diff options
| author | H.J. Lu <hjl.tools@gmail.com> | 2021-03-05 07:15:03 -0800 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2021-03-29 07:40:17 -0700 |
| commit | 1b968b6b9b3aac702ac2f133e0dd16cfdbb415ee (patch) | |
| tree | 03329adc8a73b1fbfafad45ff41e8706c799d5c0 /sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S | |
| parent | 63ad43566f7a25d140dc723598aeb441ad657eed (diff) | |
| download | glibc-1b968b6b9b3aac702ac2f133e0dd16cfdbb415ee.tar.gz glibc-1b968b6b9b3aac702ac2f133e0dd16cfdbb415ee.tar.xz glibc-1b968b6b9b3aac702ac2f133e0dd16cfdbb415ee.zip | |
x86-64: Add memset family functions with 256-bit EVEX
Update ifunc-memset.h/ifunc-wmemset.h to select the function optimized with 256-bit EVEX instructions using YMM16-YMM31 registers to avoid RTM abort with usable AVX512VL and AVX512BW since VZEROUPPER isn't needed at function exit.
Diffstat (limited to 'sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S')
| -rw-r--r-- | sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S | 20 |
1 files changed, 14 insertions, 6 deletions
diff --git a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S index faa4085615..358ee4be12 100644 --- a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S +++ b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S @@ -34,6 +34,14 @@ # define WMEMSET_CHK_SYMBOL(p,s) WMEMSET_SYMBOL(p, s) #endif +#ifndef XMM0 +# define XMM0 xmm0 +#endif + +#ifndef YMM0 +# define YMM0 ymm0 +#endif + #ifndef VZEROUPPER # if VEC_SIZE > 16 # define VZEROUPPER vzeroupper @@ -67,7 +75,7 @@ ENTRY (__bzero) mov %RDI_LP, %RAX_LP /* Set return value. */ mov %RSI_LP, %RDX_LP /* Set n. */ - pxor %xmm0, %xmm0 + pxor %XMM0, %XMM0 jmp L(entry_from_bzero) END (__bzero) weak_alias (__bzero, bzero) @@ -223,7 +231,7 @@ L(less_vec): cmpb $16, %dl jae L(between_16_31) # endif - MOVQ %xmm0, %rcx + MOVQ %XMM0, %rcx cmpb $8, %dl jae L(between_8_15) cmpb $4, %dl @@ -238,16 +246,16 @@ L(less_vec): # if VEC_SIZE > 32 /* From 32 to 63. No branch when size == 32. */ L(between_32_63): - vmovdqu %ymm0, -32(%rdi,%rdx) - vmovdqu %ymm0, (%rdi) + VMOVU %YMM0, -32(%rdi,%rdx) + VMOVU %YMM0, (%rdi) VZEROUPPER ret # endif # if VEC_SIZE > 16 /* From 16 to 31. No branch when size == 16. */ L(between_16_31): - vmovdqu %xmm0, -16(%rdi,%rdx) - vmovdqu %xmm0, (%rdi) + VMOVU %XMM0, -16(%rdi,%rdx) + VMOVU %XMM0, (%rdi) VZEROUPPER ret # endif |