glibc/sysdeps/x86_64/multiarch/Makefile
Ling Ma 5c74e47cd6 Add x86_64 memset optimized for AVX2
In this patch we take advantage of HSW memory bandwidth, manage to
reduce miss branch prediction by avoiding using branch instructions and
force destination to be aligned with avx & avx2 instruction.

The CPU2006 403.gcc benchmark indicates this patch improves performance
from 26% to 59%.

	* sysdeps/x86_64/multiarch/Makefile: Add memset-avx2.
	* sysdeps/x86_64/multiarch/memset-avx2.S: New file.
	* sysdeps/x86_64/multiarch/memset.S: Likewise.
	* sysdeps/x86_64/multiarch/memset_chk.S: Likewise.
	* sysdeps/x86_64/multiarch/rtld-memset.S: Likewise.
2014-06-19 15:14:08 -07:00

35 lines
1.1 KiB
Makefile

ifeq ($(subdir),csu)
aux += init-arch
tests += test-multiarch
gen-as-const-headers += ifunc-defines.sym
endif
ifeq ($(subdir),string)
sysdep_routines += strncat-c stpncpy-c strncpy-c strcmp-ssse3 \
strcmp-sse2-unaligned strncmp-ssse3 \
memcmp-sse4 memcpy-ssse3 \
memcpy-sse2-unaligned mempcpy-ssse3 \
memmove-ssse3 memcpy-ssse3-back mempcpy-ssse3-back \
memmove-ssse3-back strcasecmp_l-ssse3 \
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 \
memset-avx2
ifeq (yes,$(config-cflags-sse4))
sysdep_routines += strcspn-c strpbrk-c strspn-c varshift
CFLAGS-varshift.c += -msse4
CFLAGS-strcspn-c.c += -msse4
CFLAGS-strpbrk-c.c += -msse4
CFLAGS-strspn-c.c += -msse4
endif
endif
ifeq ($(subdir),wcsmbs)
sysdep_routines += wmemcmp-sse4 wmemcmp-ssse3 wmemcmp-c wcscpy-ssse3 wcscpy-c
endif