mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-27 07:20:11 +00:00
1a153e47fc
Optimize x86-64 strcat/strncat, strcpy/strncpy and stpcpy/stpncpy with AVX2.
It uses vector comparison as much as possible. In general, the larger the
source string, the greater performance gain observed, reaching speedups of
1.6x compared to SSE2 unaligned routines. Select AVX2 strcat/strncat,
strcpy/strncpy and stpcpy/stpncpy on AVX2 machines where vzeroupper is
preferred and AVX unaligned load is fast.
* sysdeps/x86_64/multiarch/Makefile (sysdep_routines): Add
strcat-avx2, strncat-avx2, strcpy-avx2, strncpy-avx2,
stpcpy-avx2 and stpncpy-avx2.
* sysdeps/x86_64/multiarch/ifunc-impl-list.c:
(__libc_ifunc_impl_list): Add tests for __strcat_avx2,
__strncat_avx2, __strcpy_avx2, __strncpy_avx2, __stpcpy_avx2
and __stpncpy_avx2.
* sysdeps/x86_64/multiarch/{ifunc-unaligned-ssse3.h =>
ifunc-strcpy.h}: rename header for a more generic name.
* sysdeps/x86_64/multiarch/ifunc-strcpy.h:
(IFUNC_SELECTOR): Return OPTIMIZE (avx2) on AVX 2 machines if
AVX unaligned load is fast and vzeroupper is preferred.
* sysdeps/x86_64/multiarch/stpcpy-avx2.S: New file
* sysdeps/x86_64/multiarch/stpncpy-avx2.S: Likewise
* sysdeps/x86_64/multiarch/strcat-avx2.S: Likewise
* sysdeps/x86_64/multiarch/strcpy-avx2.S: Likewise
* sysdeps/x86_64/multiarch/strncat-avx2.S: Likewise
* sysdeps/x86_64/multiarch/strncpy-avx2.S: Likewise
71 lines
2.3 KiB
Makefile
71 lines
2.3 KiB
Makefile
ifeq ($(subdir),csu)
|
|
tests += test-multiarch
|
|
endif
|
|
|
|
ifeq ($(subdir),string)
|
|
|
|
sysdep_routines += strncat-c stpncpy-c strncpy-c \
|
|
strcmp-sse2 strcmp-sse2-unaligned strcmp-ssse3 \
|
|
strcmp-sse4_2 strcmp-avx2 \
|
|
strncmp-sse2 strncmp-ssse3 strncmp-sse4_2 strncmp-avx2 \
|
|
memchr-sse2 rawmemchr-sse2 memchr-avx2 rawmemchr-avx2 \
|
|
memrchr-sse2 memrchr-avx2 \
|
|
memcmp-sse2 \
|
|
memcmp-avx2-movbe \
|
|
memcmp-sse4 memcpy-ssse3 \
|
|
memmove-ssse3 \
|
|
memcpy-ssse3-back \
|
|
memmove-ssse3-back \
|
|
memmove-avx512-no-vzeroupper \
|
|
strcasecmp_l-sse2 strcasecmp_l-ssse3 \
|
|
strcasecmp_l-sse4_2 strcasecmp_l-avx \
|
|
strncase_l-sse2 strncase_l-ssse3 \
|
|
strncase_l-sse4_2 strncase_l-avx \
|
|
strchr-sse2 strchrnul-sse2 strchr-avx2 strchrnul-avx2 \
|
|
strrchr-sse2 strrchr-avx2 \
|
|
strlen-sse2 strnlen-sse2 strlen-avx2 strnlen-avx2 \
|
|
strcat-avx2 strncat-avx2 \
|
|
strcat-ssse3 strncat-ssse3\
|
|
strcpy-avx2 strncpy-avx2 \
|
|
strcpy-sse2 stpcpy-sse2 \
|
|
strcpy-ssse3 strncpy-ssse3 stpcpy-ssse3 stpncpy-ssse3 \
|
|
strcpy-sse2-unaligned strncpy-sse2-unaligned \
|
|
stpcpy-sse2-unaligned stpncpy-sse2-unaligned \
|
|
stpcpy-avx2 stpncpy-avx2 \
|
|
strcat-sse2 \
|
|
strcat-sse2-unaligned strncat-sse2-unaligned \
|
|
strchr-sse2-no-bsf memcmp-ssse3 strstr-sse2-unaligned \
|
|
strcspn-sse2 strpbrk-sse2 strspn-sse2 \
|
|
strcspn-c strpbrk-c strspn-c varshift \
|
|
memset-avx512-no-vzeroupper \
|
|
memmove-sse2-unaligned-erms \
|
|
memmove-avx-unaligned-erms \
|
|
memmove-avx512-unaligned-erms \
|
|
memset-sse2-unaligned-erms \
|
|
memset-avx2-unaligned-erms \
|
|
memset-avx512-unaligned-erms
|
|
CFLAGS-varshift.c += -msse4
|
|
CFLAGS-strcspn-c.c += -msse4
|
|
CFLAGS-strpbrk-c.c += -msse4
|
|
CFLAGS-strspn-c.c += -msse4
|
|
endif
|
|
|
|
ifeq ($(subdir),wcsmbs)
|
|
sysdep_routines += wmemcmp-sse4 wmemcmp-ssse3 wmemcmp-c \
|
|
wmemcmp-avx2-movbe \
|
|
wmemchr-sse2 wmemchr-avx2 \
|
|
wcscmp-sse2 wcscmp-avx2 \
|
|
wcsncmp-sse2 wcsncmp-avx2 \
|
|
wcscpy-ssse3 wcscpy-c \
|
|
wcschr-sse2 wcschr-avx2 \
|
|
wcsrchr-sse2 wcsrchr-avx2 \
|
|
wcsnlen-sse4_1 wcsnlen-c \
|
|
wcslen-sse2 wcslen-avx2 wcsnlen-avx2
|
|
endif
|
|
|
|
ifeq ($(subdir),debug)
|
|
sysdep_routines += memcpy_chk-nonshared mempcpy_chk-nonshared \
|
|
memmove_chk-nonshared memset_chk-nonshared \
|
|
wmemset_chk-nonshared
|
|
endif
|