glibc/sysdeps/x86_64/multiarch/Makefile
H.J. Lu 3d9f171bfb x86-64: Optimize bzero
memset with zero as the value to set is by far the majority value (99%+
for Python3 and GCC).

bzero can be slightly more optimized for this case by using a zero-idiom
xor for broadcasting the set value to a register (vector or GPR).

Co-developed-by: Noah Goldstein <goldstein.w.n@gmail.com>
2022-02-08 15:58:56 -08:00

191 lines
3.6 KiB
Makefile

ifeq ($(subdir),string)
sysdep_routines += \
bzero \
memchr-avx2 \
memchr-avx2-rtm \
memchr-evex \
memchr-evex-rtm \
memchr-sse2 \
memcmp-avx2-movbe \
memcmp-avx2-movbe-rtm \
memcmp-evex-movbe \
memcmp-sse2 \
memcmp-sse4 \
memcmp-ssse3 \
memcmpeq-avx2 \
memcmpeq-avx2-rtm \
memcmpeq-evex \
memcmpeq-sse2 \
memcpy-ssse3 \
memcpy-ssse3-back \
memmove-avx-unaligned-erms \
memmove-avx-unaligned-erms-rtm \
memmove-avx512-no-vzeroupper \
memmove-avx512-unaligned-erms \
memmove-evex-unaligned-erms \
memmove-sse2-unaligned-erms \
memmove-ssse3 \
memmove-ssse3-back \
memrchr-avx2 \
memrchr-avx2-rtm \
memrchr-evex \
memrchr-sse2 \
memset-avx2-unaligned-erms \
memset-avx2-unaligned-erms-rtm \
memset-avx512-no-vzeroupper \
memset-avx512-unaligned-erms \
memset-evex-unaligned-erms \
memset-sse2-unaligned-erms \
rawmemchr-avx2 \
rawmemchr-avx2-rtm \
rawmemchr-evex \
rawmemchr-evex-rtm \
rawmemchr-sse2 \
stpcpy-avx2 \
stpcpy-avx2-rtm \
stpcpy-evex \
stpcpy-sse2 \
stpcpy-sse2-unaligned \
stpcpy-ssse3 \
stpncpy-avx2 \
stpncpy-avx2-rtm \
stpncpy-c \
stpncpy-evex \
stpncpy-sse2-unaligned \
stpncpy-ssse3 \
strcasecmp_l-avx \
strcasecmp_l-sse2 \
strcasecmp_l-sse4_2 \
strcasecmp_l-ssse3 \
strcat-avx2 \
strcat-avx2-rtm \
strcat-evex \
strcat-sse2 \
strcat-sse2-unaligned \
strcat-ssse3 \
strchr-avx2 \
strchr-avx2-rtm \
strchr-evex \
strchr-sse2 \
strchr-sse2-no-bsf \
strchrnul-avx2 \
strchrnul-avx2-rtm \
strchrnul-evex \
strchrnul-sse2 \
strcmp-avx2 \
strcmp-avx2-rtm \
strcmp-evex \
strcmp-sse2 \
strcmp-sse2-unaligned \
strcmp-sse4_2 \
strcmp-ssse3 \
strcpy-avx2 \
strcpy-avx2-rtm \
strcpy-evex \
strcpy-sse2 \
strcpy-sse2-unaligned \
strcpy-ssse3 \
strcspn-c \
strcspn-sse2 \
strlen-avx2 \
strlen-avx2-rtm \
strlen-evex \
strlen-sse2 \
strncase_l-avx \
strncase_l-sse2 \
strncase_l-sse4_2 \
strncase_l-ssse3 \
strncat-avx2 \
strncat-avx2-rtm \
strncat-c \
strncat-evex \
strncat-sse2-unaligned \
strncat-ssse3 \
strncmp-avx2 \
strncmp-avx2-rtm \
strncmp-evex \
strncmp-sse2 \
strncmp-sse4_2 \
strncmp-ssse3 \
strncpy-avx2 \
strncpy-avx2-rtm \
strncpy-c \
strncpy-evex \
strncpy-sse2-unaligned \
strncpy-ssse3 \
strnlen-avx2 \
strnlen-avx2-rtm \
strnlen-evex \
strnlen-sse2 \
strpbrk-c \
strpbrk-sse2 \
strrchr-avx2 \
strrchr-avx2-rtm \
strrchr-evex \
strrchr-sse2 \
strspn-c \
strspn-sse2 \
strstr-sse2-unaligned \
varshift \
# sysdep_routines
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 += \
wcschr-avx2 \
wcschr-avx2-rtm \
wcschr-evex \
wcschr-sse2 \
wcscmp-avx2 \
wcscmp-avx2-rtm \
wcscmp-evex \
wcscmp-sse2 \
wcscpy-c \
wcscpy-ssse3 \
wcslen-avx2 \
wcslen-avx2-rtm \
wcslen-evex \
wcslen-sse2 \
wcslen-sse4_1 \
wcsncmp-avx2 \
wcsncmp-avx2-rtm \
wcsncmp-evex \
wcsncmp-sse2 \
wcsnlen-avx2 \
wcsnlen-avx2-rtm \
wcsnlen-c \
wcsnlen-evex \
wcsnlen-sse4_1 \
wcsrchr-avx2 \
wcsrchr-avx2-rtm \
wcsrchr-evex \
wcsrchr-sse2 \
wmemchr-avx2 \
wmemchr-avx2-rtm \
wmemchr-evex \
wmemchr-evex-rtm \
wmemchr-sse2 \
wmemcmp-avx2-movbe \
wmemcmp-avx2-movbe-rtm \
wmemcmp-c \
wmemcmp-evex-movbe \
wmemcmp-sse4 \
wmemcmp-ssse3 \
# sysdep_routines
endif
ifeq ($(subdir),debug)
sysdep_routines += \
memcpy_chk-nonshared \
memmove_chk-nonshared \
mempcpy_chk-nonshared \
memset_chk-nonshared \
wmemset_chk-nonshared \
# sysdep_routines
endif