540ff H..........H..@. - 0850 ffff0040 000041bd 00100000 0f882e04 ...@..A......... - 0860 0000488b bd20ffff ff488b85 48ffffff ..H.. ...H..H... - 0870 48894580 4801f848 89458848 01f84889 H.E.H..H.E.H..H. - 0880 45904801 f84883bd 28ffffff 01488945 E.H..H..(....H.E - 0890 980f8409 03000031 f64a8d14 ad000000 .......1.J...... - 08a0 004c89f7 e8000000 004883bd 10ffffff .L.......H...... - 08b0 010f84fe 02000048 83bd68ff ffff000f .......H..h..... - 08c0 84730400 00488d7d 80488d9d 7cffffff .s...H.}.H..|... - 08d0 4c8b8df0 feffff48 8b8518ff ffff4889 L......H......H. - 08e0 bd50ffff ff4c8d65 a04531d2 4989d848 .P...L.e.E1.I..H - 08f0 8b9d00ff ffff4c89 ad60ffff ff4c89f1 ......L..`...L.. - 0900 4d89fd4c 89e24d89 cf4d89d6 4989c490 M..L..M..M..I... - 0910 c4c17a10 0424488b b550ffff ffc5fa11 ..z..$H..P...... - 0920 45a0c481 7a10042c 488bbd60 ffffffc5 E...z..,H..`.... - 0930 fa1145a4 c4c17a10 0749ffc6 c5fa1145 ..E...z..I.....E - 0940 a8c4817a 10042f4c 03a570ff ffffc5fa ...z../L..p..... - 0950 1145ace8 78f8ffff 48015d80 48015d88 .E..x...H.].H.]. - 0960 48015d90 48015d98 4c03bd70 ffffff4c H.].H.].L..p...L - 0970 39b568ff ffff7598 488bb548 ffffff4d 9.h...u.H..H...M - 0980 89ef4c8b 95f8feff ff4c8bad 60ffffff ..L......L..`... - 0990 4989ce48 03b5e8fe ffff4883 bd58ffff I..H......H..X.. - 09a0 ff007446 4531db48 8d9d7cff ffff4989 ..tFE1.H..|...I. - 09b0 d84c89db 4c8b9d20 ffffff4c 8d65a090 .L..L.. ...L.e.. - 09c0 c4c17a10 024c89f1 4c89e24c 89ef48ff ..z..L..L..L..H. - 09d0 c3c5fa11 45a04d01 fae832f9 ffff4c01 ....E.M...2...L. - 09e0 de48399d 58ffffff 75d6488b bd40ffff .H9.X...u.H..@.. - 09f0 ff488b9d 28ffffff 4801bd48 ffffff48 .H..(...H..H...H - 0a00 83fb010f 847f0100 004c8b9d 30ffffff .........L..0... - 0a10 4889d94c 89da4c89 f64c89ef e87ff9ff H..L..L..L...... - 0a20 ff4889d8 490fafc5 498d0483 48898530 .H..I...I...H..0 - 0a30 ffffff49 81fd0010 00000f84 00feffff ...I............ - 0a40 488bbda8 feffff48 85ff0f84 08010000 H......H........ - 0a50 4883bd10 ffffff01 0f94c048 83ff030f H..........H.... - 0a60 84070900 004883bd a8feffff 020f84eb .....H.......... - 0a70 02000048 83bde0fe ffff010f 85ab0800 ...H............ - 0a80 0084c00f 84a30800 00488b95 c8feffff .........H...... - 0a90 4883e2fc 0f84e20a 000048ff ca48c1ea H.........H..H.. - 0aa0 0248ffc2 488bbd48 ffffff48 89d648c1 .H..H..H...H..H. - 0ab0 e604488b 8d18ffff ff4889f8 4801fec5 ..H......H..H... - 0ac0 f057c90f 1f440000 c5fa1040 04c5fa10 .W...D.....@.... - 0ad0 38c5fa59 41044883 c0104883 c110c4e2 8..YA.H...H..... - 0ae0 41b941f0 c5fa1078 f8c4e241 b941f8c5 A.A....x...A.A.. - 0af0 fa1078fc c4e241b9 41fcc5f2 58c84839 ..x...A.A...X.H9 - 0b00 c675c548 c1e20248 3995c8fe ffff7e2b .u.H...H9.....~+ - 0b10 488b85c8 feffff48 8b8d48ff ffff488b H......H..H...H. - 0b20 b518ffff ff0f1f00 c5fa102c 91c4e251 ...........,...Q - 0b30 b90c9648 ffc24839 d07fed48 8b8530ff ...H..H9...H..0. - 0b40 ffffc5fa 1028c4e2 51998d7c ffffffc5 .....(..Q..|.... - 0b50 fa11080f 1f440000 488b45c8 64482b04 .....D..H.E.dH+. - 0b60 25280000 000f854d 0a000048 81c44001 %(.....M...H..@. - 0b70 00005b41 5a415c41 5d415e41 5f31c05d ..[AZA\A]A^A_1.] - 0b80 498d62f8 c30f1f00 488bbd40 ffffff48 I.b.....H..@...H - 0b90 01bd30ff ffffe998 feffff0f 1f440000 ..0..........D.. - 0ba0 4883bd10 ffffff01 4c8bb530 ffffff0f H.......L..0.... - 0bb0 8502fdff ff4883bd 68ffffff 000f8488 .....H..h....... - 0bc0 01000045 31e4488d 9d7cffff ff4c89bd ...E1.H..|...L.. - 0bd0 60ffffff 488d4580 488b9518 ffffff4c `...H.E.H......L - 0be0 8bbdc0fe ffff4989 d94c89e3 4989c490 ......I..L..I... - 0bf0 4c8b8538 ffffff4c 89f14c89 e64c89ef L..8...L..L..L.. - 0c00 48ffc3e8 f8f3ffff 4c017d80 4c017d88 H.......L.}.L.}. - 0c10 4c017d90 4c017d98 4883c220 48399d68 L.}.L.}.H.. H9.h - 0c20 ffffff75 cb4c8ba5 48ffffff 4c8bbd60 ...u.L..H...L..` - 0c30 ffffff48 8b9db0fe ffff4c03 a5b8feff ...H......L..... - 0c40 fff68558 ffffff04 756ef685 58ffffff ...X....un..X... - 0c50 020f85a8 000000f6 8558ffff ff010f84 .........X...... - 0c60 86fdffff 488b8de0 feffffc5 fa10857c ....H..........| - 0c70 ffffff4d 89f14989 d84c89e2 be010000 ...M..I..L...... - 0c80 004c89ef e877f7ff ffe95cfd ffff6690 .L...w....\...f. - 0c90 4c8badd8 feffff4d 85ed0f84 a0fdffff L......M........ - 0ca0 488b85d0 feffff48 898540ff ffffe9af H......H..@..... - 0cb0 fbffff0f 1f440000 488d4580 4889da48 .....D..H.E.H..H - 0cc0 89c64c8d 857cffff ff4c89f1 4c89efe8 ..L..|...L..L... - 0cd0 fcf4ffff 488b8500 ffffff48 83c31048 ....H......H...H - 0ce0 01458048 01458848 01459048 01459849 .E.H.E.H.E.H.E.I - 0cf0 01c4f685 58ffffff 020f8458 ffffff48 ....X......X...H - 0d00 8b8de0fe ffffc5fa 10857cff ffff4989 ..........|...I. - 0d10 d84c89e2 4d89f1be 02000000 4c89efe8 .L..M.......L... - 0d20 dcf6ffff 4883c308 4c03a5a0 feffffe9 ....H...L....... - 0d30 23ffffff 0f1f4000 4c8b9518 ffffff48 #.....@.L......H - 0d40 8bb548ff ffffe94f fcffff48 8b9d18ff ..H....O...H.... - 0d50 ffff4c8b a548ffff ffe9e3fe ffff4883 ..L..H........H. - 0d60 bde0feff ff020f85 76070000 84c00f84 ........v....... - 0d70 6e070000 488b95c8 feffff48 83e2fc0f n...H......H.... - 0d80 84260800 00c5f857 c0488b85 48ffffff .&.....W.H..H... - 0d90 488bb518 ffffffc5 f828d031 c9c5fa10 H........(.1.... - 0da0 648e04c5 fa100c8e c5da5958 08c5da59 d.........YX...Y - 0db0 600c4883 c020c4e2 71b958e0 c4e25999 `.H.. ..q.X...Y. - 0dc0 48e4c5e2 58d2c5fa 105c8e0c c5f258c0 H...X....\....X. - 0dd0 c5e25960 f8c5e259 58fcc5fa 104c8e08 ..Y`...YX....L.. - 0de0 4883c104 c4e271b9 60f0c4e2 619948f4 H.....q.`...a.H. - 0df0 c5da58d2 c5f258c0 4839ca7f a048ffca ..X...X.H9...H.. - 0e00 48c1ea02 48ffc248 89d048c1 e0054801 H...H..H..H...H. - 0e10 8548ffff ff4889d0 48c1e004 48c1e202 .H...H..H...H... - 0e20 48018518 ffffff48 3995c8fe ffff7e3d H......H9.....~= - 0e30 488b8548 ffffff48 8bbd18ff ffff4889 H..H...H......H. - 0e40 d148f7d9 488bb5c8 feffff48 8d04c848 .H..H......H...H - 0e50 8d0c8fc5 fa100c91 c4e271b9 14d0c4e2 ..........q..... - 0e60 71b944d0 0448ffc2 4839d67f e6488b85 q.D..H..H9...H.. - 0e70 30ffffff c5fa108d 7cffffff 488bbd28 0.......|...H..( - 0e80 ffffffc4 e271a910 c5fa1110 488d04b8 .....q......H... - 0e90 c4e279a9 08c5fa11 08e9bafc ffff4883 ..y...........H. - 0ea0 f9017428 48c1e102 4c89ca31 c00f1f00 ..t(H...L..1.... - 0eb0 c5fa1002 4801cac4 c17a1104 8648ffc0 ....H....z...H.. - 0ec0 4839c67f eb4c89b5 18ffffff 488b9530 H9...L......H..0 - 0ed0 ffffff48 8b8528ff ffff4889 d64883f8 ...H..(...H..H.. - 0ee0 01743148 8b8dc8fe ffff498d 348e488d .t1H......I.4.H. - 0ef0 0c850000 000031c0 0f1f8400 00000000 ......1......... - 0f00 c5fa1002 4801cac5 fa110486 48ffc048 ....H.......H..H - 0f10 39c77fec 4989f962 727d4818 4ddf4983 9...I..br}H.M.I. - 0f20 e1800f84 43010000 488b85e0 feffff4c ....C...H......L /usr/lib64/libopenblas_openmp.a/sgemv_n_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/sgemv_n_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sgemv_n_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/sgemv_n_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/sgemv_n_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sgemv_n_COOPERLAKE.o (objdump) @@ -7,13 +7,12 @@ 0020 00000000 c4010000 00410e10 830203c2 .........A...... 0030 010e0800 10000000 38000000 00000000 ........8....... 0040 31010000 00000000 10000000 4c000000 1...........L... - 0050 00000000 88000000 00000000 10000000 ................ - 0060 60000000 00000000 5c000000 00000000 `.......\....... - 0070 28000000 74000000 00000000 35020000 (...t.......5... - 0080 00410e10 8602490d 064b8e03 8d048c05 .A....I..K...... - 0090 44830603 1b020c07 08000000 48000000 D...........H... - 00a0 a0000000 00000000 7d0f0000 00450c0a ........}....E.. - 00b0 004c1006 0276004a 0f037658 06100f02 .L...v.J..vX.... - 00c0 7678100e 02767010 0d027668 100c0276 vx...vp...vh...v - 00d0 60481003 02765003 12050a0c 0a004f0c `H...vP.......O. - 00e0 0708440b 00000000 ..D..... + 0050 00000000 5e000000 00000000 10000000 ....^........... + 0060 60000000 00000000 88000000 00000000 `............... + 0070 10000000 74000000 00000000 5c000000 ....t.......\... + 0080 00000000 50000000 88000000 00000000 ....P........... + 0090 9c0a0000 00420e10 8f02420e 188e0342 .....B....B....B + 00a0 0e208d04 420e288c 05410e30 8606410e . ..B.(..A.0..A. + 00b0 38830747 0ee00203 df040a0e 38410e30 8..G........8A.0 + 00c0 410e2842 0e20420e 18420e10 440e0844 A.(B. B..B..D..D + 00d0 0b000000 00000000 ........ /usr/lib64/libopenblas_openmp.a/sgemv_n_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sgemv_n_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sgemv_n_SKYLAKEX.o (disasm) @@ -167,6 +167,32 @@ data16 cs nopw offset(%rax,%rax,1) nopl offset(%rax) +sgemv_kernel_4x2: + mov (%rsi),%r9 + xor %eax,%eax + mov offset(%rsi),%rsi + movss (%rdx),%xmm12 + movss (%r8),%xmm4 + movss offset(%rdx),%xmm13 + mulss %xmm4,%xmm12 + mulss %xmm4,%xmm13 + shufps $something,%xmm12,%xmm12 + shufps $something,%xmm13,%xmm13 + movups (%rcx,%rax,4),%xmm4 + movups (%r9,%rax,4),%xmm8 + movups (%rsi,%rax,4),%xmm9 + mulps %xmm12,%xmm8 + mulps %xmm13,%xmm9 + addps %xmm8,%xmm4 + add $something,%rax + addps %xmm9,%xmm4 + movups %xmm4,-offset(%rcx,%rax,4) + sub $something,%rdi + jne + vzeroupper + ret + xchg %ax,%ax + sgemv_kernel_4x1: mov %rdi,%rax mov %rdx,%r9 @@ -233,525 +259,376 @@ ret nopl offset(%rax) -sgemv_kernel_n_64.isra.0: - push %rbp - mov %rdi,%r10 - mov %rdx,%r11 - mov %rsp,%rbp - push %r14 - vbroadcastss %xmm0,%ymm5 - push %r13 - push %r12 - mov %rdi,%r12 - push %rbx - mov %rcx,%rbx - and $something,%r12 - jle - mov %r9,%rcx - mov %rdx,%r14 - lea offset(,%rbx,4),%rdi - xor %r13d,%r13d - nopw offset(%rax,%rax,1) - vxorps %xmm1,%xmm1,%xmm1 - mov %r14,%rax - vmovaps %ymm1,%ymm2 - vmovaps %ymm1,%ymm3 - vmovaps %ymm1,%ymm4 - xor %edx,%edx - nopl (%rax) - vbroadcastss (%r8,%rdx,4),%ymm0 - inc %rdx - vfmadd231ps (%rax),%ymm0,%ymm4 - vfmadd231ps offset(%rax),%ymm0,%ymm3 - vfmadd231ps offset(%rax),%ymm0,%ymm2 - vfmadd231ps offset(%rax),%ymm0,%ymm1 - add %rdi,%rax - cmp %rsi,%rdx - jne - vfmadd213ps (%rcx),%ymm5,%ymm4 - vfmadd213ps offset(%rcx),%ymm5,%ymm3 - vfmadd213ps offset(%rcx),%ymm5,%ymm2 - vfmadd213ps offset(%rcx),%ymm5,%ymm1 - add $something,%r13 - vmovups %ymm4,(%rcx) - vmovups %ymm3,offset(%rcx) - vmovups %ymm2,offset(%rcx) - vmovups %ymm1,offset(%rcx) - sub $something,%r14 - sub $something,%rcx - cmp %r13,%r12 - jg - cmp %r12,%r10 - je - mov %r10,%r14 - and $something,%r14 - cmp %r14,%r12 - jge - lea offset(,%r12,4),%r13 - lea (%r9,%r13,1),%rdi - lea offset(,%rbx,4),%rcx - add %r11,%r13 - nopw offset(%rax,%rax,1) - vxorps %xmm1,%xmm1,%xmm1 - mov %r13,%rdx - vmovaps %ymm1,%ymm2 - xor %eax,%eax - nopl (%rax) - vbroadcastss (%r8,%rax,4),%ymm0 - inc %rax - vfmadd231ps (%rdx),%ymm0,%ymm2 - vfmadd231ps offset(%rdx),%ymm0,%ymm1 - add %rcx,%rdx - cmp %rax,%rsi - jne - vfmadd213ps (%rdi),%ymm5,%ymm2 - vfmadd213ps offset(%rdi),%ymm5,%ymm1 - add $something,%r12 - add $something,%rdi - add $something,%r13 - vmovups %ymm2,-offset(%rdi) - vmovups %ymm1,-offset(%rdi) - cmp %r12,%r14 - jg - cmp %r14,%r10 - je - mov %r10,%r12 - and $something,%r12 - cmp %r12,%r14 - jge - lea -offset(%r12),%rcx - sub %r14,%rcx - and $something,%rcx - lea offset(,%r14,4),%rdx - add %r14,%rcx - lea (%r11,%rdx,1),%rax - lea offset(%r11,%rcx,4),%rcx - add %r9,%rdx - lea offset(,%rbx,4),%rdi - vxorps %xmm1,%xmm1,%xmm1 - cs nopw offset(%rax,%rax,1) - vbroadcastss (%r8),%ymm0 - vfmadd132ps (%rax),%ymm1,%ymm0 - cmp $something,%rsi - jne - vbroadcastss offset(%r8),%ymm6 - vfmadd231ps (%rdi,%rax,1),%ymm6,%ymm0 - vfmadd213ps (%rdx),%ymm5,%ymm0 - add $something,%rax - add $something,%rdx - vmovups %ymm0,-offset(%rdx) - cmp %rax,%rcx - jne - cmp %r12,%r10 - je - and $something,%r10d - mov $something,%eax - sub %r10d,%eax - mov %eax,%edx - mov $something,%eax - sarx %edx,%eax,%eax - kmovd %eax,%k1 - lea offset(,%r12,4),%rax - vmovups (%r11,%rax,1),%ymm0{%k1}{z} - vxorps %xmm1,%xmm1,%xmm1 - vfmadd132ps (%r8){1to8},%ymm1,%ymm0{%k1}{z} - cmp $something,%rsi - jne - add %rbx,%r12 - vmovups (%r11,%r12,4),%ymm1{%k1}{z} - vfmadd231ps offset(%r8){1to8},%ymm1,%ymm0{%k1}{z} - add %rax,%r9 - vmovups (%r9),%ymm1{%k1}{z} - vfmadd132ps %ymm5,%ymm1,%ymm0{%k1}{z} - vmovups %ymm0,(%r9){%k1} - vzeroupper - pop %rbx - pop %r12 - pop %r13 - pop %r14 - pop %rbp - ret - data16 cs nopw offset(%rax,%rax,1) - sgemv_n_SKYLAKEX: - lea offset(%rsp),%r10 - and $something,%rsp - push -offset(%r10) - push %rbp - mov %rsp,%rbp push %r15 push %r14 push %r13 push %r12 - push %r10 + push %rbp push %rbx sub $something,%rsp - mov offset(%r10),%rax - mov %rcx,-offset(%rbp) - mov %rax,-offset(%rbp) - mov (%r10),%rcx - mov offset(%r10),%rax - mov %rsi,-offset(%rbp) - mov %r8,-offset(%rbp) /usr/lib64/libopenblas_openmp.a/sgemv_n_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sgemv_n_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sgemv_n_SKYLAKEX.o (objdump) @@ -51,302 +51,194 @@ 02e0 c46255b8 cec57c11 0481c57c 114c8120 .bU...|....|.L. 02f0 4883c010 4883ef10 759ac5f8 77c5f877 H...H...u...w..w 0300 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. - 0310 4889f849 89d14883 e0f883e7 0431d2f3 H..I..H......1.. - 0320 450f1021 f3450f59 20450fc6 e4004883 E..!.E.Y E....H. - 0330 f800743a 0f102491 0f106c91 10440f10 ..t:..$...l..D.. - 0340 0496440f 104c9610 450f59c4 450f59cc ..D..L..E.Y.E.Y. - 0350 440f58c4 440f58cd 4883c208 440f1144 D.X.D.X.H...D..D - 0360 91e0440f 114c91f0 4883e808 75c648f7 ..D..L..H...u.H. - 0370 c7040000 00741d0f 10249144 0f100496 .....t...$.D.... - 0380 450f59c4 410f58e0 0f112491 4883c204 E.Y.A.X...$.H... - 0390 4883e804 c5f877c3 0f1f8400 00000000 H.....w......... - 03a0 4883f901 743248c1 e102488d 04be4885 H...t2H...H...H. - 03b0 ff7e480f 1f440000 c5fa1002 4883c604 .~H..D......H... - 03c0 c5fa5846 fcc5fa11 024801ca 4839f075 ..XF.....H..H9.u - 03d0 e7c3660f 1f440000 31c0440f 10248644 ..f..D..1.D..$.D - 03e0 0f101c82 450f58dc 4883c004 440f115c ....E.X.H...D..\ - 03f0 82f04883 ef0475e2 c5f877c3 0f1f4000 ..H...u...w...@. - 0400 554989fa 4989d348 89e54156 c4e27d18 UI..I..H..AV..}. - 0410 e8415541 544989fc 534889cb 4983e4e0 .AUATI..SH..I... - 0420 0f8e9500 00004c89 c94989d6 488d3c9d ......L..I..H.<. - 0430 00000000 4531ed66 0f1f8400 00000000 ....E1.f........ - 0440 c5f057c9 4c89f0c5 fc28d1c5 fc28d9c5 ..W.L....(...(.. - 0450 fc28e131 d20f1f00 c4c27d18 049048ff .(.1......}...H. - 0460 c2c4e27d b820c4e2 7db85820 c4e27db8 ...}. ..}.X ..}. - 0470 5040c4e2 7db84860 4801f848 39f275d8 P@..}.H`H..H9.u. - 0480 c4e255a8 21c4e255 a85920c4 e255a851 ..U.!..U.Y ..U.Q - 0490 40c4e255 a8496049 83c520c5 fc1121c5 @..U.I`I.. ...!. - 04a0 fc115920 c5fc1151 40c5fc11 49604983 ..Y ...Q@...I`I. - 04b0 ee804883 e9804d39 ec7f854d 39e20f84 ..H...M9...M9... - 04c0 65010000 4d89d649 83e6f04d 39f47d72 e...M..I...M9.}r - 04d0 4e8d2ca5 00000000 4b8d3c29 488d0c9d N.,.....K.<)H... - 04e0 00000000 4d01dd66 0f1f8400 00000000 ....M..f........ - 04f0 c5f057c9 4c89eac5 fc28d131 c00f1f00 ..W.L....(.1.... - 0500 c4c27d18 048048ff c0c4e27d b812c4e2 ..}...H....}.... - 0510 7db84a20 4801ca48 39c675e4 c4e255a8 }.J H..H9.u...U. - 0520 17c4e255 a84f2049 83c41048 83c74049 ...U.O I...H..@I - 0530 83c540c5 fc1157c0 c5fc114f e04d39e6 ..@...W....O.M9. - 0540 7fae4d39 f20f84de 0000004d 89d44983 ..M9.......M..I. - 0550 e4f84d39 e67d6c49 8d4c24ff 4c29f148 ..M9.}lI.L$.L).H - 0560 83e1f84a 8d14b500 0000004c 01f1498d ...J.......L..I. - 0570 0413498d 4c8b204c 01ca488d 3c9d0000 ..I.L. L..H.<... - 0580 0000c5f0 57c9662e 0f1f8400 00000000 ....W.f......... - 0590 c4c27d18 00c4e275 98004883 fe02750c ..}....u..H...u. - 05a0 c4c27d18 7004c4e2 4db80407 c4e255a8 ..}.p...M.....U. - 05b0 024883c0 204883c2 20c5fc11 42e04839 .H.. H.. ...B.H9 - 05c0 c175cd4d 39e27461 4183e207 b8080000 .u.M9.taA....... - 05d0 004429d0 89c2b8ff 000000c4 e26af7c0 .D)..........j.. - 05e0 c5fb92c8 4a8d04a5 00000000 62d17ca9 ....J.......b.|. - 05f0 100403c5 f057c962 d275b998 004883fe .....W.b.u...H.. - 0600 02751149 01dc6291 7ca9100c a362d275 .u.I..b.|....b.u - 0610 b9b84001 4901c162 d17ca910 0962f275 ..@.I..b.|...b.u - 0620 a998c562 d17c2911 01c5f877 5b415c41 ...b.|)....w[A\A - 0630 5d415e5d c366662e 0f1f8400 00000000 ]A^].ff......... - 0640 4c8d5424 084883e4 c041ff72 f8554889 L.T$.H...A.r.UH. - 0650 e5415741 56415541 54415253 4881ec40 .AWAVAUATARSH..@ - 0660 01000049 8b420848 898d48ff ffff4889 ...I.B.H..H...H. - 0670 8530ffff ff498b0a 498b4210 4889b5c8 .0...I..I.B.H... - 0680 feffff4c 8985e0fe ffff4c89 8d18ffff ...L......L..... - 0690 ff48898d 10ffffff 48898528 ffffffc5 .H......H..(.... - 06a0 fa11857c ffffff4d 8b721864 488b0425 ...|...M.r.dH..% - 06b0 28000000 488945c8 31c04885 ff0f8e95 (...H.E.1.H..... - 06c0 04000048 85f60f8e 8c040000 4883fe30 ...H........H..0 - 06d0 0f9ec248 83fe040f 95c084c2 740d4881 ...H........t.H. - 06e0 ff004000 000f8eb3 07000048 8b85e0fe ..@........H.... - 06f0 ffff488d 0c850000 00004889 8d38ffff ..H.......H..8.. - 0700 ff488b8d c8feffff 48c1e003 4889ce48 .H......H...H..H - 0710 c1fe0283 e1034883 bd10ffff ff014889 ......H.......H. - 0720 b568ffff ff48898d 58ffffff 751f488b .h...H..X...u.H. - 0730 8dc8feff ff4889ce 48c1fe03 83e10748 .....H..H......H - 0740 89b568ff ffff4889 8d58ffff ff4889f9 ..h...H..X...H.. - 0750 83e10348 8b9de0fe ffff4889 fe81e7ff ...H......H..... - 0760 0f000048 29cf488d 14850000 00004889 ...H).H.......H. - 0770 8da8feff ff488d04 dd000000 004889f9 .....H.......H.. - 0780 4889bdd8 feffff48 8d3c9d00 00000048 H......H.<.....H - 0790 89bd20ff ffff4889 85a0feff ff488bbd .. ...H......H.. - 07a0 10ffffff 488d048d 00000000 488b8d18 ....H.......H... - 07b0 ffffff48 8985d0fe ffff4c8d 3cbd0000 ...H......L.<... - 07c0 00004889 f8488d3c f94889bd f0feffff ..H..H.<.H...... - 07d0 488bbd68 ffffff48 83e6fc48 c1e00448 H..h...H...H...H - 07e0 89b508ff ffff4889 8570ffff ff488bb5 ......H..p...H.. - 07f0 38ffffff 480fafc7 48c1e602 4889b500 8...H...H...H... - 0800 ffffff48 01c8480f aff74889 95c0feff ...H..H...H..... - 0810 ff480faf d748c1e7 05488985 f8feffff .H...H...H...... - 0820 4889f848 01c84889 b5e8feff ff488995 H..H..H......H.. - 0830 b8feffff 488985b0 feffff0f 1f440000 ....H........D.. - 0840 4881ad08 ffffff00 10000048 c78540ff H..........H..@. - 0850 ffff0040 000041bd 00100000 0f882e04 ...@..A......... - 0860 0000488b bd20ffff ff488b85 48ffffff ..H.. ...H..H... - 0870 48894580 4801f848 89458848 01f84889 H.E.H..H.E.H..H. - 0880 45904801 f84883bd 28ffffff 01488945 E.H..H..(....H.E - 0890 980f8409 03000031 f64a8d14 ad000000 .......1.J...... - 08a0 004c89f7 e8000000 004883bd 10ffffff .L.......H...... - 08b0 010f84fe 02000048 83bd68ff ffff000f .......H..h..... - 08c0 84730400 00488d7d 80488d9d 7cffffff .s...H.}.H..|... - 08d0 4c8b8df0 feffff48 8b8518ff ffff4889 L......H......H. - 08e0 bd50ffff ff4c8d65 a04531d2 4989d848 .P...L.e.E1.I..H - 08f0 8b9d00ff ffff4c89 ad60ffff ff4c89f1 ......L..`...L.. - 0900 4d89fd4c 89e24d89 cf4d89d6 4989c490 M..L..M..M..I... - 0910 c4c17a10 0424488b b550ffff ffc5fa11 ..z..$H..P...... - 0920 45a0c481 7a10042c 488bbd60 ffffffc5 E...z..,H..`.... - 0930 fa1145a4 c4c17a10 0749ffc6 c5fa1145 ..E...z..I.....E - 0940 a8c4817a 10042f4c 03a570ff ffffc5fa ...z../L..p..... - 0950 1145ace8 78f8ffff 48015d80 48015d88 .E..x...H.].H.]. - 0960 48015d90 48015d98 4c03bd70 ffffff4c H.].H.].L..p...L - 0970 39b568ff ffff7598 488bb548 ffffff4d 9.h...u.H..H...M - 0980 89ef4c8b 95f8feff ff4c8bad 60ffffff ..L......L..`... - 0990 4989ce48 03b5e8fe ffff4883 bd58ffff I..H......H..X.. - 09a0 ff007446 4531db48 8d9d7cff ffff4989 ..tFE1.H..|...I. - 09b0 d84c89db 4c8b9d20 ffffff4c 8d65a090 .L..L.. ...L.e.. - 09c0 c4c17a10 024c89f1 4c89e24c 89ef48ff ..z..L..L..L..H. - 09d0 c3c5fa11 45a04d01 fae832f9 ffff4c01 ....E.M...2...L. - 09e0 de48399d 58ffffff 75d6488b bd40ffff .H9.X...u.H..@.. - 09f0 ff488b9d 28ffffff 4801bd48 ffffff48 .H..(...H..H...H - 0a00 83fb010f 847f0100 004c8b9d 30ffffff .........L..0... - 0a10 4889d94c 89da4c89 f64c89ef e87ff9ff H..L..L..L...... - 0a20 ff4889d8 490fafc5 498d0483 48898530 .H..I...I...H..0 - 0a30 ffffff49 81fd0010 00000f84 00feffff ...I............ - 0a40 488bbda8 feffff48 85ff0f84 08010000 H......H........ - 0a50 4883bd10 ffffff01 0f94c048 83ff030f H..........H.... - 0a60 84070900 004883bd a8feffff 020f84eb .....H.......... - 0a70 02000048 83bde0fe ffff010f 85ab0800 ...H............ - 0a80 0084c00f 84a30800 00488b95 c8feffff .........H...... - 0a90 4883e2fc 0f84e20a 000048ff ca48c1ea H.........H..H.. - 0aa0 0248ffc2 488bbd48 ffffff48 89d648c1 .H..H..H...H..H. - 0ab0 e604488b 8d18ffff ff4889f8 4801fec5 ..H......H..H... - 0ac0 f057c90f 1f440000 c5fa1040 04c5fa10 .W...D.....@.... - 0ad0 38c5fa59 41044883 c0104883 c110c4e2 8..YA.H...H..... - 0ae0 41b941f0 c5fa1078 f8c4e241 b941f8c5 A.A....x...A.A.. - 0af0 fa1078fc c4e241b9 41fcc5f2 58c84839 ..x...A.A...X.H9 - 0b00 c675c548 c1e20248 3995c8fe ffff7e2b .u.H...H9.....~+ - 0b10 488b85c8 feffff48 8b8d48ff ffff488b H......H..H...H. - 0b20 b518ffff ff0f1f00 c5fa102c 91c4e251 ...........,...Q - 0b30 b90c9648 ffc24839 d07fed48 8b8530ff ...H..H9...H..0. - 0b40 ffffc5fa 1028c4e2 51998d7c ffffffc5 .....(..Q..|.... - 0b50 fa11080f 1f440000 488b45c8 64482b04 .....D..H.E.dH+. - 0b60 25280000 000f854d 0a000048 81c44001 %(.....M...H..@. - 0b70 00005b41 5a415c41 5d415e41 5f31c05d ..[AZA\A]A^A_1.] - 0b80 498d62f8 c30f1f00 488bbd40 ffffff48 I.b.....H..@...H - 0b90 01bd30ff ffffe998 feffff0f 1f440000 ..0..........D.. - 0ba0 4883bd10 ffffff01 4c8bb530 ffffff0f H.......L..0.... - 0bb0 8502fdff ff4883bd 68ffffff 000f8488 .....H..h....... - 0bc0 01000045 31e4488d 9d7cffff ff4c89bd ...E1.H..|...L.. - 0bd0 60ffffff 488d4580 488b9518 ffffff4c `...H.E.H......L - 0be0 8bbdc0fe ffff4989 d94c89e3 4989c490 ......I..L..I... - 0bf0 4c8b8538 ffffff4c 89f14c89 e64c89ef L..8...L..L..L.. - 0c00 48ffc3e8 f8f3ffff 4c017d80 4c017d88 H.......L.}.L.}. - 0c10 4c017d90 4c017d98 4883c220 48399d68 L.}.L.}.H.. H9.h - 0c20 ffffff75 cb4c8ba5 48ffffff 4c8bbd60 ...u.L..H...L..` - 0c30 ffffff48 8b9db0fe ffff4c03 a5b8feff ...H......L..... - 0c40 fff68558 ffffff04 756ef685 58ffffff ...X....un..X... - 0c50 020f85a8 000000f6 8558ffff ff010f84 .........X...... - 0c60 86fdffff 488b8de0 feffffc5 fa10857c ....H..........| - 0c70 ffffff4d 89f14989 d84c89e2 be010000 ...M..I..L...... - 0c80 004c89ef e877f7ff ffe95cfd ffff6690 .L...w....\...f. - 0c90 4c8badd8 feffff4d 85ed0f84 a0fdffff L......M........ - 0ca0 488b85d0 feffff48 898540ff ffffe9af H......H..@..... - 0cb0 fbffff0f 1f440000 488d4580 4889da48 .....D..H.E.H..H - 0cc0 89c64c8d 857cffff ff4c89f1 4c89efe8 ..L..|...L..L... - 0cd0 fcf4ffff 488b8500 ffffff48 83c31048 ....H......H...H - 0ce0 01458048 01458848 01459048 01459849 .E.H.E.H.E.H.E.I - 0cf0 01c4f685 58ffffff 020f8458 ffffff48 ....X......X...H - 0d00 8b8de0fe ffffc5fa 10857cff ffff4989 ..........|...I. - 0d10 d84c89e2 4d89f1be 02000000 4c89efe8 .L..M.......L... - 0d20 dcf6ffff 4883c308 4c03a5a0 feffffe9 ....H...L....... - 0d30 23ffffff 0f1f4000 4c8b9518 ffffff48 #.....@.L......H - 0d40 8bb548ff ffffe94f fcffff48 8b9d18ff ..H....O...H.... - 0d50 ffff4c8b a548ffff ffe9e3fe ffff4883 ..L..H........H. - 0d60 bde0feff ff020f85 76070000 84c00f84 ........v....... - 0d70 6e070000 488b95c8 feffff48 83e2fc0f n...H......H.... - 0d80 84260800 00c5f857 c0488b85 48ffffff .&.....W.H..H... - 0d90 488bb518 ffffffc5 f828d031 c9c5fa10 H........(.1.... - 0da0 648e04c5 fa100c8e c5da5958 08c5da59 d.........YX...Y - 0db0 600c4883 c020c4e2 71b958e0 c4e25999 `.H.. ..q.X...Y. - 0dc0 48e4c5e2 58d2c5fa 105c8e0c c5f258c0 H...X....\....X. - 0dd0 c5e25960 f8c5e259 58fcc5fa 104c8e08 ..Y`...YX....L.. - 0de0 4883c104 c4e271b9 60f0c4e2 619948f4 H.....q.`...a.H. - 0df0 c5da58d2 c5f258c0 4839ca7f a048ffca ..X...X.H9...H.. - 0e00 48c1ea02 48ffc248 89d048c1 e0054801 H...H..H..H...H. - 0e10 8548ffff ff4889d0 48c1e004 48c1e202 .H...H..H...H... - 0e20 48018518 ffffff48 3995c8fe ffff7e3d H......H9.....~= - 0e30 488b8548 ffffff48 8bbd18ff ffff4889 H..H...H......H. - 0e40 d148f7d9 488bb5c8 feffff48 8d04c848 .H..H......H...H - 0e50 8d0c8fc5 fa100c91 c4e271b9 14d0c4e2 ..........q..... - 0e60 71b944d0 0448ffc2 4839d67f e6488b85 q.D..H..H9...H.. - 0e70 30ffffff c5fa108d 7cffffff 488bbd28 0.......|...H..( - 0e80 ffffffc4 e271a910 c5fa1110 488d04b8 .....q......H... - 0e90 c4e279a9 08c5fa11 08e9bafc ffff4883 ..y...........H. - 0ea0 f9017428 48c1e102 4c89ca31 c00f1f00 ..t(H...L..1.... - 0eb0 c5fa1002 4801cac4 c17a1104 8648ffc0 ....H....z...H.. - 0ec0 4839c67f eb4c89b5 18ffffff 488b9530 H9...L......H..0 - 0ed0 ffffff48 8b8528ff ffff4889 d64883f8 ...H..(...H..H.. - 0ee0 01743148 8b8dc8fe ffff498d 348e488d .t1H......I.4.H. - 0ef0 0c850000 000031c0 0f1f8400 00000000 ......1......... - 0f00 c5fa1002 4801cac5 fa110486 48ffc048 ....H.......H..H - 0f10 39c77fec 4989f962 727d4818 4ddf4983 9...I..br}H.M.I. - 0f20 e1800f84 43010000 488b85e0 feffff4c ....C...H......L /usr/lib64/libopenblas_openmp.a/sgemv_n_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/sgemv_n_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sgemv_n_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/sgemv_n_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/sgemv_n_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sgemv_n_SKYLAKEX.o (objdump) @@ -7,13 +7,12 @@ 0020 00000000 c4010000 00410e10 830203c2 .........A...... 0030 010e0800 10000000 38000000 00000000 ........8....... 0040 31010000 00000000 10000000 4c000000 1...........L... - 0050 00000000 88000000 00000000 10000000 ................ - 0060 60000000 00000000 5c000000 00000000 `.......\....... - 0070 28000000 74000000 00000000 35020000 (...t.......5... - 0080 00410e10 8602490d 064b8e03 8d048c05 .A....I..K...... - 0090 44830603 1b020c07 08000000 48000000 D...........H... - 00a0 a0000000 00000000 7d0f0000 00450c0a ........}....E.. - 00b0 004c1006 0276004a 0f037658 06100f02 .L...v.J..vX.... - 00c0 7678100e 02767010 0d027668 100c0276 vx...vp...vh...v - 00d0 60481003 02765003 12050a0c 0a004f0c `H...vP.......O. - 00e0 0708440b 00000000 ..D..... + 0050 00000000 5e000000 00000000 10000000 ....^........... + 0060 60000000 00000000 88000000 00000000 `............... + 0070 10000000 74000000 00000000 5c000000 ....t.......\... + 0080 00000000 50000000 88000000 00000000 ....P........... + 0090 9c0a0000 00420e10 8f02420e 188e0342 .....B....B....B + 00a0 0e208d04 420e288c 05410e30 8606410e . ..B.(..A.0..A. + 00b0 38830747 0ee00203 df040a0e 38410e30 8..G........8A.0 + 00c0 410e2842 0e20420e 18420e10 440e0844 A.(B. B..B..D..D + 00d0 0b000000 00000000 ........ /usr/lib64/libopenblas_openmp.a/sneg_tcopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/sneg_tcopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/sneg_tcopy_COOPERLAKE.o (disasm) @@ -6,82 +6,273 @@ sneg_tcopy_COOPERLAKE: push %r15 - mov %rdi,%r11 - mov %rdx,%r10 + mov %rsi,%rax + and $something,%rax push %r14 push %r13 push %r12 + mov %r8,%r12 push %rbp - mov %rsi,%rbp - sar $something,%rbp push %rbx - mov %rsi,%rbx - mov %rcx,-offset(%rsp) - mov %rbp,-offset(%rsp) - test %rbp,%rbp + mov %rdi,%rbx + imul %rbx,%rax + sub $something,%rsp + mov %rdi,offset(%rsp) + lea (%r8,%rax,4),%r13 + mov %rsi,%rax + and $something,%rax + imul %rbx,%rax + mov %rsi,offset(%rsp) + mov %rsi,%rdi + lea (%r8,%rax,4),%r15 + mov %rsi,%rax + and $something,%rax + imul %rbx,%rax + mov %rbx,%rsi + sar $something,%rsi + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %rsi,offset(%rsp) + lea (%r8,%rax,4),%r14 + test %rsi,%rsi jle - mov %rdi,%r12 - lea offset(,%rcx,8),%rdi - sar %r12 mov %rdi,%rax - imul %r12,%rax - mov %rcx,%rsi - mov %r12,%rcx - mov %r11,%r13 + sar $something,%rax + mov %rcx,%r8 + lea offset(,%rcx,4),%r11 + mov %rax,offset(%rsp) shl $something,%rcx - lea -offset(,%rsi,4),%rsi + shl $something,%rax + add %rdx,%rax + mov %rcx,offset(%rsp) + mov %rdi,%rcx + and $something,%ecx + mov %rax,offset(%rsp) + lea offset(,%r8,8),%rax + mov %rcx,offset(%rsp) + mov %rax,offset(%rsp) + mov %rdi,%rcx + lea (%r8,%r8,2),%rax + and $something,%edi + mov %rdi,offset(%rsp) + lea offset(,%rax,4),%rdi + shl $something,%rax + mov %rdx,%rbp + and $something,%ecx + mov %rax,offset(%rsp) + mov %r11,%rdx + imul $something,%r8,%rax + add %r8,%rdx + mov %rcx,offset(%rsp) + mov %r8,%rcx + shl $something,%rcx + mov %rdi,offset(%rsp) + shl $something,%rbx + lea offset(,%rdx,4),%rdi vmovss offset(%rip),%xmm0 # - sub $something,%rax - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) - mov %rax,-offset(%rsp) - and $something,%r13d - mov %rdx,%r9 - vmovaps %xmm0,%xmm31 + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rsi,offset(%rsp) + mov %r11,offset(%rsp) + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + mov %r12,offset(%rsp) + mov %r12,offset(%rsp) + vmovaps %xmm0,%xmm1 + mov %rbp,%rcx + mov %r13,%rsi + mov %r15,%rdi + mov %r14,%r8 jmp - nopl offset(%rax) - test %r13,%r13 + nopl offset(%rax,%rax,1) + cmpq $something,offset(%rsp) je - vmovss offset(%rdx),%xmm15 - vmovss offset(%rdx),%xmm14 - vmovss offset(%rdx),%xmm13 - vmovss offset(%rdx),%xmm12 - vmovss offset(%rdx),%xmm11 - vmovss offset(%rdx),%xmm10 - vmovss offset(%rdx),%xmm9 - vmovss offset(%rdx),%xmm8 - vmovss offset(%rdx),%xmm7 - vmovss offset(%rdx),%xmm6 - vmovss offset(%rdx),%xmm5 - vmovss offset(%rdx),%xmm4 - vmovss offset(%rdx),%xmm3 - vmovss offset(%rdx),%xmm2 - vmovss offset(%rdx),%xmm1 - vmovss (%rdx),%xmm16 - vxorps %xmm31,%xmm15,%xmm15 - vxorps %xmm31,%xmm16,%xmm16 - vxorps %xmm31,%xmm14,%xmm14 - vxorps %xmm31,%xmm13,%xmm13 - vxorps %xmm31,%xmm12,%xmm12 - vxorps %xmm31,%xmm11,%xmm11 - vxorps %xmm31,%xmm10,%xmm10 - vxorps %xmm31,%xmm9,%xmm9 - vxorps %xmm31,%xmm8,%xmm8 - vxorps %xmm31,%xmm7,%xmm7 - vxorps %xmm31,%xmm6,%xmm6 - vxorps %xmm31,%xmm5,%xmm5 - vxorps %xmm31,%xmm4,%xmm4 - vxorps %xmm31,%xmm3,%xmm3 - vxorps %xmm31,%xmm2,%xmm2 - vxorps %xmm31,%xmm1,%xmm1 - vmovss %xmm16,(%r8) - vmovss %xmm15,offset(%r8) - vmovss %xmm14,offset(%r8) - vmovss %xmm13,offset(%r8) - vmovss %xmm12,offset(%r8) - vmovss %xmm11,offset(%r8) - vmovss %xmm10,offset(%r8) - vmovss %xmm9,offset(%r8) + mov (%r9),%edx + mov offset(%r9),%eax + vmovss offset(%r11),%xmm7 + vmovd %edx,%xmm2 + mov offset(%r10),%r15d + vxorps %xmm1,%xmm2,%xmm2 + vmovss offset(%r9),%xmm31 + vmovss offset(%r9),%xmm30 + vmovss (%r14),%xmm29 + vmovss offset(%r14),%xmm28 + vmovss offset(%r14),%xmm27 + vmovss offset(%r14),%xmm26 + vmovss offset(%r13),%xmm25 + vmovss offset(%r13),%xmm24 + vmovss offset(%r13),%xmm23 + vmovss offset(%r13),%xmm22 + vmovss (%r12),%xmm21 + vmovss offset(%r12),%xmm20 + vmovss offset(%r12),%xmm19 + vmovss offset(%r12),%xmm18 + vmovss offset(%rbp),%xmm17 + vmovss offset(%rbp),%xmm16 + vmovss offset(%rbp),%xmm15 + vmovss offset(%rbp),%xmm14 + vmovss (%rbx),%xmm13 + vmovss offset(%rbx),%xmm12 + vmovss offset(%rbx),%xmm11 + vmovss offset(%rbx),%xmm10 + vmovss (%r11),%xmm9 + vmovss offset(%r11),%xmm8 + vmovss offset(%r11),%xmm6 + vmovss (%r10),%xmm5 + vmovss offset(%r10),%xmm4 + vmovss offset(%r10),%xmm3 + vxorps %xmm1,%xmm7,%xmm7 + vmovss %xmm2,(%rsi) + vmovd %eax,%xmm2 + vxorps %xmm1,%xmm2,%xmm2 + vmovss %xmm7,offset(%rsi) + vmovd %r15d,%xmm7 + vmovss %xmm2,offset(%rsi) + vxorps %xmm1,%xmm31,%xmm31 + vxorps %xmm1,%xmm30,%xmm30 + vxorps %xmm1,%xmm29,%xmm29 + vxorps %xmm1,%xmm28,%xmm28 + vxorps %xmm1,%xmm27,%xmm27 + vxorps %xmm1,%xmm26,%xmm26 + vxorps %xmm1,%xmm25,%xmm25 /usr/lib64/libopenblas_openmp.a/sneg_tcopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sneg_tcopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sneg_tcopy_COOPERLAKE.o (objdump) @@ -2,143 +2,367 @@ /usr/lib64/libopenblas_openmp.a/sneg_tcopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574989 fb4989d2 41564155 41545548 AWI..I..AVAUATUH - 0010 89f548c1 fd045348 89f34889 4c24f048 ..H...SH..H.L$.H - 0020 896c24f8 4885ed0f 8eff0300 004989fc .l$.H........I.. - 0030 488d3ccd 00000000 49d1fc48 89f8490f H.<.....I..H..I. - 0040 afc44889 ce4c89e1 4d89dd48 c1e10748 ..H..L..M..H...H - 0050 8d34b5c0 ffffffc5 fa100500 00000048 .4.............H - 0060 83e84048 894c24d8 48897424 e0488944 ..@H.L$.H.t$.H.D - 0070 24e84183 e5014989 d162617c 0828f8e9 $.A...I..ba|.(.. - 0080 2b010000 0f1f4000 4d85ed0f 84150100 +.....@.M....... - 0090 00c57a10 7a04c57a 107208c5 7a106a0c ..z.z..z.r..z.j. - 00a0 c57a1062 10c57a10 5a14c57a 105218c5 .z.b..z.Z..z.R.. - 00b0 7a104a1c c57a1042 20c5fa10 7a24c5fa z.J..z.B ...z$.. - 00c0 107228c5 fa106a2c c5fa1062 30c5fa10 .r(...j,...b0... - 00d0 5a34c5fa 105238c5 fa104a3c 62e17e08 Z4...R8...J - mov %rdi,%r12 - lea offset(,%rcx,8),%rdi - sar %r12 mov %rdi,%rax - imul %r12,%rax - mov %rcx,%rsi - mov %r12,%rcx - mov %r11,%r13 + sar $something,%rax + mov %rcx,%r8 + lea offset(,%rcx,4),%r11 + mov %rax,offset(%rsp) shl $something,%rcx - lea -offset(,%rsi,4),%rsi + shl $something,%rax + add %rdx,%rax + mov %rcx,offset(%rsp) + mov %rdi,%rcx + and $something,%ecx + mov %rax,offset(%rsp) + lea offset(,%r8,8),%rax + mov %rcx,offset(%rsp) + mov %rax,offset(%rsp) + mov %rdi,%rcx + lea (%r8,%r8,2),%rax + and $something,%edi + mov %rdi,offset(%rsp) + lea offset(,%rax,4),%rdi + shl $something,%rax + mov %rdx,%rbp + and $something,%ecx + mov %rax,offset(%rsp) + mov %r11,%rdx + imul $something,%r8,%rax + add %r8,%rdx + mov %rcx,offset(%rsp) + mov %r8,%rcx + shl $something,%rcx + mov %rdi,offset(%rsp) + shl $something,%rbx + lea offset(,%rdx,4),%rdi vmovss offset(%rip),%xmm0 # - sub $something,%rax - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) - mov %rax,-offset(%rsp) - and $something,%r13d - mov %rdx,%r9 - vmovaps %xmm0,%xmm31 + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rsi,offset(%rsp) + mov %r11,offset(%rsp) + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + mov %r12,offset(%rsp) + mov %r12,offset(%rsp) + vmovaps %xmm0,%xmm1 + mov %rbp,%rcx + mov %r13,%rsi + mov %r15,%rdi + mov %r14,%r8 jmp - nopl offset(%rax) - test %r13,%r13 + nopl offset(%rax,%rax,1) + cmpq $something,offset(%rsp) je - vmovss offset(%rdx),%xmm15 - vmovss offset(%rdx),%xmm14 - vmovss offset(%rdx),%xmm13 - vmovss offset(%rdx),%xmm12 - vmovss offset(%rdx),%xmm11 - vmovss offset(%rdx),%xmm10 - vmovss offset(%rdx),%xmm9 - vmovss offset(%rdx),%xmm8 - vmovss offset(%rdx),%xmm7 - vmovss offset(%rdx),%xmm6 - vmovss offset(%rdx),%xmm5 - vmovss offset(%rdx),%xmm4 - vmovss offset(%rdx),%xmm3 - vmovss offset(%rdx),%xmm2 - vmovss offset(%rdx),%xmm1 - vmovss (%rdx),%xmm16 - vxorps %xmm31,%xmm15,%xmm15 - vxorps %xmm31,%xmm16,%xmm16 - vxorps %xmm31,%xmm14,%xmm14 - vxorps %xmm31,%xmm13,%xmm13 - vxorps %xmm31,%xmm12,%xmm12 - vxorps %xmm31,%xmm11,%xmm11 - vxorps %xmm31,%xmm10,%xmm10 - vxorps %xmm31,%xmm9,%xmm9 - vxorps %xmm31,%xmm8,%xmm8 - vxorps %xmm31,%xmm7,%xmm7 - vxorps %xmm31,%xmm6,%xmm6 - vxorps %xmm31,%xmm5,%xmm5 - vxorps %xmm31,%xmm4,%xmm4 - vxorps %xmm31,%xmm3,%xmm3 - vxorps %xmm31,%xmm2,%xmm2 - vxorps %xmm31,%xmm1,%xmm1 - vmovss %xmm16,(%r8) - vmovss %xmm15,offset(%r8) - vmovss %xmm14,offset(%r8) - vmovss %xmm13,offset(%r8) - vmovss %xmm12,offset(%r8) - vmovss %xmm11,offset(%r8) - vmovss %xmm10,offset(%r8) - vmovss %xmm9,offset(%r8) + mov (%r9),%edx + mov offset(%r9),%eax + vmovss offset(%r11),%xmm7 + vmovd %edx,%xmm2 + mov offset(%r10),%r15d + vxorps %xmm1,%xmm2,%xmm2 + vmovss offset(%r9),%xmm31 + vmovss offset(%r9),%xmm30 + vmovss (%r14),%xmm29 + vmovss offset(%r14),%xmm28 + vmovss offset(%r14),%xmm27 + vmovss offset(%r14),%xmm26 + vmovss offset(%r13),%xmm25 + vmovss offset(%r13),%xmm24 + vmovss offset(%r13),%xmm23 + vmovss offset(%r13),%xmm22 + vmovss (%r12),%xmm21 + vmovss offset(%r12),%xmm20 + vmovss offset(%r12),%xmm19 + vmovss offset(%r12),%xmm18 + vmovss offset(%rbp),%xmm17 + vmovss offset(%rbp),%xmm16 + vmovss offset(%rbp),%xmm15 + vmovss offset(%rbp),%xmm14 + vmovss (%rbx),%xmm13 + vmovss offset(%rbx),%xmm12 + vmovss offset(%rbx),%xmm11 + vmovss offset(%rbx),%xmm10 + vmovss (%r11),%xmm9 + vmovss offset(%r11),%xmm8 + vmovss offset(%r11),%xmm6 + vmovss (%r10),%xmm5 + vmovss offset(%r10),%xmm4 + vmovss offset(%r10),%xmm3 + vxorps %xmm1,%xmm7,%xmm7 + vmovss %xmm2,(%rsi) + vmovd %eax,%xmm2 + vxorps %xmm1,%xmm2,%xmm2 + vmovss %xmm7,offset(%rsi) + vmovd %r15d,%xmm7 + vmovss %xmm2,offset(%rsi) + vxorps %xmm1,%xmm31,%xmm31 + vxorps %xmm1,%xmm30,%xmm30 + vxorps %xmm1,%xmm29,%xmm29 + vxorps %xmm1,%xmm28,%xmm28 + vxorps %xmm1,%xmm27,%xmm27 + vxorps %xmm1,%xmm26,%xmm26 + vxorps %xmm1,%xmm25,%xmm25 /usr/lib64/libopenblas_openmp.a/sneg_tcopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/sneg_tcopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/sneg_tcopy_SKYLAKEX.o (objdump) @@ -2,143 +2,367 @@ /usr/lib64/libopenblas_openmp.a/sneg_tcopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574989 fb4989d2 41564155 41545548 AWI..I..AVAUATUH - 0010 89f548c1 fd045348 89f34889 4c24f048 ..H...SH..H.L$.H - 0020 896c24f8 4885ed0f 8eff0300 004989fc .l$.H........I.. - 0030 488d3ccd 00000000 49d1fc48 89f8490f H.<.....I..H..I. - 0040 afc44889 ce4c89e1 4d89dd48 c1e10748 ..H..L..M..H...H - 0050 8d34b5c0 ffffffc5 fa100500 00000048 .4.............H - 0060 83e84048 894c24d8 48897424 e0488944 ..@H.L$.H.t$.H.D - 0070 24e84183 e5014989 d162617c 0828f8e9 $.A...I..ba|.(.. - 0080 2b010000 0f1f4000 4d85ed0f 84150100 +.....@.M....... - 0090 00c57a10 7a04c57a 107208c5 7a106a0c ..z.z..z.r..z.j. - 00a0 c57a1062 10c57a10 5a14c57a 105218c5 .z.b..z.Z..z.R.. - 00b0 7a104a1c c57a1042 20c5fa10 7a24c5fa z.J..z.B ...z$.. - 00c0 107228c5 fa106a2c c5fa1062 30c5fa10 .r(...j,...b0... - 00d0 5a34c5fa 105238c5 fa104a3c 62e17e08 Z4...R8...J cmp $something,%rdx jne cmp $something,%r8 jne - mov %edi,%r10d - mov %edi,%ecx - and $something,%r10d - vbroadcastss %xmm0,%zmm0 - vbroadcastss %xmm1,%zmm2 - and $something,%ecx - jle - movslq %ecx,%rcx - dec %rcx - shr $something,%rcx - mov %rcx,%r8 - shl $something,%r8 - mov %r9,%rax - mov %rsi,%rdx - lea offset(%r9,%r8,1),%r8 - nopl offset(%rax) - vmovups (%rdx),%zmm7 - vmovups offset(%rdx),%zmm6 - vmovups offset(%rdx),%zmm5 - vmovups offset(%rdx),%zmm3 - vmulps %zmm7,%zmm2,%zmm15 - vmulps %zmm6,%zmm2,%zmm14 - vmulps %zmm5,%zmm2,%zmm13 - vmulps %zmm3,%zmm2,%zmm12 - vmovups (%rax),%zmm11 - vmovups offset(%rax),%zmm10 - vmovups offset(%rax),%zmm9 - vmovups offset(%rax),%zmm8 - vfmadd231ps %zmm11,%zmm0,%zmm15 - vfmadd231ps %zmm10,%zmm0,%zmm14 - vfmadd231ps %zmm9,%zmm0,%zmm13 - vfmadd231ps %zmm8,%zmm0,%zmm12 - vmulps %zmm11,%zmm2,%zmm11 - vmulps %zmm10,%zmm2,%zmm10 - vmulps %zmm9,%zmm2,%zmm9 - vmulps %zmm8,%zmm2,%zmm8 - vmovups %zmm15,(%rax) - vfmsub132ps %zmm0,%zmm11,%zmm7 - vfmsub132ps %zmm0,%zmm10,%zmm6 - vfmsub132ps %zmm0,%zmm9,%zmm5 - vfmsub132ps %zmm0,%zmm8,%zmm3 - vmovups %zmm14,offset(%rax) - vmovups %zmm13,offset(%rax) - vmovups %zmm12,offset(%rax) - add $something,%rax - vmovups %zmm7,(%rdx) - vmovups %zmm6,offset(%rdx) - vmovups %zmm5,offset(%rdx) - vmovups %zmm3,offset(%rdx) - add $something,%rdx - cmp %rax,%r8 + mov %r9,%r8 + and $something,%rdi + and $something,%r8 + cmp $something,%r9 + jg + test %r8,%r8 + je + lea -offset(,%r8,4),%r10 + and $something,%r10 + mov %rax,%rdx + mov %rcx,%rsi + lea offset(%rax,%r10,1),%r10 + nop + vmovups (%rsi),%ymm7 + vmovups offset(%rsi),%ymm6 + vmovups offset(%rsi),%ymm5 + vmovups offset(%rsi),%ymm0 + vmulps %ymm2,%ymm7,%ymm15 + vmulps %ymm2,%ymm6,%ymm14 + vmulps %ymm2,%ymm5,%ymm13 + vmulps %ymm2,%ymm0,%ymm12 + vmovups (%rdx),%ymm11 + vmovups offset(%rdx),%ymm10 + vmovups offset(%rdx),%ymm9 + vmovups offset(%rdx),%ymm8 + vfmadd231ps %ymm11,%ymm3,%ymm15 + vfmadd231ps %ymm10,%ymm3,%ymm14 + vfmadd231ps %ymm9,%ymm3,%ymm13 + vfmadd231ps %ymm8,%ymm3,%ymm12 + vmulps %ymm2,%ymm11,%ymm11 + vmulps %ymm2,%ymm10,%ymm10 + vmulps %ymm2,%ymm9,%ymm9 + vmulps %ymm2,%ymm8,%ymm8 + vmovups %ymm15,(%rdx) + vfmsub132ps %ymm3,%ymm11,%ymm7 + vfmsub132ps %ymm3,%ymm10,%ymm6 + vfmsub132ps %ymm3,%ymm9,%ymm5 + vfmsub132ps %ymm3,%ymm8,%ymm0 + vmovups %ymm14,offset(%rdx) + vmovups %ymm13,offset(%rdx) + vmovups %ymm12,offset(%rdx) + sub $something,%rdx + vmovups %ymm7,(%rsi) + vmovups %ymm6,offset(%rsi) + vmovups %ymm5,offset(%rsi) + vmovups %ymm0,offset(%rsi) + sub $something,%rsi + cmp %rdx,%r10 jne - lea offset(%rcx),%rax - shl $something,%rax - movslq %r10d,%rcx - cmp %rax,%rcx + cmp %r8,%rdi jle - mov %rax,%rdx - nopl (%rax) - vmovups (%rsi,%rdx,4),%zmm3 - vmovups (%r9,%rdx,4),%zmm5 - vmulps %zmm3,%zmm2,%zmm6 - vfmadd231ps %zmm5,%zmm0,%zmm6 - vmulps %zmm5,%zmm2,%zmm5 - vmovups %zmm6,(%r9,%rdx,4) - vfmsub132ps %zmm0,%zmm5,%zmm3 - vmovups %zmm3,(%rsi,%rdx,4) - add $something,%rdx - cmp %rcx,%rdx - jl - dec %rcx - sub %rax,%rcx - and $something,%rcx - lea offset(%rax,%rcx,1),%rax - cmp %rax,%rdi + nopw offset(%rax,%rax,1) + vmovups (%rcx,%r8,4),%ymm0 + vmovups (%rax,%r8,4),%ymm5 + vmulps %ymm0,%ymm2,%ymm6 + vfmadd231ps %ymm5,%ymm3,%ymm6 + vmulps %ymm5,%ymm2,%ymm5 + vmovups %ymm6,(%rax,%r8,4) + vfmsub132ps %ymm3,%ymm5,%ymm0 + vmovups %ymm0,(%rcx,%r8,4) + add $something,%r8 + cmp %r8,%rdi + jg + cmp %rdi,%r9 jle - nopl offset(%rax) - vmovss (%rsi,%rax,4),%xmm0 - vmovss (%r9,%rax,4),%xmm2 + nopl offset(%rax,%rax,1) + vmovss (%rcx,%rdi,4),%xmm0 + vmovss (%rax,%rdi,4),%xmm2 vmulss %xmm0,%xmm1,%xmm3 vfmadd231ss %xmm2,%xmm4,%xmm3 vmulss %xmm2,%xmm1,%xmm2 vfmsub132ss %xmm4,%xmm2,%xmm0 - vmovss %xmm0,(%rsi,%rax,4) - vmovss %xmm3,(%r9,%rax,4) - inc %rax - cmp %rax,%rdi + vmovss %xmm0,(%rcx,%rdi,4) + vmovss %xmm3,(%rax,%rdi,4) + inc %rdi + cmp %rdi,%r9 jne vzeroupper ret - nopl offset(%rax) - mov %rsi,%rax + nopw offset(%rax,%rax,1) shl $something,%rdx - mov %r9,%rcx shl $something,%r8 xor %esi,%esi - vmovss (%rax),%xmm0 - vmovss (%rcx),%xmm2 + nopw offset(%rax,%rax,1) + vmovss (%rcx),%xmm0 + vmovss (%rax),%xmm2 vmulss %xmm0,%xmm1,%xmm3 inc %rsi vfmadd231ss %xmm2,%xmm4,%xmm3 vmulss %xmm2,%xmm1,%xmm2 vfmsub132ss %xmm4,%xmm2,%xmm0 - vmovss %xmm0,(%rax) - vmovss %xmm3,(%rcx) - add %r8,%rax - add %rdx,%rcx - cmp %rsi,%rdi + vmovss %xmm0,(%rcx) + vmovss %xmm3,(%rax) /usr/lib64/libopenblas_openmp.a/srot_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/srot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/srot_k_COOPERLAKE.o (objdump) @@ -2,66 +2,59 @@ /usr/lib64/libopenblas_openmp.a/srot_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 4989f1c5 f828e048 89ce4885 ff0f8ed8 I....(.H..H..... - 0010 01000048 83fa010f 85d30100 004983f8 ...H.........I.. - 0020 010f85c9 01000041 89fa89f9 4183e2f0 .......A....A... - 0030 62f27d48 18c062f2 7d4818d1 83e1c00f b.}H..b.}H...... - 0040 8eec0100 004863c9 48ffc948 c1e90649 .....Hc.H..H...I - 0050 89c849c1 e0084c89 c84889f2 4f8d8401 ..I...L..H..O... - 0060 00010000 0f1f4000 62f17c48 103a62f1 ......@.b.|H.:b. - 0070 7c481072 0162f17c 48106a02 62f17c48 |H.r.b.|H.j.b.|H - 0080 105a0362 716c4859 ff62716c 4859f662 .Z.bqlHY.bqlHY.b - 0090 716c4859 ed62716c 4859e362 717c4810 qlHY.bqlHY.bq|H. - 00a0 1862717c 48105001 62717c48 10480262 .bq|H.P.bq|H.H.b - 00b0 717c4810 40036252 7d48b8fb 62527d48 q|H.@.bR}H..bR}H - 00c0 b8f26252 7d48b8e9 62527d48 b8e06251 ..bR}H..bR}H..bQ - 00d0 6c4859db 62516c48 59d26251 6c4859c9 lHY.bQlHY.bQlHY. - 00e0 62516c48 59c06271 7c481138 62f22548 bQlHY.bq|H.8b.%H - 00f0 9af862f2 2d489af0 62f23548 9ae862f2 ..b.-H..b.5H..b. - 0100 3d489ad8 62717c48 11700162 717c4811 =H..bq|H.p.bq|H. - 0110 68026271 7c481160 03480500 01000062 h.bq|H.`.H.....b - 0120 f17c4811 3a62f17c 48117201 62f17c48 .|H.:b.|H.r.b.|H - 0130 116a0262 f17c4811 5a034881 c2000100 .j.b.|H.Z.H..... - 0140 004939c0 0f851eff ffff488d 410148c1 .I9.......H.A.H. - 0150 e0064963 ca4839c1 7e524889 c20f1f00 ..Ic.H9.~RH..... - 0160 62f17c48 101c9662 d17c4810 2c9162f1 b.|H...b.|H.,.b. - 0170 6c4859f3 62f27d48 b8f562f1 6c4859ed lHY.b.}H..b.lHY. - 0180 62d17c48 11349162 f255489a d862f17c b.|H.4.b.UH..b.| - 0190 48111c96 4883c210 4839ca7c c348ffc9 H...H...H9.|.H.. - 01a0 4829c148 83e1f048 8d440810 4839c77e H).H...H.D..H9.~ - 01b0 370f1f80 00000000 c5fa1004 86c4c17a 7..............z - 01c0 101481c5 f259d8c4 e259b9da c5f259d2 .....Y...Y....Y. - 01d0 c4e2699b c4c5fa11 0486c4c1 7a111c81 ..i.........z... - 01e0 48ffc048 39c775d0 c5f877c3 0f1f4000 H..H9.u...w...@. - 01f0 4889f048 c1e2024c 89c949c1 e00231f6 H..H...L..I...1. - 0200 c5fa1000 c5fa1011 c5f259d8 48ffc6c4 ..........Y.H... - 0210 e259b9da c5f259d2 c4e2699b c4c5fa11 .Y....Y...i..... - 0220 00c5fa11 194c01c0 4801d148 39f775d0 .....L..H..H9.u. - 0230 c34963ca 31c04585 d20f8f1b ffffffe9 .Ic.1.E......... - 0240 74ffffff 66662e0f 1f840000 00000090 t...ff.......... - 0250 4883ec08 488b4720 4c8b4f30 488b4f08 H...H.G L.O0H.O. - 0260 488b5748 c5fa1048 04c5fa10 004c8b47 H.WH...H.....L.G - 0270 50488b37 4c89cfe8 84fdffff 31c04883 PH.7L.......1.H. - 0280 c408c366 662e0f1f 84000000 00006690 ...ff.........f. - 0290 41574156 4989ce41 554989f5 41544989 AWAVI..AUI..ATI. - 02a0 d4554889 fd534883 ec486448 8b042528 .UH..SH..HdH..%( - 02b0 00000048 89442438 31c04d85 c00f94c0 ...H.D$81.M..... - 02c0 4881ffa0 8601000f 9ec208d0 c5fa1144 H..............D - 02d0 2430c5fa 114c2434 75054d85 e475394c $0...L$4u.M..u9L - 02e0 89f14c89 e24c89ee 4889efe8 10fdffff ..L..L..H....... - 02f0 488b4424 3864482b 04252800 00000f85 H.D$8dH+.%(..... - 0300 e6000000 4883c448 5b5d415c 415d415e ....H..H[]A\A]A^ - 0310 31c0415f c30f1f00 4c894424 08c5fa11 1.A_....L.D$.... - 0320 4c2418c5 fa114424 14e80000 000083f8 L$....D$........ - 0330 014c8b44 2408c5fa 10442414 c5fa104c .L.D$....D$....L - 0340 24184189 c77498e8 00000000 85c04c8b $.A..t........L. - 0350 442408c5 fa104424 14c5fa10 4c24180f D$....D$....L$.. - 0360 857affff ff488b1d 00000000 c5fa114c .z...H.........L - 0370 24148b03 c5fa1144 24084139 c7754148 $......D$.A9.uAH - 0380 83ec0850 488d05c5 feffff4d 89e95031 ...PH......M..P1 - 0390 c931d26a 004889ee bf024000 00488d44 .1.j.H....@..H.D - 03a0 244c5041 50415641 544c8d44 2470e800 $LPAPAVATL.D$p.. - 03b0 00000048 83c440e9 34ffffff 0f1f4000 ...H..@.4.....@. - 03c0 4489ff4c 89442418 e8000000 008b034c D..L.D$........L - 03d0 8b442418 83f801c5 fa104424 08c5fa10 .D$.......D$.... - 03e0 4c241475 9ae9f5fe ffffe800 000000 L$.u........... + 0000 4989f948 89f0c5f8 28e04885 ff0f8e6e I..H....(.H....n + 0010 01000048 83fa010f 856b0100 004983f8 ...H.....k...I.. + 0020 010f8561 0100004d 89c84883 e7f84983 ...a...M..H...I. + 0030 e0e04983 f9070f8f 94010000 4d85c00f ..I.........M... + 0040 84f90000 004e8d14 85fcffff ff4983e2 .....N.......I.. + 0050 804889c2 4889ce4e 8d941080 00000090 .H..H..N........ + 0060 c5fc103e c5fc1076 20c5fc10 6e40c5fc ...>...v ...n@.. + 0070 104660c5 4459fac5 4c59f2c5 5459eac5 .F`.DY..LY..TY.. + 0080 7c59e2c5 7c101ac5 7c105220 c57c104a |Y..|...|.R .|.J + 0090 40c57c10 4260c442 65b8fbc4 4265b8f2 @.|.B`.Be...Be.. + 00a0 c44265b8 e9c44265 b8e0c524 59dac52c .Be...Be...$Y.., + 00b0 59d2c534 59cac53c 59c2c57c 113ac4e2 Y..4Y.....v .. + 00f0 116e40c5 fc114660 4883ee80 4939d20f .n@...F`H...I9.. + 0100 855bffff ff4c39c7 7e39660f 1f440000 .[...L9.~9f..D.. + 0110 c4a17c10 0481c4a1 7c102c80 c5ec59f0 ..|.....|.,...Y. + 0120 c4e265b8 f5c5ec59 edc4a17c 113480c4 ..e....Y...|.4.. + 0130 e2559ac3 c4a17c11 04814983 c0084c39 .U....|...I...L9 + 0140 c77fcd49 39f97e36 0f1f8400 00000000 ...I9.~6........ + 0150 c5fa1004 b9c5fa10 14b8c5f2 59d8c4e2 ............Y... + 0160 59b9dac5 f259d2c4 e2699bc4 c5fa1104 Y....Y...i...... + 0170 b9c5fa11 1cb848ff c74939f9 75d2c5f8 ......H..I9.u... + 0180 77c3660f 1f440000 48c1e202 49c1e002 w.f..D..H...I... + 0190 31f6660f 1f440000 c5fa1001 c5fa1010 1.f..D.......... + 01a0 c5f259d8 48ffc6c4 e259b9da c5f259d2 ..Y.H....Y....Y. + 01b0 c4e2699b c4c5fa11 01c5fa11 184c01c1 ..i..........L.. + 01c0 4801d049 39f175d0 c30f1f80 00000000 H..I9.u......... + 01d0 c4e27d18 d8c4e27d 18d1e95d feffff90 ..}....}...].... + 01e0 4883ec08 488b4720 4c8b4f30 488b4f08 H...H.G L.O0H.O. + 01f0 488b5748 c5fa1048 04c5fa10 004c8b47 H.WH...H.....L.G + 0200 50488b37 4c89cfe8 f4fdffff 31c04883 PH.7L.......1.H. + 0210 c408c366 662e0f1f 84000000 00006690 ...ff.........f. + 0220 41574156 4989ce41 554989f5 41544989 AWAVI..AUI..ATI. + 0230 d4554889 fd534883 ec486448 8b042528 .UH..SH..HdH..%( + 0240 00000048 89442438 31c04d85 c00f94c0 ...H.D$81.M..... + 0250 4881ffa0 8601000f 9ec208d0 c5fa1144 H..............D + 0260 2430c5fa 114c2434 75054d85 e475394c $0...L$4u.M..u9L + 0270 89f14c89 e24c89ee 4889efe8 80fdffff ..L..L..H....... + 0280 488b4424 3864482b 04252800 00000f85 H.D$8dH+.%(..... + 0290 e6000000 4883c448 5b5d415c 415d415e ....H..H[]A\A]A^ + 02a0 31c0415f c30f1f00 4c894424 08c5fa11 1.A_....L.D$.... + 02b0 4c2418c5 fa114424 14e80000 000083f8 L$....D$........ + 02c0 014c8b44 2408c5fa 10442414 c5fa104c .L.D$....D$....L + 02d0 24184189 c77498e8 00000000 85c04c8b $.A..t........L. + 02e0 442408c5 fa104424 14c5fa10 4c24180f D$....D$....L$.. + 02f0 857affff ff488b1d 00000000 c5fa114c .z...H.........L + 0300 24148b03 c5fa1144 24084139 c7754148 $......D$.A9.uAH + 0310 83ec0850 488d05c5 feffff4d 89e95031 ...PH......M..P1 + 0320 c931d26a 004889ee bf024000 00488d44 .1.j.H....@..H.D + 0330 244c5041 50415641 544c8d44 2470e800 $LPAPAVATL.D$p.. + 0340 00000048 83c440e9 34ffffff 0f1f4000 ...H..@.4.....@. + 0350 4489ff4c 89442418 e8000000 008b034c D..L.D$........L + 0360 8b442418 83f801c5 fa104424 08c5fa10 .D$.......D$.... + 0370 4c241475 9ae9f5fe ffffe800 000000 L$.u........... /usr/lib64/libopenblas_openmp.a/srot_k_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/srot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/srot_k_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39000000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/srot_k_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/srot_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/srot_k_COOPERLAKE.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 10000000 1c000000 ................ - 0020 00000000 44020000 00000000 14000000 ....D........... + 0020 00000000 df010000 00000000 14000000 ................ 0030 30000000 00000000 33000000 00440e10 0.......3....D.. 0040 6e0e0800 70000000 48000000 00000000 n...p...H....... 0050 5f010000 00420e10 8f02420e 188e0345 _....B....B....E /usr/lib64/libopenblas_openmp.a/srot_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/srot_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/srot_k_SKYLAKEX.o (disasm) @@ -5,118 +5,118 @@ Disassembly of section .text: rot_compute: + mov %rdi,%r9 mov %rsi,%rax + vmovaps %xmm0,%xmm4 test %rdi,%rdi jle cmp $something,%rdx jne cmp $something,%r8 jne - mov %rdi,%r9 - mov %rdi,%r8 - vbroadcastss %xmm0,%zmm0 - vbroadcastss %xmm1,%zmm1 - and $something,%r9 + mov %r9,%r8 + and $something,%rdi and $something,%r8 + cmp $something,%r9 + jg + test %r8,%r8 je - mov %rsi,%rdx - lea (%rax,%r8,4),%r10 + lea -offset(,%r8,4),%r10 + and $something,%r10 + mov %rax,%rdx mov %rcx,%rsi - nopw offset(%rax,%rax,1) - vmovups (%rsi),%zmm5 - vmovups offset(%rsi),%zmm4 - vmovups offset(%rsi),%zmm3 - vmovups offset(%rsi),%zmm2 - vmulps %zmm5,%zmm1,%zmm13 - vmulps %zmm4,%zmm1,%zmm12 - vmulps %zmm3,%zmm1,%zmm11 - vmulps %zmm2,%zmm1,%zmm10 - vmovups (%rdx),%zmm9 - vmovups offset(%rdx),%zmm8 - vmovups offset(%rdx),%zmm7 - vmovups offset(%rdx),%zmm6 - vfmadd231ps %zmm9,%zmm0,%zmm13 - vfmadd231ps %zmm8,%zmm0,%zmm12 - vfmadd231ps %zmm7,%zmm0,%zmm11 - vfmadd231ps %zmm6,%zmm0,%zmm10 - vmulps %zmm9,%zmm1,%zmm9 - vmulps %zmm8,%zmm1,%zmm8 - vmulps %zmm7,%zmm1,%zmm7 - vmulps %zmm6,%zmm1,%zmm6 - vmovups %zmm13,(%rdx) - vfmsub132ps %zmm0,%zmm9,%zmm5 - vfmsub132ps %zmm0,%zmm8,%zmm4 - vfmsub132ps %zmm0,%zmm7,%zmm3 - vfmsub132ps %zmm0,%zmm6,%zmm2 - vmovups %zmm12,offset(%rdx) - vmovups %zmm11,offset(%rdx) - vmovups %zmm10,offset(%rdx) - add $something,%rdx - vmovups %zmm5,(%rsi) - vmovups %zmm4,offset(%rsi) - vmovups %zmm3,offset(%rsi) - vmovups %zmm2,offset(%rsi) - add $something,%rsi + lea offset(%rax,%r10,1),%r10 + nop + vmovups (%rsi),%ymm7 + vmovups offset(%rsi),%ymm6 + vmovups offset(%rsi),%ymm5 + vmovups offset(%rsi),%ymm0 + vmulps %ymm2,%ymm7,%ymm15 + vmulps %ymm2,%ymm6,%ymm14 + vmulps %ymm2,%ymm5,%ymm13 + vmulps %ymm2,%ymm0,%ymm12 + vmovups (%rdx),%ymm11 + vmovups offset(%rdx),%ymm10 + vmovups offset(%rdx),%ymm9 + vmovups offset(%rdx),%ymm8 + vfmadd231ps %ymm11,%ymm3,%ymm15 + vfmadd231ps %ymm10,%ymm3,%ymm14 + vfmadd231ps %ymm9,%ymm3,%ymm13 + vfmadd231ps %ymm8,%ymm3,%ymm12 + vmulps %ymm2,%ymm11,%ymm11 + vmulps %ymm2,%ymm10,%ymm10 + vmulps %ymm2,%ymm9,%ymm9 + vmulps %ymm2,%ymm8,%ymm8 + vmovups %ymm15,(%rdx) + vfmsub132ps %ymm3,%ymm11,%ymm7 + vfmsub132ps %ymm3,%ymm10,%ymm6 + vfmsub132ps %ymm3,%ymm9,%ymm5 + vfmsub132ps %ymm3,%ymm8,%ymm0 + vmovups %ymm14,offset(%rdx) + vmovups %ymm13,offset(%rdx) + vmovups %ymm12,offset(%rdx) + sub $something,%rdx + vmovups %ymm7,(%rsi) + vmovups %ymm6,offset(%rsi) + vmovups %ymm5,offset(%rsi) + vmovups %ymm0,offset(%rsi) + sub $something,%rsi cmp %rdx,%r10 jne - cmp %r8,%r9 + cmp %r8,%rdi jle - nopl offset(%rax,%rax,1) - vmovups (%rcx,%r8,4),%zmm2 - vmovups (%rax,%r8,4),%zmm3 - vmulps %zmm2,%zmm1,%zmm4 - vfmadd231ps %zmm3,%zmm0,%zmm4 - vmulps %zmm3,%zmm1,%zmm3 - vmovups %zmm4,(%rax,%r8,4) - vfmsub132ps %zmm0,%zmm3,%zmm2 - vmovups %zmm2,(%rcx,%r8,4) + nopw offset(%rax,%rax,1) + vmovups (%rcx,%r8,4),%ymm0 + vmovups (%rax,%r8,4),%ymm5 + vmulps %ymm0,%ymm2,%ymm6 + vfmadd231ps %ymm5,%ymm3,%ymm6 + vmulps %ymm5,%ymm2,%ymm5 + vmovups %ymm6,(%rax,%r8,4) + vfmsub132ps %ymm3,%ymm5,%ymm0 + vmovups %ymm0,(%rcx,%r8,4) add $something,%r8 - cmp %r8,%r9 + cmp %r8,%rdi jg - and $something,%edi - je - shl $something,%r9 - mov $something,%esi - add %r9,%rax - sub %edi,%esi - add %rcx,%r9 - mov $something,%edx - sarx %esi,%edx,%edi - kmovd %edi,%k1 - vmovups (%r9),%zmm3{%k1}{z} - vmovups (%rax),%zmm4{%k1}{z} - vmulps %zmm3,%zmm1,%zmm2 - vmulps %zmm4,%zmm1,%zmm1 - vfmadd231ps %zmm4,%zmm0,%zmm2 - vfmsub132ps %zmm3,%zmm1,%zmm0 - vmovups %zmm2,(%rax){%k1} - vmovups %zmm0,(%r9){%k1} - vzeroupper - ret - nopl (%rax) + cmp %rdi,%r9 + jle + nopl offset(%rax,%rax,1) + vmovss (%rcx,%rdi,4),%xmm0 + vmovss (%rax,%rdi,4),%xmm2 + vmulss %xmm0,%xmm1,%xmm3 + vfmadd231ss %xmm2,%xmm4,%xmm3 + vmulss %xmm2,%xmm1,%xmm2 + vfmsub132ss %xmm4,%xmm2,%xmm0 + vmovss %xmm0,(%rcx,%rdi,4) + vmovss %xmm3,(%rax,%rdi,4) + inc %rdi + cmp %rdi,%r9 + jne vzeroupper ret - nopl offset(%rax) + nopw offset(%rax,%rax,1) shl $something,%rdx shl $something,%r8 xor %esi,%esi nopw offset(%rax,%rax,1) - vmovss (%rcx),%xmm2 - vmovss (%rax),%xmm3 - vmulss %xmm2,%xmm1,%xmm4 + vmovss (%rcx),%xmm0 + vmovss (%rax),%xmm2 + vmulss %xmm0,%xmm1,%xmm3 inc %rsi - vfmadd231ss %xmm3,%xmm0,%xmm4 - vmulss %xmm3,%xmm1,%xmm3 - vfmsub132ss %xmm0,%xmm3,%xmm2 - vmovss %xmm2,(%rcx) - vmovss %xmm4,(%rax) + vfmadd231ss %xmm2,%xmm4,%xmm3 + vmulss %xmm2,%xmm1,%xmm2 + vfmsub132ss %xmm4,%xmm2,%xmm0 + vmovss %xmm0,(%rcx) + vmovss %xmm3,(%rax) add %r8,%rcx add %rdx,%rax - cmp %rsi,%rdi + cmp %rsi,%r9 jne ret - data16 cs nopw offset(%rax,%rax,1) nopl offset(%rax) + vbroadcastss %xmm0,%ymm3 /usr/lib64/libopenblas_openmp.a/srot_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/srot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/srot_k_SKYLAKEX.o (objdump) @@ -2,64 +2,59 @@ /usr/lib64/libopenblas_openmp.a/srot_k_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 4889f048 85ff0f8e cf010000 4883fa01 H..H........H... - 0010 0f85ca01 00004983 f8010f85 c0010000 ......I......... - 0020 4989f949 89f862f2 7d4818c0 62f27d48 I..I..b.}H..b.}H - 0030 18c94983 e1f04983 e0c00f84 38010000 ..I...I.....8... - 0040 4889f24e 8d148048 89ce660f 1f440000 H..N...H..f..D.. - 0050 62f17c48 102e62f1 7c481066 0162f17c b.|H..b.|H.f.b.| - 0060 48105e02 62f17c48 10560362 71744859 H.^.b.|H.V.bqtHY - 0070 ed627174 4859e462 71744859 db627174 .bqtHY.bqtHY.bqt - 0080 4859d262 717c4810 0a62717c 48104201 HY.bq|H..bq|H.B. - 0090 62f17c48 107a0262 f17c4810 72036252 b.|H.z.b.|H.r.bR - 00a0 7d48b8e9 62527d48 b8e06272 7d48b8df }H..bR}H..br}H.. - 00b0 62727d48 b8d66251 744859c9 62517448 br}H..bQtHY.bQtH - 00c0 59c062f1 744859ff 62f17448 59f66271 Y.b.tHY.b.tHY.bq - 00d0 7c48112a 62f23548 9ae862f2 3d489ae0 |H.*b.5H..b.=H.. - 00e0 62f24548 9ad862f2 4d489ad0 62717c48 b.EH..b.MH..bq|H - 00f0 11620162 717c4811 5a026271 7c481152 .b.bq|H.Z.bq|H.R - 0100 034881c2 00010000 62f17c48 112e62f1 .H......b.|H..b. - 0110 7c481166 0162f17c 48115e02 62f17c48 |H.f.b.|H.^.b.|H - 0120 11560348 81c60001 00004939 d20f851d .V.H......I9.... - 0130 ffffff4d 39c17e45 0f1f8400 00000000 ...M9.~E........ - 0140 62b17c48 10148162 b17c4810 1c8062f1 b.|H...b.|H...b. - 0150 744859e2 62f27d48 b8e362f1 744859db tHY.b.}H..b.tHY. - 0160 62b17c48 11248062 f265489a d062b17c b.|H.$.b.eH..b.| - 0170 48111481 4983c010 4d39c17f c383e70f H...I...M9...... - 0180 745649c1 e102be10 0000004c 01c829fe tVI........L..). - 0190 4901c9ba ffff0000 c4e24af7 fac5fb92 I.........J..... - 01a0 cf62d17c c9101962 f17cc910 2062f174 .b.|...b.|.. b.t - 01b0 4859d362 f1744859 cc62f27d 48b8d462 HY.b.tHY.b.}H..b - 01c0 f275489a c362f17c 49111062 d17c4911 .uH..b.|I..b.|I. - 01d0 01c5f877 c30f1f00 c5f877c3 0f1f4000 ...w......w...@. - 01e0 48c1e202 49c1e002 31f6660f 1f440000 H...I...1.f..D.. - 01f0 c5fa1011 c5fa1018 c5f259e2 48ffc6c4 ..........Y.H... - 0200 e279b9e3 c5f259db c4e2619b d0c5fa11 .y....Y...a..... - 0210 11c5fa11 204c01c1 4801d048 39f775d0 .... L..H..H9.u. - 0220 c366662e 0f1f8400 00000000 0f1f4000 .ff...........@. - 0230 4883ec08 488b4720 4c8b4f30 488b4f08 H...H.G L.O0H.O. - 0240 488b5748 c5fa1048 04c5fa10 004c8b47 H.WH...H.....L.G - 0250 50488b37 4c89cfe8 a4fdffff 31c04883 PH.7L.......1.H. - 0260 c408c366 662e0f1f 84000000 00006690 ...ff.........f. - 0270 41574156 4989ce41 554989f5 41544989 AWAVI..AUI..ATI. - 0280 d4554889 fd534883 ec486448 8b042528 .UH..SH..HdH..%( - 0290 00000048 89442438 31c04d85 c00f94c0 ...H.D$81.M..... - 02a0 4881ffa0 8601000f 9ec208d0 c5fa1144 H..............D - 02b0 2430c5fa 114c2434 75054d85 e475394c $0...L$4u.M..u9L - 02c0 89f14c89 e24c89ee 4889efe8 30fdffff ..L..L..H...0... - 02d0 488b4424 3864482b 04252800 00000f85 H.D$8dH+.%(..... - 02e0 e6000000 4883c448 5b5d415c 415d415e ....H..H[]A\A]A^ - 02f0 31c0415f c30f1f00 4c894424 08c5fa11 1.A_....L.D$.... - 0300 4c2418c5 fa114424 14e80000 000083f8 L$....D$........ - 0310 014c8b44 2408c5fa 10442414 c5fa104c .L.D$....D$....L - 0320 24184189 c77498e8 00000000 85c04c8b $.A..t........L. - 0330 442408c5 fa104424 14c5fa10 4c24180f D$....D$....L$.. - 0340 857affff ff488b1d 00000000 c5fa114c .z...H.........L - 0350 24148b03 c5fa1144 24084139 c7754148 $......D$.A9.uAH - 0360 83ec0850 488d05c5 feffff4d 89e95031 ...PH......M..P1 - 0370 c931d26a 004889ee bf024000 00488d44 .1.j.H....@..H.D - 0380 244c5041 50415641 544c8d44 2470e800 $LPAPAVATL.D$p.. - 0390 00000048 83c440e9 34ffffff 0f1f4000 ...H..@.4.....@. - 03a0 4489ff4c 89442418 e8000000 008b034c D..L.D$........L - 03b0 8b442418 83f801c5 fa104424 08c5fa10 .D$.......D$.... - 03c0 4c241475 9ae9f5fe ffffe800 000000 L$.u........... + 0000 4989f948 89f0c5f8 28e04885 ff0f8e6e I..H....(.H....n + 0010 01000048 83fa010f 856b0100 004983f8 ...H.....k...I.. + 0020 010f8561 0100004d 89c84883 e7f84983 ...a...M..H...I. + 0030 e0e04983 f9070f8f 94010000 4d85c00f ..I.........M... + 0040 84f90000 004e8d14 85fcffff ff4983e2 .....N.......I.. + 0050 804889c2 4889ce4e 8d941080 00000090 .H..H..N........ + 0060 c5fc103e c5fc1076 20c5fc10 6e40c5fc ...>...v ...n@.. + 0070 104660c5 4459fac5 4c59f2c5 5459eac5 .F`.DY..LY..TY.. + 0080 7c59e2c5 7c101ac5 7c105220 c57c104a |Y..|...|.R .|.J + 0090 40c57c10 4260c442 65b8fbc4 4265b8f2 @.|.B`.Be...Be.. + 00a0 c44265b8 e9c44265 b8e0c524 59dac52c .Be...Be...$Y.., + 00b0 59d2c534 59cac53c 59c2c57c 113ac4e2 Y..4Y.....v .. + 00f0 116e40c5 fc114660 4883ee80 4939d20f .n@...F`H...I9.. + 0100 855bffff ff4c39c7 7e39660f 1f440000 .[...L9.~9f..D.. + 0110 c4a17c10 0481c4a1 7c102c80 c5ec59f0 ..|.....|.,...Y. + 0120 c4e265b8 f5c5ec59 edc4a17c 113480c4 ..e....Y...|.4.. + 0130 e2559ac3 c4a17c11 04814983 c0084c39 .U....|...I...L9 + 0140 c77fcd49 39f97e36 0f1f8400 00000000 ...I9.~6........ + 0150 c5fa1004 b9c5fa10 14b8c5f2 59d8c4e2 ............Y... + 0160 59b9dac5 f259d2c4 e2699bc4 c5fa1104 Y....Y...i...... + 0170 b9c5fa11 1cb848ff c74939f9 75d2c5f8 ......H..I9.u... + 0180 77c3660f 1f440000 48c1e202 49c1e002 w.f..D..H...I... + 0190 31f6660f 1f440000 c5fa1001 c5fa1010 1.f..D.......... + 01a0 c5f259d8 48ffc6c4 e259b9da c5f259d2 ..Y.H....Y....Y. + 01b0 c4e2699b c4c5fa11 01c5fa11 184c01c1 ..i..........L.. + 01c0 4801d049 39f175d0 c30f1f80 00000000 H..I9.u......... + 01d0 c4e27d18 d8c4e27d 18d1e95d feffff90 ..}....}...].... + 01e0 4883ec08 488b4720 4c8b4f30 488b4f08 H...H.G L.O0H.O. + 01f0 488b5748 c5fa1048 04c5fa10 004c8b47 H.WH...H.....L.G + 0200 50488b37 4c89cfe8 f4fdffff 31c04883 PH.7L.......1.H. + 0210 c408c366 662e0f1f 84000000 00006690 ...ff.........f. + 0220 41574156 4989ce41 554989f5 41544989 AWAVI..AUI..ATI. + 0230 d4554889 fd534883 ec486448 8b042528 .UH..SH..HdH..%( + 0240 00000048 89442438 31c04d85 c00f94c0 ...H.D$81.M..... + 0250 4881ffa0 8601000f 9ec208d0 c5fa1144 H..............D + 0260 2430c5fa 114c2434 75054d85 e475394c $0...L$4u.M..u9L + 0270 89f14c89 e24c89ee 4889efe8 80fdffff ..L..L..H....... + 0280 488b4424 3864482b 04252800 00000f85 H.D$8dH+.%(..... + 0290 e6000000 4883c448 5b5d415c 415d415e ....H..H[]A\A]A^ + 02a0 31c0415f c30f1f00 4c894424 08c5fa11 1.A_....L.D$.... + 02b0 4c2418c5 fa114424 14e80000 000083f8 L$....D$........ + 02c0 014c8b44 2408c5fa 10442414 c5fa104c .L.D$....D$....L + 02d0 24184189 c77498e8 00000000 85c04c8b $.A..t........L. + 02e0 442408c5 fa104424 14c5fa10 4c24180f D$....D$....L$.. + 02f0 857affff ff488b1d 00000000 c5fa114c .z...H.........L + 0300 24148b03 c5fa1144 24084139 c7754148 $......D$.A9.uAH + 0310 83ec0850 488d05c5 feffff4d 89e95031 ...PH......M..P1 + 0320 c931d26a 004889ee bf024000 00488d44 .1.j.H....@..H.D + 0330 244c5041 50415641 544c8d44 2470e800 $LPAPAVATL.D$p.. + 0340 00000048 83c440e9 34ffffff 0f1f4000 ...H..@.4.....@. + 0350 4489ff4c 89442418 e8000000 008b034c D..L.D$........L + 0360 8b442418 83f801c5 fa104424 08c5fa10 .D$.......D$.... + 0370 4c241475 9ae9f5fe ffffe800 000000 L$.u........... /usr/lib64/libopenblas_openmp.a/srot_k_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/srot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/srot_k_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/srot_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/srot_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/srot_k_SKYLAKEX.o (objdump) @@ -4,7 +4,7 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 10000000 1c000000 ................ - 0020 00000000 21020000 00000000 14000000 ....!........... + 0020 00000000 df010000 00000000 14000000 ................ 0030 30000000 00000000 33000000 00440e10 0.......3....D.. 0040 6e0e0800 70000000 48000000 00000000 n...p...H....... 0050 5f010000 00420e10 8f02420e 188e0345 _....B....B....E /usr/lib64/libopenblas_openmp.a/ssum_k_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/ssum_k_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/ssum_k_COOPERLAKE.o (disasm) @@ -32,32 +32,32 @@ lea -offset(%r9),%rax shr $something,%rax mov %rax,%r9 - vxorps %xmm0,%xmm0,%xmm0 + vxorps %xmm3,%xmm3,%xmm3 shl $something,%r9 mov %rcx,%rdx lea offset(%rcx,%r9,1),%r9 - vmovaps %zmm0,%zmm3 - vmovaps %zmm0,%zmm1 - vmovaps %zmm0,%zmm2 - nopw offset(%rax,%rax,1) - vaddps (%rdx),%zmm2,%zmm2 - vaddps offset(%rdx),%zmm1,%zmm1 - vaddps offset(%rdx),%zmm3,%zmm3 - vaddps offset(%rdx),%zmm0,%zmm0 - add $something,%rdx + vmovaps %ymm3,%ymm0 + vmovaps %ymm3,%ymm2 + vmovaps %ymm3,%ymm1 + nopl offset(%rax) + vaddps (%rdx),%ymm1,%ymm1 + vaddps offset(%rdx),%ymm2,%ymm2 + vaddps offset(%rdx),%ymm0,%ymm0 + vaddps offset(%rdx),%ymm3,%ymm3 + sub $something,%rdx cmp %rdx,%r9 jne - vaddps %zmm3,%zmm0,%zmm0 - vaddps %zmm2,%zmm1,%zmm1 + vaddps %ymm3,%ymm0,%ymm0 + vaddps %ymm2,%ymm1,%ymm1 inc %rax shl $something,%rax - vaddps %zmm1,%zmm0,%zmm0 + vaddps %ymm1,%ymm0,%ymm0 movslq %r8d,%r8 cmp %rax,%r8 jle mov %rax,%rdx - nopl offset(%rax,%rax,1) - vaddps (%rcx,%rdx,4),%zmm0,%zmm0 + nopw offset(%rax,%rax,1) + vaddps (%rcx,%rdx,4),%ymm0,%ymm0 add $something,%rdx cmp %rdx,%r8 jg @@ -65,14 +65,11 @@ sub %rax,%r8 and $something,%r8 lea offset(%rax,%r8,1),%rax - vshuff32x4 $something,%zmm0,%zmm0,%zmm1 - vaddps %zmm0,%zmm1,%zmm1 - vshuff32x4 $something,%zmm1,%zmm1,%zmm0 - vaddps %zmm1,%zmm0,%zmm0 - vpermilps $something,%zmm0,%zmm1 - vaddps %zmm1,%zmm0,%zmm0 - vpermilps $something,%zmm0,%zmm1 - vaddps %zmm1,%zmm0,%zmm0 + vhaddps %ymm0,%ymm0,%ymm0 + vhaddps %ymm0,%ymm0,%ymm0 + vmovaps %xmm0,%xmm1 + vextractf128 $something,%ymm0,%xmm0 + vaddps %xmm0,%xmm1,%xmm0 cmp %rax,%rdi jle vzeroupper /usr/lib64/libopenblas_openmp.a/ssum_k_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/ssum_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ssum_k_COOPERLAKE.o (objdump) @@ -2,26 +2,23 @@ /usr/lib64/libopenblas_openmp.a/ssum_k_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 4889f148 89d64885 ff0f8e49 01000048 H..H..H....I...H - 0010 85d20f8e 40010000 480faffa c5f857c0 ....@...H.....W. + 0000 4889f148 89d64885 ff0f8e11 01000048 H..H..H........H + 0010 85d20f8e 08010000 480faffa c5f857c0 ........H.....W. 0020 31c04883 fa017418 0f1f8400 00000000 1.H...t......... 0030 c5fa5804 814801f0 4839c77f f3c36690 ..X..H..H9....f. - 0040 4189f841 89f94183 e0f04183 e1c00f8e A..A..A...A..... - 0050 10010000 4d63c949 8d41ff48 c1e80649 ....Mc.I.A.H...I - 0060 89c1c5f8 57c049c1 e1084889 ca4e8d8c ....W.I...H..N.. - 0070 09000100 0062f17c 4828d862 f17c4828 .....b.|H(.b.|H( - 0080 c862f17c 4828d066 0f1f8400 00000000 .b.|H(.f........ - 0090 62f16c48 581262f1 7448584a 0162f164 b.lHX.b.tHXJ.b.d - 00a0 48585a02 62f17c48 58420348 81c20001 HXZ.b.|HXB.H.... - 00b0 00004939 d175d962 f17c4858 c362f174 ..I9.u.b.|HX.b.t - 00c0 4858ca48 ffc048c1 e00662f1 7c4858c1 HX.H..H...b.|HX. - 00d0 4d63c049 39c07e27 4889c20f 1f440000 Mc.I9.~'H....D.. - 00e0 62f17c48 58049148 83c21049 39d07ff0 b.|HX..H...I9... - 00f0 49ffc849 29c04983 e0f04a8d 44001062 I..I).I...J.D..b - 0100 f37d4823 c8ee62f1 744858c8 62f37548 .}H#..b.tHX.b.uH - 0110 23c14e62 f17c4858 c162f37d 4804c84e #.Nb.|HX.b.}H..N - 0120 62f17c48 58c162f3 7d4804c8 b162f17c b.|HX.b.}H...b.| - 0130 4858c148 39c77e28 c5f877c5 fa580481 HX.H9.~(..w..X.. - 0140 4801f048 39c70f8f e4feffff e9ecfeff H..H9........... - 0150 ff0f1f80 00000000 c5f857c0 c30f1f00 ..........W..... - 0160 c5f877c3 c5f857c0 e963ffff ff ..w...W..c... + 0040 4189f841 89f94183 e0f84183 e1e00f8e A..A..A...A..... + 0050 d8000000 4d63c949 8d41ff48 c1e80549 ....Mc.I.A.H...I + 0060 89c1c5e0 57db49c1 e1074889 ca4e8d8c ....W.I...H..N.. + 0070 09800000 00c5fc28 c3c5fc28 d3c5fc28 .......(...(...( + 0080 cb0f1f80 00000000 c5f4580a c5ec5852 ..........X...XR + 0090 20c5fc58 4240c5e4 585a6048 83ea8049 ..XB@..XZ`H...I + 00a0 39d175e4 c5fc58c3 c5f458ca 48ffc048 9.u...X...X.H..H + 00b0 c1e005c5 fc58c14d 63c04939 c07e2648 .....X.Mc.I9.~&H + 00c0 89c2660f 1f440000 c5fc5804 914883c2 ..f..D....X..H.. + 00d0 084939d0 7ff249ff c84929c0 4983e0f8 .I9...I..I).I... + 00e0 4a8d4400 08c5ff7c c0c5ff7c c0c5f828 J.D....|...|...( + 00f0 c8c4e37d 19c001c5 f058c048 39c77e28 ...}.....X.H9.~( + 0100 c5f877c5 fa580481 4801f048 39c70f8f ..w..X..H..H9... + 0110 1cffffff e924ffff ff0f1f80 00000000 .....$.......... + 0120 c5f857c0 c30f1f00 c5f877c3 c5f857c0 ..W.......w...W. + 0130 eb85 .. /usr/lib64/libopenblas_openmp.a/ssum_k_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/ssum_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ssum_k_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39000000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/ssum_k_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/ssum_k_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ssum_k_COOPERLAKE.o (objdump) @@ -4,4 +4,4 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 14000000 1c000000 ................ - 0020 00000000 6d010000 00000000 00000000 ....m........... + 0020 00000000 32010000 00000000 00000000 ....2........... /usr/lib64/libopenblas_openmp.a/ssum_k_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/ssum_k_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/ssum_k_SKYLAKEX.o (disasm) @@ -32,32 +32,32 @@ lea -offset(%r9),%rax shr $something,%rax mov %rax,%r9 - vxorps %xmm0,%xmm0,%xmm0 + vxorps %xmm3,%xmm3,%xmm3 shl $something,%r9 mov %rcx,%rdx lea offset(%rcx,%r9,1),%r9 - vmovaps %zmm0,%zmm3 - vmovaps %zmm0,%zmm1 - vmovaps %zmm0,%zmm2 - nopw offset(%rax,%rax,1) - vaddps (%rdx),%zmm2,%zmm2 - vaddps offset(%rdx),%zmm1,%zmm1 - vaddps offset(%rdx),%zmm3,%zmm3 - vaddps offset(%rdx),%zmm0,%zmm0 - add $something,%rdx + vmovaps %ymm3,%ymm0 + vmovaps %ymm3,%ymm2 + vmovaps %ymm3,%ymm1 + nopl offset(%rax) + vaddps (%rdx),%ymm1,%ymm1 + vaddps offset(%rdx),%ymm2,%ymm2 + vaddps offset(%rdx),%ymm0,%ymm0 + vaddps offset(%rdx),%ymm3,%ymm3 + sub $something,%rdx cmp %rdx,%r9 jne - vaddps %zmm3,%zmm0,%zmm0 - vaddps %zmm2,%zmm1,%zmm1 + vaddps %ymm3,%ymm0,%ymm0 + vaddps %ymm2,%ymm1,%ymm1 inc %rax shl $something,%rax - vaddps %zmm1,%zmm0,%zmm0 + vaddps %ymm1,%ymm0,%ymm0 movslq %r8d,%r8 cmp %rax,%r8 jle mov %rax,%rdx - nopl offset(%rax,%rax,1) - vaddps (%rcx,%rdx,4),%zmm0,%zmm0 + nopw offset(%rax,%rax,1) + vaddps (%rcx,%rdx,4),%ymm0,%ymm0 add $something,%rdx cmp %rdx,%r8 jg @@ -65,14 +65,11 @@ sub %rax,%r8 and $something,%r8 lea offset(%rax,%r8,1),%rax - vshuff32x4 $something,%zmm0,%zmm0,%zmm1 - vaddps %zmm0,%zmm1,%zmm1 - vshuff32x4 $something,%zmm1,%zmm1,%zmm0 - vaddps %zmm1,%zmm0,%zmm0 - vpermilps $something,%zmm0,%zmm1 - vaddps %zmm1,%zmm0,%zmm0 - vpermilps $something,%zmm0,%zmm1 - vaddps %zmm1,%zmm0,%zmm0 + vhaddps %ymm0,%ymm0,%ymm0 + vhaddps %ymm0,%ymm0,%ymm0 + vmovaps %xmm0,%xmm1 + vextractf128 $something,%ymm0,%xmm0 + vaddps %xmm0,%xmm1,%xmm0 cmp %rax,%rdi jle vzeroupper /usr/lib64/libopenblas_openmp.a/ssum_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/ssum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ssum_k_SKYLAKEX.o (objdump) @@ -2,26 +2,23 @@ /usr/lib64/libopenblas_openmp.a/ssum_k_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 4889f148 89d64885 ff0f8e49 01000048 H..H..H....I...H - 0010 85d20f8e 40010000 480faffa c5f857c0 ....@...H.....W. + 0000 4889f148 89d64885 ff0f8e11 01000048 H..H..H........H + 0010 85d20f8e 08010000 480faffa c5f857c0 ........H.....W. 0020 31c04883 fa017418 0f1f8400 00000000 1.H...t......... 0030 c5fa5804 814801f0 4839c77f f3c36690 ..X..H..H9....f. - 0040 4189f841 89f94183 e0f04183 e1c00f8e A..A..A...A..... - 0050 10010000 4d63c949 8d41ff48 c1e80649 ....Mc.I.A.H...I - 0060 89c1c5f8 57c049c1 e1084889 ca4e8d8c ....W.I...H..N.. - 0070 09000100 0062f17c 4828d862 f17c4828 .....b.|H(.b.|H( - 0080 c862f17c 4828d066 0f1f8400 00000000 .b.|H(.f........ - 0090 62f16c48 581262f1 7448584a 0162f164 b.lHX.b.tHXJ.b.d - 00a0 48585a02 62f17c48 58420348 81c20001 HXZ.b.|HXB.H.... - 00b0 00004939 d175d962 f17c4858 c362f174 ..I9.u.b.|HX.b.t - 00c0 4858ca48 ffc048c1 e00662f1 7c4858c1 HX.H..H...b.|HX. - 00d0 4d63c049 39c07e27 4889c20f 1f440000 Mc.I9.~'H....D.. - 00e0 62f17c48 58049148 83c21049 39d07ff0 b.|HX..H...I9... - 00f0 49ffc849 29c04983 e0f04a8d 44001062 I..I).I...J.D..b - 0100 f37d4823 c8ee62f1 744858c8 62f37548 .}H#..b.tHX.b.uH - 0110 23c14e62 f17c4858 c162f37d 4804c84e #.Nb.|HX.b.}H..N - 0120 62f17c48 58c162f3 7d4804c8 b162f17c b.|HX.b.}H...b.| - 0130 4858c148 39c77e28 c5f877c5 fa580481 HX.H9.~(..w..X.. - 0140 4801f048 39c70f8f e4feffff e9ecfeff H..H9........... - 0150 ff0f1f80 00000000 c5f857c0 c30f1f00 ..........W..... - 0160 c5f877c3 c5f857c0 e963ffff ff ..w...W..c... + 0040 4189f841 89f94183 e0f84183 e1e00f8e A..A..A...A..... + 0050 d8000000 4d63c949 8d41ff48 c1e80549 ....Mc.I.A.H...I + 0060 89c1c5e0 57db49c1 e1074889 ca4e8d8c ....W.I...H..N.. + 0070 09800000 00c5fc28 c3c5fc28 d3c5fc28 .......(...(...( + 0080 cb0f1f80 00000000 c5f4580a c5ec5852 ..........X...XR + 0090 20c5fc58 4240c5e4 585a6048 83ea8049 ..XB@..XZ`H...I + 00a0 39d175e4 c5fc58c3 c5f458ca 48ffc048 9.u...X...X.H..H + 00b0 c1e005c5 fc58c14d 63c04939 c07e2648 .....X.Mc.I9.~&H + 00c0 89c2660f 1f440000 c5fc5804 914883c2 ..f..D....X..H.. + 00d0 084939d0 7ff249ff c84929c0 4983e0f8 .I9...I..I).I... + 00e0 4a8d4400 08c5ff7c c0c5ff7c c0c5f828 J.D....|...|...( + 00f0 c8c4e37d 19c001c5 f058c048 39c77e28 ...}.....X.H9.~( + 0100 c5f877c5 fa580481 4801f048 39c70f8f ..w..X..H..H9... + 0110 1cffffff e924ffff ff0f1f80 00000000 .....$.......... + 0120 c5f857c0 c30f1f00 c5f877c3 c5f857c0 ..W.......w...W. + 0130 eb85 .. /usr/lib64/libopenblas_openmp.a/ssum_k_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/ssum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ssum_k_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39000000 00000000 ........9....... + 0010 020001c0 04000000 05000000 00000000 ................ + 0020 010001c0 04000000 19000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/ssum_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/ssum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ssum_k_SKYLAKEX.o (objdump) @@ -4,4 +4,4 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 14000000 1c000000 ................ - 0020 00000000 6d010000 00000000 00000000 ....m........... + 0020 00000000 32010000 00000000 00000000 ....2........... /usr/lib64/libopenblas_openmp.a/ssymm_iltcopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/ssymm_iltcopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/ssymm_iltcopy_COOPERLAKE.o (disasm) @@ -12,338 +12,94 @@ push %rbp push %rbx sub $something,%rsp - mov %rsi,offset(%rsp) + mov %rsi,(%rsp) sar $something,%rsi mov %rdi,-offset(%rsp) - mov %rdx,(%rsp) - mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) + mov %rdx,-offset(%rsp) + mov %rcx,-offset(%rsp) + mov %r8,-offset(%rsp) mov %r9,offset(%rsp) mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rcx,%r14 - mov %r9,%rax - imul %r14,%rax - mov %rdx,%r11 - mov %rsi,%r10 - add %r8,%rax - lea (%r11,%rax,4),%rax - mov %rax,-offset(%rsp) - mov %r14,%rax + mov %rsi,%r11 + mov %rcx,%rsi + mov %rsi,%rax shl $something,%rax mov %rax,-offset(%rsp) - mov %r10,%rax - shl $something,%rax + mov %rsi,%rax + imul %r8,%rax + lea offset(,%rcx,4),%rcx + mov %r8,%r13 + add %r9,%rax + lea (%rdx,%rax,4),%r15 + mov %r9,%rax + imul %rsi,%rax + sub %r9,%r13 + mov %r13,%r12 add %r8,%rax + lea (%rdx,%rax,4),%r14 + lea (%r8,%r11,8),%rax mov %rax,-offset(%rsp) - mov %r14,%rax + mov %rcx,%rax + neg %rax + lea offset(%r8),%rdx imul %r8,%rax - mov %r9,%rdx - lea offset(,%rcx,4),%rsi - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %r8,%rcx - sub %r9,%rcx - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %rcx,-offset(%rsp) - sub %rdi,%rcx - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %rdi,%r9 - mov %rcx,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax + imul %rcx,%rdx + sub %rdi,%r12 + shl $something,%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + mov %rdi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) mov %r8,-offset(%rsp) - movq $something,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - shl $something,%r9 - mov %r9,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - mov -offset(%rsp),%rax - mov %rax,%rdx - test %rax,%rax - jle - mov -offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - lea offset(%rax),%rcx - mov -offset(%rsp),%rax - add $something,%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - lea offset(%rax),%r8 - mov -offset(%rsp),%rax - lea offset(%rax),%r9 - mov -offset(%rsp),%rax - lea offset(%rax),%r10 - mov -offset(%rsp),%rax - lea offset(%rax),%r11 - mov -offset(%rsp),%rax - lea offset(%rax),%rbx /usr/lib64/libopenblas_openmp.a/ssymm_iltcopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/ssymm_iltcopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ssymm_iltcopy_COOPERLAKE.o (objdump) @@ -2,218 +2,106 @@ /usr/lib64/libopenblas_openmp.a/ssymm_iltcopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ecb00000 AWAVAUATUSH..... - 0010 004889b4 24900000 0048c1fe 0448897c .H..$....H...H.| - 0020 24e04889 14244889 4c24084c 89442410 $.H..$H.L$.L.D$. - 0030 4c894c24 184889b4 24a80000 004885f6 L.L$.H..$....H.. - 0040 0f8ee504 00004989 ce4c89c8 490fafc6 ......I..L..I... - 0050 4989d349 89f24c01 c0498d04 83488944 I..I..L..I...H.D - 0060 24b84c89 f048c1e0 06488944 24e84c89 $.L..H...H.D$.L. - 0070 d048c1e0 044c01c0 48894424 f04c89f0 .H...L..H.D$.L.. - 0080 490fafc0 4c89ca48 8d348d00 00000048 I...L..H.4.....H - 0090 01d0498d 04834889 8424a000 0000498d ..I...H..$....I. - 00a0 4001490f afc64c89 c14c29c9 4801d049 @.I...L..L).H..I - 00b0 8d048348 89842498 00000049 8d400249 ...H..$....I.@.I - 00c0 0fafc648 894c24b0 4829f948 01d0498d ...H.L$.H).H..I. - 00d0 04834889 44242849 8d400349 0fafc649 ..H.D$(I.@.I...I - 00e0 89f94889 4c24c048 01d0498d 04834889 ..H.L$.H..I...H. - 00f0 44243049 8d400449 0fafc64c 894424d0 D$0I.@.I...L.D$. - 0100 48c74424 c8000000 004801d0 498d0483 H.D$.....H..I... - 0110 48894424 38498d40 05490faf c64801d0 H.D$8I.@.I...H.. - 0120 498d0483 48894424 20498d40 06490faf I...H.D$ I.@.I.. - 0130 c64801d0 498d0483 48894424 40498d40 .H..I...H.D$@I.@ - 0140 07490faf c64801d0 498d0483 48894424 .I...H..I...H.D$ - 0150 48498d40 08490faf c64801d0 498d0483 HI.@.I...H..I... - 0160 48894424 50498d40 09490faf c64801d0 H.D$PI.@.I...H.. - 0170 498d0483 48894424 58498d40 0a490faf I...H.D$XI.@.I.. - 0180 c64801d0 498d0483 48894424 60498d40 .H..I...H.D$`I.@ - 0190 0b490faf c64801d0 498d0483 48894424 .I...H..I...H.D$ - 01a0 68498d40 0c490faf c64801d0 498d0483 hI.@.I...H..I... - 01b0 48898424 80000000 498d400d 490fafc6 H..$....I.@.I... - 01c0 49c1e106 4c894c24 f84801d0 498d0483 I...L.L$.H..I... - 01d0 48894424 70498d40 0e490faf c64801d0 H.D$pI.@.I...H.. - 01e0 498d0483 48894424 78498d40 0f490faf I...H.D$xI.@.I.. - 01f0 c64801d0 498d0483 48898424 88000000 .H..I...H..$.... - 0200 488b4424 b04889c2 4885c00f 8e9f0400 H.D$.H..H....... - 0210 00488b44 24b84889 44249848 8b4424b8 .H.D$.H.D$.H.D$. - 0220 4883c004 48894424 a0488b44 24b8488d H...H.D$.H.D$.H. - 0230 4808488b 4424b848 83c00c48 89442488 H.H.D$.H...H.D$. - 0240 488b4424 b84883c0 10488944 2490488b H.D$.H...H.D$.H. - 0250 4424b84c 8d401448 8b4424b8 4c8d4818 D$.L.@.H.D$.L.H. - 0260 488b4424 b84c8d50 1c488b44 24b84c8d H.D$.L.P.H.D$.L. - 0270 5820488b 4424b848 8d582448 8b4424b8 X H.D$.H.X$H.D$. - 0280 488d6828 488b4424 b84c8d60 2c488b44 H.h(H.D$.L.`,H.D - 0290 24b84c8d 6830488b 4424b84c 8d703448 $.L.h0H.D$.L.p4H - 02a0 8b4424b8 4c8d7838 488b4424 b8488d78 .D$.L.x8H.D$.H.x - 02b0 3c48837c 24e00048 8b8424e8 0000000f - mov %rcx,%r14 - mov %r9,%rax - imul %r14,%rax - mov %rdx,%r11 - mov %rsi,%r10 - add %r8,%rax - lea (%r11,%rax,4),%rax - mov %rax,-offset(%rsp) - mov %r14,%rax + mov %rsi,%r11 + mov %rcx,%rsi + mov %rsi,%rax shl $something,%rax mov %rax,-offset(%rsp) - mov %r10,%rax - shl $something,%rax + mov %rsi,%rax + imul %r8,%rax + lea offset(,%rcx,4),%rcx + mov %r8,%r13 + add %r9,%rax + lea (%rdx,%rax,4),%r15 + mov %r9,%rax + imul %rsi,%rax + sub %r9,%r13 + mov %r13,%r12 add %r8,%rax + lea (%rdx,%rax,4),%r14 + lea (%r8,%r11,8),%rax mov %rax,-offset(%rsp) - mov %r14,%rax + mov %rcx,%rax + neg %rax + lea offset(%r8),%rdx imul %r8,%rax - mov %r9,%rdx - lea offset(,%rcx,4),%rsi - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %r8,%rcx - sub %r9,%rcx - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %rcx,-offset(%rsp) - sub %rdi,%rcx - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %rdi,%r9 - mov %rcx,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax + imul %rcx,%rdx + sub %rdi,%r12 + shl $something,%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + mov %rdi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) mov %r8,-offset(%rsp) - movq $something,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - shl $something,%r9 - mov %r9,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - mov -offset(%rsp),%rax - mov %rax,%rdx - test %rax,%rax - jle - mov -offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - lea offset(%rax),%rcx - mov -offset(%rsp),%rax - add $something,%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - lea offset(%rax),%r8 - mov -offset(%rsp),%rax - lea offset(%rax),%r9 - mov -offset(%rsp),%rax - lea offset(%rax),%r10 - mov -offset(%rsp),%rax - lea offset(%rax),%r11 - mov -offset(%rsp),%rax - lea offset(%rax),%rbx /usr/lib64/libopenblas_openmp.a/ssymm_iltcopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/ssymm_iltcopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ssymm_iltcopy_SKYLAKEX.o (objdump) @@ -2,218 +2,106 @@ /usr/lib64/libopenblas_openmp.a/ssymm_iltcopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ecb00000 AWAVAUATUSH..... - 0010 004889b4 24900000 0048c1fe 0448897c .H..$....H...H.| - 0020 24e04889 14244889 4c24084c 89442410 $.H..$H.L$.L.D$. - 0030 4c894c24 184889b4 24a80000 004885f6 L.L$.H..$....H.. - 0040 0f8ee504 00004989 ce4c89c8 490fafc6 ......I..L..I... - 0050 4989d349 89f24c01 c0498d04 83488944 I..I..L..I...H.D - 0060 24b84c89 f048c1e0 06488944 24e84c89 $.L..H...H.D$.L. - 0070 d048c1e0 044c01c0 48894424 f04c89f0 .H...L..H.D$.L.. - 0080 490fafc0 4c89ca48 8d348d00 00000048 I...L..H.4.....H - 0090 01d0498d 04834889 8424a000 0000498d ..I...H..$....I. - 00a0 4001490f afc64c89 c14c29c9 4801d049 @.I...L..L).H..I - 00b0 8d048348 89842498 00000049 8d400249 ...H..$....I.@.I - 00c0 0fafc648 894c24b0 4829f948 01d0498d ...H.L$.H).H..I. - 00d0 04834889 44242849 8d400349 0fafc649 ..H.D$(I.@.I...I - 00e0 89f94889 4c24c048 01d0498d 04834889 ..H.L$.H..I...H. - 00f0 44243049 8d400449 0fafc64c 894424d0 D$0I.@.I...L.D$. - 0100 48c74424 c8000000 004801d0 498d0483 H.D$.....H..I... - 0110 48894424 38498d40 05490faf c64801d0 H.D$8I.@.I...H.. - 0120 498d0483 48894424 20498d40 06490faf I...H.D$ I.@.I.. - 0130 c64801d0 498d0483 48894424 40498d40 .H..I...H.D$@I.@ - 0140 07490faf c64801d0 498d0483 48894424 .I...H..I...H.D$ - 0150 48498d40 08490faf c64801d0 498d0483 HI.@.I...H..I... - 0160 48894424 50498d40 09490faf c64801d0 H.D$PI.@.I...H.. - 0170 498d0483 48894424 58498d40 0a490faf I...H.D$XI.@.I.. - 0180 c64801d0 498d0483 48894424 60498d40 .H..I...H.D$`I.@ - 0190 0b490faf c64801d0 498d0483 48894424 .I...H..I...H.D$ - 01a0 68498d40 0c490faf c64801d0 498d0483 hI.@.I...H..I... - 01b0 48898424 80000000 498d400d 490fafc6 H..$....I.@.I... - 01c0 49c1e106 4c894c24 f84801d0 498d0483 I...L.L$.H..I... - 01d0 48894424 70498d40 0e490faf c64801d0 H.D$pI.@.I...H.. - 01e0 498d0483 48894424 78498d40 0f490faf I...H.D$xI.@.I.. - 01f0 c64801d0 498d0483 48898424 88000000 .H..I...H..$.... - 0200 488b4424 b04889c2 4885c00f 8e9f0400 H.D$.H..H....... - 0210 00488b44 24b84889 44249848 8b4424b8 .H.D$.H.D$.H.D$. - 0220 4883c004 48894424 a0488b44 24b8488d H...H.D$.H.D$.H. - 0230 4808488b 4424b848 83c00c48 89442488 H.H.D$.H...H.D$. - 0240 488b4424 b84883c0 10488944 2490488b H.D$.H...H.D$.H. - 0250 4424b84c 8d401448 8b4424b8 4c8d4818 D$.L.@.H.D$.L.H. - 0260 488b4424 b84c8d50 1c488b44 24b84c8d H.D$.L.P.H.D$.L. - 0270 5820488b 4424b848 8d582448 8b4424b8 X H.D$.H.X$H.D$. - 0280 488d6828 488b4424 b84c8d60 2c488b44 H.h(H.D$.L.`,H.D - 0290 24b84c8d 6830488b 4424b84c 8d703448 $.L.h0H.D$.L.p4H - 02a0 8b4424b8 4c8d7838 488b4424 b8488d78 .D$.L.x8H.D$.H.x - 02b0 3c48837c 24e00048 8b8424e8 0000000f - mov %rcx,%r14 + mov %rsi,%r11 mov %r9,%rax - imul %r14,%rax - mov %rdx,%r11 - mov %rsi,%r10 + mov %rcx,%rsi + imul %rsi,%rax + mov %r8,%r13 + sub %r9,%r13 add %r8,%rax - lea offset(,%rcx,4),%rsi - mov %r8,%rcx - sub %r9,%rcx - lea (%r11,%rax,4),%rax - mov %rax,-offset(%rsp) - mov %rcx,%rax - sub %rdi,%rax - mov %rax,-offset(%rsp) - mov %r14,%rax + lea (%rdx,%rax,4),%r15 + mov %rsi,%rax shl $something,%rax mov %rax,-offset(%rsp) - mov %r10,%rax - shl $something,%rax - add %rcx,%rax - mov %rax,-offset(%rsp) - mov %r14,%rax - imul %r8,%rax - mov %r9,%rdx - mov %rdi,%r9 - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %rcx,-offset(%rsp) - movq $something,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - shl $something,%r9 - mov %r9,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - nopl offset(%rax,%rax,1) - mov -offset(%rsp),%rax - mov %rax,%rdx - test %rax,%rax - jle - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rcx - add offset(%rsp),%rcx - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%r8 - add offset(%rsp),%r8 - mov -offset(%rsp),%r9 - add offset(%rsp),%r9 - mov -offset(%rsp),%r10 - add offset(%rsp),%r10 - mov -offset(%rsp),%r11 - add offset(%rsp),%r11 - mov -offset(%rsp),%rbx - add offset(%rsp),%rbx - mov -offset(%rsp),%rbp - add offset(%rsp),%rbp - mov -offset(%rsp),%r12 - add offset(%rsp),%r12 - mov -offset(%rsp),%r13 - add offset(%rsp),%r13 - mov -offset(%rsp),%r14 - add offset(%rsp),%r14 - mov -offset(%rsp),%r15 - add offset(%rsp),%r15 - mov -offset(%rsp),%rdi - add offset(%rsp),%rdi - cmpq $something,-offset(%rsp) - mov offset(%rsp),%rax - jle - mov %rdx,-offset(%rsp) + imul %rsi,%rax + lea offset(,%rcx,4),%rcx + mov %r13,%r12 + add %r9,%rax + lea (%rdx,%rax,4),%r14 + lea offset(%r13,%r11,8),%rax + mov %rax,-offset(%rsp) + mov %r8,%rax + neg %rax + lea -offset(,%rax,4),%rax + mov %r8,%rdx + imul %rsi,%rax + imul %rcx,%rdx + sub %rdi,%r12 + shl $something,%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) mov %rdi,-offset(%rsp) - mov %rsi,%rdx /usr/lib64/libopenblas_openmp.a/ssymm_iutcopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/ssymm_iutcopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ssymm_iutcopy_COOPERLAKE.o (objdump) @@ -2,207 +2,104 @@ /usr/lib64/libopenblas_openmp.a/ssymm_iutcopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 eca80000 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 0448897c .H..$....H...H.| - 0020 24d84889 14244889 4c24084c 894424e0 $.H..$H.L$.L.D$. - 0030 4c894c24 104889b4 24a00000 004885f6 L.L$.H..$....H.. - 0040 0f8eff04 00004989 ce4c89c8 490fafc6 ......I..L..I... - 0050 4989d349 89f24c01 c0488d34 8d000000 I..I..L..H.4.... - 0060 004c89c1 4c29c949 8d048348 894424c8 .L..L).I...H.D$. - 0070 4889c848 29f84889 4424c04c 89f048c1 H..H).H.D$.L..H. - 0080 e0064889 4424e84c 89d048c1 e0044801 ..H.D$.L..H...H. - 0090 c8488944 24f04c89 f0490faf c04c89ca .H.D$.L..I...L.. - 00a0 4989f948 01d0498d 04834889 44241849 I..H..I...H.D$.I - 00b0 8d400149 0fafc648 894c24b0 48c74424 .@.I...H.L$.H.D$ - 00c0 b8000000 004801d0 498d0483 48894424 .....H..I...H.D$ - 00d0 20498d40 02490faf c64801d0 498d0483 I.@.I...H..I... - 00e0 48894424 28498d40 03490faf c64801d0 H.D$(I.@.I...H.. - 00f0 498d0483 48894424 60498d40 04490faf I...H.D$`I.@.I.. - 0100 c64801d0 498d0483 48894424 70498d40 .H..I...H.D$pI.@ - 0110 05490faf c64801d0 498d0483 48898424 .I...H..I...H..$ - 0120 88000000 498d4006 490fafc6 4801d049 ....I.@.I...H..I - 0130 8d048348 89842490 00000049 8d400749 ...H..$....I.@.I - 0140 0fafc648 01d0498d 04834889 44246849 ...H..I...H.D$hI - 0150 8d400849 0fafc648 01d0498d 04834889 .@.I...H..I...H. - 0160 44247849 8d400949 0fafc648 01d0498d D$xI.@.I...H..I. - 0170 04834889 84248000 0000498d 400a490f ..H..$....I.@.I. - 0180 afc64801 d0498d04 83488944 2458498d ..H..I...H.D$XI. - 0190 400b490f afc64801 d0498d04 83488944 @.I...H..I...H.D - 01a0 2450498d 400c490f afc64801 d0498d04 $PI.@.I...H..I.. - 01b0 83488944 2448498d 400d490f afc649c1 .H.D$HI.@.I...I. - 01c0 e1064c89 4c24f848 01d0498d 04834889 ..L.L$.H..I...H. - 01d0 44243049 8d400e49 0fafc648 01d0498d D$0I.@.I...H..I. - 01e0 04834889 44244049 8d400f49 0fafc648 ..H.D$@I.@.I...H - 01f0 01d0498d 04834889 4424380f 1f440000 ..I...H.D$8..D.. - 0200 488b4424 b04889c2 4885c00f 8e4f0500 H.D$.H..H....O.. - 0210 00488b44 24b84803 44241848 89442498 .H.D$.H.D$.H.D$. - 0220 488b4424 b8480344 24204889 4424a048 H.D$.H.D$ H.D$.H - 0230 8b4c24b8 48034c24 28488b44 24b84803 .L$.H.L$(H.D$.H. - 0240 44246048 89442488 488b4424 b8480344 D$`H.D$.H.D$.H.D - 0250 24704889 4424904c 8b4424b8 4c038424 $pH.D$.L.D$.L..$ - 0260 88000000 4c8b4c24 b84c038c 24900000 ....L.L$.L..$... - 0270 004c8b54 24b84c03 5424684c 8b5c24b8 .L.T$.L.T$hL.\$. - 0280 4c035c24 78488b5c 24b84803 9c248000 L.\$xH.\$.H..$.. - 0290 0000488b 6c24b848 036c2458 4c8b6424 ..H.l$.H.l$XL.d$ - 02a0 b84c0364 24504c8b 6c24b84c 036c2448 .L.d$PL.l$.L.l$H - 02b0 4c8b7424 b84c0374 24304c8b 7c24b84c L.t$.L.t$0L.|$.L - 02c0 037c2440 488b7c24 b848037c 24384883 .|$@H.|$.H.|$8H. - 02d0 7c24d800 488b8424 e0000000 0f8e1e02 |$..H..$........ - 02e0 00004889 5424d048 897c24a8 4889f248 ..H.T$.H.|$.H..H - 02f0 8b7424d0 e9b20000 000f1f80 00000000 .t$............. - 0300 48834424 98044883 4424a004 4883c104 H.D$..H.D$..H... - 0310 48834424 88044883 44249004 4983c004 H.D$..H.D$..I... - 0320 4983c104 4983c204 4983c304 4883c304 I...I...I...H... - 0330 4883c504 4983c404 4983c504 4983c604 H...I...I...I... - 0340 4983c704 48834424 a80448ff cec57a11 I...H.D$..H...z. - 0350 38c57a11 7004c57a 116808c5 7a11600c 8.z.p..z.h..z.`. - 0360 c57a1158 10c57a11 5014c57a 114818c5 .z.X..z.P..z.H.. - 0370 7a11401c c5fa1178 20c5fa11 7024c5fa z.@....x ...p$.. - 0380 116828c5 fa11602c c5fa1158 30c5fa11 .h(...`,...X0... - 0390 5034c5fa 114838c5 fa11403c 4883c040 P4...H8...@ - mov %rcx,%r14 + mov %rsi,%r11 mov %r9,%rax - imul %r14,%rax - mov %rdx,%r11 - mov %rsi,%r10 + mov %rcx,%rsi + imul %rsi,%rax + mov %r8,%r13 + sub %r9,%r13 add %r8,%rax - lea offset(,%rcx,4),%rsi - mov %r8,%rcx - sub %r9,%rcx - lea (%r11,%rax,4),%rax - mov %rax,-offset(%rsp) - mov %rcx,%rax - sub %rdi,%rax - mov %rax,-offset(%rsp) - mov %r14,%rax + lea (%rdx,%rax,4),%r15 + mov %rsi,%rax shl $something,%rax mov %rax,-offset(%rsp) - mov %r10,%rax - shl $something,%rax - add %rcx,%rax - mov %rax,-offset(%rsp) - mov %r14,%rax - imul %r8,%rax - mov %r9,%rdx - mov %rdi,%r9 - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - mov %rcx,-offset(%rsp) - movq $something,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - shl $something,%r9 - mov %r9,-offset(%rsp) - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%r8),%rax - imul %r14,%rax - add %rdx,%rax - lea (%r11,%rax,4),%rax - mov %rax,offset(%rsp) - nopl offset(%rax,%rax,1) - mov -offset(%rsp),%rax - mov %rax,%rdx - test %rax,%rax - jle - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rcx - add offset(%rsp),%rcx - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - add offset(%rsp),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%r8 - add offset(%rsp),%r8 - mov -offset(%rsp),%r9 - add offset(%rsp),%r9 - mov -offset(%rsp),%r10 - add offset(%rsp),%r10 - mov -offset(%rsp),%r11 - add offset(%rsp),%r11 - mov -offset(%rsp),%rbx - add offset(%rsp),%rbx - mov -offset(%rsp),%rbp - add offset(%rsp),%rbp - mov -offset(%rsp),%r12 - add offset(%rsp),%r12 - mov -offset(%rsp),%r13 - add offset(%rsp),%r13 - mov -offset(%rsp),%r14 - add offset(%rsp),%r14 - mov -offset(%rsp),%r15 - add offset(%rsp),%r15 - mov -offset(%rsp),%rdi - add offset(%rsp),%rdi - cmpq $something,-offset(%rsp) - mov offset(%rsp),%rax - jle - mov %rdx,-offset(%rsp) + imul %rsi,%rax + lea offset(,%rcx,4),%rcx + mov %r13,%r12 + add %r9,%rax + lea (%rdx,%rax,4),%r14 + lea offset(%r13,%r11,8),%rax + mov %rax,-offset(%rsp) + mov %r8,%rax + neg %rax + lea -offset(,%rax,4),%rax + mov %r8,%rdx + imul %rsi,%rax + imul %rcx,%rdx + sub %rdi,%r12 + shl $something,%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%r8),%rdx + imul %rcx,%rdx + mov %rsi,-offset(%rsp) mov %rdi,-offset(%rsp) - mov %rsi,%rdx /usr/lib64/libopenblas_openmp.a/ssymm_iutcopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/ssymm_iutcopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/ssymm_iutcopy_SKYLAKEX.o (objdump) @@ -2,207 +2,104 @@ /usr/lib64/libopenblas_openmp.a/ssymm_iutcopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 eca80000 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 0448897c .H..$....H...H.| - 0020 24d84889 14244889 4c24084c 894424e0 $.H..$H.L$.L.D$. - 0030 4c894c24 104889b4 24a00000 004885f6 L.L$.H..$....H.. - 0040 0f8eff04 00004989 ce4c89c8 490fafc6 ......I..L..I... - 0050 4989d349 89f24c01 c0488d34 8d000000 I..I..L..H.4.... - 0060 004c89c1 4c29c949 8d048348 894424c8 .L..L).I...H.D$. - 0070 4889c848 29f84889 4424c04c 89f048c1 H..H).H.D$.L..H. - 0080 e0064889 4424e84c 89d048c1 e0044801 ..H.D$.L..H...H. - 0090 c8488944 24f04c89 f0490faf c04c89ca .H.D$.L..I...L.. - 00a0 4989f948 01d0498d 04834889 44241849 I..H..I...H.D$.I - 00b0 8d400149 0fafc648 894c24b0 48c74424 .@.I...H.L$.H.D$ - 00c0 b8000000 004801d0 498d0483 48894424 .....H..I...H.D$ - 00d0 20498d40 02490faf c64801d0 498d0483 I.@.I...H..I... - 00e0 48894424 28498d40 03490faf c64801d0 H.D$(I.@.I...H.. - 00f0 498d0483 48894424 60498d40 04490faf I...H.D$`I.@.I.. - 0100 c64801d0 498d0483 48894424 70498d40 .H..I...H.D$pI.@ - 0110 05490faf c64801d0 498d0483 48898424 .I...H..I...H..$ - 0120 88000000 498d4006 490fafc6 4801d049 ....I.@.I...H..I - 0130 8d048348 89842490 00000049 8d400749 ...H..$....I.@.I - 0140 0fafc648 01d0498d 04834889 44246849 ...H..I...H.D$hI - 0150 8d400849 0fafc648 01d0498d 04834889 .@.I...H..I...H. - 0160 44247849 8d400949 0fafc648 01d0498d D$xI.@.I...H..I. - 0170 04834889 84248000 0000498d 400a490f ..H..$....I.@.I. - 0180 afc64801 d0498d04 83488944 2458498d ..H..I...H.D$XI. - 0190 400b490f afc64801 d0498d04 83488944 @.I...H..I...H.D - 01a0 2450498d 400c490f afc64801 d0498d04 $PI.@.I...H..I.. - 01b0 83488944 2448498d 400d490f afc649c1 .H.D$HI.@.I...I. - 01c0 e1064c89 4c24f848 01d0498d 04834889 ..L.L$.H..I...H. - 01d0 44243049 8d400e49 0fafc648 01d0498d D$0I.@.I...H..I. - 01e0 04834889 44244049 8d400f49 0fafc648 ..H.D$@I.@.I...H - 01f0 01d0498d 04834889 4424380f 1f440000 ..I...H.D$8..D.. - 0200 488b4424 b04889c2 4885c00f 8e4f0500 H.D$.H..H....O.. - 0210 00488b44 24b84803 44241848 89442498 .H.D$.H.D$.H.D$. - 0220 488b4424 b8480344 24204889 4424a048 H.D$.H.D$ H.D$.H - 0230 8b4c24b8 48034c24 28488b44 24b84803 .L$.H.L$(H.D$.H. - 0240 44246048 89442488 488b4424 b8480344 D$`H.D$.H.D$.H.D - 0250 24704889 4424904c 8b4424b8 4c038424 $pH.D$.L.D$.L..$ - 0260 88000000 4c8b4c24 b84c038c 24900000 ....L.L$.L..$... - 0270 004c8b54 24b84c03 5424684c 8b5c24b8 .L.T$.L.T$hL.\$. - 0280 4c035c24 78488b5c 24b84803 9c248000 L.\$xH.\$.H..$.. - 0290 0000488b 6c24b848 036c2458 4c8b6424 ..H.l$.H.l$XL.d$ - 02a0 b84c0364 24504c8b 6c24b84c 036c2448 .L.d$PL.l$.L.l$H - 02b0 4c8b7424 b84c0374 24304c8b 7c24b84c L.t$.L.t$0L.|$.L - 02c0 037c2440 488b7c24 b848037c 24384883 .|$@H.|$.H.|$8H. - 02d0 7c24d800 488b8424 e0000000 0f8e1e02 |$..H..$........ - 02e0 00004889 5424d048 897c24a8 4889f248 ..H.T$.H.|$.H..H - 02f0 8b7424d0 e9b20000 000f1f80 00000000 .t$............. - 0300 48834424 98044883 4424a004 4883c104 H.D$..H.D$..H... - 0310 48834424 88044883 44249004 4983c004 H.D$..H.D$..I... - 0320 4983c104 4983c204 4983c304 4883c304 I...I...I...H... - 0330 4883c504 4983c404 4983c504 4983c604 H...I...I...I... - 0340 4983c704 48834424 a80448ff cec57a11 I...H.D$..H...z. - 0350 38c57a11 7004c57a 116808c5 7a11600c 8.z.p..z.h..z.`. - 0360 c57a1158 10c57a11 5014c57a 114818c5 .z.X..z.P..z.H.. - 0370 7a11401c c5fa1178 20c5fa11 7024c5fa z.@....x ...p$.. - 0380 116828c5 fa11602c c5fa1158 30c5fa11 .h(...`,...X0... - 0390 5034c5fa 114838c5 fa11403c 4883c040 P4...H8...@ - mov %r8,%rsi - imul %rcx,%rsi - mov %rcx,%rax - mov %r8,%r9 - lea (%rcx,%rsi,1),%rcx - mov %rsi,%rdx - lea (%rax,%rcx,1),%rsi - lea (%rax,%rsi,1),%rdi - lea (%rax,%rdi,1),%r8 - lea (%r8,%rax,1),%r11 - mov %rax,%rbx - add %r11,%rbx - mov %r11,-offset(%rsp) - lea (%rbx,%rax,1),%r11 - mov %rbx,-offset(%rsp) - lea (%r11,%rax,1),%rbx - lea (%rbx,%rax,1),%rbp - lea offset(%rbp,%rax,1),%r12 - lea (%r12,%rax,1),%r13 - lea offset(%r13,%rax,1),%r14 - lea (%r14,%rax,1),%r15 - lea (%r15,%rax,1),%r10 - mov %r10,-offset(%rsp) - mov offset(%rsp),%r10 - shl $something,%rax - sar $something,%r10 - mov %r10,offset(%rsp) - mov offset(%rsp),%r10 + mov %rcx,%rsi + imul %r8,%rsi + mov %rdi,%r12 + mov %r12,%rax + mov %r9,%r15 + and $something,%eax + lea (%rsi,%rcx,2),%rdi mov %rax,offset(%rsp) - and $something,%r10d - mov %r10,offset(%rsp) - shl $something,%r10 - mov %r10,offset(%rsp) - mov offset(%rsp),%r10 - mov offset(%rsp),%rax - shl $something,%r10 - add %rax,%r10 - mov %r10,offset(%rsp) - mov %rax,%r10 - imul offset(%rsp),%rax - add %r9,%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,4),%r9 - mov %r10,%rax - inc %rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r9,offset(%rsp) - mov %r10,%rax - mov offset(%rsp),%r9 - add %rdx,%rax - lea (%r9,%rax,4),%rdx - mov %rdx,offset(%rsp) - lea (%r10,%rcx,1),%rax - mov %r10,%rdx - mov %r9,%r10 - lea (%r9,%rax,4),%r9 - lea (%rdx,%rsi,1),%rax - mov %rdx,%rcx - lea (%r10,%rax,4),%rsi - lea (%rdx,%rdi,1),%rax - mov %rsi,offset(%rsp) - mov %rdx,%rsi - lea (%r10,%rax,4),%rdx - lea (%rcx,%r8,1),%rax - mov %rdx,offset(%rsp) - lea (%r10,%rax,4),%rdx - mov -offset(%rsp),%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r10,%rax,4),%rdx - mov -offset(%rsp),%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r10,%rax,4),%rdx - lea (%rcx,%r11,1),%rax - mov %rdx,offset(%rsp) - lea (%r10,%rax,4),%rdx - lea (%rcx,%rbx,1),%rax /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_COOPERLAKE.o (objdump) @@ -2,832 +2,425 @@ /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24a00000 0048c1fe 044889bc .H..$....H...H.. - 0020 24900000 00488954 24684889 4c24584c $....H.T$hH.L$XL - 0030 89442440 4c898c24 80000000 4889b424 .D$@L..$....H..$ - 0040 c0010000 4885f60f 8e571600 004c89c6 ....H....W...L.. - 0050 480faff1 4889c84d 89c1488d 0c314889 H...H..M..H..1H. - 0060 f2488d34 08488d3c 304c8d04 384d8d1c .H.4.H.<0L..8M.. - 0070 004889c3 4c01db4c 895c2488 4c8d1c03 .H..L..L.\$.L... - 0080 48895c24 98498d1c 03488d2c 034c8d64 H.\$.I...H.,.L.d - 0090 05004d8d 2c044d8d 7405004d 8d3c064d ..M.,.M.t..M.<.M - 00a0 8d14074c 89542490 4c8b9424 90000000 ...L.T$.L..$.... - 00b0 48c1e006 49c1fa04 4c899424 88000000 H...I...L..$.... - 00c0 4c8b9424 90000000 48894424 604183e2 L..$....H.D$`A.. - 00d0 0f4c8954 245049c1 e2064c89 9424b801 .L.T$PI...L..$.. - 00e0 00004c8b 9424c001 0000488b 84248000 ..L..$....H..$.. - 00f0 000049c1 e2044901 c24c8994 24980000 ..I...I..L..$... - 0100 004989c2 480faf44 24584c01 c84c8b4c .I..H..D$XL..L.L - 0110 24684d8d 0c814c89 d048ffc0 480faf44 $hM...L..H..H..D - 0120 24584c89 8c24f800 00004c8b 4c246848 $XL..$....L.L$hH - 0130 03442440 4d8d0c81 4c89d048 83c00248 .D$@M...L..H...H - 0140 0faf4424 584c898c 24d00000 004c8b4c ..D$XL..$....L.L - 0150 24684803 4424404d 8d0c814c 89d04883 $hH.D$@M...L..H. - 0160 c003480f af442458 4c898c24 e0000000 ..H..D$XL..$.... - 0170 4c8b4c24 68480344 24404d8d 0c814c89 L.L$hH.D$@M...L. - 0180 d04883c0 04480faf 4424584c 898c24a8 .H...H..D$XL..$. - 0190 0000004c 8b4c2468 48034424 404d8d0c ...L.L$hH.D$@M.. - 01a0 814c89d0 4883c005 480faf44 24584c89 .L..H...H..D$XL. - 01b0 8c24c000 00004803 4424404c 8b4c2468 .$....H.D$@L.L$h - 01c0 4d8d0c81 4c89d048 83c00648 0faf4424 M...L..H...H..D$ - 01d0 584c898c 24000100 004c8b4c 24684803 XL..$....L.L$hH. - 01e0 4424404d 8d0c814c 89d04883 c007480f D$@M...L..H...H. - 01f0 af442458 4c898c24 10010000 4c8b4c24 .D$XL..$....L.L$ - 0200 68480344 24404d8d 0c814c89 d04883c0 hH.D$@M...L..H.. - 0210 08480faf 4424584c 898c2420 0100004c .H..D$XL..$ ...L - 0220 8b4c2468 48034424 404d8d0c 814c89d0 .L$hH.D$@M...L.. - 0230 4883c009 480faf44 24584c89 8c243001 H...H..D$XL..$0. - 0240 00004c8b 4c246848 03442440 4d8d0c81 ..L.L$hH.D$@M... - 0250 4c89d048 83c00a48 0faf4424 584c898c L..H...H..D$XL.. - 0260 24400100 004c8b4c 24684803 4424404d $@...L.L$hH.D$@M - 0270 8d0c814c 89d04883 c00b480f af442458 ...L..H...H..D$X - 0280 4c898c24 50010000 4c8b4c24 68480344 L..$P...L.L$hH.D - 0290 24404d8d 0c814c89 d04883c0 0c480faf $@M...L..H...H.. - 02a0 4424584c 898c2460 0100004c 8b4c2468 D$XL..$`...L.L$h - 02b0 48034424 404d8d0c 814c89d0 4883c00d H.D$@M...L..H... - 02c0 480faf44 24584c89 8c247001 00004803 H..D$XL..$p...H. - 02d0 4424404c 8b4c2468 4d8d0c81 4c89d048 D$@L.L$hM...L..H - 02e0 83c00e48 0faf4424 584c898c 24800100 ...H..D$XL..$... - 02f0 004c8b4c 24684803 4424404d 8d0c814c .L.L$hH.D$@M...L - 0300 89d04883 c00f480f af442458 4c898c24 ..H...H..D$XL..$ - 0310 90010000 4c8b4c24 68480344 24404d8d ....L.L$hH.D$@M. - 0320 0c814c89 8c24a001 00004c89 d04c8b4c ..L..$....L..L.L - 0330 24684801 d0498d14 81488994 24b80000 $hH..I...H..$... - 0340 00498d04 0a4c89d2 4d89ca4d 8d0c8148 .I...L..M..M...H - 0350 8d043248 89d1498d 3482488d 043a4889 ..2H..I.4.H..:H. - 0360 b424b000 00004889 d6498d14 824a8d04 .$....H..I...J.. - 0370 01488994 24c80000 00498d14 82488b44 .H..$....I...H.D - 0380 24884889 9424d800 00004801 c8498d14 $.H..$....H..I.. - 0390 82488b44 24984889 9424f000 00004801 .H.D$.H..$....H. - 03a0 c8498d14 824a8d04 19488994 24080100 .I...J...H..$... - 03b0 00498d14 82488d04 19488994 24180100 .I...H...H..$... - 03c0 00498d14 82488d04 29488994 24280100 .I...H..)H..$(.. - 03d0 00498d14 824a8d04 21488994 24380100 .I...J..!H..$8.. - 03e0 00498d14 824a8d04 29488994 24480100 .I...J..)H..$H.. - 03f0 00498d14 824a8d04 31488b5c 24904889 .I...J..1H.\$.H. - 0400 94245801 0000498d 14824a8d 04394889 .$X...I...J..9H. - 0410 94246801 0000498d 14824889 c84801d8 .$h...I...H..H.. - 0420 48035c24 58488994 24780100 00498d14 H.\$XH..$x...I.. - 0430 824889d8 4801c849 8d1c8248 899c2498 .H..H..I...H..$. - 0440 0100004c 898c24e8 00000048 89942488 ...L..$....H..$. - 0450 01000048 8bbc2490 00000048 8b4c2440 ...H..$....H.L$@ - 0460 4889f848 83e0f048 01c84889 44244848 H..H...H..H.D$HH - 0470 8b842488 00000048 897424e0 4889c348 ..$....H.t$.H..H - 0480 c1e30a48 c1e00448 01c84889 8424b001 ...H...H..H..$.. - 0490 00004889 f883e00e 48898424 c8010000 ..H.....H..$.... - 04a0 4889f883 e00c83e7 0848899c 24a80100 H........H..$... - 04b0 0048c744 24780000 000048c7 44247000 .H.D$x....H.D$p. - 04c0 00000048 898424d0 01000048 89bc24d8 ...H..$....H..$. - 04d0 010000e9 71010000 0f1f8400 00000000 ....q........... - 04e0 488b4424 70488bbc 24e80000 00488b8c H.D$pH..$....H.. - 04f0 24d80000 004801c7 48897c24 c0488bbc $....H..H.|$.H.. - 0500 24c80000 004801c1 4801c748 897c24d0 $....H..H..H.|$. - 0510 488bbc24 f0000000 48894c24 d84801c7 H..$....H.L$.H.. - 0520 48897c24 f0488bb4 24b80000 00488b8c H.|$.H..$....H.. - 0530 24080100 00488bbc 24180100 004801c6 $....H..$....H.. - 0540 4801c148 01c74889 7424b848 894c24f8 H..H..H.t$.H.L$. - 0550 48893c24 488b9c24 b0000000 488b8c24 H.<$H..$....H..$ - 0560 28010000 488bb424 38010000 488bbc24 (...H..$8...H..$ - 0570 48010000 4801c348 01c14801 c64801c7 H...H..H..H..H.. - 0580 48895c24 c848894c 24084889 74241048 H.\$.H.L$.H.t$.H - 0590 897c2418 488b9c24 58010000 488b8c24 .|$.H..$X...H..$ - 05a0 68010000 488bb424 78010000 488bbc24 h...H..$x...H..$ - 05b0 88010000 4801c348 01c14801 c64801c7 ....H..H..H..H.. - 05c0 48038424 98010000 48895c24 2048894c H..$....H.\$ H.L - 05d0 24284889 74243048 897c24e8 48894424 $(H.t$0H.|$.H.D$ - 05e0 384883bc 24880000 0000488b 4424400f 8H..$.....H.D$@. - 05f0 8f790100 0048837c 24500074 23483944 .y...H.|$P.t#H9D - 0600 24e00f8c ef260000 0f8e7219 0000488b $....&....r...H. - 0610 8424b801 00004801 84241802 00006690 .$....H..$....f. - 0620 48834424 e010488b 7c246048 83442470 H.D$..H.|$`H.D$p - 0630 4048017c 2478488b 4424e048 3b842498 @H.|$xH.D$.H;.$. - 0640 0000000f 843c1000 00488b4c 24404839 .....<...H.L$@H9 - 0650 4c24e00f 8d87feff ff488b44 2478488b L$.......H.D$xH. - 0660 bc24f800 0000488b b424d000 0000488b .$....H..$....H. - 0670 9c24e000 00004801 c74801c6 4801c348 .$....H..H..H..H - 0680 897c24b8 48897424 c048895c 24c8488b .|$.H.t$.H.\$.H. - 0690 bc24a800 0000488b b424c000 0000488b .$....H..$....H. - 06a0 9c240001 0000488b 8c241001 00004801 .$....H..$....H. - 06b0 c74801c6 4801c348 01c14889 7c24d048 .H..H..H..H.|$.H - 06c0 897424d8 48895c24 f048894c 24f8488b .t$.H.\$.H.L$.H. - 06d0 b4242001 0000488b bc243001 0000488b .$ ...H..$0...H. - 06e0 9c244001 0000488b 8c245001 00004801 .$@...H..$P...H. - 06f0 c64801c7 4801c348 01c14889 34244889 .H..H..H..H.4$H. - 0700 7c240848 895c2410 48894c24 18488bb4 |$.H.\$.H.L$.H.. - 0710 24600100 00488bbc 24700100 00488b9c $`...H..$p...H.. - 0720 24800100 00488b8c 24900100 004801c6 $....H..$....H.. - 0730 4801c748 01c34801 c1480384 24a00100 H..H..H..H..$... - 0740 00488974 24204889 7c242848 895c2430 .H.t$ H.|$(H.\$0 - 0750 48894c24 e8488944 24384883 bc248800 H.L$.H.D$8H..$.. - 0760 00000048 8b442440 0f8e87fe ffff488b ...H.D$@......H. - 0770 84241802 0000488d 90000400 00488b44 .$....H......H.D - 0780 24404889 4424b0eb 780f1f80 00000000 $@H.D$..x....... - 0790 488b4424 60480144 24b84801 4424c048 H.D$`H.D$.H.D$.H - 07a0 014424c8 48014424 d0480144 24d84801 .D$.H.D$.H.D$.H. - 07b0 4424f048 014424f8 48010424 48014424 D$.H.D$.H..$H.D$ - 07c0 08480144 24104801 44241848 01442420 .H.D$.H.D$.H.D$ - 07d0 48014424 28480144 24304801 4424e848 H.D$(H.D$0H.D$.H - 07e0 01442438 48834424 b0104881 c2000400 .D$8H.D$..H..... - 07f0 00488b44 24b0483b 4424480f 84670e00 .H.D$.H;D$H..g.. - 0800 00488b7c 24b0488d 8200fcff ff48397c .H.|$.H......H9| - 0810 24e00f8c 680c0000 0f8f72ff ffff488b $...h.....r...H. - 0820 4424b848 8b5c24c0 c5fa1000 c78204fc D$.H.\$......... - 0830 ffff0000 0000c782 08fcffff 00000000 ................ - 0840 c7820cfc ffff0000 0000c782 10fcffff ................ - 0850 00000000 c78214fc ffff0000 0000c782 ................ - 0860 18fcffff 00000000 c7821cfc ffff0000 ................ - 0870 0000c782 20fcffff 00000000 c78224fc .... .........$. - 0880 ffff0000 0000c782 28fcffff 00000000 ........(....... - 0890 c7822cfc ffff0000 0000c782 30fcffff ..,.........0... - 08a0 00000000 c78234fc ffff0000 0000c782 ......4......... - 08b0 38fcffff 00000000 c7823cfc ffff0000 8.........<..... - 08c0 0000c5fa 118200fc ffff4883 c340c5fa ..........H..@.. - 08d0 104004c5 fa118240 fcffffc5 fa1043c4 .@.....@......C. - 08e0 c78248fc ffff0000 0000c5fa 118244fc ..H...........D. - 08f0 ffffc782 4cfcffff 00000000 c78250fc ....L.........P. - 0900 ffff0000 0000c782 54fcffff 00000000 ........T....... - 0910 c78258fc ffff0000 0000c782 5cfcffff ..X.........\... - 0920 00000000 c78260fc ffff0000 0000c782 ......`......... - 0930 64fcffff 00000000 c78268fc ffff0000 d.........h..... - 0940 0000c782 6cfcffff 00000000 c78270fc ....l.........p. - 0950 ffff0000 0000c782 74fcffff 00000000 ........t....... - 0960 c78278fc ffff0000 0000c782 7cfcffff ..x.........|... - 0970 00000000 488b7424 c8488b7c 24d0c5fa ....H.t$.H.|$... - 0980 10400848 83c640c5 fa118280 fcffffc5 .@.H..@......... - 0990 fa1043c8 4883c740 c5fa1182 84fcffff ..C.H..@........ - 09a0 c5fa1046 c8c7828c fcffff00 000000c7 ...F............ - 09b0 8290fcff ff000000 00c78294 fcffff00 ................ - 09c0 000000c7 8298fcff ff000000 00c7829c ................ - 09d0 fcffff00 000000c7 82a0fcff ff000000 ................ - 09e0 00c782a4 fcffff00 000000c7 82a8fcff ................ - 09f0 ff000000 00c782ac fcffff00 000000c7 ................ - 0a00 82b0fcff ff000000 00c782b4 fcffff00 ................ - 0a10 000000c7 82b8fcff ff000000 00c782bc ................ - 0a20 fcffff00 000000c5 fa118288 fcffffc5 ................ - 0a30 fa10400c c5fa1182 c0fcffff c5fa1043 ..@............C - 0a40 ccc5fa11 82c4fcff ffc5fa10 46ccc5fa ............F... - 0a50 1182c8fc ffffc5fa 1047ccc5 fa1182cc .........G...... - 0a60 fcffffc7 82d0fcff ff000000 00c782d4 ................ - 0a70 fcffff00 000000c7 82d8fcff ff000000 ................ - 0a80 00c782dc fcffff00 000000c7 82e0fcff ................ - 0a90 ff000000 00c782e4 fcffff00 000000c7 ................ - 0aa0 82e8fcff ff000000 00c782ec fcffff00 ................ - 0ab0 000000c7 82f0fcff ff000000 00c782f4 ................ - 0ac0 fcffff00 000000c7 82f8fcff ff000000 ................ - 0ad0 00c782fc fcffff00 00000048 8b4c24d8 ...........H.L$. - 0ae0 c5fa1040 10c5fa11 8200fdff ffc5fa10 ...@............ - 0af0 43d0c5fa 118204fd ffffc5fa 1046d0c5 C............F.. - 0b00 fa118208 fdffffc5 fa1047d0 c5fa1182 ..........G..... - 0b10 0cfdffff c5fa1041 10c78214 fdffff00 .......A........ - 0b20 000000c5 fa118210 fdffffc7 8218fdff ................ - 0b30 ff000000 00c7821c fdffff00 000000c7 ................ - 0b40 8220fdff ff000000 00c78224 fdffff00 . .........$.... - 0b50 000000c7 8228fdff ff000000 00c7822c .....(........., - 0b60 fdffff00 000000c7 8230fdff ff000000 .........0...... - 0b70 00c78234 fdffff00 000000c7 8238fdff ...4.........8.. - 0b80 ff000000 00c7823c fdffff00 0000004c .......<.......L - 0b90 8b7424f0 c5fa1040 144983c6 40c5fa11 .t$....@.I..@... - 0ba0 8240fdff ffc5fa10 43d4c5fa 118244fd .@......C.....D. - 0bb0 ffffc5fa 1046d4c5 fa118248 fdffffc5 .....F.....H.... - 0bc0 fa1047d4 c5fa1182 4cfdffff c5fa1041 ..G.....L......A - 0bd0 14c5fa11 8250fdff ffc4c17a 1046d4c7 .....P.....z.F.. - 0be0 8258fdff ff000000 00c7825c fdffff00 .X.........\.... - 0bf0 000000c7 8260fdff ff000000 00c78264 .....`.........d - 0c00 fdffff00 000000c7 8268fdff ff000000 .........h...... - 0c10 00c7826c fdffff00 000000c7 8270fdff ...l.........p.. /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39000000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 c5330000 00420e10 8f02420e .....3...B....B. + 0020 00000000 571a0000 00420e10 8f02420e ....W....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 591f0a0e ..A.8..G....Y... + 0040 8606410e 38830747 0ec00203 95140a0e ..A.8..G........ 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e084a 0b000000 D..J.... + 0060 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_SKYLAKEX.o (disasm) @@ -17,1312 +17,907 @@ mov %rdi,offset(%rsp) mov %rdx,offset(%rsp) mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) + mov %r8,-offset(%rsp) mov %r9,offset(%rsp) mov %rsi,offset(%rsp) + mov offset(%rsp),%rbp test %rsi,%rsi jle - mov %r8,%rsi - imul %rcx,%rsi - mov %rcx,%rax - mov %r8,%r9 - lea (%rcx,%rsi,1),%rcx - mov %rsi,%rdx - lea (%rax,%rcx,1),%rsi - lea (%rax,%rsi,1),%rdi - lea (%rax,%rdi,1),%r8 - lea (%r8,%rax,1),%r11 - mov %rax,%rbx - add %r11,%rbx - mov %r11,-offset(%rsp) - lea (%rbx,%rax,1),%r11 - mov %rbx,-offset(%rsp) - lea (%r11,%rax,1),%rbx - lea (%rbx,%rax,1),%rbp - lea offset(%rbp,%rax,1),%r12 - lea (%r12,%rax,1),%r13 - lea offset(%r13,%rax,1),%r14 - lea (%r14,%rax,1),%r15 - lea (%r15,%rax,1),%r10 - mov %r10,-offset(%rsp) - mov offset(%rsp),%r10 - shl $something,%rax - sar $something,%r10 - mov %r10,offset(%rsp) - mov offset(%rsp),%r10 + mov %rcx,%rsi + imul %r8,%rsi + mov %rdi,%r12 + mov %r12,%rax + mov %r9,%r15 + and $something,%eax + lea (%rsi,%rcx,2),%rdi mov %rax,offset(%rsp) - and $something,%r10d - mov %r10,offset(%rsp) - shl $something,%r10 - mov %r10,offset(%rsp) - mov offset(%rsp),%r10 - mov offset(%rsp),%rax - shl $something,%r10 - add %rax,%r10 - mov %r10,offset(%rsp) - mov %rax,%r10 - imul offset(%rsp),%rax - add %r9,%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,4),%r9 - mov %r10,%rax - inc %rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r10,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r9,offset(%rsp) - mov %r10,%rax - mov offset(%rsp),%r9 - add %rdx,%rax - lea (%r9,%rax,4),%rdx - mov %rdx,offset(%rsp) - lea (%r10,%rcx,1),%rax - mov %r10,%rdx - mov %r9,%r10 - lea (%r9,%rax,4),%r9 - lea (%rdx,%rsi,1),%rax - mov %rdx,%rcx - lea (%r10,%rax,4),%rsi - lea (%rdx,%rdi,1),%rax - mov %rsi,offset(%rsp) - mov %rdx,%rsi - lea (%r10,%rax,4),%rdx - lea (%rcx,%r8,1),%rax - mov %rdx,offset(%rsp) - lea (%r10,%rax,4),%rdx - mov -offset(%rsp),%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r10,%rax,4),%rdx - mov -offset(%rsp),%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r10,%rax,4),%rdx - lea (%rcx,%r11,1),%rax - mov %rdx,offset(%rsp) - lea (%r10,%rax,4),%rdx - lea (%rcx,%rbx,1),%rax /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_SKYLAKEX.o (objdump) @@ -2,832 +2,425 @@ /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24a00000 0048c1fe 044889bc .H..$....H...H.. - 0020 24900000 00488954 24684889 4c24584c $....H.T$hH.L$XL - 0030 89442440 4c898c24 80000000 4889b424 .D$@L..$....H..$ - 0040 c0010000 4885f60f 8e571600 004c89c6 ....H....W...L.. - 0050 480faff1 4889c84d 89c1488d 0c314889 H...H..M..H..1H. - 0060 f2488d34 08488d3c 304c8d04 384d8d1c .H.4.H.<0L..8M.. - 0070 004889c3 4c01db4c 895c2488 4c8d1c03 .H..L..L.\$.L... - 0080 48895c24 98498d1c 03488d2c 034c8d64 H.\$.I...H.,.L.d - 0090 05004d8d 2c044d8d 7405004d 8d3c064d ..M.,.M.t..M.<.M - 00a0 8d14074c 89542490 4c8b9424 90000000 ...L.T$.L..$.... - 00b0 48c1e006 49c1fa04 4c899424 88000000 H...I...L..$.... - 00c0 4c8b9424 90000000 48894424 604183e2 L..$....H.D$`A.. - 00d0 0f4c8954 245049c1 e2064c89 9424b801 .L.T$PI...L..$.. - 00e0 00004c8b 9424c001 0000488b 84248000 ..L..$....H..$.. - 00f0 000049c1 e2044901 c24c8994 24980000 ..I...I..L..$... - 0100 004989c2 480faf44 24584c01 c84c8b4c .I..H..D$XL..L.L - 0110 24684d8d 0c814c89 d048ffc0 480faf44 $hM...L..H..H..D - 0120 24584c89 8c24f800 00004c8b 4c246848 $XL..$....L.L$hH - 0130 03442440 4d8d0c81 4c89d048 83c00248 .D$@M...L..H...H - 0140 0faf4424 584c898c 24d00000 004c8b4c ..D$XL..$....L.L - 0150 24684803 4424404d 8d0c814c 89d04883 $hH.D$@M...L..H. - 0160 c003480f af442458 4c898c24 e0000000 ..H..D$XL..$.... - 0170 4c8b4c24 68480344 24404d8d 0c814c89 L.L$hH.D$@M...L. - 0180 d04883c0 04480faf 4424584c 898c24a8 .H...H..D$XL..$. - 0190 0000004c 8b4c2468 48034424 404d8d0c ...L.L$hH.D$@M.. - 01a0 814c89d0 4883c005 480faf44 24584c89 .L..H...H..D$XL. - 01b0 8c24c000 00004803 4424404c 8b4c2468 .$....H.D$@L.L$h - 01c0 4d8d0c81 4c89d048 83c00648 0faf4424 M...L..H...H..D$ - 01d0 584c898c 24000100 004c8b4c 24684803 XL..$....L.L$hH. - 01e0 4424404d 8d0c814c 89d04883 c007480f D$@M...L..H...H. - 01f0 af442458 4c898c24 10010000 4c8b4c24 .D$XL..$....L.L$ - 0200 68480344 24404d8d 0c814c89 d04883c0 hH.D$@M...L..H.. - 0210 08480faf 4424584c 898c2420 0100004c .H..D$XL..$ ...L - 0220 8b4c2468 48034424 404d8d0c 814c89d0 .L$hH.D$@M...L.. - 0230 4883c009 480faf44 24584c89 8c243001 H...H..D$XL..$0. - 0240 00004c8b 4c246848 03442440 4d8d0c81 ..L.L$hH.D$@M... - 0250 4c89d048 83c00a48 0faf4424 584c898c L..H...H..D$XL.. - 0260 24400100 004c8b4c 24684803 4424404d $@...L.L$hH.D$@M - 0270 8d0c814c 89d04883 c00b480f af442458 ...L..H...H..D$X - 0280 4c898c24 50010000 4c8b4c24 68480344 L..$P...L.L$hH.D - 0290 24404d8d 0c814c89 d04883c0 0c480faf $@M...L..H...H.. - 02a0 4424584c 898c2460 0100004c 8b4c2468 D$XL..$`...L.L$h - 02b0 48034424 404d8d0c 814c89d0 4883c00d H.D$@M...L..H... - 02c0 480faf44 24584c89 8c247001 00004803 H..D$XL..$p...H. - 02d0 4424404c 8b4c2468 4d8d0c81 4c89d048 D$@L.L$hM...L..H - 02e0 83c00e48 0faf4424 584c898c 24800100 ...H..D$XL..$... - 02f0 004c8b4c 24684803 4424404d 8d0c814c .L.L$hH.D$@M...L - 0300 89d04883 c00f480f af442458 4c898c24 ..H...H..D$XL..$ - 0310 90010000 4c8b4c24 68480344 24404d8d ....L.L$hH.D$@M. - 0320 0c814c89 8c24a001 00004c89 d04c8b4c ..L..$....L..L.L - 0330 24684801 d0498d14 81488994 24b80000 $hH..I...H..$... - 0340 00498d04 0a4c89d2 4d89ca4d 8d0c8148 .I...L..M..M...H - 0350 8d043248 89d1498d 3482488d 043a4889 ..2H..I.4.H..:H. - 0360 b424b000 00004889 d6498d14 824a8d04 .$....H..I...J.. - 0370 01488994 24c80000 00498d14 82488b44 .H..$....I...H.D - 0380 24884889 9424d800 00004801 c8498d14 $.H..$....H..I.. - 0390 82488b44 24984889 9424f000 00004801 .H.D$.H..$....H. - 03a0 c8498d14 824a8d04 19488994 24080100 .I...J...H..$... - 03b0 00498d14 82488d04 19488994 24180100 .I...H...H..$... - 03c0 00498d14 82488d04 29488994 24280100 .I...H..)H..$(.. - 03d0 00498d14 824a8d04 21488994 24380100 .I...J..!H..$8.. - 03e0 00498d14 824a8d04 29488994 24480100 .I...J..)H..$H.. - 03f0 00498d14 824a8d04 31488b5c 24904889 .I...J..1H.\$.H. - 0400 94245801 0000498d 14824a8d 04394889 .$X...I...J..9H. - 0410 94246801 0000498d 14824889 c84801d8 .$h...I...H..H.. - 0420 48035c24 58488994 24780100 00498d14 H.\$XH..$x...I.. - 0430 824889d8 4801c849 8d1c8248 899c2498 .H..H..I...H..$. - 0440 0100004c 898c24e8 00000048 89942488 ...L..$....H..$. - 0450 01000048 8bbc2490 00000048 8b4c2440 ...H..$....H.L$@ - 0460 4889f848 83e0f048 01c84889 44244848 H..H...H..H.D$HH - 0470 8b842488 00000048 897424e0 4889c348 ..$....H.t$.H..H - 0480 c1e30a48 c1e00448 01c84889 8424b001 ...H...H..H..$.. - 0490 00004889 f883e00e 48898424 c8010000 ..H.....H..$.... - 04a0 4889f883 e00c83e7 0848899c 24a80100 H........H..$... - 04b0 0048c744 24780000 000048c7 44247000 .H.D$x....H.D$p. - 04c0 00000048 898424d0 01000048 89bc24d8 ...H..$....H..$. - 04d0 010000e9 71010000 0f1f8400 00000000 ....q........... - 04e0 488b4424 70488bbc 24e80000 00488b8c H.D$pH..$....H.. - 04f0 24d80000 004801c7 48897c24 c0488bbc $....H..H.|$.H.. - 0500 24c80000 004801c1 4801c748 897c24d0 $....H..H..H.|$. - 0510 488bbc24 f0000000 48894c24 d84801c7 H..$....H.L$.H.. - 0520 48897c24 f0488bb4 24b80000 00488b8c H.|$.H..$....H.. - 0530 24080100 00488bbc 24180100 004801c6 $....H..$....H.. - 0540 4801c148 01c74889 7424b848 894c24f8 H..H..H.t$.H.L$. - 0550 48893c24 488b9c24 b0000000 488b8c24 H.<$H..$....H..$ - 0560 28010000 488bb424 38010000 488bbc24 (...H..$8...H..$ - 0570 48010000 4801c348 01c14801 c64801c7 H...H..H..H..H.. - 0580 48895c24 c848894c 24084889 74241048 H.\$.H.L$.H.t$.H - 0590 897c2418 488b9c24 58010000 488b8c24 .|$.H..$X...H..$ - 05a0 68010000 488bb424 78010000 488bbc24 h...H..$x...H..$ - 05b0 88010000 4801c348 01c14801 c64801c7 ....H..H..H..H.. - 05c0 48038424 98010000 48895c24 2048894c H..$....H.\$ H.L - 05d0 24284889 74243048 897c24e8 48894424 $(H.t$0H.|$.H.D$ - 05e0 384883bc 24880000 0000488b 4424400f 8H..$.....H.D$@. - 05f0 8f790100 0048837c 24500074 23483944 .y...H.|$P.t#H9D - 0600 24e00f8c ef260000 0f8e7219 0000488b $....&....r...H. - 0610 8424b801 00004801 84241802 00006690 .$....H..$....f. - 0620 48834424 e010488b 7c246048 83442470 H.D$..H.|$`H.D$p - 0630 4048017c 2478488b 4424e048 3b842498 @H.|$xH.D$.H;.$. - 0640 0000000f 843c1000 00488b4c 24404839 .....<...H.L$@H9 - 0650 4c24e00f 8d87feff ff488b44 2478488b L$.......H.D$xH. - 0660 bc24f800 0000488b b424d000 0000488b .$....H..$....H. - 0670 9c24e000 00004801 c74801c6 4801c348 .$....H..H..H..H - 0680 897c24b8 48897424 c048895c 24c8488b .|$.H.t$.H.\$.H. - 0690 bc24a800 0000488b b424c000 0000488b .$....H..$....H. - 06a0 9c240001 0000488b 8c241001 00004801 .$....H..$....H. - 06b0 c74801c6 4801c348 01c14889 7c24d048 .H..H..H..H.|$.H - 06c0 897424d8 48895c24 f048894c 24f8488b .t$.H.\$.H.L$.H. - 06d0 b4242001 0000488b bc243001 0000488b .$ ...H..$0...H. - 06e0 9c244001 0000488b 8c245001 00004801 .$@...H..$P...H. - 06f0 c64801c7 4801c348 01c14889 34244889 .H..H..H..H.4$H. - 0700 7c240848 895c2410 48894c24 18488bb4 |$.H.\$.H.L$.H.. - 0710 24600100 00488bbc 24700100 00488b9c $`...H..$p...H.. - 0720 24800100 00488b8c 24900100 004801c6 $....H..$....H.. - 0730 4801c748 01c34801 c1480384 24a00100 H..H..H..H..$... - 0740 00488974 24204889 7c242848 895c2430 .H.t$ H.|$(H.\$0 - 0750 48894c24 e8488944 24384883 bc248800 H.L$.H.D$8H..$.. - 0760 00000048 8b442440 0f8e87fe ffff488b ...H.D$@......H. - 0770 84241802 0000488d 90000400 00488b44 .$....H......H.D - 0780 24404889 4424b0eb 780f1f80 00000000 $@H.D$..x....... - 0790 488b4424 60480144 24b84801 4424c048 H.D$`H.D$.H.D$.H - 07a0 014424c8 48014424 d0480144 24d84801 .D$.H.D$.H.D$.H. - 07b0 4424f048 014424f8 48010424 48014424 D$.H.D$.H..$H.D$ - 07c0 08480144 24104801 44241848 01442420 .H.D$.H.D$.H.D$ - 07d0 48014424 28480144 24304801 4424e848 H.D$(H.D$0H.D$.H - 07e0 01442438 48834424 b0104881 c2000400 .D$8H.D$..H..... - 07f0 00488b44 24b0483b 4424480f 84670e00 .H.D$.H;D$H..g.. - 0800 00488b7c 24b0488d 8200fcff ff48397c .H.|$.H......H9| - 0810 24e00f8c 680c0000 0f8f72ff ffff488b $...h.....r...H. - 0820 4424b848 8b5c24c0 c5fa1000 c78204fc D$.H.\$......... - 0830 ffff0000 0000c782 08fcffff 00000000 ................ - 0840 c7820cfc ffff0000 0000c782 10fcffff ................ - 0850 00000000 c78214fc ffff0000 0000c782 ................ - 0860 18fcffff 00000000 c7821cfc ffff0000 ................ - 0870 0000c782 20fcffff 00000000 c78224fc .... .........$. - 0880 ffff0000 0000c782 28fcffff 00000000 ........(....... - 0890 c7822cfc ffff0000 0000c782 30fcffff ..,.........0... - 08a0 00000000 c78234fc ffff0000 0000c782 ......4......... - 08b0 38fcffff 00000000 c7823cfc ffff0000 8.........<..... - 08c0 0000c5fa 118200fc ffff4883 c340c5fa ..........H..@.. - 08d0 104004c5 fa118240 fcffffc5 fa1043c4 .@.....@......C. - 08e0 c78248fc ffff0000 0000c5fa 118244fc ..H...........D. - 08f0 ffffc782 4cfcffff 00000000 c78250fc ....L.........P. - 0900 ffff0000 0000c782 54fcffff 00000000 ........T....... - 0910 c78258fc ffff0000 0000c782 5cfcffff ..X.........\... - 0920 00000000 c78260fc ffff0000 0000c782 ......`......... - 0930 64fcffff 00000000 c78268fc ffff0000 d.........h..... - 0940 0000c782 6cfcffff 00000000 c78270fc ....l.........p. - 0950 ffff0000 0000c782 74fcffff 00000000 ........t....... - 0960 c78278fc ffff0000 0000c782 7cfcffff ..x.........|... - 0970 00000000 488b7424 c8488b7c 24d0c5fa ....H.t$.H.|$... - 0980 10400848 83c640c5 fa118280 fcffffc5 .@.H..@......... - 0990 fa1043c8 4883c740 c5fa1182 84fcffff ..C.H..@........ - 09a0 c5fa1046 c8c7828c fcffff00 000000c7 ...F............ - 09b0 8290fcff ff000000 00c78294 fcffff00 ................ - 09c0 000000c7 8298fcff ff000000 00c7829c ................ - 09d0 fcffff00 000000c7 82a0fcff ff000000 ................ - 09e0 00c782a4 fcffff00 000000c7 82a8fcff ................ - 09f0 ff000000 00c782ac fcffff00 000000c7 ................ - 0a00 82b0fcff ff000000 00c782b4 fcffff00 ................ - 0a10 000000c7 82b8fcff ff000000 00c782bc ................ - 0a20 fcffff00 000000c5 fa118288 fcffffc5 ................ - 0a30 fa10400c c5fa1182 c0fcffff c5fa1043 ..@............C - 0a40 ccc5fa11 82c4fcff ffc5fa10 46ccc5fa ............F... - 0a50 1182c8fc ffffc5fa 1047ccc5 fa1182cc .........G...... - 0a60 fcffffc7 82d0fcff ff000000 00c782d4 ................ - 0a70 fcffff00 000000c7 82d8fcff ff000000 ................ - 0a80 00c782dc fcffff00 000000c7 82e0fcff ................ - 0a90 ff000000 00c782e4 fcffff00 000000c7 ................ - 0aa0 82e8fcff ff000000 00c782ec fcffff00 ................ - 0ab0 000000c7 82f0fcff ff000000 00c782f4 ................ - 0ac0 fcffff00 000000c7 82f8fcff ff000000 ................ - 0ad0 00c782fc fcffff00 00000048 8b4c24d8 ...........H.L$. - 0ae0 c5fa1040 10c5fa11 8200fdff ffc5fa10 ...@............ - 0af0 43d0c5fa 118204fd ffffc5fa 1046d0c5 C............F.. - 0b00 fa118208 fdffffc5 fa1047d0 c5fa1182 ..........G..... - 0b10 0cfdffff c5fa1041 10c78214 fdffff00 .......A........ - 0b20 000000c5 fa118210 fdffffc7 8218fdff ................ - 0b30 ff000000 00c7821c fdffff00 000000c7 ................ - 0b40 8220fdff ff000000 00c78224 fdffff00 . .........$.... - 0b50 000000c7 8228fdff ff000000 00c7822c .....(........., - 0b60 fdffff00 000000c7 8230fdff ff000000 .........0...... - 0b70 00c78234 fdffff00 000000c7 8238fdff ...4.........8.. - 0b80 ff000000 00c7823c fdffff00 0000004c .......<.......L - 0b90 8b7424f0 c5fa1040 144983c6 40c5fa11 .t$....@.I..@... - 0ba0 8240fdff ffc5fa10 43d4c5fa 118244fd .@......C.....D. - 0bb0 ffffc5fa 1046d4c5 fa118248 fdffffc5 .....F.....H.... - 0bc0 fa1047d4 c5fa1182 4cfdffff c5fa1041 ..G.....L......A - 0bd0 14c5fa11 8250fdff ffc4c17a 1046d4c7 .....P.....z.F.. - 0be0 8258fdff ff000000 00c7825c fdffff00 .X.........\.... - 0bf0 000000c7 8260fdff ff000000 00c78264 .....`.........d - 0c00 fdffff00 000000c7 8268fdff ff000000 .........h...... - 0c10 00c7826c fdffff00 000000c7 8270fdff ...l.........p.. /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39000000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnncopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 c5330000 00420e10 8f02420e .....3...B....B. + 0020 00000000 571a0000 00420e10 8f02420e ....W....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 591f0a0e ..A.8..G....Y... + 0040 8606410e 38830747 0ec00203 95140a0e ..A.8..G........ 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e084a 0b000000 D..J.... + 0060 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_COOPERLAKE.o (disasm) @@ -17,1279 +17,881 @@ mov %rdi,offset(%rsp) mov %rdx,offset(%rsp) mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) + mov %r8,-offset(%rsp) mov %r9,offset(%rsp) mov %rsi,offset(%rsp) + mov offset(%rsp),%rbp test %rsi,%rsi jle + mov %rcx,%r15 mov %r8,%rbx - imul %rcx,%rbx - mov %rcx,%rax - mov %r8,%r9 - lea (%rcx,%rbx,1),%rcx - lea (%rax,%rcx,1),%rsi - mov %rbx,%rdx - lea (%rax,%rsi,1),%rbx - lea (%rax,%rbx,1),%r8 - mov %rbx,-offset(%rsp) - lea (%r8,%rax,1),%rbx - lea (%rbx,%rax,1),%r10 - lea (%r10,%rax,1),%r11 - mov %rbx,-offset(%rsp) - lea (%r11,%rax,1),%rbx - lea (%rbx,%rax,1),%rbp - lea offset(%rbp,%rax,1),%r12 - lea (%r12,%rax,1),%r13 - lea offset(%r13,%rax,1),%r14 - lea (%r14,%rax,1),%r15 - lea (%r15,%rax,1),%rdi - mov %rdi,-offset(%rsp) - mov offset(%rsp),%rdi - shl $something,%rax - sar $something,%rdi - mov %rdi,offset(%rsp) - mov offset(%rsp),%rdi - mov %rax,offset(%rsp) - and $something,%edi - mov %rdi,offset(%rsp) - shl $something,%rdi - mov %rdi,offset(%rsp) - mov offset(%rsp),%rdi - mov offset(%rsp),%rax - shl $something,%rdi - add %rax,%rdi - mov %rdi,offset(%rsp) - mov %rax,%rdi - imul offset(%rsp),%rax - add %r9,%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - inc %rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r9,offset(%rsp) - mov %rdi,%rax - mov offset(%rsp),%r9 - add %rdx,%rax - lea (%r9,%rax,4),%rdx - lea (%rdi,%rcx,1),%rax - lea (%r9,%rax,4),%rax + imul %r15,%rbx + mov %rdi,%r12 + mov %r12,%rax + mov %rbx,%rsi + mov %r9,%rcx + and $something,%eax + lea (%rbx,%r15,2),%rdi mov %rax,offset(%rsp) - lea (%rdi,%rsi,1),%rax - mov %rdx,offset(%rsp) - lea (%r9,%rax,4),%rdx - mov -offset(%rsp),%rax - mov %rdx,offset(%rsp) - add %rdi,%rax - lea (%r9,%rax,4),%rdx - lea (%rdi,%r8,1),%rax - mov %rdx,offset(%rsp) - lea (%r9,%rax,4),%rdx - mov -offset(%rsp),%rax - mov %rdx,offset(%rsp) - add %rdi,%rax - lea (%r9,%rax,4),%rdx - lea (%rdi,%r10,1),%rax - mov %rdx,offset(%rsp) - lea (%r9,%rax,4),%rdx - lea (%rdi,%r11,1),%rax - mov %rdx,offset(%rsp) - lea (%r9,%rax,4),%rdx - lea (%rdi,%rbx,1),%rax - mov %rdx,offset(%rsp) - lea (%r9,%rax,4),%rdx - lea (%rdi,%rbp,1),%rax /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_COOPERLAKE.o (objdump) @@ -2,803 +2,395 @@ /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24a00000 0048c1fe 044889bc .H..$....H...H.. - 0020 24900000 00488954 24684889 4c24584c $....H.T$hH.L$XL - 0030 89442438 4c898c24 80000000 4889b424 .D$8L..$....H..$ - 0040 c0010000 4885f60f 8ee71500 004c89c3 ....H........L.. - 0050 480fafd9 4889c84d 89c1488d 0c19488d H...H..M..H...H. - 0060 34084889 da488d1c 304c8d04 1848895c 4.H..H..0L...H.\ - 0070 2498498d 1c004c8d 14034d8d 1c024889 $.I...L...M...H. - 0080 5c249049 8d1c0348 8d2c034c 8d640500 \$.I...H.,.L.d.. - 0090 4d8d2c04 4d8d7405 004d8d3c 06498d3c M.,.M.t..M.<.I.< - 00a0 0748897c 2488488b bc249000 000048c1 .H.|$.H..$....H. - 00b0 e00648c1 ff044889 bc248800 0000488b ..H...H..$....H. - 00c0 bc249000 00004889 44246083 e70f4889 .$....H.D$`...H. - 00d0 7c245048 c1e70648 89bc24b8 01000048 |$PH...H..$....H - 00e0 8bbc24c0 01000048 8b842480 00000048 ..$....H..$....H - 00f0 c1e70448 01c74889 bc249800 00004889 ...H..H..$....H. - 0100 c7480faf 4424584c 01c84c8b 4c24684d .H..D$XL..L.L$hM - 0110 8d0c8148 89f848ff c0480faf 4424584c ...H..H..H..D$XL - 0120 898c24b8 0000004c 8b4c2468 48034424 ..$....L.L$hH.D$ - 0130 384d8d0c 814889f8 4883c002 480faf44 8M...H..H...H..D - 0140 24584c89 8c24c800 00004c8b 4c246848 $XL..$....L.L$hH - 0150 03442438 4d8d0c81 4889f848 83c00348 .D$8M...H..H...H - 0160 0faf4424 584c898c 24d80000 004c8b4c ..D$XL..$....L.L - 0170 24684803 4424384d 8d0c8148 89f84883 $hH.D$8M...H..H. - 0180 c004480f af442458 4c898c24 a8000000 ..H..D$XL..$.... - 0190 4c8b4c24 68480344 24384d8d 0c814889 L.L$hH.D$8M...H. - 01a0 f84883c0 05480faf 4424584c 898c24f0 .H...H..D$XL..$. - 01b0 00000048 03442438 4c8b4c24 684d8d0c ...H.D$8L.L$hM.. - 01c0 814889f8 4883c006 480faf44 24584c89 .H..H...H..D$XL. - 01d0 8c240001 00004c8b 4c246848 03442438 .$....L.L$hH.D$8 - 01e0 4d8d0c81 4889f848 83c00748 0faf4424 M...H..H...H..D$ - 01f0 584c898c 24100100 004c8b4c 24684803 XL..$....L.L$hH. - 0200 4424384d 8d0c8148 89f84883 c008480f D$8M...H..H...H. - 0210 af442458 4c898c24 20010000 4c8b4c24 .D$XL..$ ...L.L$ - 0220 68480344 24384d8d 0c814889 f84883c0 hH.D$8M...H..H.. - 0230 09480faf 4424584c 898c2430 0100004c .H..D$XL..$0...L - 0240 8b4c2468 48034424 384d8d0c 814889f8 .L$hH.D$8M...H.. - 0250 4883c00a 480faf44 24584c89 8c244001 H...H..D$XL..$@. - 0260 00004c8b 4c246848 03442438 4d8d0c81 ..L.L$hH.D$8M... - 0270 4889f848 83c00b48 0faf4424 584c898c H..H...H..D$XL.. - 0280 24500100 004c8b4c 24684803 4424384d $P...L.L$hH.D$8M - 0290 8d0c8148 89f84883 c00c480f af442458 ...H..H...H..D$X - 02a0 4c898c24 60010000 4c8b4c24 68480344 L..$`...L.L$hH.D - 02b0 24384d8d 0c814889 f84883c0 0d480faf $8M...H..H...H.. - 02c0 4424584c 898c2470 01000048 03442438 D$XL..$p...H.D$8 - 02d0 4c8b4c24 684d8d0c 814889f8 4883c00e L.L$hM...H..H... - 02e0 480faf44 24584c89 8c248001 00004c8b H..D$XL..$....L. - 02f0 4c246848 03442438 4d8d0c81 4889f848 L$hH.D$8M...H..H - 0300 83c00f48 0faf4424 584c898c 24900100 ...H..D$XL..$... - 0310 004c8b4c 24684803 4424384d 8d0c814c .L.L$hH.D$8M...L - 0320 898c24a0 01000048 89f84c8b 4c246848 ..$....H..L.L$hH - 0330 01d0498d 1481488d 040f498d 04814889 ..I...H...I...H. - 0340 8424e000 0000488d 04374889 9424d000 .$....H..7H..$.. - 0350 0000498d 1481488b 44249848 899424b0 ..I...H.D$.H..$. - 0360 00000048 01f8498d 14814a8d 04074889 ...H..I...J...H. - 0370 9424c000 0000498d 1481488b 44249048 .$....I...H.D$.H - 0380 899424e8 00000048 01f8498d 14814a8d ..$....H..I...J. - 0390 04174889 9424f800 0000498d 14814a8d ..H..$....I...J. - 03a0 041f4889 94240801 0000498d 1481488d ..H..$....I...H. - 03b0 041f4889 94241801 0000498d 1481488d ..H..$....I...H. - 03c0 042f4889 94242801 0000498d 14814a8d ./H..$(...I...J. - 03d0 04274889 94243801 0000498d 14814a8d .'H..$8...I...J. - 03e0 042f4889 94244801 0000498d 14814a8d ./H..$H...I...J. - 03f0 0437488b 4c248848 89942458 01000049 .7H.L$.H..$X...I - 0400 8d14814a 8d043f48 89942468 01000049 ...J..?H..$h...I - 0410 8d148148 89f84801 c848034c 24584889 ...H..H..H.L$XH. - 0420 94247801 0000498d 14814889 c84801f8 .$x...I...H..H.. - 0430 498d0c81 48898c24 98010000 48899424 I...H..$....H..$ - 0440 88010000 488b9c24 90000000 488b7424 ....H..$....H.t$ - 0450 384889d8 4883e0f0 4801f048 89442448 8H..H...H..H.D$H - 0460 488b8424 88000000 48897c24 d84889c1 H..$....H.|$.H.. - 0470 48c1e004 48c1e10a 4801f048 898424b0 H...H...H..H..$. - 0480 01000048 89d883e0 0e488984 24c80100 ...H.....H..$... - 0490 004889d8 83e00c83 e3084889 8c24a801 .H........H..$.. - 04a0 000048c7 44247800 00000048 c7442470 ..H.D$x....H.D$p - 04b0 00000000 48898424 d0010000 48899c24 ....H..$....H..$ - 04c0 d8010000 c5fa100d 00000000 e9780100 .............x.. - 04d0 000f1f80 00000000 488b4424 70488bbc ........H.D$pH.. - 04e0 24d00000 00488b8c 24c00000 004801c7 $....H..$....H.. - 04f0 48897c24 b8488bbc 24e00000 004801c1 H.|$.H..$....H.. - 0500 4801c748 897c24c0 488bbc24 b0000000 H..H.|$.H..$.... - 0510 48894c24 d04801c7 48897c24 c8488bbc H.L$.H..H.|$.H.. - 0520 24e80000 00488b8c 24f80000 004801c7 $....H..$....H.. - 0530 48897c24 e0488bbc 24080100 004801c1 H.|$.H..$....H.. - 0540 4801c748 894c24e8 48897c24 f0488b8c H..H.L$.H.|$.H.. - 0550 24180100 00488bb4 24280100 00488bbc $....H..$(...H.. - 0560 24380100 00488b9c 24480100 004801c1 $8...H..$H...H.. - 0570 4801c648 01c74801 c348894c 24f84889 H..H..H..H.L$.H. - 0580 34244889 7c240848 895c2410 488b8c24 4$H.|$.H.\$.H..$ - 0590 58010000 488bb424 68010000 488bbc24 X...H..$h...H..$ - 05a0 78010000 488b9c24 88010000 4801c148 x...H..$....H..H - 05b0 01c64801 c74801c3 48038424 98010000 ..H..H..H..$.... - 05c0 48894c24 18488974 24204889 7c242848 H.L$.H.t$ H.|$(H - 05d0 895c2430 48894424 404883bc 24880000 .\$0H.D$@H..$... - 05e0 0000488b 4424380f 8f810100 0048837c ..H.D$8......H.| - 05f0 24500074 2b483944 24d80f8c 5e250000 $P.t+H9D$...^%.. - 0600 0f8eea18 0000488b 8424b801 00004801 ......H..$....H. - 0610 84241802 0000662e 0f1f8400 00000000 .$....f......... - 0620 48834424 d810488b 74246048 83442470 H.D$..H.t$`H.D$p - 0630 40480174 2478488b 4424d848 3b842498 @H.t$xH.D$.H;.$. - 0640 0000000f 84cc0f00 00488b74 24384839 .........H.t$8H9 - 0650 7424d80f 8d7ffeff ff488b44 2478488b t$.......H.D$xH. - 0660 9c24b800 0000488b bc24c800 0000488b .$....H..$....H. - 0670 b424d800 00004801 c34801c7 4801c648 .$....H..H..H..H - 0680 895c24b8 48897c24 c0488974 24c8488b .\$.H.|$.H.t$.H. - 0690 9c24a800 0000488b 8c24f000 0000488b .$....H..$....H. - 06a0 b4240001 0000488b bc241001 00004801 .$....H..$....H. - 06b0 c34801c1 4801c648 01c74889 5c24d048 .H..H..H..H.\$.H - 06c0 894c24e0 48897424 e848897c 24f0488b .L$.H.t$.H.|$.H. - 06d0 9c242001 0000488b 8c243001 0000488b .$ ...H..$0...H. - 06e0 b4244001 0000488b bc245001 00004801 .$@...H..$P...H. - 06f0 c34801c1 4801c648 01c74889 5c24f848 .H..H..H..H.\$.H - 0700 890c2448 89742408 48897c24 10488b9c ..$H.t$.H.|$.H.. - 0710 24600100 00488b8c 24700100 00488bb4 $`...H..$p...H.. - 0720 24800100 00488bbc 24900100 004801c3 $....H..$....H.. - 0730 4801c148 01c64801 c7480384 24a00100 H..H..H..H..$... - 0740 0048895c 24184889 4c242048 89742428 .H.\$.H.L$ H.t$( - 0750 48897c24 30488944 24404883 bc248800 H.|$0H.D$@H..$.. - 0760 00000048 8b442438 0f8e7ffe ffff488b ...H.D$8......H. - 0770 84241802 0000488d 90000400 00488b44 .$....H......H.D - 0780 24384889 4424b0eb 780f1f80 00000000 $8H.D$..x....... - 0790 488b4424 60480144 24b84801 4424c048 H.D$`H.D$.H.D$.H - 07a0 014424c8 48014424 d0480144 24e04801 .D$.H.D$.H.D$.H. - 07b0 4424e848 014424f0 48014424 f8480104 D$.H.D$.H.D$.H.. - 07c0 24480144 24084801 44241048 01442418 $H.D$.H.D$.H.D$. - 07d0 48014424 20480144 24284801 44243048 H.D$ H.D$(H.D$0H - 07e0 01442440 48834424 b0104881 c2000400 .D$@H.D$..H..... - 07f0 00488b44 24b0483b 4424480f 84f70d00 .H.D$.H;D$H..... - 0800 00488b4c 24b0488d 8200fcff ff48394c .H.L$.H......H9L - 0810 24d80f8c 000c0000 0f8f72ff ffffc782 $.........r..... - 0820 04fcffff 00000000 c78208fc ffff0000 ................ - 0830 0000c782 0cfcffff 00000000 c78210fc ................ - 0840 ffff0000 0000c782 14fcffff 00000000 ................ - 0850 c78218fc ffff0000 0000c782 1cfcffff ................ - 0860 00000000 c78220fc ffff0000 0000c782 ...... ......... - 0870 24fcffff 00000000 c78228fc ffff0000 $.........(..... - 0880 0000c782 2cfcffff 00000000 c78230fc ....,.........0. - 0890 ffff0000 0000c782 34fcffff 00000000 ........4....... - 08a0 c78238fc ffff0000 0000c782 3cfcffff ..8.........<... - 08b0 00000000 488b4424 b8c5fa11 8a00fcff ....H.D$........ - 08c0 ffc5fa10 4004c782 48fcffff 00000000 ....@...H....... - 08d0 c5fa1182 40fcffff c7824cfc ffff0000 ....@.....L..... - 08e0 0000c782 50fcffff 00000000 c78254fc ....P.........T. - 08f0 ffff0000 0000c782 58fcffff 00000000 ........X....... - 0900 c7825cfc ffff0000 0000c782 60fcffff ..\.........`... - 0910 00000000 c78264fc ffff0000 0000c782 ......d......... - 0920 68fcffff 00000000 c7826cfc ffff0000 h.........l..... - 0930 0000c782 70fcffff 00000000 c78274fc ....p.........t. - 0940 ffff0000 0000c5fa 118a44fc ffffc782 ..........D..... - 0950 78fcffff 00000000 c7827cfc ffff0000 x.........|..... - 0960 0000488b 5c24c048 8b7424c8 c5fa1040 ..H.\$.H.t$....@ - 0970 084883c3 40c5fa11 8280fcff ffc5fa10 .H..@........... - 0980 43c8c782 8cfcffff 00000000 c78290fc C............... - 0990 ffff0000 0000c782 94fcffff 00000000 ................ - 09a0 c78298fc ffff0000 0000c782 9cfcffff ................ - 09b0 00000000 c782a0fc ffff0000 0000c782 ................ - 09c0 a4fcffff 00000000 c782a8fc ffff0000 ................ - 09d0 0000c782 acfcffff 00000000 c782b0fc ................ - 09e0 ffff0000 0000c782 b4fcffff 00000000 ................ - 09f0 c782b8fc ffff0000 0000c782 bcfcffff ................ - 0a00 00000000 c5fa1182 84fcffff c5fa118a ................ - 0a10 88fcffff c5fa1040 0c4883c6 40c5fa11 .......@.H..@... - 0a20 82c0fcff ffc5fa10 43ccc5fa 1182c4fc ........C....... - 0a30 ffffc5fa 1046ccc7 82d0fcff ff000000 .....F.......... - 0a40 00c5fa11 82c8fcff ffc782d4 fcffff00 ................ - 0a50 000000c7 82d8fcff ff000000 00c782dc ................ - 0a60 fcffff00 000000c5 fa118acc fcffffc7 ................ - 0a70 82e0fcff ff000000 00c782e4 fcffff00 ................ - 0a80 000000c7 82e8fcff ff000000 00c782ec ................ - 0a90 fcffff00 000000c7 82f0fcff ff000000 ................ - 0aa0 00c782f4 fcffff00 000000c7 82f8fcff ................ - 0ab0 ff000000 00c782fc fcffff00 00000048 ...............H - 0ac0 8b7c24d0 c5fa1040 104883c7 40c5fa11 .|$....@.H..@... - 0ad0 8200fdff ffc5fa10 43d0c5fa 118204fd ........C....... - 0ae0 ffffc5fa 1046d0c5 fa118208 fdffffc5 .....F.......... - 0af0 fa1047d0 c78214fd ffff0000 0000c782 ..G............. - 0b00 18fdffff 00000000 c7821cfd ffff0000 ................ - 0b10 0000c782 20fdffff 00000000 c78224fd .... .........$. - 0b20 ffff0000 0000c782 28fdffff 00000000 ........(....... - 0b30 c7822cfd ffff0000 0000c782 30fdffff ..,.........0... - 0b40 00000000 c78234fd ffff0000 0000c782 ......4......... - 0b50 38fdffff 00000000 c7823cfd ffff0000 8.........<..... - 0b60 0000c5fa 11820cfd ffffc5fa 118a10fd ................ - 0b70 ffffc5fa 104014c5 fa118240 fdffffc5 .....@.....@.... - 0b80 fa1043d4 c5fa1182 44fdffff c5fa1046 ..C.....D......F - 0b90 d4488b4c 24e0c5fa 118248fd ffffc5fa .H.L$.....H..... - 0ba0 1047d44c 8b7424e8 c5fa1182 4cfdffff .G.L.t$.....L... - 0bb0 c5fa1041 14c78258 fdffff00 000000c7 ...A...X........ - 0bc0 825cfdff ff000000 00c78260 fdffff00 .\.........`.... - 0bd0 000000c7 8264fdff ff000000 00c78268 .....d.........h - 0be0 fdffff00 000000c7 826cfdff ff000000 .........l...... - 0bf0 00c78270 fdffff00 000000c7 8274fdff ...p.........t.. - 0c00 ff000000 00c78278 fdffff00 000000c7 .......x........ - 0c10 827cfdff ff000000 00c5fa11 8250fdff .|...........P.. /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39000000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 f1310000 00420e10 8f02420e .....1...B....B. + 0020 00000000 7a180000 00420e10 8f02420e ....z....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 c91e0a0e ..A.8..G........ + 0040 8606410e 38830747 0ec00203 e9130a0e ..A.8..G........ 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. 0060 440e084a 0b000000 D..J.... /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_SKYLAKEX.o (disasm) @@ -17,1279 +17,881 @@ mov %rdi,offset(%rsp) mov %rdx,offset(%rsp) mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) + mov %r8,-offset(%rsp) mov %r9,offset(%rsp) mov %rsi,offset(%rsp) + mov offset(%rsp),%rbp test %rsi,%rsi jle + mov %rcx,%r15 mov %r8,%rbx - imul %rcx,%rbx - mov %rcx,%rax - mov %r8,%r9 - lea (%rcx,%rbx,1),%rcx - lea (%rax,%rcx,1),%rsi - mov %rbx,%rdx - lea (%rax,%rsi,1),%rbx - lea (%rax,%rbx,1),%r8 - mov %rbx,-offset(%rsp) - lea (%r8,%rax,1),%rbx - lea (%rbx,%rax,1),%r10 - lea (%r10,%rax,1),%r11 - mov %rbx,-offset(%rsp) - lea (%r11,%rax,1),%rbx - lea (%rbx,%rax,1),%rbp - lea offset(%rbp,%rax,1),%r12 - lea (%r12,%rax,1),%r13 - lea offset(%r13,%rax,1),%r14 - lea (%r14,%rax,1),%r15 - lea (%r15,%rax,1),%rdi - mov %rdi,-offset(%rsp) - mov offset(%rsp),%rdi - shl $something,%rax - sar $something,%rdi - mov %rdi,offset(%rsp) - mov offset(%rsp),%rdi - mov %rax,offset(%rsp) - and $something,%edi - mov %rdi,offset(%rsp) - shl $something,%rdi - mov %rdi,offset(%rsp) - mov offset(%rsp),%rdi - mov offset(%rsp),%rax - shl $something,%rdi - add %rax,%rdi - mov %rdi,offset(%rsp) - mov %rax,%rdi - imul offset(%rsp),%rax - add %r9,%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - inc %rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - add offset(%rsp),%rax - mov offset(%rsp),%r9 - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %rdi,%rax - add $something,%rax - imul offset(%rsp),%rax - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add offset(%rsp),%rax - lea (%r9,%rax,4),%r9 - mov %r9,offset(%rsp) - mov %rdi,%rax - mov offset(%rsp),%r9 - add %rdx,%rax - lea (%r9,%rax,4),%rdx - lea (%rdi,%rcx,1),%rax - lea (%r9,%rax,4),%rax + imul %r15,%rbx + mov %rdi,%r12 + mov %r12,%rax + mov %rbx,%rsi + mov %r9,%rcx + and $something,%eax + lea (%rbx,%r15,2),%rdi mov %rax,offset(%rsp) - lea (%rdi,%rsi,1),%rax - mov %rdx,offset(%rsp) - lea (%r9,%rax,4),%rdx - mov -offset(%rsp),%rax - mov %rdx,offset(%rsp) - add %rdi,%rax - lea (%r9,%rax,4),%rdx - lea (%rdi,%r8,1),%rax - mov %rdx,offset(%rsp) - lea (%r9,%rax,4),%rdx - mov -offset(%rsp),%rax - mov %rdx,offset(%rsp) - add %rdi,%rax - lea (%r9,%rax,4),%rdx - lea (%rdi,%r10,1),%rax - mov %rdx,offset(%rsp) - lea (%r9,%rax,4),%rdx - lea (%rdi,%r11,1),%rax - mov %rdx,offset(%rsp) - lea (%r9,%rax,4),%rdx - lea (%rdi,%rbx,1),%rax - mov %rdx,offset(%rsp) - lea (%r9,%rax,4),%rdx - lea (%rdi,%rbp,1),%rax /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_SKYLAKEX.o (objdump) @@ -2,803 +2,395 @@ /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24a00000 0048c1fe 044889bc .H..$....H...H.. - 0020 24900000 00488954 24684889 4c24584c $....H.T$hH.L$XL - 0030 89442438 4c898c24 80000000 4889b424 .D$8L..$....H..$ - 0040 c0010000 4885f60f 8ee71500 004c89c3 ....H........L.. - 0050 480fafd9 4889c84d 89c1488d 0c19488d H...H..M..H...H. - 0060 34084889 da488d1c 304c8d04 1848895c 4.H..H..0L...H.\ - 0070 2498498d 1c004c8d 14034d8d 1c024889 $.I...L...M...H. - 0080 5c249049 8d1c0348 8d2c034c 8d640500 \$.I...H.,.L.d.. - 0090 4d8d2c04 4d8d7405 004d8d3c 06498d3c M.,.M.t..M.<.I.< - 00a0 0748897c 2488488b bc249000 000048c1 .H.|$.H..$....H. - 00b0 e00648c1 ff044889 bc248800 0000488b ..H...H..$....H. - 00c0 bc249000 00004889 44246083 e70f4889 .$....H.D$`...H. - 00d0 7c245048 c1e70648 89bc24b8 01000048 |$PH...H..$....H - 00e0 8bbc24c0 01000048 8b842480 00000048 ..$....H..$....H - 00f0 c1e70448 01c74889 bc249800 00004889 ...H..H..$....H. - 0100 c7480faf 4424584c 01c84c8b 4c24684d .H..D$XL..L.L$hM - 0110 8d0c8148 89f848ff c0480faf 4424584c ...H..H..H..D$XL - 0120 898c24b8 0000004c 8b4c2468 48034424 ..$....L.L$hH.D$ - 0130 384d8d0c 814889f8 4883c002 480faf44 8M...H..H...H..D - 0140 24584c89 8c24c800 00004c8b 4c246848 $XL..$....L.L$hH - 0150 03442438 4d8d0c81 4889f848 83c00348 .D$8M...H..H...H - 0160 0faf4424 584c898c 24d80000 004c8b4c ..D$XL..$....L.L - 0170 24684803 4424384d 8d0c8148 89f84883 $hH.D$8M...H..H. - 0180 c004480f af442458 4c898c24 a8000000 ..H..D$XL..$.... - 0190 4c8b4c24 68480344 24384d8d 0c814889 L.L$hH.D$8M...H. - 01a0 f84883c0 05480faf 4424584c 898c24f0 .H...H..D$XL..$. - 01b0 00000048 03442438 4c8b4c24 684d8d0c ...H.D$8L.L$hM.. - 01c0 814889f8 4883c006 480faf44 24584c89 .H..H...H..D$XL. - 01d0 8c240001 00004c8b 4c246848 03442438 .$....L.L$hH.D$8 - 01e0 4d8d0c81 4889f848 83c00748 0faf4424 M...H..H...H..D$ - 01f0 584c898c 24100100 004c8b4c 24684803 XL..$....L.L$hH. - 0200 4424384d 8d0c8148 89f84883 c008480f D$8M...H..H...H. - 0210 af442458 4c898c24 20010000 4c8b4c24 .D$XL..$ ...L.L$ - 0220 68480344 24384d8d 0c814889 f84883c0 hH.D$8M...H..H.. - 0230 09480faf 4424584c 898c2430 0100004c .H..D$XL..$0...L - 0240 8b4c2468 48034424 384d8d0c 814889f8 .L$hH.D$8M...H.. - 0250 4883c00a 480faf44 24584c89 8c244001 H...H..D$XL..$@. - 0260 00004c8b 4c246848 03442438 4d8d0c81 ..L.L$hH.D$8M... - 0270 4889f848 83c00b48 0faf4424 584c898c H..H...H..D$XL.. - 0280 24500100 004c8b4c 24684803 4424384d $P...L.L$hH.D$8M - 0290 8d0c8148 89f84883 c00c480f af442458 ...H..H...H..D$X - 02a0 4c898c24 60010000 4c8b4c24 68480344 L..$`...L.L$hH.D - 02b0 24384d8d 0c814889 f84883c0 0d480faf $8M...H..H...H.. - 02c0 4424584c 898c2470 01000048 03442438 D$XL..$p...H.D$8 - 02d0 4c8b4c24 684d8d0c 814889f8 4883c00e L.L$hM...H..H... - 02e0 480faf44 24584c89 8c248001 00004c8b H..D$XL..$....L. - 02f0 4c246848 03442438 4d8d0c81 4889f848 L$hH.D$8M...H..H - 0300 83c00f48 0faf4424 584c898c 24900100 ...H..D$XL..$... - 0310 004c8b4c 24684803 4424384d 8d0c814c .L.L$hH.D$8M...L - 0320 898c24a0 01000048 89f84c8b 4c246848 ..$....H..L.L$hH - 0330 01d0498d 1481488d 040f498d 04814889 ..I...H...I...H. - 0340 8424e000 0000488d 04374889 9424d000 .$....H..7H..$.. - 0350 0000498d 1481488b 44249848 899424b0 ..I...H.D$.H..$. - 0360 00000048 01f8498d 14814a8d 04074889 ...H..I...J...H. - 0370 9424c000 0000498d 1481488b 44249048 .$....I...H.D$.H - 0380 899424e8 00000048 01f8498d 14814a8d ..$....H..I...J. - 0390 04174889 9424f800 0000498d 14814a8d ..H..$....I...J. - 03a0 041f4889 94240801 0000498d 1481488d ..H..$....I...H. - 03b0 041f4889 94241801 0000498d 1481488d ..H..$....I...H. - 03c0 042f4889 94242801 0000498d 14814a8d ./H..$(...I...J. - 03d0 04274889 94243801 0000498d 14814a8d .'H..$8...I...J. - 03e0 042f4889 94244801 0000498d 14814a8d ./H..$H...I...J. - 03f0 0437488b 4c248848 89942458 01000049 .7H.L$.H..$X...I - 0400 8d14814a 8d043f48 89942468 01000049 ...J..?H..$h...I - 0410 8d148148 89f84801 c848034c 24584889 ...H..H..H.L$XH. - 0420 94247801 0000498d 14814889 c84801f8 .$x...I...H..H.. - 0430 498d0c81 48898c24 98010000 48899424 I...H..$....H..$ - 0440 88010000 488b9c24 90000000 488b7424 ....H..$....H.t$ - 0450 384889d8 4883e0f0 4801f048 89442448 8H..H...H..H.D$H - 0460 488b8424 88000000 48897c24 d84889c1 H..$....H.|$.H.. - 0470 48c1e004 48c1e10a 4801f048 898424b0 H...H...H..H..$. - 0480 01000048 89d883e0 0e488984 24c80100 ...H.....H..$... - 0490 004889d8 83e00c83 e3084889 8c24a801 .H........H..$.. - 04a0 000048c7 44247800 00000048 c7442470 ..H.D$x....H.D$p - 04b0 00000000 48898424 d0010000 48899c24 ....H..$....H..$ - 04c0 d8010000 c5fa100d 00000000 e9780100 .............x.. - 04d0 000f1f80 00000000 488b4424 70488bbc ........H.D$pH.. - 04e0 24d00000 00488b8c 24c00000 004801c7 $....H..$....H.. - 04f0 48897c24 b8488bbc 24e00000 004801c1 H.|$.H..$....H.. - 0500 4801c748 897c24c0 488bbc24 b0000000 H..H.|$.H..$.... - 0510 48894c24 d04801c7 48897c24 c8488bbc H.L$.H..H.|$.H.. - 0520 24e80000 00488b8c 24f80000 004801c7 $....H..$....H.. - 0530 48897c24 e0488bbc 24080100 004801c1 H.|$.H..$....H.. - 0540 4801c748 894c24e8 48897c24 f0488b8c H..H.L$.H.|$.H.. - 0550 24180100 00488bb4 24280100 00488bbc $....H..$(...H.. - 0560 24380100 00488b9c 24480100 004801c1 $8...H..$H...H.. - 0570 4801c648 01c74801 c348894c 24f84889 H..H..H..H.L$.H. - 0580 34244889 7c240848 895c2410 488b8c24 4$H.|$.H.\$.H..$ - 0590 58010000 488bb424 68010000 488bbc24 X...H..$h...H..$ - 05a0 78010000 488b9c24 88010000 4801c148 x...H..$....H..H - 05b0 01c64801 c74801c3 48038424 98010000 ..H..H..H..$.... - 05c0 48894c24 18488974 24204889 7c242848 H.L$.H.t$ H.|$(H - 05d0 895c2430 48894424 404883bc 24880000 .\$0H.D$@H..$... - 05e0 0000488b 4424380f 8f810100 0048837c ..H.D$8......H.| - 05f0 24500074 2b483944 24d80f8c 5e250000 $P.t+H9D$...^%.. - 0600 0f8eea18 0000488b 8424b801 00004801 ......H..$....H. - 0610 84241802 0000662e 0f1f8400 00000000 .$....f......... - 0620 48834424 d810488b 74246048 83442470 H.D$..H.t$`H.D$p - 0630 40480174 2478488b 4424d848 3b842498 @H.t$xH.D$.H;.$. - 0640 0000000f 84cc0f00 00488b74 24384839 .........H.t$8H9 - 0650 7424d80f 8d7ffeff ff488b44 2478488b t$.......H.D$xH. - 0660 9c24b800 0000488b bc24c800 0000488b .$....H..$....H. - 0670 b424d800 00004801 c34801c7 4801c648 .$....H..H..H..H - 0680 895c24b8 48897c24 c0488974 24c8488b .\$.H.|$.H.t$.H. - 0690 9c24a800 0000488b 8c24f000 0000488b .$....H..$....H. - 06a0 b4240001 0000488b bc241001 00004801 .$....H..$....H. - 06b0 c34801c1 4801c648 01c74889 5c24d048 .H..H..H..H.\$.H - 06c0 894c24e0 48897424 e848897c 24f0488b .L$.H.t$.H.|$.H. - 06d0 9c242001 0000488b 8c243001 0000488b .$ ...H..$0...H. - 06e0 b4244001 0000488b bc245001 00004801 .$@...H..$P...H. - 06f0 c34801c1 4801c648 01c74889 5c24f848 .H..H..H..H.\$.H - 0700 890c2448 89742408 48897c24 10488b9c ..$H.t$.H.|$.H.. - 0710 24600100 00488b8c 24700100 00488bb4 $`...H..$p...H.. - 0720 24800100 00488bbc 24900100 004801c3 $....H..$....H.. - 0730 4801c148 01c64801 c7480384 24a00100 H..H..H..H..$... - 0740 0048895c 24184889 4c242048 89742428 .H.\$.H.L$ H.t$( - 0750 48897c24 30488944 24404883 bc248800 H.|$0H.D$@H..$.. - 0760 00000048 8b442438 0f8e7ffe ffff488b ...H.D$8......H. - 0770 84241802 0000488d 90000400 00488b44 .$....H......H.D - 0780 24384889 4424b0eb 780f1f80 00000000 $8H.D$..x....... - 0790 488b4424 60480144 24b84801 4424c048 H.D$`H.D$.H.D$.H - 07a0 014424c8 48014424 d0480144 24e04801 .D$.H.D$.H.D$.H. - 07b0 4424e848 014424f0 48014424 f8480104 D$.H.D$.H.D$.H.. - 07c0 24480144 24084801 44241048 01442418 $H.D$.H.D$.H.D$. - 07d0 48014424 20480144 24284801 44243048 H.D$ H.D$(H.D$0H - 07e0 01442440 48834424 b0104881 c2000400 .D$@H.D$..H..... - 07f0 00488b44 24b0483b 4424480f 84f70d00 .H.D$.H;D$H..... - 0800 00488b4c 24b0488d 8200fcff ff48394c .H.L$.H......H9L - 0810 24d80f8c 000c0000 0f8f72ff ffffc782 $.........r..... - 0820 04fcffff 00000000 c78208fc ffff0000 ................ - 0830 0000c782 0cfcffff 00000000 c78210fc ................ - 0840 ffff0000 0000c782 14fcffff 00000000 ................ - 0850 c78218fc ffff0000 0000c782 1cfcffff ................ - 0860 00000000 c78220fc ffff0000 0000c782 ...... ......... - 0870 24fcffff 00000000 c78228fc ffff0000 $.........(..... - 0880 0000c782 2cfcffff 00000000 c78230fc ....,.........0. - 0890 ffff0000 0000c782 34fcffff 00000000 ........4....... - 08a0 c78238fc ffff0000 0000c782 3cfcffff ..8.........<... - 08b0 00000000 488b4424 b8c5fa11 8a00fcff ....H.D$........ - 08c0 ffc5fa10 4004c782 48fcffff 00000000 ....@...H....... - 08d0 c5fa1182 40fcffff c7824cfc ffff0000 ....@.....L..... - 08e0 0000c782 50fcffff 00000000 c78254fc ....P.........T. - 08f0 ffff0000 0000c782 58fcffff 00000000 ........X....... - 0900 c7825cfc ffff0000 0000c782 60fcffff ..\.........`... - 0910 00000000 c78264fc ffff0000 0000c782 ......d......... - 0920 68fcffff 00000000 c7826cfc ffff0000 h.........l..... - 0930 0000c782 70fcffff 00000000 c78274fc ....p.........t. - 0940 ffff0000 0000c5fa 118a44fc ffffc782 ..........D..... - 0950 78fcffff 00000000 c7827cfc ffff0000 x.........|..... - 0960 0000488b 5c24c048 8b7424c8 c5fa1040 ..H.\$.H.t$....@ - 0970 084883c3 40c5fa11 8280fcff ffc5fa10 .H..@........... - 0980 43c8c782 8cfcffff 00000000 c78290fc C............... - 0990 ffff0000 0000c782 94fcffff 00000000 ................ - 09a0 c78298fc ffff0000 0000c782 9cfcffff ................ - 09b0 00000000 c782a0fc ffff0000 0000c782 ................ - 09c0 a4fcffff 00000000 c782a8fc ffff0000 ................ - 09d0 0000c782 acfcffff 00000000 c782b0fc ................ - 09e0 ffff0000 0000c782 b4fcffff 00000000 ................ - 09f0 c782b8fc ffff0000 0000c782 bcfcffff ................ - 0a00 00000000 c5fa1182 84fcffff c5fa118a ................ - 0a10 88fcffff c5fa1040 0c4883c6 40c5fa11 .......@.H..@... - 0a20 82c0fcff ffc5fa10 43ccc5fa 1182c4fc ........C....... - 0a30 ffffc5fa 1046ccc7 82d0fcff ff000000 .....F.......... - 0a40 00c5fa11 82c8fcff ffc782d4 fcffff00 ................ - 0a50 000000c7 82d8fcff ff000000 00c782dc ................ - 0a60 fcffff00 000000c5 fa118acc fcffffc7 ................ - 0a70 82e0fcff ff000000 00c782e4 fcffff00 ................ - 0a80 000000c7 82e8fcff ff000000 00c782ec ................ - 0a90 fcffff00 000000c7 82f0fcff ff000000 ................ - 0aa0 00c782f4 fcffff00 000000c7 82f8fcff ................ - 0ab0 ff000000 00c782fc fcffff00 00000048 ...............H - 0ac0 8b7c24d0 c5fa1040 104883c7 40c5fa11 .|$....@.H..@... - 0ad0 8200fdff ffc5fa10 43d0c5fa 118204fd ........C....... - 0ae0 ffffc5fa 1046d0c5 fa118208 fdffffc5 .....F.......... - 0af0 fa1047d0 c78214fd ffff0000 0000c782 ..G............. - 0b00 18fdffff 00000000 c7821cfd ffff0000 ................ - 0b10 0000c782 20fdffff 00000000 c78224fd .... .........$. - 0b20 ffff0000 0000c782 28fdffff 00000000 ........(....... - 0b30 c7822cfd ffff0000 0000c782 30fdffff ..,.........0... - 0b40 00000000 c78234fd ffff0000 0000c782 ......4......... - 0b50 38fdffff 00000000 c7823cfd ffff0000 8.........<..... - 0b60 0000c5fa 11820cfd ffffc5fa 118a10fd ................ - 0b70 ffffc5fa 104014c5 fa118240 fdffffc5 .....@.....@.... - 0b80 fa1043d4 c5fa1182 44fdffff c5fa1046 ..C.....D......F - 0b90 d4488b4c 24e0c5fa 118248fd ffffc5fa .H.L$.....H..... - 0ba0 1047d44c 8b7424e8 c5fa1182 4cfdffff .G.L.t$.....L... - 0bb0 c5fa1041 14c78258 fdffff00 000000c7 ...A...X........ - 0bc0 825cfdff ff000000 00c78260 fdffff00 .\.........`.... - 0bd0 000000c7 8264fdff ff000000 00c78268 .....d.........h - 0be0 fdffff00 000000c7 826cfdff ff000000 .........l...... - 0bf0 00c78270 fdffff00 000000c7 8274fdff ...p.........t.. - 0c00 ff000000 00c78278 fdffff00 000000c7 .......x........ - 0c10 827cfdff ff000000 00c5fa11 8250fdff .|...........P.. /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39000000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_ilnucopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 f1310000 00420e10 8f02420e .....1...B....B. + 0020 00000000 7a180000 00420e10 8f02420e ....z....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 c91e0a0e ..A.8..G........ + 0040 8606410e 38830747 0ec00203 e9130a0e ..A.8..G........ 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. 0060 440e084a 0b000000 D..J.... /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_COOPERLAKE.o (disasm) @@ -15,773 +15,543 @@ mov %rsi,offset(%rsp) sar $something,%rsi mov %rdi,offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rcx,(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) mov %r8,-offset(%rsp) mov %r9,-offset(%rsp) mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov offset(%rsp),%r12 test %rsi,%rsi jle - mov %r8,%r10 - imul %rcx,%r10 - mov %r8,%rdi + mov %rcx,%rsi mov %rcx,%rax - lea (%rcx,%r10,1),%r9 - lea (%r9,%rcx,1),%r8 - lea (%rcx,%r8,1),%rbx - lea (%rbx,%rcx,1),%rsi - mov %rbx,-offset(%rsp) - lea (%rcx,%rsi,1),%rbx - lea (%rbx,%rcx,1),%rdx - lea (%rcx,%rdx,1),%r11 - mov %rbx,-offset(%rsp) - lea (%rcx,%r11,1),%rbx - lea (%rcx,%rbx,1),%rbp - lea (%rcx,%rbp,1),%r12 - lea (%rcx,%r12,1),%r13 - lea (%rcx,%r13,1),%r14 - lea (%rcx,%r14,1),%rcx - mov %rcx,-offset(%rsp) - mov -offset(%rsp),%rcx - add %rax,%rcx - mov %rcx,-offset(%rsp) - mov offset(%rsp),%rcx - sar $something,%rcx - mov %rcx,offset(%rsp) - lea offset(,%rax,4),%rcx - mov %rcx,offset(%rsp) - mov %rax,%rcx - mov offset(%rsp),%rax - shl $something,%rcx - and $something,%eax - mov %rax,-offset(%rsp) + imul %r8,%rsi + mov %rdi,%r13 shl $something,%rax mov %rax,offset(%rsp) - mov offset(%rsp),%rax - mov %rcx,-offset(%rsp) + mov %r13,%rax + mov %r9,%r14 + and $something,%eax + lea (%rsi,%rcx,2),%rdi + lea offset(,%rcx,8),%r15 + mov %rax,-offset(%rsp) + lea (%r14,%rsi,1),%rax + lea (%rdi,%rcx,1),%r8 + kmovq %r15,%k2 + lea (%rdx,%rax,4),%r15 + mov %r14,%rax + lea (%r8,%rcx,1),%r9 + imul %rcx,%rax + lea (%rcx,%r9,1),%r10 + lea (%rcx,%r10,1),%r11 + mov %rcx,%rdx + mov %rcx,%rbp + mov offset(%rsp),%rcx + add -offset(%rsp),%rax + lea (%rcx,%rax,4),%r14 mov -offset(%rsp),%rcx - shl $something,%rax - add %rcx,%rax + mov offset(%rsp),%rax + sub %rsi,%rdi + lea (%rcx,%rax,8),%rax mov %rax,offset(%rsp) - mov (%rsp),%rax - imul %rcx,%rax - add %rdi,%rax - mov -offset(%rsp),%rdi - lea (%rdi,%rax,4),%rdi + mov %rdx,%rax + neg %rax + lea offset(,%rax,4),%rdx mov %rcx,%rax - mov (%rsp),%rcx - inc %rax - imul %rcx,%rax - mov %rdi,offset(%rsp) - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - add -offset(%rsp),%rax - mov -offset(%rsp),%rdi - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - add -offset(%rsp),%rax - mov -offset(%rsp),%rdi - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax + imul %rdx,%rax + mov %rdx,offset(%rsp) + inc %rcx + neg %rdx + imul %rdx,%rcx + lea offset(,%rdi,4),%rdi mov %rdi,offset(%rsp) - add $something,%rax /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_COOPERLAKE.o (objdump) @@ -2,696 +2,414 @@ /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ec700100 AWAVAUATUSH..p.. - 0010 00488974 242048c1 fe044889 7c241048 .H.t$ H...H.|$.H - 0020 895424e0 48890c24 4c894424 a84c894c .T$.H..$L.D$.L.L - 0030 24c84889 b4245001 00004c8b bc24a801 $.H..$P...L..$.. - 0040 00004885 f60f8e56 1c00004d 89c24c0f ..H....V...M..L. - 0050 afd14c89 c74889c8 4e8d0c11 4d8d0409 ..L..H..N...M... - 0060 4a8d1c01 488d340b 48895c24 98488d1c J...H.4.H.\$.H.. - 0070 31488d14 0b4c8d1c 1148895c 24904a8d 1H...L...H.\$.J. - 0080 1c19488d 2c194c8d 24294e8d 2c214e8d ..H.,.L.$)N.,!N. - 0090 34294a8d 0c314889 4c248848 8b4c2488 4)J..1H.L$.H.L$. - 00a0 4801c148 894c24a0 488b4c24 1048c1f9 H..H.L$.H.L$.H.. - 00b0 0448894c 2408488d 0c850000 00004889 .H.L$.H.......H. - 00c0 8c243001 00004889 c1488b44 241048c1 .$0...H..H.D$.H. - 00d0 e10683e0 0f488944 24d848c1 e0064889 .....H.D$.H...H. - 00e0 84244801 0000488b 84245001 00004889 .$H...H..$P...H. - 00f0 4c24f848 8b4c24c8 48c1e004 4801c848 L$.H.L$.H...H..H - 0100 89442418 488b0424 480fafc1 4801f848 .D$.H..$H...H..H - 0110 8b7c24e0 488d3c87 4889c848 8b0c2448 .|$.H.<.H..H..$H - 0120 ffc0480f afc14889 7c243848 8b7c24e0 ..H...H.|$8H.|$. - 0130 48034424 a8488d3c 87488b44 24c84889 H.D$.H.<.H.D$.H. - 0140 7c244848 83c00248 0fafc148 8b7c24e0 |$HH...H...H.|$. - 0150 48034424 a8488d3c 87488b44 24c84889 H.D$.H.<.H.D$.H. - 0160 7c245848 83c00348 0fafc148 8b7c24e0 |$XH...H...H.|$. - 0170 48034424 a8488d3c 87488b44 24c84889 H.D$.H.<.H.D$.H. - 0180 7c246848 83c00448 0fafc148 034424a8 |$hH...H...H.D$. - 0190 488b7c24 e0488d3c 87488b44 24c84889 H.|$.H.<.H.D$.H. - 01a0 7c247848 83c00548 0fafc148 8b7c24e0 |$xH...H...H.|$. - 01b0 48034424 a8488d3c 87488b44 24c84889 H.D$.H.<.H.D$.H. - 01c0 bc248800 00004883 c006480f afc1488b .$....H...H...H. - 01d0 7c24e048 034424a8 488d3c87 488b4424 |$.H.D$.H.<.H.D$ - 01e0 c84889bc 24980000 004883c0 07480faf .H..$....H...H.. - 01f0 c1488b7c 24e04803 4424a848 8d3c8748 .H.|$.H.D$.H.<.H - 0200 8b4424c8 4889bc24 a8000000 4883c008 .D$.H..$....H... - 0210 480fafc1 488b7c24 e0480344 24a8488d H...H.|$.H.D$.H. - 0220 3c87488b 4424c848 89bc24b8 00000048 <.H.D$.H..$....H - 0230 83c00948 0fafc148 8b7c24e0 48034424 ...H...H.|$.H.D$ - 0240 a8488d3c 87488b44 24c84889 bc24c800 .H.<.H.D$.H..$.. - 0250 00004883 c00a480f afc1488b 7c24e048 ..H...H...H.|$.H - 0260 034424a8 488d3c87 488b4424 c84889bc .D$.H.<.H.D$.H.. - 0270 24d80000 004883c0 0b480faf c1488b7c $....H...H...H.| - 0280 24e04803 4424a848 8d3c8748 8b4424c8 $.H.D$.H.<.H.D$. - 0290 4889bc24 e8000000 4883c00c 480fafc1 H..$....H...H... - 02a0 48034424 a8488b7c 24e0488d 3c87488b H.D$.H.|$.H.<.H. - 02b0 4424c848 89bc24f8 00000048 83c00d48 D$.H..$....H...H - 02c0 0fafc148 8b7c24e0 48034424 a8488d3c ...H.|$.H.D$.H.< - 02d0 87488b44 24c84889 bc240801 00004883 .H.D$.H..$....H. - 02e0 c00e480f afc1488b 7c24e048 034424a8 ..H...H.|$.H.D$. - 02f0 488d3c87 488b4424 c84889bc 24180100 H.<.H.D$.H..$... - 0300 004883c0 0f480faf c1488b4c 24e04803 .H...H...H.L$.H. - 0310 4424a848 8d3c8148 8b4424c8 4889bc24 D$.H.<.H.D$.H..$ - 0320 28010000 488b7c24 984901c2 4901c048 (...H.|$.I..I..H - 0330 01c74801 c64e8d14 914901c1 4e8d0481 ..H..N...I..N... - 0340 4c895424 304c8944 24504c8d 14b14c8d L.T$0L.D$PL...L. - 0350 04b94e8d 0c894889 c74889c8 488b4c24 ..N...H..H..H.L$ - 0360 904901fb 4801f948 01fa4801 fb4e8d1c .I..H..H..H..N.. - 0370 984c8954 24704c8d 14884801 fd4c8994 .L.T$pL...H..L.. - 0380 24800000 004c899c 24a00000 004c8d14 $....L..$....L.. - 0390 904c8d1c 98488b54 24884c89 9c24b000 .L...H.T$.L..$.. - 03a0 00004901 fc4c8d1c a84c899c 24c00000 ..I..L...L..$... - 03b0 004901fd 4e8d1ca0 4901fe48 01fa488d .I..N...I..H..H. - 03c0 14904c89 9c24d000 00004e8d 34b04e8d ..L..$....N.4.N. - 03d0 1ca84889 94240001 00004c89 4c24404c ..H..$....L.L$@L - 03e0 89442460 4c899424 90000000 4c899c24 .D$`L..$....L..$ - 03f0 e0000000 4c89b424 f0000000 488b5c24 ....L..$....H.\$ - 0400 a04889c6 4889d848 01f8488d 1486488b .H..H..H..H...H. - 0410 04244889 94241001 00004801 d84801f8 .$H..$....H..H.. - 0420 488d1486 488b7424 104889fb 4889f048 H...H.t$.H..H..H - 0430 8b7c24a8 4883e0f0 4801f848 894424d0 .|$.H...H..H.D$. - 0440 488b4424 08488994 24200100 004889c2 H.D$.H..$ ...H.. - 0450 48c1e004 4801f848 89842438 01000048 H...H..H..$8...H - 0460 89f083e0 0e488984 24580100 004889f0 .....H..$X...H.. - 0470 48c1e20a 83e00c83 e6084889 94244001 H.........H..$@. - 0480 00004889 5c249048 c74424f0 00000000 ..H.\$.H.D$..... - 0490 48c74424 e8000000 00488984 24600100 H.D$.....H..$`.. - 04a0 004889b4 24680100 00e91001 00006690 .H..$h........f. - 04b0 488b4424 e8488b8c 24e00000 00488b74 H.D$.H..$....H.t - 04c0 24304801 c148894c 2498488b 8c24f000 $0H..H.L$.H..$.. - 04d0 0000488b 7c244048 01c14889 4c24a048 ..H.|$@H..H.L$.H - 04e0 8b8c2400 0100004c 8b442450 4801c148 ..$....L.D$PH..H - 04f0 894c24b0 4c8b4c24 604c8b54 24704c8b .L$.L.L$`L.T$pL. - 0500 9c248000 0000488b 9c249000 0000488b .$....H..$....H. - 0510 ac24a000 00004c8b a424b000 00004c8b .$....L..$....L. - 0520 ac24c000 00004c8b b424d000 0000488b .$....L..$....H. - 0530 8c241001 00004801 c64801c1 4801c749 .$....H..H..H..I - 0540 01c04901 c14901c2 4901c348 01c34801 ..I..I..I..H..H. - 0550 c54901c4 4901c549 01c64803 84242001 .I..I..I..H..$ . - 0560 00004883 7c240800 48894424 c048894c ..H.|$..H.D$.H.L - 0570 24b8488b 4424a80f 8f1e0100 0048837c $.H.D$.......H.| - 0580 24d80074 13483944 24900f8d e00e0000 $..t.H9D$....... - 0590 4c03bc24 48010000 48834424 9010488b L..$H...H.D$..H. - 05a0 7c24f848 834424e8 4048017c 24f0488b |$.H.D$.@H.|$.H. - 05b0 44249048 3b442418 0f84ca16 0000488b D$.H;D$.......H. - 05c0 5c24a848 395c2490 0f8de2fe ffff488b \$.H9\$.......H. - 05d0 4424f048 8b8c24e8 00000048 8b742438 D$.H..$....H.t$8 - 05e0 4801c148 894c2498 488b8c24 f8000000 H..H.L$.H..$.... - 05f0 488b7c24 484801c1 48894c24 a0488b8c H.|$HH..H.L$.H.. - 0600 24080100 004c8b44 24584801 c148894c $....L.D$XH..H.L - 0610 24b04c8b 4c24684c 8b542478 4c8b9c24 $.L.L$hL.T$xL..$ - 0620 88000000 488b9c24 98000000 488bac24 ....H..$....H..$ - 0630 a8000000 4c8ba424 b8000000 4c8bac24 ....L..$....L..$ - 0640 c8000000 4c8bb424 d8000000 488b8c24 ....L..$....H..$ - 0650 18010000 4801c648 01c14801 c74901c0 ....H..H..H..I.. - 0660 4901c149 01c24901 c34801c3 4801c549 I..I..I..H..H..I - 0670 01c44901 c54901c6 48038424 28010000 ..I..I..H..$(... - 0680 48837c24 08004889 4424c048 894c24b8 H.|$..H.D$.H.L$. - 0690 488b4424 a80f8ee2 feffff48 8b5424a8 H.D$.......H.T$. - 06a0 4c89bc24 a8010000 48895424 88498d87 L..$....H.T$.I.. - 06b0 00040000 eb70662e 0f1f8400 00000000 .....pf......... - 06c0 48834424 98404883 4424a040 48834424 H.D$.@H.D$.@H.D$ - 06d0 b0404883 4424b840 48834424 c0404883 .@H.D$.@H.D$.@H. - 06e0 c6404883 c7404983 c0404983 c1404983 .@H..@I..@I..@I. - 06f0 c2404983 c3404883 c3404883 c5404983 .@I..@H..@H..@I. - 0700 c4404983 c5404983 c6404883 44248810 .@I..@I..@H.D$.. - 0710 48050004 0000488b 4c248848 3b4c24d0 H.....H.L$.H;L$. - 0720 0f842a0d 00004c8b 7c248848 8d9000fc ..*...L.|$.H.... - 0730 ffff4c39 7c24907c 87c5fa10 060f8ff5 ..L9|$.|........ - 0740 0b0000c5 fa118000 fcffffc5 fa104604 ..............F. - 0750 4883c740 c5fa1180 04fcffff c5fa1046 H..@...........F - 0760 084983c0 40c5fa11 8008fcff ffc5fa10 .I..@........... - 0770 460c4983 c140c5fa 11800cfc ffffc5fa F.I..@.......... - 0780 10461049 83c240c5 fa118010 fcffffc5 .F.I..@......... - 0790 fa104614 4983c340 c5fa1180 14fcffff ..F.I..@........ - 07a0 c5fa1046 184883c3 40c5fa11 8018fcff ...F.H..@....... - 07b0 ffc5fa10 461c4883 c540c5fa 11801cfc ....F.H..@...... - 07c0 ffffc5fa 10462049 83c440c5 fa118020 .....F I..@.... - 07d0 fcffffc5 fa104624 4983c540 c5fa1180 ......F$I..@.... - 07e0 24fcffff c5fa1046 284983c6 40c5fa11 $......F(I..@... - 07f0 8028fcff ffc5fa10 462c4883 c640c5fa .(......F,H..@.. - 0800 11802cfc ffffc5fa 1046f0c5 fa118030 ..,......F.....0 - 0810 fcffffc5 fa1046f4 c5fa1180 34fcffff ......F.....4... - 0820 c5fa1046 f8c5fa11 8038fcff ffc5fa10 ...F.....8...... - 0830 46fcc780 40fcffff 00000000 c5fa1180 F...@........... - 0840 3cfcffff c5fa1047 c4c5fa11 8044fcff <......G.....D.. - 0850 ffc5fa10 47c8c5fa 118048fc ffffc5fa ....G.....H..... - 0860 1047ccc5 fa11804c fcffffc5 fa1047d0 .G.....L......G. - 0870 c5fa1180 50fcffff c5fa1047 d4c5fa11 ....P......G.... - 0880 8054fcff ffc5fa10 47d8c5fa 118058fc .T......G.....X. - 0890 ffffc5fa 1047dcc5 fa11805c fcffffc5 .....G.....\.... - 08a0 fa1047e0 c5fa1180 60fcffff c5fa1047 ..G.....`......G - 08b0 e4c5fa11 8064fcff ffc5fa10 47e8c5fa .....d......G... - 08c0 118068fc ffffc5fa 1047ecc5 fa11806c ..h......G.....l - 08d0 fcffffc5 fa1047f0 c5fa1180 70fcffff ......G.....p... - 08e0 c5fa1047 f4c5fa11 8074fcff ffc5fa10 ...G.....t...... - 08f0 47f8c5fa 118078fc ffffc5fa 1047fcc7 G.....x......G.. - 0900 8080fcff ff000000 00c78084 fcffff00 ................ - 0910 000000c5 fa11807c fcffffc4 c17a1040 .......|.....z.@ - 0920 c8c5fa11 8088fcff ffc4c17a 1040ccc5 ...........z.@.. - 0930 fa11808c fcffffc4 c17a1040 d0c5fa11 .........z.@.... - 0940 8090fcff ffc4c17a 1040d4c5 fa118094 .......z.@...... - 0950 fcffffc4 c17a1040 d8c5fa11 8098fcff .....z.@........ - 0960 ffc4c17a 1040dcc5 fa11809c fcffffc4 ...z.@.......... - 0970 c17a1040 e0c5fa11 80a0fcff ffc4c17a .z.@...........z - 0980 1040e4c5 fa1180a4 fcffffc4 c17a1040 .@...........z.@ - 0990 e8c5fa11 80a8fcff ffc4c17a 1040ecc5 ...........z.@.. - 09a0 fa1180ac fcffffc4 c17a1040 f0c5fa11 .........z.@.... - 09b0 80b0fcff ffc4c17a 1040f4c5 fa1180b4 .......z.@...... - 09c0 fcffffc4 c17a1040 f8c5fa11 80b8fcff .....z.@........ - 09d0 ffc4c17a 1040fcc7 80c0fcff ff000000 ...z.@.......... - 09e0 00c780c4 fcffff00 000000c7 80c8fcff ................ - 09f0 ff000000 00c5fa11 80bcfcff ffc4c17a ...............z - 0a00 1041ccc5 fa1180cc fcffffc4 c17a1041 .A...........z.A - 0a10 d0c5fa11 80d0fcff ffc4c17a 1041d4c5 ...........z.A.. - 0a20 fa1180d4 fcffffc4 c17a1041 d8c5fa11 .........z.A.... - 0a30 80d8fcff ffc4c17a 1041dcc5 fa1180dc .......z.A...... - 0a40 fcffffc4 c17a1041 e0c5fa11 80e0fcff .....z.A........ - 0a50 ffc4c17a 1041e4c5 fa1180e4 fcffffc4 ...z.A.......... - 0a60 c17a1041 e8c5fa11 80e8fcff ffc4c17a .z.A...........z - 0a70 1041ecc5 fa1180ec fcffffc4 c17a1041 .A...........z.A - 0a80 f0c5fa11 80f0fcff ffc4c17a 1041f4c5 ...........z.A.. - 0a90 fa1180f4 fcffffc4 c17a1041 f8c5fa11 .........z.A.... - 0aa0 80f8fcff ffc4c17a 1041fcc7 8000fdff .......z.A...... - 0ab0 ff000000 00c78004 fdffff00 000000c7 ................ - 0ac0 8008fdff ff000000 00c7800c fdffff00 ................ - 0ad0 000000c5 fa1180fc fcffffc4 c17a1042 .............z.B - 0ae0 d0c5fa11 8010fdff ffc4c17a 1042d4c5 ...........z.B.. - 0af0 fa118014 fdffffc4 c17a1042 d8c5fa11 .........z.B.... - 0b00 8018fdff ffc4c17a 1042dcc5 fa11801c .......z.B...... - 0b10 fdffffc4 c17a1042 e0c5fa11 8020fdff .....z.B..... .. - 0b20 ffc4c17a 1042e4c5 fa118024 fdffffc4 ...z.B.....$.... - 0b30 c17a1042 e8c5fa11 8028fdff ffc4c17a .z.B.....(.....z - 0b40 1042ecc5 fa11802c fdffffc4 c17a1042 .B.....,.....z.B - 0b50 f0c5fa11 8030fdff ffc4c17a 1042f4c5 .....0.....z.B.. - 0b60 fa118034 fdffffc4 c17a1042 f8c5fa11 ...4.....z.B.... - 0b70 8038fdff ffc4c17a 1042fcc7 8040fdff .8.....z.B...@.. - 0b80 ff000000 00c78044 fdffff00 000000c7 .......D........ - 0b90 8048fdff ff000000 00c7804c fdffff00 .H.........L.... - 0ba0 000000c7 8050fdff ff000000 00c5fa11 .....P.......... - 0bb0 803cfdff ffc4c17a 1043d4c5 fa118054 .<.....z.C.....T - 0bc0 fdffffc4 c17a1043 d8c5fa11 8058fdff .....z.C.....X.. - 0bd0 ffc4c17a 1043dcc5 fa11805c fdffffc4 ...z.C.....\.... - 0be0 c17a1043 e0c5fa11 8060fdff ffc4c17a .z.C.....`.....z - 0bf0 1043e4c5 fa118064 fdffffc4 c17a1043 .C.....d.....z.C - 0c00 e8c5fa11 8068fdff ffc4c17a 1043ecc5 .....h.....z.C.. - 0c10 fa11806c fdffffc4 c17a1043 f0c5fa11 ...l.....z.C.... /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 19080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 442b0000 00420e10 8f02420e ....D+...B....B. + 0020 00000000 aa190000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ea80303 7d250a0e ..A.8..G....}%.. + 0040 8606410e 38830747 0ed00203 29130a0e ..A.8..G....)... 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0846 0b000000 D..F.... + 0060 440e084a 0b000000 D..J.... /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_SKYLAKEX.o (disasm) @@ -15,773 +15,543 @@ mov %rsi,offset(%rsp) sar $something,%rsi mov %rdi,offset(%rsp) - mov %rdx,-offset(%rsp) - mov %rcx,(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) mov %r8,-offset(%rsp) mov %r9,-offset(%rsp) mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov offset(%rsp),%r12 test %rsi,%rsi jle - mov %r8,%r10 - imul %rcx,%r10 - mov %r8,%rdi + mov %rcx,%rsi mov %rcx,%rax - lea (%rcx,%r10,1),%r9 - lea (%r9,%rcx,1),%r8 - lea (%rcx,%r8,1),%rbx - lea (%rbx,%rcx,1),%rsi - mov %rbx,-offset(%rsp) - lea (%rcx,%rsi,1),%rbx - lea (%rbx,%rcx,1),%rdx - lea (%rcx,%rdx,1),%r11 - mov %rbx,-offset(%rsp) - lea (%rcx,%r11,1),%rbx - lea (%rcx,%rbx,1),%rbp - lea (%rcx,%rbp,1),%r12 - lea (%rcx,%r12,1),%r13 - lea (%rcx,%r13,1),%r14 - lea (%rcx,%r14,1),%rcx - mov %rcx,-offset(%rsp) - mov -offset(%rsp),%rcx - add %rax,%rcx - mov %rcx,-offset(%rsp) - mov offset(%rsp),%rcx - sar $something,%rcx - mov %rcx,offset(%rsp) - lea offset(,%rax,4),%rcx - mov %rcx,offset(%rsp) - mov %rax,%rcx - mov offset(%rsp),%rax - shl $something,%rcx - and $something,%eax - mov %rax,-offset(%rsp) + imul %r8,%rsi + mov %rdi,%r13 shl $something,%rax mov %rax,offset(%rsp) - mov offset(%rsp),%rax - mov %rcx,-offset(%rsp) + mov %r13,%rax + mov %r9,%r14 + and $something,%eax + lea (%rsi,%rcx,2),%rdi + lea offset(,%rcx,8),%r15 + mov %rax,-offset(%rsp) + lea (%r14,%rsi,1),%rax + lea (%rdi,%rcx,1),%r8 + kmovq %r15,%k2 + lea (%rdx,%rax,4),%r15 + mov %r14,%rax + lea (%r8,%rcx,1),%r9 + imul %rcx,%rax + lea (%rcx,%r9,1),%r10 + lea (%rcx,%r10,1),%r11 + mov %rcx,%rdx + mov %rcx,%rbp + mov offset(%rsp),%rcx + add -offset(%rsp),%rax + lea (%rcx,%rax,4),%r14 mov -offset(%rsp),%rcx - shl $something,%rax - add %rcx,%rax + mov offset(%rsp),%rax + sub %rsi,%rdi + lea (%rcx,%rax,8),%rax mov %rax,offset(%rsp) - mov (%rsp),%rax - imul %rcx,%rax - add %rdi,%rax - mov -offset(%rsp),%rdi - lea (%rdi,%rax,4),%rdi + mov %rdx,%rax + neg %rax + lea offset(,%rax,4),%rdx mov %rcx,%rax - mov (%rsp),%rcx - inc %rax - imul %rcx,%rax - mov %rdi,offset(%rsp) - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - add -offset(%rsp),%rax - mov -offset(%rsp),%rdi - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - add -offset(%rsp),%rax - mov -offset(%rsp),%rdi - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul %rcx,%rax - mov -offset(%rsp),%rdi - add -offset(%rsp),%rax - lea (%rdi,%rax,4),%rdi - mov -offset(%rsp),%rax + imul %rdx,%rax + mov %rdx,offset(%rsp) + inc %rcx + neg %rdx + imul %rdx,%rcx + lea offset(,%rdi,4),%rdi mov %rdi,offset(%rsp) - add $something,%rax /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_SKYLAKEX.o (objdump) @@ -2,696 +2,414 @@ /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ec700100 AWAVAUATUSH..p.. - 0010 00488974 242048c1 fe044889 7c241048 .H.t$ H...H.|$.H - 0020 895424e0 48890c24 4c894424 a84c894c .T$.H..$L.D$.L.L - 0030 24c84889 b4245001 00004c8b bc24a801 $.H..$P...L..$.. - 0040 00004885 f60f8e56 1c00004d 89c24c0f ..H....V...M..L. - 0050 afd14c89 c74889c8 4e8d0c11 4d8d0409 ..L..H..N...M... - 0060 4a8d1c01 488d340b 48895c24 98488d1c J...H.4.H.\$.H.. - 0070 31488d14 0b4c8d1c 1148895c 24904a8d 1H...L...H.\$.J. - 0080 1c19488d 2c194c8d 24294e8d 2c214e8d ..H.,.L.$)N.,!N. - 0090 34294a8d 0c314889 4c248848 8b4c2488 4)J..1H.L$.H.L$. - 00a0 4801c148 894c24a0 488b4c24 1048c1f9 H..H.L$.H.L$.H.. - 00b0 0448894c 2408488d 0c850000 00004889 .H.L$.H.......H. - 00c0 8c243001 00004889 c1488b44 241048c1 .$0...H..H.D$.H. - 00d0 e10683e0 0f488944 24d848c1 e0064889 .....H.D$.H...H. - 00e0 84244801 0000488b 84245001 00004889 .$H...H..$P...H. - 00f0 4c24f848 8b4c24c8 48c1e004 4801c848 L$.H.L$.H...H..H - 0100 89442418 488b0424 480fafc1 4801f848 .D$.H..$H...H..H - 0110 8b7c24e0 488d3c87 4889c848 8b0c2448 .|$.H.<.H..H..$H - 0120 ffc0480f afc14889 7c243848 8b7c24e0 ..H...H.|$8H.|$. - 0130 48034424 a8488d3c 87488b44 24c84889 H.D$.H.<.H.D$.H. - 0140 7c244848 83c00248 0fafc148 8b7c24e0 |$HH...H...H.|$. - 0150 48034424 a8488d3c 87488b44 24c84889 H.D$.H.<.H.D$.H. - 0160 7c245848 83c00348 0fafc148 8b7c24e0 |$XH...H...H.|$. - 0170 48034424 a8488d3c 87488b44 24c84889 H.D$.H.<.H.D$.H. - 0180 7c246848 83c00448 0fafc148 034424a8 |$hH...H...H.D$. - 0190 488b7c24 e0488d3c 87488b44 24c84889 H.|$.H.<.H.D$.H. - 01a0 7c247848 83c00548 0fafc148 8b7c24e0 |$xH...H...H.|$. - 01b0 48034424 a8488d3c 87488b44 24c84889 H.D$.H.<.H.D$.H. - 01c0 bc248800 00004883 c006480f afc1488b .$....H...H...H. - 01d0 7c24e048 034424a8 488d3c87 488b4424 |$.H.D$.H.<.H.D$ - 01e0 c84889bc 24980000 004883c0 07480faf .H..$....H...H.. - 01f0 c1488b7c 24e04803 4424a848 8d3c8748 .H.|$.H.D$.H.<.H - 0200 8b4424c8 4889bc24 a8000000 4883c008 .D$.H..$....H... - 0210 480fafc1 488b7c24 e0480344 24a8488d H...H.|$.H.D$.H. - 0220 3c87488b 4424c848 89bc24b8 00000048 <.H.D$.H..$....H - 0230 83c00948 0fafc148 8b7c24e0 48034424 ...H...H.|$.H.D$ - 0240 a8488d3c 87488b44 24c84889 bc24c800 .H.<.H.D$.H..$.. - 0250 00004883 c00a480f afc1488b 7c24e048 ..H...H...H.|$.H - 0260 034424a8 488d3c87 488b4424 c84889bc .D$.H.<.H.D$.H.. - 0270 24d80000 004883c0 0b480faf c1488b7c $....H...H...H.| - 0280 24e04803 4424a848 8d3c8748 8b4424c8 $.H.D$.H.<.H.D$. - 0290 4889bc24 e8000000 4883c00c 480fafc1 H..$....H...H... - 02a0 48034424 a8488b7c 24e0488d 3c87488b H.D$.H.|$.H.<.H. - 02b0 4424c848 89bc24f8 00000048 83c00d48 D$.H..$....H...H - 02c0 0fafc148 8b7c24e0 48034424 a8488d3c ...H.|$.H.D$.H.< - 02d0 87488b44 24c84889 bc240801 00004883 .H.D$.H..$....H. - 02e0 c00e480f afc1488b 7c24e048 034424a8 ..H...H.|$.H.D$. - 02f0 488d3c87 488b4424 c84889bc 24180100 H.<.H.D$.H..$... - 0300 004883c0 0f480faf c1488b4c 24e04803 .H...H...H.L$.H. - 0310 4424a848 8d3c8148 8b4424c8 4889bc24 D$.H.<.H.D$.H..$ - 0320 28010000 488b7c24 984901c2 4901c048 (...H.|$.I..I..H - 0330 01c74801 c64e8d14 914901c1 4e8d0481 ..H..N...I..N... - 0340 4c895424 304c8944 24504c8d 14b14c8d L.T$0L.D$PL...L. - 0350 04b94e8d 0c894889 c74889c8 488b4c24 ..N...H..H..H.L$ - 0360 904901fb 4801f948 01fa4801 fb4e8d1c .I..H..H..H..N.. - 0370 984c8954 24704c8d 14884801 fd4c8994 .L.T$pL...H..L.. - 0380 24800000 004c899c 24a00000 004c8d14 $....L..$....L.. - 0390 904c8d1c 98488b54 24884c89 9c24b000 .L...H.T$.L..$.. - 03a0 00004901 fc4c8d1c a84c899c 24c00000 ..I..L...L..$... - 03b0 004901fd 4e8d1ca0 4901fe48 01fa488d .I..N...I..H..H. - 03c0 14904c89 9c24d000 00004e8d 34b04e8d ..L..$....N.4.N. - 03d0 1ca84889 94240001 00004c89 4c24404c ..H..$....L.L$@L - 03e0 89442460 4c899424 90000000 4c899c24 .D$`L..$....L..$ - 03f0 e0000000 4c89b424 f0000000 488b5c24 ....L..$....H.\$ - 0400 a04889c6 4889d848 01f8488d 1486488b .H..H..H..H...H. - 0410 04244889 94241001 00004801 d84801f8 .$H..$....H..H.. - 0420 488d1486 488b7424 104889fb 4889f048 H...H.t$.H..H..H - 0430 8b7c24a8 4883e0f0 4801f848 894424d0 .|$.H...H..H.D$. - 0440 488b4424 08488994 24200100 004889c2 H.D$.H..$ ...H.. - 0450 48c1e004 4801f848 89842438 01000048 H...H..H..$8...H - 0460 89f083e0 0e488984 24580100 004889f0 .....H..$X...H.. - 0470 48c1e20a 83e00c83 e6084889 94244001 H.........H..$@. - 0480 00004889 5c249048 c74424f0 00000000 ..H.\$.H.D$..... - 0490 48c74424 e8000000 00488984 24600100 H.D$.....H..$`.. - 04a0 004889b4 24680100 00e91001 00006690 .H..$h........f. - 04b0 488b4424 e8488b8c 24e00000 00488b74 H.D$.H..$....H.t - 04c0 24304801 c148894c 2498488b 8c24f000 $0H..H.L$.H..$.. - 04d0 0000488b 7c244048 01c14889 4c24a048 ..H.|$@H..H.L$.H - 04e0 8b8c2400 0100004c 8b442450 4801c148 ..$....L.D$PH..H - 04f0 894c24b0 4c8b4c24 604c8b54 24704c8b .L$.L.L$`L.T$pL. - 0500 9c248000 0000488b 9c249000 0000488b .$....H..$....H. - 0510 ac24a000 00004c8b a424b000 00004c8b .$....L..$....L. - 0520 ac24c000 00004c8b b424d000 0000488b .$....L..$....H. - 0530 8c241001 00004801 c64801c1 4801c749 .$....H..H..H..I - 0540 01c04901 c14901c2 4901c348 01c34801 ..I..I..I..H..H. - 0550 c54901c4 4901c549 01c64803 84242001 .I..I..I..H..$ . - 0560 00004883 7c240800 48894424 c048894c ..H.|$..H.D$.H.L - 0570 24b8488b 4424a80f 8f1e0100 0048837c $.H.D$.......H.| - 0580 24d80074 13483944 24900f8d e00e0000 $..t.H9D$....... - 0590 4c03bc24 48010000 48834424 9010488b L..$H...H.D$..H. - 05a0 7c24f848 834424e8 4048017c 24f0488b |$.H.D$.@H.|$.H. - 05b0 44249048 3b442418 0f84ca16 0000488b D$.H;D$.......H. - 05c0 5c24a848 395c2490 0f8de2fe ffff488b \$.H9\$.......H. - 05d0 4424f048 8b8c24e8 00000048 8b742438 D$.H..$....H.t$8 - 05e0 4801c148 894c2498 488b8c24 f8000000 H..H.L$.H..$.... - 05f0 488b7c24 484801c1 48894c24 a0488b8c H.|$HH..H.L$.H.. - 0600 24080100 004c8b44 24584801 c148894c $....L.D$XH..H.L - 0610 24b04c8b 4c24684c 8b542478 4c8b9c24 $.L.L$hL.T$xL..$ - 0620 88000000 488b9c24 98000000 488bac24 ....H..$....H..$ - 0630 a8000000 4c8ba424 b8000000 4c8bac24 ....L..$....L..$ - 0640 c8000000 4c8bb424 d8000000 488b8c24 ....L..$....H..$ - 0650 18010000 4801c648 01c14801 c74901c0 ....H..H..H..I.. - 0660 4901c149 01c24901 c34801c3 4801c549 I..I..I..H..H..I - 0670 01c44901 c54901c6 48038424 28010000 ..I..I..H..$(... - 0680 48837c24 08004889 4424c048 894c24b8 H.|$..H.D$.H.L$. - 0690 488b4424 a80f8ee2 feffff48 8b5424a8 H.D$.......H.T$. - 06a0 4c89bc24 a8010000 48895424 88498d87 L..$....H.T$.I.. - 06b0 00040000 eb70662e 0f1f8400 00000000 .....pf......... - 06c0 48834424 98404883 4424a040 48834424 H.D$.@H.D$.@H.D$ - 06d0 b0404883 4424b840 48834424 c0404883 .@H.D$.@H.D$.@H. - 06e0 c6404883 c7404983 c0404983 c1404983 .@H..@I..@I..@I. - 06f0 c2404983 c3404883 c3404883 c5404983 .@I..@H..@H..@I. - 0700 c4404983 c5404983 c6404883 44248810 .@I..@I..@H.D$.. - 0710 48050004 0000488b 4c248848 3b4c24d0 H.....H.L$.H;L$. - 0720 0f842a0d 00004c8b 7c248848 8d9000fc ..*...L.|$.H.... - 0730 ffff4c39 7c24907c 87c5fa10 060f8ff5 ..L9|$.|........ - 0740 0b0000c5 fa118000 fcffffc5 fa104604 ..............F. - 0750 4883c740 c5fa1180 04fcffff c5fa1046 H..@...........F - 0760 084983c0 40c5fa11 8008fcff ffc5fa10 .I..@........... - 0770 460c4983 c140c5fa 11800cfc ffffc5fa F.I..@.......... - 0780 10461049 83c240c5 fa118010 fcffffc5 .F.I..@......... - 0790 fa104614 4983c340 c5fa1180 14fcffff ..F.I..@........ - 07a0 c5fa1046 184883c3 40c5fa11 8018fcff ...F.H..@....... - 07b0 ffc5fa10 461c4883 c540c5fa 11801cfc ....F.H..@...... - 07c0 ffffc5fa 10462049 83c440c5 fa118020 .....F I..@.... - 07d0 fcffffc5 fa104624 4983c540 c5fa1180 ......F$I..@.... - 07e0 24fcffff c5fa1046 284983c6 40c5fa11 $......F(I..@... - 07f0 8028fcff ffc5fa10 462c4883 c640c5fa .(......F,H..@.. - 0800 11802cfc ffffc5fa 1046f0c5 fa118030 ..,......F.....0 - 0810 fcffffc5 fa1046f4 c5fa1180 34fcffff ......F.....4... - 0820 c5fa1046 f8c5fa11 8038fcff ffc5fa10 ...F.....8...... - 0830 46fcc780 40fcffff 00000000 c5fa1180 F...@........... - 0840 3cfcffff c5fa1047 c4c5fa11 8044fcff <......G.....D.. - 0850 ffc5fa10 47c8c5fa 118048fc ffffc5fa ....G.....H..... - 0860 1047ccc5 fa11804c fcffffc5 fa1047d0 .G.....L......G. - 0870 c5fa1180 50fcffff c5fa1047 d4c5fa11 ....P......G.... - 0880 8054fcff ffc5fa10 47d8c5fa 118058fc .T......G.....X. - 0890 ffffc5fa 1047dcc5 fa11805c fcffffc5 .....G.....\.... - 08a0 fa1047e0 c5fa1180 60fcffff c5fa1047 ..G.....`......G - 08b0 e4c5fa11 8064fcff ffc5fa10 47e8c5fa .....d......G... - 08c0 118068fc ffffc5fa 1047ecc5 fa11806c ..h......G.....l - 08d0 fcffffc5 fa1047f0 c5fa1180 70fcffff ......G.....p... - 08e0 c5fa1047 f4c5fa11 8074fcff ffc5fa10 ...G.....t...... - 08f0 47f8c5fa 118078fc ffffc5fa 1047fcc7 G.....x......G.. - 0900 8080fcff ff000000 00c78084 fcffff00 ................ - 0910 000000c5 fa11807c fcffffc4 c17a1040 .......|.....z.@ - 0920 c8c5fa11 8088fcff ffc4c17a 1040ccc5 ...........z.@.. - 0930 fa11808c fcffffc4 c17a1040 d0c5fa11 .........z.@.... - 0940 8090fcff ffc4c17a 1040d4c5 fa118094 .......z.@...... - 0950 fcffffc4 c17a1040 d8c5fa11 8098fcff .....z.@........ - 0960 ffc4c17a 1040dcc5 fa11809c fcffffc4 ...z.@.......... - 0970 c17a1040 e0c5fa11 80a0fcff ffc4c17a .z.@...........z - 0980 1040e4c5 fa1180a4 fcffffc4 c17a1040 .@...........z.@ - 0990 e8c5fa11 80a8fcff ffc4c17a 1040ecc5 ...........z.@.. - 09a0 fa1180ac fcffffc4 c17a1040 f0c5fa11 .........z.@.... - 09b0 80b0fcff ffc4c17a 1040f4c5 fa1180b4 .......z.@...... - 09c0 fcffffc4 c17a1040 f8c5fa11 80b8fcff .....z.@........ - 09d0 ffc4c17a 1040fcc7 80c0fcff ff000000 ...z.@.......... - 09e0 00c780c4 fcffff00 000000c7 80c8fcff ................ - 09f0 ff000000 00c5fa11 80bcfcff ffc4c17a ...............z - 0a00 1041ccc5 fa1180cc fcffffc4 c17a1041 .A...........z.A - 0a10 d0c5fa11 80d0fcff ffc4c17a 1041d4c5 ...........z.A.. - 0a20 fa1180d4 fcffffc4 c17a1041 d8c5fa11 .........z.A.... - 0a30 80d8fcff ffc4c17a 1041dcc5 fa1180dc .......z.A...... - 0a40 fcffffc4 c17a1041 e0c5fa11 80e0fcff .....z.A........ - 0a50 ffc4c17a 1041e4c5 fa1180e4 fcffffc4 ...z.A.......... - 0a60 c17a1041 e8c5fa11 80e8fcff ffc4c17a .z.A...........z - 0a70 1041ecc5 fa1180ec fcffffc4 c17a1041 .A...........z.A - 0a80 f0c5fa11 80f0fcff ffc4c17a 1041f4c5 ...........z.A.. - 0a90 fa1180f4 fcffffc4 c17a1041 f8c5fa11 .........z.A.... - 0aa0 80f8fcff ffc4c17a 1041fcc7 8000fdff .......z.A...... - 0ab0 ff000000 00c78004 fdffff00 000000c7 ................ - 0ac0 8008fdff ff000000 00c7800c fdffff00 ................ - 0ad0 000000c5 fa1180fc fcffffc4 c17a1042 .............z.B - 0ae0 d0c5fa11 8010fdff ffc4c17a 1042d4c5 ...........z.B.. - 0af0 fa118014 fdffffc4 c17a1042 d8c5fa11 .........z.B.... - 0b00 8018fdff ffc4c17a 1042dcc5 fa11801c .......z.B...... - 0b10 fdffffc4 c17a1042 e0c5fa11 8020fdff .....z.B..... .. - 0b20 ffc4c17a 1042e4c5 fa118024 fdffffc4 ...z.B.....$.... - 0b30 c17a1042 e8c5fa11 8028fdff ffc4c17a .z.B.....(.....z - 0b40 1042ecc5 fa11802c fdffffc4 c17a1042 .B.....,.....z.B - 0b50 f0c5fa11 8030fdff ffc4c17a 1042f4c5 .....0.....z.B.. - 0b60 fa118034 fdffffc4 c17a1042 f8c5fa11 ...4.....z.B.... - 0b70 8038fdff ffc4c17a 1042fcc7 8040fdff .8.....z.B...@.. - 0b80 ff000000 00c78044 fdffff00 000000c7 .......D........ - 0b90 8048fdff ff000000 00c7804c fdffff00 .H.........L.... - 0ba0 000000c7 8050fdff ff000000 00c5fa11 .....P.......... - 0bb0 803cfdff ffc4c17a 1043d4c5 fa118054 .<.....z.C.....T - 0bc0 fdffffc4 c17a1043 d8c5fa11 8058fdff .....z.C.....X.. - 0bd0 ffc4c17a 1043dcc5 fa11805c fdffffc4 ...z.C.....\.... - 0be0 c17a1043 e0c5fa11 8060fdff ffc4c17a .z.C.....`.....z - 0bf0 1043e4c5 fa118064 fdffffc4 c17a1043 .C.....d.....z.C - 0c00 e8c5fa11 8068fdff ffc4c17a 1043ecc5 .....h.....z.C.. - 0c10 fa11806c fdffffc4 c17a1043 f0c5fa11 ...l.....z.C.... /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 19080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltncopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 442b0000 00420e10 8f02420e ....D+...B....B. + 0020 00000000 aa190000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ea80303 7d250a0e ..A.8..G....}%.. + 0040 8606410e 38830747 0ed00203 29130a0e ..A.8..G....)... 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0846 0b000000 D..F.... + 0060 440e084a 0b000000 D..J.... /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_COOPERLAKE.o (disasm) @@ -14,599 +14,466 @@ sub $something,%rsp mov %rsi,offset(%rsp) sar $something,%rsi - mov %rdi,(%rsp) + mov %rdi,offset(%rsp) mov %rdx,offset(%rsp) - mov %rcx,-offset(%rsp) + mov %rcx,offset(%rsp) mov %r8,-offset(%rsp) mov %r9,-offset(%rsp) mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov offset(%rsp),%rbp test %rsi,%rsi jle - mov %r8,%rbx - imul %rcx,%rbx - mov %r8,%rdi + mov %rcx,%rsi mov %rcx,%rax - lea (%rcx,%rbx,1),%r11 - lea (%r11,%rcx,1),%rsi - lea (%rcx,%rsi,1),%r9 - lea (%r9,%rcx,1),%r8 - mov %rsi,-offset(%rsp) - lea (%rcx,%r8,1),%rsi - mov %rsi,-offset(%rsp) - add %rcx,%rsi - lea (%rcx,%rsi,1),%rcx - lea (%rax,%rcx,1),%rdx - lea (%rax,%rdx,1),%rbp - lea (%rax,%rbp,1),%r12 - lea (%rax,%r12,1),%r13 - lea (%rax,%r13,1),%r14 - lea (%rax,%r14,1),%r10 - mov %r10,-offset(%rsp) - mov (%rsp),%r10 - sar $something,%r10 - mov %r10,-offset(%rsp) - lea offset(,%rax,4),%r10 - mov %r10,offset(%rsp) - mov (%rsp),%r10 + imul %r8,%rsi + mov %rdi,%r12 shl $something,%rax - and $something,%r10d - mov %r10,-offset(%rsp) - shl $something,%r10 + mov %rax,offset(%rsp) + mov %r12,%rax + mov %r9,%r14 + lea offset(,%rcx,8),%r15 + and $something,%eax mov %rax,-offset(%rsp) - mov %r10,offset(%rsp) - mov -offset(%rsp),%rax - mov offset(%rsp),%r10 - imul -offset(%rsp),%rax - shl $something,%r10 - add -offset(%rsp),%r10 - mov %r10,offset(%rsp) - mov offset(%rsp),%r10 - add %rdi,%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - inc %rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov %rdi,offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov %rdi,offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax + kmovq %r15,%k2 + lea (%r14,%rsi,1),%rax + mov %r14,%r15 + lea (%rdx,%rax,4),%r14 + mov %r15,%rax + imul %rcx,%rax + mov %r15,%rdx + mov offset(%rsp),%r15 add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add %rax,%rbx - add %rax,%r11 - mov %r10,%rdi - lea (%r10,%rbx,4),%rbx - lea (%r10,%r11,4),%r11 - mov -offset(%rsp),%r10 - mov %rbx,offset(%rsp) - mov %rax,%rbx - add %rbx,%r10 - mov %r11,offset(%rsp) - add %rbx,%r9 - lea (%rdi,%r10,4),%r11 - add %rbx,%rcx - lea (%rdi,%rcx,4),%rcx - add %rbx,%rdx - mov %r11,offset(%rsp) - add %rbx,%r8 - lea (%rdi,%r9,4),%r11 - mov %r11,offset(%rsp) + lea (%r15,%rax,4),%r15 + mov offset(%rsp),%rax + lea (%rsi,%rcx,2),%rdi + lea (%rdi,%rcx,1),%r8 + lea (%rdx,%rax,8),%rax + lea (%r8,%rcx,1),%r9 + mov %rax,offset(%rsp) + mov %rcx,%rax + lea (%rcx,%r9,1),%r10 + neg %rax + lea (%rcx,%r10,1),%r11 + mov %rcx,%r13 + lea offset(,%rax,4),%rcx mov %rcx,offset(%rsp) - lea (%rdi,%r8,4),%r11 - lea (%rdi,%rdx,4),%rcx - add %rbx,%rbp - mov -offset(%rsp),%rdx - mov %r11,offset(%rsp) + mov %rcx,%rax /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_COOPERLAKE.o (objdump) @@ -2,670 +2,352 @@ /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ec580100 AWAVAUATUSH..X.. - 0010 00488974 241048c1 fe044889 3c244889 .H.t$.H...H.<$H. - 0020 54242048 894c24d8 4c894424 b04c894c T$ H.L$.L.D$.L.L - 0030 24c04889 b4243801 00004c8b bc249001 $.H..$8...L..$.. - 0040 00004885 f60f8e0e 1b00004c 89c3480f ..H........L..H. - 0050 afd94c89 c74889c8 4c8d1c19 498d340b ..L..H..L...I.4. - 0060 4c8d0c31 4d8d0409 48897424 984a8d34 L..1M...H.t$.J.4 - 0070 01488974 24884801 ce488d0c 31488d14 .H.t$.H..H..1H.. - 0080 08488d2c 104c8d24 284e8d2c 204e8d34 .H.,.L.$(N., N.4 - 0090 284e8d14 304c8954 24904c8b 142449c1 (N..0L.T$.L..$I. - 00a0 fa044c89 5424f84c 8d148500 0000004c ..L.T$.L.......L - 00b0 89942418 0100004c 8b142448 c1e00641 ..$....L..$H...A - 00c0 83e20f4c 895424d0 49c1e206 48894424 ...L.T$.I...H.D$ - 00d0 f04c8994 24300100 00488b44 24d84c8b .L..$0...H.D$.L. - 00e0 94243801 0000480f af4424c0 49c1e204 .$8...H..D$.I... - 00f0 4c035424 c04c8954 24084c8b 54242048 L.T$.L.T$.L.T$ H - 0100 01f8498d 3c82488b 4424c048 897c2430 ..I.<.H.D$.H.|$0 - 0110 48ffc048 0faf4424 d8480344 24b0498d H..H..D$.H.D$.I. - 0120 3c82488b 4424c048 897c2440 4883c002 <.H.D$.H.|$@H... - 0130 480faf44 24d84803 4424b049 8d3c8248 H..D$.H.D$.I.<.H - 0140 8b4424c0 48897c24 504883c0 03480faf .D$.H.|$PH...H.. - 0150 4424d848 034424b0 498d3c82 488b4424 D$.H.D$.I.<.H.D$ - 0160 c048897c 24604883 c004480f af4424d8 .H.|$`H...H..D$. - 0170 48034424 b0498d3c 8248897c 2470488b H.D$.I.<.H.|$pH. - 0180 4424c048 83c00548 0faf4424 d8480344 D$.H...H..D$.H.D - 0190 24b0498d 3c82488b 4424c048 89bc2480 $.I.<.H.D$.H..$. - 01a0 00000048 83c00648 0faf4424 d8480344 ...H...H..D$.H.D - 01b0 24b0498d 3c82488b 4424c048 89bc2490 $.I.<.H.D$.H..$. - 01c0 00000048 83c00748 0faf4424 d8480344 ...H...H..D$.H.D - 01d0 24b0498d 3c82488b 4424c048 89bc24a0 $.I.<.H.D$.H..$. - 01e0 00000048 83c00848 0faf4424 d8480344 ...H...H..D$.H.D - 01f0 24b0498d 3c82488b 4424c048 89bc24b0 $.I.<.H.D$.H..$. - 0200 00000048 83c00948 0faf4424 d8480344 ...H...H..D$.H.D - 0210 24b0498d 3c82488b 4424c048 89bc24c0 $.I.<.H.D$.H..$. - 0220 00000048 83c00a48 0faf4424 d8480344 ...H...H..D$.H.D - 0230 24b0498d 3c82488b 4424c048 89bc24d0 $.I.<.H.D$.H..$. - 0240 00000048 83c00b48 0faf4424 d8480344 ...H...H..D$.H.D - 0250 24b0498d 3c82488b 4424c048 89bc24e0 $.I.<.H.D$.H..$. - 0260 00000048 83c00c48 0faf4424 d8480344 ...H...H..D$.H.D - 0270 24b0498d 3c824889 bc24f000 0000488b $.I.<.H..$....H. - 0280 4424c048 83c00d48 0faf4424 d8480344 D$.H...H..D$.H.D - 0290 24b0498d 3c82488b 4424c048 89bc2400 $.I.<.H.D$.H..$. - 02a0 01000048 83c00e48 0faf4424 d8480344 ...H...H..D$.H.D - 02b0 24b0498d 3c82488b 4424c048 89bc2410 $.I.<.H.D$.H..$. - 02c0 01000048 01c34901 c34c89d7 498d1c9a ...H..I..L..I... - 02d0 4f8d1c9a 4c8b5424 9848895c 24284889 O...L.T$.H.\$(H. - 02e0 c34901da 4c895c24 384901d9 4e8d1c97 .I..L.\$8I..N... - 02f0 4801d948 8d0c8f48 01da4c89 5c244849 H..H...H..L.\$HI - 0300 01d84e8d 1c8f4c89 5c245848 898c2498 ..N...L.\$XH..$. - 0310 0000004e 8d1c8748 8d0c9748 01dd488b ...N...H...H..H. - 0320 5424904c 895c2468 48898c24 a8000000 T$.L.\$hH..$.... - 0330 4c8b5c24 88488d0c af4901dc 48898c24 L.\$.H...I..H..$ - 0340 b8000000 4901dd4a 8d0ca748 01de4889 ....I..J...H..H. - 0350 8c24c800 00004901 db4a8d0c af4901de .$....I..J...I.. - 0360 4889d04e 8d1c9f48 035424d8 48898c24 H..N...H.T$.H..$ - 0370 d8000000 4801d84a 8d0cb74c 895c2478 ....H..J...L.\$x - 0380 48898c24 e8000000 4c8d1cb7 488d0c87 H..$....L...H... - 0390 488b3424 4889d048 01d8488d 1487488b H.4$H..H..H...H. - 03a0 7c24b048 89f04883 e0f04801 f8488944 |$.H..H...H..H.D - 03b0 24c8488b 4424f848 89942408 01000048 $.H.D$.H..$....H - 03c0 89c248c1 e0044801 f848c1e2 0a4c899c ..H...H..H...L.. - 03d0 24880000 0048898c 24f80000 00488994 $....H..$....H.. - 03e0 24200100 00488984 24280100 004889f0 $ ...H..$(...H.. - 03f0 83e00e48 89842440 01000048 89f083e0 ...H..$@...H.... - 0400 0c83e608 48895c24 9048c744 24e80000 ....H.\$.H.D$... - 0410 000048c7 4424e000 00000048 89842448 ..H.D$.....H..$H - 0420 01000048 89b42450 010000c5 fa100500 ...H..$P........ - 0430 000000e9 03010000 0f1f8400 00000000 ................ - 0440 488b4424 e0488b8c 24d80000 00488b74 H.D$.H..$....H.t - 0450 24284801 c148894c 24b8488b 8c24e800 $(H..H.L$.H..$.. - 0460 0000488b 7c243848 01c14889 4c24984c ..H.|$8H..H.L$.L - 0470 8b442448 4c8b4c24 584c8b54 24684c8b .D$HL.L$XL.T$hL. - 0480 5c247848 8b9c2488 00000048 8bac2498 \$xH..$....H..$. - 0490 0000004c 8ba424a8 0000004c 8bac24b8 ...L..$....L..$. - 04a0 0000004c 8bb424c8 00000048 8b8c24f8 ...L..$....H..$. - 04b0 00000048 01c64801 c14801c7 4901c049 ...H..H..H..I..I - 04c0 01c14901 c24901c3 4801c348 01c54901 ..I..I..H..H..I. - 04d0 c44901c5 4901c648 03842408 01000048 .I..I..H..$....H - 04e0 837c24f8 00488944 24a84889 4c24a048 .|$..H.D$.H.L$.H - 04f0 8b4424b0 0f8f0e01 00004883 7c24d000 .D$.......H.|$.. - 0500 74134839 4424900f 8d6b0e00 004c03bc t.H9D$...k...L.. - 0510 24300100 00488344 24901048 8b7c24f0 $0...H.D$..H.|$. - 0520 48834424 e0404801 7c24e848 8b442490 H.D$.@H.|$.H.D$. - 0530 483b4424 080f8405 16000048 8b5c24b0 H;D$.......H.\$. - 0540 48395c24 900f8df5 feffff48 8b4424e8 H9\$.......H.D$. - 0550 488b8c24 e0000000 488b7424 304801c1 H..$....H.t$0H.. - 0560 48894c24 b8488b8c 24f00000 00488b7c H.L$.H..$....H.| - 0570 24404801 c148894c 24984c8b 4424504c $@H..H.L$.L.D$PL - 0580 8b4c2460 4c8b5424 704c8b9c 24800000 .L$`L.T$pL..$... - 0590 00488b9c 24900000 00488bac 24a00000 .H..$....H..$... - 05a0 004c8ba4 24b00000 004c8bac 24c00000 .L..$....L..$... - 05b0 004c8bb4 24d00000 00488b8c 24000100 .L..$....H..$... - 05c0 004801c6 4801c148 01c74901 c04901c1 .H..H..H..I..I.. - 05d0 4901c249 01c34801 c34801c5 4901c449 I..I..H..H..I..I - 05e0 01c54901 c6480384 24100100 0048837c ..I..H..$....H.| - 05f0 24f80048 894424a8 48894c24 a0488b44 $..H.D$.H.L$.H.D - 0600 24b00f8e f2feffff 488b5424 b04c89bc $.......H.T$.L.. - 0610 24900100 00498d87 00040000 48895424 $....I......H.T$ - 0620 884c8b7c 24b8eb66 0f1f8400 00000000 .L.|$..f........ - 0630 48834424 98404883 4424a040 48834424 H.D$.@H.D$.@H.D$ - 0640 a8404883 c6404883 c7404983 c0404983 .@H..@H..@I..@I. - 0650 c1404983 c2404983 c3404883 c3404883 .@I..@I..@H..@H. - 0660 c5404983 c4404983 c5404983 c6404983 .@I..@I..@I..@I. - 0670 c7404883 44248810 48050004 0000488b .@H.D$..H.....H. - 0680 4c248848 3b4c24c8 0f84c20c 0000488d L$.H;L$.......H. - 0690 9000fcff ff488954 24b8488b 54248848 .....H.T$.H.T$.H - 06a0 39542490 7c8a0f8f 940b0000 c5fa1180 9T$.|........... - 06b0 00fcffff c5fa104e 044883c7 40c5fa11 .......N.H..@... - 06c0 8804fcff ffc5fa10 4e084983 c040c5fa ........N.I..@.. - 06d0 118808fc ffffc5fa 104e0c49 83c140c5 .........N.I..@. - 06e0 fa11880c fcffffc5 fa104e10 4983c240 ..........N.I..@ - 06f0 c5fa1188 10fcffff c5fa104e 144983c3 ...........N.I.. - 0700 40c5fa11 8814fcff ffc5fa10 4e184883 @...........N.H. - 0710 c340c5fa 118818fc ffffc5fa 104e1c48 .@...........N.H - 0720 83c540c5 fa11881c fcffffc5 fa104e20 ..@...........N - 0730 4983c440 c5fa1188 20fcffff c5fa104e I..@.... ......N - 0740 244983c5 40c5fa11 8824fcff ffc5fa10 $I..@....$...... - 0750 4e284983 c640c5fa 118828fc ffffc5fa N(I..@....(..... - 0760 104e2c49 83c740c5 fa11882c fcffffc5 .N,I..@....,.... - 0770 fa104e30 4883c640 c5fa1188 30fcffff ..N0H..@....0... - 0780 c5fa104e f4c5fa11 8834fcff ffc5fa10 ...N.....4...... - 0790 4ef8c5fa 118838fc ffffc5fa 104efcc7 N.....8......N.. - 07a0 8040fcff ff000000 00c5fa11 883cfcff .@...........<.. - 07b0 ffc5fa11 8044fcff ffc5fa10 4fc8c5fa .....D......O... - 07c0 118848fc ffffc5fa 104fccc5 fa11884c ..H......O.....L - 07d0 fcffffc5 fa104fd0 c5fa1188 50fcffff ......O.....P... - 07e0 c5fa104f d4c5fa11 8854fcff ffc5fa10 ...O.....T...... - 07f0 4fd8c5fa 118858fc ffffc5fa 104fdcc5 O.....X......O.. - 0800 fa11885c fcffffc5 fa104fe0 c5fa1188 ...\......O..... - 0810 60fcffff c5fa104f e4c5fa11 8864fcff `......O.....d.. - 0820 ffc5fa10 4fe8c5fa 118868fc ffffc5fa ....O.....h..... - 0830 104fecc5 fa11886c fcffffc5 fa104ff0 .O.....l......O. - 0840 c5fa1188 70fcffff c5fa104f f4c5fa11 ....p......O.... - 0850 8874fcff ffc5fa10 4ff8c5fa 118878fc .t......O.....x. - 0860 ffffc5fa 104ffcc7 8080fcff ff000000 .....O.......... - 0870 00c78084 fcffff00 000000c5 fa11887c ...............| - 0880 fcffffc5 fa118088 fcffffc4 c17a1048 .............z.H - 0890 ccc5fa11 888cfcff ffc4c17a 1048d0c5 ...........z.H.. - 08a0 fa118890 fcffffc4 c17a1048 d4c5fa11 .........z.H.... - 08b0 8894fcff ffc4c17a 1048d8c5 fa118898 .......z.H...... - 08c0 fcffffc4 c17a1048 dcc5fa11 889cfcff .....z.H........ - 08d0 ffc4c17a 1048e0c5 fa1188a0 fcffffc4 ...z.H.......... - 08e0 c17a1048 e4c5fa11 88a4fcff ffc4c17a .z.H...........z - 08f0 1048e8c5 fa1188a8 fcffffc4 c17a1048 .H...........z.H - 0900 ecc5fa11 88acfcff ffc4c17a 1048f0c5 ...........z.H.. - 0910 fa1188b0 fcffffc4 c17a1048 f4c5fa11 .........z.H.... - 0920 88b4fcff ffc4c17a 1048f8c5 fa1188b8 .......z.H...... - 0930 fcffffc4 c17a1048 fcc780c0 fcffff00 .....z.H........ - 0940 000000c7 80c4fcff ff000000 00c780c8 ................ - 0950 fcffff00 000000c5 fa1188bc fcffffc5 ................ - 0960 fa1180cc fcffffc4 c17a1049 d0c5fa11 .........z.I.... - 0970 88d0fcff ffc4c17a 1049d4c5 fa1188d4 .......z.I...... - 0980 fcffffc4 c17a1049 d8c5fa11 88d8fcff .....z.I........ - 0990 ffc4c17a 1049dcc5 fa1188dc fcffffc4 ...z.I.......... - 09a0 c17a1049 e0c5fa11 88e0fcff ffc4c17a .z.I...........z - 09b0 1049e4c5 fa1188e4 fcffffc4 c17a1049 .I...........z.I - 09c0 e8c5fa11 88e8fcff ffc4c17a 1049ecc5 ...........z.I.. - 09d0 fa1188ec fcffffc4 c17a1049 f0c5fa11 .........z.I.... - 09e0 88f0fcff ffc4c17a 1049f4c5 fa1188f4 .......z.I...... - 09f0 fcffffc4 c17a1049 f8c5fa11 88f8fcff .....z.I........ - 0a00 ffc4c17a 1049fcc7 8000fdff ff000000 ...z.I.......... - 0a10 00c78004 fdffff00 000000c7 8008fdff ................ - 0a20 ff000000 00c7800c fdffff00 000000c5 ................ - 0a30 fa1188fc fcffffc5 fa118010 fdffffc4 ................ - 0a40 c17a104a d4c5fa11 8814fdff ffc4c17a .z.J...........z - 0a50 104ad8c5 fa118818 fdffffc4 c17a104a .J...........z.J - 0a60 dcc5fa11 881cfdff ffc4c17a 104ae0c5 ...........z.J.. - 0a70 fa118820 fdffffc4 c17a104a e4c5fa11 ... .....z.J.... - 0a80 8824fdff ffc4c17a 104ae8c5 fa118828 .$.....z.J.....( - 0a90 fdffffc4 c17a104a ecc5fa11 882cfdff .....z.J.....,.. - 0aa0 ffc4c17a 104af0c5 fa118830 fdffffc4 ...z.J.....0.... - 0ab0 c17a104a f4c5fa11 8834fdff ffc4c17a .z.J.....4.....z - 0ac0 104af8c5 fa118838 fdffffc4 c17a104a .J.....8.....z.J - 0ad0 fcc78040 fdffff00 000000c7 8044fdff ...@.........D.. - 0ae0 ff000000 00c78048 fdffff00 000000c7 .......H........ - 0af0 804cfdff ff000000 00c78050 fdffff00 .L.........P.... - 0b00 000000c5 fa11883c fdffffc5 fa118054 .......<.......T - 0b10 fdffffc4 c17a104b d8c5fa11 8858fdff .....z.K.....X.. - 0b20 ffc4c17a 104bdcc5 fa11885c fdffffc4 ...z.K.....\.... - 0b30 c17a104b e0c5fa11 8860fdff ffc4c17a .z.K.....`.....z - 0b40 104be4c5 fa118864 fdffffc4 c17a104b .K.....d.....z.K - 0b50 e8c5fa11 8868fdff ffc4c17a 104becc5 .....h.....z.K.. - 0b60 fa11886c fdffffc4 c17a104b f0c5fa11 ...l.....z.K.... - 0b70 8870fdff ffc4c17a 104bf4c5 fa118874 .p.....z.K.....t - 0b80 fdffffc4 c17a104b f8c5fa11 8878fdff .....z.K.....x.. - 0b90 ffc4c17a 104bfcc7 8080fdff ff000000 ...z.K.......... - 0ba0 00c78084 fdffff00 000000c7 8088fdff ................ - 0bb0 ff000000 00c7808c fdffff00 000000c7 ................ - 0bc0 8090fdff ff000000 00c78094 fdffff00 ................ - 0bd0 000000c5 fa11887c fdffffc5 fa118098 .......|........ - 0be0 fdffffc5 fa104bdc c5fa1188 9cfdffff ......K......... - 0bf0 c5fa104b e0c5fa11 88a0fdff ffc5fa10 ...K............ - 0c00 4be4c5fa 1188a4fd ffffc5fa 104be8c5 K............K.. - 0c10 fa1188a8 fdffffc5 fa104bec c5fa1188 ..........K..... /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 09080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 a8290000 00420e10 8f02420e .....)...B....B. + 0020 00000000 c6150000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e900303 e1230a0e ..A.8..G.....#.. + 0040 8606410e 38830747 0ec80203 b1100a0e ..A.8..G........ 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. 0060 440e0842 0b000000 D..B.... /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_SKYLAKEX.o (disasm) @@ -14,599 +14,466 @@ sub $something,%rsp mov %rsi,offset(%rsp) sar $something,%rsi - mov %rdi,(%rsp) + mov %rdi,offset(%rsp) mov %rdx,offset(%rsp) - mov %rcx,-offset(%rsp) + mov %rcx,offset(%rsp) mov %r8,-offset(%rsp) mov %r9,-offset(%rsp) mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov offset(%rsp),%rbp test %rsi,%rsi jle - mov %r8,%rbx - imul %rcx,%rbx - mov %r8,%rdi + mov %rcx,%rsi mov %rcx,%rax - lea (%rcx,%rbx,1),%r11 - lea (%r11,%rcx,1),%rsi - lea (%rcx,%rsi,1),%r9 - lea (%r9,%rcx,1),%r8 - mov %rsi,-offset(%rsp) - lea (%rcx,%r8,1),%rsi - mov %rsi,-offset(%rsp) - add %rcx,%rsi - lea (%rcx,%rsi,1),%rcx - lea (%rax,%rcx,1),%rdx - lea (%rax,%rdx,1),%rbp - lea (%rax,%rbp,1),%r12 - lea (%rax,%r12,1),%r13 - lea (%rax,%r13,1),%r14 - lea (%rax,%r14,1),%r10 - mov %r10,-offset(%rsp) - mov (%rsp),%r10 - sar $something,%r10 - mov %r10,-offset(%rsp) - lea offset(,%rax,4),%r10 - mov %r10,offset(%rsp) - mov (%rsp),%r10 + imul %r8,%rsi + mov %rdi,%r12 shl $something,%rax - and $something,%r10d - mov %r10,-offset(%rsp) - shl $something,%r10 + mov %rax,offset(%rsp) + mov %r12,%rax + mov %r9,%r14 + lea offset(,%rcx,8),%r15 + and $something,%eax mov %rax,-offset(%rsp) - mov %r10,offset(%rsp) - mov -offset(%rsp),%rax - mov offset(%rsp),%r10 - imul -offset(%rsp),%rax - shl $something,%r10 - add -offset(%rsp),%r10 - mov %r10,offset(%rsp) - mov offset(%rsp),%r10 - add %rdi,%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - inc %rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov %rdi,offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov %rdi,offset(%rsp) - mov -offset(%rsp),%rax - add $something,%rax - imul -offset(%rsp),%rax - add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add $something,%rax - imul -offset(%rsp),%rax + kmovq %r15,%k2 + lea (%r14,%rsi,1),%rax + mov %r14,%r15 + lea (%rdx,%rax,4),%r14 + mov %r15,%rax + imul %rcx,%rax + mov %r15,%rdx + mov offset(%rsp),%r15 add -offset(%rsp),%rax - lea (%r10,%rax,4),%rdi - mov -offset(%rsp),%rax - mov %rdi,offset(%rsp) - add %rax,%rbx - add %rax,%r11 - mov %r10,%rdi - lea (%r10,%rbx,4),%rbx - lea (%r10,%r11,4),%r11 - mov -offset(%rsp),%r10 - mov %rbx,offset(%rsp) - mov %rax,%rbx - add %rbx,%r10 - mov %r11,offset(%rsp) - add %rbx,%r9 - lea (%rdi,%r10,4),%r11 - add %rbx,%rcx - lea (%rdi,%rcx,4),%rcx - add %rbx,%rdx - mov %r11,offset(%rsp) - add %rbx,%r8 - lea (%rdi,%r9,4),%r11 - mov %r11,offset(%rsp) + lea (%r15,%rax,4),%r15 + mov offset(%rsp),%rax + lea (%rsi,%rcx,2),%rdi + lea (%rdi,%rcx,1),%r8 + lea (%rdx,%rax,8),%rax + lea (%r8,%rcx,1),%r9 + mov %rax,offset(%rsp) + mov %rcx,%rax + lea (%rcx,%r9,1),%r10 + neg %rax + lea (%rcx,%r10,1),%r11 + mov %rcx,%r13 + lea offset(,%rax,4),%rcx mov %rcx,offset(%rsp) - lea (%rdi,%r8,4),%r11 - lea (%rdi,%rdx,4),%rcx - add %rbx,%rbp - mov -offset(%rsp),%rdx - mov %r11,offset(%rsp) + mov %rcx,%rax /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_SKYLAKEX.o (objdump) @@ -2,670 +2,352 @@ /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ec580100 AWAVAUATUSH..X.. - 0010 00488974 241048c1 fe044889 3c244889 .H.t$.H...H.<$H. - 0020 54242048 894c24d8 4c894424 b04c894c T$ H.L$.L.D$.L.L - 0030 24c04889 b4243801 00004c8b bc249001 $.H..$8...L..$.. - 0040 00004885 f60f8e0e 1b00004c 89c3480f ..H........L..H. - 0050 afd94c89 c74889c8 4c8d1c19 498d340b ..L..H..L...I.4. - 0060 4c8d0c31 4d8d0409 48897424 984a8d34 L..1M...H.t$.J.4 - 0070 01488974 24884801 ce488d0c 31488d14 .H.t$.H..H..1H.. - 0080 08488d2c 104c8d24 284e8d2c 204e8d34 .H.,.L.$(N., N.4 - 0090 284e8d14 304c8954 24904c8b 142449c1 (N..0L.T$.L..$I. - 00a0 fa044c89 5424f84c 8d148500 0000004c ..L.T$.L.......L - 00b0 89942418 0100004c 8b142448 c1e00641 ..$....L..$H...A - 00c0 83e20f4c 895424d0 49c1e206 48894424 ...L.T$.I...H.D$ - 00d0 f04c8994 24300100 00488b44 24d84c8b .L..$0...H.D$.L. - 00e0 94243801 0000480f af4424c0 49c1e204 .$8...H..D$.I... - 00f0 4c035424 c04c8954 24084c8b 54242048 L.T$.L.T$.L.T$ H - 0100 01f8498d 3c82488b 4424c048 897c2430 ..I.<.H.D$.H.|$0 - 0110 48ffc048 0faf4424 d8480344 24b0498d H..H..D$.H.D$.I. - 0120 3c82488b 4424c048 897c2440 4883c002 <.H.D$.H.|$@H... - 0130 480faf44 24d84803 4424b049 8d3c8248 H..D$.H.D$.I.<.H - 0140 8b4424c0 48897c24 504883c0 03480faf .D$.H.|$PH...H.. - 0150 4424d848 034424b0 498d3c82 488b4424 D$.H.D$.I.<.H.D$ - 0160 c048897c 24604883 c004480f af4424d8 .H.|$`H...H..D$. - 0170 48034424 b0498d3c 8248897c 2470488b H.D$.I.<.H.|$pH. - 0180 4424c048 83c00548 0faf4424 d8480344 D$.H...H..D$.H.D - 0190 24b0498d 3c82488b 4424c048 89bc2480 $.I.<.H.D$.H..$. - 01a0 00000048 83c00648 0faf4424 d8480344 ...H...H..D$.H.D - 01b0 24b0498d 3c82488b 4424c048 89bc2490 $.I.<.H.D$.H..$. - 01c0 00000048 83c00748 0faf4424 d8480344 ...H...H..D$.H.D - 01d0 24b0498d 3c82488b 4424c048 89bc24a0 $.I.<.H.D$.H..$. - 01e0 00000048 83c00848 0faf4424 d8480344 ...H...H..D$.H.D - 01f0 24b0498d 3c82488b 4424c048 89bc24b0 $.I.<.H.D$.H..$. - 0200 00000048 83c00948 0faf4424 d8480344 ...H...H..D$.H.D - 0210 24b0498d 3c82488b 4424c048 89bc24c0 $.I.<.H.D$.H..$. - 0220 00000048 83c00a48 0faf4424 d8480344 ...H...H..D$.H.D - 0230 24b0498d 3c82488b 4424c048 89bc24d0 $.I.<.H.D$.H..$. - 0240 00000048 83c00b48 0faf4424 d8480344 ...H...H..D$.H.D - 0250 24b0498d 3c82488b 4424c048 89bc24e0 $.I.<.H.D$.H..$. - 0260 00000048 83c00c48 0faf4424 d8480344 ...H...H..D$.H.D - 0270 24b0498d 3c824889 bc24f000 0000488b $.I.<.H..$....H. - 0280 4424c048 83c00d48 0faf4424 d8480344 D$.H...H..D$.H.D - 0290 24b0498d 3c82488b 4424c048 89bc2400 $.I.<.H.D$.H..$. - 02a0 01000048 83c00e48 0faf4424 d8480344 ...H...H..D$.H.D - 02b0 24b0498d 3c82488b 4424c048 89bc2410 $.I.<.H.D$.H..$. - 02c0 01000048 01c34901 c34c89d7 498d1c9a ...H..I..L..I... - 02d0 4f8d1c9a 4c8b5424 9848895c 24284889 O...L.T$.H.\$(H. - 02e0 c34901da 4c895c24 384901d9 4e8d1c97 .I..L.\$8I..N... - 02f0 4801d948 8d0c8f48 01da4c89 5c244849 H..H...H..L.\$HI - 0300 01d84e8d 1c8f4c89 5c245848 898c2498 ..N...L.\$XH..$. - 0310 0000004e 8d1c8748 8d0c9748 01dd488b ...N...H...H..H. - 0320 5424904c 895c2468 48898c24 a8000000 T$.L.\$hH..$.... - 0330 4c8b5c24 88488d0c af4901dc 48898c24 L.\$.H...I..H..$ - 0340 b8000000 4901dd4a 8d0ca748 01de4889 ....I..J...H..H. - 0350 8c24c800 00004901 db4a8d0c af4901de .$....I..J...I.. - 0360 4889d04e 8d1c9f48 035424d8 48898c24 H..N...H.T$.H..$ - 0370 d8000000 4801d84a 8d0cb74c 895c2478 ....H..J...L.\$x - 0380 48898c24 e8000000 4c8d1cb7 488d0c87 H..$....L...H... - 0390 488b3424 4889d048 01d8488d 1487488b H.4$H..H..H...H. - 03a0 7c24b048 89f04883 e0f04801 f8488944 |$.H..H...H..H.D - 03b0 24c8488b 4424f848 89942408 01000048 $.H.D$.H..$....H - 03c0 89c248c1 e0044801 f848c1e2 0a4c899c ..H...H..H...L.. - 03d0 24880000 0048898c 24f80000 00488994 $....H..$....H.. - 03e0 24200100 00488984 24280100 004889f0 $ ...H..$(...H.. - 03f0 83e00e48 89842440 01000048 89f083e0 ...H..$@...H.... - 0400 0c83e608 48895c24 9048c744 24e80000 ....H.\$.H.D$... - 0410 000048c7 4424e000 00000048 89842448 ..H.D$.....H..$H - 0420 01000048 89b42450 010000c5 fa100500 ...H..$P........ - 0430 000000e9 03010000 0f1f8400 00000000 ................ - 0440 488b4424 e0488b8c 24d80000 00488b74 H.D$.H..$....H.t - 0450 24284801 c148894c 24b8488b 8c24e800 $(H..H.L$.H..$.. - 0460 0000488b 7c243848 01c14889 4c24984c ..H.|$8H..H.L$.L - 0470 8b442448 4c8b4c24 584c8b54 24684c8b .D$HL.L$XL.T$hL. - 0480 5c247848 8b9c2488 00000048 8bac2498 \$xH..$....H..$. - 0490 0000004c 8ba424a8 0000004c 8bac24b8 ...L..$....L..$. - 04a0 0000004c 8bb424c8 00000048 8b8c24f8 ...L..$....H..$. - 04b0 00000048 01c64801 c14801c7 4901c049 ...H..H..H..I..I - 04c0 01c14901 c24901c3 4801c348 01c54901 ..I..I..H..H..I. - 04d0 c44901c5 4901c648 03842408 01000048 .I..I..H..$....H - 04e0 837c24f8 00488944 24a84889 4c24a048 .|$..H.D$.H.L$.H - 04f0 8b4424b0 0f8f0e01 00004883 7c24d000 .D$.......H.|$.. - 0500 74134839 4424900f 8d6b0e00 004c03bc t.H9D$...k...L.. - 0510 24300100 00488344 24901048 8b7c24f0 $0...H.D$..H.|$. - 0520 48834424 e0404801 7c24e848 8b442490 H.D$.@H.|$.H.D$. - 0530 483b4424 080f8405 16000048 8b5c24b0 H;D$.......H.\$. - 0540 48395c24 900f8df5 feffff48 8b4424e8 H9\$.......H.D$. - 0550 488b8c24 e0000000 488b7424 304801c1 H..$....H.t$0H.. - 0560 48894c24 b8488b8c 24f00000 00488b7c H.L$.H..$....H.| - 0570 24404801 c148894c 24984c8b 4424504c $@H..H.L$.L.D$PL - 0580 8b4c2460 4c8b5424 704c8b9c 24800000 .L$`L.T$pL..$... - 0590 00488b9c 24900000 00488bac 24a00000 .H..$....H..$... - 05a0 004c8ba4 24b00000 004c8bac 24c00000 .L..$....L..$... - 05b0 004c8bb4 24d00000 00488b8c 24000100 .L..$....H..$... - 05c0 004801c6 4801c148 01c74901 c04901c1 .H..H..H..I..I.. - 05d0 4901c249 01c34801 c34801c5 4901c449 I..I..H..H..I..I - 05e0 01c54901 c6480384 24100100 0048837c ..I..H..$....H.| - 05f0 24f80048 894424a8 48894c24 a0488b44 $..H.D$.H.L$.H.D - 0600 24b00f8e f2feffff 488b5424 b04c89bc $.......H.T$.L.. - 0610 24900100 00498d87 00040000 48895424 $....I......H.T$ - 0620 884c8b7c 24b8eb66 0f1f8400 00000000 .L.|$..f........ - 0630 48834424 98404883 4424a040 48834424 H.D$.@H.D$.@H.D$ - 0640 a8404883 c6404883 c7404983 c0404983 .@H..@H..@I..@I. - 0650 c1404983 c2404983 c3404883 c3404883 .@I..@I..@H..@H. - 0660 c5404983 c4404983 c5404983 c6404983 .@I..@I..@I..@I. - 0670 c7404883 44248810 48050004 0000488b .@H.D$..H.....H. - 0680 4c248848 3b4c24c8 0f84c20c 0000488d L$.H;L$.......H. - 0690 9000fcff ff488954 24b8488b 54248848 .....H.T$.H.T$.H - 06a0 39542490 7c8a0f8f 940b0000 c5fa1180 9T$.|........... - 06b0 00fcffff c5fa104e 044883c7 40c5fa11 .......N.H..@... - 06c0 8804fcff ffc5fa10 4e084983 c040c5fa ........N.I..@.. - 06d0 118808fc ffffc5fa 104e0c49 83c140c5 .........N.I..@. - 06e0 fa11880c fcffffc5 fa104e10 4983c240 ..........N.I..@ - 06f0 c5fa1188 10fcffff c5fa104e 144983c3 ...........N.I.. - 0700 40c5fa11 8814fcff ffc5fa10 4e184883 @...........N.H. - 0710 c340c5fa 118818fc ffffc5fa 104e1c48 .@...........N.H - 0720 83c540c5 fa11881c fcffffc5 fa104e20 ..@...........N - 0730 4983c440 c5fa1188 20fcffff c5fa104e I..@.... ......N - 0740 244983c5 40c5fa11 8824fcff ffc5fa10 $I..@....$...... - 0750 4e284983 c640c5fa 118828fc ffffc5fa N(I..@....(..... - 0760 104e2c49 83c740c5 fa11882c fcffffc5 .N,I..@....,.... - 0770 fa104e30 4883c640 c5fa1188 30fcffff ..N0H..@....0... - 0780 c5fa104e f4c5fa11 8834fcff ffc5fa10 ...N.....4...... - 0790 4ef8c5fa 118838fc ffffc5fa 104efcc7 N.....8......N.. - 07a0 8040fcff ff000000 00c5fa11 883cfcff .@...........<.. - 07b0 ffc5fa11 8044fcff ffc5fa10 4fc8c5fa .....D......O... - 07c0 118848fc ffffc5fa 104fccc5 fa11884c ..H......O.....L - 07d0 fcffffc5 fa104fd0 c5fa1188 50fcffff ......O.....P... - 07e0 c5fa104f d4c5fa11 8854fcff ffc5fa10 ...O.....T...... - 07f0 4fd8c5fa 118858fc ffffc5fa 104fdcc5 O.....X......O.. - 0800 fa11885c fcffffc5 fa104fe0 c5fa1188 ...\......O..... - 0810 60fcffff c5fa104f e4c5fa11 8864fcff `......O.....d.. - 0820 ffc5fa10 4fe8c5fa 118868fc ffffc5fa ....O.....h..... - 0830 104fecc5 fa11886c fcffffc5 fa104ff0 .O.....l......O. - 0840 c5fa1188 70fcffff c5fa104f f4c5fa11 ....p......O.... - 0850 8874fcff ffc5fa10 4ff8c5fa 118878fc .t......O.....x. - 0860 ffffc5fa 104ffcc7 8080fcff ff000000 .....O.......... - 0870 00c78084 fcffff00 000000c5 fa11887c ...............| - 0880 fcffffc5 fa118088 fcffffc4 c17a1048 .............z.H - 0890 ccc5fa11 888cfcff ffc4c17a 1048d0c5 ...........z.H.. - 08a0 fa118890 fcffffc4 c17a1048 d4c5fa11 .........z.H.... - 08b0 8894fcff ffc4c17a 1048d8c5 fa118898 .......z.H...... - 08c0 fcffffc4 c17a1048 dcc5fa11 889cfcff .....z.H........ - 08d0 ffc4c17a 1048e0c5 fa1188a0 fcffffc4 ...z.H.......... - 08e0 c17a1048 e4c5fa11 88a4fcff ffc4c17a .z.H...........z - 08f0 1048e8c5 fa1188a8 fcffffc4 c17a1048 .H...........z.H - 0900 ecc5fa11 88acfcff ffc4c17a 1048f0c5 ...........z.H.. - 0910 fa1188b0 fcffffc4 c17a1048 f4c5fa11 .........z.H.... - 0920 88b4fcff ffc4c17a 1048f8c5 fa1188b8 .......z.H...... - 0930 fcffffc4 c17a1048 fcc780c0 fcffff00 .....z.H........ - 0940 000000c7 80c4fcff ff000000 00c780c8 ................ - 0950 fcffff00 000000c5 fa1188bc fcffffc5 ................ - 0960 fa1180cc fcffffc4 c17a1049 d0c5fa11 .........z.I.... - 0970 88d0fcff ffc4c17a 1049d4c5 fa1188d4 .......z.I...... - 0980 fcffffc4 c17a1049 d8c5fa11 88d8fcff .....z.I........ - 0990 ffc4c17a 1049dcc5 fa1188dc fcffffc4 ...z.I.......... - 09a0 c17a1049 e0c5fa11 88e0fcff ffc4c17a .z.I...........z - 09b0 1049e4c5 fa1188e4 fcffffc4 c17a1049 .I...........z.I - 09c0 e8c5fa11 88e8fcff ffc4c17a 1049ecc5 ...........z.I.. - 09d0 fa1188ec fcffffc4 c17a1049 f0c5fa11 .........z.I.... - 09e0 88f0fcff ffc4c17a 1049f4c5 fa1188f4 .......z.I...... - 09f0 fcffffc4 c17a1049 f8c5fa11 88f8fcff .....z.I........ - 0a00 ffc4c17a 1049fcc7 8000fdff ff000000 ...z.I.......... - 0a10 00c78004 fdffff00 000000c7 8008fdff ................ - 0a20 ff000000 00c7800c fdffff00 000000c5 ................ - 0a30 fa1188fc fcffffc5 fa118010 fdffffc4 ................ - 0a40 c17a104a d4c5fa11 8814fdff ffc4c17a .z.J...........z - 0a50 104ad8c5 fa118818 fdffffc4 c17a104a .J...........z.J - 0a60 dcc5fa11 881cfdff ffc4c17a 104ae0c5 ...........z.J.. - 0a70 fa118820 fdffffc4 c17a104a e4c5fa11 ... .....z.J.... - 0a80 8824fdff ffc4c17a 104ae8c5 fa118828 .$.....z.J.....( - 0a90 fdffffc4 c17a104a ecc5fa11 882cfdff .....z.J.....,.. - 0aa0 ffc4c17a 104af0c5 fa118830 fdffffc4 ...z.J.....0.... - 0ab0 c17a104a f4c5fa11 8834fdff ffc4c17a .z.J.....4.....z - 0ac0 104af8c5 fa118838 fdffffc4 c17a104a .J.....8.....z.J - 0ad0 fcc78040 fdffff00 000000c7 8044fdff ...@.........D.. - 0ae0 ff000000 00c78048 fdffff00 000000c7 .......H........ - 0af0 804cfdff ff000000 00c78050 fdffff00 .L.........P.... - 0b00 000000c5 fa11883c fdffffc5 fa118054 .......<.......T - 0b10 fdffffc4 c17a104b d8c5fa11 8858fdff .....z.K.....X.. - 0b20 ffc4c17a 104bdcc5 fa11885c fdffffc4 ...z.K.....\.... - 0b30 c17a104b e0c5fa11 8860fdff ffc4c17a .z.K.....`.....z - 0b40 104be4c5 fa118864 fdffffc4 c17a104b .K.....d.....z.K - 0b50 e8c5fa11 8868fdff ffc4c17a 104becc5 .....h.....z.K.. - 0b60 fa11886c fdffffc4 c17a104b f0c5fa11 ...l.....z.K.... - 0b70 8870fdff ffc4c17a 104bf4c5 fa118874 .p.....z.K.....t - 0b80 fdffffc4 c17a104b f8c5fa11 8878fdff .....z.K.....x.. - 0b90 ffc4c17a 104bfcc7 8080fdff ff000000 ...z.K.......... - 0ba0 00c78084 fdffff00 000000c7 8088fdff ................ - 0bb0 ff000000 00c7808c fdffff00 000000c7 ................ - 0bc0 8090fdff ff000000 00c78094 fdffff00 ................ - 0bd0 000000c5 fa11887c fdffffc5 fa118098 .......|........ - 0be0 fdffffc5 fa104bdc c5fa1188 9cfdffff ......K......... - 0bf0 c5fa104b e0c5fa11 88a0fdff ffc5fa10 ...K............ - 0c00 4be4c5fa 1188a4fd ffffc5fa 104be8c5 K............K.. - 0c10 fa1188a8 fdffffc5 fa104bec c5fa1188 ..........K..... /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 09080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iltucopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 a8290000 00420e10 8f02420e .....)...B....B. + 0020 00000000 c6150000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e900303 e1230a0e ..A.8..G.....#.. + 0040 8606410e 38830747 0ec80203 b1100a0e ..A.8..G........ 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. 0060 440e0842 0b000000 D..B.... /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_COOPERLAKE.o (disasm) @@ -17,1195 +17,699 @@ mov %rdi,offset(%rsp) mov %rdx,offset(%rsp) mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) + mov %r8,-offset(%rsp) mov %r9,offset(%rsp) mov %rsi,offset(%rsp) + mov offset(%rsp),%r14 test %rsi,%rsi jle - mov %rdi,%rax - sar $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax + mov %rdi,%r11 + mov %r9,%r10 + mov %rcx,%rax + mov %rdi,%rbx + and $something,%edi + mov %rcx,%rbp + imul %r8,%rax + mov %rdi,offset(%rsp) + mov %r10,%rdi + imul %rbp,%rdi mov %r8,%r12 - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - imul %rcx,%r12 - and $something,%eax - mov %rax,offset(%rsp) - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - shl $something,%rax - lea (%rcx,%rbx,1),%r11 - add offset(%rsp),%rax - lea (%rcx,%r11,1),%r10 - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%r10,%rcx,1),%r9 - add offset(%rsp),%r12 - lea (%r9,%rcx,1),%r8 - lea (%rax,%r12,4),%r12 - lea (%r8,%rcx,1),%rdi - mov %r12,offset(%rsp) - mov offset(%rsp),%r12 - lea (%rdi,%rcx,1),%rsi - mov %rcx,%r13 - add %r12,%rbp + lea (%rax,%rcx,2),%rsi + mov %rax,%r8 + mov %rdx,%r13 lea (%rsi,%rcx,1),%rcx - lea (%rcx,%r13,1),%rdx - lea (%rax,%rbp,4),%rbp - lea (%rdx,%r13,1),%r15 - mov %rbp,offset(%rsp) - mov %r12,%rbp - mov %r15,-offset(%rsp) - add %rbp,%r11 - lea (%rax,%r11,4),%r11 - add %rbp,%rsi - add %rbp,%r9 - add %r12,%rbx - lea (%rax,%r9,4),%r9 - add %rbp,%rcx - mov %r11,offset(%rsp) - add %rbp,%r10 - lea (%rax,%rsi,4),%r11 - add %rbp,%r8 - add %rbp,%rdi - add %rbp,%rdx - mov %rax,%r12 - lea (%rax,%rbx,4),%rbx - lea (%rax,%rdx,4),%rdx - mov %r9,offset(%rsp) - mov %r11,offset(%rsp) - lea (%rax,%r10,4),%r10 - lea (%rax,%rcx,4),%r11 - lea (%rax,%r8,4),%r9 - lea (%rax,%rdi,4),%rdi - mov -offset(%rsp),%rax - lea (%r15,%r13,1),%r14 - add %rbp,%rax - lea (%r14,%r13,1),%r15 - mov %rdx,offset(%rsp) - add %rbp,%r14 - lea (%r12,%rax,4),%rdx - mov offset(%rsp),%rsi - add %r15,%r13 - mov %rdx,offset(%rsp) - add %rbp,%r15 - lea (%r12,%r14,4),%rdx - mov %rdx,offset(%rsp) - lea offset(%rbp,%r13,1),%rax - lea (%r12,%r15,4),%rdx - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx - lea offset(%r13,%rsi,1),%rax - add %rbp,%rax - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx - mov %rbp,%rax - imul %rsi,%rax - mov offset(%rsp),%rcx - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rbx,offset(%rsp) + add %r12,%rdi + sub %r8,%rsi + lea (%rcx,%rbp,1),%rdx + mov %r13,%r12 + shl $something,%rsi + sub %r8,%rcx + lea offset(%r13,%rdi,4),%r13 + lea (%r10,%r8,1),%rdi + lea offset(%rbp,%rdx,1),%rax + lea (%r12,%rdi,4),%r12 + mov %rsi,offset(%rsp) + mov %r10,%rdi + lea offset(,%rcx,4),%rsi + mov offset(%rsp),%r10 + sub %r8,%rdx + lea offset(%rbp,%rax,1),%r9 + mov %rsi,offset(%rsp) + sub %r8,%rax + lea offset(,%rdx,4),%rsi + lea (%rdi,%r10,8),%r10 + mov %rsi,offset(%rsp) + lea offset(,%rax,4),%rsi mov %r10,offset(%rsp) - add %rcx,%rax - mov %r9,offset(%rsp) - mov %rdi,offset(%rsp) - mov %r11,offset(%rsp) - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rbp,%r10 + mov %r9,%rsi + lea (%r10,%r9,1),%rax + sub %r8,%rsi + mov %rbp,%r15 + lea offset(,%rsi,4),%rsi + lea offset(,%rbp,4),%rbp + sub %r8,%rax + mov %rsi,offset(%rsp) + lea offset(,%rax,4),%rsi + mov %rbp,%rax + mov %rsi,offset(%rsp) + lea offset(%rdi),%rdx + mov %rbp,%rsi + neg %rax + imul %rdi,%rax + imul %rsi,%rdx mov %rbp,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_COOPERLAKE.o (objdump) @@ -2,886 +2,454 @@ /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 044889bc .H..$....H...H.. - 0020 24800000 00488994 24a00000 0048898c $....H..$....H.. - 0030 24900000 004c8944 24404c89 4c246048 $....L.D$@L.L$`H - 0040 89b424c0 01000048 85f60f8e 9e170000 ..$....H........ - 0050 4889f848 c1f80448 89442478 488b8424 H..H...H.D$xH..$ - 0060 90000000 4d89c448 c1e00648 89442448 ....M..H...H.D$H - 0070 488b8424 80000000 4c0fafe1 83e00f48 H..$....L......H - 0080 89442458 48c1e006 48898424 b8010000 .D$XH...H..$.... - 0090 488b8424 c0010000 4a8d2c21 488d1c29 H..$....J.,!H..) - 00a0 48c1e004 4c8d1c19 48034424 604e8d14 H...L...H.D$`N.. - 00b0 19488984 24880000 00488b84 24a00000 .H..$....H..$... - 00c0 004d8d0c 0a4c0364 24604d8d 04094e8d .M...L.d$`M...N. - 00d0 24a0498d 3c084c89 a424f800 00004c8b $.I.<.L..$....L. - 00e0 64246048 8d340f49 89cd4c01 e5488d0c d$`H.4.I..L..H.. - 00f0 0e4a8d14 29488d2c a84e8d3c 2a4889ac .J..)H.,.N.<*H.. - 0100 24e00000 004c89e5 4c897c24 884901eb $....L..L.|$.I.. - 0110 4e8d1c98 4801ee49 01e94c01 e34e8d0c N...H..I..L..N.. - 0120 884801e9 4c899c24 e8000000 4901ea4c .H..L..$....I..L - 0130 8d1cb049 01e84801 ef4801ea 4989c448 ...I..H..H..I..H - 0140 8d1c9848 8d14904c 898c24b8 0000004c ...H...L..$....L - 0150 899c2430 0100004e 8d14904c 8d1c884e ..$0...N...L...N - 0160 8d0c8048 8d3cb848 8b442488 4f8d342f ...H.<.H.D$.O.4/ - 0170 4801e84f 8d3c2e48 89942450 01000049 H..O.<.H..$P...I - 0180 01ee498d 1484488b b4249000 00004d01 ..I...H..$....M. - 0190 fd488994 24600100 004901ef 4b8d14b4 .H..$`...I..K... - 01a0 48899424 70010000 4a8d442d 004b8d14 H..$p...J.D-.K.. - 01b0 bc488994 24800100 00498d14 84498d44 .H..$....I...I.D - 01c0 35004801 e8488994 24900100 00498d14 5.H..H..$....I.. - 01d0 844889e8 480fafc6 488b4c24 40488994 .H..H...H.L$@H.. - 01e0 24a00100 004801c8 498d1484 488d4501 $....H..I...H.E. - 01f0 480fafc6 48899c24 d8000000 4c899424 H...H..$....L..$ - 0200 18010000 4801c84c 898c24c8 00000048 ....H..L..$....H - 0210 89bc2420 0100004c 899c2440 01000048 ..$ ...L..$@...H - 0220 89942410 01000049 8d148448 8d450248 ..$....I...H.E.H - 0230 0fafc648 89942408 01000048 896c2430 ...H..$....H.l$0 - 0240 4801c849 8d148448 8d450348 0fafc648 H..I...H.E.H...H - 0250 89942400 01000048 c7442470 00000000 ..$....H.D$p.... - 0260 4801c849 8d148448 8d450448 0fafc648 H..I...H.E.H...H - 0270 899424b0 00000048 c7442468 00000000 ..$....H.D$h.... - 0280 4801c849 8d148448 8d450548 0fafc648 H..I...H.E.H...H - 0290 899424c0 00000048 01c8498d 1484488d ..$....H..I...H. - 02a0 4506480f afc64889 9424d000 00004801 E.H...H..$....H. - 02b0 c8498d14 84488d45 07480faf c6488994 .I...H.E.H...H.. - 02c0 24f00000 004801c8 498d1484 488d4508 $....H..I...H.E. - 02d0 480fafc6 48899424 a8000000 4801c849 H...H..$....H..I - 02e0 8d148448 8d450948 0fafc648 89942428 ...H.E.H...H..$( - 02f0 01000048 01c8498d 1484488d 450a480f ...H..I...H.E.H. - 0300 afc64889 94243801 00004801 c8498d14 ..H..$8...H..I.. - 0310 84488d45 0b480faf c6488994 24480100 .H.E.H...H..$H.. - 0320 004801c8 498d1484 488d450c 480fafc6 .H..I...H.E.H... - 0330 48899424 58010000 4801c849 8d148448 H..$X...H..I...H - 0340 8d450d48 0fafc648 89942468 01000048 .E.H...H..$h...H - 0350 01c8498d 1484488d 450e480f afc64889 ..I...H.E.H...H. - 0360 94247801 00004801 c8498d14 84488d45 .$x...H..I...H.E - 0370 0f480faf c6488bb4 24800000 00488994 .H...H..$....H.. - 0380 24880100 004801c8 498d1c84 48899c24 $....H..I...H..$ - 0390 98010000 4889f348 8b442478 4883e3f0 ....H..H.D$xH... - 03a0 4801cb48 895c2450 4889c348 c1e00448 H..H.\$PH..H...H - 03b0 01c84889 8424b001 00004889 f083e00e ..H..$....H..... - 03c0 48898424 c8010000 4889f048 c1e30a83 H..$....H..H.... - 03d0 e00c83e6 0848899c 24a80100 00488984 .....H..$....H.. - 03e0 24d00100 004889b4 24d80100 00e96f01 $....H..$.....o. - 03f0 0000660f 1f440000 488b4424 68488b9c ..f..D..H.D$hH.. - 0400 24100100 00488bb4 24b00000 004801c3 $....H..$....H.. - 0410 48895c24 28488b9c 24080100 004801c6 H.\$(H..$....H.. - 0420 4801c348 895c2420 488b9c24 00010000 H..H.\$ H..$.... - 0430 48897424 084801c3 48895c24 18488b9c H.t$.H..H.\$.H.. - 0440 24c00000 00488bbc 24480100 004801c3 $....H..$H...H.. - 0450 48895c24 10488b9c 24d00000 00488bb4 H.\$.H..$....H.. - 0460 24580100 004801c3 48891c24 488b9c24 $X...H..H..$H..$ - 0470 f0000000 4801c748 01c34889 5c24e848 ....H..H..H.\$.H - 0480 8b9c24a8 00000048 01c64801 c348895c ..$....H..H..H.\ - 0490 24e0488b 9c242801 00004889 7c24c848 $.H..$(...H.|$.H - 04a0 01c34889 5c24d848 8b9c2438 01000048 ..H.\$.H..$8...H - 04b0 897424c0 4801c348 895c24d0 488bbc24 .t$.H..H.\$.H..$ - 04c0 78010000 488b9c24 68010000 488bb424 x...H..$h...H..$ - 04d0 88010000 4801c348 01c74801 c6480384 ....H..H..H..H.. - 04e0 24980100 0048895c 24b84889 7c24b048 $....H.\$.H.|$.H - 04f0 897424a8 48894424 3848837c 24780048 .t$.H.D$8H.|$x.H - 0500 8b442440 0f8f7901 00004883 7c245800 .D$@..y...H.|$X. - 0510 74264839 4424300f 8f662a00 000f8d6d t&H9D$0..f*....m - 0520 1c000048 8b8424b8 01000048 01842418 ...H..$....H..$. - 0530 0200000f 1f440000 48834424 3010488b .....D..H.D$0.H. - 0540 7c244848 83442470 4048017c 2468488b |$HH.D$p@H.|$hH. - 0550 44243048 3b842488 0000000f 84741200 D$0H;.$......t.. - 0560 00488b7c 24404839 7c24300f 8d87feff .H.|$@H9|$0..... - 0570 ff488b44 2470488b bc24e000 0000488b .H.D$pH..$....H. - 0580 b424f800 00004801 c748897c 2420488b .$....H..H.|$ H. - 0590 bc241801 00004801 c64801c7 48897424 .$....H..H..H.t$ - 05a0 2848897c 2410488b b424e800 0000488b (H.|$.H..$....H. - 05b0 bc24b800 00004801 c64801c7 48897424 .$....H..H..H.t$ - 05c0 0848893c 24488bb4 24200100 00488bbc .H.<$H..$ ...H.. - 05d0 24300100 004801c6 4801c748 897424e0 $0...H..H..H.t$. - 05e0 48897c24 d8488bb4 24400100 00488bbc H.|$.H..$@...H.. - 05f0 24500100 004801c6 4801c748 897424d0 $P...H..H..H.t$. - 0600 48897c24 c8488b9c 24d80000 00488bb4 H.|$.H..$....H.. - 0610 24600100 00488bbc 24700100 004801c3 $`...H..$p...H.. - 0620 4801c648 01c74889 5c241848 897424c0 H..H..H.\$.H.t$. - 0630 48897c24 b8488b9c 24c80000 00488bb4 H.|$.H..$....H.. - 0640 24800100 00488bbc 24900100 004801c3 $....H..$....H.. - 0650 4801c648 01c74803 8424a001 00004889 H..H..H..$....H. - 0660 5c24e848 897424b0 48897c24 a8488944 \$.H.t$.H.|$.H.D - 0670 24384883 7c247800 488b4424 400f8e87 $8H.|$x.H.D$@... - 0680 feffff48 8b842418 02000048 8d900004 ...H..$....H.... - 0690 0000488b 44244048 894424f8 e9060e00 ..H.D$@H.D$..... - 06a0 000f1f80 00000000 488b4c24 28c5fa10 ........H.L$(... - 06b0 01488b4c 2420c5fa 118200fc ffffc5fa .H.L$ .......... - 06c0 1001488b 4c2418c5 fa118204 fcffffc5 ..H.L$.......... - 06d0 fa100148 8b4c2408 c5fa1182 08fcffff ...H.L$......... - 06e0 c5fa1001 488b4c24 10c5fa11 820cfcff ....H.L$........ - 06f0 ffc5fa10 01488b0c 24c5fa11 8210fcff .....H..$....... - 0700 ffc5fa10 01488b4c 24e8c5fa 118214fc .....H.L$....... - 0710 ffffc5fa 1001488b 4c24e0c5 fa118218 ......H.L$...... - 0720 fcffffc5 fa100148 8b4c24d8 c5fa1182 .......H.L$..... - 0730 1cfcffff c5fa1001 488b4c24 d0c5fa11 ........H.L$.... - 0740 8220fcff ffc5fa10 01488b4c 24c8c5fa . .......H.L$... - 0750 118224fc ffffc5fa 1001c5fa 118228fc ..$...........(. - 0760 ffff488b 4c24c048 8b442438 c5fa1001 ..H.L$.H.D$8.... - 0770 488b4c24 b8c5fa11 822cfcff ffc5fa10 H.L$.....,...... - 0780 01488b4c 24b0c5fa 118230fc ffffc5fa .H.L$.....0..... - 0790 1001488b 4c24a8c5 fa118234 fcffffc5 ..H.L$.....4.... - 07a0 fa100148 8b4c2420 c5fa1182 38fcffff ...H.L$ ....8... - 07b0 c5fa1000 c78240fc ffff0000 0000c5fa ......@......... - 07c0 11823cfc ffffc5fa 10410448 8b4c2418 ..<......A.H.L$. - 07d0 c5fa1182 44fcffff c5fa1041 04488b4c ....D......A.H.L - 07e0 2408c5fa 118248fc ffffc5fa 10410448 $.....H......A.H - 07f0 8b4c2410 c5fa1182 4cfcffff c5fa1041 .L$.....L......A - 0800 04488b0c 24c5fa11 8250fcff ffc5fa10 .H..$....P...... - 0810 4104488b 4c24e8c5 fa118254 fcffffc5 A.H.L$.....T.... - 0820 fa104104 488b4c24 e0c5fa11 8258fcff ..A.H.L$.....X.. - 0830 ffc5fa10 4104488b 4c24d8c5 fa11825c ....A.H.L$.....\ - 0840 fcffffc5 fa104104 488b4c24 d0c5fa11 ......A.H.L$.... - 0850 8260fcff ffc5fa10 4104488b 4c24c8c5 .`......A.H.L$.. - 0860 fa118264 fcffffc5 fa104104 488b4c24 ...d......A.H.L$ - 0870 c0c5fa11 8268fcff ffc5fa10 4104488b .....h......A.H. - 0880 4c24b8c5 fa11826c fcffffc5 fa104104 L$.....l......A. - 0890 488b4c24 b0c5fa11 8270fcff ffc5fa10 H.L$.....p...... - 08a0 4104488b 4c24a8c5 fa118274 fcffffc5 A.H.L$.....t.... - 08b0 fa104104 488b4c24 18c5fa11 8278fcff ..A.H.L$.....x.. - 08c0 ffc5fa10 4004c782 80fcffff 00000000 ....@........... - 08d0 c78284fc ffff0000 0000c5fa 11827cfc ..............|. - 08e0 ffffc5fa 104108c5 fa118288 fcffff48 .....A.........H - 08f0 8b4c2408 c5fa1041 08488b4c 2410c5fa .L$....A.H.L$... - 0900 11828cfc ffffc5fa 10410848 8b0c24c5 .........A.H..$. - 0910 fa118290 fcffffc5 fa104108 488b4c24 ..........A.H.L$ - 0920 e8c5fa11 8294fcff ffc5fa10 4108488b ............A.H. - 0930 4c24e0c5 fa118298 fcffffc5 fa104108 L$............A. - 0940 488b4c24 d8c5fa11 829cfcff ffc5fa10 H.L$............ - 0950 4108488b 4c24d0c5 fa1182a0 fcffffc5 A.H.L$.......... - 0960 fa104108 488b4c24 c8c5fa11 82a4fcff ..A.H.L$........ - 0970 ffc5fa10 4108488b 4c24c0c5 fa1182a8 ....A.H.L$...... - 0980 fcffffc5 fa104108 488b4c24 b8c5fa11 ......A.H.L$.... - 0990 82acfcff ffc5fa10 4108488b 4c24b0c5 ........A.H.L$.. - 09a0 fa1182b0 fcffffc5 fa104108 c5fa1182 ..........A..... - 09b0 b4fcffff 488b4c24 a8c5fa10 4108488b ....H.L$....A.H. - 09c0 4c2408c5 fa1182b8 fcffffc5 fa104008 L$............@. - 09d0 c782c0fc ffff0000 0000c782 c4fcffff ................ - 09e0 00000000 c782c8fc ffff0000 0000c5fa ................ - 09f0 1182bcfc ffffc5fa 10410c48 8b4c2410 .........A.H.L$. - 0a00 c5fa1182 ccfcffff c5fa1041 0c488b0c ...........A.H.. - 0a10 24c5fa11 82d0fcff ffc5fa10 410c488b $...........A.H. - 0a20 4c24e8c5 fa1182d4 fcffffc5 fa10410c L$............A. - 0a30 488b4c24 e0c5fa11 82d8fcff ffc5fa10 H.L$............ - 0a40 410c488b 4c24d8c5 fa1182dc fcffffc5 A.H.L$.......... - 0a50 fa10410c 488b4c24 d0c5fa11 82e0fcff ..A.H.L$........ - 0a60 ffc5fa10 410c488b 4c24c8c5 fa1182e4 ....A.H.L$...... - 0a70 fcffffc5 fa10410c c5fa1182 e8fcffff ......A......... - 0a80 488b4c24 c0c5fa10 410c488b 4c24b8c5 H.L$....A.H.L$.. - 0a90 fa1182ec fcffffc5 fa10410c 488b4c24 ..........A.H.L$ - 0aa0 b0c5fa11 82f0fcff ffc5fa10 410c488b ............A.H. - 0ab0 4c24a8c5 fa1182f4 fcffffc5 fa10410c L$............A. - 0ac0 488b4c24 10c5fa11 82f8fcff ffc5fa10 H.L$............ - 0ad0 400cc782 00fdffff 00000000 c78204fd @............... - 0ae0 ffff0000 0000c782 08fdffff 00000000 ................ - 0af0 c7820cfd ffff0000 0000c5fa 1182fcfc ................ - 0b00 ffffc5fa 10411048 8b0c24c5 fa118210 .....A.H..$..... - 0b10 fdffffc5 fa104110 488b4c24 e8c5fa11 ......A.H.L$.... - 0b20 8214fdff ffc5fa10 4110488b 4c24e0c5 ........A.H.L$.. - 0b30 fa118218 fdffffc5 fa104110 488b4c24 ..........A.H.L$ - 0b40 d8c5fa11 821cfdff ffc5fa10 4110c5fa ............A... - 0b50 118220fd ffff488b 4c24d0c5 fa104110 .. ...H.L$....A. - 0b60 488b4c24 c8c5fa11 8224fdff ffc5fa10 H.L$.....$...... - 0b70 4110488b 4c24c0c5 fa118228 fdffffc5 A.H.L$.....(.... - 0b80 fa104110 488b4c24 b8c5fa11 822cfdff ..A.H.L$.....,.. - 0b90 ffc5fa10 4110488b 4c24b0c5 fa118230 ....A.H.L$.....0 - 0ba0 fdffffc5 fa104110 488b4c24 a8c5fa11 ......A.H.L$.... - 0bb0 8234fdff ffc5fa10 4110488b 0c24c5fa .4......A.H..$.. - 0bc0 118238fd ffffc5fa 104010c7 8240fdff ..8......@...@.. - 0bd0 ff000000 00c78244 fdffff00 000000c7 .......D........ - 0be0 8248fdff ff000000 00c7824c fdffff00 .H.........L.... - 0bf0 000000c7 8250fdff ff000000 00c5fa11 .....P.......... - 0c00 823cfdff ffc5fa10 4114488b 4c24e8c5 .<......A.H.L$.. - 0c10 fa118254 fdffffc5 fa104114 488b4c24 ...T......A.H.L$ /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39000000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 2e370000 00420e10 8f02420e .....7...B....B. + 0020 00000000 261c0000 00420e10 8f02420e ....&....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 71210a0e ..A.8..G....q!.. + 0040 8606410e 38830747 0ed80203 66160a0e ..A.8..G....f... 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0842 0b000000 D..B.... + 0060 440e0845 0b000000 D..E.... /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_SKYLAKEX.o (disasm) @@ -17,1195 +17,699 @@ mov %rdi,offset(%rsp) mov %rdx,offset(%rsp) mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) + mov %r8,-offset(%rsp) mov %r9,offset(%rsp) mov %rsi,offset(%rsp) + mov offset(%rsp),%r14 test %rsi,%rsi jle - mov %rdi,%rax - sar $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax + mov %rdi,%r11 + mov %r9,%r10 + mov %rcx,%rax + mov %rdi,%rbx + and $something,%edi + mov %rcx,%rbp + imul %r8,%rax + mov %rdi,offset(%rsp) + mov %r10,%rdi + imul %rbp,%rdi mov %r8,%r12 - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - imul %rcx,%r12 - and $something,%eax - mov %rax,offset(%rsp) - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - shl $something,%rax - lea (%rcx,%rbx,1),%r11 - add offset(%rsp),%rax - lea (%rcx,%r11,1),%r10 - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%r10,%rcx,1),%r9 - add offset(%rsp),%r12 - lea (%r9,%rcx,1),%r8 - lea (%rax,%r12,4),%r12 - lea (%r8,%rcx,1),%rdi - mov %r12,offset(%rsp) - mov offset(%rsp),%r12 - lea (%rdi,%rcx,1),%rsi - mov %rcx,%r13 - add %r12,%rbp + lea (%rax,%rcx,2),%rsi + mov %rax,%r8 + mov %rdx,%r13 lea (%rsi,%rcx,1),%rcx - lea (%rcx,%r13,1),%rdx - lea (%rax,%rbp,4),%rbp - lea (%rdx,%r13,1),%r15 - mov %rbp,offset(%rsp) - mov %r12,%rbp - mov %r15,-offset(%rsp) - add %rbp,%r11 - lea (%rax,%r11,4),%r11 - add %rbp,%rsi - add %rbp,%r9 - add %r12,%rbx - lea (%rax,%r9,4),%r9 - add %rbp,%rcx - mov %r11,offset(%rsp) - add %rbp,%r10 - lea (%rax,%rsi,4),%r11 - add %rbp,%r8 - add %rbp,%rdi - add %rbp,%rdx - mov %rax,%r12 - lea (%rax,%rbx,4),%rbx - lea (%rax,%rdx,4),%rdx - mov %r9,offset(%rsp) - mov %r11,offset(%rsp) - lea (%rax,%r10,4),%r10 - lea (%rax,%rcx,4),%r11 - lea (%rax,%r8,4),%r9 - lea (%rax,%rdi,4),%rdi - mov -offset(%rsp),%rax - lea (%r15,%r13,1),%r14 - add %rbp,%rax - lea (%r14,%r13,1),%r15 - mov %rdx,offset(%rsp) - add %rbp,%r14 - lea (%r12,%rax,4),%rdx - mov offset(%rsp),%rsi - add %r15,%r13 - mov %rdx,offset(%rsp) - add %rbp,%r15 - lea (%r12,%r14,4),%rdx - mov %rdx,offset(%rsp) - lea offset(%rbp,%r13,1),%rax - lea (%r12,%r15,4),%rdx - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx - lea offset(%r13,%rsi,1),%rax - add %rbp,%rax - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx - mov %rbp,%rax - imul %rsi,%rax - mov offset(%rsp),%rcx - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rbx,offset(%rsp) + add %r12,%rdi + sub %r8,%rsi + lea (%rcx,%rbp,1),%rdx + mov %r13,%r12 + shl $something,%rsi + sub %r8,%rcx + lea offset(%r13,%rdi,4),%r13 + lea (%r10,%r8,1),%rdi + lea offset(%rbp,%rdx,1),%rax + lea (%r12,%rdi,4),%r12 + mov %rsi,offset(%rsp) + mov %r10,%rdi + lea offset(,%rcx,4),%rsi + mov offset(%rsp),%r10 + sub %r8,%rdx + lea offset(%rbp,%rax,1),%r9 + mov %rsi,offset(%rsp) + sub %r8,%rax + lea offset(,%rdx,4),%rsi + lea (%rdi,%r10,8),%r10 + mov %rsi,offset(%rsp) + lea offset(,%rax,4),%rsi mov %r10,offset(%rsp) - add %rcx,%rax - mov %r9,offset(%rsp) - mov %rdi,offset(%rsp) - mov %r11,offset(%rsp) - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) + mov %rsi,offset(%rsp) + mov %rbp,%r10 + mov %r9,%rsi + lea (%r10,%r9,1),%rax + sub %r8,%rsi + mov %rbp,%r15 + lea offset(,%rsi,4),%rsi + lea offset(,%rbp,4),%rbp + sub %r8,%rax + mov %rsi,offset(%rsp) + lea offset(,%rax,4),%rsi + mov %rbp,%rax + mov %rsi,offset(%rsp) + lea offset(%rdi),%rdx + mov %rbp,%rsi + neg %rax + imul %rdi,%rax + imul %rsi,%rdx mov %rbp,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rdx,offset(%rsp) /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_SKYLAKEX.o (objdump) @@ -2,886 +2,454 @@ /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 044889bc .H..$....H...H.. - 0020 24800000 00488994 24a00000 0048898c $....H..$....H.. - 0030 24900000 004c8944 24404c89 4c246048 $....L.D$@L.L$`H - 0040 89b424c0 01000048 85f60f8e 9e170000 ..$....H........ - 0050 4889f848 c1f80448 89442478 488b8424 H..H...H.D$xH..$ - 0060 90000000 4d89c448 c1e00648 89442448 ....M..H...H.D$H - 0070 488b8424 80000000 4c0fafe1 83e00f48 H..$....L......H - 0080 89442458 48c1e006 48898424 b8010000 .D$XH...H..$.... - 0090 488b8424 c0010000 4a8d2c21 488d1c29 H..$....J.,!H..) - 00a0 48c1e004 4c8d1c19 48034424 604e8d14 H...L...H.D$`N.. - 00b0 19488984 24880000 00488b84 24a00000 .H..$....H..$... - 00c0 004d8d0c 0a4c0364 24604d8d 04094e8d .M...L.d$`M...N. - 00d0 24a0498d 3c084c89 a424f800 00004c8b $.I.<.L..$....L. - 00e0 64246048 8d340f49 89cd4c01 e5488d0c d$`H.4.I..L..H.. - 00f0 0e4a8d14 29488d2c a84e8d3c 2a4889ac .J..)H.,.N.<*H.. - 0100 24e00000 004c89e5 4c897c24 884901eb $....L..L.|$.I.. - 0110 4e8d1c98 4801ee49 01e94c01 e34e8d0c N...H..I..L..N.. - 0120 884801e9 4c899c24 e8000000 4901ea4c .H..L..$....I..L - 0130 8d1cb049 01e84801 ef4801ea 4989c448 ...I..H..H..I..H - 0140 8d1c9848 8d14904c 898c24b8 0000004c ...H...L..$....L - 0150 899c2430 0100004e 8d14904c 8d1c884e ..$0...N...L...N - 0160 8d0c8048 8d3cb848 8b442488 4f8d342f ...H.<.H.D$.O.4/ - 0170 4801e84f 8d3c2e48 89942450 01000049 H..O.<.H..$P...I - 0180 01ee498d 1484488b b4249000 00004d01 ..I...H..$....M. - 0190 fd488994 24600100 004901ef 4b8d14b4 .H..$`...I..K... - 01a0 48899424 70010000 4a8d442d 004b8d14 H..$p...J.D-.K.. - 01b0 bc488994 24800100 00498d14 84498d44 .H..$....I...I.D - 01c0 35004801 e8488994 24900100 00498d14 5.H..H..$....I.. - 01d0 844889e8 480fafc6 488b4c24 40488994 .H..H...H.L$@H.. - 01e0 24a00100 004801c8 498d1484 488d4501 $....H..I...H.E. - 01f0 480fafc6 48899c24 d8000000 4c899424 H...H..$....L..$ - 0200 18010000 4801c84c 898c24c8 00000048 ....H..L..$....H - 0210 89bc2420 0100004c 899c2440 01000048 ..$ ...L..$@...H - 0220 89942410 01000049 8d148448 8d450248 ..$....I...H.E.H - 0230 0fafc648 89942408 01000048 896c2430 ...H..$....H.l$0 - 0240 4801c849 8d148448 8d450348 0fafc648 H..I...H.E.H...H - 0250 89942400 01000048 c7442470 00000000 ..$....H.D$p.... - 0260 4801c849 8d148448 8d450448 0fafc648 H..I...H.E.H...H - 0270 899424b0 00000048 c7442468 00000000 ..$....H.D$h.... - 0280 4801c849 8d148448 8d450548 0fafc648 H..I...H.E.H...H - 0290 899424c0 00000048 01c8498d 1484488d ..$....H..I...H. - 02a0 4506480f afc64889 9424d000 00004801 E.H...H..$....H. - 02b0 c8498d14 84488d45 07480faf c6488994 .I...H.E.H...H.. - 02c0 24f00000 004801c8 498d1484 488d4508 $....H..I...H.E. - 02d0 480fafc6 48899424 a8000000 4801c849 H...H..$....H..I - 02e0 8d148448 8d450948 0fafc648 89942428 ...H.E.H...H..$( - 02f0 01000048 01c8498d 1484488d 450a480f ...H..I...H.E.H. - 0300 afc64889 94243801 00004801 c8498d14 ..H..$8...H..I.. - 0310 84488d45 0b480faf c6488994 24480100 .H.E.H...H..$H.. - 0320 004801c8 498d1484 488d450c 480fafc6 .H..I...H.E.H... - 0330 48899424 58010000 4801c849 8d148448 H..$X...H..I...H - 0340 8d450d48 0fafc648 89942468 01000048 .E.H...H..$h...H - 0350 01c8498d 1484488d 450e480f afc64889 ..I...H.E.H...H. - 0360 94247801 00004801 c8498d14 84488d45 .$x...H..I...H.E - 0370 0f480faf c6488bb4 24800000 00488994 .H...H..$....H.. - 0380 24880100 004801c8 498d1c84 48899c24 $....H..I...H..$ - 0390 98010000 4889f348 8b442478 4883e3f0 ....H..H.D$xH... - 03a0 4801cb48 895c2450 4889c348 c1e00448 H..H.\$PH..H...H - 03b0 01c84889 8424b001 00004889 f083e00e ..H..$....H..... - 03c0 48898424 c8010000 4889f048 c1e30a83 H..$....H..H.... - 03d0 e00c83e6 0848899c 24a80100 00488984 .....H..$....H.. - 03e0 24d00100 004889b4 24d80100 00e96f01 $....H..$.....o. - 03f0 0000660f 1f440000 488b4424 68488b9c ..f..D..H.D$hH.. - 0400 24100100 00488bb4 24b00000 004801c3 $....H..$....H.. - 0410 48895c24 28488b9c 24080100 004801c6 H.\$(H..$....H.. - 0420 4801c348 895c2420 488b9c24 00010000 H..H.\$ H..$.... - 0430 48897424 084801c3 48895c24 18488b9c H.t$.H..H.\$.H.. - 0440 24c00000 00488bbc 24480100 004801c3 $....H..$H...H.. - 0450 48895c24 10488b9c 24d00000 00488bb4 H.\$.H..$....H.. - 0460 24580100 004801c3 48891c24 488b9c24 $X...H..H..$H..$ - 0470 f0000000 4801c748 01c34889 5c24e848 ....H..H..H.\$.H - 0480 8b9c24a8 00000048 01c64801 c348895c ..$....H..H..H.\ - 0490 24e0488b 9c242801 00004889 7c24c848 $.H..$(...H.|$.H - 04a0 01c34889 5c24d848 8b9c2438 01000048 ..H.\$.H..$8...H - 04b0 897424c0 4801c348 895c24d0 488bbc24 .t$.H..H.\$.H..$ - 04c0 78010000 488b9c24 68010000 488bb424 x...H..$h...H..$ - 04d0 88010000 4801c348 01c74801 c6480384 ....H..H..H..H.. - 04e0 24980100 0048895c 24b84889 7c24b048 $....H.\$.H.|$.H - 04f0 897424a8 48894424 3848837c 24780048 .t$.H.D$8H.|$x.H - 0500 8b442440 0f8f7901 00004883 7c245800 .D$@..y...H.|$X. - 0510 74264839 4424300f 8f662a00 000f8d6d t&H9D$0..f*....m - 0520 1c000048 8b8424b8 01000048 01842418 ...H..$....H..$. - 0530 0200000f 1f440000 48834424 3010488b .....D..H.D$0.H. - 0540 7c244848 83442470 4048017c 2468488b |$HH.D$p@H.|$hH. - 0550 44243048 3b842488 0000000f 84741200 D$0H;.$......t.. - 0560 00488b7c 24404839 7c24300f 8d87feff .H.|$@H9|$0..... - 0570 ff488b44 2470488b bc24e000 0000488b .H.D$pH..$....H. - 0580 b424f800 00004801 c748897c 2420488b .$....H..H.|$ H. - 0590 bc241801 00004801 c64801c7 48897424 .$....H..H..H.t$ - 05a0 2848897c 2410488b b424e800 0000488b (H.|$.H..$....H. - 05b0 bc24b800 00004801 c64801c7 48897424 .$....H..H..H.t$ - 05c0 0848893c 24488bb4 24200100 00488bbc .H.<$H..$ ...H.. - 05d0 24300100 004801c6 4801c748 897424e0 $0...H..H..H.t$. - 05e0 48897c24 d8488bb4 24400100 00488bbc H.|$.H..$@...H.. - 05f0 24500100 004801c6 4801c748 897424d0 $P...H..H..H.t$. - 0600 48897c24 c8488b9c 24d80000 00488bb4 H.|$.H..$....H.. - 0610 24600100 00488bbc 24700100 004801c3 $`...H..$p...H.. - 0620 4801c648 01c74889 5c241848 897424c0 H..H..H.\$.H.t$. - 0630 48897c24 b8488b9c 24c80000 00488bb4 H.|$.H..$....H.. - 0640 24800100 00488bbc 24900100 004801c3 $....H..$....H.. - 0650 4801c648 01c74803 8424a001 00004889 H..H..H..$....H. - 0660 5c24e848 897424b0 48897c24 a8488944 \$.H.t$.H.|$.H.D - 0670 24384883 7c247800 488b4424 400f8e87 $8H.|$x.H.D$@... - 0680 feffff48 8b842418 02000048 8d900004 ...H..$....H.... - 0690 0000488b 44244048 894424f8 e9060e00 ..H.D$@H.D$..... - 06a0 000f1f80 00000000 488b4c24 28c5fa10 ........H.L$(... - 06b0 01488b4c 2420c5fa 118200fc ffffc5fa .H.L$ .......... - 06c0 1001488b 4c2418c5 fa118204 fcffffc5 ..H.L$.......... - 06d0 fa100148 8b4c2408 c5fa1182 08fcffff ...H.L$......... - 06e0 c5fa1001 488b4c24 10c5fa11 820cfcff ....H.L$........ - 06f0 ffc5fa10 01488b0c 24c5fa11 8210fcff .....H..$....... - 0700 ffc5fa10 01488b4c 24e8c5fa 118214fc .....H.L$....... - 0710 ffffc5fa 1001488b 4c24e0c5 fa118218 ......H.L$...... - 0720 fcffffc5 fa100148 8b4c24d8 c5fa1182 .......H.L$..... - 0730 1cfcffff c5fa1001 488b4c24 d0c5fa11 ........H.L$.... - 0740 8220fcff ffc5fa10 01488b4c 24c8c5fa . .......H.L$... - 0750 118224fc ffffc5fa 1001c5fa 118228fc ..$...........(. - 0760 ffff488b 4c24c048 8b442438 c5fa1001 ..H.L$.H.D$8.... - 0770 488b4c24 b8c5fa11 822cfcff ffc5fa10 H.L$.....,...... - 0780 01488b4c 24b0c5fa 118230fc ffffc5fa .H.L$.....0..... - 0790 1001488b 4c24a8c5 fa118234 fcffffc5 ..H.L$.....4.... - 07a0 fa100148 8b4c2420 c5fa1182 38fcffff ...H.L$ ....8... - 07b0 c5fa1000 c78240fc ffff0000 0000c5fa ......@......... - 07c0 11823cfc ffffc5fa 10410448 8b4c2418 ..<......A.H.L$. - 07d0 c5fa1182 44fcffff c5fa1041 04488b4c ....D......A.H.L - 07e0 2408c5fa 118248fc ffffc5fa 10410448 $.....H......A.H - 07f0 8b4c2410 c5fa1182 4cfcffff c5fa1041 .L$.....L......A - 0800 04488b0c 24c5fa11 8250fcff ffc5fa10 .H..$....P...... - 0810 4104488b 4c24e8c5 fa118254 fcffffc5 A.H.L$.....T.... - 0820 fa104104 488b4c24 e0c5fa11 8258fcff ..A.H.L$.....X.. - 0830 ffc5fa10 4104488b 4c24d8c5 fa11825c ....A.H.L$.....\ - 0840 fcffffc5 fa104104 488b4c24 d0c5fa11 ......A.H.L$.... - 0850 8260fcff ffc5fa10 4104488b 4c24c8c5 .`......A.H.L$.. - 0860 fa118264 fcffffc5 fa104104 488b4c24 ...d......A.H.L$ - 0870 c0c5fa11 8268fcff ffc5fa10 4104488b .....h......A.H. - 0880 4c24b8c5 fa11826c fcffffc5 fa104104 L$.....l......A. - 0890 488b4c24 b0c5fa11 8270fcff ffc5fa10 H.L$.....p...... - 08a0 4104488b 4c24a8c5 fa118274 fcffffc5 A.H.L$.....t.... - 08b0 fa104104 488b4c24 18c5fa11 8278fcff ..A.H.L$.....x.. - 08c0 ffc5fa10 4004c782 80fcffff 00000000 ....@........... - 08d0 c78284fc ffff0000 0000c5fa 11827cfc ..............|. - 08e0 ffffc5fa 104108c5 fa118288 fcffff48 .....A.........H - 08f0 8b4c2408 c5fa1041 08488b4c 2410c5fa .L$....A.H.L$... - 0900 11828cfc ffffc5fa 10410848 8b0c24c5 .........A.H..$. - 0910 fa118290 fcffffc5 fa104108 488b4c24 ..........A.H.L$ - 0920 e8c5fa11 8294fcff ffc5fa10 4108488b ............A.H. - 0930 4c24e0c5 fa118298 fcffffc5 fa104108 L$............A. - 0940 488b4c24 d8c5fa11 829cfcff ffc5fa10 H.L$............ - 0950 4108488b 4c24d0c5 fa1182a0 fcffffc5 A.H.L$.......... - 0960 fa104108 488b4c24 c8c5fa11 82a4fcff ..A.H.L$........ - 0970 ffc5fa10 4108488b 4c24c0c5 fa1182a8 ....A.H.L$...... - 0980 fcffffc5 fa104108 488b4c24 b8c5fa11 ......A.H.L$.... - 0990 82acfcff ffc5fa10 4108488b 4c24b0c5 ........A.H.L$.. - 09a0 fa1182b0 fcffffc5 fa104108 c5fa1182 ..........A..... - 09b0 b4fcffff 488b4c24 a8c5fa10 4108488b ....H.L$....A.H. - 09c0 4c2408c5 fa1182b8 fcffffc5 fa104008 L$............@. - 09d0 c782c0fc ffff0000 0000c782 c4fcffff ................ - 09e0 00000000 c782c8fc ffff0000 0000c5fa ................ - 09f0 1182bcfc ffffc5fa 10410c48 8b4c2410 .........A.H.L$. - 0a00 c5fa1182 ccfcffff c5fa1041 0c488b0c ...........A.H.. - 0a10 24c5fa11 82d0fcff ffc5fa10 410c488b $...........A.H. - 0a20 4c24e8c5 fa1182d4 fcffffc5 fa10410c L$............A. - 0a30 488b4c24 e0c5fa11 82d8fcff ffc5fa10 H.L$............ - 0a40 410c488b 4c24d8c5 fa1182dc fcffffc5 A.H.L$.......... - 0a50 fa10410c 488b4c24 d0c5fa11 82e0fcff ..A.H.L$........ - 0a60 ffc5fa10 410c488b 4c24c8c5 fa1182e4 ....A.H.L$...... - 0a70 fcffffc5 fa10410c c5fa1182 e8fcffff ......A......... - 0a80 488b4c24 c0c5fa10 410c488b 4c24b8c5 H.L$....A.H.L$.. - 0a90 fa1182ec fcffffc5 fa10410c 488b4c24 ..........A.H.L$ - 0aa0 b0c5fa11 82f0fcff ffc5fa10 410c488b ............A.H. - 0ab0 4c24a8c5 fa1182f4 fcffffc5 fa10410c L$............A. - 0ac0 488b4c24 10c5fa11 82f8fcff ffc5fa10 H.L$............ - 0ad0 400cc782 00fdffff 00000000 c78204fd @............... - 0ae0 ffff0000 0000c782 08fdffff 00000000 ................ - 0af0 c7820cfd ffff0000 0000c5fa 1182fcfc ................ - 0b00 ffffc5fa 10411048 8b0c24c5 fa118210 .....A.H..$..... - 0b10 fdffffc5 fa104110 488b4c24 e8c5fa11 ......A.H.L$.... - 0b20 8214fdff ffc5fa10 4110488b 4c24e0c5 ........A.H.L$.. - 0b30 fa118218 fdffffc5 fa104110 488b4c24 ..........A.H.L$ - 0b40 d8c5fa11 821cfdff ffc5fa10 4110c5fa ............A... - 0b50 118220fd ffff488b 4c24d0c5 fa104110 .. ...H.L$....A. - 0b60 488b4c24 c8c5fa11 8224fdff ffc5fa10 H.L$.....$...... - 0b70 4110488b 4c24c0c5 fa118228 fdffffc5 A.H.L$.....(.... - 0b80 fa104110 488b4c24 b8c5fa11 822cfdff ..A.H.L$.....,.. - 0b90 ffc5fa10 4110488b 4c24b0c5 fa118230 ....A.H.L$.....0 - 0ba0 fdffffc5 fa104110 488b4c24 a8c5fa11 ......A.H.L$.... - 0bb0 8234fdff ffc5fa10 4110488b 0c24c5fa .4......A.H..$.. - 0bc0 118238fd ffffc5fa 104010c7 8240fdff ..8......@...@.. - 0bd0 ff000000 00c78244 fdffff00 000000c7 .......D........ - 0be0 8248fdff ff000000 00c7824c fdffff00 .H.........L.... - 0bf0 000000c7 8250fdff ff000000 00c5fa11 .....P.......... - 0c00 823cfdff ffc5fa10 4114488b 4c24e8c5 .<......A.H.L$.. - 0c10 fa118254 fdffffc5 fa104114 488b4c24 ...T......A.H.L$ /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39000000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunncopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 2e370000 00420e10 8f02420e .....7...B....B. + 0020 00000000 261c0000 00420e10 8f02420e ....&....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 71210a0e ..A.8..G....q!.. + 0040 8606410e 38830747 0ed80203 66160a0e ..A.8..G....f... 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0842 0b000000 D..B.... + 0060 440e0845 0b000000 D..E.... /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_COOPERLAKE.o (disasm) @@ -17,1138 +17,675 @@ mov %rdi,offset(%rsp) mov %rdx,offset(%rsp) mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) + mov %r8,-offset(%rsp) mov %r9,offset(%rsp) mov %rsi,offset(%rsp) + mov offset(%rsp),%r13 test %rsi,%rsi jle - mov %rdi,%rax - sar $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax + mov %rdi,%r11 + mov %r9,%r10 + mov %rcx,%rax + mov %rdi,%rbx + and $something,%edi + mov %rcx,%rbp + imul %r8,%rax + mov %rdi,offset(%rsp) + mov %r10,%rdi + imul %rbp,%rdi mov %r8,%r12 - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - imul %rcx,%r12 - and $something,%eax - mov %rax,offset(%rsp) - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - shl $something,%rax - lea (%rcx,%rbx,1),%r11 - add offset(%rsp),%rax - lea (%rcx,%r11,1),%r10 - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%r10,%rcx,1),%r9 - add offset(%rsp),%r12 - lea (%r9,%rcx,1),%r8 - lea (%rax,%r12,4),%r12 - lea (%r8,%rcx,1),%rdi - mov %r12,offset(%rsp) - mov offset(%rsp),%r12 - lea (%rdi,%rcx,1),%rsi - mov %rcx,%r13 - add %r12,%rbp + lea (%rax,%rcx,2),%rsi + mov %rax,%r8 + mov %rdx,%r15 lea (%rsi,%rcx,1),%rcx - lea (%rcx,%r13,1),%rdx - lea (%rax,%rbp,4),%rbp - lea (%rdx,%r13,1),%r15 - mov %rbp,offset(%rsp) - mov %r12,%rbp - mov %r15,-offset(%rsp) - add %rbp,%r11 - lea (%rax,%r11,4),%r11 - add %rbp,%r9 - add %rbp,%r8 - add %r12,%rbx - lea (%rax,%r9,4),%r9 - add %rbp,%rdi - add %rbp,%rcx - mov %r11,offset(%rsp) - add %rbp,%r10 - lea (%rax,%r8,4),%r11 - add %rbp,%rsi - add %rbp,%rdx - mov %rax,%r12 - lea (%rax,%rsi,4),%rsi - lea (%rax,%rdx,4),%rdx - mov %r9,offset(%rsp) - mov %r11,offset(%rsp) - lea (%rax,%rcx,4),%r9 - lea (%rax,%rdi,4),%r11 - lea (%rax,%rbx,4),%rbx - lea (%rax,%r10,4),%r10 - mov -offset(%rsp),%rax - lea (%r15,%r13,1),%r14 - add %rbp,%rax - lea (%r14,%r13,1),%r15 - mov %rdx,offset(%rsp) - add %rbp,%r14 - lea (%r12,%rax,4),%rdx - mov offset(%rsp),%rdi - add %r15,%r13 - mov %rdx,offset(%rsp) - add %rbp,%r15 - lea (%r12,%r14,4),%rdx - mov %rdx,offset(%rsp) - lea offset(%rbp,%r13,1),%rax - lea (%r12,%r15,4),%rdx - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx - lea offset(%r13,%rdi,1),%rax - add %rbp,%rax - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx + add %r12,%rdi + lea offset(%rbp,%rcx,1),%rdx + mov %r15,%r12 + sub %r8,%rcx + lea (%r15,%rdi,4),%r15 + lea (%r10,%r8,1),%rdi + lea offset(%rbp,%rdx,1),%rax + lea (%r12,%rdi,4),%r12 + shl $something,%rcx + mov %r10,%rdi + sub %r8,%rdx + mov offset(%rsp),%r10 + lea (%rax,%rbp,1),%r9 + mov %rcx,offset(%rsp) + sub %r8,%rax + lea offset(,%rdx,4),%rcx + lea (%rdi,%r10,8),%r10 + mov %rcx,offset(%rsp) + lea offset(,%rax,4),%rcx + mov %r10,offset(%rsp) + mov %rcx,offset(%rsp) + mov %rbp,%r10 + mov %r9,%rcx + sub %r8,%rcx + lea (%r9,%r10,1),%rax + mov %rbp,%r14 + lea offset(,%rcx,4),%rcx + lea offset(,%rbp,4),%rbp + sub %r8,%rax + sub %r8,%rsi + mov %rcx,offset(%rsp) + shl $something,%rsi + lea offset(,%rax,4),%rcx mov %rbp,%rax - imul %rdi,%rax - mov offset(%rsp),%rcx - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax mov %rsi,offset(%rsp) - mov %rbx,offset(%rsp) - add %rcx,%rax - mov %r10,offset(%rsp) - mov %r11,offset(%rsp) - mov %r9,offset(%rsp) - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax + lea offset(%rdi),%rdx + mov %rbp,%rsi + neg %rax imul %rdi,%rax - mov %rdx,offset(%rsp) + imul %rsi,%rdx mov %rbp,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - vmovss offset(%rip),%xmm1 # - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_COOPERLAKE.o (objdump) @@ -2,851 +2,440 @@ /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 044889bc .H..$....H...H.. - 0020 24800000 00488994 24a00000 0048898c $....H..$....H.. - 0030 24900000 004c8944 24404c89 4c246048 $....L.D$@L.L$`H - 0040 89b424c0 01000048 85f60f8e ae160000 ..$....H........ - 0050 4889f848 c1f80448 89442478 488b8424 H..H...H.D$xH..$ - 0060 90000000 4d89c448 c1e00648 89442448 ....M..H...H.D$H - 0070 488b8424 80000000 4c0fafe1 83e00f48 H..$....L......H - 0080 89442458 48c1e006 48898424 b8010000 .D$XH...H..$.... - 0090 488b8424 c0010000 4a8d2c21 488d1c29 H..$....J.,!H..) - 00a0 48c1e004 4c8d1c19 48034424 604e8d14 H...L...H.D$`N.. - 00b0 19488984 24880000 00488b84 24a00000 .H..$....H..$... - 00c0 004d8d0c 0a4c0364 24604d8d 04094e8d .M...L.d$`M...N. - 00d0 24a0498d 3c084c89 a424d000 00004c8b $.I.<.L..$....L. - 00e0 64246048 8d340f49 89cd4c01 e5488d0c d$`H.4.I..L..H.. - 00f0 0e4a8d14 29488d2c a84e8d3c 2a4889ac .J..)H.,.N.<*H.. - 0100 24b80000 004c89e5 4c897c24 884901eb $....L..L.|$.I.. - 0110 4e8d1c98 4901e949 01e84c01 e34e8d0c N...I..I..L..N.. - 0120 884801ef 4801e94c 899c24e0 00000049 .H..H..L..$....I - 0130 01ea4e8d 1c804801 ee4801ea 4989c448 ..N...H..H..I..H - 0140 8d34b048 8d14904c 898c24b0 0000004c .4.H...L..$....L - 0150 899c2410 0100004c 8d0c884c 8d1cb848 ..$....L...L...H - 0160 8d1c984e 8d149048 8b442488 4f8d342f ...N...H.D$.O.4/ - 0170 4801e84f 8d3c2e48 89942450 01000049 H..O.<.H..$P...I - 0180 01ee498d 1484488b bc249000 00004d01 ..I...H..$....M. - 0190 fd488994 24600100 004901ef 4b8d14b4 .H..$`...I..K... - 01a0 48899424 70010000 4a8d442d 004b8d14 H..$p...J.D-.K.. - 01b0 bc488994 24800100 00498d14 84498d44 .H..$....I...I.D - 01c0 3d004801 e8488994 24900100 00498d14 =.H..H..$....I.. - 01d0 844889e8 480fafc7 488b4c24 40488994 .H..H...H.L$@H.. - 01e0 24a00100 004801c8 498d1484 488d4501 $....H..I...H.E. - 01f0 480fafc7 4889b424 30010000 48899c24 H...H..$0...H..$ - 0200 c8000000 4801c84c 899424f8 0000004c ....H..L..$....L - 0210 899c2420 0100004c 898c2440 01000048 ..$ ...L..$@...H - 0220 899424f0 00000049 8d148448 8d450248 ..$....I...H.E.H - 0230 0fafc748 899424d8 00000048 896c2428 ...H..$....H.l$( - 0240 4801c849 8d148448 8d450348 0fafc748 H..I...H.E.H...H - 0250 899424e8 00000048 c7442468 00000000 ..$....H.D$h.... - 0260 4801c849 8d148448 8d450448 0fafc748 H..I...H.E.H...H - 0270 89942400 01000048 c7442470 00000000 ..$....H.D$p.... - 0280 4801c849 8d148448 8d450548 0fafc748 H..I...H.E.H...H - 0290 899424a8 000000c5 fa100d00 00000048 ..$............H - 02a0 01c8498d 1484488d 4506480f afc74889 ..I...H.E.H...H. - 02b0 9424c000 00004801 c8498d14 84488d45 .$....H..I...H.E - 02c0 07480faf c7488994 24080100 004801c8 .H...H..$....H.. - 02d0 498d1484 488d4508 480fafc7 48899424 I...H.E.H...H..$ - 02e0 18010000 4801c849 8d148448 8d450948 ....H..I...H.E.H - 02f0 0fafc748 89942428 01000048 01c8498d ...H..$(...H..I. - 0300 1484488d 450a480f afc74889 94243801 ..H.E.H...H..$8. - 0310 00004801 c8498d14 84488d45 0b480faf ..H..I...H.E.H.. - 0320 c7488994 24480100 004801c8 498d1484 .H..$H...H..I... - 0330 488d450c 480fafc7 48899424 58010000 H.E.H...H..$X... - 0340 4801c849 8d148448 8d450d48 0fafc748 H..I...H.E.H...H - 0350 89942468 01000048 01c8498d 1484488d ..$h...H..I...H. - 0360 450e480f afc74889 94247801 00004801 E.H...H..$x...H. - 0370 c8498d14 84488d45 0f480faf c7488bbc .I...H.E.H...H.. - 0380 24800000 00488994 24880100 004801c8 $....H..$....H.. - 0390 498d3484 4889b424 98010000 4889fe48 I.4.H..$....H..H - 03a0 8b442478 4883e6f0 4801ce48 89742450 .D$xH...H..H.t$P - 03b0 4889c648 c1e00448 01c84889 8424b001 H..H...H..H..$.. - 03c0 00004889 f883e00e 48898424 c8010000 ..H.....H..$.... - 03d0 4889f848 c1e60a83 e00c83e7 084889b4 H..H.........H.. - 03e0 24a80100 00488984 24d00100 004889bc $....H..$....H.. - 03f0 24d80100 00e96f01 0000660f 1f440000 $.....o...f..D.. - 0400 488b4424 70488b9c 24e80000 00488bb4 H.D$pH..$....H.. - 0410 24f00000 004801c3 48895c24 18488b9c $....H..H.\$.H.. - 0420 24000100 004801c6 4801c348 895c2408 $....H..H..H.\$. - 0430 488b9c24 08010000 48897424 384801c3 H..$....H.t$8H.. - 0440 48895c24 f8488b9c 24180100 00488bbc H.\$.H..$....H.. - 0450 24d80000 004801c3 48895c24 e0488b9c $....H..H.\$.H.. - 0460 24280100 00488bb4 24a80000 004801c3 $(...H..$....H.. - 0470 48895c24 d8488b9c 24380100 004801c7 H.\$.H..$8...H.. - 0480 4801c348 895c24d0 488b9c24 48010000 H..H.\$.H..$H... - 0490 4801c648 01c34889 5c24c848 8b9c2458 H..H..H.\$.H..$X - 04a0 01000048 897c2420 4801c348 895c24c0 ...H.|$ H..H.\$. - 04b0 488b9c24 68010000 48897424 104801c3 H..$h...H.t$.H.. - 04c0 48895c24 b8488bbc 24c00000 00488bb4 H.\$.H..$....H.. - 04d0 24780100 00488b9c 24880100 004801c7 $x...H..$....H.. - 04e0 4801c648 01c34803 84249801 00004889 H..H..H..$....H. - 04f0 3c244889 7424b048 895c24a8 48894424 <$H.t$.H.\$.H.D$ - 0500 3048837c 24780048 8b442440 0f8f7901 0H.|$x.H.D$@..y. - 0510 00004883 7c245800 74264839 4424280f ..H.|$X.t&H9D$(. - 0520 8f542800 000f8d45 1b000048 8b8424b8 .T(....E...H..$. - 0530 01000048 01842418 0200000f 1f440000 ...H..$......D.. - 0540 48834424 2810488b 7c244848 83442468 H.D$(.H.|$HH.D$h - 0550 4048017c 2470488b 44242848 3b842488 @H.|$pH.D$(H;.$. - 0560 0000000f 847c1100 00488b5c 24404839 .....|...H.\$@H9 - 0570 5c24280f 8d87feff ff488b44 2468488b \$(......H.D$hH. - 0580 9c24d000 0000488b b424b800 0000488b .$....H..$....H. - 0590 bc24c800 00004801 c34801c6 4801c748 .$....H..H..H..H - 05a0 895c2438 48897424 2048897c 2418488b .\$8H.t$ H.|$.H. - 05b0 9c24e000 0000488b bc24f800 0000488b .$....H..$....H. - 05c0 b424b000 00004801 c34801c7 4801c648 .$....H..H..H..H - 05d0 895c2408 48897c24 10488934 24488b9c .\$.H.|$.H.4$H.. - 05e0 24200100 00488bb4 24100100 00488bbc $ ...H..$....H.. - 05f0 24300100 004801c6 4801c348 01c74889 $0...H..H..H..H. - 0600 7424f848 895c24e0 48897c24 d8488bb4 t$.H.\$.H.|$.H.. - 0610 24400100 00488b9c 24500100 00488bbc $@...H..$P...H.. - 0620 24600100 004801c6 4801c348 01c74889 $`...H..H..H..H. - 0630 7424d048 895c24c8 48897c24 c0488bb4 t$.H.\$.H.|$.H.. - 0640 24700100 00488b9c 24800100 00488bbc $p...H..$....H.. - 0650 24900100 004801c6 4801c348 01c74803 $....H..H..H..H. - 0660 8424a001 00004889 7424b848 895c24b0 .$....H.t$.H.\$. - 0670 48897c24 a8488944 24304883 7c247800 H.|$.H.D$0H.|$x. - 0680 488b4424 400f8e87 feffff48 8b842418 H.D$@......H..$. - 0690 02000048 8d900004 0000488b 44244048 ...H......H.D$@H - 06a0 894424f0 e9630d00 000f1f80 00000000 .D$..c.......... - 06b0 488b4c24 20c5fa11 8a00fcff ffc5fa10 H.L$ ........... - 06c0 01488b4c 2418c5fa 118204fc ffffc5fa .H.L$........... - 06d0 1001488b 4c2408c5 fa118208 fcffffc5 ..H.L$.......... - 06e0 fa100148 8b4c2410 c5fa1182 0cfcffff ...H.L$......... - 06f0 c5fa1001 488b0c24 c5fa1182 10fcffff ....H..$........ - 0700 c5fa1001 488b4c24 f8c5fa11 8214fcff ....H.L$........ - 0710 ffc5fa10 01488b4c 24e0c5fa 118218fc .....H.L$....... - 0720 ffffc5fa 1001488b 4c24d8c5 fa11821c ......H.L$...... - 0730 fcffffc5 fa100148 8b4c24d0 c5fa1182 .......H.L$..... - 0740 20fcffff c5fa1001 488b4c24 c8c5fa11 .......H.L$.... - 0750 8224fcff ffc5fa10 01488b4c 24c0c5fa .$.......H.L$... - 0760 118228fc ffffc5fa 1001488b 4c24b8c5 ..(.......H.L$.. - 0770 fa11822c fcffffc5 fa100148 8b4c24b0 ...,.......H.L$. - 0780 c5fa1182 30fcffff c5fa1001 488b4c24 ....0.......H.L$ - 0790 a8c5fa11 8234fcff ffc5fa10 01488b44 .....4.......H.D - 07a0 2430c5fa 118238fc ffffc5fa 1000c782 $0....8......... - 07b0 40fcffff 00000000 488b4c24 18c5fa11 @.......H.L$.... - 07c0 823cfcff ffc5fa11 8a44fcff ffc5fa10 .<.......D...... - 07d0 4104488b 4c2408c5 fa118248 fcffffc5 A.H.L$.....H.... - 07e0 fa104104 488b4c24 10c5fa11 824cfcff ..A.H.L$.....L.. - 07f0 ffc5fa10 4104488b 0c24c5fa 118250fc ....A.H..$....P. - 0800 ffffc5fa 10410448 8b4c24f8 c5fa1182 .....A.H.L$..... - 0810 54fcffff c5fa1041 04488b4c 24e0c5fa T......A.H.L$... - 0820 118258fc ffffc5fa 10410448 8b4c24d8 ..X......A.H.L$. - 0830 c5fa1182 5cfcffff c5fa1041 04488b4c ....\......A.H.L - 0840 24d0c5fa 118260fc ffffc5fa 10410448 $.....`......A.H - 0850 8b4c24c8 c5fa1182 64fcffff c5fa1041 .L$.....d......A - 0860 04488b4c 24c0c5fa 118268fc ffffc5fa .H.L$.....h..... - 0870 10410448 8b4c24b8 c5fa1182 6cfcffff .A.H.L$.....l... - 0880 c5fa1041 04488b4c 24b0c5fa 118270fc ...A.H.L$.....p. - 0890 ffffc5fa 10410448 8b4c24a8 c5fa1182 .....A.H.L$..... - 08a0 74fcffff c5fa1041 04488b4c 2408c5fa t......A.H.L$... - 08b0 118278fc ffffc5fa 104004c7 8280fcff ..x......@...... - 08c0 ff000000 00c78284 fcffff00 000000c5 ................ - 08d0 fa11827c fcffffc5 fa118a88 fcffffc5 ...|............ - 08e0 fa104108 488b4c24 10c5fa11 828cfcff ..A.H.L$........ - 08f0 ffc5fa10 4108488b 0c24c5fa 118290fc ....A.H..$...... - 0900 ffffc5fa 10410848 8b4c24f8 c5fa1182 .....A.H.L$..... - 0910 94fcffff c5fa1041 08488b4c 24e0c5fa .......A.H.L$... - 0920 118298fc ffffc5fa 10410848 8b4c24d8 .........A.H.L$. - 0930 c5fa1182 9cfcffff c5fa1041 08488b4c ...........A.H.L - 0940 24d0c5fa 1182a0fc ffffc5fa 10410848 $............A.H - 0950 8b4c24c8 c5fa1182 a4fcffff c5fa1041 .L$............A - 0960 08488b4c 24c0c5fa 1182a8fc ffffc5fa .H.L$........... - 0970 10410848 8b4c24b8 c5fa1182 acfcffff .A.H.L$......... - 0980 c5fa1041 08488b4c 24b0c5fa 1182b0fc ...A.H.L$....... - 0990 ffffc5fa 10410848 8b4c24a8 c5fa1182 .....A.H.L$..... - 09a0 b4fcffff c5fa1041 08c5fa11 82b8fcff .......A........ - 09b0 ffc5fa10 4008c782 c0fcffff 00000000 ....@........... - 09c0 c782c4fc ffff0000 0000c782 c8fcffff ................ - 09d0 00000000 488b4c24 10c5fa11 82bcfcff ....H.L$........ - 09e0 ffc5fa11 8accfcff ffc5fa10 410c488b ............A.H. - 09f0 0c24c5fa 1182d0fc ffffc5fa 10410c48 .$...........A.H - 0a00 8b4c24f8 c5fa1182 d4fcffff c5fa1041 .L$............A - 0a10 0c488b4c 24e0c5fa 1182d8fc ffffc5fa .H.L$........... - 0a20 10410c48 8b4c24d8 c5fa1182 dcfcffff .A.H.L$......... - 0a30 c5fa1041 0c488b4c 24d0c5fa 1182e0fc ...A.H.L$....... - 0a40 ffffc5fa 10410c48 8b4c24c8 c5fa1182 .....A.H.L$..... - 0a50 e4fcffff c5fa1041 0c488b4c 24c0c5fa .......A.H.L$... - 0a60 1182e8fc ffffc5fa 10410c48 8b4c24b8 .........A.H.L$. - 0a70 c5fa1182 ecfcffff c5fa1041 0cc5fa11 ...........A.... - 0a80 82f0fcff ff488b4c 24b0c5fa 10410c48 .....H.L$....A.H - 0a90 8b4c24a8 c5fa1182 f4fcffff c5fa1041 .L$............A - 0aa0 0c488b0c 24c5fa11 82f8fcff ffc5fa10 .H..$........... - 0ab0 400cc782 00fdffff 00000000 c78204fd @............... - 0ac0 ffff0000 0000c782 08fdffff 00000000 ................ - 0ad0 c7820cfd ffff0000 0000c5fa 1182fcfc ................ - 0ae0 ffffc5fa 118a10fd ffffc5fa 10411048 .............A.H - 0af0 8b4c24f8 c5fa1182 14fdffff c5fa1041 .L$............A - 0b00 10488b4c 24e0c5fa 118218fd ffffc5fa .H.L$........... - 0b10 10411048 8b4c24d8 c5fa1182 1cfdffff .A.H.L$......... - 0b20 c5fa1041 10488b4c 24d0c5fa 118220fd ...A.H.L$..... . - 0b30 ffffc5fa 10411048 8b4c24c8 c5fa1182 .....A.H.L$..... - 0b40 24fdffff c5fa1041 10488b4c 24c0c5fa $......A.H.L$... - 0b50 118228fd ffffc5fa 10411048 8b4c24b8 ..(......A.H.L$. - 0b60 c5fa1182 2cfdffff c5fa1041 10488b4c ....,......A.H.L - 0b70 24b0c5fa 118230fd ffffc5fa 10411048 $.....0......A.H - 0b80 8b4c24a8 c5fa1182 34fdffff c5fa1041 .L$.....4......A - 0b90 10488b4c 24f8c5fa 118238fd ffffc5fa .H.L$.....8..... - 0ba0 104010c7 8240fdff ff000000 00c78244 .@...@.........D - 0bb0 fdffff00 000000c7 8248fdff ff000000 .........H...... - 0bc0 00c7824c fdffff00 000000c7 8250fdff ...L.........P.. - 0bd0 ff000000 00c5fa11 823cfdff ffc5fa11 .........<...... - 0be0 8a54fdff ffc5fa10 4114488b 4c24e0c5 .T......A.H.L$.. - 0bf0 fa118258 fdffffc5 fa104114 488b4c24 ...X......A.H.L$ - 0c00 d8c5fa11 825cfdff ffc5fa10 4114488b .....\......A.H. - 0c10 4c24d0c5 fa118260 fdffffc5 fa104114 L$.....`......A. /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39000000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 fc340000 00420e10 8f02420e .....4...B....B. + 0020 00000000 431b0000 00420e10 8f02420e ....C....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 51200a0e ..A.8..G....Q .. + 0040 8606410e 38830747 0ed00203 25160a0e ..A.8..G....%... 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0842 0b000000 D..B.... + 0060 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_SKYLAKEX.o (disasm) @@ -17,1138 +17,675 @@ mov %rdi,offset(%rsp) mov %rdx,offset(%rsp) mov %rcx,offset(%rsp) - mov %r8,offset(%rsp) + mov %r8,-offset(%rsp) mov %r9,offset(%rsp) mov %rsi,offset(%rsp) + mov offset(%rsp),%r13 test %rsi,%rsi jle - mov %rdi,%rax - sar $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax + mov %rdi,%r11 + mov %r9,%r10 + mov %rcx,%rax + mov %rdi,%rbx + and $something,%edi + mov %rcx,%rbp + imul %r8,%rax + mov %rdi,offset(%rsp) + mov %r10,%rdi + imul %rbp,%rdi mov %r8,%r12 - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - imul %rcx,%r12 - and $something,%eax - mov %rax,offset(%rsp) - shl $something,%rax - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - shl $something,%rax - lea (%rcx,%rbx,1),%r11 - add offset(%rsp),%rax - lea (%rcx,%r11,1),%r10 - mov %rax,offset(%rsp) - mov offset(%rsp),%rax - lea (%r10,%rcx,1),%r9 - add offset(%rsp),%r12 - lea (%r9,%rcx,1),%r8 - lea (%rax,%r12,4),%r12 - lea (%r8,%rcx,1),%rdi - mov %r12,offset(%rsp) - mov offset(%rsp),%r12 - lea (%rdi,%rcx,1),%rsi - mov %rcx,%r13 - add %r12,%rbp + lea (%rax,%rcx,2),%rsi + mov %rax,%r8 + mov %rdx,%r15 lea (%rsi,%rcx,1),%rcx - lea (%rcx,%r13,1),%rdx - lea (%rax,%rbp,4),%rbp - lea (%rdx,%r13,1),%r15 - mov %rbp,offset(%rsp) - mov %r12,%rbp - mov %r15,-offset(%rsp) - add %rbp,%r11 - lea (%rax,%r11,4),%r11 - add %rbp,%r9 - add %rbp,%r8 - add %r12,%rbx - lea (%rax,%r9,4),%r9 - add %rbp,%rdi - add %rbp,%rcx - mov %r11,offset(%rsp) - add %rbp,%r10 - lea (%rax,%r8,4),%r11 - add %rbp,%rsi - add %rbp,%rdx - mov %rax,%r12 - lea (%rax,%rsi,4),%rsi - lea (%rax,%rdx,4),%rdx - mov %r9,offset(%rsp) - mov %r11,offset(%rsp) - lea (%rax,%rcx,4),%r9 - lea (%rax,%rdi,4),%r11 - lea (%rax,%rbx,4),%rbx - lea (%rax,%r10,4),%r10 - mov -offset(%rsp),%rax - lea (%r15,%r13,1),%r14 - add %rbp,%rax - lea (%r14,%r13,1),%r15 - mov %rdx,offset(%rsp) - add %rbp,%r14 - lea (%r12,%rax,4),%rdx - mov offset(%rsp),%rdi - add %r15,%r13 - mov %rdx,offset(%rsp) - add %rbp,%r15 - lea (%r12,%r14,4),%rdx - mov %rdx,offset(%rsp) - lea offset(%rbp,%r13,1),%rax - lea (%r12,%r15,4),%rdx - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx - lea offset(%r13,%rdi,1),%rax - add %rbp,%rax - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx + add %r12,%rdi + lea offset(%rbp,%rcx,1),%rdx + mov %r15,%r12 + sub %r8,%rcx + lea (%r15,%rdi,4),%r15 + lea (%r10,%r8,1),%rdi + lea offset(%rbp,%rdx,1),%rax + lea (%r12,%rdi,4),%r12 + shl $something,%rcx + mov %r10,%rdi + sub %r8,%rdx + mov offset(%rsp),%r10 + lea (%rax,%rbp,1),%r9 + mov %rcx,offset(%rsp) + sub %r8,%rax + lea offset(,%rdx,4),%rcx + lea (%rdi,%r10,8),%r10 + mov %rcx,offset(%rsp) + lea offset(,%rax,4),%rcx + mov %r10,offset(%rsp) + mov %rcx,offset(%rsp) + mov %rbp,%r10 + mov %r9,%rcx + sub %r8,%rcx + lea (%r9,%r10,1),%rax + mov %rbp,%r14 + lea offset(,%rcx,4),%rcx + lea offset(,%rbp,4),%rbp + sub %r8,%rax + sub %r8,%rsi + mov %rcx,offset(%rsp) + shl $something,%rsi + lea offset(,%rax,4),%rcx mov %rbp,%rax - imul %rdi,%rax - mov offset(%rsp),%rcx - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax mov %rsi,offset(%rsp) - mov %rbx,offset(%rsp) - add %rcx,%rax - mov %r10,offset(%rsp) - mov %r11,offset(%rsp) - mov %r9,offset(%rsp) - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax + lea offset(%rdi),%rdx + mov %rbp,%rsi + neg %rax imul %rdi,%rax - mov %rdx,offset(%rsp) + imul %rsi,%rdx mov %rbp,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - vmovss offset(%rip),%xmm1 # - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx - lea offset(%rbp),%rax - imul %rdi,%rax - mov %rdx,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rdx /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_SKYLAKEX.o (objdump) @@ -2,851 +2,440 @@ /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 044889bc .H..$....H...H.. - 0020 24800000 00488994 24a00000 0048898c $....H..$....H.. - 0030 24900000 004c8944 24404c89 4c246048 $....L.D$@L.L$`H - 0040 89b424c0 01000048 85f60f8e ae160000 ..$....H........ - 0050 4889f848 c1f80448 89442478 488b8424 H..H...H.D$xH..$ - 0060 90000000 4d89c448 c1e00648 89442448 ....M..H...H.D$H - 0070 488b8424 80000000 4c0fafe1 83e00f48 H..$....L......H - 0080 89442458 48c1e006 48898424 b8010000 .D$XH...H..$.... - 0090 488b8424 c0010000 4a8d2c21 488d1c29 H..$....J.,!H..) - 00a0 48c1e004 4c8d1c19 48034424 604e8d14 H...L...H.D$`N.. - 00b0 19488984 24880000 00488b84 24a00000 .H..$....H..$... - 00c0 004d8d0c 0a4c0364 24604d8d 04094e8d .M...L.d$`M...N. - 00d0 24a0498d 3c084c89 a424d000 00004c8b $.I.<.L..$....L. - 00e0 64246048 8d340f49 89cd4c01 e5488d0c d$`H.4.I..L..H.. - 00f0 0e4a8d14 29488d2c a84e8d3c 2a4889ac .J..)H.,.N.<*H.. - 0100 24b80000 004c89e5 4c897c24 884901eb $....L..L.|$.I.. - 0110 4e8d1c98 4901e949 01e84c01 e34e8d0c N...I..I..L..N.. - 0120 884801ef 4801e94c 899c24e0 00000049 .H..H..L..$....I - 0130 01ea4e8d 1c804801 ee4801ea 4989c448 ..N...H..H..I..H - 0140 8d34b048 8d14904c 898c24b0 0000004c .4.H...L..$....L - 0150 899c2410 0100004c 8d0c884c 8d1cb848 ..$....L...L...H - 0160 8d1c984e 8d149048 8b442488 4f8d342f ...N...H.D$.O.4/ - 0170 4801e84f 8d3c2e48 89942450 01000049 H..O.<.H..$P...I - 0180 01ee498d 1484488b bc249000 00004d01 ..I...H..$....M. - 0190 fd488994 24600100 004901ef 4b8d14b4 .H..$`...I..K... - 01a0 48899424 70010000 4a8d442d 004b8d14 H..$p...J.D-.K.. - 01b0 bc488994 24800100 00498d14 84498d44 .H..$....I...I.D - 01c0 3d004801 e8488994 24900100 00498d14 =.H..H..$....I.. - 01d0 844889e8 480fafc7 488b4c24 40488994 .H..H...H.L$@H.. - 01e0 24a00100 004801c8 498d1484 488d4501 $....H..I...H.E. - 01f0 480fafc7 4889b424 30010000 48899c24 H...H..$0...H..$ - 0200 c8000000 4801c84c 899424f8 0000004c ....H..L..$....L - 0210 899c2420 0100004c 898c2440 01000048 ..$ ...L..$@...H - 0220 899424f0 00000049 8d148448 8d450248 ..$....I...H.E.H - 0230 0fafc748 899424d8 00000048 896c2428 ...H..$....H.l$( - 0240 4801c849 8d148448 8d450348 0fafc748 H..I...H.E.H...H - 0250 899424e8 00000048 c7442468 00000000 ..$....H.D$h.... - 0260 4801c849 8d148448 8d450448 0fafc748 H..I...H.E.H...H - 0270 89942400 01000048 c7442470 00000000 ..$....H.D$p.... - 0280 4801c849 8d148448 8d450548 0fafc748 H..I...H.E.H...H - 0290 899424a8 000000c5 fa100d00 00000048 ..$............H - 02a0 01c8498d 1484488d 4506480f afc74889 ..I...H.E.H...H. - 02b0 9424c000 00004801 c8498d14 84488d45 .$....H..I...H.E - 02c0 07480faf c7488994 24080100 004801c8 .H...H..$....H.. - 02d0 498d1484 488d4508 480fafc7 48899424 I...H.E.H...H..$ - 02e0 18010000 4801c849 8d148448 8d450948 ....H..I...H.E.H - 02f0 0fafc748 89942428 01000048 01c8498d ...H..$(...H..I. - 0300 1484488d 450a480f afc74889 94243801 ..H.E.H...H..$8. - 0310 00004801 c8498d14 84488d45 0b480faf ..H..I...H.E.H.. - 0320 c7488994 24480100 004801c8 498d1484 .H..$H...H..I... - 0330 488d450c 480fafc7 48899424 58010000 H.E.H...H..$X... - 0340 4801c849 8d148448 8d450d48 0fafc748 H..I...H.E.H...H - 0350 89942468 01000048 01c8498d 1484488d ..$h...H..I...H. - 0360 450e480f afc74889 94247801 00004801 E.H...H..$x...H. - 0370 c8498d14 84488d45 0f480faf c7488bbc .I...H.E.H...H.. - 0380 24800000 00488994 24880100 004801c8 $....H..$....H.. - 0390 498d3484 4889b424 98010000 4889fe48 I.4.H..$....H..H - 03a0 8b442478 4883e6f0 4801ce48 89742450 .D$xH...H..H.t$P - 03b0 4889c648 c1e00448 01c84889 8424b001 H..H...H..H..$.. - 03c0 00004889 f883e00e 48898424 c8010000 ..H.....H..$.... - 03d0 4889f848 c1e60a83 e00c83e7 084889b4 H..H.........H.. - 03e0 24a80100 00488984 24d00100 004889bc $....H..$....H.. - 03f0 24d80100 00e96f01 0000660f 1f440000 $.....o...f..D.. - 0400 488b4424 70488b9c 24e80000 00488bb4 H.D$pH..$....H.. - 0410 24f00000 004801c3 48895c24 18488b9c $....H..H.\$.H.. - 0420 24000100 004801c6 4801c348 895c2408 $....H..H..H.\$. - 0430 488b9c24 08010000 48897424 384801c3 H..$....H.t$8H.. - 0440 48895c24 f8488b9c 24180100 00488bbc H.\$.H..$....H.. - 0450 24d80000 004801c3 48895c24 e0488b9c $....H..H.\$.H.. - 0460 24280100 00488bb4 24a80000 004801c3 $(...H..$....H.. - 0470 48895c24 d8488b9c 24380100 004801c7 H.\$.H..$8...H.. - 0480 4801c348 895c24d0 488b9c24 48010000 H..H.\$.H..$H... - 0490 4801c648 01c34889 5c24c848 8b9c2458 H..H..H.\$.H..$X - 04a0 01000048 897c2420 4801c348 895c24c0 ...H.|$ H..H.\$. - 04b0 488b9c24 68010000 48897424 104801c3 H..$h...H.t$.H.. - 04c0 48895c24 b8488bbc 24c00000 00488bb4 H.\$.H..$....H.. - 04d0 24780100 00488b9c 24880100 004801c7 $x...H..$....H.. - 04e0 4801c648 01c34803 84249801 00004889 H..H..H..$....H. - 04f0 3c244889 7424b048 895c24a8 48894424 <$H.t$.H.\$.H.D$ - 0500 3048837c 24780048 8b442440 0f8f7901 0H.|$x.H.D$@..y. - 0510 00004883 7c245800 74264839 4424280f ..H.|$X.t&H9D$(. - 0520 8f542800 000f8d45 1b000048 8b8424b8 .T(....E...H..$. - 0530 01000048 01842418 0200000f 1f440000 ...H..$......D.. - 0540 48834424 2810488b 7c244848 83442468 H.D$(.H.|$HH.D$h - 0550 4048017c 2470488b 44242848 3b842488 @H.|$pH.D$(H;.$. - 0560 0000000f 847c1100 00488b5c 24404839 .....|...H.\$@H9 - 0570 5c24280f 8d87feff ff488b44 2468488b \$(......H.D$hH. - 0580 9c24d000 0000488b b424b800 0000488b .$....H..$....H. - 0590 bc24c800 00004801 c34801c6 4801c748 .$....H..H..H..H - 05a0 895c2438 48897424 2048897c 2418488b .\$8H.t$ H.|$.H. - 05b0 9c24e000 0000488b bc24f800 0000488b .$....H..$....H. - 05c0 b424b000 00004801 c34801c7 4801c648 .$....H..H..H..H - 05d0 895c2408 48897c24 10488934 24488b9c .\$.H.|$.H.4$H.. - 05e0 24200100 00488bb4 24100100 00488bbc $ ...H..$....H.. - 05f0 24300100 004801c6 4801c348 01c74889 $0...H..H..H..H. - 0600 7424f848 895c24e0 48897c24 d8488bb4 t$.H.\$.H.|$.H.. - 0610 24400100 00488b9c 24500100 00488bbc $@...H..$P...H.. - 0620 24600100 004801c6 4801c348 01c74889 $`...H..H..H..H. - 0630 7424d048 895c24c8 48897c24 c0488bb4 t$.H.\$.H.|$.H.. - 0640 24700100 00488b9c 24800100 00488bbc $p...H..$....H.. - 0650 24900100 004801c6 4801c348 01c74803 $....H..H..H..H. - 0660 8424a001 00004889 7424b848 895c24b0 .$....H.t$.H.\$. - 0670 48897c24 a8488944 24304883 7c247800 H.|$.H.D$0H.|$x. - 0680 488b4424 400f8e87 feffff48 8b842418 H.D$@......H..$. - 0690 02000048 8d900004 0000488b 44244048 ...H......H.D$@H - 06a0 894424f0 e9630d00 000f1f80 00000000 .D$..c.......... - 06b0 488b4c24 20c5fa11 8a00fcff ffc5fa10 H.L$ ........... - 06c0 01488b4c 2418c5fa 118204fc ffffc5fa .H.L$........... - 06d0 1001488b 4c2408c5 fa118208 fcffffc5 ..H.L$.......... - 06e0 fa100148 8b4c2410 c5fa1182 0cfcffff ...H.L$......... - 06f0 c5fa1001 488b0c24 c5fa1182 10fcffff ....H..$........ - 0700 c5fa1001 488b4c24 f8c5fa11 8214fcff ....H.L$........ - 0710 ffc5fa10 01488b4c 24e0c5fa 118218fc .....H.L$....... - 0720 ffffc5fa 1001488b 4c24d8c5 fa11821c ......H.L$...... - 0730 fcffffc5 fa100148 8b4c24d0 c5fa1182 .......H.L$..... - 0740 20fcffff c5fa1001 488b4c24 c8c5fa11 .......H.L$.... - 0750 8224fcff ffc5fa10 01488b4c 24c0c5fa .$.......H.L$... - 0760 118228fc ffffc5fa 1001488b 4c24b8c5 ..(.......H.L$.. - 0770 fa11822c fcffffc5 fa100148 8b4c24b0 ...,.......H.L$. - 0780 c5fa1182 30fcffff c5fa1001 488b4c24 ....0.......H.L$ - 0790 a8c5fa11 8234fcff ffc5fa10 01488b44 .....4.......H.D - 07a0 2430c5fa 118238fc ffffc5fa 1000c782 $0....8......... - 07b0 40fcffff 00000000 488b4c24 18c5fa11 @.......H.L$.... - 07c0 823cfcff ffc5fa11 8a44fcff ffc5fa10 .<.......D...... - 07d0 4104488b 4c2408c5 fa118248 fcffffc5 A.H.L$.....H.... - 07e0 fa104104 488b4c24 10c5fa11 824cfcff ..A.H.L$.....L.. - 07f0 ffc5fa10 4104488b 0c24c5fa 118250fc ....A.H..$....P. - 0800 ffffc5fa 10410448 8b4c24f8 c5fa1182 .....A.H.L$..... - 0810 54fcffff c5fa1041 04488b4c 24e0c5fa T......A.H.L$... - 0820 118258fc ffffc5fa 10410448 8b4c24d8 ..X......A.H.L$. - 0830 c5fa1182 5cfcffff c5fa1041 04488b4c ....\......A.H.L - 0840 24d0c5fa 118260fc ffffc5fa 10410448 $.....`......A.H - 0850 8b4c24c8 c5fa1182 64fcffff c5fa1041 .L$.....d......A - 0860 04488b4c 24c0c5fa 118268fc ffffc5fa .H.L$.....h..... - 0870 10410448 8b4c24b8 c5fa1182 6cfcffff .A.H.L$.....l... - 0880 c5fa1041 04488b4c 24b0c5fa 118270fc ...A.H.L$.....p. - 0890 ffffc5fa 10410448 8b4c24a8 c5fa1182 .....A.H.L$..... - 08a0 74fcffff c5fa1041 04488b4c 2408c5fa t......A.H.L$... - 08b0 118278fc ffffc5fa 104004c7 8280fcff ..x......@...... - 08c0 ff000000 00c78284 fcffff00 000000c5 ................ - 08d0 fa11827c fcffffc5 fa118a88 fcffffc5 ...|............ - 08e0 fa104108 488b4c24 10c5fa11 828cfcff ..A.H.L$........ - 08f0 ffc5fa10 4108488b 0c24c5fa 118290fc ....A.H..$...... - 0900 ffffc5fa 10410848 8b4c24f8 c5fa1182 .....A.H.L$..... - 0910 94fcffff c5fa1041 08488b4c 24e0c5fa .......A.H.L$... - 0920 118298fc ffffc5fa 10410848 8b4c24d8 .........A.H.L$. - 0930 c5fa1182 9cfcffff c5fa1041 08488b4c ...........A.H.L - 0940 24d0c5fa 1182a0fc ffffc5fa 10410848 $............A.H - 0950 8b4c24c8 c5fa1182 a4fcffff c5fa1041 .L$............A - 0960 08488b4c 24c0c5fa 1182a8fc ffffc5fa .H.L$........... - 0970 10410848 8b4c24b8 c5fa1182 acfcffff .A.H.L$......... - 0980 c5fa1041 08488b4c 24b0c5fa 1182b0fc ...A.H.L$....... - 0990 ffffc5fa 10410848 8b4c24a8 c5fa1182 .....A.H.L$..... - 09a0 b4fcffff c5fa1041 08c5fa11 82b8fcff .......A........ - 09b0 ffc5fa10 4008c782 c0fcffff 00000000 ....@........... - 09c0 c782c4fc ffff0000 0000c782 c8fcffff ................ - 09d0 00000000 488b4c24 10c5fa11 82bcfcff ....H.L$........ - 09e0 ffc5fa11 8accfcff ffc5fa10 410c488b ............A.H. - 09f0 0c24c5fa 1182d0fc ffffc5fa 10410c48 .$...........A.H - 0a00 8b4c24f8 c5fa1182 d4fcffff c5fa1041 .L$............A - 0a10 0c488b4c 24e0c5fa 1182d8fc ffffc5fa .H.L$........... - 0a20 10410c48 8b4c24d8 c5fa1182 dcfcffff .A.H.L$......... - 0a30 c5fa1041 0c488b4c 24d0c5fa 1182e0fc ...A.H.L$....... - 0a40 ffffc5fa 10410c48 8b4c24c8 c5fa1182 .....A.H.L$..... - 0a50 e4fcffff c5fa1041 0c488b4c 24c0c5fa .......A.H.L$... - 0a60 1182e8fc ffffc5fa 10410c48 8b4c24b8 .........A.H.L$. - 0a70 c5fa1182 ecfcffff c5fa1041 0cc5fa11 ...........A.... - 0a80 82f0fcff ff488b4c 24b0c5fa 10410c48 .....H.L$....A.H - 0a90 8b4c24a8 c5fa1182 f4fcffff c5fa1041 .L$............A - 0aa0 0c488b0c 24c5fa11 82f8fcff ffc5fa10 .H..$........... - 0ab0 400cc782 00fdffff 00000000 c78204fd @............... - 0ac0 ffff0000 0000c782 08fdffff 00000000 ................ - 0ad0 c7820cfd ffff0000 0000c5fa 1182fcfc ................ - 0ae0 ffffc5fa 118a10fd ffffc5fa 10411048 .............A.H - 0af0 8b4c24f8 c5fa1182 14fdffff c5fa1041 .L$............A - 0b00 10488b4c 24e0c5fa 118218fd ffffc5fa .H.L$........... - 0b10 10411048 8b4c24d8 c5fa1182 1cfdffff .A.H.L$......... - 0b20 c5fa1041 10488b4c 24d0c5fa 118220fd ...A.H.L$..... . - 0b30 ffffc5fa 10411048 8b4c24c8 c5fa1182 .....A.H.L$..... - 0b40 24fdffff c5fa1041 10488b4c 24c0c5fa $......A.H.L$... - 0b50 118228fd ffffc5fa 10411048 8b4c24b8 ..(......A.H.L$. - 0b60 c5fa1182 2cfdffff c5fa1041 10488b4c ....,......A.H.L - 0b70 24b0c5fa 118230fd ffffc5fa 10411048 $.....0......A.H - 0b80 8b4c24a8 c5fa1182 34fdffff c5fa1041 .L$.....4......A - 0b90 10488b4c 24f8c5fa 118238fd ffffc5fa .H.L$.....8..... - 0ba0 104010c7 8240fdff ff000000 00c78244 .@...@.........D - 0bb0 fdffff00 000000c7 8248fdff ff000000 .........H...... - 0bc0 00c7824c fdffff00 000000c7 8250fdff ...L.........P.. - 0bd0 ff000000 00c5fa11 823cfdff ffc5fa11 .........<...... - 0be0 8a54fdff ffc5fa10 4114488b 4c24e0c5 .T......A.H.L$.. - 0bf0 fa118258 fdffffc5 fa104114 488b4c24 ...X......A.H.L$ - 0c00 d8c5fa11 825cfdff ffc5fa10 4114488b .....\......A.H. - 0c10 4c24d0c5 fa118260 fdffffc5 fa104114 L$.....`......A. /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39000000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iunucopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 fc340000 00420e10 8f02420e .....4...B....B. + 0020 00000000 431b0000 00420e10 8f02420e ....C....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 51200a0e ..A.8..G....Q .. + 0040 8606410e 38830747 0ed00203 25160a0e ..A.8..G....%... 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0842 0b000000 D..B.... + 0060 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_COOPERLAKE.o (disasm) @@ -20,1291 +20,430 @@ mov %r8,-offset(%rsp) mov %r9,offset(%rsp) mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov offset(%rsp),%r13 test %rsi,%rsi jle + mov %rcx,%r11 + mov %r9,%rbp + mov %r11,%r15 + imul %r11,%r9 + shl $something,%r15 + mov %rcx,%rax + imul %r8,%rax + mov %rdi,%r10 mov %r8,%r12 - imul %rcx,%r12 - mov %rcx,%r14 + mov %r15,offset(%rsp) + lea offset(,%r11,8),%r15 + add %r12,%r9 + kmovq %r15,%k2 + mov offset(%rsp),%r12 + mov %r10,%r15 + and $something,%r15d + lea (%rax,%rcx,2),%r8 + mov %r15,-offset(%rsp) + lea (%r12,%r9,4),%r15 + lea offset(%rbp,%rax,1),%r9 + lea (%r8,%rcx,1),%rdi + lea (%r12,%r9,4),%r12 mov offset(%rsp),%r9 - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - lea (%rcx,%rbx,1),%r11 - lea (%r11,%rcx,1),%r10 - lea (%rcx,%r10,1),%rax - lea (%rax,%rcx,1),%r8 - lea (%rcx,%r8,1),%rdi - lea (%rcx,%rdi,1),%rsi - mov %rax,-offset(%rsp) - lea (%rcx,%rsi,1),%rax - lea (%rcx,%rax,1),%rdx - mov %rax,-offset(%rsp) - lea (%rcx,%rdx,1),%rax - lea (%rcx,%rax,1),%r13 - mov %r13,%rcx - mov %r14,%r13 - add %rcx,%r13 - mov %rcx,-offset(%rsp) - mov %r13,%rcx - mov %r14,%r13 - add %rcx,%r13 - mov %rcx,-offset(%rsp) - mov %r9,%rcx - sar $something,%rcx - and $something,%r9d - mov %rcx,offset(%rsp) + lea (%rdi,%rcx,1),%rsi + lea (%rsi,%rcx,1),%rcx + sub %rax,%rdi + lea offset(%rbp,%r9,8),%r9 + lea (%rcx,%r11,1),%rdx + shl $something,%rdi + sub %rax,%rcx mov %r9,offset(%rsp) - mov %r14,%rcx - shl $something,%r9 + mov %r11,%r9 + sub %rax,%rsi + mov %rdi,offset(%rsp) + mov %r11,%r14 + lea offset(,%rcx,4),%rdi + lea offset(,%r11,4),%r11 + mov %rdx,%rcx + add %r9,%rdx + sub %rax,%rdx + sub %rax,%r8 + shl $something,%rsi + sub %rax,%rcx + mov %r11,%rax + mov %rsi,offset(%rsp) + neg %rax + lea offset(,%rdx,4),%rsi + lea offset(%rbp),%rdx + imul %rbp,%rax + imul %r11,%rdx shl $something,%rcx - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 mov %rcx,offset(%rsp) - mov offset(%rsp),%rcx - shl $something,%r9 - add %rcx,%r9 - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add %rcx,%r12 - lea (%r9,%r12,4),%r12 - add %rcx,%rbp - lea (%r9,%rbp,4),%rbp - mov %r12,offset(%rsp) - mov %rcx,%r12 - mov %rbp,offset(%rsp) - mov %r12,%rbp - add %r12,%rbx - add %rbp,%rdx - mov %r9,%r12 - add %rbp,%rax - lea (%r12,%rdx,4),%rdx - mov %rdx,offset(%rsp) - add %rbp,%r11 - lea (%r12,%rax,4),%rdx - add %rbp,%r10 - mov -offset(%rsp),%rax - mov %r9,%rcx - lea (%r9,%r11,4),%r11 - lea (%r9,%r10,4),%r10 - lea (%r9,%rbx,4),%rbx - mov -offset(%rsp),%r9 - add %rbp,%rax - add %rbp,%r9 - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx - mov -offset(%rsp),%rax - add %rbp,%rsi - mov %r10,offset(%rsp) - add %rbp,%r8 - lea (%rcx,%r9,4),%r10 - add %rbp,%rdi - mov %r11,offset(%rsp) - mov %r10,offset(%rsp) - lea (%rcx,%rsi,4),%r11 - lea (%rcx,%r8,4),%r10 - lea (%rcx,%rdi,4),%rdi - add %rbp,%rax - mov -offset(%rsp),%rcx - lea (%r12,%rax,4),%rax - add %rbp,%rcx - mov %rax,offset(%rsp) - lea offset(%r13,%rbp,1),%rax - mov %r11,offset(%rsp) - lea (%r12,%rax,4),%rax - lea (%r12,%rcx,4),%r11 - mov %r10,offset(%rsp) - mov %rax,offset(%rsp) - mov %rbx,offset(%rsp) + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + mov %rcx,offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) mov %rdi,offset(%rsp) - mov %r11,offset(%rsp) - mov %rdx,offset(%rsp) - mov offset(%rsp),%rsi - mov -offset(%rsp),%rcx - lea (%rsi,%r13,1),%rax - add %rbp,%rax - lea (%r12,%rax,4),%rax - mov %rax,offset(%rsp) - mov %rsi,%rax - imul %rbp,%rax + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rcx,offset(%rsp) + mov %r10,%rbx + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + sar $something,%rbx + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rbx,offset(%rsp) shl $something,%r14 - mov offset(%rsp),%r9 - add %rcx,%rax - lea (%r12,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rbp,-offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - movq $something,offset(%rsp) - mov %r15,%r10 - add %rcx,%rax /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_COOPERLAKE.o (objdump) @@ -2,711 +2,347 @@ /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24900000 0048c1fe 0448897c .H..$....H...H.| - 0020 24784889 94249800 00004889 8c248800 $xH..$....H..$.. - 0030 00004c89 4424c04c 894c2458 4889b424 ..L.D$.L.L$XH..$ - 0040 c0010000 4c8bbc24 18020000 4885f60f ....L..$....H... - 0050 8e971d00 004d89c4 4c0fafe1 4989ce4c .....M..L...I..L - 0060 8b4c2478 4a8d2c21 488d1c29 4c8d1c19 .L$xJ.,!H..)L... - 0070 4d8d140b 4a8d0411 4c8d0408 4a8d3c01 M...J...L...J.<. - 0080 488d3439 48894424 98488d04 31488d14 H.49H.D$.H..1H.. - 0090 01488944 24a0488d 04114c8d 2c014c89 .H.D$.H...L.,.L. - 00a0 e94d89f5 4901cd48 894c2488 4c89e94d .M..I..H.L$.L..M - 00b0 89f54901 cd48894c 24904c89 c948c1f9 ..I..H.L$.L..H.. - 00c0 044183e1 0f48894c 24704c89 4c24504c .A...H.L$pL.L$PL - 00d0 89f149c1 e10648c1 e1024c89 8c24b801 ..I...H...L..$.. - 00e0 00004c8b 8c24c001 00004889 8c24a001 ..L..$....H..$.. - 00f0 0000488b 4c245849 c1e10449 01c94c89 ..H.L$XI...I..L. - 0100 8c248000 00004c8b 8c249800 00004901 .$....L..$....I. - 0110 cc4f8d24 a14801cd 498d2ca9 4c89a424 .O.$.H..I.,.L..$ - 0120 a8000000 4989cc48 89ac24b8 0000004c ....I..H..$....L - 0130 89e54c01 e34801ea 4d89cc48 01e8498d ..L..H..M..H..I. - 0140 14944889 94244801 00004901 eb498d14 ..H..$H...I..I.. - 0150 844901ea 488b4424 884c89c9 4f8d1c99 .I..H.D$.L..O... - 0160 4f8d1491 498d1c99 4c8b4c24 984801e8 O...I...L.L$.H.. - 0170 4901e948 89942458 01000049 8d148448 I..H..$X...I...H - 0180 8b442490 4801ee4c 899424e8 00000049 .D$.H..L..$....I - 0190 01e84e8d 14894801 ef4c899c 24d80000 ..N...H..L..$... - 01a0 004c8994 24f80000 004c8d1c b14e8d14 .L..$....L...N.. - 01b0 81488d3c b94801e8 488b4c24 a0498d04 .H.<.H..H.L$.I.. - 01c0 844801e9 48898424 78010000 498d442d .H..H..$x...I.D- - 01d0 004c899c 24280100 00498d04 844d8d1c .L..$(...I...M.. - 01e0 8c4c8994 24080100 00488984 24880100 .L..$....H..$... - 01f0 0048899c 24c80000 004889bc 24180100 .H..$....H..$... - 0200 004c899c 24380100 00488994 24680100 .L..$8...H..$h.. - 0210 00488bb4 24880000 00488b4c 24c04a8d .H..$....H.L$.J. - 0220 042e4801 e8498d04 84488984 24980100 ..H..I...H..$... - 0230 004889f0 480fafc5 49c1e606 4c8b4c24 .H..H...I...L.L$ - 0240 704801c8 498d0484 48898424 a0000000 pH..I...H..$.... - 0250 488d4501 480fafc6 48896c24 9048c744 H.E.H...H.l$.H.D - 0260 24680000 00004801 c8498d04 84488984 $h....H..I...H.. - 0270 24b00000 00488d45 02480faf c648c744 $....H.E.H...H.D - 0280 24600000 00004d89 fa4801c8 498d0484 $`....M..H..I... - 0290 48898424 c0000000 488d4503 480fafc6 H..$....H.E.H... - 02a0 4801c849 8d048448 898424d0 00000048 H..I...H..$....H - 02b0 8d450448 0fafc648 01c8498d 04844889 .E.H...H..I...H. - 02c0 8424e000 0000488d 4505480f afc64801 .$....H.E.H...H. - 02d0 c8498d04 84488984 24f00000 00488d45 .I...H..$....H.E - 02e0 06480faf c64801c8 498d0484 48898424 .H...H..I...H..$ - 02f0 00010000 488d4507 480fafc6 4801c849 ....H.E.H...H..I - 0300 8d048448 89842410 01000048 8d450848 ...H..$....H.E.H - 0310 0fafc648 01c8498d 04844889 84242001 ...H..I...H..$ . - 0320 0000488d 4509480f afc64801 c8498d04 ..H.E.H...H..I.. - 0330 84488984 24300100 00488d45 0a480faf .H..$0...H.E.H.. - 0340 c64801c8 498d0484 48898424 40010000 .H..I...H..$@... - 0350 488d450b 480fafc6 4801c849 8d048448 H.E.H...H..I...H - 0360 89842450 01000048 8d450c48 0fafc648 ..$P...H.E.H...H - 0370 01c8498d 04844889 84246001 0000488d ..I...H..$`...H. - 0380 450d480f afc64801 c8498d04 84488984 E.H...H..I...H.. - 0390 24700100 00488d45 0e480faf c64801c8 $p...H.E.H...H.. - 03a0 498d0484 48898424 80010000 488d450f I...H..$....H.E. - 03b0 480fafc6 488b7424 784801c8 498d0484 H...H.t$xH..I... - 03c0 48898424 90010000 4889f048 83e0f048 H..$....H..H...H - 03d0 01c84889 4424d04c 89c848c1 e00a4889 ..H.D$.L..H...H. - 03e0 8424a801 00004c89 c848c1e0 044801c8 .$....L..H...H.. - 03f0 48898424 b0010000 4889f083 e00e4889 H..$....H.....H. - 0400 8424c801 00004889 f083e00c 83e60848 .$....H........H - 0410 89b424d8 01000048 898424d0 0100004c ..$....H..$....L - 0420 89f6e927 01000066 0f1f8400 00000000 ...'...f........ - 0430 488b4424 60488bbc 24b00000 00488b9c H.D$`H..$....H.. - 0440 24f00000 004801c7 48897c24 98488bbc $....H..H.|$.H.. - 0450 24c00000 004801c3 4801c748 897c24a0 $....H..H..H.|$. - 0460 488bbc24 d0000000 48895c24 c84801c7 H..$....H.\$.H.. - 0470 48897c24 a8488bbc 24e00000 004c8b8c H.|$.H..$....L.. - 0480 24a00000 004801c7 48897c24 b0488b8c $....H..H.|$.H.. - 0490 24100100 00488bbc 24000100 004c8bbc $....H..$....L.. - 04a0 24200100 004c8bb4 24300100 004c8bac $ ...L..$0...L.. - 04b0 24400100 004c8ba4 24500100 00488bac $@...L..$P...H.. - 04c0 24600100 00488b9c 24700100 004c8b9c $`...H..$p...L.. - 04d0 24800100 004901c1 4801c748 01c14901 $....I..H..H..I. - 04e0 c74901c6 4901c549 01c44801 c54801c3 .I..I..I..H..H.. - 04f0 4901c348 03842490 01000048 837c2470 I..H..$....H.|$p - 0500 004889c2 488b4424 c00f8f2e 01000048 .H..H.D$.......H - 0510 837c2450 00741348 39442490 0f8e7e10 .|$P.t.H9D$...~. - 0520 00004c03 9424b801 00004883 44249010 ..L..$....H.D$.. - 0530 48017424 60488344 24684048 8b442490 H.t$`H.D$h@H.D$. - 0540 483b8424 80000000 0f848218 0000488b H;.$..........H. - 0550 7c24c048 397c2490 0f8dd2fe ffff488b |$.H9|$.......H. - 0560 44246848 8bbc24b8 00000048 8b9c24c8 D$hH..$....H..$. - 0570 00000048 01c74889 7c249848 8bbc24d8 ...H..H.|$.H..$. - 0580 00000048 01c34801 c748895c 24a04889 ...H..H..H.\$.H. - 0590 7c24a848 8b9c24e8 00000048 8bbc24f8 |$.H..$....H..$. - 05a0 00000048 01c34801 c748895c 24b04889 ...H..H..H.\$.H. - 05b0 7c24c84c 8b8c24a8 00000048 8bbc2408 |$.L..$....H..$. - 05c0 01000048 8b8c2418 0100004c 8bbc2428 ...H..$....L..$( - 05d0 0100004c 8bb42438 0100004c 8bac2448 ...L..$8...L..$H - 05e0 0100004c 8ba42458 01000048 8bac2468 ...L..$X...H..$h - 05f0 01000048 8b9c2478 0100004c 8b9c2488 ...H..$x...L..$. - 0600 01000049 01c14801 c74801c1 4901c749 ...I..H..H..I..I - 0610 01c64901 c54901c4 4801c548 01c34901 ..I..I..H..H..I. - 0620 c3480384 24980100 0048837c 24700048 .H..$....H.|$p.H - 0630 89c2488b 4424c00f 8ed2feff ff4c894c ..H.D$.......L.L - 0640 24b84c89 94241802 00004d8d 82000400 $.L..$....M..... - 0650 004989d1 4d89da48 89442488 488b5424 .I..M..H.D$.H.T$ - 0660 c84989f3 eb71662e 0f1f8400 00000000 .I...qf......... - 0670 48834424 b8404883 44249840 48834424 H.D$.@H.D$.@H.D$ - 0680 a0404883 4424a840 48834424 b0404883 .@H.D$.@H.D$.@H. - 0690 c2404883 c7404883 c1404983 c7404983 .@H..@H..@I..@I. - 06a0 c6404983 c5404983 c4404883 c5404883 .@I..@I..@H..@H. - 06b0 c3404983 c2404983 c1404883 44248810 .@I..@I..@H.D$.. - 06c0 4981c000 04000048 8b442488 483b4424 I......H.D$.H;D$ - 06d0 d00f8499 0e000049 8d8000fc ffff4889 .......I......H. - 06e0 4424c848 8b442488 48394424 907f8148 D$.H.D$.H9D$...H - 06f0 8b4424b8 488b7424 88c5fa10 00488b44 .D$.H.t$.....H.D - 0700 24984c01 d8488944 2418488b 4424a04c $.L..H.D$.H.D$.L - 0710 01d84889 44241048 8b4424a8 4c01d848 ..H.D$.H.D$.L..H - 0720 894424f8 488b4424 b04c01d8 48894424 .D$.H.D$.L..H.D$ - 0730 084a8d04 1a488944 24f04a8d 041f4889 .J...H.D$.J...H. - 0740 04244a8d 04194889 4424e84b 8d041f48 .$J...H.D$.K...H - 0750 89442448 4b8d041e 48894424 404b8d44 .D$HK...H.D$@K.D - 0760 1d004889 4424384b 8d041c48 894424e0 ..H.D$8K...H.D$. - 0770 4a8d441d 00488944 24304a8d 041b4889 J.D..H.D$0J...H. - 0780 4424d84b 8d041a48 89442428 4b8d0419 D$.K...H.D$(K... - 0790 48894424 20483974 24900f8c 000d0000 H.D$ H9t$....... - 07a0 41c78004 fcffff00 00000041 c78008fc A..........A.... - 07b0 ffff0000 000041c7 800cfcff ff000000 ......A......... - 07c0 0041c780 10fcffff 00000000 41c78014 .A..........A... - 07d0 fcffff00 00000041 c78018fc ffff0000 .......A........ - 07e0 000041c7 801cfcff ff000000 0041c780 ..A..........A.. - 07f0 20fcffff 00000000 41c78024 fcffff00 .......A..$.... - 0800 00000041 c78028fc ffff0000 000041c7 ...A..(.......A. - 0810 802cfcff ff000000 0041c780 30fcffff .,.......A..0... - 0820 00000000 41c78034 fcffff00 00000041 ....A..4.......A - 0830 c78038fc ffff0000 000041c7 803cfcff ..8.......A..<.. - 0840 ff000000 00488b44 2498c4c1 7a118000 .....H.D$...z... - 0850 fcffffc5 fa1000c4 c17a1180 40fcffff .........z..@... - 0860 c5fa1040 0441c780 48fcffff 00000000 ...@.A..H....... - 0870 c4c17a11 8044fcff ff41c780 4cfcffff ..z..D...A..L... - 0880 00000000 41c78050 fcffff00 00000041 ....A..P.......A - 0890 c78054fc ffff0000 000041c7 8058fcff ..T.......A..X.. - 08a0 ff000000 0041c780 5cfcffff 00000000 .....A..\....... - 08b0 41c78060 fcffff00 00000041 c78064fc A..`.......A..d. - 08c0 ffff0000 000041c7 8068fcff ff000000 ......A..h...... - 08d0 0041c780 6cfcffff 00000000 41c78070 .A..l.......A..p - 08e0 fcffff00 00000041 c78074fc ffff0000 .......A..t..... - 08f0 000041c7 8078fcff ff000000 0041c780 ..A..x.......A.. - 0900 7cfcffff 00000000 488b4424 a0c5fa10 |.......H.D$.... - 0910 00c4c17a 118080fc ffffc5fa 104004c4 ...z.........@.. - 0920 c17a1180 84fcffff c5fa1040 0841c780 .z.........@.A.. - 0930 8cfcffff 00000000 41c78090 fcffff00 ........A....... - 0940 00000041 c78094fc ffff0000 000041c7 ...A..........A. - 0950 8098fcff ff000000 0041c780 9cfcffff .........A...... - 0960 00000000 41c780a0 fcffff00 00000041 ....A..........A - 0970 c780a4fc ffff0000 000041c7 80a8fcff ..........A..... - 0980 ff000000 0041c780 acfcffff 00000000 .....A.......... - 0990 41c780b0 fcffff00 00000041 c780b4fc A..........A.... - 09a0 ffff0000 000041c7 80b8fcff ff000000 ......A......... - 09b0 0041c780 bcfcffff 00000000 488b4424 .A..........H.D$ - 09c0 a8c4c17a 118088fc ffffc5fa 1000c4c1 ...z............ - 09d0 7a1180c0 fcffffc5 fa104004 c4c17a11 z.........@...z. - 09e0 80c4fcff ffc5fa10 4008c4c1 7a1180c8 ........@...z... - 09f0 fcffffc5 fa10400c 41c780d0 fcffff00 ......@.A....... - 0a00 000000c4 c17a1180 ccfcffff 41c780d4 .....z......A... - 0a10 fcffff00 00000041 c780d8fc ffff0000 .......A........ - 0a20 000041c7 80dcfcff ff000000 0041c780 ..A..........A.. - 0a30 e0fcffff 00000000 41c780e4 fcffff00 ........A....... - 0a40 00000041 c780e8fc ffff0000 000041c7 ...A..........A. - 0a50 80ecfcff ff000000 0041c780 f0fcffff .........A...... - 0a60 00000000 41c780f4 fcffff00 00000041 ....A..........A - 0a70 c780f8fc ffff0000 000041c7 80fcfcff ..........A..... - 0a80 ff000000 00488b44 24b0c5fa 1000c4c1 .....H.D$....... - 0a90 7a118000 fdffffc5 fa104004 c4c17a11 z.........@...z. - 0aa0 8004fdff ffc5fa10 4008c4c1 7a118008 ........@...z... - 0ab0 fdffffc5 fa10400c c4c17a11 800cfdff ......@...z..... - 0ac0 ffc5fa10 401041c7 8014fdff ff000000 ....@.A......... - 0ad0 0041c780 18fdffff 00000000 41c7801c .A..........A... - 0ae0 fdffff00 00000041 c78020fd ffff0000 .......A.. ..... - 0af0 000041c7 8024fdff ff000000 0041c780 ..A..$.......A.. - 0b00 28fdffff 00000000 41c7802c fdffff00 (.......A..,.... - 0b10 00000041 c78030fd ffff0000 000041c7 ...A..0.......A. - 0b20 8034fdff ff000000 0041c780 38fdffff .4.......A..8... - 0b30 00000000 41c7803c fdffff00 000000c4 ....A..<........ - 0b40 c17a1180 10fdffff c5fa1002 c4c17a11 .z............z. - 0b50 8040fdff ffc5fa10 4204c4c1 7a118044 .@......B...z..D - 0b60 fdffffc5 fa104208 c4c17a11 8048fdff ......B...z..H.. - 0b70 ffc5fa10 420cc4c1 7a11804c fdffffc5 ....B...z..L.... - 0b80 fa104210 c4c17a11 8050fdff ffc5fa10 ..B...z..P...... - 0b90 421441c7 8058fdff ff000000 0041c780 B.A..X.......A.. - 0ba0 5cfdffff 00000000 41c78060 fdffff00 \.......A..`.... - 0bb0 00000041 c78064fd ffff0000 000041c7 ...A..d.......A. - 0bc0 8068fdff ff000000 0041c780 6cfdffff .h.......A..l... - 0bd0 00000000 41c78070 fdffff00 00000041 ....A..p.......A - 0be0 c78074fd ffff0000 000041c7 8078fdff ..t.......A..x.. - 0bf0 ff000000 0041c780 7cfdffff 00000000 .....A..|....... - 0c00 c4c17a11 8054fdff ffc5fa10 07c4c17a ..z..T.........z - 0c10 118080fd ffffc5fa 104704c4 c17a1180 .........G...z.. /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39080000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 3d2c0000 00420e10 8f02420e ....=,...B....B. + 0020 00000000 7d150000 00420e10 8f02420e ....}....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 1b260a0e ..A.8..G.....&.. + 0040 8606410e 38830747 0ee00203 ab100a0e ..A.8..G........ 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0060 440e0848 0b000000 D..H.... /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_SKYLAKEX.o (disasm) @@ -20,1291 +20,430 @@ mov %r8,-offset(%rsp) mov %r9,offset(%rsp) mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov offset(%rsp),%r13 test %rsi,%rsi jle + mov %rcx,%r11 + mov %r9,%rbp + mov %r11,%r15 + imul %r11,%r9 + shl $something,%r15 + mov %rcx,%rax + imul %r8,%rax + mov %rdi,%r10 mov %r8,%r12 - imul %rcx,%r12 - mov %rcx,%r14 + mov %r15,offset(%rsp) + lea offset(,%r11,8),%r15 + add %r12,%r9 + kmovq %r15,%k2 + mov offset(%rsp),%r12 + mov %r10,%r15 + and $something,%r15d + lea (%rax,%rcx,2),%r8 + mov %r15,-offset(%rsp) + lea (%r12,%r9,4),%r15 + lea offset(%rbp,%rax,1),%r9 + lea (%r8,%rcx,1),%rdi + lea (%r12,%r9,4),%r12 mov offset(%rsp),%r9 - lea (%rcx,%r12,1),%rbp - lea (%rcx,%rbp,1),%rbx - lea (%rcx,%rbx,1),%r11 - lea (%r11,%rcx,1),%r10 - lea (%rcx,%r10,1),%rax - lea (%rax,%rcx,1),%r8 - lea (%rcx,%r8,1),%rdi - lea (%rcx,%rdi,1),%rsi - mov %rax,-offset(%rsp) - lea (%rcx,%rsi,1),%rax - lea (%rcx,%rax,1),%rdx - mov %rax,-offset(%rsp) - lea (%rcx,%rdx,1),%rax - lea (%rcx,%rax,1),%r13 - mov %r13,%rcx - mov %r14,%r13 - add %rcx,%r13 - mov %rcx,-offset(%rsp) - mov %r13,%rcx - mov %r14,%r13 - add %rcx,%r13 - mov %rcx,-offset(%rsp) - mov %r9,%rcx - sar $something,%rcx - and $something,%r9d - mov %rcx,offset(%rsp) + lea (%rdi,%rcx,1),%rsi + lea (%rsi,%rcx,1),%rcx + sub %rax,%rdi + lea offset(%rbp,%r9,8),%r9 + lea (%rcx,%r11,1),%rdx + shl $something,%rdi + sub %rax,%rcx mov %r9,offset(%rsp) - mov %r14,%rcx - shl $something,%r9 + mov %r11,%r9 + sub %rax,%rsi + mov %rdi,offset(%rsp) + mov %r11,%r14 + lea offset(,%rcx,4),%rdi + lea offset(,%r11,4),%r11 + mov %rdx,%rcx + add %r9,%rdx + sub %rax,%rdx + sub %rax,%r8 + shl $something,%rsi + sub %rax,%rcx + mov %r11,%rax + mov %rsi,offset(%rsp) + neg %rax + lea offset(,%rdx,4),%rsi + lea offset(%rbp),%rdx + imul %rbp,%rax + imul %r11,%rdx shl $something,%rcx - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 mov %rcx,offset(%rsp) - mov offset(%rsp),%rcx - shl $something,%r9 - add %rcx,%r9 - mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add %rcx,%r12 - lea (%r9,%r12,4),%r12 - add %rcx,%rbp - lea (%r9,%rbp,4),%rbp - mov %r12,offset(%rsp) - mov %rcx,%r12 - mov %rbp,offset(%rsp) - mov %r12,%rbp - add %r12,%rbx - add %rbp,%rdx - mov %r9,%r12 - add %rbp,%rax - lea (%r12,%rdx,4),%rdx - mov %rdx,offset(%rsp) - add %rbp,%r11 - lea (%r12,%rax,4),%rdx - add %rbp,%r10 - mov -offset(%rsp),%rax - mov %r9,%rcx - lea (%r9,%r11,4),%r11 - lea (%r9,%r10,4),%r10 - lea (%r9,%rbx,4),%rbx - mov -offset(%rsp),%r9 - add %rbp,%rax - add %rbp,%r9 - mov %rdx,offset(%rsp) - lea (%r12,%rax,4),%rdx - mov -offset(%rsp),%rax - add %rbp,%rsi - mov %r10,offset(%rsp) - add %rbp,%r8 - lea (%rcx,%r9,4),%r10 - add %rbp,%rdi - mov %r11,offset(%rsp) - mov %r10,offset(%rsp) - lea (%rcx,%rsi,4),%r11 - lea (%rcx,%r8,4),%r10 - lea (%rcx,%rdi,4),%rdi - add %rbp,%rax - mov -offset(%rsp),%rcx - lea (%r12,%rax,4),%rax - add %rbp,%rcx - mov %rax,offset(%rsp) - lea offset(%r13,%rbp,1),%rax - mov %r11,offset(%rsp) - lea (%r12,%rax,4),%rax - lea (%r12,%rcx,4),%r11 - mov %r10,offset(%rsp) - mov %rax,offset(%rsp) - mov %rbx,offset(%rsp) + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + mov %rcx,offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) mov %rdi,offset(%rsp) - mov %r11,offset(%rsp) - mov %rdx,offset(%rsp) - mov offset(%rsp),%rsi - mov -offset(%rsp),%rcx - lea (%rsi,%r13,1),%rax - add %rbp,%rax - lea (%r12,%rax,4),%rax - mov %rax,offset(%rsp) - mov %rsi,%rax - imul %rbp,%rax + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rcx,offset(%rsp) + mov %r10,%rbx + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + sar $something,%rbx + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rbx,offset(%rsp) shl $something,%r14 - mov offset(%rsp),%r9 - add %rcx,%rax - lea (%r12,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - mov %rbp,-offset(%rsp) - movq $something,offset(%rsp) - add %rcx,%rax - lea (%r12,%rax,4),%rax - mov %rax,offset(%rsp) - lea offset(%rbp),%rax - imul %rsi,%rax - movq $something,offset(%rsp) - mov %r15,%r10 - add %rcx,%rax /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_SKYLAKEX.o (objdump) @@ -2,711 +2,347 @@ /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24900000 0048c1fe 0448897c .H..$....H...H.| - 0020 24784889 94249800 00004889 8c248800 $xH..$....H..$.. - 0030 00004c89 4424c04c 894c2458 4889b424 ..L.D$.L.L$XH..$ - 0040 c0010000 4c8bbc24 18020000 4885f60f ....L..$....H... - 0050 8e971d00 004d89c4 4c0fafe1 4989ce4c .....M..L...I..L - 0060 8b4c2478 4a8d2c21 488d1c29 4c8d1c19 .L$xJ.,!H..)L... - 0070 4d8d140b 4a8d0411 4c8d0408 4a8d3c01 M...J...L...J.<. - 0080 488d3439 48894424 98488d04 31488d14 H.49H.D$.H..1H.. - 0090 01488944 24a0488d 04114c8d 2c014c89 .H.D$.H...L.,.L. - 00a0 e94d89f5 4901cd48 894c2488 4c89e94d .M..I..H.L$.L..M - 00b0 89f54901 cd48894c 24904c89 c948c1f9 ..I..H.L$.L..H.. - 00c0 044183e1 0f48894c 24704c89 4c24504c .A...H.L$pL.L$PL - 00d0 89f149c1 e10648c1 e1024c89 8c24b801 ..I...H...L..$.. - 00e0 00004c8b 8c24c001 00004889 8c24a001 ..L..$....H..$.. - 00f0 0000488b 4c245849 c1e10449 01c94c89 ..H.L$XI...I..L. - 0100 8c248000 00004c8b 8c249800 00004901 .$....L..$....I. - 0110 cc4f8d24 a14801cd 498d2ca9 4c89a424 .O.$.H..I.,.L..$ - 0120 a8000000 4989cc48 89ac24b8 0000004c ....I..H..$....L - 0130 89e54c01 e34801ea 4d89cc48 01e8498d ..L..H..M..H..I. - 0140 14944889 94244801 00004901 eb498d14 ..H..$H...I..I.. - 0150 844901ea 488b4424 884c89c9 4f8d1c99 .I..H.D$.L..O... - 0160 4f8d1491 498d1c99 4c8b4c24 984801e8 O...I...L.L$.H.. - 0170 4901e948 89942458 01000049 8d148448 I..H..$X...I...H - 0180 8b442490 4801ee4c 899424e8 00000049 .D$.H..L..$....I - 0190 01e84e8d 14894801 ef4c899c 24d80000 ..N...H..L..$... - 01a0 004c8994 24f80000 004c8d1c b14e8d14 .L..$....L...N.. - 01b0 81488d3c b94801e8 488b4c24 a0498d04 .H.<.H..H.L$.I.. - 01c0 844801e9 48898424 78010000 498d442d .H..H..$x...I.D- - 01d0 004c899c 24280100 00498d04 844d8d1c .L..$(...I...M.. - 01e0 8c4c8994 24080100 00488984 24880100 .L..$....H..$... - 01f0 0048899c 24c80000 004889bc 24180100 .H..$....H..$... - 0200 004c899c 24380100 00488994 24680100 .L..$8...H..$h.. - 0210 00488bb4 24880000 00488b4c 24c04a8d .H..$....H.L$.J. - 0220 042e4801 e8498d04 84488984 24980100 ..H..I...H..$... - 0230 004889f0 480fafc5 49c1e606 4c8b4c24 .H..H...I...L.L$ - 0240 704801c8 498d0484 48898424 a0000000 pH..I...H..$.... - 0250 488d4501 480fafc6 48896c24 9048c744 H.E.H...H.l$.H.D - 0260 24680000 00004801 c8498d04 84488984 $h....H..I...H.. - 0270 24b00000 00488d45 02480faf c648c744 $....H.E.H...H.D - 0280 24600000 00004d89 fa4801c8 498d0484 $`....M..H..I... - 0290 48898424 c0000000 488d4503 480fafc6 H..$....H.E.H... - 02a0 4801c849 8d048448 898424d0 00000048 H..I...H..$....H - 02b0 8d450448 0fafc648 01c8498d 04844889 .E.H...H..I...H. - 02c0 8424e000 0000488d 4505480f afc64801 .$....H.E.H...H. - 02d0 c8498d04 84488984 24f00000 00488d45 .I...H..$....H.E - 02e0 06480faf c64801c8 498d0484 48898424 .H...H..I...H..$ - 02f0 00010000 488d4507 480fafc6 4801c849 ....H.E.H...H..I - 0300 8d048448 89842410 01000048 8d450848 ...H..$....H.E.H - 0310 0fafc648 01c8498d 04844889 84242001 ...H..I...H..$ . - 0320 0000488d 4509480f afc64801 c8498d04 ..H.E.H...H..I.. - 0330 84488984 24300100 00488d45 0a480faf .H..$0...H.E.H.. - 0340 c64801c8 498d0484 48898424 40010000 .H..I...H..$@... - 0350 488d450b 480fafc6 4801c849 8d048448 H.E.H...H..I...H - 0360 89842450 01000048 8d450c48 0fafc648 ..$P...H.E.H...H - 0370 01c8498d 04844889 84246001 0000488d ..I...H..$`...H. - 0380 450d480f afc64801 c8498d04 84488984 E.H...H..I...H.. - 0390 24700100 00488d45 0e480faf c64801c8 $p...H.E.H...H.. - 03a0 498d0484 48898424 80010000 488d450f I...H..$....H.E. - 03b0 480fafc6 488b7424 784801c8 498d0484 H...H.t$xH..I... - 03c0 48898424 90010000 4889f048 83e0f048 H..$....H..H...H - 03d0 01c84889 4424d04c 89c848c1 e00a4889 ..H.D$.L..H...H. - 03e0 8424a801 00004c89 c848c1e0 044801c8 .$....L..H...H.. - 03f0 48898424 b0010000 4889f083 e00e4889 H..$....H.....H. - 0400 8424c801 00004889 f083e00c 83e60848 .$....H........H - 0410 89b424d8 01000048 898424d0 0100004c ..$....H..$....L - 0420 89f6e927 01000066 0f1f8400 00000000 ...'...f........ - 0430 488b4424 60488bbc 24b00000 00488b9c H.D$`H..$....H.. - 0440 24f00000 004801c7 48897c24 98488bbc $....H..H.|$.H.. - 0450 24c00000 004801c3 4801c748 897c24a0 $....H..H..H.|$. - 0460 488bbc24 d0000000 48895c24 c84801c7 H..$....H.\$.H.. - 0470 48897c24 a8488bbc 24e00000 004c8b8c H.|$.H..$....L.. - 0480 24a00000 004801c7 48897c24 b0488b8c $....H..H.|$.H.. - 0490 24100100 00488bbc 24000100 004c8bbc $....H..$....L.. - 04a0 24200100 004c8bb4 24300100 004c8bac $ ...L..$0...L.. - 04b0 24400100 004c8ba4 24500100 00488bac $@...L..$P...H.. - 04c0 24600100 00488b9c 24700100 004c8b9c $`...H..$p...L.. - 04d0 24800100 004901c1 4801c748 01c14901 $....I..H..H..I. - 04e0 c74901c6 4901c549 01c44801 c54801c3 .I..I..I..H..H.. - 04f0 4901c348 03842490 01000048 837c2470 I..H..$....H.|$p - 0500 004889c2 488b4424 c00f8f2e 01000048 .H..H.D$.......H - 0510 837c2450 00741348 39442490 0f8e7e10 .|$P.t.H9D$...~. - 0520 00004c03 9424b801 00004883 44249010 ..L..$....H.D$.. - 0530 48017424 60488344 24684048 8b442490 H.t$`H.D$h@H.D$. - 0540 483b8424 80000000 0f848218 0000488b H;.$..........H. - 0550 7c24c048 397c2490 0f8dd2fe ffff488b |$.H9|$.......H. - 0560 44246848 8bbc24b8 00000048 8b9c24c8 D$hH..$....H..$. - 0570 00000048 01c74889 7c249848 8bbc24d8 ...H..H.|$.H..$. - 0580 00000048 01c34801 c748895c 24a04889 ...H..H..H.\$.H. - 0590 7c24a848 8b9c24e8 00000048 8bbc24f8 |$.H..$....H..$. - 05a0 00000048 01c34801 c748895c 24b04889 ...H..H..H.\$.H. - 05b0 7c24c84c 8b8c24a8 00000048 8bbc2408 |$.L..$....H..$. - 05c0 01000048 8b8c2418 0100004c 8bbc2428 ...H..$....L..$( - 05d0 0100004c 8bb42438 0100004c 8bac2448 ...L..$8...L..$H - 05e0 0100004c 8ba42458 01000048 8bac2468 ...L..$X...H..$h - 05f0 01000048 8b9c2478 0100004c 8b9c2488 ...H..$x...L..$. - 0600 01000049 01c14801 c74801c1 4901c749 ...I..H..H..I..I - 0610 01c64901 c54901c4 4801c548 01c34901 ..I..I..H..H..I. - 0620 c3480384 24980100 0048837c 24700048 .H..$....H.|$p.H - 0630 89c2488b 4424c00f 8ed2feff ff4c894c ..H.D$.......L.L - 0640 24b84c89 94241802 00004d8d 82000400 $.L..$....M..... - 0650 004989d1 4d89da48 89442488 488b5424 .I..M..H.D$.H.T$ - 0660 c84989f3 eb71662e 0f1f8400 00000000 .I...qf......... - 0670 48834424 b8404883 44249840 48834424 H.D$.@H.D$.@H.D$ - 0680 a0404883 4424a840 48834424 b0404883 .@H.D$.@H.D$.@H. - 0690 c2404883 c7404883 c1404983 c7404983 .@H..@H..@I..@I. - 06a0 c6404983 c5404983 c4404883 c5404883 .@I..@I..@H..@H. - 06b0 c3404983 c2404983 c1404883 44248810 .@I..@I..@H.D$.. - 06c0 4981c000 04000048 8b442488 483b4424 I......H.D$.H;D$ - 06d0 d00f8499 0e000049 8d8000fc ffff4889 .......I......H. - 06e0 4424c848 8b442488 48394424 907f8148 D$.H.D$.H9D$...H - 06f0 8b4424b8 488b7424 88c5fa10 00488b44 .D$.H.t$.....H.D - 0700 24984c01 d8488944 2418488b 4424a04c $.L..H.D$.H.D$.L - 0710 01d84889 44241048 8b4424a8 4c01d848 ..H.D$.H.D$.L..H - 0720 894424f8 488b4424 b04c01d8 48894424 .D$.H.D$.L..H.D$ - 0730 084a8d04 1a488944 24f04a8d 041f4889 .J...H.D$.J...H. - 0740 04244a8d 04194889 4424e84b 8d041f48 .$J...H.D$.K...H - 0750 89442448 4b8d041e 48894424 404b8d44 .D$HK...H.D$@K.D - 0760 1d004889 4424384b 8d041c48 894424e0 ..H.D$8K...H.D$. - 0770 4a8d441d 00488944 24304a8d 041b4889 J.D..H.D$0J...H. - 0780 4424d84b 8d041a48 89442428 4b8d0419 D$.K...H.D$(K... - 0790 48894424 20483974 24900f8c 000d0000 H.D$ H9t$....... - 07a0 41c78004 fcffff00 00000041 c78008fc A..........A.... - 07b0 ffff0000 000041c7 800cfcff ff000000 ......A......... - 07c0 0041c780 10fcffff 00000000 41c78014 .A..........A... - 07d0 fcffff00 00000041 c78018fc ffff0000 .......A........ - 07e0 000041c7 801cfcff ff000000 0041c780 ..A..........A.. - 07f0 20fcffff 00000000 41c78024 fcffff00 .......A..$.... - 0800 00000041 c78028fc ffff0000 000041c7 ...A..(.......A. - 0810 802cfcff ff000000 0041c780 30fcffff .,.......A..0... - 0820 00000000 41c78034 fcffff00 00000041 ....A..4.......A - 0830 c78038fc ffff0000 000041c7 803cfcff ..8.......A..<.. - 0840 ff000000 00488b44 2498c4c1 7a118000 .....H.D$...z... - 0850 fcffffc5 fa1000c4 c17a1180 40fcffff .........z..@... - 0860 c5fa1040 0441c780 48fcffff 00000000 ...@.A..H....... - 0870 c4c17a11 8044fcff ff41c780 4cfcffff ..z..D...A..L... - 0880 00000000 41c78050 fcffff00 00000041 ....A..P.......A - 0890 c78054fc ffff0000 000041c7 8058fcff ..T.......A..X.. - 08a0 ff000000 0041c780 5cfcffff 00000000 .....A..\....... - 08b0 41c78060 fcffff00 00000041 c78064fc A..`.......A..d. - 08c0 ffff0000 000041c7 8068fcff ff000000 ......A..h...... - 08d0 0041c780 6cfcffff 00000000 41c78070 .A..l.......A..p - 08e0 fcffff00 00000041 c78074fc ffff0000 .......A..t..... - 08f0 000041c7 8078fcff ff000000 0041c780 ..A..x.......A.. - 0900 7cfcffff 00000000 488b4424 a0c5fa10 |.......H.D$.... - 0910 00c4c17a 118080fc ffffc5fa 104004c4 ...z.........@.. - 0920 c17a1180 84fcffff c5fa1040 0841c780 .z.........@.A.. - 0930 8cfcffff 00000000 41c78090 fcffff00 ........A....... - 0940 00000041 c78094fc ffff0000 000041c7 ...A..........A. - 0950 8098fcff ff000000 0041c780 9cfcffff .........A...... - 0960 00000000 41c780a0 fcffff00 00000041 ....A..........A - 0970 c780a4fc ffff0000 000041c7 80a8fcff ..........A..... - 0980 ff000000 0041c780 acfcffff 00000000 .....A.......... - 0990 41c780b0 fcffff00 00000041 c780b4fc A..........A.... - 09a0 ffff0000 000041c7 80b8fcff ff000000 ......A......... - 09b0 0041c780 bcfcffff 00000000 488b4424 .A..........H.D$ - 09c0 a8c4c17a 118088fc ffffc5fa 1000c4c1 ...z............ - 09d0 7a1180c0 fcffffc5 fa104004 c4c17a11 z.........@...z. - 09e0 80c4fcff ffc5fa10 4008c4c1 7a1180c8 ........@...z... - 09f0 fcffffc5 fa10400c 41c780d0 fcffff00 ......@.A....... - 0a00 000000c4 c17a1180 ccfcffff 41c780d4 .....z......A... - 0a10 fcffff00 00000041 c780d8fc ffff0000 .......A........ - 0a20 000041c7 80dcfcff ff000000 0041c780 ..A..........A.. - 0a30 e0fcffff 00000000 41c780e4 fcffff00 ........A....... - 0a40 00000041 c780e8fc ffff0000 000041c7 ...A..........A. - 0a50 80ecfcff ff000000 0041c780 f0fcffff .........A...... - 0a60 00000000 41c780f4 fcffff00 00000041 ....A..........A - 0a70 c780f8fc ffff0000 000041c7 80fcfcff ..........A..... - 0a80 ff000000 00488b44 24b0c5fa 1000c4c1 .....H.D$....... - 0a90 7a118000 fdffffc5 fa104004 c4c17a11 z.........@...z. - 0aa0 8004fdff ffc5fa10 4008c4c1 7a118008 ........@...z... - 0ab0 fdffffc5 fa10400c c4c17a11 800cfdff ......@...z..... - 0ac0 ffc5fa10 401041c7 8014fdff ff000000 ....@.A......... - 0ad0 0041c780 18fdffff 00000000 41c7801c .A..........A... - 0ae0 fdffff00 00000041 c78020fd ffff0000 .......A.. ..... - 0af0 000041c7 8024fdff ff000000 0041c780 ..A..$.......A.. - 0b00 28fdffff 00000000 41c7802c fdffff00 (.......A..,.... - 0b10 00000041 c78030fd ffff0000 000041c7 ...A..0.......A. - 0b20 8034fdff ff000000 0041c780 38fdffff .4.......A..8... - 0b30 00000000 41c7803c fdffff00 000000c4 ....A..<........ - 0b40 c17a1180 10fdffff c5fa1002 c4c17a11 .z............z. - 0b50 8040fdff ffc5fa10 4204c4c1 7a118044 .@......B...z..D - 0b60 fdffffc5 fa104208 c4c17a11 8048fdff ......B...z..H.. - 0b70 ffc5fa10 420cc4c1 7a11804c fdffffc5 ....B...z..L.... - 0b80 fa104210 c4c17a11 8050fdff ffc5fa10 ..B...z..P...... - 0b90 421441c7 8058fdff ff000000 0041c780 B.A..X.......A.. - 0ba0 5cfdffff 00000000 41c78060 fdffff00 \.......A..`.... - 0bb0 00000041 c78064fd ffff0000 000041c7 ...A..d.......A. - 0bc0 8068fdff ff000000 0041c780 6cfdffff .h.......A..l... - 0bd0 00000000 41c78070 fdffff00 00000041 ....A..p.......A - 0be0 c78074fd ffff0000 000041c7 8078fdff ..t.......A..x.. - 0bf0 ff000000 0041c780 7cfdffff 00000000 .....A..|....... - 0c00 c4c17a11 8054fdff ffc5fa10 07c4c17a ..z..T.........z - 0c10 118080fd ffffc5fa 104704c4 c17a1180 .........G...z.. /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39080000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutncopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 3d2c0000 00420e10 8f02420e ....=,...B....B. + 0020 00000000 7d150000 00420e10 8f02420e ....}....B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 1b260a0e ..A.8..G.....&.. + 0040 8606410e 38830747 0ee00203 ab100a0e ..A.8..G........ 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0060 440e0848 0b000000 D..H.... /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_COOPERLAKE.o (disasm) @@ -20,1251 +20,436 @@ mov %r8,-offset(%rsp) mov %r9,offset(%rsp) mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov offset(%rsp),%r14 test %rsi,%rsi jle - mov %r8,%rbp - imul %rcx,%rbp - mov %rcx,%r14 - mov offset(%rsp),%r9 - lea (%rcx,%rbp,1),%rbx - lea (%rcx,%rbx,1),%r11 - lea (%rcx,%r11,1),%r10 - lea (%r10,%rcx,1),%rax - lea (%rcx,%rax,1),%r8 + mov %r8,%rax + imul %rcx,%rax + mov %rcx,%rbp + mov %rbp,%r11 + mov %r8,%r12 + shl $something,%r11 + lea (%rax,%rcx,2),%r8 + mov %rdi,%r10 + mov %r11,offset(%rsp) lea (%r8,%rcx,1),%rdi - lea (%rcx,%rdi,1),%rsi - mov %rax,-offset(%rsp) - lea (%rcx,%rsi,1),%rax - lea (%rcx,%rax,1),%rdx - mov %rax,-offset(%rsp) - lea (%rcx,%rdx,1),%rax - lea (%rcx,%rax,1),%r13 - lea (%rcx,%r13,1),%r12 - mov %r12,%rcx - mov %r14,%r12 - add %rcx,%r12 - mov %rcx,-offset(%rsp) - mov %r12,%rcx - mov %r14,%r12 - add %rcx,%r12 - mov %rcx,-offset(%rsp) - mov %r9,%rcx - sar $something,%rcx - and $something,%r9d - mov %rcx,offset(%rsp) - mov %r9,offset(%rsp) - mov %r14,%rcx - shl $something,%r9 - shl $something,%rcx - mov %r9,offset(%rsp) + lea offset(,%rbp,8),%r11 + mov %r9,%r13 + lea (%rdi,%rcx,1),%rsi + imul %rbp,%r9 + kmovq %r11,%k2 + mov %r10,%r11 + lea (%rsi,%rcx,1),%rcx + and $something,%r11d + lea (%rcx,%rbp,1),%rdx + mov %r11,-offset(%rsp) + mov %rbp,%r15 + mov %rbp,%r11 + mov offset(%rsp),%rbp + add %r12,%r9 + lea offset(%rbp,%r9,4),%r12 + mov %r13,%rbp + lea offset(%r13,%rax,1),%r9 + mov offset(%rsp),%r13 + sub %rax,%rdi + lea offset(%r13,%r9,4),%r13 mov offset(%rsp),%r9 - mov %rcx,offset(%rsp) - mov offset(%rsp),%rcx - shl $something,%r9 - add %rcx,%r9 + sub %rax,%rsi + lea offset(%rbp,%r9,8),%r9 + shl $something,%rdi + sub %rax,%rcx mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add %rcx,%rbp - lea (%r9,%rbp,4),%rbp - add %rcx,%rbx - lea (%r9,%rbx,4),%rbx - mov %rbp,offset(%rsp) - mov %rcx,%rbp + mov %rdi,offset(%rsp) + mov %r11,%r9 + lea offset(,%rsi,4),%rdi + lea offset(,%r11,4),%r11 + mov %rdi,offset(%rsp) + lea offset(,%rcx,4),%rdi + mov %rdx,%rcx + add %r9,%rdx + sub %rax,%rcx + sub %rax,%rdx + sub %rax,%r8 + mov %r11,%rax + lea offset(,%rdx,4),%rsi + neg %rax + lea offset(%rbp),%rdx + imul %rbp,%rax + imul %r11,%rdx + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + lea offset(,%rcx,4),%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + mov %r10,%rbx + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rcx,offset(%rsp) + sar $something,%rbx + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx mov %rbx,offset(%rsp) - mov %rbp,%rbx - add %rbp,%r11 - add %rbx,%rdx - mov %r9,%rbp - add %rbx,%rax - lea offset(%rbp,%rdx,4),%rdx - mov %rdx,offset(%rsp) - add %rbx,%r10 - lea offset(%rbp,%rax,4),%rdx - mov -offset(%rsp),%rax - mov %r9,%rcx - lea (%r9,%r11,4),%r11 - lea (%r9,%r10,4),%r10 - add %rbx,%r13 - mov -offset(%rsp),%r9 - add %rbx,%rax - mov %rdx,offset(%rsp) - lea offset(%rbp,%r13,4),%rdx - add %rbx,%r9 - mov %rdx,offset(%rsp) - lea offset(%rbp,%rax,4),%rdx - mov -offset(%rsp),%rax - add %rbx,%rsi - mov %r10,offset(%rsp) - add %rbx,%r8 - lea (%rcx,%r9,4),%r10 - add %rbx,%rdi - mov %r11,offset(%rsp) - mov %r10,offset(%rsp) - lea (%rcx,%rsi,4),%r11 - lea (%rcx,%r8,4),%r10 - lea (%rcx,%rdi,4),%rdi - add %rbx,%rax - mov -offset(%rsp),%rcx - lea offset(%rbp,%rax,4),%rax - add %rbx,%rcx - mov %rax,offset(%rsp) - lea (%r12,%rbx,1),%rax - mov %r11,offset(%rsp) - lea offset(%rbp,%rax,4),%rax - lea offset(%rbp,%rcx,4),%r11 - mov %r10,offset(%rsp) - mov %rax,offset(%rsp) + shl $something,%r15 + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + shl $something,%r8 + vmovss %xmm14,-offset(%rsp) + lea (%rdx,%rax,1),%rdi + mov %r10,%rax + and $something,%rax mov %rdi,offset(%rsp) + mov %rax,%rdi + mov -offset(%rsp),%rax mov %r11,offset(%rsp) - mov %rdx,offset(%rsp) - mov offset(%rsp),%rsi - mov -offset(%rsp),%rcx - lea (%rsi,%r12,1),%rax - add %rbx,%rax - lea offset(%rbp,%rax,4),%rax - mov %rax,offset(%rsp) - mov %rsi,%rax - imul %rbx,%rax - shl $something,%r14 /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_COOPERLAKE.o (objdump) @@ -2,695 +2,364 @@ /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24900000 0048c1fe 0448897c .H..$....H...H.| - 0020 24784889 94249800 00004889 8c248800 $xH..$....H..$.. - 0030 00004c89 4424c04c 894c2458 4889b424 ..L.D$.L.L$XH..$ - 0040 c0010000 4c8bbc24 18020000 4885f60f ....L..$....H... - 0050 8ec71c00 004c89c5 480fafe9 4989ce4c .....L..H...I..L - 0060 8b4c2478 488d1c29 4c8d1c19 4e8d1419 .L$xH..)L...N... - 0070 498d040a 4c8d0401 498d3c08 488d3439 I...L...I.<.H.49 - 0080 48894424 a0488d04 31488d14 01488944 H.D$.H..1H...H.D - 0090 2498488d 04114c8d 2c014e8d 24294c89 $.H...L.,.N.$)L. - 00a0 e14d89f4 4901cc48 894c2488 4c89e14d .M..I..H.L$.L..M - 00b0 89f44901 cc48894c 24904c89 c948c1f9 ..I..H.L$.L..H.. - 00c0 044183e1 0f48894c 24704c89 4c24504c .A...H.L$pL.L$PL - 00d0 89f149c1 e10648c1 e1024c89 8c24b801 ..I...H...L..$.. - 00e0 00004c8b 8c24c001 00004889 8c24a001 ..L..$....H..$.. - 00f0 0000488b 4c245849 c1e10449 01c94c89 ..H.L$XI...I..L. - 0100 8c248000 00004c8b 8c249800 00004801 .$....L..$....H. - 0110 cd498d2c a94801cb 498d1c99 4889ac24 .I.,.H..I...H..$ - 0120 a8000000 4889cd48 899c24b8 00000048 ....H..H..$....H - 0130 89eb4901 eb4801da 4c89cd48 01d8488d ..I..H..L..H..H. - 0140 54950048 89942438 01000049 01da488d T..H..$8...I..H. - 0150 54850048 8b442488 4c89c94f 8d1c994f T..H.D$.L..O...O - 0160 8d149149 01dd4c8b 4c24a048 01d84889 ...I..L.L$.H..H. - 0170 94244801 00004a8d 54ad0049 01d94889 .$H...J.T..I..H. - 0180 94245801 0000488d 54850048 8b442490 .$X...H.T..H.D$. - 0190 4801de4c 899424d8 00000049 01d84e8d H..L..$....I..N. - 01a0 14894801 df4c899c 24c80000 004c8994 ..H..L..$....L.. - 01b0 24e80000 004c8d1c b14e8d14 81488d3c $....L...N...H.< - 01c0 b94801d8 488b4c24 98488d44 85004801 .H..H.L$.H.D..H. - 01d0 d9488984 24780100 00498d04 1c4c899c .H..$x...I...L.. - 01e0 24180100 00488d44 85004c8d 5c8d004c $....H.D..L.\..L - 01f0 899424f8 00000048 89842488 01000048 ..$....H..$....H - 0200 89bc2408 0100004c 899c2428 01000048 ..$....L..$(...H - 0210 89942468 01000048 8bb42488 00000048 ..$h...H..$....H - 0220 8b4c24c0 4a8d0426 4801d848 8d448500 .L$.J..&H..H.D.. - 0230 48898424 98010000 4889f048 0fafc349 H..$....H..H...I - 0240 c1e6064c 8b4c2470 4801c848 8d448500 ...L.L$pH..H.D.. - 0250 48898424 a0000000 488d4301 480fafc6 H..$....H.C.H... - 0260 48895c24 9048c744 24680000 00004801 H.\$.H.D$h....H. - 0270 c8488d44 85004889 8424b000 0000488d .H.D..H..$....H. - 0280 4302480f afc648c7 44246000 000000c5 C.H...H.D$`..... - 0290 fa100500 00000048 01c8488d 44850048 .......H..H.D..H - 02a0 898424c0 00000048 8d430348 0fafc64d ..$....H.C.H...M - 02b0 89fa4801 c8488d44 85004889 8424d000 ..H..H.D..H..$.. - 02c0 0000488d 4304480f afc64801 c8488d44 ..H.C.H...H..H.D - 02d0 85004889 8424e000 0000488d 4305480f ..H..$....H.C.H. - 02e0 afc64801 c8488d44 85004889 8424f000 ..H..H.D..H..$.. - 02f0 0000488d 4306480f afc64801 c8488d44 ..H.C.H...H..H.D - 0300 85004889 84240001 0000488d 4307480f ..H..$....H.C.H. - 0310 afc64801 c8488d44 85004889 84241001 ..H..H.D..H..$.. - 0320 0000488d 4308480f afc64801 c8488d44 ..H.C.H...H..H.D - 0330 85004889 84242001 0000488d 4309480f ..H..$ ...H.C.H. - 0340 afc64801 c8488d44 85004889 84243001 ..H..H.D..H..$0. - 0350 0000488d 430a480f afc64801 c8488d44 ..H.C.H...H..H.D - 0360 85004889 84244001 0000488d 430b480f ..H..$@...H.C.H. - 0370 afc64801 c8488d44 85004889 84245001 ..H..H.D..H..$P. - 0380 0000488d 430c480f afc64801 c8488d44 ..H.C.H...H..H.D - 0390 85004889 84246001 0000488d 430d480f ..H..$`...H.C.H. - 03a0 afc64801 c8488d44 85004889 84247001 ..H..H.D..H..$p. - 03b0 0000488d 430e480f afc64801 c8488d44 ..H.C.H...H..H.D - 03c0 85004889 84248001 0000488d 430f480f ..H..$....H.C.H. - 03d0 afc6488b 74247848 01c8488d 44850048 ..H.t$xH..H.D..H - 03e0 89842490 01000048 89f04883 e0f04801 ..$....H..H...H. - 03f0 c8488944 24d04c89 c848c1e0 0a488984 .H.D$.L..H...H.. - 0400 24b00100 004c89c8 48c1e004 4801c848 $....L..H...H..H - 0410 898424a8 01000048 89f083e0 0e488984 ..$....H.....H.. - 0420 24c80100 004889f0 83e00c83 e6084889 $....H........H. - 0430 b424d801 00004889 8424d001 00004c89 .$....H..$....L. - 0440 f6e92801 0000662e 0f1f8400 00000000 ..(...f......... - 0450 488b4424 60488bbc 24b00000 004c8b8c H.D$`H..$....L.. - 0460 24a00000 004801c7 48897c24 98488bbc $....H..H.|$.H.. - 0470 24c00000 00488b8c 24100100 004801c7 $....H..$....H.. - 0480 48897c24 a0488bbc 24d00000 004c8bbc H.|$.H..$....L.. - 0490 24200100 004801c7 48897c24 a8488bbc $ ...H..H.|$.H.. - 04a0 24e00000 004c8bb4 24300100 004801c7 $....L..$0...H.. - 04b0 48897c24 b0488bbc 24f00000 004c8bac H.|$.H..$....L.. - 04c0 24400100 004801c7 48897c24 c84c8ba4 $@...H..H.|$.L.. - 04d0 24500100 00488bbc 24000100 00488bac $P...H..$....H.. - 04e0 24600100 00488b9c 24700100 004c8b9c $`...H..$p...L.. - 04f0 24800100 004901c1 4801c748 01c14901 $....I..H..H..I. - 0500 c74901c6 4901c549 01c44801 c54801c3 .I..I..I..H..H.. - 0510 4901c348 03842490 01000048 837c2470 I..H..$....H.|$p - 0520 004889c2 488b4424 c00f8f2e 01000048 .H..H.D$.......H - 0530 837c2450 00741348 39442490 0f8e1e10 .|$P.t.H9D$..... - 0540 00004c03 9424b801 00004883 44249010 ..L..$....H.D$.. - 0550 48017424 60488344 24684048 8b442490 H.t$`H.D$h@H.D$. - 0560 483b8424 80000000 0f849217 0000488b H;.$..........H. - 0570 7c24c048 397c2490 0f8dd2fe ffff488b |$.H9|$.......H. - 0580 44246848 8b9c24b8 00000048 8bbc24c8 D$hH..$....H..$. - 0590 00000048 01c34889 5c249848 8b9c24d8 ...H..H.\$.H..$. - 05a0 00000048 01c74801 c348897c 24a04889 ...H..H..H.|$.H. - 05b0 5c24a848 8bbc24e8 00000048 8b9c24f8 \$.H..$....H..$. - 05c0 00000048 01c74801 c348897c 24b04889 ...H..H..H.|$.H. - 05d0 5c24c84c 8b8c24a8 00000048 8bbc2408 \$.L..$....H..$. - 05e0 01000048 8b8c2418 0100004c 8bbc2428 ...H..$....L..$( - 05f0 0100004c 8bb42438 0100004c 8bac2448 ...L..$8...L..$H - 0600 0100004c 8ba42458 01000048 8bac2468 ...L..$X...H..$h - 0610 01000048 8b9c2478 0100004c 8b9c2488 ...H..$x...L..$. - 0620 01000049 01c14801 c74801c1 4901c749 ...I..H..H..I..I - 0630 01c64901 c54901c4 4801c548 01c34901 ..I..I..H..H..I. - 0640 c3480384 24980100 0048837c 24700048 .H..$....H.|$p.H - 0650 89c2488b 4424c00f 8ed2feff ff4c894c ..H.D$.......L.L - 0660 24b84c89 94241802 00004d8d 82000400 $.L..$....M..... - 0670 004989d1 4d89da48 89442488 488b5424 .I..M..H.D$.H.T$ - 0680 c84989f3 eb71662e 0f1f8400 00000000 .I...qf......... - 0690 48834424 b8404883 44249840 48834424 H.D$.@H.D$.@H.D$ - 06a0 a0404883 4424a840 48834424 b0404883 .@H.D$.@H.D$.@H. - 06b0 c2404883 c7404883 c1404983 c7404983 .@H..@H..@I..@I. - 06c0 c6404983 c5404983 c4404883 c5404883 .@I..@I..@H..@H. - 06d0 c3404983 c2404983 c1404883 44248810 .@I..@I..@H.D$.. - 06e0 4981c000 04000048 8b442488 483b4424 I......H.D$.H;D$ - 06f0 d00f8439 0e000049 8d8000fc ffff4889 ...9...I......H. - 0700 4424c848 8b442488 48394424 907f8148 D$.H.D$.H9D$...H - 0710 8b442498 488b7424 884c01d8 48894424 .D$.H.t$.L..H.D$ - 0720 38488b44 24a04c01 d8488904 24488b44 8H.D$.L..H..$H.D - 0730 24a84c01 d8488944 2420488b 4424b04c $.L..H.D$ H.D$.L - 0740 01d84889 4424f04a 8d041a48 89442430 ..H.D$.J...H.D$0 - 0750 4a8d041f 48894424 f84a8d04 19488944 J...H.D$.J...H.D - 0760 24284b8d 041f4889 4424184b 8d041e48 $(K...H.D$.K...H - 0770 894424e8 4b8d441d 00488944 24104b8d .D$.K.D..H.D$.K. - 0780 041c4889 4424e04a 8d441d00 48894424 ..H.D$.J.D..H.D$ - 0790 084a8d04 1b488944 24d84b8d 041a4889 .J...H.D$.K...H. - 07a0 4424484b 8d041948 89442440 48397424 D$HK...H.D$@H9t$ - 07b0 900f8ca9 0c000041 c78004fc ffff0000 .......A........ - 07c0 000041c7 8008fcff ff000000 0041c780 ..A..........A.. - 07d0 0cfcffff 00000000 41c78010 fcffff00 ........A....... - 07e0 00000041 c78014fc ffff0000 000041c7 ...A..........A. - 07f0 8018fcff ff000000 0041c780 1cfcffff .........A...... - 0800 00000000 41c78020 fcffff00 00000041 ....A.. .......A - 0810 c78024fc ffff0000 000041c7 8028fcff ..$.......A..(.. - 0820 ff000000 0041c780 2cfcffff 00000000 .....A..,....... - 0830 41c78030 fcffff00 00000041 c78034fc A..0.......A..4. - 0840 ffff0000 000041c7 8038fcff ff000000 ......A..8...... - 0850 0041c780 3cfcffff 00000000 488b4424 .A..<.......H.D$ - 0860 98c4c17a 118000fc ffffc5fa 100841c7 ...z..........A. - 0870 8048fcff ff000000 00c4c17a 118840fc .H.........z..@. - 0880 ffff41c7 804cfcff ff000000 0041c780 ..A..L.......A.. - 0890 50fcffff 00000000 41c78054 fcffff00 P.......A..T.... - 08a0 00000041 c78058fc ffff0000 000041c7 ...A..X.......A. - 08b0 805cfcff ff000000 0041c780 60fcffff .\.......A..`... - 08c0 00000000 41c78064 fcffff00 00000041 ....A..d.......A - 08d0 c78068fc ffff0000 000041c7 806cfcff ..h.......A..l.. - 08e0 ff000000 0041c780 70fcffff 00000000 .....A..p....... - 08f0 41c78074 fcffff00 000000c4 c17a1180 A..t.........z.. - 0900 44fcffff 41c78078 fcffff00 00000041 D...A..x.......A - 0910 c7807cfc ffff0000 0000488b 4424a0c5 ..|.......H.D$.. - 0920 fa1008c4 c17a1188 80fcffff c5fa1048 .....z.........H - 0930 0441c780 8cfcffff 00000000 41c78090 .A..........A... - 0940 fcffff00 00000041 c78094fc ffff0000 .......A........ - 0950 000041c7 8098fcff ff000000 0041c780 ..A..........A.. - 0960 9cfcffff 00000000 41c780a0 fcffff00 ........A....... - 0970 00000041 c780a4fc ffff0000 000041c7 ...A..........A. - 0980 80a8fcff ff000000 0041c780 acfcffff .........A...... - 0990 00000000 41c780b0 fcffff00 00000041 ....A..........A - 09a0 c780b4fc ffff0000 000041c7 80b8fcff ..........A..... - 09b0 ff000000 0041c780 bcfcffff 00000000 .....A.......... - 09c0 488b4424 a8c4c17a 118884fc ffffc4c1 H.D$...z........ - 09d0 7a118088 fcffffc5 fa1008c4 c17a1188 z............z.. - 09e0 c0fcffff c5fa1048 04c4c17a 1188c4fc .......H...z.... - 09f0 ffffc5fa 10480841 c780d0fc ffff0000 .....H.A........ - 0a00 0000c4c1 7a1188c8 fcffff41 c780d4fc ....z......A.... - 0a10 ffff0000 000041c7 80d8fcff ff000000 ......A......... - 0a20 0041c780 dcfcffff 00000000 c4c17a11 .A............z. - 0a30 80ccfcff ff41c780 e0fcffff 00000000 .....A.......... - 0a40 41c780e4 fcffff00 00000041 c780e8fc A..........A.... - 0a50 ffff0000 000041c7 80ecfcff ff000000 ......A......... - 0a60 0041c780 f0fcffff 00000000 41c780f4 .A..........A... - 0a70 fcffff00 00000041 c780f8fc ffff0000 .......A........ - 0a80 000041c7 80fcfcff ff000000 00488b44 ..A..........H.D - 0a90 24b0c5fa 1008c4c1 7a118800 fdffffc5 $.......z....... - 0aa0 fa104804 c4c17a11 8804fdff ffc5fa10 ..H...z......... - 0ab0 4808c4c1 7a118808 fdffffc5 fa10480c H...z.........H. - 0ac0 41c78014 fdffff00 00000041 c78018fd A..........A.... - 0ad0 ffff0000 000041c7 801cfdff ff000000 ......A......... - 0ae0 0041c780 20fdffff 00000000 41c78024 .A.. .......A..$ - 0af0 fdffff00 00000041 c78028fd ffff0000 .......A..(..... - 0b00 000041c7 802cfdff ff000000 0041c780 ..A..,.......A.. - 0b10 30fdffff 00000000 41c78034 fdffff00 0.......A..4.... - 0b20 00000041 c78038fd ffff0000 000041c7 ...A..8.......A. - 0b30 803cfdff ff000000 00c4c17a 11880cfd .<.........z.... - 0b40 ffffc4c1 7a118010 fdffffc5 fa100ac4 ....z........... - 0b50 c17a1188 40fdffff c5fa104a 04c4c17a .z..@......J...z - 0b60 118844fd ffffc5fa 104a08c4 c17a1188 ..D......J...z.. - 0b70 48fdffff c5fa104a 0cc4c17a 11884cfd H......J...z..L. - 0b80 ffffc5fa 104a1041 c78058fd ffff0000 .....J.A..X..... - 0b90 000041c7 805cfdff ff000000 0041c780 ..A..\.......A.. - 0ba0 60fdffff 00000000 41c78064 fdffff00 `.......A..d.... - 0bb0 00000041 c78068fd ffff0000 000041c7 ...A..h.......A. - 0bc0 806cfdff ff000000 0041c780 70fdffff .l.......A..p... - 0bd0 00000000 41c78074 fdffff00 00000041 ....A..t.......A - 0be0 c78078fd ffff0000 000041c7 807cfdff ..x.......A..|.. - 0bf0 ff000000 00c4c17a 118850fd ffffc4c1 .......z..P..... - 0c00 7a118054 fdffffc5 fa100fc4 c17a1188 z..T.........z.. - 0c10 80fdffff c5fa104f 04c4c17a 118884fd .......O...z.... /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39080000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 3a2b0000 00420e10 8f02420e ....:+...B....B. + 0020 00000000 8e160000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 45250a0e ..A.8..G....E%.. + 0040 8606410e 38830747 0ee80203 e5110a0e ..A.8..G........ 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0060 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_SKYLAKEX.o (disasm) @@ -20,1251 +20,436 @@ mov %r8,-offset(%rsp) mov %r9,offset(%rsp) mov %rsi,offset(%rsp) - mov offset(%rsp),%r15 + mov offset(%rsp),%r14 test %rsi,%rsi jle - mov %r8,%rbp - imul %rcx,%rbp - mov %rcx,%r14 - mov offset(%rsp),%r9 - lea (%rcx,%rbp,1),%rbx - lea (%rcx,%rbx,1),%r11 - lea (%rcx,%r11,1),%r10 - lea (%r10,%rcx,1),%rax - lea (%rcx,%rax,1),%r8 + mov %r8,%rax + imul %rcx,%rax + mov %rcx,%rbp + mov %rbp,%r11 + mov %r8,%r12 + shl $something,%r11 + lea (%rax,%rcx,2),%r8 + mov %rdi,%r10 + mov %r11,offset(%rsp) lea (%r8,%rcx,1),%rdi - lea (%rcx,%rdi,1),%rsi - mov %rax,-offset(%rsp) - lea (%rcx,%rsi,1),%rax - lea (%rcx,%rax,1),%rdx - mov %rax,-offset(%rsp) - lea (%rcx,%rdx,1),%rax - lea (%rcx,%rax,1),%r13 - lea (%rcx,%r13,1),%r12 - mov %r12,%rcx - mov %r14,%r12 - add %rcx,%r12 - mov %rcx,-offset(%rsp) - mov %r12,%rcx - mov %r14,%r12 - add %rcx,%r12 - mov %rcx,-offset(%rsp) - mov %r9,%rcx - sar $something,%rcx - and $something,%r9d - mov %rcx,offset(%rsp) - mov %r9,offset(%rsp) - mov %r14,%rcx - shl $something,%r9 - shl $something,%rcx - mov %r9,offset(%rsp) + lea offset(,%rbp,8),%r11 + mov %r9,%r13 + lea (%rdi,%rcx,1),%rsi + imul %rbp,%r9 + kmovq %r11,%k2 + mov %r10,%r11 + lea (%rsi,%rcx,1),%rcx + and $something,%r11d + lea (%rcx,%rbp,1),%rdx + mov %r11,-offset(%rsp) + mov %rbp,%r15 + mov %rbp,%r11 + mov offset(%rsp),%rbp + add %r12,%r9 + lea offset(%rbp,%r9,4),%r12 + mov %r13,%rbp + lea offset(%r13,%rax,1),%r9 + mov offset(%rsp),%r13 + sub %rax,%rdi + lea offset(%r13,%r9,4),%r13 mov offset(%rsp),%r9 - mov %rcx,offset(%rsp) - mov offset(%rsp),%rcx - shl $something,%r9 - add %rcx,%r9 + sub %rax,%rsi + lea offset(%rbp,%r9,8),%r9 + shl $something,%rdi + sub %rax,%rcx mov %r9,offset(%rsp) - mov offset(%rsp),%r9 - add %rcx,%rbp - lea (%r9,%rbp,4),%rbp - add %rcx,%rbx - lea (%r9,%rbx,4),%rbx - mov %rbp,offset(%rsp) - mov %rcx,%rbp + mov %rdi,offset(%rsp) + mov %r11,%r9 + lea offset(,%rsi,4),%rdi + lea offset(,%r11,4),%r11 + mov %rdi,offset(%rsp) + lea offset(,%rcx,4),%rdi + mov %rdx,%rcx + add %r9,%rdx + sub %rax,%rcx + sub %rax,%rdx + sub %rax,%r8 + mov %r11,%rax + lea offset(,%rdx,4),%rsi + neg %rax + lea offset(%rbp),%rdx + imul %rbp,%rax + imul %r11,%rdx + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + lea offset(,%rcx,4),%rdi + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rsi,offset(%rsp) + mov %r10,%rbx + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + mov %rcx,offset(%rsp) + sar $something,%rbx + lea (%rdx,%rax,1),%rsi + lea offset(%rbp),%rdx + imul %r11,%rdx mov %rbx,offset(%rsp) - mov %rbp,%rbx - add %rbp,%r11 - add %rbx,%rdx - mov %r9,%rbp - add %rbx,%rax - lea offset(%rbp,%rdx,4),%rdx - mov %rdx,offset(%rsp) - add %rbx,%r10 - lea offset(%rbp,%rax,4),%rdx - mov -offset(%rsp),%rax - mov %r9,%rcx - lea (%r9,%r11,4),%r11 - lea (%r9,%r10,4),%r10 - add %rbx,%r13 - mov -offset(%rsp),%r9 - add %rbx,%rax - mov %rdx,offset(%rsp) - lea offset(%rbp,%r13,4),%rdx - add %rbx,%r9 - mov %rdx,offset(%rsp) - lea offset(%rbp,%rax,4),%rdx - mov -offset(%rsp),%rax - add %rbx,%rsi - mov %r10,offset(%rsp) - add %rbx,%r8 - lea (%rcx,%r9,4),%r10 - add %rbx,%rdi - mov %r11,offset(%rsp) - mov %r10,offset(%rsp) - lea (%rcx,%rsi,4),%r11 - lea (%rcx,%r8,4),%r10 - lea (%rcx,%rdi,4),%rdi - add %rbx,%rax - mov -offset(%rsp),%rcx - lea offset(%rbp,%rax,4),%rax - add %rbx,%rcx - mov %rax,offset(%rsp) - lea (%r12,%rbx,1),%rax - mov %r11,offset(%rsp) - lea offset(%rbp,%rax,4),%rax - lea offset(%rbp,%rcx,4),%r11 - mov %r10,offset(%rsp) - mov %rax,offset(%rsp) + shl $something,%r15 + lea (%rdx,%rax,1),%rcx + lea offset(%rbp),%rdx + imul %r11,%rdx + shl $something,%r8 + vmovss %xmm14,-offset(%rsp) + lea (%rdx,%rax,1),%rdi + mov %r10,%rax + and $something,%rax mov %rdi,offset(%rsp) + mov %rax,%rdi + mov -offset(%rsp),%rax mov %r11,offset(%rsp) - mov %rdx,offset(%rsp) - mov offset(%rsp),%rsi - mov -offset(%rsp),%rcx - lea (%rsi,%r12,1),%rax - add %rbx,%rax - lea offset(%rbp,%rax,4),%rax - mov %rax,offset(%rsp) - mov %rsi,%rax - imul %rbx,%rax - shl $something,%r14 /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_SKYLAKEX.o (objdump) @@ -2,695 +2,364 @@ /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ece00100 AWAVAUATUSH..... - 0010 004889b4 24900000 0048c1fe 0448897c .H..$....H...H.| - 0020 24784889 94249800 00004889 8c248800 $xH..$....H..$.. - 0030 00004c89 4424c04c 894c2458 4889b424 ..L.D$.L.L$XH..$ - 0040 c0010000 4c8bbc24 18020000 4885f60f ....L..$....H... - 0050 8ec71c00 004c89c5 480fafe9 4989ce4c .....L..H...I..L - 0060 8b4c2478 488d1c29 4c8d1c19 4e8d1419 .L$xH..)L...N... - 0070 498d040a 4c8d0401 498d3c08 488d3439 I...L...I.<.H.49 - 0080 48894424 a0488d04 31488d14 01488944 H.D$.H..1H...H.D - 0090 2498488d 04114c8d 2c014e8d 24294c89 $.H...L.,.N.$)L. - 00a0 e14d89f4 4901cc48 894c2488 4c89e14d .M..I..H.L$.L..M - 00b0 89f44901 cc48894c 24904c89 c948c1f9 ..I..H.L$.L..H.. - 00c0 044183e1 0f48894c 24704c89 4c24504c .A...H.L$pL.L$PL - 00d0 89f149c1 e10648c1 e1024c89 8c24b801 ..I...H...L..$.. - 00e0 00004c8b 8c24c001 00004889 8c24a001 ..L..$....H..$.. - 00f0 0000488b 4c245849 c1e10449 01c94c89 ..H.L$XI...I..L. - 0100 8c248000 00004c8b 8c249800 00004801 .$....L..$....H. - 0110 cd498d2c a94801cb 498d1c99 4889ac24 .I.,.H..I...H..$ - 0120 a8000000 4889cd48 899c24b8 00000048 ....H..H..$....H - 0130 89eb4901 eb4801da 4c89cd48 01d8488d ..I..H..L..H..H. - 0140 54950048 89942438 01000049 01da488d T..H..$8...I..H. - 0150 54850048 8b442488 4c89c94f 8d1c994f T..H.D$.L..O...O - 0160 8d149149 01dd4c8b 4c24a048 01d84889 ...I..L.L$.H..H. - 0170 94244801 00004a8d 54ad0049 01d94889 .$H...J.T..I..H. - 0180 94245801 0000488d 54850048 8b442490 .$X...H.T..H.D$. - 0190 4801de4c 899424d8 00000049 01d84e8d H..L..$....I..N. - 01a0 14894801 df4c899c 24c80000 004c8994 ..H..L..$....L.. - 01b0 24e80000 004c8d1c b14e8d14 81488d3c $....L...N...H.< - 01c0 b94801d8 488b4c24 98488d44 85004801 .H..H.L$.H.D..H. - 01d0 d9488984 24780100 00498d04 1c4c899c .H..$x...I...L.. - 01e0 24180100 00488d44 85004c8d 5c8d004c $....H.D..L.\..L - 01f0 899424f8 00000048 89842488 01000048 ..$....H..$....H - 0200 89bc2408 0100004c 899c2428 01000048 ..$....L..$(...H - 0210 89942468 01000048 8bb42488 00000048 ..$h...H..$....H - 0220 8b4c24c0 4a8d0426 4801d848 8d448500 .L$.J..&H..H.D.. - 0230 48898424 98010000 4889f048 0fafc349 H..$....H..H...I - 0240 c1e6064c 8b4c2470 4801c848 8d448500 ...L.L$pH..H.D.. - 0250 48898424 a0000000 488d4301 480fafc6 H..$....H.C.H... - 0260 48895c24 9048c744 24680000 00004801 H.\$.H.D$h....H. - 0270 c8488d44 85004889 8424b000 0000488d .H.D..H..$....H. - 0280 4302480f afc648c7 44246000 000000c5 C.H...H.D$`..... - 0290 fa100500 00000048 01c8488d 44850048 .......H..H.D..H - 02a0 898424c0 00000048 8d430348 0fafc64d ..$....H.C.H...M - 02b0 89fa4801 c8488d44 85004889 8424d000 ..H..H.D..H..$.. - 02c0 0000488d 4304480f afc64801 c8488d44 ..H.C.H...H..H.D - 02d0 85004889 8424e000 0000488d 4305480f ..H..$....H.C.H. - 02e0 afc64801 c8488d44 85004889 8424f000 ..H..H.D..H..$.. - 02f0 0000488d 4306480f afc64801 c8488d44 ..H.C.H...H..H.D - 0300 85004889 84240001 0000488d 4307480f ..H..$....H.C.H. - 0310 afc64801 c8488d44 85004889 84241001 ..H..H.D..H..$.. - 0320 0000488d 4308480f afc64801 c8488d44 ..H.C.H...H..H.D - 0330 85004889 84242001 0000488d 4309480f ..H..$ ...H.C.H. - 0340 afc64801 c8488d44 85004889 84243001 ..H..H.D..H..$0. - 0350 0000488d 430a480f afc64801 c8488d44 ..H.C.H...H..H.D - 0360 85004889 84244001 0000488d 430b480f ..H..$@...H.C.H. - 0370 afc64801 c8488d44 85004889 84245001 ..H..H.D..H..$P. - 0380 0000488d 430c480f afc64801 c8488d44 ..H.C.H...H..H.D - 0390 85004889 84246001 0000488d 430d480f ..H..$`...H.C.H. - 03a0 afc64801 c8488d44 85004889 84247001 ..H..H.D..H..$p. - 03b0 0000488d 430e480f afc64801 c8488d44 ..H.C.H...H..H.D - 03c0 85004889 84248001 0000488d 430f480f ..H..$....H.C.H. - 03d0 afc6488b 74247848 01c8488d 44850048 ..H.t$xH..H.D..H - 03e0 89842490 01000048 89f04883 e0f04801 ..$....H..H...H. - 03f0 c8488944 24d04c89 c848c1e0 0a488984 .H.D$.L..H...H.. - 0400 24b00100 004c89c8 48c1e004 4801c848 $....L..H...H..H - 0410 898424a8 01000048 89f083e0 0e488984 ..$....H.....H.. - 0420 24c80100 004889f0 83e00c83 e6084889 $....H........H. - 0430 b424d801 00004889 8424d001 00004c89 .$....H..$....L. - 0440 f6e92801 0000662e 0f1f8400 00000000 ..(...f......... - 0450 488b4424 60488bbc 24b00000 004c8b8c H.D$`H..$....L.. - 0460 24a00000 004801c7 48897c24 98488bbc $....H..H.|$.H.. - 0470 24c00000 00488b8c 24100100 004801c7 $....H..$....H.. - 0480 48897c24 a0488bbc 24d00000 004c8bbc H.|$.H..$....L.. - 0490 24200100 004801c7 48897c24 a8488bbc $ ...H..H.|$.H.. - 04a0 24e00000 004c8bb4 24300100 004801c7 $....L..$0...H.. - 04b0 48897c24 b0488bbc 24f00000 004c8bac H.|$.H..$....L.. - 04c0 24400100 004801c7 48897c24 c84c8ba4 $@...H..H.|$.L.. - 04d0 24500100 00488bbc 24000100 00488bac $P...H..$....H.. - 04e0 24600100 00488b9c 24700100 004c8b9c $`...H..$p...L.. - 04f0 24800100 004901c1 4801c748 01c14901 $....I..H..H..I. - 0500 c74901c6 4901c549 01c44801 c54801c3 .I..I..I..H..H.. - 0510 4901c348 03842490 01000048 837c2470 I..H..$....H.|$p - 0520 004889c2 488b4424 c00f8f2e 01000048 .H..H.D$.......H - 0530 837c2450 00741348 39442490 0f8e1e10 .|$P.t.H9D$..... - 0540 00004c03 9424b801 00004883 44249010 ..L..$....H.D$.. - 0550 48017424 60488344 24684048 8b442490 H.t$`H.D$h@H.D$. - 0560 483b8424 80000000 0f849217 0000488b H;.$..........H. - 0570 7c24c048 397c2490 0f8dd2fe ffff488b |$.H9|$.......H. - 0580 44246848 8b9c24b8 00000048 8bbc24c8 D$hH..$....H..$. - 0590 00000048 01c34889 5c249848 8b9c24d8 ...H..H.\$.H..$. - 05a0 00000048 01c74801 c348897c 24a04889 ...H..H..H.|$.H. - 05b0 5c24a848 8bbc24e8 00000048 8b9c24f8 \$.H..$....H..$. - 05c0 00000048 01c74801 c348897c 24b04889 ...H..H..H.|$.H. - 05d0 5c24c84c 8b8c24a8 00000048 8bbc2408 \$.L..$....H..$. - 05e0 01000048 8b8c2418 0100004c 8bbc2428 ...H..$....L..$( - 05f0 0100004c 8bb42438 0100004c 8bac2448 ...L..$8...L..$H - 0600 0100004c 8ba42458 01000048 8bac2468 ...L..$X...H..$h - 0610 01000048 8b9c2478 0100004c 8b9c2488 ...H..$x...L..$. - 0620 01000049 01c14801 c74801c1 4901c749 ...I..H..H..I..I - 0630 01c64901 c54901c4 4801c548 01c34901 ..I..I..H..H..I. - 0640 c3480384 24980100 0048837c 24700048 .H..$....H.|$p.H - 0650 89c2488b 4424c00f 8ed2feff ff4c894c ..H.D$.......L.L - 0660 24b84c89 94241802 00004d8d 82000400 $.L..$....M..... - 0670 004989d1 4d89da48 89442488 488b5424 .I..M..H.D$.H.T$ - 0680 c84989f3 eb71662e 0f1f8400 00000000 .I...qf......... - 0690 48834424 b8404883 44249840 48834424 H.D$.@H.D$.@H.D$ - 06a0 a0404883 4424a840 48834424 b0404883 .@H.D$.@H.D$.@H. - 06b0 c2404883 c7404883 c1404983 c7404983 .@H..@H..@I..@I. - 06c0 c6404983 c5404983 c4404883 c5404883 .@I..@I..@H..@H. - 06d0 c3404983 c2404983 c1404883 44248810 .@I..@I..@H.D$.. - 06e0 4981c000 04000048 8b442488 483b4424 I......H.D$.H;D$ - 06f0 d00f8439 0e000049 8d8000fc ffff4889 ...9...I......H. - 0700 4424c848 8b442488 48394424 907f8148 D$.H.D$.H9D$...H - 0710 8b442498 488b7424 884c01d8 48894424 .D$.H.t$.L..H.D$ - 0720 38488b44 24a04c01 d8488904 24488b44 8H.D$.L..H..$H.D - 0730 24a84c01 d8488944 2420488b 4424b04c $.L..H.D$ H.D$.L - 0740 01d84889 4424f04a 8d041a48 89442430 ..H.D$.J...H.D$0 - 0750 4a8d041f 48894424 f84a8d04 19488944 J...H.D$.J...H.D - 0760 24284b8d 041f4889 4424184b 8d041e48 $(K...H.D$.K...H - 0770 894424e8 4b8d441d 00488944 24104b8d .D$.K.D..H.D$.K. - 0780 041c4889 4424e04a 8d441d00 48894424 ..H.D$.J.D..H.D$ - 0790 084a8d04 1b488944 24d84b8d 041a4889 .J...H.D$.K...H. - 07a0 4424484b 8d041948 89442440 48397424 D$HK...H.D$@H9t$ - 07b0 900f8ca9 0c000041 c78004fc ffff0000 .......A........ - 07c0 000041c7 8008fcff ff000000 0041c780 ..A..........A.. - 07d0 0cfcffff 00000000 41c78010 fcffff00 ........A....... - 07e0 00000041 c78014fc ffff0000 000041c7 ...A..........A. - 07f0 8018fcff ff000000 0041c780 1cfcffff .........A...... - 0800 00000000 41c78020 fcffff00 00000041 ....A.. .......A - 0810 c78024fc ffff0000 000041c7 8028fcff ..$.......A..(.. - 0820 ff000000 0041c780 2cfcffff 00000000 .....A..,....... - 0830 41c78030 fcffff00 00000041 c78034fc A..0.......A..4. - 0840 ffff0000 000041c7 8038fcff ff000000 ......A..8...... - 0850 0041c780 3cfcffff 00000000 488b4424 .A..<.......H.D$ - 0860 98c4c17a 118000fc ffffc5fa 100841c7 ...z..........A. - 0870 8048fcff ff000000 00c4c17a 118840fc .H.........z..@. - 0880 ffff41c7 804cfcff ff000000 0041c780 ..A..L.......A.. - 0890 50fcffff 00000000 41c78054 fcffff00 P.......A..T.... - 08a0 00000041 c78058fc ffff0000 000041c7 ...A..X.......A. - 08b0 805cfcff ff000000 0041c780 60fcffff .\.......A..`... - 08c0 00000000 41c78064 fcffff00 00000041 ....A..d.......A - 08d0 c78068fc ffff0000 000041c7 806cfcff ..h.......A..l.. - 08e0 ff000000 0041c780 70fcffff 00000000 .....A..p....... - 08f0 41c78074 fcffff00 000000c4 c17a1180 A..t.........z.. - 0900 44fcffff 41c78078 fcffff00 00000041 D...A..x.......A - 0910 c7807cfc ffff0000 0000488b 4424a0c5 ..|.......H.D$.. - 0920 fa1008c4 c17a1188 80fcffff c5fa1048 .....z.........H - 0930 0441c780 8cfcffff 00000000 41c78090 .A..........A... - 0940 fcffff00 00000041 c78094fc ffff0000 .......A........ - 0950 000041c7 8098fcff ff000000 0041c780 ..A..........A.. - 0960 9cfcffff 00000000 41c780a0 fcffff00 ........A....... - 0970 00000041 c780a4fc ffff0000 000041c7 ...A..........A. - 0980 80a8fcff ff000000 0041c780 acfcffff .........A...... - 0990 00000000 41c780b0 fcffff00 00000041 ....A..........A - 09a0 c780b4fc ffff0000 000041c7 80b8fcff ..........A..... - 09b0 ff000000 0041c780 bcfcffff 00000000 .....A.......... - 09c0 488b4424 a8c4c17a 118884fc ffffc4c1 H.D$...z........ - 09d0 7a118088 fcffffc5 fa1008c4 c17a1188 z............z.. - 09e0 c0fcffff c5fa1048 04c4c17a 1188c4fc .......H...z.... - 09f0 ffffc5fa 10480841 c780d0fc ffff0000 .....H.A........ - 0a00 0000c4c1 7a1188c8 fcffff41 c780d4fc ....z......A.... - 0a10 ffff0000 000041c7 80d8fcff ff000000 ......A......... - 0a20 0041c780 dcfcffff 00000000 c4c17a11 .A............z. - 0a30 80ccfcff ff41c780 e0fcffff 00000000 .....A.......... - 0a40 41c780e4 fcffff00 00000041 c780e8fc A..........A.... - 0a50 ffff0000 000041c7 80ecfcff ff000000 ......A......... - 0a60 0041c780 f0fcffff 00000000 41c780f4 .A..........A... - 0a70 fcffff00 00000041 c780f8fc ffff0000 .......A........ - 0a80 000041c7 80fcfcff ff000000 00488b44 ..A..........H.D - 0a90 24b0c5fa 1008c4c1 7a118800 fdffffc5 $.......z....... - 0aa0 fa104804 c4c17a11 8804fdff ffc5fa10 ..H...z......... - 0ab0 4808c4c1 7a118808 fdffffc5 fa10480c H...z.........H. - 0ac0 41c78014 fdffff00 00000041 c78018fd A..........A.... - 0ad0 ffff0000 000041c7 801cfdff ff000000 ......A......... - 0ae0 0041c780 20fdffff 00000000 41c78024 .A.. .......A..$ - 0af0 fdffff00 00000041 c78028fd ffff0000 .......A..(..... - 0b00 000041c7 802cfdff ff000000 0041c780 ..A..,.......A.. - 0b10 30fdffff 00000000 41c78034 fdffff00 0.......A..4.... - 0b20 00000041 c78038fd ffff0000 000041c7 ...A..8.......A. - 0b30 803cfdff ff000000 00c4c17a 11880cfd .<.........z.... - 0b40 ffffc4c1 7a118010 fdffffc5 fa100ac4 ....z........... - 0b50 c17a1188 40fdffff c5fa104a 04c4c17a .z..@......J...z - 0b60 118844fd ffffc5fa 104a08c4 c17a1188 ..D......J...z.. - 0b70 48fdffff c5fa104a 0cc4c17a 11884cfd H......J...z..L. - 0b80 ffffc5fa 104a1041 c78058fd ffff0000 .....J.A..X..... - 0b90 000041c7 805cfdff ff000000 0041c780 ..A..\.......A.. - 0ba0 60fdffff 00000000 41c78064 fdffff00 `.......A..d.... - 0bb0 00000041 c78068fd ffff0000 000041c7 ...A..h.......A. - 0bc0 806cfdff ff000000 0041c780 70fdffff .l.......A..p... - 0bd0 00000000 41c78074 fdffff00 00000041 ....A..t.......A - 0be0 c78078fd ffff0000 000041c7 807cfdff ..x.......A..|.. - 0bf0 ff000000 00c4c17a 118850fd ffffc4c1 .......z..P..... - 0c00 7a118054 fdffffc5 fa100fc4 c17a1188 z..T.........z.. - 0c10 80fdffff c5fa104f 04c4c17a 118884fd .......O...z.... /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 39080000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strmm_iutucopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 3a2b0000 00420e10 8f02420e ....:+...B....B. + 0020 00000000 8e160000 00420e10 8f02420e .........B....B. 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0e980403 45250a0e ..A.8..G....E%.. + 0040 8606410e 38830747 0ee80203 e5110a0e ..A.8..G........ 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0060 440e0846 0b000000 D..F.... /usr/lib64/libopenblas_openmp.a/strsm_ilnncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strsm_ilnncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strsm_ilnncopy_COOPERLAKE.o (disasm) @@ -8,435 +8,858 @@ push %r15 push %r14 push %r13 + mov %r9,%r13 push %r12 push %rbp push %rbx sub $something,%rsp mov %rsi,offset(%rsp) sar $something,%rsi - mov %rdi,-offset(%rsp) + mov %rdi,offset(%rsp) mov %rdx,offset(%rsp) mov %rcx,offset(%rsp) mov %r8,offset(%rsp) - mov %r9,-offset(%rsp) mov %rsi,offset(%rsp) test %rsi,%rsi jle mov %rcx,%rbx - lea offset(,%rcx,4),%rbp - lea (%rcx,%rcx,2),%rax - mov %rdx,%r11 - mov %rsi,%r15 - lea offset(%rbp,%rbx,1),%rdx - lea offset(,%rax,4),%rsi - mov %rsi,offset(%rsp) - lea offset(,%rdx,4),%rsi - mov %rsi,offset(%rsp) - lea offset(,%rax,8),%rsi - shl $something,%rax - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - mov %rsi,offset(%rsp) - imul $something,%rbx,%rsi - mov %rax,offset(%rsp) + lea offset(,%rcx,4),%rcx + lea (%rbx,%rbx,2),%rax + mov %rcx,%r10 + mov %rsi,%r9 + lea offset(,%rbx,8),%r11 + lea offset(,%rax,4),%r15 + lea offset(,%rax,8),%r12 + mov %rbx,%rsi imul $something,%rbx,%rax - lea offset(,%rcx,8),%r10 - shl $something,%rcx + add %rbx,%r10 + shl $something,%rbx + mov %rbx,offset(%rsp) + mov %rdi,%rbx + and $something,%ebx + mov %rbx,offset(%rsp) + mov %rdi,%rbx + and $something,%ebx + mov %rax,%rbp mov %rax,offset(%rsp) - imul $something,%rbx,%rax + mov %rbx,offset(%rsp) + mov %rdi,%rax + mov %rdi,%rbx + sar $something,%rax + and $something,%ebx + and $something,%rdi + mov %rdi,%r14 + mov %rbx,offset(%rsp) + mov %rax,%rdi + lea (%r8,%r9,8),%rbx + shl $something,%rdi + shl $something,%rsi + mov %rbx,offset(%rsp) + mov %rbp,%rbx mov %rcx,offset(%rsp) + mov %r15,offset(%rsp) mov %rsi,offset(%rsp) mov %rax,offset(%rsp) - mov %r8,%rax - imul %rbp,%rax - mov %rbx,%rsi - mov %r10,%rcx - mov %r11,%r14 - add %rbx,%rcx - shl $something,%rsi - sub %rax,%r14 - mov %r15,%rax - mov %rsi,offset(%rsp) + add %rdi,%rcx + add %rdi,%r15 + add %rdi,%rsi + add %rdi,%rbx shl $something,%rax - lea offset(,%rcx,4),%rsi - imul $something,%rbx,%rcx - add %r8,%rax + lea offset(,%r10,4),%r10 + mov %r12,offset(%rsp) + mov offset(%rsp),%rbp + add %rdi,%r12 + mov %rdi,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r15,offset(%rsp) mov %rsi,offset(%rsp) + mov %rbx,offset(%rsp) mov %rax,offset(%rsp) - lea offset(,%rdx,8),%rsi - lea offset(%rbp),%rax - shl $something,%rdi - mov %r10,(%rsp) - mov %rsi,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r14,offset(%rsp) - mov %rax,-offset(%rsp) - mov %rdi,offset(%rsp) - shl $something,%rbx - vmovss offset(%rip),%xmm1 # - mov %rbx,-offset(%rsp) - mov %rbp,%rbx - mov %r8,%rbp - nopl (%rax) - lea (%rbx,%r11,1),%rax - mov %rax,-offset(%rsp) - mov (%rsp),%rax - mov %r11,%r9 - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) + mov %r11,offset(%rsp) + mov %r10,offset(%rsp) + add %rdi,%r11 + add %rdi,%r10 + mov %r12,offset(%rsp) + vmovss offset(%rip),%xmm0 # + mov %r8,%r12 + mov %r11,offset(%rsp) + mov %r10,offset(%rsp) + mov %rbp,%r8 + mov %r12,%r9 + mov %r14,%r10 + mov %r13,%r11 + nopl offset(%rax) mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) + cmpq $something,offset(%rsp) + lea (%rax,%r8,1),%rcx mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) + lea (%rax,%r8,1),%r15 mov offset(%rsp),%rax - lea (%rax,%r11,1),%rsi + lea (%r8,%rax,1),%r14 mov offset(%rsp),%rax - lea (%r11,%rax,1),%r12 + lea (%rax,%r8,1),%r13 mov offset(%rsp),%rax - lea (%rax,%r11,1),%r13 + lea (%r8,%rax,1),%r12 mov offset(%rsp),%rax - lea (%rax,%r11,1),%r14 + lea (%r8,%rax,1),%rbp mov offset(%rsp),%rax - lea (%rax,%r11,1),%r15 - add -offset(%rsp),%r11 - cmpq $something,-offset(%rsp) + lea (%rax,%r8,1),%rbx jle - mov -offset(%rsp),%rdx - mov %rbp,%rdi - neg %rdi - mov %r11,-offset(%rsp) - mov offset(%rsp),%r10 - lea (%rdx,%rdi,4),%r8 - xor %eax,%eax - mov %rsi,%r11 + mov %r8,%rsi + mov %r11,%rdx + mov %r9,%rax + xor %edi,%edi + mov %r11,%r9 /usr/lib64/libopenblas_openmp.a/strsm_ilnncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_ilnncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_ilnncopy_COOPERLAKE.o (objdump) @@ -2,139 +2,310 @@ /usr/lib64/libopenblas_openmp.a/strsm_ilnncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ecb00000 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 0448897c .H..$....H...H.| - 0020 24884889 94249000 00004889 8c24a000 $.H..$....H..$.. - 0030 00004c89 84248800 00004c89 4c24e848 ..L..$....L.L$.H - 0040 89b424a8 00000048 85f60f8e 91030000 ..$....H........ - 0050 4889cb48 8d2c8d00 00000048 8d044949 H..H.,.....H..II - 0060 89d34989 f7488d54 1d00488d 34850000 ..I..H.T..H.4... - 0070 00004889 74244848 8d349500 00000048 ..H.t$HH.4.....H - 0080 89742450 488d34c5 00000000 48c1e004 .t$PH.4.....H... - 0090 48894424 70486bc3 34488974 2458486b H.D$pHk.4H.t$XHk - 00a0 f31c4889 44242848 6bc3384c 8d14cd00 ..H.D$(Hk.8L.... - 00b0 00000048 c1e10448 89442430 486bc33c ...H...H.D$0Hk.< - 00c0 48894c24 08488974 24104889 4424384c H.L$.H.t$.H.D$8L - 00d0 89c0480f afc54889 de4c89d1 4d89de48 ..H...H..L..M..H - 00e0 01d948c1 e6054929 c64c89f8 48897424 ..H...I).L..H.t$ - 00f0 1848c1e0 04488d34 8d000000 00486bcb .H...H.4.....Hk. - 0100 2c4c01c0 48897424 60488944 2440488d ,L..H.t$`H.D$@H. - 0110 34d50000 0000488d 450448c1 e7064c89 4.....H.E.H...L. - 0120 14244889 74246848 894c2420 4c89b424 .$H.t$hH.L$ L..$ - 0130 80000000 48894424 9048897c 247848c1 ....H.D$.H.|$xH. - 0140 e306c5fa 100d0000 00004889 5c24f848 ..........H.\$.H - 0150 89eb4c89 c50f1f00 4a8d041b 48894424 ..L.....J...H.D$ - 0160 98488b04 244d89d9 4c01d848 894424a0 .H..$M..L..H.D$. - 0170 488b4424 484c01d8 48894424 a8488b44 H.D$HL..H.D$.H.D - 0180 24084c01 d8488944 24b0488b 4424504c $.L..H.D$.H.D$PL - 0190 01d84889 4424b848 8b442458 4c01d848 ..H.D$.H.D$XL..H - 01a0 894424c0 488b4424 104c01d8 48894424 .D$.H.D$.L..H.D$ - 01b0 c8488b44 24184c01 d8488944 24d0488b .H.D$.L..H.D$.H. - 01c0 4424604c 01d84889 4424d848 8b442468 D$`L..H.D$.H.D$h - 01d0 4c01d848 894424e0 488b4424 204a8d34 L..H.D$.H.D$ J.4 - 01e0 18488b44 24704d8d 2403488b 4424284e .H.D$pM.$.H.D$(N - 01f0 8d2c1848 8b442430 4e8d3418 488b4424 .,.H.D$0N.4.H.D$ - 0200 384e8d3c 184c035c 24f84883 7c248800 8N.<.L.\$.H.|$.. - 0210 0f8e8901 0000488b 5424e848 89ef48f7 ......H.T$.H..H. - 0220 df4c895c 24f04c8b 94248000 00004c8d .L.\$.L..$....L. - 0230 04ba31c0 4989f3e9 03010000 0f1f4000 ..1.I.........@. - 0240 4883ff0f 0f8e0e01 0000c4c1 7a100148 H...........z..H - 0250 8b4c2498 c5fa1102 c5fa1004 81488b4c .L$..........H.L - 0260 24a0c5fa 114204c5 fa100481 488b7424 $....B......H.t$ - 0270 a8c5fa11 4208c5fa 10048648 8b4c24b0 ....B......H.L$. - 0280 c5fa1142 0cc5fa10 0481488b 7424b8c5 ...B......H.t$.. - 0290 fa114210 c5fa1004 86488b4c 24c0c5fa ..B......H.L$... - 02a0 114214c5 fa100481 488b7424 c8c5fa11 .B......H.t$.... - 02b0 4218c5fa 10048648 8b4c24d0 c5fa1142 B......H.L$....B - 02c0 1cc5fa10 0481488b 7424d8c5 fa114220 ......H.t$....B - 02d0 c5fa1004 86488b4c 24e0c5fa 114224c5 .....H.L$....B$. - 02e0 fa100481 c5fa1142 28c4c17a 100483c5 .......B(..z.... - 02f0 fa11422c c4c17a10 0484c5fa 114230c4 ..B,..z......B0. - 0300 c17a1044 8500c5fa 114234c4 c17a1004 .z.D.....B4..z.. - 0310 86c5fa11 4238c4c1 7a100487 c5fa1142 ....B8..z......B - 0320 3c48ffc0 4983c104 4883c240 48ffc74c mov %rcx,%rbx - lea offset(,%rcx,4),%rbp - lea (%rcx,%rcx,2),%rax - mov %rdx,%r11 - mov %rsi,%r15 - lea offset(%rbp,%rbx,1),%rdx - lea offset(,%rax,4),%rsi - mov %rsi,offset(%rsp) - lea offset(,%rdx,4),%rsi - mov %rsi,offset(%rsp) - lea offset(,%rax,8),%rsi - shl $something,%rax - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - mov %rsi,offset(%rsp) - imul $something,%rbx,%rsi - mov %rax,offset(%rsp) + lea offset(,%rcx,4),%rcx + lea (%rbx,%rbx,2),%rax + mov %rcx,%r10 + mov %rsi,%r9 + lea offset(,%rbx,8),%r11 + lea offset(,%rax,4),%r15 + lea offset(,%rax,8),%r12 + mov %rbx,%rsi imul $something,%rbx,%rax - lea offset(,%rcx,8),%r10 - shl $something,%rcx + add %rbx,%r10 + shl $something,%rbx + mov %rbx,offset(%rsp) + mov %rdi,%rbx + and $something,%ebx + mov %rbx,offset(%rsp) + mov %rdi,%rbx + and $something,%ebx + mov %rax,%rbp mov %rax,offset(%rsp) - imul $something,%rbx,%rax + mov %rbx,offset(%rsp) + mov %rdi,%rax + mov %rdi,%rbx + sar $something,%rax + and $something,%ebx + and $something,%rdi + mov %rdi,%r14 + mov %rbx,offset(%rsp) + mov %rax,%rdi + lea (%r8,%r9,8),%rbx + shl $something,%rdi + shl $something,%rsi + mov %rbx,offset(%rsp) + mov %rbp,%rbx mov %rcx,offset(%rsp) + mov %r15,offset(%rsp) mov %rsi,offset(%rsp) mov %rax,offset(%rsp) - mov %r8,%rax - imul %rbp,%rax - mov %rbx,%rsi - mov %r10,%rcx - mov %r11,%r14 - add %rbx,%rcx - shl $something,%rsi - sub %rax,%r14 - mov %r15,%rax - mov %rsi,offset(%rsp) + add %rdi,%rcx + add %rdi,%r15 + add %rdi,%rsi + add %rdi,%rbx shl $something,%rax - lea offset(,%rcx,4),%rsi - imul $something,%rbx,%rcx - add %r8,%rax + lea offset(,%r10,4),%r10 + mov %r12,offset(%rsp) + mov offset(%rsp),%rbp + add %rdi,%r12 + mov %rdi,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r15,offset(%rsp) mov %rsi,offset(%rsp) + mov %rbx,offset(%rsp) mov %rax,offset(%rsp) - lea offset(,%rdx,8),%rsi - lea offset(%rbp),%rax - shl $something,%rdi - mov %r10,(%rsp) - mov %rsi,offset(%rsp) - mov %rcx,offset(%rsp) - mov %r14,offset(%rsp) - mov %rax,-offset(%rsp) - mov %rdi,offset(%rsp) - shl $something,%rbx - vmovss offset(%rip),%xmm1 # - mov %rbx,-offset(%rsp) - mov %rbp,%rbx - mov %r8,%rbp - nopl (%rax) - lea (%rbx,%r11,1),%rax - mov %rax,-offset(%rsp) - mov (%rsp),%rax - mov %r11,%r9 - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) + mov %r11,offset(%rsp) + mov %r10,offset(%rsp) + add %rdi,%r11 + add %rdi,%r10 + mov %r12,offset(%rsp) + vmovss offset(%rip),%xmm0 # + mov %r8,%r12 + mov %r11,offset(%rsp) + mov %r10,offset(%rsp) + mov %rbp,%r8 + mov %r12,%r9 + mov %r14,%r10 + mov %r13,%r11 + nopl offset(%rax) mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) + cmpq $something,offset(%rsp) + lea (%rax,%r8,1),%rcx mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) + lea (%rax,%r8,1),%r15 mov offset(%rsp),%rax - lea (%rax,%r11,1),%rsi + lea (%r8,%rax,1),%r14 mov offset(%rsp),%rax - lea (%r11,%rax,1),%r12 + lea (%rax,%r8,1),%r13 mov offset(%rsp),%rax - lea (%rax,%r11,1),%r13 + lea (%r8,%rax,1),%r12 mov offset(%rsp),%rax - lea (%rax,%r11,1),%r14 + lea (%r8,%rax,1),%rbp mov offset(%rsp),%rax - lea (%rax,%r11,1),%r15 - add -offset(%rsp),%r11 - cmpq $something,-offset(%rsp) + lea (%rax,%r8,1),%rbx jle - mov -offset(%rsp),%rdx - mov %rbp,%rdi - neg %rdi - mov %r11,-offset(%rsp) - mov offset(%rsp),%r10 - lea (%rdx,%rdi,4),%r8 - xor %eax,%eax - mov %rsi,%r11 + mov %r8,%rsi + mov %r11,%rdx + mov %r9,%rax + xor %edi,%edi + mov %r11,%r9 /usr/lib64/libopenblas_openmp.a/strsm_ilnncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_ilnncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_ilnncopy_SKYLAKEX.o (objdump) @@ -2,139 +2,310 @@ /usr/lib64/libopenblas_openmp.a/strsm_ilnncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ecb00000 AWAVAUATUSH..... - 0010 004889b4 24980000 0048c1fe 0448897c .H..$....H...H.| - 0020 24884889 94249000 00004889 8c24a000 $.H..$....H..$.. - 0030 00004c89 84248800 00004c89 4c24e848 ..L..$....L.L$.H - 0040 89b424a8 00000048 85f60f8e 91030000 ..$....H........ - 0050 4889cb48 8d2c8d00 00000048 8d044949 H..H.,.....H..II - 0060 89d34989 f7488d54 1d00488d 34850000 ..I..H.T..H.4... - 0070 00004889 74244848 8d349500 00000048 ..H.t$HH.4.....H - 0080 89742450 488d34c5 00000000 48c1e004 .t$PH.4.....H... - 0090 48894424 70486bc3 34488974 2458486b H.D$pHk.4H.t$XHk - 00a0 f31c4889 44242848 6bc3384c 8d14cd00 ..H.D$(Hk.8L.... - 00b0 00000048 c1e10448 89442430 486bc33c ...H...H.D$0Hk.< - 00c0 48894c24 08488974 24104889 4424384c H.L$.H.t$.H.D$8L - 00d0 89c0480f afc54889 de4c89d1 4d89de48 ..H...H..L..M..H - 00e0 01d948c1 e6054929 c64c89f8 48897424 ..H...I).L..H.t$ - 00f0 1848c1e0 04488d34 8d000000 00486bcb .H...H.4.....Hk. - 0100 2c4c01c0 48897424 60488944 2440488d ,L..H.t$`H.D$@H. - 0110 34d50000 0000488d 450448c1 e7064c89 4.....H.E.H...L. - 0120 14244889 74246848 894c2420 4c89b424 .$H.t$hH.L$ L..$ - 0130 80000000 48894424 9048897c 247848c1 ....H.D$.H.|$xH. - 0140 e306c5fa 100d0000 00004889 5c24f848 ..........H.\$.H - 0150 89eb4c89 c50f1f00 4a8d041b 48894424 ..L.....J...H.D$ - 0160 98488b04 244d89d9 4c01d848 894424a0 .H..$M..L..H.D$. - 0170 488b4424 484c01d8 48894424 a8488b44 H.D$HL..H.D$.H.D - 0180 24084c01 d8488944 24b0488b 4424504c $.L..H.D$.H.D$PL - 0190 01d84889 4424b848 8b442458 4c01d848 ..H.D$.H.D$XL..H - 01a0 894424c0 488b4424 104c01d8 48894424 .D$.H.D$.L..H.D$ - 01b0 c8488b44 24184c01 d8488944 24d0488b .H.D$.L..H.D$.H. - 01c0 4424604c 01d84889 4424d848 8b442468 D$`L..H.D$.H.D$h - 01d0 4c01d848 894424e0 488b4424 204a8d34 L..H.D$.H.D$ J.4 - 01e0 18488b44 24704d8d 2403488b 4424284e .H.D$pM.$.H.D$(N - 01f0 8d2c1848 8b442430 4e8d3418 488b4424 .,.H.D$0N.4.H.D$ - 0200 384e8d3c 184c035c 24f84883 7c248800 8N.<.L.\$.H.|$.. - 0210 0f8e8901 0000488b 5424e848 89ef48f7 ......H.T$.H..H. - 0220 df4c895c 24f04c8b 94248000 00004c8d .L.\$.L..$....L. - 0230 04ba31c0 4989f3e9 03010000 0f1f4000 ..1.I.........@. - 0240 4883ff0f 0f8e0e01 0000c4c1 7a100148 H...........z..H - 0250 8b4c2498 c5fa1102 c5fa1004 81488b4c .L$..........H.L - 0260 24a0c5fa 114204c5 fa100481 488b7424 $....B......H.t$ - 0270 a8c5fa11 4208c5fa 10048648 8b4c24b0 ....B......H.L$. - 0280 c5fa1142 0cc5fa10 0481488b 7424b8c5 ...B......H.t$.. - 0290 fa114210 c5fa1004 86488b4c 24c0c5fa ..B......H.L$... - 02a0 114214c5 fa100481 488b7424 c8c5fa11 .B......H.t$.... - 02b0 4218c5fa 10048648 8b4c24d0 c5fa1142 B......H.L$....B - 02c0 1cc5fa10 0481488b 7424d8c5 fa114220 ......H.t$....B - 02d0 c5fa1004 86488b4c 24e0c5fa 114224c5 .....H.L$....B$. - 02e0 fa100481 c5fa1142 28c4c17a 100483c5 .......B(..z.... - 02f0 fa11422c c4c17a10 0484c5fa 114230c4 ..B,..z......B0. - 0300 c17a1044 8500c5fa 114234c4 c17a1004 .z.D.....B4..z.. - 0310 86c5fa11 4238c4c1 7a100487 c5fa1142 ....B8..z......B - 0320 3c48ffc0 4983c104 4883c240 48ffc74c + lea offset(,%rcx,4),%r9 lea (%rcx,%rcx,2),%rax - lea offset(,%rcx,4),%rbx - lea offset(,%rcx,8),%r14 - mov %rsi,%r15 + mov %r9,%rdx + lea offset(,%rcx,8),%r10 + lea offset(,%rax,4),%r11 + lea offset(,%rax,8),%rbp + mov %rsi,%rbx + imul $something,%rcx,%rax mov %rcx,%rsi - lea offset(,%rax,4),%rcx - mov %rcx,offset(%rsp) - mov %rsi,%rcx + add %rcx,%rdx shl $something,%rcx - mov %rdx,%r10 - lea (%rbx,%rsi,1),%rdx - mov %rcx,(%rsp) - lea offset(,%rdx,4),%rcx mov %rcx,offset(%rsp) - lea offset(,%rax,8),%rcx - shl $something,%rax + mov %rdi,%rcx + and $something,%ecx mov %rcx,offset(%rsp) + mov %rdi,%rcx mov %rax,offset(%rsp) - imul $something,%rsi,%rcx - imul $something,%rsi,%rax - shl $something,%rdi + and $something,%ecx + mov %rdi,%rax + sar $something,%rax mov %rcx,offset(%rsp) + mov %rdi,%rcx + and $something,%rdi + mov %rdi,%r13 + mov %rax,%rdi + shl $something,%rdi + shl $something,%rsi + shl $something,%rdx + mov %rsi,offset(%rsp) + add %rdi,%rsi + mov %r9,offset(%rsp) + mov %r10,offset(%rsp) + add %rdi,%r9 + add %rdi,%r10 + mov %r11,offset(%rsp) + mov %rdx,offset(%rsp) + add %rdi,%r11 + add %rdi,%rdx + mov %rbp,offset(%rsp) mov %rax,offset(%rsp) - mov %rsi,%rcx - imul $something,%rsi,%rax - shl $something,%rcx - mov %rcx,offset(%rsp) - mov %r14,%rcx - add %rsi,%rcx + add %rdi,%rbp + mov %rsi,offset(%rsp) + shl $something,%rax + mov offset(%rsp),%rsi + and $something,%ecx + mov %r9,offset(%rsp) + mov %r10,offset(%rsp) + mov %r11,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rbp,offset(%rsp) mov %rax,offset(%rsp) - imul $something,%rsi,%rax - shl $something,%rcx - mov %rcx,offset(%rsp) - lea offset(,%rdx,8),%rcx + mov %r12,offset(%rsp) + add %rdi,%rsi mov %rcx,offset(%rsp) - mov %rax,offset(%rsp) - imul $something,%rsi,%rcx - mov %r15,%rax - shl $something,%rax - shl $something,%rsi - add %r8,%rax - mov %r14,-offset(%rsp) + vmovss offset(%rip),%xmm0 # + lea (%r8,%rbx,8),%rcx mov %rcx,offset(%rsp) - mov %rsi,-offset(%rsp) - mov %rax,offset(%rsp) mov %rdi,offset(%rsp) - vmovss offset(%rip),%xmm1 # - mov %rbx,%r11 - mov %r8,%rbx - nop - lea (%r11,%r10,1),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - mov %r10,%r9 - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov (%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) + mov %rsi,offset(%rsp) + mov %r12,%rcx + mov %r8,%rsi + mov %r13,%rdi + mov %r14,%r8 + nopl offset(%rax) mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) + cmpq $something,offset(%rsp) + lea (%rax,%rcx,1),%r13 mov offset(%rsp),%rax - lea (%r10,%rax,1),%rcx + lea (%rax,%rcx,1),%r12 mov offset(%rsp),%rax - lea (%rax,%r10,1),%rbp + lea (%rcx,%rax,1),%rbp mov offset(%rsp),%rax - lea (%r10,%rax,1),%r12 + lea (%rax,%rcx,1),%rbx mov offset(%rsp),%rax - lea (%rax,%r10,1),%r13 + lea (%rcx,%rax,1),%r11 mov offset(%rsp),%rax - lea (%rax,%r10,1),%r14 + lea (%rcx,%rax,1),%r10 mov offset(%rsp),%rax - lea (%rax,%r10,1),%r15 - add -offset(%rsp),%r10 - cmpq $something,-offset(%rsp) + lea (%rax,%rcx,1),%r9 jle - mov -offset(%rsp),%rdx - mov %rbx,%rdi - neg %rdi - mov %r10,-offset(%rsp) - lea (%rdx,%rdi,4),%r8 - xor %eax,%eax - mov %rcx,%r10 + xor %r15d,%r15d + mov %rcx,%r14 + mov %rcx,%rax + mov %r8,%rdx + mov %rsi,%rcx + mov %r15,%rsi jmp - nopl offset(%rax,%rax,1) - cmp $something,%rdi - jle - vmovss (%r9),%xmm0 - mov -offset(%rsp),%rcx + nopw offset(%rax,%rax,1) + jge + vmovss offset(%r14),%xmm7 + vmovss offset(%r14),%xmm5 /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_COOPERLAKE.o (objdump) @@ -2,120 +2,289 @@ /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ec980000 AWAVAUATUSH..... - 0010 004889b4 24800000 0048c1fe 0448897c .H..$....H...H.| - 0020 24884889 54247848 898c2488 0000004c $.H.T$xH..$....L - 0030 894424f0 4c894c24 d84889b4 24900000 .D$.L.L$.H..$... - 0040 004885f6 0f8e4e03 0000488d 0449488d .H....N...H..IH. - 0050 1c8d0000 00004c8d 34cd0000 00004989 ......L.4.....I. - 0060 f74889ce 488d0c85 00000000 48894c24 .H..H.......H.L$ - 0070 404889f1 48c1e104 4989d248 8d143348 @H..H...I..H..3H - 0080 890c2448 8d0c9500 00000048 894c2448 ..$H.......H.L$H - 0090 488d0cc5 00000000 48c1e004 48894c24 H.......H...H.L$ - 00a0 50488944 2468486b ce1c486b c63448c1 PH.D$hHk..Hk.4H. - 00b0 e7064889 4c240848 89442420 4889f148 ..H.L$.H.D$ H..H - 00c0 6bc63848 c1e10548 894c2410 4c89f148 k.8H...H.L$.L..H - 00d0 01f14889 44242848 6bc63c48 c1e10248 ..H.D$(Hk.b + 03b0 417e0810 4b0162c1 7e081053 02c4417a A~..K.b.~..S..Az + 03c0 106b0cc4 c17a1073 1462417e 08104201 .k...z.s.bA~..B. + 03d0 62c17e08 104a02c4 c17a106a 14c4c17a b.~..J...z.j...z + 03e0 105a1862 c17e0810 4102c4c1 7a107910 .Z.b.~..A...z.y. + 03f0 62c17e08 107901c4 c17a1061 14c4c17a b.~..y...z.a...z + 0400 105118c5 fa114c24 f0c57a11 4c24f4c4 .Q....L$..z.L$.. + 0410 c17a1049 1cc4417a 104b10c5 7a115c24 .z.I..Az.K..z.\$ + 0420 f8c57a11 6424fcc4 417a1059 0cc4417a ..z.d$..Az.Y..Az + 0430 10620cc5 7a110424 62617e08 117c2401 .b..z..$ba~..|$. + 0440 c4417a10 42106241 7e081039 c57a113a .Az.B.bA~..9.z.: + 0450 c57a107c 24b46261 7e08117a 07c57a11 .z.|$.ba~..z..z. + 0460 7a08c57a 107c24cc 62617e08 107c24e8 z..z.|$.ba~..|$. + 0470 c57a117a 0cc57a10 7c24e462 617e0811 .z.z..z.|$.ba~.. + 0480 7208c57a 117a10c5 7a107c24 f462617e r..z.z..z.|$.ba~ + 0490 08107424 e3c57a11 7a146261 7e08116a ..t$..z.z.ba~..j + 04a0 09c57a10 3c246261 7e08106c 24e2c57a ..z.<$ba~..l$..z + 04b0 117a1862 617e0811 520c6261 7e08114a .z.ba~..R.ba~..J + 04c0 0d62617e 0811420e 62e17e08 11621362 .ba~..B.b.~..b.b /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_COOPERLAKE.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 42070000 00420e10 8f02420e ....B....B....B. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ed00103 b1060a0e ..A.8..G........ + 0020 00000000 dc110000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05440e30 ...E. ..B.(..D.0 + 0040 8606410e 38830747 0ea00203 59110a0e ..A.8..G....Y... 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0060 440e0844 0b000000 D..D.... /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_SKYLAKEX.o (disasm) @@ -7,390 +7,802 @@ strsm_ilnucopy_SKYLAKEX: push %r15 push %r14 + mov %r9,%r14 push %r13 push %r12 + mov %rdx,%r12 push %rbp push %rbx sub $something,%rsp mov %rsi,offset(%rsp) sar $something,%rsi - mov %rdi,-offset(%rsp) - mov %rdx,offset(%rsp) + mov %rdi,offset(%rsp) mov %rcx,offset(%rsp) - mov %r8,-offset(%rsp) - mov %r9,-offset(%rsp) + mov %r8,offset(%rsp) mov %rsi,offset(%rsp) test %rsi,%rsi jle + lea offset(,%rcx,4),%r9 lea (%rcx,%rcx,2),%rax - lea offset(,%rcx,4),%rbx - lea offset(,%rcx,8),%r14 - mov %rsi,%r15 + mov %r9,%rdx + lea offset(,%rcx,8),%r10 + lea offset(,%rax,4),%r11 + lea offset(,%rax,8),%rbp + mov %rsi,%rbx + imul $something,%rcx,%rax mov %rcx,%rsi - lea offset(,%rax,4),%rcx - mov %rcx,offset(%rsp) - mov %rsi,%rcx + add %rcx,%rdx shl $something,%rcx - mov %rdx,%r10 - lea (%rbx,%rsi,1),%rdx - mov %rcx,(%rsp) - lea offset(,%rdx,4),%rcx mov %rcx,offset(%rsp) - lea offset(,%rax,8),%rcx - shl $something,%rax + mov %rdi,%rcx + and $something,%ecx mov %rcx,offset(%rsp) + mov %rdi,%rcx mov %rax,offset(%rsp) - imul $something,%rsi,%rcx - imul $something,%rsi,%rax - shl $something,%rdi + and $something,%ecx + mov %rdi,%rax + sar $something,%rax mov %rcx,offset(%rsp) + mov %rdi,%rcx + and $something,%rdi + mov %rdi,%r13 + mov %rax,%rdi + shl $something,%rdi + shl $something,%rsi + shl $something,%rdx + mov %rsi,offset(%rsp) + add %rdi,%rsi + mov %r9,offset(%rsp) + mov %r10,offset(%rsp) + add %rdi,%r9 + add %rdi,%r10 + mov %r11,offset(%rsp) + mov %rdx,offset(%rsp) + add %rdi,%r11 + add %rdi,%rdx + mov %rbp,offset(%rsp) mov %rax,offset(%rsp) - mov %rsi,%rcx - imul $something,%rsi,%rax - shl $something,%rcx - mov %rcx,offset(%rsp) - mov %r14,%rcx - add %rsi,%rcx + add %rdi,%rbp + mov %rsi,offset(%rsp) + shl $something,%rax + mov offset(%rsp),%rsi + and $something,%ecx + mov %r9,offset(%rsp) + mov %r10,offset(%rsp) + mov %r11,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rbp,offset(%rsp) mov %rax,offset(%rsp) - imul $something,%rsi,%rax - shl $something,%rcx - mov %rcx,offset(%rsp) - lea offset(,%rdx,8),%rcx + mov %r12,offset(%rsp) + add %rdi,%rsi mov %rcx,offset(%rsp) - mov %rax,offset(%rsp) - imul $something,%rsi,%rcx - mov %r15,%rax - shl $something,%rax - shl $something,%rsi - add %r8,%rax - mov %r14,-offset(%rsp) + vmovss offset(%rip),%xmm0 # + lea (%r8,%rbx,8),%rcx mov %rcx,offset(%rsp) - mov %rsi,-offset(%rsp) - mov %rax,offset(%rsp) mov %rdi,offset(%rsp) - vmovss offset(%rip),%xmm1 # - mov %rbx,%r11 - mov %r8,%rbx - nop - lea (%r11,%r10,1),%rax - mov %rax,-offset(%rsp) - mov -offset(%rsp),%rax - mov %r10,%r9 - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov (%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) + mov %rsi,offset(%rsp) + mov %r12,%rcx + mov %r8,%rsi + mov %r13,%rdi + mov %r14,%r8 + nopl offset(%rax) mov offset(%rsp),%rax - add %r10,%rax - mov %rax,-offset(%rsp) + cmpq $something,offset(%rsp) + lea (%rax,%rcx,1),%r13 mov offset(%rsp),%rax - lea (%r10,%rax,1),%rcx + lea (%rax,%rcx,1),%r12 mov offset(%rsp),%rax - lea (%rax,%r10,1),%rbp + lea (%rcx,%rax,1),%rbp mov offset(%rsp),%rax - lea (%r10,%rax,1),%r12 + lea (%rax,%rcx,1),%rbx mov offset(%rsp),%rax - lea (%rax,%r10,1),%r13 + lea (%rcx,%rax,1),%r11 mov offset(%rsp),%rax - lea (%rax,%r10,1),%r14 + lea (%rcx,%rax,1),%r10 mov offset(%rsp),%rax - lea (%rax,%r10,1),%r15 - add -offset(%rsp),%r10 - cmpq $something,-offset(%rsp) + lea (%rax,%rcx,1),%r9 jle - mov -offset(%rsp),%rdx - mov %rbx,%rdi - neg %rdi - mov %r10,-offset(%rsp) - lea (%rdx,%rdi,4),%r8 - xor %eax,%eax - mov %rcx,%r10 + xor %r15d,%r15d + mov %rcx,%r14 + mov %rcx,%rax + mov %r8,%rdx + mov %rsi,%rcx + mov %r15,%rsi jmp - nopl offset(%rax,%rax,1) - cmp $something,%rdi - jle - vmovss (%r9),%xmm0 - mov -offset(%rsp),%rcx + nopw offset(%rax,%rax,1) + jge + vmovss offset(%r14),%xmm7 + vmovss offset(%r14),%xmm5 /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_SKYLAKEX.o (objdump) @@ -2,120 +2,289 @@ /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 55534881 ec980000 AWAVAUATUSH..... - 0010 004889b4 24800000 0048c1fe 0448897c .H..$....H...H.| - 0020 24884889 54247848 898c2488 0000004c $.H.T$xH..$....L - 0030 894424f0 4c894c24 d84889b4 24900000 .D$.L.L$.H..$... - 0040 004885f6 0f8e4e03 0000488d 0449488d .H....N...H..IH. - 0050 1c8d0000 00004c8d 34cd0000 00004989 ......L.4.....I. - 0060 f74889ce 488d0c85 00000000 48894c24 .H..H.......H.L$ - 0070 404889f1 48c1e104 4989d248 8d143348 @H..H...I..H..3H - 0080 890c2448 8d0c9500 00000048 894c2448 ..$H.......H.L$H - 0090 488d0cc5 00000000 48c1e004 48894c24 H.......H...H.L$ - 00a0 50488944 2468486b ce1c486b c63448c1 PH.D$hHk..Hk.4H. - 00b0 e7064889 4c240848 89442420 4889f148 ..H.L$.H.D$ H..H - 00c0 6bc63848 c1e10548 894c2410 4c89f148 k.8H...H.L$.L..H - 00d0 01f14889 44242848 6bc63c48 c1e10248 ..H.D$(Hk.b + 03b0 417e0810 4b0162c1 7e081053 02c4417a A~..K.b.~..S..Az + 03c0 106b0cc4 c17a1073 1462417e 08104201 .k...z.s.bA~..B. + 03d0 62c17e08 104a02c4 c17a106a 14c4c17a b.~..J...z.j...z + 03e0 105a1862 c17e0810 4102c4c1 7a107910 .Z.b.~..A...z.y. + 03f0 62c17e08 107901c4 c17a1061 14c4c17a b.~..y...z.a...z + 0400 105118c5 fa114c24 f0c57a11 4c24f4c4 .Q....L$..z.L$.. + 0410 c17a1049 1cc4417a 104b10c5 7a115c24 .z.I..Az.K..z.\$ + 0420 f8c57a11 6424fcc4 417a1059 0cc4417a ..z.d$..Az.Y..Az + 0430 10620cc5 7a110424 62617e08 117c2401 .b..z..$ba~..|$. + 0440 c4417a10 42106241 7e081039 c57a113a .Az.B.bA~..9.z.: + 0450 c57a107c 24b46261 7e08117a 07c57a11 .z.|$.ba~..z..z. + 0460 7a08c57a 107c24cc 62617e08 107c24e8 z..z.|$.ba~..|$. + 0470 c57a117a 0cc57a10 7c24e462 617e0811 .z.z..z.|$.ba~.. + 0480 7208c57a 117a10c5 7a107c24 f462617e r..z.z..z.|$.ba~ + 0490 08107424 e3c57a11 7a146261 7e08116a ..t$..z.z.ba~..j + 04a0 09c57a10 3c246261 7e08106c 24e2c57a ..z.<$ba~..l$..z + 04b0 117a1862 617e0811 520c6261 7e08114a .z.ba~..R.ba~..J + 04c0 0d62617e 0811420e 62e17e08 11621362 .ba~..B.b.~..b.b /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ 0020 010001c0 04000000 09000000 00000000 ................ /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_ilnucopy_SKYLAKEX.o (objdump) @@ -4,8 +4,8 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... - 0020 00000000 42070000 00420e10 8f02420e ....B....B....B. - 0030 188e0342 0e208d04 420e288c 05410e30 ...B. ..B.(..A.0 - 0040 8606410e 38830747 0ed00103 b1060a0e ..A.8..G........ + 0020 00000000 dc110000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05440e30 ...E. ..B.(..D.0 + 0040 8606410e 38830747 0ea00203 59110a0e ..A.8..G....Y... 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. - 0060 440e0841 0b000000 D..A.... + 0060 440e0844 0b000000 D..D.... /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_COOPERLAKE.o (disasm) @@ -7,289 +7,783 @@ strsm_iltncopy_COOPERLAKE: push %r15 push %r14 + mov %r9,%r14 push %r13 push %r12 - mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) sar $something,%rsi - mov %rdi,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %r8,%r15 - mov %rsi,%rax - neg %r15 + lea offset(,%rcx,8),%rax + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rcx,%rbx + mov %rdx,%r15 + lea offset(,%rcx,4),%rdx + lea offset(,%rax,4),%rcx shl $something,%rax - add %r8,%rax - shl $something,%r15 + mov %rax,offset(%rsp) + mov %rbx,%rax + shl $something,%rax + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + add %rbx,%rdx + mov %rbx,%rcx + imul $something,%rbx,%rbx + mov %rax,%r13 + mov %rdi,%rax + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) mov %rdi,%rbx - mov %rax,-offset(%rsp) - mov %rdx,-offset(%rsp) - lea (%rdx,%r15,1),%rax - mov %rdi,%rbp - mov %rax,-offset(%rsp) - lea offset(,%rcx,4),%r13 mov %rdi,%rax + sar $something,%rbx + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + imul %r13,%rax + shl $something,%rcx + mov %rcx,offset(%rsp) + add %r15,%rax + mov %rax,offset(%rsp) + lea offset(,%rdx,4),%rcx + and $something,%edi + lea (%r8,%rsi,8),%rax + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + lea offset(,%rbx,8),%r12 + mov %rbx,offset(%rsp) + vmovss offset(%rip),%xmm0 # shl $something,%rbx - vmovss offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%rbp - mov %r8,%rdi - lea offset(%r13),%r14 - mov %rbx,%r12 - mov %rax,%r8 - nopw offset(%rax,%rax,1) - mov -offset(%rsp),%rax - sub %r15,%rax - test %r8,%r8 - jle - mov %rdi,%rsi - mov $something,%r10d - neg %rsi - lea (%rax,%r15,1),%rbx - lea (%r9,%r15,1),%r11 - sub %rdi,%r10 - mov %r9,%rdx + mov %rbx,offset(%rsp) + mov %r8,%rbp + mov %r15,%rbx + mov %r12,%r14 + mov %r9,%r15 + nopl offset(%rax) + mov offset(%rsp),%rax + mov offset(%rsp),%rcx + lea (%rax,%rbx,1),%r10 + mov offset(%rsp),%rax + mov offset(%rsp),%rsi + lea (%rax,%rbx,1),%rdx + mov offset(%rsp),%rax + mov offset(%rsp),%rdi + lea (%rbx,%rax,1),%r8 + mov offset(%rsp),%rax + add %rbx,%rcx + add %rbx,%rax + add %rbx,%rsi + add %rbx,%rdi + cmpq $something,offset(%rsp) + jle + mov %r15,%r9 + xor %r12d,%r12d + mov %r15,-offset(%rsp) + mov %rbx,%r11 + mov %r12,%r15 + mov %rbp,%r12 + mov %rbx,%rbp + mov %r14,%rbx + mov %r9,%r14 jmp - nopl (%rax) - cmp $something,%rsi + nopl offset(%rax) jle - inc %rsi - add $something,%rdx + vmovss offset(%r11),%xmm7 + vmovss offset(%r11),%xmm5 + vmovss offset(%r11),%xmm6 + vmovss offset(%r11),%xmm4 + vmovss offset(%r11),%xmm3 + vmovss offset(%r11),%xmm31 + vmovss offset(%r11),%xmm30 + vmovss (%r10),%xmm29 + vmovss offset(%r10),%xmm28 + vmovss offset(%r10),%xmm27 + vmovss offset(%r10),%xmm26 + vmovss offset(%r10),%xmm25 + vmovss offset(%r10),%xmm24 + vmovss offset(%r10),%xmm23 + vmovss offset(%r10),%xmm22 + vmovss (%rdx),%xmm21 + vmovss offset(%rdx),%xmm20 + vmovss offset(%rdx),%xmm19 + vmovss offset(%rdx),%xmm18 + vmovss offset(%rdx),%xmm17 + vmovss offset(%rdx),%xmm16 + vmovss offset(%rdx),%xmm15 + vmovss offset(%rdx),%xmm14 + vmovss (%r8),%xmm13 + vmovss offset(%r8),%xmm12 + vmovss offset(%r8),%xmm11 + vmovss offset(%r8),%xmm10 + vmovss %xmm7,-offset(%rsp) + vmovss %xmm5,-offset(%rsp) + vmovss %xmm6,-offset(%rsp) + vmovss %xmm4,-offset(%rsp) + vmovss %xmm3,-offset(%rsp) + vmovss offset(%r8),%xmm9 + vmovss offset(%r8),%xmm7 + vmovss offset(%r8),%xmm8 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rax),%xmm7 + vmovss offset(%r8),%xmm6 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rax),%xmm7 + vmovss (%rax),%xmm5 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rax),%xmm7 + vmovss offset(%rax),%xmm4 + vmovss %xmm7,-offset(%rsp) + vmovss (%rcx),%xmm7 + vmovss offset(%rax),%xmm3 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss offset(%rax),%xmm2 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss offset(%rax),%xmm1 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss %xmm7,-offset(%rsp) /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_COOPERLAKE.o (objdump) @@ -2,95 +2,271 @@ /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t - 0010 24d048c1 fe044889 7c24d848 894c24e0 $.H...H.|$.H.L$. - 0020 48897424 e84885f6 0f8eef01 00004d89 H.t$.H........M. - 0030 c74889f0 49f7df48 c1e0044c 01c049c1 .H..I..H...L..I. - 0040 e7024889 fb488944 24c04889 5424f04a ..H..H.D$.H.T$.J - 0050 8d043a48 89fd4889 4424c84c 8d2c8d00 ..:H..H.D$.L.,.. - 0060 00000048 89f848c1 e306c5fa 100d0000 ...H..H......... - 0070 00004c89 4424f84c 29c54c89 c74d8d75 ..L.D$.L).L..M.u - 0080 044989dc 4989c066 0f1f8400 00000000 .I..I..f........ - 0090 488b4424 c84c29f8 4d85c00f 8e420100 H.D$.L).M....B.. - 00a0 004889fe 41ba0100 000048f7 de4a8d1c .H..A.....H..J.. - 00b0 384f8d1c 394929fa 4c89caeb 2a0f1f00 8O..9I).L...*... - 00c0 4883fe0f 0f8ed600 000048ff c64883c2 H.........H..H.. - 00d0 404c01e8 4c01f349 83c34449 ffc24839 @L..L..I..DI..H9 - 00e0 ee0f84f9 00000048 8d0c3e48 39cf7ed0 .......H..>H9.~. - 00f0 4885f679 d5c5fa10 00c5fa11 02c5fa10 H..y............ - 0100 4004c5fa 114204c5 fa104008 c5fa1142 @....B....@....B - 0110 08c5fa10 400cc5fa 11420cc5 fa104010 ....@....B....@. - 0120 c5fa1142 10c5fa10 4014c5fa 114214c5 ...B....@....B.. - 0130 fa104018 c5fa1142 18c5fa10 401cc5fa ..@....B....@... - 0140 11421cc5 fa104020 c5fa1142 20c5fa10 .B....@ ...B ... - 0150 4024c5fa 114224c5 fa104028 c5fa1142 @$...B$...@(...B - 0160 28c5fa10 402cc5fa 11422cc5 fa104030 (...@,...B,...@0 - 0170 c5fa1142 30c5fa10 4034c5fa 114234c5 ...B0...@4...B4. - 0180 fa104038 c5fa1142 38c5fa10 403cc5fa ..@8...B8...@<.. - 0190 11423ce9 32ffffff 0f1f8400 00000000 .B<.2........... - 01a0 c5f25e03 4c89d1c4 c17a1103 4983fa10 ..^.L....z..I... - 01b0 0f8414ff ffff662e 0f1f8400 00000000 ......f......... - 01c0 c5fa1004 88c5fa11 048a48ff c14883f9 ..........H..H.. - 01d0 1075ede9 f2feffff 0f1f8400 00000000 .u.............. - 01e0 4d01e148 83c71048 83ed1049 83ef4048 M..H...H...I..@H - 01f0 3b7c24c0 0f8596fe ffff488b 5c24e84c ;|$.......H.\$.L - 0200 8b6424f0 4889d848 c1e0064c 8b4424f8 .d$.H..H...L.D$. - 0210 4901c448 89d848c1 e0044901 c0f64424 I..H..H...I...D$ - 0220 d0080f84 ff000000 488b4424 d84d8d6c ........H.D$.M.l - 0230 24204885 c00f8ee5 00000048 8b5c24e0 $ H........H.\$. - 0240 4c89c148 f7d94c8d 1c9d0000 0000488d L..H..L.......H. - 0250 3c8d0000 00004c29 c0be0100 00004d8d <.....L)......M. - 0260 143c4889 c3c5fa10 0d000000 00498d6b .J...I9.~.H..y - 03c0 d9c4c17a 100424c5 fa1101c4 c17a1044 ...z..$......z.D - 03d0 2404c5fa 114104c4 c17a1044 2408c5fa $....A...z.D$... - 03e0 114108c4 c17a1044 240cc5fa 11410ceb .A...z.D$....A.. - 03f0 a9488b44 24d848c1 e0044901 c14983c0 .H.D$.H...I..I.. - 0400 044d89ec f64424d0 020f84ad 00000048 .M...D$........H - 0410 8b7c24d8 498d6c24 084885ff 0f8e9300 .|$.I.l$.H...... - 0420 0000488b 4424e04c 29c74c8d 14850000 ..H.D$.L).L..... - 0430 00004c89 c048f7d8 488d0c85 00000000 ..L..H..H....... - 0440 498d340c c5fa100d 00000000 498d5a04 I.4.........I.Z. - 0450 4c01c949 89fb4c89 caeb360f 1f440000 L..I..L...6..D.. - 0460 4885c079 16c4c17a 100424c5 fa1102c4 H..y...z..$..... - 0470 c17a1044 2404c5fa 11420448 ffc04883 .z.D$....B.H..H. - 0480 c2084d01 d44801de 4883c10c 4c39d874 ..M..H..H...L9.t - 0490 1b498d3c 004939f8 7fc64883 f8017fdb .I.<.I9...H..... - 04a0 c5f25e06 c5fa1101 75c5ebcf 488b4424 ..^.....u...H.D$ - 04b0 d84d8d0c c14983c0 024989ec f64424d0 .M...I...I...D$. - 04c0 0175765b 5d415c41 5d415e31 c0415fc3 .uv[]A\A]A^1.A_. - 04d0 c4c1725e 024889f2 c5fa1107 4883fe08 ..r^.H......H... - 04e0 0f84a4fd ffff662e 0f1f8400 00000000 ......f......... - 04f0 c4c17a10 0494c5fa 11049048 ffc24883 ..z........H..H. - 0500 fa0875ec e981fdff ffc4c172 5e024889 ..u........r^.H. - 0510 f0c5fa11 074883fe 040f847b feffff90 .....H.....{.... - 0520 c4c17a10 0484c5fa 11048148 ffc04883 ..z........H..H. - 0530 f80475ec e961feff ff4c8b5c 24d84d85 ..u..a...L.\$.M. - 0540 db7e8048 8b4c24e0 4c89c248 f7da4c8d .~.H.L$.L..H..L. - 0550 14950000 000048c1 e1024b8d 3414c5fa ......H...K.4... - 0560 100d0000 0000488d 79044d01 ca31c0eb ......H.y.M..1.. - 0570 280f1f80 00000000 750ac5f2 5e06c481 (.......u...^... - 0580 7a1104c2 48ffc049 01cc48ff c24801fe z...H..I..H..H.. - 0590 4939c30f 842affff ff4939c0 7eda4885 I9...*...I9.~.H. - 05a0 d279e1c4 c17a1004 24c4c17a 110481eb .y...z..$..z.... - 05b0 d3 . + 0000 41574156 4d89ce41 55415455 534881ec AWAVM..AUATUSH.. + 0010 b0000000 4889b424 90000000 48c1fe03 ....H..$....H... + 0020 4889bc24 98000000 48899424 88000000 H..$....H..$.... + 0030 48898c24 a0000000 4c898424 80000000 H..$....L..$.... + 0040 4889b424 a8000000 4885f60f 8e710a00 H..$....H....q.. + 0050 00488d04 cd000000 00488944 2420488d .H.......H.D$ H. + 0060 04494889 cb4989d7 488d148d 00000000 .IH..I..H....... + 0070 488d0c85 00000000 48c1e003 48894424 H.......H...H.D$ + 0080 704889d8 48c1e005 48895424 1048894c pH..H...H.T$.H.L + 0090 24604801 da4889d9 486bdb1c 4989c548 $`H..H..Hk..I..H + 00a0 89f883e0 0448895c 24304889 44244848 .....H.\$0H.D$HH + 00b0 89fb4889 f848c1fb 0383e002 48894424 ..H..H......H.D$ + 00c0 504889d8 490fafc5 48c1e104 48894c24 PH..I...H...H.L$ + 00d0 284c01f8 48894424 18488d0c 95000000 (L..H.D$.H...... + 00e0 0083e701 498d04f0 48894c24 6848897c ....I...H.L$hH.| + 00f0 24584889 4424384c 8d24dd00 00000048 $XH.D$8L.$.....H + 0100 895c2440 c5fa1005 00000000 48c1e308 .\$@........H... + 0110 48895c24 784c89c5 4c89fb4d 89e64d89 H.\$xL..L..M..M. + 0120 cf0f1f80 00000000 488b4424 10488b4c ........H.D$.H.L + 0130 24684c8d 1418488b 44242048 8b742470 $hL...H.D$ H.t$p + 0140 488d1418 488b4424 60488b7c 24304c8d H...H.D$`H.|$0L. + 0150 0403488b 44242848 01d94801 d84801de ..H.D$(H..H..H.. + 0160 4801df48 837c2440 000f8e99 0e00004d H..H.|$@.......M + 0170 89f94531 e44c897c 24884989 db4d89e7 ..E1.L.|$.I..M.. + 0180 4989ec48 89dd4c89 f34d89ce e9180500 I..H..L..M...... + 0190 000f1f80 00000000 0f8edf04 0000c4c1 ................ + 01a0 7a107b04 c4c17a10 6b08c4c1 7a10730c z.{...z.k...z.s. + 01b0 c4c17a10 6310c4c1 7a105b14 62417e08 ..z.c...z.[.bA~. + 01c0 107b0662 417e0810 73076241 7e08102a .{.bA~..s.bA~..* + 01d0 62417e08 10620162 417e0810 5a026241 bA~..b.bA~..Z.bA + 01e0 7e081052 0362417e 08104a04 62417e08 ~..R.bA~..J.bA~. + 01f0 10420562 c17e0810 7a0662c1 7e081072 .B.b.~..z.b.~..r + 0200 0762e17e 08102a62 e17e0810 620162e1 .b.~..*b.~..b.b. + 0210 7e08105a 0262e17e 08105203 62e17e08 ~..Z.b.~..R.b.~. + 0220 104a0462 e17e0810 4205c57a 107a18c5 .J.b.~..B..z.z.. + 0230 7a10721c c4417a10 28c4417a 106004c4 z.r..Az.(.Az.`.. + 0240 417a1058 08c4417a 10500cc5 fa117c24 Az.X..Az.P....|$ + 0250 88c5fa11 6c2490c5 fa117424 94c5fa11 ....l$....t$.... + 0260 642498c5 fa115c24 9cc4417a 104810c4 d$....\$..Az.H.. + 0270 c17a1078 18c4417a 104014c5 fa117c24 .z.x..Az.@....|$ + 0280 a0c5fa10 7814c4c1 7a10701c c5fa117c ....x...z.p....| + 0290 24a4c5fa 107818c5 fa1028c5 fa117c24 $....x....(...|$ + 02a0 a8c5fa10 781cc5fa 106004c5 fa117c24 ....x....`....|$ + 02b0 acc5fa10 39c5fa10 5808c5fa 117c24b0 ....9...X....|$. + 02c0 c5fa1079 04c5fa10 500cc5fa 117c24b4 ...y....P....|$. + 02d0 c5fa1079 08c5fa10 4810c5fa 117c24b8 ...y....H....|$. + 02e0 c5fa1079 0cc5fa11 7c24bcc5 fa107910 ...y....|$....y. + 02f0 c5fa117c 24c0c5fa 107914c5 fa117c24 ...|$....y....|$ + 0300 c4c5fa10 7918c5fa 117c24c8 c5fa1079 ....y....|$....y + 0310 1cc5fa11 7c24ccc5 fa103ec5 fa117c24 ....|$....>...|$ + 0320 d0c5fa10 7e04c5fa 117c24d4 c5fa107e ....~....|$....~ + 0330 08c5fa11 7c24d8c5 fa107e0c c5fa117c ....|$....~....| + 0340 24dcc5fa 107e10c5 fa117c24 e0c5fa10 $....~....|$.... + 0350 7e14c5fa 117c24e4 c5fa107e 18c5fa11 ~....|$....~.... + 0360 7c24e8c5 fa107e1c c5fa117c 24ecc5fa |$....~....|$... + 0370 103fc5fa 117c24f0 c5fa107f 04c5fa11 .?...|$......... + 0380 7c24f4c5 fa107f08 c5fa117c 24f8c5fa |$.........|$... + 0390 107f0cc5 fa117c24 fcc5fa10 7f10c5fa ......|$........ + 03a0 113c24c5 fa107f14 c5fa117c 2404c5fa .<$........|$... + 03b0 107f18c5 fa117c24 08c5fa10 7f1cc5fa ......|$........ + 03c0 117c240c c4c17a10 3b62417e 08117906 .|$...z.;bA~..y. + 03d0 c4c17a11 39c5fa10 7c248862 417e0811 ..z.9...|$.bA~.. + 03e0 7107c4c1 7a117904 c5fa107c 24906241 q...z.y....|$.bA + 03f0 7e081169 08c4c17a 117908c5 fa107c24 ~..i...z.y....|$ + 0400 9462417e 08116109 c4c17a11 790cc5fa .bA~..a...z.y... + 0410 107c2498 62417e08 11590ac4 c17a1179 .|$.bA~..Y...z.y + 0420 10c5fa10 7c249c62 417e0811 510bc4c1 ....|$.bA~..Q... + 0430 7a117914 62417e08 11490c62 417e0811 z.y.bA~..I.bA~.. + 0440 410d62c1 7e081179 0e62c17e 0811710f A.b.~..y.b.~..q. + 0450 62c17e08 11691062 c17e0811 611162c1 b.~..i.b.~..a.b. + 0460 7e081159 1262c17e 08115113 62c17e08 ~..Y.b.~..Q.b.~. + 0470 11491462 c17e0811 4115c441 7a117958 .I.b.~..A..Az.yX + 0480 c4417a11 715cc441 7a116960 c4417a11 .Az.q\.Az.i`.Az. + 0490 6164c441 7a115968 c5fa107c 24a0c441 ad.Az.Yh...|$..A + 04a0 7a11516c c4c17a11 7978c5fa 107c24a4 z.Ql..z.yx...|$. + 04b0 c4417a11 4970c4c1 7a11b994 000000c5 .Az.Ip..z....... + 04c0 fa107c24 a8c4417a 114174c4 c17a11b9 ..|$..Az.At..z.. + 04d0 98000000 c5fa107c 24acc4c1 7a11717c .......|$...z.q| + 04e0 c4c17a11 b99c0000 00c5fa10 7c24b0c4 ..z.........|$.. + 04f0 c17a11a9 80000000 c4c17a11 b9a00000 .z........z..... + 0500 00c5fa10 7c24b4c4 c17a11a1 84000000 ....|$...z...... + 0510 c4c17a11 b9a40000 00c5fa10 7c24b8c4 ..z.........|$.. + 0520 c17a1199 88000000 c4c17a11 b9a80000 .z........z..... + 0530 00c5fa10 7c24bcc4 c17a1191 8c000000 ....|$...z...... + 0540 c4c17a11 b9ac0000 00c5fa10 7c24c0c4 ..z.........|$.. + 0550 c17a1189 90000000 c4c17a11 b9b00000 .z........z..... + 0560 00c5fa10 7c24c4c4 c17a11b9 b4000000 ....|$...z...... + 0570 c5fa107c 24c8c4c1 7a11b9b8 000000c5 ...|$...z....... + 0580 fa107c24 ccc4c17a 11b9bc00 0000c5fa ..|$...z........ + 0590 107c24d0 c4c17a11 b9c00000 00c5fa10 .|$...z......... + 05a0 7c24d4c4 c17a11b9 c4000000 c5fa107c |$...z.........| + 05b0 24d8c4c1 7a11b9c8 000000c5 fa107c24 $...z.........|$ + 05c0 dcc4c17a 11b9cc00 0000c5fa 107c24e0 ...z.........|$. + 05d0 c4c17a11 b9d00000 00c5fa10 7c24e4c4 ..z.........|$.. + 05e0 c17a11b9 d4000000 c5fa107c 24e8c4c1 .z.........|$... + 05f0 7a11b9d8 000000c5 fa107c24 ecc4c17a z.........|$...z + 0600 11b9dc00 0000c5fa 107c24f0 c4c17a11 .........|$...z. + 0610 b9e00000 00c5fa10 7c24f4c4 c17a11b9 ........|$...z.. + 0620 e4000000 c5fa107c 24f8c4c1 7a11b9e8 .......|$...z... + 0630 000000c5 fa107c24 fcc4c17a 11b9ec00 ......|$...z.... + 0640 0000c5fa 103c24c4 c17a11b9 f0000000 .....<$..z...... + 0650 c5fa107c 2404c4c1 7a11b9f4 000000c5 ...|$...z....... /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 09080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 b1050000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 b7040a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 bd100000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05410e30 ...E. ..B.(..A.0 + 0040 8606410e 38830747 0ee80103 e40f0a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0844 0b000000 D..D.... /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_SKYLAKEX.o (disasm) @@ -7,289 +7,783 @@ strsm_iltncopy_SKYLAKEX: push %r15 push %r14 + mov %r9,%r14 push %r13 push %r12 - mov %rdx,%r12 push %rbp push %rbx - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) sar $something,%rsi - mov %rdi,-offset(%rsp) - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %r8,%r15 - mov %rsi,%rax - neg %r15 + lea offset(,%rcx,8),%rax + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rcx,%rbx + mov %rdx,%r15 + lea offset(,%rcx,4),%rdx + lea offset(,%rax,4),%rcx shl $something,%rax - add %r8,%rax - shl $something,%r15 + mov %rax,offset(%rsp) + mov %rbx,%rax + shl $something,%rax + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + add %rbx,%rdx + mov %rbx,%rcx + imul $something,%rbx,%rbx + mov %rax,%r13 + mov %rdi,%rax + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) mov %rdi,%rbx - mov %rax,-offset(%rsp) - mov %rdx,-offset(%rsp) - lea (%rdx,%r15,1),%rax - mov %rdi,%rbp - mov %rax,-offset(%rsp) - lea offset(,%rcx,4),%r13 mov %rdi,%rax + sar $something,%rbx + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + imul %r13,%rax + shl $something,%rcx + mov %rcx,offset(%rsp) + add %r15,%rax + mov %rax,offset(%rsp) + lea offset(,%rdx,4),%rcx + and $something,%edi + lea (%r8,%rsi,8),%rax + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + lea offset(,%rbx,8),%r12 + mov %rbx,offset(%rsp) + vmovss offset(%rip),%xmm0 # shl $something,%rbx - vmovss offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%rbp - mov %r8,%rdi - lea offset(%r13),%r14 - mov %rbx,%r12 - mov %rax,%r8 - nopw offset(%rax,%rax,1) - mov -offset(%rsp),%rax - sub %r15,%rax - test %r8,%r8 - jle - mov %rdi,%rsi - mov $something,%r10d - neg %rsi - lea (%rax,%r15,1),%rbx - lea (%r9,%r15,1),%r11 - sub %rdi,%r10 - mov %r9,%rdx + mov %rbx,offset(%rsp) + mov %r8,%rbp + mov %r15,%rbx + mov %r12,%r14 + mov %r9,%r15 + nopl offset(%rax) + mov offset(%rsp),%rax + mov offset(%rsp),%rcx + lea (%rax,%rbx,1),%r10 + mov offset(%rsp),%rax + mov offset(%rsp),%rsi + lea (%rax,%rbx,1),%rdx + mov offset(%rsp),%rax + mov offset(%rsp),%rdi + lea (%rbx,%rax,1),%r8 + mov offset(%rsp),%rax + add %rbx,%rcx + add %rbx,%rax + add %rbx,%rsi + add %rbx,%rdi + cmpq $something,offset(%rsp) + jle + mov %r15,%r9 + xor %r12d,%r12d + mov %r15,-offset(%rsp) + mov %rbx,%r11 + mov %r12,%r15 + mov %rbp,%r12 + mov %rbx,%rbp + mov %r14,%rbx + mov %r9,%r14 jmp - nopl (%rax) - cmp $something,%rsi + nopl offset(%rax) jle - inc %rsi - add $something,%rdx + vmovss offset(%r11),%xmm7 + vmovss offset(%r11),%xmm5 + vmovss offset(%r11),%xmm6 + vmovss offset(%r11),%xmm4 + vmovss offset(%r11),%xmm3 + vmovss offset(%r11),%xmm31 + vmovss offset(%r11),%xmm30 + vmovss (%r10),%xmm29 + vmovss offset(%r10),%xmm28 + vmovss offset(%r10),%xmm27 + vmovss offset(%r10),%xmm26 + vmovss offset(%r10),%xmm25 + vmovss offset(%r10),%xmm24 + vmovss offset(%r10),%xmm23 + vmovss offset(%r10),%xmm22 + vmovss (%rdx),%xmm21 + vmovss offset(%rdx),%xmm20 + vmovss offset(%rdx),%xmm19 + vmovss offset(%rdx),%xmm18 + vmovss offset(%rdx),%xmm17 + vmovss offset(%rdx),%xmm16 + vmovss offset(%rdx),%xmm15 + vmovss offset(%rdx),%xmm14 + vmovss (%r8),%xmm13 + vmovss offset(%r8),%xmm12 + vmovss offset(%r8),%xmm11 + vmovss offset(%r8),%xmm10 + vmovss %xmm7,-offset(%rsp) + vmovss %xmm5,-offset(%rsp) + vmovss %xmm6,-offset(%rsp) + vmovss %xmm4,-offset(%rsp) + vmovss %xmm3,-offset(%rsp) + vmovss offset(%r8),%xmm9 + vmovss offset(%r8),%xmm7 + vmovss offset(%r8),%xmm8 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rax),%xmm7 + vmovss offset(%r8),%xmm6 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rax),%xmm7 + vmovss (%rax),%xmm5 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rax),%xmm7 + vmovss offset(%rax),%xmm4 + vmovss %xmm7,-offset(%rsp) + vmovss (%rcx),%xmm7 + vmovss offset(%rax),%xmm3 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss offset(%rax),%xmm2 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss offset(%rax),%xmm1 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rcx),%xmm7 + vmovss %xmm7,-offset(%rsp) /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_SKYLAKEX.o (objdump) @@ -2,95 +2,271 @@ /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989d455 53488974 AWAVAUATI..USH.t - 0010 24d048c1 fe044889 7c24d848 894c24e0 $.H...H.|$.H.L$. - 0020 48897424 e84885f6 0f8eef01 00004d89 H.t$.H........M. - 0030 c74889f0 49f7df48 c1e0044c 01c049c1 .H..I..H...L..I. - 0040 e7024889 fb488944 24c04889 5424f04a ..H..H.D$.H.T$.J - 0050 8d043a48 89fd4889 4424c84c 8d2c8d00 ..:H..H.D$.L.,.. - 0060 00000048 89f848c1 e306c5fa 100d0000 ...H..H......... - 0070 00004c89 4424f84c 29c54c89 c74d8d75 ..L.D$.L).L..M.u - 0080 044989dc 4989c066 0f1f8400 00000000 .I..I..f........ - 0090 488b4424 c84c29f8 4d85c00f 8e420100 H.D$.L).M....B.. - 00a0 004889fe 41ba0100 000048f7 de4a8d1c .H..A.....H..J.. - 00b0 384f8d1c 394929fa 4c89caeb 2a0f1f00 8O..9I).L...*... - 00c0 4883fe0f 0f8ed600 000048ff c64883c2 H.........H..H.. - 00d0 404c01e8 4c01f349 83c34449 ffc24839 @L..L..I..DI..H9 - 00e0 ee0f84f9 00000048 8d0c3e48 39cf7ed0 .......H..>H9.~. - 00f0 4885f679 d5c5fa10 00c5fa11 02c5fa10 H..y............ - 0100 4004c5fa 114204c5 fa104008 c5fa1142 @....B....@....B - 0110 08c5fa10 400cc5fa 11420cc5 fa104010 ....@....B....@. - 0120 c5fa1142 10c5fa10 4014c5fa 114214c5 ...B....@....B.. - 0130 fa104018 c5fa1142 18c5fa10 401cc5fa ..@....B....@... - 0140 11421cc5 fa104020 c5fa1142 20c5fa10 .B....@ ...B ... - 0150 4024c5fa 114224c5 fa104028 c5fa1142 @$...B$...@(...B - 0160 28c5fa10 402cc5fa 11422cc5 fa104030 (...@,...B,...@0 - 0170 c5fa1142 30c5fa10 4034c5fa 114234c5 ...B0...@4...B4. - 0180 fa104038 c5fa1142 38c5fa10 403cc5fa ..@8...B8...@<.. - 0190 11423ce9 32ffffff 0f1f8400 00000000 .B<.2........... - 01a0 c5f25e03 4c89d1c4 c17a1103 4983fa10 ..^.L....z..I... - 01b0 0f8414ff ffff662e 0f1f8400 00000000 ......f......... - 01c0 c5fa1004 88c5fa11 048a48ff c14883f9 ..........H..H.. - 01d0 1075ede9 f2feffff 0f1f8400 00000000 .u.............. - 01e0 4d01e148 83c71048 83ed1049 83ef4048 M..H...H...I..@H - 01f0 3b7c24c0 0f8596fe ffff488b 5c24e84c ;|$.......H.\$.L - 0200 8b6424f0 4889d848 c1e0064c 8b4424f8 .d$.H..H...L.D$. - 0210 4901c448 89d848c1 e0044901 c0f64424 I..H..H...I...D$ - 0220 d0080f84 ff000000 488b4424 d84d8d6c ........H.D$.M.l - 0230 24204885 c00f8ee5 00000048 8b5c24e0 $ H........H.\$. - 0240 4c89c148 f7d94c8d 1c9d0000 0000488d L..H..L.......H. - 0250 3c8d0000 00004c29 c0be0100 00004d8d <.....L)......M. - 0260 143c4889 c3c5fa10 0d000000 00498d6b .J...I9.~.H..y - 03c0 d9c4c17a 100424c5 fa1101c4 c17a1044 ...z..$......z.D - 03d0 2404c5fa 114104c4 c17a1044 2408c5fa $....A...z.D$... - 03e0 114108c4 c17a1044 240cc5fa 11410ceb .A...z.D$....A.. - 03f0 a9488b44 24d848c1 e0044901 c14983c0 .H.D$.H...I..I.. - 0400 044d89ec f64424d0 020f84ad 00000048 .M...D$........H - 0410 8b7c24d8 498d6c24 084885ff 0f8e9300 .|$.I.l$.H...... - 0420 0000488b 4424e04c 29c74c8d 14850000 ..H.D$.L).L..... - 0430 00004c89 c048f7d8 488d0c85 00000000 ..L..H..H....... - 0440 498d340c c5fa100d 00000000 498d5a04 I.4.........I.Z. - 0450 4c01c949 89fb4c89 caeb360f 1f440000 L..I..L...6..D.. - 0460 4885c079 16c4c17a 100424c5 fa1102c4 H..y...z..$..... - 0470 c17a1044 2404c5fa 11420448 ffc04883 .z.D$....B.H..H. - 0480 c2084d01 d44801de 4883c10c 4c39d874 ..M..H..H...L9.t - 0490 1b498d3c 004939f8 7fc64883 f8017fdb .I.<.I9...H..... - 04a0 c5f25e06 c5fa1101 75c5ebcf 488b4424 ..^.....u...H.D$ - 04b0 d84d8d0c c14983c0 024989ec f64424d0 .M...I...I...D$. - 04c0 0175765b 5d415c41 5d415e31 c0415fc3 .uv[]A\A]A^1.A_. - 04d0 c4c1725e 024889f2 c5fa1107 4883fe08 ..r^.H......H... - 04e0 0f84a4fd ffff662e 0f1f8400 00000000 ......f......... - 04f0 c4c17a10 0494c5fa 11049048 ffc24883 ..z........H..H. - 0500 fa0875ec e981fdff ffc4c172 5e024889 ..u........r^.H. - 0510 f0c5fa11 074883fe 040f847b feffff90 .....H.....{.... - 0520 c4c17a10 0484c5fa 11048148 ffc04883 ..z........H..H. - 0530 f80475ec e961feff ff4c8b5c 24d84d85 ..u..a...L.\$.M. - 0540 db7e8048 8b4c24e0 4c89c248 f7da4c8d .~.H.L$.L..H..L. - 0550 14950000 000048c1 e1024b8d 3414c5fa ......H...K.4... - 0560 100d0000 0000488d 79044d01 ca31c0eb ......H.y.M..1.. - 0570 280f1f80 00000000 750ac5f2 5e06c481 (.......u...^... - 0580 7a1104c2 48ffc049 01cc48ff c24801fe z...H..I..H..H.. - 0590 4939c30f 842affff ff4939c0 7eda4885 I9...*...I9.~.H. - 05a0 d279e1c4 c17a1004 24c4c17a 110481eb .y...z..$..z.... - 05b0 d3 . + 0000 41574156 4d89ce41 55415455 534881ec AWAVM..AUATUSH.. + 0010 b0000000 4889b424 90000000 48c1fe03 ....H..$....H... + 0020 4889bc24 98000000 48899424 88000000 H..$....H..$.... + 0030 48898c24 a0000000 4c898424 80000000 H..$....L..$.... + 0040 4889b424 a8000000 4885f60f 8e710a00 H..$....H....q.. + 0050 00488d04 cd000000 00488944 2420488d .H.......H.D$ H. + 0060 04494889 cb4989d7 488d148d 00000000 .IH..I..H....... + 0070 488d0c85 00000000 48c1e003 48894424 H.......H...H.D$ + 0080 704889d8 48c1e005 48895424 1048894c pH..H...H.T$.H.L + 0090 24604801 da4889d9 486bdb1c 4989c548 $`H..H..Hk..I..H + 00a0 89f883e0 0448895c 24304889 44244848 .....H.\$0H.D$HH + 00b0 89fb4889 f848c1fb 0383e002 48894424 ..H..H......H.D$ + 00c0 504889d8 490fafc5 48c1e104 48894c24 PH..I...H...H.L$ + 00d0 284c01f8 48894424 18488d0c 95000000 (L..H.D$.H...... + 00e0 0083e701 498d04f0 48894c24 6848897c ....I...H.L$hH.| + 00f0 24584889 4424384c 8d24dd00 00000048 $XH.D$8L.$.....H + 0100 895c2440 c5fa1005 00000000 48c1e308 .\$@........H... + 0110 48895c24 784c89c5 4c89fb4d 89e64d89 H.\$xL..L..M..M. + 0120 cf0f1f80 00000000 488b4424 10488b4c ........H.D$.H.L + 0130 24684c8d 1418488b 44242048 8b742470 $hL...H.D$ H.t$p + 0140 488d1418 488b4424 60488b7c 24304c8d H...H.D$`H.|$0L. + 0150 0403488b 44242848 01d94801 d84801de ..H.D$(H..H..H.. + 0160 4801df48 837c2440 000f8e99 0e00004d H..H.|$@.......M + 0170 89f94531 e44c897c 24884989 db4d89e7 ..E1.L.|$.I..M.. + 0180 4989ec48 89dd4c89 f34d89ce e9180500 I..H..L..M...... + 0190 000f1f80 00000000 0f8edf04 0000c4c1 ................ + 01a0 7a107b04 c4c17a10 6b08c4c1 7a10730c z.{...z.k...z.s. + 01b0 c4c17a10 6310c4c1 7a105b14 62417e08 ..z.c...z.[.bA~. + 01c0 107b0662 417e0810 73076241 7e08102a .{.bA~..s.bA~..* + 01d0 62417e08 10620162 417e0810 5a026241 bA~..b.bA~..Z.bA + 01e0 7e081052 0362417e 08104a04 62417e08 ~..R.bA~..J.bA~. + 01f0 10420562 c17e0810 7a0662c1 7e081072 .B.b.~..z.b.~..r + 0200 0762e17e 08102a62 e17e0810 620162e1 .b.~..*b.~..b.b. + 0210 7e08105a 0262e17e 08105203 62e17e08 ~..Z.b.~..R.b.~. + 0220 104a0462 e17e0810 4205c57a 107a18c5 .J.b.~..B..z.z.. + 0230 7a10721c c4417a10 28c4417a 106004c4 z.r..Az.(.Az.`.. + 0240 417a1058 08c4417a 10500cc5 fa117c24 Az.X..Az.P....|$ + 0250 88c5fa11 6c2490c5 fa117424 94c5fa11 ....l$....t$.... + 0260 642498c5 fa115c24 9cc4417a 104810c4 d$....\$..Az.H.. + 0270 c17a1078 18c4417a 104014c5 fa117c24 .z.x..Az.@....|$ + 0280 a0c5fa10 7814c4c1 7a10701c c5fa117c ....x...z.p....| + 0290 24a4c5fa 107818c5 fa1028c5 fa117c24 $....x....(...|$ + 02a0 a8c5fa10 781cc5fa 106004c5 fa117c24 ....x....`....|$ + 02b0 acc5fa10 39c5fa10 5808c5fa 117c24b0 ....9...X....|$. + 02c0 c5fa1079 04c5fa10 500cc5fa 117c24b4 ...y....P....|$. + 02d0 c5fa1079 08c5fa10 4810c5fa 117c24b8 ...y....H....|$. + 02e0 c5fa1079 0cc5fa11 7c24bcc5 fa107910 ...y....|$....y. + 02f0 c5fa117c 24c0c5fa 107914c5 fa117c24 ...|$....y....|$ + 0300 c4c5fa10 7918c5fa 117c24c8 c5fa1079 ....y....|$....y + 0310 1cc5fa11 7c24ccc5 fa103ec5 fa117c24 ....|$....>...|$ + 0320 d0c5fa10 7e04c5fa 117c24d4 c5fa107e ....~....|$....~ + 0330 08c5fa11 7c24d8c5 fa107e0c c5fa117c ....|$....~....| + 0340 24dcc5fa 107e10c5 fa117c24 e0c5fa10 $....~....|$.... + 0350 7e14c5fa 117c24e4 c5fa107e 18c5fa11 ~....|$....~.... + 0360 7c24e8c5 fa107e1c c5fa117c 24ecc5fa |$....~....|$... + 0370 103fc5fa 117c24f0 c5fa107f 04c5fa11 .?...|$......... + 0380 7c24f4c5 fa107f08 c5fa117c 24f8c5fa |$.........|$... + 0390 107f0cc5 fa117c24 fcc5fa10 7f10c5fa ......|$........ + 03a0 113c24c5 fa107f14 c5fa117c 2404c5fa .<$........|$... + 03b0 107f18c5 fa117c24 08c5fa10 7f1cc5fa ......|$........ + 03c0 117c240c c4c17a10 3b62417e 08117906 .|$...z.;bA~..y. + 03d0 c4c17a11 39c5fa10 7c248862 417e0811 ..z.9...|$.bA~.. + 03e0 7107c4c1 7a117904 c5fa107c 24906241 q...z.y....|$.bA + 03f0 7e081169 08c4c17a 117908c5 fa107c24 ~..i...z.y....|$ + 0400 9462417e 08116109 c4c17a11 790cc5fa .bA~..a...z.y... + 0410 107c2498 62417e08 11590ac4 c17a1179 .|$.bA~..Y...z.y + 0420 10c5fa10 7c249c62 417e0811 510bc4c1 ....|$.bA~..Q... + 0430 7a117914 62417e08 11490c62 417e0811 z.y.bA~..I.bA~.. + 0440 410d62c1 7e081179 0e62c17e 0811710f A.b.~..y.b.~..q. + 0450 62c17e08 11691062 c17e0811 611162c1 b.~..i.b.~..a.b. + 0460 7e081159 1262c17e 08115113 62c17e08 ~..Y.b.~..Q.b.~. + 0470 11491462 c17e0811 4115c441 7a117958 .I.b.~..A..Az.yX + 0480 c4417a11 715cc441 7a116960 c4417a11 .Az.q\.Az.i`.Az. + 0490 6164c441 7a115968 c5fa107c 24a0c441 ad.Az.Yh...|$..A + 04a0 7a11516c c4c17a11 7978c5fa 107c24a4 z.Ql..z.yx...|$. + 04b0 c4417a11 4970c4c1 7a11b994 000000c5 .Az.Ip..z....... + 04c0 fa107c24 a8c4417a 114174c4 c17a11b9 ..|$..Az.At..z.. + 04d0 98000000 c5fa107c 24acc4c1 7a11717c .......|$...z.q| + 04e0 c4c17a11 b99c0000 00c5fa10 7c24b0c4 ..z.........|$.. + 04f0 c17a11a9 80000000 c4c17a11 b9a00000 .z........z..... + 0500 00c5fa10 7c24b4c4 c17a11a1 84000000 ....|$...z...... + 0510 c4c17a11 b9a40000 00c5fa10 7c24b8c4 ..z.........|$.. + 0520 c17a1199 88000000 c4c17a11 b9a80000 .z........z..... + 0530 00c5fa10 7c24bcc4 c17a1191 8c000000 ....|$...z...... + 0540 c4c17a11 b9ac0000 00c5fa10 7c24c0c4 ..z.........|$.. + 0550 c17a1189 90000000 c4c17a11 b9b00000 .z........z..... + 0560 00c5fa10 7c24c4c4 c17a11b9 b4000000 ....|$...z...... + 0570 c5fa107c 24c8c4c1 7a11b9b8 000000c5 ...|$...z....... + 0580 fa107c24 ccc4c17a 11b9bc00 0000c5fa ..|$...z........ + 0590 107c24d0 c4c17a11 b9c00000 00c5fa10 .|$...z......... + 05a0 7c24d4c4 c17a11b9 c4000000 c5fa107c |$...z.........| + 05b0 24d8c4c1 7a11b9c8 000000c5 fa107c24 $...z.........|$ + 05c0 dcc4c17a 11b9cc00 0000c5fa 107c24e0 ...z.........|$. + 05d0 c4c17a11 b9d00000 00c5fa10 7c24e4c4 ..z.........|$.. + 05e0 c17a11b9 d4000000 c5fa107c 24e8c4c1 .z.........|$... + 05f0 7a11b9d8 000000c5 fa107c24 ecc4c17a z.........|$...z + 0600 11b9dc00 0000c5fa 107c24f0 c4c17a11 .........|$...z. + 0610 b9e00000 00c5fa10 7c24f4c4 c17a11b9 ........|$...z.. + 0620 e4000000 c5fa107c 24f8c4c1 7a11b9e8 .......|$...z... + 0630 000000c5 fa107c24 fcc4c17a 11b9ec00 ......|$...z.... + 0640 0000c5fa 103c24c4 c17a11b9 f0000000 .....<$..z...... + 0650 c5fa107c 2404c4c1 7a11b9f4 000000c5 ...|$...z....... /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 09080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltncopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 b1050000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606410e 38830703 b7040a0e 30410e28 ..A.8.......0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 bd100000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05410e30 ...E. ..B.(..A.0 + 0040 8606410e 38830747 0ee80103 e40f0a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0844 0b000000 D..D.... /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_COOPERLAKE.o (disasm) @@ -7,264 +7,738 @@ strsm_iltucopy_COOPERLAKE: push %r15 push %r14 + mov %r9,%r14 push %r13 push %r12 - mov %rdi,%r12 push %rbp - mov %rdx,%rbp push %rbx - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) sar $something,%rsi - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %r8,%rax - shl $something,%rsi - neg %rax - mov %rdx,-offset(%rsp) + lea offset(,%rcx,8),%rax + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rcx,%rbx + mov %rdx,%r15 + lea offset(,%rcx,4),%rdx + lea offset(,%rax,4),%rcx + shl $something,%rax + mov %rax,offset(%rsp) + mov %rbx,%rax + shl $something,%rax + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + add %rbx,%rdx + mov %rbx,%rcx + imul $something,%rbx,%rbx + mov %rax,%r13 + mov %rdi,%rax + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) mov %rdi,%rbx - mov %rdi,%r15 - lea (%rsi,%r8,1),%rsi - lea offset(%rdx,%rax,4),%rax - vmovss offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%rbx - mov %r8,%rdi - lea offset(,%rcx,4),%r13 - shl $something,%r15 - mov %rdx,%r14 - mov %rsi,%r8 - mov %rax,%rbp - nopw offset(%rax,%rax,1) - mov %r14,%rax - add $something,%r14 - test %r12,%r12 + mov %rdi,%rax + sar $something,%rbx + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + imul %r13,%rax + shl $something,%rcx + shl $something,%rdx + add %r15,%rax + and $something,%edi + lea offset(,%rbx,8),%r12 + mov %rax,offset(%rsp) + mov %rcx,offset(%rsp) + lea (%r8,%rsi,8),%rax + mov %rdx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + shl $something,%rbx + mov %r12,%rax + vmovss offset(%rip),%xmm0 # + mov %rbx,offset(%rsp) + mov %r13,%r12 + mov %r8,%rbx + mov %rax,%r13 + nopl (%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r15,1),%rcx + mov offset(%rsp),%rax + lea (%rax,%r15,1),%rdi + mov offset(%rsp),%rax + lea (%r15,%rax,1),%rsi + mov offset(%rsp),%rax + lea (%rax,%r15,1),%r9 + mov offset(%rsp),%rax + lea (%r15,%rax,1),%r10 + mov offset(%rsp),%rax + lea (%r15,%rax,1),%r11 + mov offset(%rsp),%rax + lea (%rax,%r15,1),%rbp jle - mov %rbp,%r10 - mov %rdi,%rsi - sub %r14,%r10 - mov $something,%r11d - neg %rsi - add %r9,%r10 - sub %rdi,%r11 - mov %r9,%rdx + mov %r14,%rax + mov %r14,-offset(%rsp) + mov %r15,%r8 + mov %rbx,%r14 + xor %edx,%edx + mov %r13,%rbx + mov %r15,%r13 + mov %rax,%r15 jmp - nopl (%rax) - cmp $something,%rsi + nopl offset(%rax) jle - inc %rsi + vmovss offset(%r8),%xmm7 + vmovss offset(%r8),%xmm5 + vmovss offset(%r8),%xmm6 + vmovss offset(%r8),%xmm4 + vmovss offset(%r8),%xmm3 + vmovss offset(%r8),%xmm31 + vmovss offset(%r8),%xmm30 + vmovss (%rcx),%xmm29 + vmovss offset(%rcx),%xmm28 + vmovss offset(%rcx),%xmm27 + vmovss offset(%rcx),%xmm26 + vmovss offset(%rcx),%xmm25 + vmovss offset(%rcx),%xmm24 + vmovss offset(%rcx),%xmm23 + vmovss offset(%rcx),%xmm22 + vmovss (%rdi),%xmm21 + vmovss offset(%rdi),%xmm20 + vmovss offset(%rdi),%xmm19 + vmovss offset(%rdi),%xmm18 + vmovss offset(%rdi),%xmm17 + vmovss offset(%rdi),%xmm16 + vmovss offset(%rdi),%xmm15 + vmovss offset(%rdi),%xmm14 + vmovss (%rsi),%xmm13 + vmovss offset(%rsi),%xmm12 + vmovss offset(%rsi),%xmm11 + vmovss offset(%rsi),%xmm10 + vmovss %xmm7,-offset(%rsp) + vmovss %xmm5,-offset(%rsp) + vmovss %xmm6,-offset(%rsp) + vmovss %xmm4,-offset(%rsp) + vmovss %xmm3,-offset(%rsp) + vmovss offset(%rsi),%xmm9 + vmovss offset(%rsi),%xmm7 + vmovss offset(%rsi),%xmm8 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r9),%xmm7 + vmovss offset(%rsi),%xmm6 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r9),%xmm7 + vmovss (%r9),%xmm5 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r9),%xmm7 + vmovss offset(%r9),%xmm4 + vmovss %xmm7,-offset(%rsp) + vmovss (%r10),%xmm7 + vmovss offset(%r9),%xmm3 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss offset(%r9),%xmm2 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss offset(%r9),%xmm1 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss (%r11),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r11),%xmm7 + vmovss %xmm7,-offset(%rsp) /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_COOPERLAKE.o (objdump) @@ -2,81 +2,252 @@ /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989fc55 4889d553 AWAVAUATI..UH..S - 0010 48897424 d848c1fe 0448894c 24e04889 H.t$.H...H.L$.H. - 0020 7424e848 85f60f8e bb010000 4c89c048 t$.H........L..H - 0030 c1e60448 f7d84889 5424f048 89fb4989 ...H..H.T$.H..I. - 0040 ff4a8d34 06488d44 8240c5fa 100d0000 .J.4.H.D.@...... - 0050 00004c89 4424f84c 29c34c89 c74c8d2c ..L.D$.L).L..L., - 0060 8d000000 0049c1e7 064989d6 4989f048 .....I...I..I..H - 0070 89c5660f 1f440000 4c89f049 83c6404d ..f..D..L..I..@M - 0080 85e40f8e 2b010000 4989ea48 89fe4d29 ....+...I..H..M) - 0090 f241bb01 00000048 f7de4d01 ca4929fb .A.....H..M..I). - 00a0 4c89caeb 270f1f00 4883fe0f 0f8ece00 L...'...H....... - 00b0 000048ff c64883c2 404c01e8 4983c244 ..H..H..@L..I..D - 00c0 49ffc348 39de0f84 e4000000 488d0c3e I..H9.......H..> - 00d0 4839cf7e d34885f6 79d8c5fa 1000c5fa H9.~.H..y....... - 00e0 1102c5fa 104004c5 fa114204 c5fa1040 .....@....B....@ - 00f0 08c5fa11 4208c5fa 10400cc5 fa11420c ....B....@....B. - 0100 c5fa1040 10c5fa11 4210c5fa 104014c5 ...@....B....@.. - 0110 fa114214 c5fa1040 18c5fa11 4218c5fa ..B....@....B... - 0120 10401cc5 fa11421c c5fa1040 20c5fa11 .@....B....@ ... - 0130 4220c5fa 104024c5 fa114224 c5fa1040 B ...@$...B$...@ - 0140 28c5fa11 4228c5fa 10402cc5 fa11422c (...B(...@,...B, - 0150 c5fa1040 30c5fa11 4230c5fa 104034c5 ...@0...B0...@4. - 0160 fa114234 c5fa1040 38c5fa11 4238c5fa ..B4...@8...B8.. - 0170 10403cc5 fa11423c e935ffff ff0f1f00 .@<...B<.5...... - 0180 c4c17a11 0a4c89d9 4983fb10 0f8420ff ..z..L..I..... . - 0190 ffff660f 1f440000 c5fa1004 88c5fa11 ..f..D.......... - 01a0 048a48ff c14883f9 1075ede9 02ffffff ..H..H...u...... - 01b0 4d01f948 83c71048 83eb104c 39c70f85 M..H...H...L9... - 01c0 b4feffff 488b5c24 e8488b6c 24f04889 ....H.\$.H.l$.H. - 01d0 d848c1e0 064c8b44 24f84801 c54889d8 .H...L.D$.H..H.. - 01e0 48c1e004 4901c0f6 4424d808 0f84d600 H...I...D$...... - 01f0 00004c8d 5d204d85 e40f8ec2 00000048 ..L.] M........H - 0200 8b4424e0 4c89c148 f7d9be01 0000004c .D$.L..H.......L - 0210 89e34c8d 14850000 0000c5fa 100d0000 ..L............. - 0220 0000498d 3c894c29 c64c29c3 4c89c8eb ..I.<.L).L).L... - 0230 270f1f80 00000000 4883f907 0f8edf01 '.......H....... - 0240 000048ff c14883c0 204c01d5 4883c724 ..H..H.. L..H..$ - 0250 48ffc648 39d9745f 4a8d1401 4939d07e H..H9.t_J...I9.~ - 0260 d74885c9 79dcc5fa 104500c5 fa1100c5 .H..y....E...... - 0270 fa104504 c5fa1140 04c5fa10 4508c5fa ..E....@....E... - 0280 114008c5 fa10450c c5fa1140 0cc5fa10 .@....E....@.... - 0290 4510c5fa 114010c5 fa104514 c5fa1140 E....@....E....@ - 02a0 14c5fa10 4518c5fa 114018c5 fa10451c ....E....@....E. - 02b0 c5fa1140 1ceb8b4c 89e048c1 e0054901 ...@...L..H...I. - 02c0 c14983c0 084c89dd f64424d8 040f84ad .I...L...D$..... - 02d0 0000004c 8d5d104d 85e40f8e 99000000 ...L.].M........ - 02e0 488b4424 e04c89c2 48f7dabe 01000000 H.D$.L..H....... - 02f0 4c89e3c5 fa100d00 0000004c 8d148500 L..........L.... - 0300 00000049 8d3c914c 29c64c29 c34c89c9 ...I.<.L).L).L.. - 0310 eb26660f 1f440000 4883fa03 0f8e2f01 .&f..D..H...../. - 0320 000048ff c24883c1 104c01d5 4883c714 ..H..H...L..H... - 0330 48ffc648 39da7437 4a8d0402 4939c07e H..H9.t7J...I9.~ - 0340 d74885d2 79dcc5fa 104500c5 fa1101c5 .H..y....E...... - 0350 fa104504 c5fa1141 04c5fa10 4508c5fa ..E....A....E... - 0360 114108c5 fa10450c c5fa1141 0cebb34c .A....E....A...L - 0370 89e048c1 e0044901 c14983c0 044c89dd ..H...I..I...L.. - 0380 f64424d8 020f8482 0000004c 8d5d084d .D$........L.].M - 0390 85e47e72 488b4424 e04c89e7 4c8d1485 ..~rH.D$.L..L... - 03a0 00000000 4c89c048 f7d8c5fa 100d0000 ....L..H........ - 03b0 0000498d 0c814c29 c74c89ca eb2d6690 ..I...L).L...-f. - 03c0 4885c079 13c5fa10 4500c5fa 1102c5fa H..y....E....... - 03d0 104504c5 fa114204 48ffc048 83c2084c .E....B.H..H...L - 03e0 01d54883 c10c4839 c7741749 8d340049 ..H...H9.t.I.4.I - 03f0 39f07fcc 4883f801 7fdec5fa 110975ce 9...H.........u. - 0400 ebd64f8d 0ce14983 c0024c89 ddf64424 ..O...I...L...D$ - 0410 d801756d 5b5d415c 415d415e 31c0415f ..um[]A\A]A^1.A_ - 0420 c3c5fa11 0f4889f2 4883fe08 0f8410fe .....H..H....... - 0430 ffff660f 1f440000 c5fa1044 9500c5fa ..f..D.....D.... - 0440 11049048 ffc24883 fa0875ec e9f1fdff ...H..H...u..... - 0450 ffc5fa11 0f4889f0 4883fe04 0f84c0fe .....H..H....... - 0460 ffff660f 1f440000 c5fa1044 8500c5fa ..f..D.....D.... - 0470 11048148 ffc04883 f80475ec e9a1feff ...H..H...u..... - 0480 ff4d85e4 7e8e488b 4c24e04c 89c248f7 .M..~.H.L$.L..H. - 0490 dac5fa10 0d000000 0048c1e1 02498d34 .........H...I.4 - 04a0 9131c0eb 1d0f1f00 7506c4a1 7a110cc6 .1......u...z... - 04b0 48ffc048 01cd48ff c24939c4 0f8452ff H..H..H..I9...R. - 04c0 ffff4939 c07ee148 85d279e4 c5fa1045 ..I9.~.H..y....E - 04d0 00c4c17a 110481eb d7 ...z..... + 0000 41574156 4d89ce41 55415455 534881ec AWAVM..AUATUSH.. + 0010 b0000000 4889b424 90000000 48c1fe03 ....H..$....H... + 0020 4889bc24 98000000 48899424 88000000 H..$....H..$.... + 0030 48898c24 a0000000 4c898424 80000000 H..$....L..$.... + 0040 4889b424 a8000000 4885f60f 8eb60900 H..$....H....... + 0050 00488d04 cd000000 00488944 2420488d .H.......H.D$ H. + 0060 04494889 cb4989d7 488d148d 00000000 .IH..I..H....... + 0070 488d0c85 00000000 48c1e003 48894424 H.......H...H.D$ + 0080 704889d8 48c1e005 48895424 1048894c pH..H...H.T$.H.L + 0090 24604801 da4889d9 486bdb1c 4989c548 $`H..H..Hk..I..H + 00a0 89f883e0 0448895c 24304889 44244848 .....H.\$0H.D$HH + 00b0 89fb4889 f848c1fb 0383e002 48894424 ..H..H......H.D$ + 00c0 504889d8 490fafc5 48c1e104 48c1e202 PH..I...H...H... + 00d0 4c01f883 e7014c8d 24dd0000 00004889 L.....L.$.....H. + 00e0 44241848 894c2428 498d04f0 48895424 D$.H.L$(I...H.T$ + 00f0 6848897c 24584889 5c244048 89442438 hH.|$XH.\$@H.D$8 + 0100 48c1e308 4c89e0c5 fa100500 00000048 H...L..........H + 0110 895c2478 4d89ec4c 89c34989 c50f1f00 .\$xM..L..I..... + 0120 488b4424 1048837c 2440004a 8d0c3848 H.D$.H.|$@.J..8H + 0130 8b442420 4a8d3c38 488b4424 60498d34 .D$ J.<8H.D$`I.4 + 0140 07488b44 24284e8d 0c38488b 4424684d .H.D$(N..8H.D$hM + 0150 8d140748 8b442470 4d8d1c07 488b4424 ...H.D$pM...H.D$ + 0160 304a8d2c 380f8e85 0d00004c 89f04c89 0J.,8......L..L. + 0170 7424884d 89f84989 de31d24c 89eb4d89 t$.M..I..1.L..M. + 0180 fd4989c7 e9f80400 000f1f80 00000000 .I.............. + 0190 0f8ec004 0000c4c1 7a107804 c4c17a10 ........z.x...z. + 01a0 6808c4c1 7a10700c c4c17a10 6010c4c1 h...z.p...z.`... + 01b0 7a105814 62417e08 10780662 417e0810 z.X.bA~..x.bA~.. + 01c0 70076261 7e081029 62617e08 10610162 p.ba~..)ba~..a.b + 01d0 617e0810 59026261 7e081051 0362617e a~..Y.ba~..Q.ba~ + 01e0 08104904 62617e08 10410562 e17e0810 ..I.ba~..A.b.~.. + 01f0 790662e1 7e081071 0762e17e 08102f62 y.b.~..q.b.~../b + 0200 e17e0810 670162e1 7e08105f 0262e17e .~..g.b.~.._.b.~ + 0210 08105703 62e17e08 104f0462 e17e0810 ..W.b.~..O.b.~.. + 0220 4705c57a 107f18c5 7a10771c c57a102e G..z....z.w..z.. + 0230 c57a1066 04c57a10 5e08c57a 10560cc5 .z.f..z.^..z.V.. + 0240 fa117c24 88c5fa11 6c2490c5 fa117424 ..|$....l$....t$ + 0250 94c5fa11 642498c5 fa115c24 9cc57a10 ....d$....\$..z. + 0260 4e10c5fa 107e18c5 7a104614 c5fa117c N....~..z.F....| + 0270 24a0c4c1 7a107914 c5fa1076 1cc5fa11 $...z.y....v.... + 0280 7c24a4c4 c17a1079 18c4c17a 1029c5fa |$...z.y...z.).. + 0290 117c24a8 c4c17a10 791cc4c1 7a106104 .|$...z.y...z.a. + 02a0 c5fa117c 24acc4c1 7a103ac4 c17a1059 ...|$...z.:..z.Y + 02b0 08c5fa11 7c24b0c4 c17a107a 04c4c17a ....|$...z.z...z + 02c0 10510cc5 fa117c24 b4c4c17a 107a08c4 .Q....|$...z.z.. + 02d0 c17a1049 10c5fa11 7c24b8c4 c17a107a .z.I....|$...z.z + 02e0 0cc5fa11 7c24bcc4 c17a107a 10c5fa11 ....|$...z.z.... + 02f0 7c24c0c4 c17a107a 14c5fa11 7c24c4c4 |$...z.z....|$.. + 0300 c17a107a 18c5fa11 7c24c8c4 c17a107a .z.z....|$...z.z + 0310 1cc5fa11 7c24ccc4 c17a103b c5fa117c ....|$...z.;...| + 0320 24d0c4c1 7a107b04 c5fa117c 24d4c4c1 $...z.{....|$... + 0330 7a107b08 c5fa117c 24d8c4c1 7a107b0c z.{....|$...z.{. + 0340 c5fa117c 24dcc4c1 7a107b10 c5fa117c ...|$...z.{....| + 0350 24e0c4c1 7a107b14 c5fa117c 24e4c4c1 $...z.{....|$... + 0360 7a107b18 c5fa117c 24e8c4c1 7a107b1c z.{....|$...z.{. + 0370 c5fa117c 24ecc5fa 107d00c5 fa117c24 ...|$....}....|$ + 0380 f0c5fa10 7d04c5fa 117c24f4 c5fa107d ....}....|$....} + 0390 08c5fa11 7c24f8c5 fa107d0c c5fa117c ....|$....}....| + 03a0 24fcc5fa 107d10c5 fa113c24 c5fa107d $....}....<$...} + 03b0 14c5fa11 7c2404c5 fa107d18 c5fa117c ....|$....}....| + 03c0 2408c5fa 107d1cc5 fa117c24 0cc4c17a $....}....|$...z + 03d0 10386261 7e081178 06c5fa11 38c5fa10 .8ba~..x....8... + 03e0 7c248862 617e0811 7007c5fa 117804c5 |$.ba~..p....x.. + 03f0 fa107c24 9062617e 08116808 c5fa1178 ..|$.ba~..h....x + 0400 08c5fa10 7c249462 617e0811 6009c5fa ....|$.ba~..`... + 0410 11780cc5 fa107c24 9862617e 0811580a .x....|$.ba~..X. + 0420 c5fa1178 10c5fa10 7c249c62 617e0811 ...x....|$.ba~.. + 0430 500bc5fa 11781462 617e0811 480c6261 P....x.ba~..H.ba + 0440 7e081140 0d62e17e 0811780e 62e17e08 ~..@.b.~..x.b.~. + 0450 11700f62 e17e0811 681062e1 7e081160 .p.b.~..h.b.~..` + 0460 1162e17e 08115812 62e17e08 11501362 .b.~..X.b.~..P.b + 0470 e17e0811 481462e1 7e081140 15c57a11 .~..H.b.~..@..z. + 0480 7858c57a 11705cc5 7a116860 c57a1160 xX.z.p\.z.h`.z.` + 0490 64c57a11 5868c5fa 107c24a0 c57a1150 d.z.Xh...|$..z.P + 04a0 6cc5fa11 7878c5fa 107c24a4 c57a1148 l...xx...|$..z.H + 04b0 70c5fa11 b8940000 00c5fa10 7c24a8c5 p...........|$.. + 04c0 7a114074 c5fa11b8 98000000 c5fa107c z.@t...........| + 04d0 24acc5fa 11707cc5 fa11b89c 000000c5 $....p|......... + 04e0 fa107c24 b0c5fa11 a8800000 00c5fa11 ..|$............ + 04f0 b8a00000 00c5fa10 7c24b4c5 fa11a084 ........|$...... + 0500 000000c5 fa11b8a4 000000c5 fa107c24 ..............|$ + 0510 b8c5fa11 98880000 00c5fa11 b8a80000 ................ + 0520 00c5fa10 7c24bcc5 fa11908c 000000c5 ....|$.......... + 0530 fa11b8ac 000000c5 fa107c24 c0c5fa11 ..........|$.... + 0540 88900000 00c5fa11 b8b00000 00c5fa10 ................ + 0550 7c24c4c5 fa11b8b4 000000c5 fa107c24 |$............|$ + 0560 c8c5fa11 b8b80000 00c5fa10 7c24ccc5 ............|$.. + 0570 fa11b8bc 000000c5 fa107c24 d0c5fa11 ..........|$.... + 0580 b8c00000 00c5fa10 7c24d4c5 fa11b8c4 ........|$...... + 0590 000000c5 fa107c24 d8c5fa11 b8c80000 ......|$........ + 05a0 00c5fa10 7c24dcc5 fa11b8cc 000000c5 ....|$.......... + 05b0 fa107c24 e0c5fa11 b8d00000 00c5fa10 ..|$............ + 05c0 7c24e4c5 fa11b8d4 000000c5 fa107c24 |$............|$ + 05d0 e8c5fa11 b8d80000 00c5fa10 7c24ecc5 ............|$.. + 05e0 fa11b8dc 000000c5 fa107c24 f0c5fa11 ..........|$.... + 05f0 b8e00000 00c5fa10 7c24f4c5 fa11b8e4 ........|$...... + 0600 000000c5 fa107c24 f8c5fa11 b8e80000 ......|$........ + 0610 00c5fa10 7c24fcc5 fa11b8ec 000000c5 ....|$.......... + 0620 fa103c24 c5fa11b8 f0000000 c5fa107c ..<$...........| + 0630 2404c5fa 11b8f400 0000c5fa 107c2408 $............|$. + 0640 c5fa11b8 f8000000 c5fa107c 240cc5fa ...........|$... + 0650 11b8fc00 00004883 c2084d01 e04c01e1 ......H...M..L.. + 0660 4c01e74c 01e64d01 e14d01e2 4d01e34c L..L..M..M..M..L + 0670 01e54805 00010000 4839d30f 84af0100 ..H.....H9...... + 0680 004939d6 0f8506fb ffff6241 7e081040 .I9.......bA~..@ + 0690 0562c17e 08107806 62c17e08 10700762 .b.~..x.b.~..p.b + 06a0 e17e0810 690262e1 7e081061 0362e17e .~..i.b.~..a.b.~ + 06b0 08105904 62e17e08 10510562 e17e0810 ..Y.b.~..Q.b.~.. + 06c0 490662e1 7e081041 07c57a10 7f0cc57a I.b.~..A..z....z + 06d0 107710c5 7a106f14 c57a1067 18c57a10 .w..z.o..z.g..z. + 06e0 5f1cc57a 105610c5 7a104e14 c57a1046 _..z.V..z.N..z.F + 06f0 18c5fa10 7e1cc4c1 7a107114 c4c17a10 ....~...z.q...z. + 0700 6918c4c1 7a10611c c4c17a10 5a18c4c1 i...z.a...z.Z... + 0710 7a10521c c4c17a10 4b1c6241 7e081060 z.R...z.K.bA~..` + 0720 0162417e 08105802 62417e08 10500362 .bA~..X.bA~..P.b + 0730 417e0810 4804c5fa 11006261 7e081160 A~..H.....ba~..` /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_COOPERLAKE.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_COOPERLAKE.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 09080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_COOPERLAKE.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_COOPERLAKE.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 d9040000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606440e 38830703 05040a0e 30410e28 ..D.8.......0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 830f0000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05410e30 ...E. ..B.(..A.0 + 0040 8606410e 38830747 0ee80103 c80e0a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0848 0b000000 D..H.... /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_SKYLAKEX.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_SKYLAKEX.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_SKYLAKEX.o (disasm) @@ -7,264 +7,738 @@ strsm_iltucopy_SKYLAKEX: push %r15 push %r14 + mov %r9,%r14 push %r13 push %r12 - mov %rdi,%r12 push %rbp - mov %rdx,%rbp push %rbx - mov %rsi,-offset(%rsp) + sub $something,%rsp + mov %rsi,offset(%rsp) sar $something,%rsi - mov %rcx,-offset(%rsp) - mov %rsi,-offset(%rsp) + mov %rdi,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r8,offset(%rsp) + mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %r8,%rax - shl $something,%rsi - neg %rax - mov %rdx,-offset(%rsp) + lea offset(,%rcx,8),%rax + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rcx,%rbx + mov %rdx,%r15 + lea offset(,%rcx,4),%rdx + lea offset(,%rax,4),%rcx + shl $something,%rax + mov %rax,offset(%rsp) + mov %rbx,%rax + shl $something,%rax + mov %rdx,offset(%rsp) + mov %rcx,offset(%rsp) + add %rbx,%rdx + mov %rbx,%rcx + imul $something,%rbx,%rbx + mov %rax,%r13 + mov %rdi,%rax + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) mov %rdi,%rbx - mov %rdi,%r15 - lea (%rsi,%r8,1),%rsi - lea offset(%rdx,%rax,4),%rax - vmovss offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%rbx - mov %r8,%rdi - lea offset(,%rcx,4),%r13 - shl $something,%r15 - mov %rdx,%r14 - mov %rsi,%r8 - mov %rax,%rbp - nopw offset(%rax,%rax,1) - mov %r14,%rax - add $something,%r14 - test %r12,%r12 + mov %rdi,%rax + sar $something,%rbx + and $something,%eax + mov %rax,offset(%rsp) + mov %rbx,%rax + imul %r13,%rax + shl $something,%rcx + shl $something,%rdx + add %r15,%rax + and $something,%edi + lea offset(,%rbx,8),%r12 + mov %rax,offset(%rsp) + mov %rcx,offset(%rsp) + lea (%r8,%rsi,8),%rax + mov %rdx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) + shl $something,%rbx + mov %r12,%rax + vmovss offset(%rip),%xmm0 # + mov %rbx,offset(%rsp) + mov %r13,%r12 + mov %r8,%rbx + mov %rax,%r13 + nopl (%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r15,1),%rcx + mov offset(%rsp),%rax + lea (%rax,%r15,1),%rdi + mov offset(%rsp),%rax + lea (%r15,%rax,1),%rsi + mov offset(%rsp),%rax + lea (%rax,%r15,1),%r9 + mov offset(%rsp),%rax + lea (%r15,%rax,1),%r10 + mov offset(%rsp),%rax + lea (%r15,%rax,1),%r11 + mov offset(%rsp),%rax + lea (%rax,%r15,1),%rbp jle - mov %rbp,%r10 - mov %rdi,%rsi - sub %r14,%r10 - mov $something,%r11d - neg %rsi - add %r9,%r10 - sub %rdi,%r11 - mov %r9,%rdx + mov %r14,%rax + mov %r14,-offset(%rsp) + mov %r15,%r8 + mov %rbx,%r14 + xor %edx,%edx + mov %r13,%rbx + mov %r15,%r13 + mov %rax,%r15 jmp - nopl (%rax) - cmp $something,%rsi + nopl offset(%rax) jle - inc %rsi + vmovss offset(%r8),%xmm7 + vmovss offset(%r8),%xmm5 + vmovss offset(%r8),%xmm6 + vmovss offset(%r8),%xmm4 + vmovss offset(%r8),%xmm3 + vmovss offset(%r8),%xmm31 + vmovss offset(%r8),%xmm30 + vmovss (%rcx),%xmm29 + vmovss offset(%rcx),%xmm28 + vmovss offset(%rcx),%xmm27 + vmovss offset(%rcx),%xmm26 + vmovss offset(%rcx),%xmm25 + vmovss offset(%rcx),%xmm24 + vmovss offset(%rcx),%xmm23 + vmovss offset(%rcx),%xmm22 + vmovss (%rdi),%xmm21 + vmovss offset(%rdi),%xmm20 + vmovss offset(%rdi),%xmm19 + vmovss offset(%rdi),%xmm18 + vmovss offset(%rdi),%xmm17 + vmovss offset(%rdi),%xmm16 + vmovss offset(%rdi),%xmm15 + vmovss offset(%rdi),%xmm14 + vmovss (%rsi),%xmm13 + vmovss offset(%rsi),%xmm12 + vmovss offset(%rsi),%xmm11 + vmovss offset(%rsi),%xmm10 + vmovss %xmm7,-offset(%rsp) + vmovss %xmm5,-offset(%rsp) + vmovss %xmm6,-offset(%rsp) + vmovss %xmm4,-offset(%rsp) + vmovss %xmm3,-offset(%rsp) + vmovss offset(%rsi),%xmm9 + vmovss offset(%rsi),%xmm7 + vmovss offset(%rsi),%xmm8 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r9),%xmm7 + vmovss offset(%rsi),%xmm6 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r9),%xmm7 + vmovss (%r9),%xmm5 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r9),%xmm7 + vmovss offset(%r9),%xmm4 + vmovss %xmm7,-offset(%rsp) + vmovss (%r10),%xmm7 + vmovss offset(%r9),%xmm3 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss offset(%r9),%xmm2 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss offset(%r9),%xmm1 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r10),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss (%r11),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r11),%xmm7 + vmovss %xmm7,-offset(%rsp) /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_SKYLAKEX.o (objdump) @@ -2,81 +2,252 @@ /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989fc55 4889d553 AWAVAUATI..UH..S - 0010 48897424 d848c1fe 0448894c 24e04889 H.t$.H...H.L$.H. - 0020 7424e848 85f60f8e bb010000 4c89c048 t$.H........L..H - 0030 c1e60448 f7d84889 5424f048 89fb4989 ...H..H.T$.H..I. - 0040 ff4a8d34 06488d44 8240c5fa 100d0000 .J.4.H.D.@...... - 0050 00004c89 4424f84c 29c34c89 c74c8d2c ..L.D$.L).L..L., - 0060 8d000000 0049c1e7 064989d6 4989f048 .....I...I..I..H - 0070 89c5660f 1f440000 4c89f049 83c6404d ..f..D..L..I..@M - 0080 85e40f8e 2b010000 4989ea48 89fe4d29 ....+...I..H..M) - 0090 f241bb01 00000048 f7de4d01 ca4929fb .A.....H..M..I). - 00a0 4c89caeb 270f1f00 4883fe0f 0f8ece00 L...'...H....... - 00b0 000048ff c64883c2 404c01e8 4983c244 ..H..H..@L..I..D - 00c0 49ffc348 39de0f84 e4000000 488d0c3e I..H9.......H..> - 00d0 4839cf7e d34885f6 79d8c5fa 1000c5fa H9.~.H..y....... - 00e0 1102c5fa 104004c5 fa114204 c5fa1040 .....@....B....@ - 00f0 08c5fa11 4208c5fa 10400cc5 fa11420c ....B....@....B. - 0100 c5fa1040 10c5fa11 4210c5fa 104014c5 ...@....B....@.. - 0110 fa114214 c5fa1040 18c5fa11 4218c5fa ..B....@....B... - 0120 10401cc5 fa11421c c5fa1040 20c5fa11 .@....B....@ ... - 0130 4220c5fa 104024c5 fa114224 c5fa1040 B ...@$...B$...@ - 0140 28c5fa11 4228c5fa 10402cc5 fa11422c (...B(...@,...B, - 0150 c5fa1040 30c5fa11 4230c5fa 104034c5 ...@0...B0...@4. - 0160 fa114234 c5fa1040 38c5fa11 4238c5fa ..B4...@8...B8.. - 0170 10403cc5 fa11423c e935ffff ff0f1f00 .@<...B<.5...... - 0180 c4c17a11 0a4c89d9 4983fb10 0f8420ff ..z..L..I..... . - 0190 ffff660f 1f440000 c5fa1004 88c5fa11 ..f..D.......... - 01a0 048a48ff c14883f9 1075ede9 02ffffff ..H..H...u...... - 01b0 4d01f948 83c71048 83eb104c 39c70f85 M..H...H...L9... - 01c0 b4feffff 488b5c24 e8488b6c 24f04889 ....H.\$.H.l$.H. - 01d0 d848c1e0 064c8b44 24f84801 c54889d8 .H...L.D$.H..H.. - 01e0 48c1e004 4901c0f6 4424d808 0f84d600 H...I...D$...... - 01f0 00004c8d 5d204d85 e40f8ec2 00000048 ..L.] M........H - 0200 8b4424e0 4c89c148 f7d9be01 0000004c .D$.L..H.......L - 0210 89e34c8d 14850000 0000c5fa 100d0000 ..L............. - 0220 0000498d 3c894c29 c64c29c3 4c89c8eb ..I.<.L).L).L... - 0230 270f1f80 00000000 4883f907 0f8edf01 '.......H....... - 0240 000048ff c14883c0 204c01d5 4883c724 ..H..H.. L..H..$ - 0250 48ffc648 39d9745f 4a8d1401 4939d07e H..H9.t_J...I9.~ - 0260 d74885c9 79dcc5fa 104500c5 fa1100c5 .H..y....E...... - 0270 fa104504 c5fa1140 04c5fa10 4508c5fa ..E....@....E... - 0280 114008c5 fa10450c c5fa1140 0cc5fa10 .@....E....@.... - 0290 4510c5fa 114010c5 fa104514 c5fa1140 E....@....E....@ - 02a0 14c5fa10 4518c5fa 114018c5 fa10451c ....E....@....E. - 02b0 c5fa1140 1ceb8b4c 89e048c1 e0054901 ...@...L..H...I. - 02c0 c14983c0 084c89dd f64424d8 040f84ad .I...L...D$..... - 02d0 0000004c 8d5d104d 85e40f8e 99000000 ...L.].M........ - 02e0 488b4424 e04c89c2 48f7dabe 01000000 H.D$.L..H....... - 02f0 4c89e3c5 fa100d00 0000004c 8d148500 L..........L.... - 0300 00000049 8d3c914c 29c64c29 c34c89c9 ...I.<.L).L).L.. - 0310 eb26660f 1f440000 4883fa03 0f8e2f01 .&f..D..H...../. - 0320 000048ff c24883c1 104c01d5 4883c714 ..H..H...L..H... - 0330 48ffc648 39da7437 4a8d0402 4939c07e H..H9.t7J...I9.~ - 0340 d74885d2 79dcc5fa 104500c5 fa1101c5 .H..y....E...... - 0350 fa104504 c5fa1141 04c5fa10 4508c5fa ..E....A....E... - 0360 114108c5 fa10450c c5fa1141 0cebb34c .A....E....A...L - 0370 89e048c1 e0044901 c14983c0 044c89dd ..H...I..I...L.. - 0380 f64424d8 020f8482 0000004c 8d5d084d .D$........L.].M - 0390 85e47e72 488b4424 e04c89e7 4c8d1485 ..~rH.D$.L..L... - 03a0 00000000 4c89c048 f7d8c5fa 100d0000 ....L..H........ - 03b0 0000498d 0c814c29 c74c89ca eb2d6690 ..I...L).L...-f. - 03c0 4885c079 13c5fa10 4500c5fa 1102c5fa H..y....E....... - 03d0 104504c5 fa114204 48ffc048 83c2084c .E....B.H..H...L - 03e0 01d54883 c10c4839 c7741749 8d340049 ..H...H9.t.I.4.I - 03f0 39f07fcc 4883f801 7fdec5fa 110975ce 9...H.........u. - 0400 ebd64f8d 0ce14983 c0024c89 ddf64424 ..O...I...L...D$ - 0410 d801756d 5b5d415c 415d415e 31c0415f ..um[]A\A]A^1.A_ - 0420 c3c5fa11 0f4889f2 4883fe08 0f8410fe .....H..H....... - 0430 ffff660f 1f440000 c5fa1044 9500c5fa ..f..D.....D.... - 0440 11049048 ffc24883 fa0875ec e9f1fdff ...H..H...u..... - 0450 ffc5fa11 0f4889f0 4883fe04 0f84c0fe .....H..H....... - 0460 ffff660f 1f440000 c5fa1044 8500c5fa ..f..D.....D.... - 0470 11048148 ffc04883 f80475ec e9a1feff ...H..H...u..... - 0480 ff4d85e4 7e8e488b 4c24e04c 89c248f7 .M..~.H.L$.L..H. - 0490 dac5fa10 0d000000 0048c1e1 02498d34 .........H...I.4 - 04a0 9131c0eb 1d0f1f00 7506c4a1 7a110cc6 .1......u...z... - 04b0 48ffc048 01cd48ff c24939c4 0f8452ff H..H..H..I9...R. - 04c0 ffff4939 c07ee148 85d279e4 c5fa1045 ..I9.~.H..y....E - 04d0 00c4c17a 110481eb d7 ...z..... + 0000 41574156 4d89ce41 55415455 534881ec AWAVM..AUATUSH.. + 0010 b0000000 4889b424 90000000 48c1fe03 ....H..$....H... + 0020 4889bc24 98000000 48899424 88000000 H..$....H..$.... + 0030 48898c24 a0000000 4c898424 80000000 H..$....L..$.... + 0040 4889b424 a8000000 4885f60f 8eb60900 H..$....H....... + 0050 00488d04 cd000000 00488944 2420488d .H.......H.D$ H. + 0060 04494889 cb4989d7 488d148d 00000000 .IH..I..H....... + 0070 488d0c85 00000000 48c1e003 48894424 H.......H...H.D$ + 0080 704889d8 48c1e005 48895424 1048894c pH..H...H.T$.H.L + 0090 24604801 da4889d9 486bdb1c 4989c548 $`H..H..Hk..I..H + 00a0 89f883e0 0448895c 24304889 44244848 .....H.\$0H.D$HH + 00b0 89fb4889 f848c1fb 0383e002 48894424 ..H..H......H.D$ + 00c0 504889d8 490fafc5 48c1e104 48c1e202 PH..I...H...H... + 00d0 4c01f883 e7014c8d 24dd0000 00004889 L.....L.$.....H. + 00e0 44241848 894c2428 498d04f0 48895424 D$.H.L$(I...H.T$ + 00f0 6848897c 24584889 5c244048 89442438 hH.|$XH.\$@H.D$8 + 0100 48c1e308 4c89e0c5 fa100500 00000048 H...L..........H + 0110 895c2478 4d89ec4c 89c34989 c50f1f00 .\$xM..L..I..... + 0120 488b4424 1048837c 2440004a 8d0c3848 H.D$.H.|$@.J..8H + 0130 8b442420 4a8d3c38 488b4424 60498d34 .D$ J.<8H.D$`I.4 + 0140 07488b44 24284e8d 0c38488b 4424684d .H.D$(N..8H.D$hM + 0150 8d140748 8b442470 4d8d1c07 488b4424 ...H.D$pM...H.D$ + 0160 304a8d2c 380f8e85 0d00004c 89f04c89 0J.,8......L..L. + 0170 7424884d 89f84989 de31d24c 89eb4d89 t$.M..I..1.L..M. + 0180 fd4989c7 e9f80400 000f1f80 00000000 .I.............. + 0190 0f8ec004 0000c4c1 7a107804 c4c17a10 ........z.x...z. + 01a0 6808c4c1 7a10700c c4c17a10 6010c4c1 h...z.p...z.`... + 01b0 7a105814 62417e08 10780662 417e0810 z.X.bA~..x.bA~.. + 01c0 70076261 7e081029 62617e08 10610162 p.ba~..)ba~..a.b + 01d0 617e0810 59026261 7e081051 0362617e a~..Y.ba~..Q.ba~ + 01e0 08104904 62617e08 10410562 e17e0810 ..I.ba~..A.b.~.. + 01f0 790662e1 7e081071 0762e17e 08102f62 y.b.~..q.b.~../b + 0200 e17e0810 670162e1 7e08105f 0262e17e .~..g.b.~.._.b.~ + 0210 08105703 62e17e08 104f0462 e17e0810 ..W.b.~..O.b.~.. + 0220 4705c57a 107f18c5 7a10771c c57a102e G..z....z.w..z.. + 0230 c57a1066 04c57a10 5e08c57a 10560cc5 .z.f..z.^..z.V.. + 0240 fa117c24 88c5fa11 6c2490c5 fa117424 ..|$....l$....t$ + 0250 94c5fa11 642498c5 fa115c24 9cc57a10 ....d$....\$..z. + 0260 4e10c5fa 107e18c5 7a104614 c5fa117c N....~..z.F....| + 0270 24a0c4c1 7a107914 c5fa1076 1cc5fa11 $...z.y....v.... + 0280 7c24a4c4 c17a1079 18c4c17a 1029c5fa |$...z.y...z.).. + 0290 117c24a8 c4c17a10 791cc4c1 7a106104 .|$...z.y...z.a. + 02a0 c5fa117c 24acc4c1 7a103ac4 c17a1059 ...|$...z.:..z.Y + 02b0 08c5fa11 7c24b0c4 c17a107a 04c4c17a ....|$...z.z...z + 02c0 10510cc5 fa117c24 b4c4c17a 107a08c4 .Q....|$...z.z.. + 02d0 c17a1049 10c5fa11 7c24b8c4 c17a107a .z.I....|$...z.z + 02e0 0cc5fa11 7c24bcc4 c17a107a 10c5fa11 ....|$...z.z.... + 02f0 7c24c0c4 c17a107a 14c5fa11 7c24c4c4 |$...z.z....|$.. + 0300 c17a107a 18c5fa11 7c24c8c4 c17a107a .z.z....|$...z.z + 0310 1cc5fa11 7c24ccc4 c17a103b c5fa117c ....|$...z.;...| + 0320 24d0c4c1 7a107b04 c5fa117c 24d4c4c1 $...z.{....|$... + 0330 7a107b08 c5fa117c 24d8c4c1 7a107b0c z.{....|$...z.{. + 0340 c5fa117c 24dcc4c1 7a107b10 c5fa117c ...|$...z.{....| + 0350 24e0c4c1 7a107b14 c5fa117c 24e4c4c1 $...z.{....|$... + 0360 7a107b18 c5fa117c 24e8c4c1 7a107b1c z.{....|$...z.{. + 0370 c5fa117c 24ecc5fa 107d00c5 fa117c24 ...|$....}....|$ + 0380 f0c5fa10 7d04c5fa 117c24f4 c5fa107d ....}....|$....} + 0390 08c5fa11 7c24f8c5 fa107d0c c5fa117c ....|$....}....| + 03a0 24fcc5fa 107d10c5 fa113c24 c5fa107d $....}....<$...} + 03b0 14c5fa11 7c2404c5 fa107d18 c5fa117c ....|$....}....| + 03c0 2408c5fa 107d1cc5 fa117c24 0cc4c17a $....}....|$...z + 03d0 10386261 7e081178 06c5fa11 38c5fa10 .8ba~..x....8... + 03e0 7c248862 617e0811 7007c5fa 117804c5 |$.ba~..p....x.. + 03f0 fa107c24 9062617e 08116808 c5fa1178 ..|$.ba~..h....x + 0400 08c5fa10 7c249462 617e0811 6009c5fa ....|$.ba~..`... + 0410 11780cc5 fa107c24 9862617e 0811580a .x....|$.ba~..X. + 0420 c5fa1178 10c5fa10 7c249c62 617e0811 ...x....|$.ba~.. + 0430 500bc5fa 11781462 617e0811 480c6261 P....x.ba~..H.ba + 0440 7e081140 0d62e17e 0811780e 62e17e08 ~..@.b.~..x.b.~. + 0450 11700f62 e17e0811 681062e1 7e081160 .p.b.~..h.b.~..` + 0460 1162e17e 08115812 62e17e08 11501362 .b.~..X.b.~..P.b + 0470 e17e0811 481462e1 7e081140 15c57a11 .~..H.b.~..@..z. + 0480 7858c57a 11705cc5 7a116860 c57a1160 xX.z.p\.z.h`.z.` + 0490 64c57a11 5868c5fa 107c24a0 c57a1150 d.z.Xh...|$..z.P + 04a0 6cc5fa11 7878c5fa 107c24a4 c57a1148 l...xx...|$..z.H + 04b0 70c5fa11 b8940000 00c5fa10 7c24a8c5 p...........|$.. + 04c0 7a114074 c5fa11b8 98000000 c5fa107c z.@t...........| + 04d0 24acc5fa 11707cc5 fa11b89c 000000c5 $....p|......... + 04e0 fa107c24 b0c5fa11 a8800000 00c5fa11 ..|$............ + 04f0 b8a00000 00c5fa10 7c24b4c5 fa11a084 ........|$...... + 0500 000000c5 fa11b8a4 000000c5 fa107c24 ..............|$ + 0510 b8c5fa11 98880000 00c5fa11 b8a80000 ................ + 0520 00c5fa10 7c24bcc5 fa11908c 000000c5 ....|$.......... + 0530 fa11b8ac 000000c5 fa107c24 c0c5fa11 ..........|$.... + 0540 88900000 00c5fa11 b8b00000 00c5fa10 ................ + 0550 7c24c4c5 fa11b8b4 000000c5 fa107c24 |$............|$ + 0560 c8c5fa11 b8b80000 00c5fa10 7c24ccc5 ............|$.. + 0570 fa11b8bc 000000c5 fa107c24 d0c5fa11 ..........|$.... + 0580 b8c00000 00c5fa10 7c24d4c5 fa11b8c4 ........|$...... + 0590 000000c5 fa107c24 d8c5fa11 b8c80000 ......|$........ + 05a0 00c5fa10 7c24dcc5 fa11b8cc 000000c5 ....|$.......... + 05b0 fa107c24 e0c5fa11 b8d00000 00c5fa10 ..|$............ + 05c0 7c24e4c5 fa11b8d4 000000c5 fa107c24 |$............|$ + 05d0 e8c5fa11 b8d80000 00c5fa10 7c24ecc5 ............|$.. + 05e0 fa11b8dc 000000c5 fa107c24 f0c5fa11 ..........|$.... + 05f0 b8e00000 00c5fa10 7c24f4c5 fa11b8e4 ........|$...... + 0600 000000c5 fa107c24 f8c5fa11 b8e80000 ......|$........ + 0610 00c5fa10 7c24fcc5 fa11b8ec 000000c5 ....|$.......... + 0620 fa103c24 c5fa11b8 f0000000 c5fa107c ..<$...........| + 0630 2404c5fa 11b8f400 0000c5fa 107c2408 $............|$. + 0640 c5fa11b8 f8000000 c5fa107c 240cc5fa ...........|$... + 0650 11b8fc00 00004883 c2084d01 e04c01e1 ......H...M..L.. + 0660 4c01e74c 01e64d01 e14d01e2 4d01e34c L..L..M..M..M..L + 0670 01e54805 00010000 4839d30f 84af0100 ..H.....H9...... + 0680 004939d6 0f8506fb ffff6241 7e081040 .I9.......bA~..@ + 0690 0562c17e 08107806 62c17e08 10700762 .b.~..x.b.~..p.b + 06a0 e17e0810 690262e1 7e081061 0362e17e .~..i.b.~..a.b.~ + 06b0 08105904 62e17e08 10510562 e17e0810 ..Y.b.~..Q.b.~.. + 06c0 490662e1 7e081041 07c57a10 7f0cc57a I.b.~..A..z....z + 06d0 107710c5 7a106f14 c57a1067 18c57a10 .w..z.o..z.g..z. + 06e0 5f1cc57a 105610c5 7a104e14 c57a1046 _..z.V..z.N..z.F + 06f0 18c5fa10 7e1cc4c1 7a107114 c4c17a10 ....~...z.q...z. + 0700 6918c4c1 7a10611c c4c17a10 5a18c4c1 i...z.a...z.Z... + 0710 7a10521c c4c17a10 4b1c6241 7e081060 z.R...z.K.bA~..` + 0720 0162417e 08105802 62417e08 10500362 .bA~..X.bA~..P.b + 0730 417e0810 4804c5fa 11006261 7e081160 A~..H.....ba~..` /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_SKYLAKEX.o (objdump) @@ -3,5 +3,5 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. - 0010 020001c0 04000000 05000000 00000000 ................ - 0020 010001c0 04000000 09000000 00000000 ................ + 0010 020001c0 04000000 0d000000 00000000 ................ + 0020 010001c0 04000000 09080000 00000000 ................ /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iltucopy_SKYLAKEX.o (objdump) @@ -3,8 +3,9 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. - 0010 1b0c0708 90010000 44000000 1c000000 ........D....... - 0020 00000000 d9040000 00420e10 8f02420e .........B....B. - 0030 188e0342 0e208d04 420e288c 05440e30 ...B. ..B.(..D.0 - 0040 8606440e 38830703 05040a0e 30410e28 ..D.8.......0A.( - 0050 420e2042 0e18420e 10440e08 410b0000 B. B..B..D..A... + 0010 1b0c0708 90010000 4c000000 1c000000 ........L....... + 0020 00000000 830f0000 00420e10 8f02420e .........B....B. + 0030 188e0345 0e208d04 420e288c 05410e30 ...E. ..B.(..A.0 + 0040 8606410e 38830747 0ee80103 c80e0a0e ..A.8..G........ + 0050 38410e30 410e2842 0e20420e 18420e10 8A.0A.(B. B..B.. + 0060 440e0848 0b000000 D..H.... /usr/lib64/libopenblas_openmp.a/strsm_iunncopy_COOPERLAKE.o differs in assembler output --- old /usr/lib64/libopenblas_openmp.a/strsm_iunncopy_COOPERLAKE.o (disasm) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iunncopy_COOPERLAKE.o (disasm) @@ -6,7 +6,7 @@ strsm_iunncopy_COOPERLAKE: push %r15 - mov %rdi,%r15 + mov %r9,%r15 push %r14 push %r13 push %r12 @@ -15,449 +15,921 @@ sub $something,%rsp mov %rsi,offset(%rsp) sar $something,%rsi + mov %rdi,offset(%rsp) mov %rdx,offset(%rsp) mov %rcx,offset(%rsp) - mov %r8,(%rsp) - mov %r9,-offset(%rsp) + mov %r8,offset(%rsp) mov %rsi,offset(%rsp) test %rsi,%rsi jle - mov %rcx,%rbx - lea offset(,%rcx,4),%r13 lea (%rcx,%rcx,2),%rax - mov %rdx,%r14 - lea offset(,%rax,4),%rdi - lea offset(%r13,%rbx,1),%rdx - mov %rdi,offset(%rsp) - lea offset(,%rdx,4),%rdi - mov %rdi,offset(%rsp) - lea offset(,%rax,8),%rdi - shl $something,%rax + mov %rsi,%rbx + mov %rcx,%rsi + lea offset(,%rcx,4),%r11 + lea offset(,%rax,4),%rbp + lea offset(,%rax,8),%r13 + imul $something,%rsi,%rax + mov %r11,%r10 + add %rsi,%r10 + shl $something,%rsi + mov %rax,%r12 mov %rax,offset(%rsp) - imul $something,%rbx,%rax + mov %rsi,offset(%rsp) + mov %rdi,%rax + mov %rdi,%rsi + and $something,%edi mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - lea offset(,%rcx,8),%r11 - shl $something,%rcx - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - mov %rcx,offset(%rsp) + mov %rsi,%rdi + and $something,%edi + sar $something,%rax mov %rdi,offset(%rsp) - mov %r11,%rcx - mov %rbx,%rdi - shl $something,%rdi - add %rbx,%rcx + mov %rsi,%rdi + and $something,%rsi + mov %rsi,%r14 + mov %rax,%rsi + shl $something,%rsi + lea offset(,%rcx,8),%r9 + lea offset(,%r10,4),%r10 + and $something,%edi + shl $something,%rcx + mov %r11,offset(%rsp) + mov %r9,offset(%rsp) + add %rsi,%r11 + add %rsi,%r9 + mov %rbp,offset(%rsp) + mov %r10,offset(%rsp) + add %rsi,%rbp + add %rsi,%r10 + mov %r13,offset(%rsp) mov %rax,offset(%rsp) - mov %r8,%rax - imul %r13,%rax - mov %rdi,offset(%rsp) - lea offset(,%rcx,4),%rdi - mov %rdi,offset(%rsp) - lea offset(,%rdx,8),%rdi + add %rsi,%r13 mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi - shl $something,%rbx - mov %rbx,offset(%rsp) - mov %r14,%rbx - sub %rax,%r14 - mov %rsi,%rax shl $something,%rax - add %r8,%rax - mov %rax,offset(%rsp) - mov %r15,%rax - shl $something,%rax - mov %r11,offset(%rsp) + lea (%r8,%rbx,8),%rdi + mov %rcx,offset(%rsp) mov %rdi,offset(%rsp) - mov %r14,offset(%rsp) + add %rsi,%rcx + mov %r12,%rdi + mov %r11,offset(%rsp) + mov %r9,offset(%rsp) + mov %rbp,offset(%rsp) + mov %r10,offset(%rsp) + mov %r13,offset(%rsp) mov %rax,offset(%rsp) - mov %r15,-offset(%rsp) - vmovss offset(%rip),%xmm1 # - lea offset(%r13),%r12 - mov %r8,%rbp + add %rsi,%rdi + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + vmovaps %xmm29,%xmm28 + mov %r8,%rsi + vmovaps %xmm30,%xmm29 + mov %r14,%rdi + vmovaps %xmm31,%xmm30 + mov %r15,%r8 + vmovaps %xmm27,%xmm31 nopl offset(%rax,%rax,1) - lea offset(%r13,%rbx,1),%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - mov %rbx,%r8 - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) + cmpq $something,offset(%rsp) + lea (%rax,%rcx,1),%r11 mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) + lea (%rax,%rcx,1),%r10 mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) + lea (%rcx,%rax,1),%r9 mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) + lea (%rax,%rcx,1),%r13 mov offset(%rsp),%rax - lea (%rax,%rbx,1),%rsi + lea (%rcx,%rax,1),%r12 mov offset(%rsp),%rax - lea (%rax,%rbx,1),%r14 + lea (%rcx,%rax,1),%rbp mov offset(%rsp),%rax - lea (%rax,%rbx,1),%r15 - add offset(%rsp),%rbx - cmpq $something,-offset(%rsp) + lea (%rax,%rcx,1),%rbx jle - mov -offset(%rsp),%rcx - mov offset(%rsp),%r10 - mov %rbp,%rax - neg %rax - mov $something,%edi - mov %rbx,-offset(%rsp) - lea (%rcx,%rax,4),%r9 - sub %rbp,%rdi - lea offset(%r13,%r10,1),%r11 - mov %rcx,%rax xor %edx,%edx /usr/lib64/libopenblas_openmp.a/strsm_iunncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_iunncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iunncopy_COOPERLAKE.o (objdump) @@ -2,142 +2,350 @@ /usr/lib64/libopenblas_openmp.a/strsm_iunncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574989 ff415641 55415455 534881ec AWI..AVAUATUSH.. - 0010 b8000000 4889b424 a0000000 48c1fe04 ....H..$....H... - 0020 48899424 98000000 48898c24 a8000000 H..$....H..$.... - 0030 4c890424 4c894c24 f04889b4 24b00000 L..$L.L$.H..$... - 0040 004885f6 0f8ed703 00004889 cb4c8d2c .H........H..L., - 0050 8d000000 00488d04 494989d6 488d3c85 .....H..II..H.<. - 0060 00000000 498d541d 0048897c 2458488d ....I.T..H.|$XH. - 0070 3c950000 00004889 7c246048 8d3cc500 <.....H.|$`H.<.. - 0080 00000048 c1e00448 89842480 00000048 ...H...H..$....H - 0090 6bc33448 897c2468 486bfb1c 48894424 k.4H.|$hHk..H.D$ - 00a0 38486bc3 384c8d1c cd000000 0048c1e1 8Hk.8L.......H.. - 00b0 04488944 2440486b c33c4889 4c241848 .H.D$@Hk. - mov %rcx,%rbx - lea offset(,%rcx,4),%r13 lea (%rcx,%rcx,2),%rax - mov %rdx,%r14 - lea offset(,%rax,4),%rdi - lea offset(%r13,%rbx,1),%rdx - mov %rdi,offset(%rsp) - lea offset(,%rdx,4),%rdi - mov %rdi,offset(%rsp) - lea offset(,%rax,8),%rdi - shl $something,%rax + mov %rsi,%rbx + mov %rcx,%rsi + lea offset(,%rcx,4),%r11 + lea offset(,%rax,4),%rbp + lea offset(,%rax,8),%r13 + imul $something,%rsi,%rax + mov %r11,%r10 + add %rsi,%r10 + shl $something,%rsi + mov %rax,%r12 mov %rax,offset(%rsp) - imul $something,%rbx,%rax + mov %rsi,offset(%rsp) + mov %rdi,%rax + mov %rdi,%rsi + and $something,%edi mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - lea offset(,%rcx,8),%r11 - shl $something,%rcx - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - mov %rcx,offset(%rsp) + mov %rsi,%rdi + and $something,%edi + sar $something,%rax mov %rdi,offset(%rsp) - mov %r11,%rcx - mov %rbx,%rdi - shl $something,%rdi - add %rbx,%rcx + mov %rsi,%rdi + and $something,%rsi + mov %rsi,%r14 + mov %rax,%rsi + shl $something,%rsi + lea offset(,%rcx,8),%r9 + lea offset(,%r10,4),%r10 + and $something,%edi + shl $something,%rcx + mov %r11,offset(%rsp) + mov %r9,offset(%rsp) + add %rsi,%r11 + add %rsi,%r9 + mov %rbp,offset(%rsp) + mov %r10,offset(%rsp) + add %rsi,%rbp + add %rsi,%r10 + mov %r13,offset(%rsp) mov %rax,offset(%rsp) - mov %r8,%rax - imul %r13,%rax - mov %rdi,offset(%rsp) - lea offset(,%rcx,4),%rdi - mov %rdi,offset(%rsp) - lea offset(,%rdx,8),%rdi + add %rsi,%r13 mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi - shl $something,%rbx - mov %rbx,offset(%rsp) - mov %r14,%rbx - sub %rax,%r14 - mov %rsi,%rax shl $something,%rax - add %r8,%rax - mov %rax,offset(%rsp) - mov %r15,%rax - shl $something,%rax - mov %r11,offset(%rsp) + lea (%r8,%rbx,8),%rdi + mov %rcx,offset(%rsp) mov %rdi,offset(%rsp) - mov %r14,offset(%rsp) + add %rsi,%rcx + mov %r12,%rdi + mov %r11,offset(%rsp) + mov %r9,offset(%rsp) + mov %rbp,offset(%rsp) + mov %r10,offset(%rsp) + mov %r13,offset(%rsp) mov %rax,offset(%rsp) - mov %r15,-offset(%rsp) - vmovss offset(%rip),%xmm1 # - lea offset(%r13),%r12 - mov %r8,%rbp + add %rsi,%rdi + mov %rcx,offset(%rsp) + mov offset(%rsp),%rcx + mov %rsi,offset(%rsp) + mov %rdi,offset(%rsp) + vmovaps %xmm29,%xmm28 + mov %r8,%rsi + vmovaps %xmm30,%xmm29 + mov %r14,%rdi + vmovaps %xmm31,%xmm30 + mov %r15,%r8 + vmovaps %xmm27,%xmm31 nopl offset(%rax,%rax,1) - lea offset(%r13,%rbx,1),%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - mov %rbx,%r8 - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) + cmpq $something,offset(%rsp) + lea (%rax,%rcx,1),%r11 mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) + lea (%rax,%rcx,1),%r10 mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) + lea (%rcx,%rax,1),%r9 mov offset(%rsp),%rax - add %rbx,%rax - mov %rax,-offset(%rsp) + lea (%rax,%rcx,1),%r13 mov offset(%rsp),%rax - lea (%rax,%rbx,1),%rsi + lea (%rcx,%rax,1),%r12 mov offset(%rsp),%rax - lea (%rax,%rbx,1),%r14 + lea (%rcx,%rax,1),%rbp mov offset(%rsp),%rax - lea (%rax,%rbx,1),%r15 - add offset(%rsp),%rbx - cmpq $something,-offset(%rsp) + lea (%rax,%rcx,1),%rbx jle - mov -offset(%rsp),%rcx - mov offset(%rsp),%r10 - mov %rbp,%rax - neg %rax - mov $something,%edi - mov %rbx,-offset(%rsp) - lea (%rcx,%rax,4),%r9 - sub %rbp,%rdi - lea offset(%r13,%r10,1),%r11 - mov %rcx,%rax xor %edx,%edx /usr/lib64/libopenblas_openmp.a/strsm_iunncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_iunncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iunncopy_SKYLAKEX.o (objdump) @@ -2,142 +2,350 @@ /usr/lib64/libopenblas_openmp.a/strsm_iunncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574989 ff415641 55415455 534881ec AWI..AVAUATUSH.. - 0010 b8000000 4889b424 a0000000 48c1fe04 ....H..$....H... - 0020 48899424 98000000 48898c24 a8000000 H..$....H..$.... - 0030 4c890424 4c894c24 f04889b4 24b00000 L..$L.L$.H..$... - 0040 004885f6 0f8ed703 00004889 cb4c8d2c .H........H..L., - 0050 8d000000 00488d04 494989d6 488d3c85 .....H..II..H.<. - 0060 00000000 498d541d 0048897c 2458488d ....I.T..H.|$XH. - 0070 3c950000 00004889 7c246048 8d3cc500 <.....H.|$`H.<.. - 0080 00000048 c1e00448 89842480 00000048 ...H...H..$....H - 0090 6bc33448 897c2468 486bfb1c 48894424 k.4H.|$hHk..H.D$ - 00a0 38486bc3 384c8d1c cd000000 0048c1e1 8Hk.8L.......H.. - 00b0 04488944 2440486b c33c4889 4c241848 .H.D$@Hk. - mov %rcx,%rbx - lea offset(,%rcx,4),%r12 + lea offset(,%rcx,4),%r11 lea (%rcx,%rcx,2),%rax - mov %rdx,%r15 - lea offset(,%rax,4),%rdi - lea (%r12,%rbx,1),%rdx - mov %rdi,offset(%rsp) - lea offset(,%rdx,4),%rdi - mov %rdi,offset(%rsp) - lea offset(,%rax,8),%rdi - shl $something,%rax - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi - mov %rax,offset(%rsp) - imul $something,%rbx,%rax + mov %r11,%rdx lea offset(,%rcx,8),%r10 + lea offset(,%rax,4),%r9 + lea offset(,%rax,8),%rbp + mov %rsi,%rbx + imul $something,%rcx,%rax + mov %rcx,%rsi + add %rcx,%rdx shl $something,%rcx - mov %rax,offset(%rsp) - imul $something,%rbx,%rax mov %rcx,offset(%rsp) - mov %rdi,offset(%rsp) + mov %rdi,%rcx + and $something,%ecx + mov %rcx,offset(%rsp) + mov %rdi,%rcx mov %rax,offset(%rsp) - mov $something,%eax - sub %r8,%rax - imul %r12,%rax - mov %rbx,%rdi - mov %r10,%rcx + and $something,%ecx + mov %rdi,%rax + sar $something,%rax + mov %rcx,offset(%rsp) + mov %rdi,%rcx + and $something,%rdi + mov %rdi,%r13 + mov %rax,%rdi shl $something,%rdi - add %rbx,%rcx - add %r15,%rax - mov %rdi,offset(%rsp) - mov %rax,offset(%rsp) - lea offset(,%rcx,4),%rdi - mov %rsi,%rax - mov %rdi,offset(%rsp) - shl $something,%rax - lea offset(,%rdx,8),%rdi - add %r8,%rax - mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi + shl $something,%rsi + shl $something,%rdx + mov %rsi,offset(%rsp) + add %rdi,%rsi + mov %r11,offset(%rsp) + mov %r10,offset(%rsp) + add %rdi,%r11 + add %rdi,%r10 + mov %r9,offset(%rsp) + mov %rdx,offset(%rsp) + add %rdi,%r9 + add %rdi,%rdx + mov %rbp,offset(%rsp) mov %rax,offset(%rsp) - mov %r14,%rax + add %rdi,%rbp + mov %rsi,offset(%rsp) shl $something,%rax + mov offset(%rsp),%rsi + and $something,%ecx + mov %r11,offset(%rsp) mov %r10,offset(%rsp) - mov %rdi,offset(%rsp) + mov %r9,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rbp,offset(%rsp) mov %rax,offset(%rsp) - mov %r14,-offset(%rsp) - shl $something,%rbx - vmovss offset(%rip),%xmm1 # - mov %rbx,-offset(%rsp) - lea offset(%r12),%rbp - mov %r8,%rbx - mov %r15,%r11 - nopl (%rax) - lea (%r12,%r11,1),%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - mov %r11,%r8 - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) + mov %r12,offset(%rsp) + add %rdi,%rsi + mov %rcx,offset(%rsp) + vmovss offset(%rip),%xmm0 # + lea (%r8,%rbx,8),%rcx + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rsi,offset(%rsp) + vmovaps %xmm29,%xmm28 + mov %r8,%rsi + vmovaps %xmm30,%xmm29 + mov %r12,%rcx + vmovaps %xmm31,%xmm30 + mov %r13,%rdi + vmovaps %xmm27,%xmm31 + mov %r14,%r8 + nopl offset(%rax) mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) + cmpq $something,offset(%rsp) + lea (%rax,%rcx,1),%r11 mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) + lea (%rax,%rcx,1),%r10 mov offset(%rsp),%rax - lea (%r11,%rax,1),%rcx + lea (%rcx,%rax,1),%r9 mov offset(%rsp),%rax - lea (%rax,%r11,1),%r13 + lea (%rax,%rcx,1),%r13 mov offset(%rsp),%rax - lea (%rax,%r11,1),%r14 + lea (%rcx,%rax,1),%r12 mov offset(%rsp),%rax - lea (%rax,%r11,1),%r15 - add -offset(%rsp),%r11 - cmpq $something,-offset(%rsp) - jle - mov -offset(%rsp),%rsi - mov %rbx,%rax - neg %rax - mov $something,%edi - mov %r11,-offset(%rsp) - lea (%rsi,%rax,4),%r9 - mov offset(%rsp),%r10 - sub %rbx,%rdi - mov %rsi,%rax - xor %edx,%edx - mov %rcx,%r11 /usr/lib64/libopenblas_openmp.a/strsm_iunucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_iunucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iunucopy_COOPERLAKE.o (objdump) @@ -2,134 +2,318 @@ /usr/lib64/libopenblas_openmp.a/strsm_iunucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 4989fe41 55415455 534881ec AWAVI..AUATUSH.. - 0010 b0000000 4889b424 98000000 48c1fe04 ....H..$....H... - 0020 48899424 90000000 48898c24 a0000000 H..$....H..$.... - 0030 4c890424 4c894c24 e84889b4 24a80000 L..$L.L$.H..$... - 0040 004885f6 0f8eb703 00004889 cb4c8d24 .H........H..L.$ - 0050 8d000000 00488d04 494989d7 488d3c85 .....H..II..H.<. - 0060 00000000 498d141c 48897c24 50488d3c ....I...H.|$PH.< - 0070 95000000 0048897c 2458488d 3cc50000 .....H.|$XH.<... - 0080 000048c1 e0044889 44247848 6bc33448 ..H...H.D$xHk.4H - 0090 897c2460 486bfb1c 48894424 30486bc3 .|$`Hk..H.D$0Hk. - 00a0 384c8d14 cd000000 0048c1e1 04488944 8L.......H...H.D - 00b0 2438486b c33c4889 4c241048 897c2418 $8Hk. - mov %rcx,%rbx - lea offset(,%rcx,4),%r12 + lea offset(,%rcx,4),%r11 lea (%rcx,%rcx,2),%rax - mov %rdx,%r15 - lea offset(,%rax,4),%rdi - lea (%r12,%rbx,1),%rdx - mov %rdi,offset(%rsp) - lea offset(,%rdx,4),%rdi - mov %rdi,offset(%rsp) - lea offset(,%rax,8),%rdi - shl $something,%rax - mov %rax,offset(%rsp) - imul $something,%rbx,%rax - mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi - mov %rax,offset(%rsp) - imul $something,%rbx,%rax + mov %r11,%rdx lea offset(,%rcx,8),%r10 + lea offset(,%rax,4),%r9 + lea offset(,%rax,8),%rbp + mov %rsi,%rbx + imul $something,%rcx,%rax + mov %rcx,%rsi + add %rcx,%rdx shl $something,%rcx - mov %rax,offset(%rsp) - imul $something,%rbx,%rax mov %rcx,offset(%rsp) - mov %rdi,offset(%rsp) + mov %rdi,%rcx + and $something,%ecx + mov %rcx,offset(%rsp) + mov %rdi,%rcx mov %rax,offset(%rsp) - mov $something,%eax - sub %r8,%rax - imul %r12,%rax - mov %rbx,%rdi - mov %r10,%rcx + and $something,%ecx + mov %rdi,%rax + sar $something,%rax + mov %rcx,offset(%rsp) + mov %rdi,%rcx + and $something,%rdi + mov %rdi,%r13 + mov %rax,%rdi shl $something,%rdi - add %rbx,%rcx - add %r15,%rax - mov %rdi,offset(%rsp) - mov %rax,offset(%rsp) - lea offset(,%rcx,4),%rdi - mov %rsi,%rax - mov %rdi,offset(%rsp) - shl $something,%rax - lea offset(,%rdx,8),%rdi - add %r8,%rax - mov %rdi,offset(%rsp) - imul $something,%rbx,%rdi + shl $something,%rsi + shl $something,%rdx + mov %rsi,offset(%rsp) + add %rdi,%rsi + mov %r11,offset(%rsp) + mov %r10,offset(%rsp) + add %rdi,%r11 + add %rdi,%r10 + mov %r9,offset(%rsp) + mov %rdx,offset(%rsp) + add %rdi,%r9 + add %rdi,%rdx + mov %rbp,offset(%rsp) mov %rax,offset(%rsp) - mov %r14,%rax + add %rdi,%rbp + mov %rsi,offset(%rsp) shl $something,%rax + mov offset(%rsp),%rsi + and $something,%ecx + mov %r11,offset(%rsp) mov %r10,offset(%rsp) - mov %rdi,offset(%rsp) + mov %r9,offset(%rsp) + mov %rdx,offset(%rsp) + mov %rbp,offset(%rsp) mov %rax,offset(%rsp) - mov %r14,-offset(%rsp) - shl $something,%rbx - vmovss offset(%rip),%xmm1 # - mov %rbx,-offset(%rsp) - lea offset(%r12),%rbp - mov %r8,%rbx - mov %r15,%r11 - nopl (%rax) - lea (%r12,%r11,1),%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - mov %r11,%r8 - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) - mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) + mov %r12,offset(%rsp) + add %rdi,%rsi + mov %rcx,offset(%rsp) + vmovss offset(%rip),%xmm0 # + lea (%r8,%rbx,8),%rcx + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rsi,offset(%rsp) + vmovaps %xmm29,%xmm28 + mov %r8,%rsi + vmovaps %xmm30,%xmm29 + mov %r12,%rcx + vmovaps %xmm31,%xmm30 + mov %r13,%rdi + vmovaps %xmm27,%xmm31 + mov %r14,%r8 + nopl offset(%rax) mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) + cmpq $something,offset(%rsp) + lea (%rax,%rcx,1),%r11 mov offset(%rsp),%rax - add %r11,%rax - mov %rax,-offset(%rsp) + lea (%rax,%rcx,1),%r10 mov offset(%rsp),%rax - lea (%r11,%rax,1),%rcx + lea (%rcx,%rax,1),%r9 mov offset(%rsp),%rax - lea (%rax,%r11,1),%r13 + lea (%rax,%rcx,1),%r13 mov offset(%rsp),%rax - lea (%rax,%r11,1),%r14 + lea (%rcx,%rax,1),%r12 mov offset(%rsp),%rax - lea (%rax,%r11,1),%r15 - add -offset(%rsp),%r11 - cmpq $something,-offset(%rsp) - jle - mov -offset(%rsp),%rsi - mov %rbx,%rax - neg %rax - mov $something,%edi - mov %r11,-offset(%rsp) - lea (%rsi,%rax,4),%r9 - mov offset(%rsp),%r10 - sub %rbx,%rdi - mov %rsi,%rax - xor %edx,%edx - mov %rcx,%r11 /usr/lib64/libopenblas_openmp.a/strsm_iunucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_iunucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iunucopy_SKYLAKEX.o (objdump) @@ -2,134 +2,318 @@ /usr/lib64/libopenblas_openmp.a/strsm_iunucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 4989fe41 55415455 534881ec AWAVI..AUATUSH.. - 0010 b0000000 4889b424 98000000 48c1fe04 ....H..$....H... - 0020 48899424 90000000 48898c24 a0000000 H..$....H..$.... - 0030 4c890424 4c894c24 e84889b4 24a80000 L..$L.L$.H..$... - 0040 004885f6 0f8eb703 00004889 cb4c8d24 .H........H..L.$ - 0050 8d000000 00488d04 494989d7 488d3c85 .....H..II..H.<. - 0060 00000000 498d141c 48897c24 50488d3c ....I...H.|$PH.< - 0070 95000000 0048897c 2458488d 3cc50000 .....H.|$XH.<... - 0080 000048c1 e0044889 44247848 6bc33448 ..H...H.D$xHk.4H - 0090 897c2460 486bfb1c 48894424 30486bc3 .|$`Hk..H.D$0Hk. - 00a0 384c8d14 cd000000 0048c1e1 04488944 8L.......H...H.D - 00b0 2438486b c33c4889 4c241048 897c2418 $8Hk. - mov %r8,%r15 - mov %rsi,%rax - neg %r15 + lea offset(,%rcx,8),%rax + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rsi,%r15 + lea offset(,%rcx,4),%rbx + mov %rcx,%rsi + lea offset(,%rax,4),%rcx shl $something,%rax - shl $something,%r15 - lea offset(,%rcx,4),%r13 - lea (%rax,%r8,1),%rcx - lea (%rdx,%r15,1),%rax - mov %rax,-offset(%rsp) - mov %rdx,-offset(%rsp) + mov %rax,offset(%rsp) + imul $something,%rsi,%rax + mov %rbx,offset(%rsp) + add %rsi,%rbx + mov %rax,offset(%rsp) mov %rdi,%rax + lea offset(,%rbx,4),%rbx + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) mov %rdi,%rbx - shl $something,%rax - vmovss offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%rbx - mov %r8,%rdi - lea offset(%r13),%r14 - mov %rax,%rbp - mov %rcx,%r8 - xchg %ax,%ax - mov -offset(%rsp),%rax - sub %r15,%rax - test %r12,%r12 + mov %rdi,%rax + sar $something,%rbx + and $something,%eax + mov %rcx,offset(%rsp) + mov %rax,offset(%rsp) + mov %rsi,%rcx + mov %rbx,%rax + shl $something,%rsi + imul %rsi,%rax + mov %rbx,offset(%rsp) + shl $something,%rcx + add %rdx,%rax + mov %rax,offset(%rsp) + and $something,%edi + lea (%r8,%r15,8),%rax + lea offset(,%rbx,8),%r15 + shl $something,%rbx + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + mov %rbx,offset(%rsp) + mov %r8,%r14 + vmovss offset(%rip),%xmm0 # + mov %r15,%r8 + mov %rsi,%r12 + mov %r14,%r15 + mov %rdx,%r14 + nopl offset(%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r14,1),%r10 + mov offset(%rsp),%rax + lea (%rax,%r14,1),%rbx + mov offset(%rsp),%rax + lea (%r14,%rax,1),%r11 + mov offset(%rsp),%rax + lea (%rax,%r14,1),%rsi + mov offset(%rsp),%rax + lea (%r14,%rax,1),%rdi + mov offset(%rsp),%rax + lea (%r14,%rax,1),%r13 + mov offset(%rsp),%rax + lea (%rax,%r14,1),%rbp jle - mov %rdi,%rcx - neg %rcx - lea (%rax,%r15,1),%r11 - lea (%r9,%r15,1),%r10 mov %r9,%rdx + xor %eax,%eax + mov %r9,-offset(%rsp) + mov %r14,%rcx + mov %r8,%r9 + mov %rax,%r8 + mov %r15,%rax + mov %r14,%r15 + mov %rdx,%r14 + jmp + nopl offset(%rax) + jge + vmovss offset(%rcx),%xmm7 + vmovss offset(%rcx),%xmm5 + vmovss offset(%rcx),%xmm6 + vmovss offset(%rcx),%xmm4 + vmovss offset(%rcx),%xmm3 + vmovss offset(%rcx),%xmm31 + vmovss offset(%rcx),%xmm30 + vmovss (%r10),%xmm29 + vmovss offset(%r10),%xmm28 + vmovss offset(%r10),%xmm27 + vmovss offset(%r10),%xmm26 + vmovss offset(%r10),%xmm25 + vmovss offset(%r10),%xmm24 + vmovss offset(%r10),%xmm23 + vmovss offset(%r10),%xmm22 + vmovss (%rbx),%xmm21 + vmovss offset(%rbx),%xmm20 + vmovss offset(%rbx),%xmm19 + vmovss offset(%rbx),%xmm18 + vmovss offset(%rbx),%xmm17 + vmovss offset(%rbx),%xmm16 + vmovss offset(%rbx),%xmm15 + vmovss offset(%rbx),%xmm14 + vmovss (%r11),%xmm13 + vmovss offset(%r11),%xmm12 + vmovss offset(%r11),%xmm11 + vmovss offset(%r11),%xmm10 + vmovss %xmm7,-offset(%rsp) + vmovss %xmm5,-offset(%rsp) + vmovss %xmm6,-offset(%rsp) + vmovss %xmm4,-offset(%rsp) + vmovss %xmm3,-offset(%rsp) + vmovss offset(%r11),%xmm9 + vmovss offset(%r11),%xmm7 + vmovss offset(%r11),%xmm8 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rsi),%xmm7 + vmovss offset(%r11),%xmm6 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rsi),%xmm7 + vmovss (%rsi),%xmm5 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rsi),%xmm7 + vmovss offset(%rsi),%xmm4 + vmovss %xmm7,-offset(%rsp) + vmovss (%rdi),%xmm7 + vmovss offset(%rsi),%xmm3 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss offset(%rsi),%xmm2 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss offset(%rsi),%xmm1 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) /usr/lib64/libopenblas_openmp.a/strsm_iutncopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_iutncopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iutncopy_COOPERLAKE.o (objdump) @@ -2,87 +2,251 @@ /usr/lib64/libopenblas_openmp.a/strsm_iutncopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989fc55 4889d553 AWAVAUATI..UH..S - 0010 48897424 d848c1fe 0448894c 24e04889 H.t$.H...H.L$.H. - 0020 7424e848 85f60f8e cf010000 4d89c748 t$.H........M..H - 0030 89f049f7 df48c1e0 0449c1e7 024c8d2c ..I..H...I...L., - 0040 8d000000 004a8d0c 004a8d04 3a488944 .....J...J..:H.D - 0050 24d04889 5424f048 89f84889 fb48c1e0 $.H.T$.H..H..H.. - 0060 06c5fa10 0d000000 004c8944 24f84c29 .........L.D$.L) - 0070 c34c89c7 4d8d7504 4889c549 89c86690 .L..M.u.H..I..f. - 0080 488b4424 d04c29f8 4d85e40f 8e320100 H.D$.L).M....2.. - 0090 004889f9 48f7d94e 8d1c384f 8d14394c .H..H..N..8O..9L - 00a0 89cae9c7 00000066 0f1f8400 00000000 .......f........ - 00b0 4883f90f 0f8ed600 0000c5fa 1000c5fa H............... - 00c0 1102c5fa 104004c5 fa114204 c5fa1040 .....@....B....@ - 00d0 08c5fa11 4208c5fa 10400cc5 fa11420c ....B....@....B. - 00e0 c5fa1040 10c5fa11 4210c5fa 104014c5 ...@....B....@.. - 00f0 fa114214 c5fa1040 18c5fa11 4218c5fa ..B....@....B... - 0100 10401cc5 fa11421c c5fa1040 20c5fa11 .@....B....@ ... - 0110 4220c5fa 104024c5 fa114224 c5fa1040 B ...@$...B$...@ - 0120 28c5fa11 4228c5fa 10402cc5 fa11422c (...B(...@,...B, - 0130 c5fa1040 30c5fa11 4230c5fa 104034c5 ...@0...B0...@4. - 0140 fa114234 c5fa1040 38c5fa11 4238c5fa ..B4...@8...B8.. - 0150 10403cc5 fa11423c 48ffc148 83c2404c .@<...B - mov %r8,%r15 - mov %rsi,%rax - neg %r15 + lea offset(,%rcx,8),%rax + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rsi,%r15 + lea offset(,%rcx,4),%rbx + mov %rcx,%rsi + lea offset(,%rax,4),%rcx shl $something,%rax - shl $something,%r15 - lea offset(,%rcx,4),%r13 - lea (%rax,%r8,1),%rcx - lea (%rdx,%r15,1),%rax - mov %rax,-offset(%rsp) - mov %rdx,-offset(%rsp) + mov %rax,offset(%rsp) + imul $something,%rsi,%rax + mov %rbx,offset(%rsp) + add %rsi,%rbx + mov %rax,offset(%rsp) mov %rdi,%rax + lea offset(,%rbx,4),%rbx + and $something,%eax + mov %rbx,offset(%rsp) + mov %rax,offset(%rsp) mov %rdi,%rbx - shl $something,%rax - vmovss offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%rbx - mov %r8,%rdi - lea offset(%r13),%r14 - mov %rax,%rbp - mov %rcx,%r8 - xchg %ax,%ax - mov -offset(%rsp),%rax - sub %r15,%rax - test %r12,%r12 + mov %rdi,%rax + sar $something,%rbx + and $something,%eax + mov %rcx,offset(%rsp) + mov %rax,offset(%rsp) + mov %rsi,%rcx + mov %rbx,%rax + shl $something,%rsi + imul %rsi,%rax + mov %rbx,offset(%rsp) + shl $something,%rcx + add %rdx,%rax + mov %rax,offset(%rsp) + and $something,%edi + lea (%r8,%r15,8),%rax + lea offset(,%rbx,8),%r15 + shl $something,%rbx + mov %rcx,offset(%rsp) + mov %rdi,offset(%rsp) + mov %rax,offset(%rsp) + mov %rbx,offset(%rsp) + mov %r8,%r14 + vmovss offset(%rip),%xmm0 # + mov %r15,%r8 + mov %rsi,%r12 + mov %r14,%r15 + mov %rdx,%r14 + nopl offset(%rax) + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r14,1),%r10 + mov offset(%rsp),%rax + lea (%rax,%r14,1),%rbx + mov offset(%rsp),%rax + lea (%r14,%rax,1),%r11 + mov offset(%rsp),%rax + lea (%rax,%r14,1),%rsi + mov offset(%rsp),%rax + lea (%r14,%rax,1),%rdi + mov offset(%rsp),%rax + lea (%r14,%rax,1),%r13 + mov offset(%rsp),%rax + lea (%rax,%r14,1),%rbp jle - mov %rdi,%rcx - neg %rcx - lea (%rax,%r15,1),%r11 - lea (%r9,%r15,1),%r10 mov %r9,%rdx + xor %eax,%eax + mov %r9,-offset(%rsp) + mov %r14,%rcx + mov %r8,%r9 + mov %rax,%r8 + mov %r15,%rax + mov %r14,%r15 + mov %rdx,%r14 + jmp + nopl offset(%rax) + jge + vmovss offset(%rcx),%xmm7 + vmovss offset(%rcx),%xmm5 + vmovss offset(%rcx),%xmm6 + vmovss offset(%rcx),%xmm4 + vmovss offset(%rcx),%xmm3 + vmovss offset(%rcx),%xmm31 + vmovss offset(%rcx),%xmm30 + vmovss (%r10),%xmm29 + vmovss offset(%r10),%xmm28 + vmovss offset(%r10),%xmm27 + vmovss offset(%r10),%xmm26 + vmovss offset(%r10),%xmm25 + vmovss offset(%r10),%xmm24 + vmovss offset(%r10),%xmm23 + vmovss offset(%r10),%xmm22 + vmovss (%rbx),%xmm21 + vmovss offset(%rbx),%xmm20 + vmovss offset(%rbx),%xmm19 + vmovss offset(%rbx),%xmm18 + vmovss offset(%rbx),%xmm17 + vmovss offset(%rbx),%xmm16 + vmovss offset(%rbx),%xmm15 + vmovss offset(%rbx),%xmm14 + vmovss (%r11),%xmm13 + vmovss offset(%r11),%xmm12 + vmovss offset(%r11),%xmm11 + vmovss offset(%r11),%xmm10 + vmovss %xmm7,-offset(%rsp) + vmovss %xmm5,-offset(%rsp) + vmovss %xmm6,-offset(%rsp) + vmovss %xmm4,-offset(%rsp) + vmovss %xmm3,-offset(%rsp) + vmovss offset(%r11),%xmm9 + vmovss offset(%r11),%xmm7 + vmovss offset(%r11),%xmm8 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rsi),%xmm7 + vmovss offset(%r11),%xmm6 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rsi),%xmm7 + vmovss (%rsi),%xmm5 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rsi),%xmm7 + vmovss offset(%rsi),%xmm4 + vmovss %xmm7,-offset(%rsp) + vmovss (%rdi),%xmm7 + vmovss offset(%rsi),%xmm3 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss offset(%rsi),%xmm2 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss offset(%rsi),%xmm1 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rdi),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) /usr/lib64/libopenblas_openmp.a/strsm_iutncopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_iutncopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iutncopy_SKYLAKEX.o (objdump) @@ -2,87 +2,251 @@ /usr/lib64/libopenblas_openmp.a/strsm_iutncopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989fc55 4889d553 AWAVAUATI..UH..S - 0010 48897424 d848c1fe 0448894c 24e04889 H.t$.H...H.L$.H. - 0020 7424e848 85f60f8e cf010000 4d89c748 t$.H........M..H - 0030 89f049f7 df48c1e0 0449c1e7 024c8d2c ..I..H...I...L., - 0040 8d000000 004a8d0c 004a8d04 3a488944 .....J...J..:H.D - 0050 24d04889 5424f048 89f84889 fb48c1e0 $.H.T$.H..H..H.. - 0060 06c5fa10 0d000000 004c8944 24f84c29 .........L.D$.L) - 0070 c34c89c7 4d8d7504 4889c549 89c86690 .L..M.u.H..I..f. - 0080 488b4424 d04c29f8 4d85e40f 8e320100 H.D$.L).M....2.. - 0090 004889f9 48f7d94e 8d1c384f 8d14394c .H..H..N..8O..9L - 00a0 89cae9c7 00000066 0f1f8400 00000000 .......f........ - 00b0 4883f90f 0f8ed600 0000c5fa 1000c5fa H............... - 00c0 1102c5fa 104004c5 fa114204 c5fa1040 .....@....B....@ - 00d0 08c5fa11 4208c5fa 10400cc5 fa11420c ....B....@....B. - 00e0 c5fa1040 10c5fa11 4210c5fa 104014c5 ...@....B....@.. - 00f0 fa114214 c5fa1040 18c5fa11 4218c5fa ..B....@....B... - 0100 10401cc5 fa11421c c5fa1040 20c5fa11 .@....B....@ ... - 0110 4220c5fa 104024c5 fa114224 c5fa1040 B ...@$...B$...@ - 0120 28c5fa11 4228c5fa 10402cc5 fa11422c (...B(...@,...B, - 0130 c5fa1040 30c5fa11 4230c5fa 104034c5 ...@0...B0...@4. - 0140 fa114234 c5fa1040 38c5fa11 4238c5fa ..B4...@8...B8.. - 0150 10403cc5 fa11423c 48ffc148 83c2404c .@<...B - mov %r8,%rax - shl $something,%rsi - neg %rax - mov %rdi,%r11 - mov %rdi,%r15 - mov %rsi,%r14 - lea offset(%rdx,%rax,4),%rax - vmovss offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%r11 - add %r8,%r14 - mov %r8,%rdi - lea offset(,%rcx,4),%rbp - shl $something,%r15 + lea offset(,%rcx,8),%rax + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rsi,%rbx + lea offset(,%rax,4),%rsi + shl $something,%rax mov %rdx,%r13 - mov %rax,%r8 + mov %rax,offset(%rsp) + lea offset(,%rcx,4),%rdx + mov %rcx,%rax + shl $something,%rax + mov %rdx,offset(%rsp) + mov %rsi,offset(%rsp) + add %rcx,%rdx + mov %rcx,%rsi + imul $something,%rcx,%rcx + mov %rax,%rbp + mov %rdi,%rax + and $something,%eax + mov %rcx,offset(%rsp) + mov %rax,offset(%rsp) + mov %rdi,%rcx + mov %rdi,%rax + sar $something,%rcx + and $something,%eax + mov %rax,offset(%rsp) + mov %rcx,%rax + imul %rbp,%rax + shl $something,%rsi + mov %rsi,offset(%rsp) + add %r13,%rax + mov %rax,offset(%rsp) + lea offset(,%rdx,4),%rsi + lea (%r8,%rbx,8),%rax + mov %rsi,offset(%rsp) + mov %rax,offset(%rsp) + lea offset(,%rcx,8),%r15 + and $something,%edi + mov %rcx,offset(%rsp) + vmovss offset(%rip),%xmm0 # + shl $something,%rcx + mov %rdi,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r13,%r14 + mov %r15,%rcx + mov %r9,%rdi + mov %r8,%r15 + mov %rbp,%r12 nopl offset(%rax) - mov %r13,%rax - add $something,%r13 - test %r12,%r12 + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r14,1),%rsi + mov offset(%rsp),%rax + lea (%rax,%r14,1),%r9 + mov offset(%rsp),%rax + lea (%r14,%rax,1),%r8 + mov offset(%rsp),%rax + lea (%rax,%r14,1),%r11 + mov offset(%rsp),%rax + lea (%r14,%rax,1),%rbx + mov offset(%rsp),%rax + lea (%r14,%rax,1),%r13 + mov offset(%rsp),%rax + lea (%rax,%r14,1),%rbp jle - mov %r8,%r10 - mov %rdi,%rcx - sub %r13,%r10 - neg %rcx - add %r9,%r10 - mov %r9,%rdx + mov %rdi,%rdx + xor %eax,%eax + mov %rdi,-offset(%rsp) + mov %r14,%r10 + mov %rax,%rdi + mov %r14,%rax + mov %rcx,%r14 + mov %r15,%rcx + mov %rdx,%r15 jmp - nopw offset(%rax,%rax,1) - cmp $something,%rcx - jle - vmovss (%rax),%xmm0 + nopl offset(%rax) + jge + vmovss offset(%r10),%xmm7 + vmovss offset(%r10),%xmm5 + vmovss offset(%r10),%xmm6 + vmovss offset(%r10),%xmm4 + vmovss offset(%r10),%xmm3 + vmovss offset(%r10),%xmm31 + vmovss offset(%r10),%xmm30 + vmovss (%rsi),%xmm29 + vmovss offset(%rsi),%xmm28 + vmovss offset(%rsi),%xmm27 + vmovss offset(%rsi),%xmm26 + vmovss offset(%rsi),%xmm25 + vmovss offset(%rsi),%xmm24 + vmovss offset(%rsi),%xmm23 + vmovss offset(%rsi),%xmm22 + vmovss (%r9),%xmm21 + vmovss offset(%r9),%xmm20 + vmovss offset(%r9),%xmm19 + vmovss offset(%r9),%xmm18 + vmovss offset(%r9),%xmm17 + vmovss offset(%r9),%xmm16 + vmovss offset(%r9),%xmm15 + vmovss offset(%r9),%xmm14 + vmovss (%r8),%xmm13 + vmovss offset(%r8),%xmm12 + vmovss offset(%r8),%xmm11 + vmovss offset(%r8),%xmm10 + vmovss %xmm7,-offset(%rsp) + vmovss %xmm5,-offset(%rsp) + vmovss %xmm6,-offset(%rsp) + vmovss %xmm4,-offset(%rsp) + vmovss %xmm3,-offset(%rsp) + vmovss offset(%r8),%xmm9 + vmovss offset(%r8),%xmm7 + vmovss offset(%r8),%xmm8 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r11),%xmm7 + vmovss offset(%r8),%xmm6 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r11),%xmm7 + vmovss (%r11),%xmm5 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r11),%xmm7 + vmovss offset(%r11),%xmm4 + vmovss %xmm7,-offset(%rsp) + vmovss (%rbx),%xmm7 + vmovss offset(%r11),%xmm3 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss offset(%r11),%xmm2 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss offset(%r11),%xmm1 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 /usr/lib64/libopenblas_openmp.a/strsm_iutucopy_COOPERLAKE.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_iutucopy_COOPERLAKE.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iutucopy_COOPERLAKE.o (objdump) @@ -2,78 +2,238 @@ /usr/lib64/libopenblas_openmp.a/strsm_iutucopy_COOPERLAKE.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989fc55 534889d3 AWAVAUATI..USH.. - 0010 48897424 e048c1fe 0448894c 24e84889 H.t$.H...H.L$.H. - 0020 7424f048 85f60f8e a6010000 4c89c048 t$.H........L..H - 0030 c1e60448 f7d84989 fb4989ff 4989f648 ...H..I..I..I..H - 0040 8d448240 c5fa100d 00000000 4c894424 .D.@........L.D$ - 0050 f84d29c3 4d01c64c 89c7488d 2c8d0000 .M).M..L..H.,... - 0060 000049c1 e7064989 d54989c0 0f1f4000 ..I...I..I....@. - 0070 4c89e849 83c5404d 85e40f8e 23010000 L..I..@M....#... - 0080 4d89c248 89f94d29 ea48f7d9 4d01ca4c M..H..M).H..M..L - 0090 89cae9c4 00000066 0f1f8400 00000000 .......f........ - 00a0 4883f90f 0f8ece00 0000c5fa 1000c5fa H............... - 00b0 1102c5fa 104004c5 fa114204 c5fa1040 .....@....B....@ - 00c0 08c5fa11 4208c5fa 10400cc5 fa11420c ....B....@....B. - 00d0 c5fa1040 10c5fa11 4210c5fa 104014c5 ...@....B....@.. - 00e0 fa114214 c5fa1040 18c5fa11 4218c5fa ..B....@....B... - 00f0 10401cc5 fa11421c c5fa1040 20c5fa11 .@....B....@ ... - 0100 4220c5fa 104024c5 fa114224 c5fa1040 B ...@$...B$...@ - 0110 28c5fa11 4228c5fa 10402cc5 fa11422c (...B(...@,...B, - 0120 c5fa1040 30c5fa11 4230c5fa 104034c5 ...@0...B0...@4. - 0130 fa114234 c5fa1040 38c5fa11 4238c5fa ..B4...@8...B8.. - 0140 10403cc5 fa11423c 48ffc148 83c24048 .@<...B - mov %r8,%rax - shl $something,%rsi - neg %rax - mov %rdi,%r11 - mov %rdi,%r15 - mov %rsi,%r14 - lea offset(%rdx,%rax,4),%rax - vmovss offset(%rip),%xmm1 # - mov %r8,-offset(%rsp) - sub %r8,%r11 - add %r8,%r14 - mov %r8,%rdi - lea offset(,%rcx,4),%rbp - shl $something,%r15 + lea offset(,%rcx,8),%rax + mov %rax,offset(%rsp) + lea (%rcx,%rcx,2),%rax + mov %rsi,%rbx + lea offset(,%rax,4),%rsi + shl $something,%rax mov %rdx,%r13 - mov %rax,%r8 + mov %rax,offset(%rsp) + lea offset(,%rcx,4),%rdx + mov %rcx,%rax + shl $something,%rax + mov %rdx,offset(%rsp) + mov %rsi,offset(%rsp) + add %rcx,%rdx + mov %rcx,%rsi + imul $something,%rcx,%rcx + mov %rax,%rbp + mov %rdi,%rax + and $something,%eax + mov %rcx,offset(%rsp) + mov %rax,offset(%rsp) + mov %rdi,%rcx + mov %rdi,%rax + sar $something,%rcx + and $something,%eax + mov %rax,offset(%rsp) + mov %rcx,%rax + imul %rbp,%rax + shl $something,%rsi + mov %rsi,offset(%rsp) + add %r13,%rax + mov %rax,offset(%rsp) + lea offset(,%rdx,4),%rsi + lea (%r8,%rbx,8),%rax + mov %rsi,offset(%rsp) + mov %rax,offset(%rsp) + lea offset(,%rcx,8),%r15 + and $something,%edi + mov %rcx,offset(%rsp) + vmovss offset(%rip),%xmm0 # + shl $something,%rcx + mov %rdi,offset(%rsp) + mov %rcx,offset(%rsp) + mov %r13,%r14 + mov %r15,%rcx + mov %r9,%rdi + mov %r8,%r15 + mov %rbp,%r12 nopl offset(%rax) - mov %r13,%rax - add $something,%r13 - test %r12,%r12 + mov offset(%rsp),%rax + cmpq $something,offset(%rsp) + lea (%rax,%r14,1),%rsi + mov offset(%rsp),%rax + lea (%rax,%r14,1),%r9 + mov offset(%rsp),%rax + lea (%r14,%rax,1),%r8 + mov offset(%rsp),%rax + lea (%rax,%r14,1),%r11 + mov offset(%rsp),%rax + lea (%r14,%rax,1),%rbx + mov offset(%rsp),%rax + lea (%r14,%rax,1),%r13 + mov offset(%rsp),%rax + lea (%rax,%r14,1),%rbp jle - mov %r8,%r10 - mov %rdi,%rcx - sub %r13,%r10 - neg %rcx - add %r9,%r10 - mov %r9,%rdx + mov %rdi,%rdx + xor %eax,%eax + mov %rdi,-offset(%rsp) + mov %r14,%r10 + mov %rax,%rdi + mov %r14,%rax + mov %rcx,%r14 + mov %r15,%rcx + mov %rdx,%r15 jmp - nopw offset(%rax,%rax,1) - cmp $something,%rcx - jle - vmovss (%rax),%xmm0 + nopl offset(%rax) + jge + vmovss offset(%r10),%xmm7 + vmovss offset(%r10),%xmm5 + vmovss offset(%r10),%xmm6 + vmovss offset(%r10),%xmm4 + vmovss offset(%r10),%xmm3 + vmovss offset(%r10),%xmm31 + vmovss offset(%r10),%xmm30 + vmovss (%rsi),%xmm29 + vmovss offset(%rsi),%xmm28 + vmovss offset(%rsi),%xmm27 + vmovss offset(%rsi),%xmm26 + vmovss offset(%rsi),%xmm25 + vmovss offset(%rsi),%xmm24 + vmovss offset(%rsi),%xmm23 + vmovss offset(%rsi),%xmm22 + vmovss (%r9),%xmm21 + vmovss offset(%r9),%xmm20 + vmovss offset(%r9),%xmm19 + vmovss offset(%r9),%xmm18 + vmovss offset(%r9),%xmm17 + vmovss offset(%r9),%xmm16 + vmovss offset(%r9),%xmm15 + vmovss offset(%r9),%xmm14 + vmovss (%r8),%xmm13 + vmovss offset(%r8),%xmm12 + vmovss offset(%r8),%xmm11 + vmovss offset(%r8),%xmm10 + vmovss %xmm7,-offset(%rsp) + vmovss %xmm5,-offset(%rsp) + vmovss %xmm6,-offset(%rsp) + vmovss %xmm4,-offset(%rsp) + vmovss %xmm3,-offset(%rsp) + vmovss offset(%r8),%xmm9 + vmovss offset(%r8),%xmm7 + vmovss offset(%r8),%xmm8 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r11),%xmm7 + vmovss offset(%r8),%xmm6 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r11),%xmm7 + vmovss (%r11),%xmm5 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r11),%xmm7 + vmovss offset(%r11),%xmm4 + vmovss %xmm7,-offset(%rsp) + vmovss (%rbx),%xmm7 + vmovss offset(%r11),%xmm3 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss offset(%r11),%xmm2 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss offset(%r11),%xmm1 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%rbx),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 + vmovss %xmm7,-offset(%rsp) + vmovss offset(%r13),%xmm7 /usr/lib64/libopenblas_openmp.a/strsm_iutucopy_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/strsm_iutucopy_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/strsm_iutucopy_SKYLAKEX.o (objdump) @@ -2,78 +2,238 @@ /usr/lib64/libopenblas_openmp.a/strsm_iutucopy_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 41574156 41554154 4989fc55 534889d3 AWAVAUATI..USH.. - 0010 48897424 e048c1fe 0448894c 24e84889 H.t$.H...H.L$.H. - 0020 7424f048 85f60f8e a6010000 4c89c048 t$.H........L..H - 0030 c1e60448 f7d84989 fb4989ff 4989f648 ...H..I..I..I..H - 0040 8d448240 c5fa100d 00000000 4c894424 .D.@........L.D$ - 0050 f84d29c3 4d01c64c 89c7488d 2c8d0000 .M).M..L..H.,... - 0060 000049c1 e7064989 d54989c0 0f1f4000 ..I...I..I....@. - 0070 4c89e849 83c5404d 85e40f8e 23010000 L..I..@M....#... - 0080 4d89c248 89f94d29 ea48f7d9 4d01ca4c M..H..M).H..M..L - 0090 89cae9c4 00000066 0f1f8400 00000000 .......f........ - 00a0 4883f90f 0f8ece00 0000c5fa 1000c5fa H............... - 00b0 1102c5fa 104004c5 fa114204 c5fa1040 .....@....B....@ - 00c0 08c5fa11 4208c5fa 10400cc5 fa11420c ....B....@....B. - 00d0 c5fa1040 10c5fa11 4210c5fa 104014c5 ...@....B....@.. - 00e0 fa114214 c5fa1040 18c5fa11 4218c5fa ..B....@....B... - 00f0 10401cc5 fa11421c c5fa1040 20c5fa11 .@....B....@ ... - 0100 4220c5fa 104024c5 fa114224 c5fa1040 B ...@$...B$...@ - 0110 28c5fa11 4228c5fa 10402cc5 fa11422c (...B(...@,...B, - 0120 c5fa1040 30c5fa11 4230c5fa 104034c5 ...@0...B0...@4. - 0130 fa114234 c5fa1040 38c5fa11 4238c5fa ..B4...@8...B8.. - 0140 10403cc5 fa11423c 48ffc148 83c24048 .@<...B @@ -13,356 +14,160 @@ cmp $something,%rdx je vmovq offset(%rip),%xmm6 # - vxorpd %xmm2,%xmm2,%xmm2 + vxorpd %xmm1,%xmm1,%xmm1 shl $something,%rdx add $something,%rax - xor %ecx,%ecx - vmovsd %xmm2,%xmm2,%xmm3 + xor %esi,%esi + vmovsd %xmm1,%xmm1,%xmm3 vmovapd %xmm6,%xmm7 nopl offset(%rax) vmovsd -offset(%rax),%xmm0 - inc %rcx - vmovsd %xmm0,%xmm0,%xmm1 + inc %rsi + vmovsd %xmm0,%xmm0,%xmm2 vxorpd %xmm6,%xmm0,%xmm4 - vcmpnltsd %xmm0,%xmm2,%xmm0 - vblendvpd %xmm0,%xmm4,%xmm1,%xmm0 - vmovsd (%rax),%xmm1 + vcmpnltsd %xmm0,%xmm1,%xmm0 + vblendvpd %xmm0,%xmm4,%xmm2,%xmm0 + vmovsd (%rax),%xmm2 add %rdx,%rax - vmovsd %xmm1,%xmm1,%xmm4 - vxorpd %xmm7,%xmm1,%xmm5 - vcmpnltsd %xmm1,%xmm2,%xmm1 - vblendvpd %xmm1,%xmm5,%xmm4,%xmm1 - vaddsd %xmm1,%xmm0,%xmm0 + vmovsd %xmm2,%xmm2,%xmm4 + vxorpd %xmm7,%xmm2,%xmm5 + vcmpnltsd %xmm2,%xmm1,%xmm2 + vblendvpd %xmm2,%xmm5,%xmm4,%xmm2 + vaddsd %xmm2,%xmm0,%xmm0 vaddsd %xmm0,%xmm3,%xmm3 - cmp %rcx,%rdi + cmp %rsi,%rcx jg vmovsd %xmm3,%xmm3,%xmm0 ret - nop - vxorpd %xmm3,%xmm3,%xmm3 - vmovsd %xmm3,%xmm3,%xmm0 - ret - nopl offset(%rax) - add %rdi,%rdi - cmp $something,%rdi - jg - prefetcht0 (%rsi) - cmp $something,%rdi - jg - vxorpd %xmm3,%xmm3,%xmm3 - vmovapd %xmm3,%xmm1 - vmovapd %xmm3,%xmm2 - vmovapd %xmm3,%xmm0 - cmp $something,%rdi - jle - vmovddup offset(%rip),%xmm4 # - vandpd (%rax),%xmm4,%xmm7 - vandpd offset(%rax),%xmm4,%xmm6 - vandpd offset(%rax),%xmm4,%xmm5 - vandpd offset(%rax),%xmm4,%xmm4 - vaddpd %xmm7,%xmm0,%xmm0 - vaddpd %xmm6,%xmm2,%xmm2 - vaddpd %xmm5,%xmm1,%xmm1 - vaddpd %xmm4,%xmm3,%xmm3 - sub $something,%rdi - add $something,%rax - cmp $something,%rdi - jle - vmovddup offset(%rip),%xmm4 # - vandpd (%rax),%xmm4,%xmm5 - vandpd offset(%rax),%xmm4,%xmm4 - vaddpd %xmm5,%xmm0,%xmm0 - vaddpd %xmm4,%xmm2,%xmm2 - sub $something,%rdi - add $something,%rax - test %rdi,%rdi - je - vmovddup offset(%rip),%xmm4 # - vandpd (%rax),%xmm4,%xmm4 - vaddpd %xmm4,%xmm0,%xmm0 - vaddpd %xmm2,%xmm0,%xmm0 - vaddpd %xmm3,%xmm1,%xmm1 - vaddpd %xmm1,%xmm0,%xmm3 - vhaddpd %xmm3,%xmm3,%xmm3 - jmp - nopl offset(%rax) - cmp $something,%rdi - jg - vmovupd (%rsi),%zmm1 - vmovupd offset(%rsi),%zmm3 - vmovupd offset(%rsi),%zmm2 - vmovupd offset(%rsi),%zmm4 - cmp $something,%rdi - jle - vbroadcastsd offset(%rip),%zmm0 # - vxorpd %xmm5,%xmm5,%xmm5 - vandpd %zmm0,%zmm1,%zmm1 - vandpd %zmm0,%zmm3,%zmm3 - vandpd %zmm0,%zmm2,%zmm2 - vandpd %zmm0,%zmm4,%zmm4 - vaddpd %zmm5,%zmm1,%zmm1 - vaddpd %zmm5,%zmm3,%zmm3 - vaddpd %zmm5,%zmm2,%zmm2 - vaddpd %zmm5,%zmm4,%zmm4 - vandpd offset(%rsi),%zmm0,%zmm9 - vandpd offset(%rsi),%zmm0,%zmm8 - vandpd offset(%rsi),%zmm0,%zmm7 - vandpd offset(%rsi),%zmm0,%zmm6 - sub $something,%rdi - vaddpd %zmm9,%zmm1,%zmm1 - vaddpd %zmm8,%zmm3,%zmm3 - vaddpd %zmm7,%zmm2,%zmm2 - vaddpd %zmm6,%zmm4,%zmm4 - add $something,%rax - cmp $something,%rdi - jg - cmp $something,%rdi - jle - vandpd (%rax),%zmm0,%zmm6 - vandpd offset(%rax),%zmm0,%zmm5 - vaddpd %zmm6,%zmm1,%zmm1 - vaddpd %zmm5,%zmm3,%zmm3 - sub $something,%rdi - sub $something,%rax - cmp $something,%rdi - jle - vandpd (%rax),%zmm0,%zmm5 - sub $something,%rdi - vaddpd %zmm5,%zmm1,%zmm1 - add $something,%rax - test %rdi,%rdi - je - mov $something,%ecx - sub %edi,%ecx - mov $something,%edx - sarx %ecx,%edx,%edx - kmovb %edx,%k1 - vmovupd (%rax),%zmm5{%k1}{z} - vandpd %zmm0,%zmm5,%zmm0 - vaddpd %zmm0,%zmm1,%zmm1 - vaddpd %zmm3,%zmm1,%zmm1 - vaddpd %zmm4,%zmm2,%zmm2 - vaddpd %zmm2,%zmm1,%zmm1 - vextractf64x4 $something,%zmm1,%ymm0 - vaddpd %ymm1,%ymm0,%ymm0 - vextractf64x2 $something,%ymm0,%xmm3 - vaddpd %xmm0,%xmm3,%xmm3 - vhaddpd %xmm3,%xmm3,%xmm3 - vzeroupper - jmp - mov %rsi,%rcx - and $something,%ecx - mov $something,%edx - sub %rcx,%rdx - shr $something,%rdx - and $something,%edx + nopw offset(%rax,%rax,1) + mov %rdi,%rdx + and $something,%rdx je - mov $something,%esi - sub %edx,%esi - mov $something,%ecx - movslq %edx,%rdx - vbroadcastsd offset(%rip),%zmm0 # - sarx %esi,%ecx,%ecx - kmovb %ecx,%k2 - vmovupd (%rax),%zmm5{%k2}{z} - sub %rdx,%rdi - lea (%rax,%rdx,8),%rax + vmovq offset(%rip),%xmm13 # vxorpd %xmm1,%xmm1,%xmm1 - vandpd %zmm0,%zmm5,%zmm5 - sub $something,%rdi - vaddpd %zmm1,%zmm5,%zmm5 - vmovapd (%rax),%zmm6 - vmovapd offset(%rax),%zmm15 - vmovapd offset(%rax),%zmm14 - vmovapd offset(%rax),%zmm13 - vmovapd offset(%rax),%zmm4 - vmovapd offset(%rax),%zmm3 - vmovapd offset(%rax),%zmm2 - vmovapd offset(%rax),%zmm1 - add $something,%rax - cmp $something,%rdi /usr/lib64/libopenblas_openmp.a/zasum_k_SKYLAKEX.o differs in ELF section .text --- old /usr/lib64/libopenblas_openmp.a/zasum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/zasum_k_SKYLAKEX.o (objdump) @@ -2,135 +2,70 @@ /usr/lib64/libopenblas_openmp.a/zasum_k_SKYLAKEX.o: file format elf64-x86-64 Contents of section .text: - 0000 4889f048 85ff7e78 4885d27e 734883fa H..H..~xH..~sH.. - 0010 01747dc5 fa7e3500 000000c5 e957d248 .t}..~5......W.H - 0020 c1e20448 83c00831 c9c5eb10 dac5f928 ...H...1.......( - 0030 fe0f1f80 00000000 c5fb1040 f848ffc1 ...........@.H.. - 0040 c5fb10c8 c5f957e6 c5ebc2c0 05c4e371 ......W........q - 0050 4bc400c5 fb100848 01d0c5f3 10e1c5f1 K......H........ - 0060 57efc5eb c2c905c4 e3594bcd 10c5fb58 W........YK....X - 0070 c1c5e358 d84839cf 7fbec5e3 10c3c390 ...X.H9......... - 0080 c5e157db c5e310c3 c30f1f80 00000000 ..W............. - 0090 4801ff48 83ff1f0f 8fab0000 000f180e H..H............ - 00a0 4883ff0f 0f8fe004 0000c5e1 57dbc5f9 H...........W... - 00b0 28cbc5f9 28d3c5f9 28c34883 ff077e33 (...(...(.H...~3 - 00c0 c5fb1225 00000000 c5d95438 c5d95470 ...%......T8..Tp - 00d0 10c5d954 6820c5d9 546030c5 f958c7c5 ...Th ..T`0..X.. - 00e0 e958d6c5 f158cdc5 e158dc48 83ef0848 .X...X...X.H...H - 00f0 83c04048 83ff037e 21c5fb12 25000000 ..@H...~!...%... - 0100 00c5d954 28c5d954 6010c5f9 58c5c5e9 ...T(..T`...X... - 0110 58d44883 ef044883 c0204885 ff7410c5 X.H...H.. H..t.. - 0120 fb122500 000000c5 d95420c5 f958c4c5 ..%......T ..X.. - 0130 f958c2c5 f158cbc5 f958d9c5 e17cdbe9 .X...X...X...|.. - 0140 36ffffff 0f1f4000 4883ff7f 0f8f4c01 6.....@.H.....L. - 0150 000062f1 fd48100e 62f1fd48 105e0162 ..b..H..b..H.^.b - 0160 f1fd4810 560262f1 fd481066 034883ff ..H.V.b..H.f.H.. - 0170 3f0f8e78 04000062 f2fd4819 05000000 ?..x...b..H..... - 0180 00c5d157 ed62f1f5 4854c862 f1e54854 ...W.b..HT.b..HT - 0190 d862f1ed 4854d062 f1dd4854 e062f1f5 .b..HT.b..HT.b.. - 01a0 4858cd62 f1e54858 dd62f1ed 4858d562 HX.b..HX.b..HX.b - 01b0 f1dd4858 e56271fd 48544e04 6271fd48 ..HX.bq.HTN.bq.H - 01c0 54460562 f1fd4854 7e0662f1 fd485476 TF.b..HT~.b..HTv - 01d0 074883ef 4062d1f5 4858c962 d1e54858 .H..@b..HX.b..HX - 01e0 d862f1ed 4858d762 f1dd4858 e6480500 .b..HX.b..HX.H.. - 01f0 02000048 83ff1f0f 8f120400 004883ff ...H.........H.. - 0200 0f7e2162 f1fd4854 3062f1fd 48546801 .~!b..HT0b..HTh. - 0210 62f1f548 58ce62f1 e54858dd 4883ef10 b..HX.b..HX.H... - 0220 4883e880 4883ff07 7e1462f1 fd485428 H...H...~.b..HT( - 0230 4883ef08 62f1f548 58cd4883 c0404885 H...b..HX.H..@H. - 0240 ff7427b9 08000000 29f9baff 000000c4 .t'.....)....... - 0250 e272f7d2 c5f992ca 62f1fdc9 102862f1 .r......b....(b. - 0260 d54854c0 62f1f548 58c862f1 f54858cb .HT.b..HX.b..HX. - 0270 62f1ed48 58d462f1 f54858ca 62f3fd48 b..HX.b..HX.b..H - 0280 1bc801c5 fd58c162 f3fd2819 c301c5e1 .....X.b..(..... - 0290 58d8c5e1 7cdbc5f8 77e9dcfd ffff4889 X...|...w.....H. - 02a0 f183e13f ba400000 004829ca 48c1ea03 ...?.@...H).H... - 02b0 83e2070f 84980300 00be0800 000029d6 ..............). - 02c0 b9ff0000 004863d2 62f2fd48 19050000 .....Hc.b..H.... - 02d0 0000c4e2 4af7c9c5 f992d162 f1fdca10 ....J......b.... - 02e0 284829d7 488d04d0 c5f157c9 62f1d548 (H).H.....W.b..H - 02f0 54e84883 ef4062f1 d54858e9 62f1fd48 T.H..@b..HX.b..H - 0300 28306271 fd482878 016271fd 48287002 (0bq.H(x.bq.H(p. - 0310 6271fd48 28680362 f1fd4828 600462f1 bq.H(h.b..H(`.b. - 0320 fd482858 0562f1fd 48285006 62f1fd48 .H(X.b..H(P.b..H - 0330 28480748 05000200 004883ff 3f0f8e62 (H.H.....H..?..b - 0340 030000c4 411957e4 4889f948 89c26251 ....A.W.H..H..bQ - 0350 fd4828d4 6251fd48 28dc660f 1f440000 .H(.bQ.H(.f..D.. - 0360 62e1cd48 54c06271 854854c8 62718d48 b..HT.bq.HT.bq.H - 0370 54c062f1 954854f8 62f1fd40 58ed6251 T.b..HT.b..@X.bQ - 0380 b54858cb 6251ad48 58c062f1 9d4858ff .HX.bQ.HX.b..HX. - 0390 62f1dd48 54e062f1 e54854d8 62f1ed48 b..HT.b..HT.b..H - 03a0 54d062f1 f54854c8 4883e940 62f1d548 T.b..HT.H..@b..H - 03b0 58ec6271 b54858db 6271bd48 58d26271 X.bq.HX.bq.HX.bq - 03c0 c54858e1 62f1fd48 28326271 fd48287a .HX.b..H(2bq.H(z - 03d0 016271fd 48287202 6271fd48 286a0362 .bq.H(r.bq.H(j.b - 03e0 f1fd4828 620462f1 fd48285a 0562f1fd ..H(b.b..H(Z.b.. - 03f0 48285206 62f1fd48 284a0748 81c20002 H(R.b..H(J.H.... - 0400 00004883 f93f0f8f 54ffffff 488d77c0 ..H..?..T...H.w. - 0410 4889f148 c1e90648 89ca48f7 da48c1e2 H..H...H..H..H.. - 0420 064531c0 4883ff3f 490f4ed0 48ffc148 .E1.H..?I.N.H..H - 0430 01f248c1 e109be00 02000048 83ff3f48 ..H........H..?H - 0440 0f4ece48 01c862f1 cd4854f0 62718548 .N.H..b..HT.bq.H - 0450 54f86271 8d4854f0 62719548 54e862f1 T.bq.HT.bq.HT.b. - 0460 cd4858f5 6251a548 58df6251 ad4858d6 .HX.bQ.HX.bQ.HX. - 0470 62519d48 58e562f1 dd4854e0 62f1e548 bQ.HX.b..HT.b..H - 0480 54d862f1 ed4854d0 62f1f548 54c862f1 T.b..HT.b..HT.b. - 0490 cd4858e4 6271a548 58db6271 ad4858d2 .HX.bq.HX.bq.HX. - 04a0 62719d48 58e14883 fa1f7e3d 62f1fd48 bq.HX.H...~=b..H - 04b0 542862f1 fd485458 0162f1fd 48545002 T(b..HTX.b..HTP. - 04c0 62f1fd48 54480362 f1dd4858 e56271a5 b..HTH.b..HX.bq. - 04d0 4858db62 71ad4858 d262719d 4858e148 HX.bq.HX.bq.HX.H - 04e0 83ea2048 05000100 004883fa 0f7e2162 .. H.....H...~!b - 04f0 f1fd4854 1062f1fd 48544801 62f1dd48 ..HT.b..HTH.b..H - 0500 58e26271 a54858d9 4883ea10 4883e880 X.bq.HX.H...H... - 0510 4883fa07 7e1462f1 fd485408 4883ea08 H...~.b..HT.H... - 0520 62f1dd48 58e14883 c0404885 d27427b9 b..HX.H..@H..t'. - 0530 08000000 29d1baff 000000c4 e272f7d2 ....)........r.. - 0540 c5f992da 62f1fdcb 280862f1 f54854c0 ....b...(.b..HT. - 0550 62f1dd48 58e062d1 dd4858e3 6251ad48 b..HX.b..HX.bQ.H - 0560 58d462d1 dd4858e2 62f3fd48 1be001c5 X.b..HX.b..H.... - 0570 fd58c462 f3fd2819 c301c5e1 58d8c5e1 .X.b..(.....X... - 0580 7cdbc5f8 77e9f0fa ffffc5fb 121d0000 |...w........... - 0590 0000c5e1 5406c5e1 545610c5 e1544e20 ....T...TV...TN - 05a0 c5e15466 30c5d157 edc5f958 c5c5e958 ..Tf0..W...X...X - 05b0 d5c5f158 cdc5d958 e5c56154 4640c5e1 ...X...X..aTF@.. - 05c0 547e50c5 e1547660 c5e1545e 70c4c179 T~P..Tv`..T^p..y - 05d0 58c0c5e9 58d7c5f1 58cec5d9 58db4883 X...X...X...X.H. - 05e0 e8804883 ef100f18 4e40e9cb faffffc5 ..H.....N@...... - 05f0 d957e462 f2fd4819 05000000 0062f1fd .W.b..H......b.. - 0600 4828d462 f1fd4828 dc62f1fd 4828cc62 H(.b..H(.b..H(.b - 0610 71fd4854 0062f1fd 48547801 62f1fd48 q.HT.b..HTx.b..H - 0620 54700262 f1fd4854 680362d1 f54858c8 Tp.b..HTh.b..HX. - 0630 62f1e548 58df62f1 ed4858d6 62f1dd48 b..HX.b..HX.b..H - 0640 58e54883 ef204805 00010000 e9acfbff X.H.. H......... - 0650 ff62f1fd 48283662 71fd4828 7e016271 .b..H(6bq.H(~.bq - 0660 fd482876 026271fd 48286e03 62f1fd48 .H(v.bq.H(n.b..H - 0670 28660462 f1fd4828 5e0562f1 fd482856 (f.b..H(^.b..H(V - 0680 0662f1fd 48284e07 62f2fd48 19050000 .b..H(N.b..H.... - 0690 00004883 ef404805 00020000 c5d157ed ..H..@H.......W. - 06a0 e99efcff ffc44119 57e44889 fa6251fd ......A.W.H..bQ. - 06b0 4828d462 51fd4828 dce988fd ffff6690 H(.bQ.H(......f. - 06c0 4883ec08 4889ce4c 89c2e831 f9ffff48 H...H..L...1...H - 06d0 8b442418 c5fb1100 31c04883 c408c390 .D$.....1.H..... - 06e0 41564989 f6415549 89d54154 4989fc55 AVI..AUI..ATI..U - 06f0 534881ec 20040000 64488b04 25280000 SH.. ...dH..%(.. - 0700 00488984 24180400 0031c0e8 00000000 .H..$....1...... - 0710 83f8010f 84e70000 0089c5e8 00000000 ................ - 0720 85c00f85 d8000000 488b1d00 00000048 ........H......H - 0730 630b39cd 740a89ef e8000000 0048630b c.9.t........Hc. - 0740 4981fc10 2700000f 8eb30000 004d85ed I...'........M.. - 0750 0f8eaa00 00004c89 e048ba4b 598638d6 ......L..H.KY.8. - 0760 c56d3448 f7ea4c89 e048c1f8 3f48c1fa .m4H..L..H..?H.. - 0770 0b4829c2 4839ca48 0f4eca48 89cd4883 .H).H9.H.N.H..H. - 0780 f901747c 4883ec08 51488d05 30ffffff ..t|H...QH..0... - 0790 4d89f150 31c931d2 6a004c89 e6bf0310 M..P1.1.j.L..... - 07a0 0000488d 5c243053 6a006a00 41554c8d ..H.\$0Sj.j.AUL. - 07b0 442440e8 00000000 4883c440 4885ed7e D$@.....H..@H..~ - 07c0 6f48c1e5 04488d14 2b4889d8 c5f957c0 oH...H..+H....W. - 07d0 c5fb5800 4883c010 4839d075 f3488b84 ..X.H...H9.u.H.. - 07e0 24180400 0064482b 04252800 00007546 $....dH+.%(...uF - 07f0 4881c420 0400005b 5d415c41 5d415ec3 H.. ...[]A\A]A^. - 0800 488b8424 18040000 64482b04 25280000 H..$....dH+.%(.. - 0810 00752348 81c42004 00005b5d 4c89e741 .u#H.. ...[]L..A - 0820 5c4c89ea 415d4c89 f6415ee9 d0f7ffff \L..A]L..A^..... - 0830 c5f957c0 eba7e800 000000 ..W........ + 0000 4889f948 89f04885 ff0f8e81 02000048 H..H..H........H + 0010 85d20f8e 78020000 4883fa01 7472c5fa ....x...H...tr.. + 0020 7e350000 0000c5f1 57c948c1 e2044883 ~5......W.H...H. + 0030 c00831f6 c5f310d9 c5f928fe 0f1f4000 ..1.......(...@. + 0040 c5fb1040 f848ffc6 c5fb10d0 c5f957e6 ...@.H........W. + 0050 c5f3c2c0 05c4e369 4bc400c5 fb101048 .......iK......H + 0060 01d0c5eb 10e2c5e9 57efc5f3 c2d205c4 ........W....... + 0070 e3594bd5 20c5fb58 c2c5e358 d84839f1 .YK. ..X...X.H9. + 0080 7fbec5e3 10c3c366 0f1f8400 00000000 .......f........ + 0090 4889fa48 83e2f80f 84fc0100 00c57a7e H..H..........z~ + 00a0 2d000000 00c5f157 c931ffc5 7310d9c5 -......W.1..s... + 00b0 7310e1c5 f310e9c5 f310f962 c1fd0828 s..........b...( + 00c0 e562c1fd 0828dd62 c1fd0828 d562c1fd .b...(.b...(.b.. + 00d0 0828cd62 c1fd0828 c562c1fd 0828fd62 .(.b...(.b...(.b + 00e0 41fd0828 c50f1f00 c5fb1026 c5fb105e A..(.......&...^ + 00f0 08c5db10 c4c4c159 57d5c5f3 c2e405c5 .......YW....... + 0100 7b105620 c57b104e 28c4e379 4be240c5 {.V .{.N(..yK.@. + 0110 e310c362 b1e50857 d4c5f3c2 db05c5db ...b...W........ + 0120 58ff4883 c704c4e3 794bda30 c5fb1056 X.H.....yK.0...V + 0130 10c5e358 edc5eb10 c262b1ed 0857f3c5 ...X.....b...W.. + 0140 f3c2d205 4883c640 c4e3794b d620c5fb ....H..@..yK. .. + 0150 1046d8c4 416b58e4 c5fb10f0 6231fd08 .F..AkX.....b1.. + 0160 57c2c5f3 c2c005c4 c3494bc0 00c52b11 W........IK...+. + 0170 d66231ad 0857c1c4 4173c2d2 05c4417b .b1..W..As....A{ + 0180 58dbc443 494bd0a0 c53311ce 6231b508 X..CIK...3..b1.. + 0190 57c0c441 73c2c905 c4c14358 fac44349 W..As.....CX..CI + 01a0 4bc890c5 7b1046f0 c4c15358 e9c53b11 K...{.F...SX..;. + 01b0 c662a1bd 0857efc4 4173c2c0 056231d7 .b...W..As...b1. + 01c0 0010f5c4 43494bc6 80c5fb10 76f8c441 ....CIK.....v..A + 01d0 1b58e062 e1cf0810 ee6281cd 0857f0c5 .X.b.....b...W.. + 01e0 f3c2f605 6231d700 10f56231 cf0010fe ....b1....b1.... + 01f0 c4c3094b f760c523 58de4839 fa0f8fe5 ...K.`.#X.H9.... + 0200 feffffc5 c358fd48 ffca48c1 ea0248ff .....X.H..H...H. + 0210 c2c4c143 58fc4889 d648c1e6 0648c1e2 ...CX.H..H...H.. + 0220 02c4c143 58fb4801 f04839d1 7e75c5fa ...CX.H..H9.~u.. + 0230 7e350000 0000c5f3 10c1c579 28c66690 ~5.........y(.f. + 0240 c5fb1010 48ffc2c5 eb10dac5 e957e6c5 ....H........W.. + 0250 f3c2d205 4883c010 c4e3614b d420c5fb ....H.....aK. .. + 0260 1058f8c5 e310e3c4 c16157e8 c5f3c2db .X.......aW..... + 0270 05c4e359 4bdd30c5 eb58d3c5 fb58c248 ...YK.0..X...X.H + 0280 39d17fbc c5fb58df c5e310c3 c30f1f00 9.....X......... + 0290 c5e157db c5e310c3 c3c5f157 c9c5f310 ..W........W.... + 02a0 f9eb8bc5 f310c1eb db0f1f80 00000000 ................ + 02b0 4889ce4c 89c2e845 fdffff48 8b442410 H..L...E...H.D$. + 02c0 c5fb1100 31c0c366 0f1f8400 00000000 ....1..f........ + 02d0 41564989 f6415549 89d54154 4989fc55 AVI..AUI..ATI..U + 02e0 534881ec 20040000 64488b04 25280000 SH.. ...dH..%(.. + 02f0 00488984 24180400 0031c0e8 00000000 .H..$....1...... + 0300 83f8010f 84e70000 0089c5e8 00000000 ................ + 0310 85c00f85 d8000000 488b1d00 00000048 ........H......H + 0320 630b39cd 740a89ef e8000000 0048630b c.9.t........Hc. + 0330 4981fc10 2700000f 8eb30000 004d85ed I...'........M.. + 0340 0f8eaa00 00004c89 e048ba4b 598638d6 ......L..H.KY.8. + 0350 c56d3448 f7ea4c89 e048c1f8 3f48c1fa .m4H..L..H..?H.. + 0360 0b4829c2 4839ca48 0f4eca48 89cd4883 .H).H9.H.N.H..H. + 0370 f901747c 4883ec08 51488d05 30ffffff ..t|H...QH..0... + 0380 4d89f150 31c931d2 6a004c89 e6bf0310 M..P1.1.j.L..... + 0390 0000488d 5c243053 6a006a00 41554c8d ..H.\$0Sj.j.AUL. + 03a0 442440e8 00000000 4883c440 4885ed7e D$@.....H..@H..~ + 03b0 6f48c1e5 04488d14 2b4889d8 c5f957c0 oH...H..+H....W. + 03c0 c5fb5800 4883c010 4839d075 f3488b84 ..X.H...H9.u.H.. + 03d0 24180400 0064482b 04252800 00007546 $....dH+.%(...uF /usr/lib64/libopenblas_openmp.a/zasum_k_SKYLAKEX.o differs in ELF section .note.gnu.property --- old /usr/lib64/libopenblas_openmp.a/zasum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/zasum_k_SKYLAKEX.o (objdump) @@ -4,4 +4,4 @@ Contents of section .note.gnu.property: 0000 04000000 20000000 05000000 474e5500 .... .......GNU. 0010 020001c0 04000000 0d000000 00000000 ................ - 0020 010001c0 04000000 39080000 00000000 ........9....... + 0020 010001c0 04000000 39000000 00000000 ........9....... /usr/lib64/libopenblas_openmp.a/zasum_k_SKYLAKEX.o differs in ELF section .eh_frame --- old /usr/lib64/libopenblas_openmp.a/zasum_k_SKYLAKEX.o (objdump) +++ new /usr/lib64/libopenblas_openmp.a/zasum_k_SKYLAKEX.o (objdump) @@ -4,14 +4,13 @@ Contents of section .eh_frame: 0000 14000000 00000000 017a5200 01781001 .........zR..x.. 0010 1b0c0708 90010000 10000000 1c000000 ................ - 0020 00000000 be060000 00000000 14000000 ................ - 0030 30000000 00000000 1f000000 00440e10 0............D.. - 0040 5a0e0800 80000000 48000000 00000000 Z.......H....... - 0050 5b010000 00420e10 8e02450e 188d0345 [....B....E....E - 0060 0e208c04 440e2886 05410e30 8306470e . ..D.(..A.0..G. - 0070 d0080290 0ed80841 0ee0084b 0ee80846 .......A...K...F - 0080 0ef0084e 0ef80842 0e800942 0e880942 ...N...B...B...B - 0090 0e90094e 0ed0087b 0a0e3041 0e28410e ...N...{..0A.(A. - 00a0 20420e18 420e1042 0e08410b 5a0a0e30 B..B..B..A.Z..0 - 00b0 410e2841 0e20450e 18450e10 450e0845 A.(A. E..E..E..E - 00c0 0b000000 00000000 ........ + 0020 00000000 a9020000 00000000 10000000 ................ + 0030 30000000 00000000 17000000 00000000 0............... + 0040 7c000000 44000000 00000000 5b010000 |...D.......[... + 0050 00420e10 8e02450e 188d0345 0e208c04 .B....E....E. .. + 0060 440e2886 05410e30 8306470e d0080290 D.(..A.0..G..... + 0070 0ed80841 0ee0084b 0ee80846 0ef0084e ...A...K...F...N + 0080 0ef80842 0e800942 0e880942 0e90094e ...B...B...B...N + 0090 0ed0087b 0a0e3041 0e28410e 20420e18 ...{..0A.(A. B.. + 00a0 420e1042 0e08410b 5a0a0e30 410e2841 B..B..A.Z..0A.(A + 00b0 0e20450e 18450e10 450e0845 0b000000 . E..E..E..E.... overalldiffered=2 (not bit-by-bit identical) overall=1