mirror of
git://sourceware.org/git/glibc.git
synced 2025-01-24 12:25:35 +08:00
dc485ceb2a
Optimize strlen/strnlen/wcslen/wcsnlen with AVX2 to check 32 bytes with a single vector compare instruction. It is as fast as SSE2 versions for size <= 16 bytes and up to 1X faster for or size > 16 bytes on Haswell. Select AVX2 version on AVX2 machines where vzeroupper is preferred and AVX unaligned load is fast. NB: It uses TZCNT instead of BSF since TZCNT produces the same result as BSF for non-zero input. TZCNT is faster than BSF and is executed as BSF if machine doesn't support TZCNT. * sysdeps/x86_64/multiarch/Makefile (sysdep_routines): Add strlen-sse2, strnlen-sse2, strlen-avx2, strnlen-avx2, wcslen-sse2, wcslen-avx2 and wcsnlen-avx2. * sysdeps/x86_64/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list): Add tests for __strlen_avx2, __strlen_sse2, __strnlen_avx2, __strnlen_sse2, __wcslen_avx2, __wcslen_sse2 and __wcsnlen_avx2. * sysdeps/x86_64/multiarch/strlen-avx2.S: New file. * sysdeps/x86_64/multiarch/strlen-sse2.S: Likewise. * sysdeps/x86_64/multiarch/strlen.c: Likewise. * sysdeps/x86_64/multiarch/strnlen-avx2.S: Likewise. * sysdeps/x86_64/multiarch/strnlen-sse2.S: Likewise. * sysdeps/x86_64/multiarch/strnlen.c: Likewise. * sysdeps/x86_64/multiarch/wcslen-avx2.S: Likewise. * sysdeps/x86_64/multiarch/wcslen-sse2.S: Likewise. * sysdeps/x86_64/multiarch/wcslen.c: Likewise. * sysdeps/x86_64/multiarch/wcsnlen-avx2.S: Likewise. * sysdeps/x86_64/multiarch/wcsnlen.c (OPTIMIZE (avx2)): New. (IFUNC_SELECTOR): Return OPTIMIZE (avx2) on AVX2 machines where vzeroupper is preferred and AVX unaligned load is fast.
47 lines
1.4 KiB
Makefile
47 lines
1.4 KiB
Makefile
ifeq ($(subdir),csu)
|
|
tests += test-multiarch
|
|
endif
|
|
|
|
ifeq ($(subdir),string)
|
|
|
|
sysdep_routines += strncat-c stpncpy-c strncpy-c strcmp-ssse3 \
|
|
strcmp-sse2-unaligned strncmp-ssse3 \
|
|
memchr-sse2 rawmemchr-sse2 memchr-avx2 rawmemchr-avx2 \
|
|
memcmp-avx2-movbe \
|
|
memcmp-sse4 memcpy-ssse3 \
|
|
memmove-ssse3 \
|
|
memcpy-ssse3-back \
|
|
memmove-ssse3-back \
|
|
memmove-avx512-no-vzeroupper strcasecmp_l-ssse3 \
|
|
strlen-sse2 strnlen-sse2 strlen-avx2 strnlen-avx2 \
|
|
strncase_l-ssse3 strcat-ssse3 strncat-ssse3\
|
|
strcpy-ssse3 strncpy-ssse3 stpcpy-ssse3 stpncpy-ssse3 \
|
|
strcpy-sse2-unaligned strncpy-sse2-unaligned \
|
|
stpcpy-sse2-unaligned stpncpy-sse2-unaligned \
|
|
strcat-sse2-unaligned strncat-sse2-unaligned \
|
|
strchr-sse2-no-bsf memcmp-ssse3 strstr-sse2-unaligned \
|
|
strcspn-c strpbrk-c strspn-c varshift \
|
|
memset-avx512-no-vzeroupper \
|
|
memmove-avx-unaligned-erms \
|
|
memmove-avx512-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 ($(subdir),wcsmbs)
|
|
sysdep_routines += wmemcmp-sse4 wmemcmp-ssse3 wmemcmp-c \
|
|
wmemcmp-avx2-movbe \
|
|
wmemchr-sse2 wmemchr-avx2 \
|
|
wcscpy-ssse3 wcscpy-c \
|
|
wcsnlen-sse4_1 wcsnlen-c \
|
|
wcslen-sse2 wcslen-avx2 wcsnlen-avx2
|
|
endif
|
|
|
|
ifeq ($(subdir),debug)
|
|
sysdep_routines += wmemset_chk-nonshared
|
|
endif
|