2016-04-03 21:32:20 +00:00
|
|
|
#if IS_IN (libc)
|
|
|
|
|
# define VEC_SIZE 16
|
|
|
|
|
# define VEC(i) xmm##i
|
2016-04-05 12:19:05 +00:00
|
|
|
/* Don't use movups and movaps since it will get larger nop paddings
|
|
|
|
|
for alignment. */
|
2016-04-03 21:32:20 +00:00
|
|
|
# define VMOVU movdqu
|
|
|
|
|
# define VMOVA movdqa
|
Add x86-64 memset with unaligned store and rep stosb
Implement x86-64 memset with unaligned store and rep movsb. Support
16-byte, 32-byte and 64-byte vector register sizes. A single file
provides 2 implementations of memset, one with rep stosb and the other
without rep stosb. They share the same codes when size is between 2
times of vector register size and REP_STOSB_THRESHOLD which defaults
to 2KB.
Key features:
1. Use overlapping store to avoid branch.
2. For size <= 4 times of vector register size, fully unroll the loop.
3. For size > 4 times of vector register size, store 4 times of vector
register size at a time.
[BZ #19881]
* sysdeps/x86_64/multiarch/Makefile (sysdep_routines): Add
memset-sse2-unaligned-erms, memset-avx2-unaligned-erms and
memset-avx512-unaligned-erms.
* sysdeps/x86_64/multiarch/ifunc-impl-list.c
(__libc_ifunc_impl_list): Test __memset_chk_sse2_unaligned,
__memset_chk_sse2_unaligned_erms, __memset_chk_avx2_unaligned,
__memset_chk_avx2_unaligned_erms, __memset_chk_avx512_unaligned,
__memset_chk_avx512_unaligned_erms, __memset_sse2_unaligned,
__memset_sse2_unaligned_erms, __memset_erms,
__memset_avx2_unaligned, __memset_avx2_unaligned_erms,
__memset_avx512_unaligned_erms and __memset_avx512_unaligned.
* sysdeps/x86_64/multiarch/memset-avx2-unaligned-erms.S: New
file.
* sysdeps/x86_64/multiarch/memset-avx512-unaligned-erms.S:
Likewise.
* sysdeps/x86_64/multiarch/memset-sse2-unaligned-erms.S:
Likewise.
* sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S:
Likewise.
2016-03-31 17:05:51 +00:00
|
|
|
|
2016-04-03 21:32:20 +00:00
|
|
|
# define VDUP_TO_VEC0_AND_SET_RETURN(d, r) \
|
Add x86-64 memset with unaligned store and rep stosb
Implement x86-64 memset with unaligned store and rep movsb. Support
16-byte, 32-byte and 64-byte vector register sizes. A single file
provides 2 implementations of memset, one with rep stosb and the other
without rep stosb. They share the same codes when size is between 2
times of vector register size and REP_STOSB_THRESHOLD which defaults
to 2KB.
Key features:
1. Use overlapping store to avoid branch.
2. For size <= 4 times of vector register size, fully unroll the loop.
3. For size > 4 times of vector register size, store 4 times of vector
register size at a time.
[BZ #19881]
* sysdeps/x86_64/multiarch/Makefile (sysdep_routines): Add
memset-sse2-unaligned-erms, memset-avx2-unaligned-erms and
memset-avx512-unaligned-erms.
* sysdeps/x86_64/multiarch/ifunc-impl-list.c
(__libc_ifunc_impl_list): Test __memset_chk_sse2_unaligned,
__memset_chk_sse2_unaligned_erms, __memset_chk_avx2_unaligned,
__memset_chk_avx2_unaligned_erms, __memset_chk_avx512_unaligned,
__memset_chk_avx512_unaligned_erms, __memset_sse2_unaligned,
__memset_sse2_unaligned_erms, __memset_erms,
__memset_avx2_unaligned, __memset_avx2_unaligned_erms,
__memset_avx512_unaligned_erms and __memset_avx512_unaligned.
* sysdeps/x86_64/multiarch/memset-avx2-unaligned-erms.S: New
file.
* sysdeps/x86_64/multiarch/memset-avx512-unaligned-erms.S:
Likewise.
* sysdeps/x86_64/multiarch/memset-sse2-unaligned-erms.S:
Likewise.
* sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S:
Likewise.
2016-03-31 17:05:51 +00:00
|
|
|
movd d, %xmm0; \
|
|
|
|
|
movq r, %rax; \
|
|
|
|
|
punpcklbw %xmm0, %xmm0; \
|
|
|
|
|
punpcklwd %xmm0, %xmm0; \
|
|
|
|
|
pshufd $0, %xmm0, %xmm0
|
|
|
|
|
|
2016-04-03 21:32:20 +00:00
|
|
|
# define SECTION(p) p
|
|
|
|
|
# define MEMSET_SYMBOL(p,s) p##_sse2_##s
|
Add x86-64 memset with unaligned store and rep stosb
Implement x86-64 memset with unaligned store and rep movsb. Support
16-byte, 32-byte and 64-byte vector register sizes. A single file
provides 2 implementations of memset, one with rep stosb and the other
without rep stosb. They share the same codes when size is between 2
times of vector register size and REP_STOSB_THRESHOLD which defaults
to 2KB.
Key features:
1. Use overlapping store to avoid branch.
2. For size <= 4 times of vector register size, fully unroll the loop.
3. For size > 4 times of vector register size, store 4 times of vector
register size at a time.
[BZ #19881]
* sysdeps/x86_64/multiarch/Makefile (sysdep_routines): Add
memset-sse2-unaligned-erms, memset-avx2-unaligned-erms and
memset-avx512-unaligned-erms.
* sysdeps/x86_64/multiarch/ifunc-impl-list.c
(__libc_ifunc_impl_list): Test __memset_chk_sse2_unaligned,
__memset_chk_sse2_unaligned_erms, __memset_chk_avx2_unaligned,
__memset_chk_avx2_unaligned_erms, __memset_chk_avx512_unaligned,
__memset_chk_avx512_unaligned_erms, __memset_sse2_unaligned,
__memset_sse2_unaligned_erms, __memset_erms,
__memset_avx2_unaligned, __memset_avx2_unaligned_erms,
__memset_avx512_unaligned_erms and __memset_avx512_unaligned.
* sysdeps/x86_64/multiarch/memset-avx2-unaligned-erms.S: New
file.
* sysdeps/x86_64/multiarch/memset-avx512-unaligned-erms.S:
Likewise.
* sysdeps/x86_64/multiarch/memset-sse2-unaligned-erms.S:
Likewise.
* sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S:
Likewise.
2016-03-31 17:05:51 +00:00
|
|
|
|
2016-04-03 21:32:20 +00:00
|
|
|
# include "memset-vec-unaligned-erms.S"
|
|
|
|
|
#endif
|