mirror of
https://sourceware.org/git/glibc.git
synced 2024-12-03 10:21:05 +00:00
23fdf8178c
This implementation is based on __memset_power8 and integrates a lot of suggestions from Anton Blanchard. The biggest difference is that it makes extensive use of stxvl to alignment and tail code to avoid branches and small stores. It has three main execution paths: a) "Short lengths" for lengths up to 64 bytes, avoiding as many branches as possible. b) "General case" for larger lengths, it has an alignment section using stxvl to avoid branches, a 128 bytes loop and then a tail code, again using stxvl with few branches. c) "Zeroing cache blocks" for lengths from 256 bytes upwards and set value being zero. It is mostly the __memset_power8 code but the alignment phase was simplified because, at this point, address is already 16-bytes aligned and also changed to use vector stores. The tail code was also simplified to reuse the general case tail. All unaligned stores use stxvl instructions that do not generate alignment interrupts on POWER10, making it safe to use on caching-inhibited memory. On average, this implementation provides something around 30% improvement when compared to __memset_power8. Reviewed-by: Matheus Castanho <msc@linux.ibm.com> Reviewed-by: Tulio Magno Quites Machado Filho <tuliom@linux.ibm.com>
43 lines
1.9 KiB
Makefile
43 lines
1.9 KiB
Makefile
ifeq ($(subdir),string)
|
|
sysdep_routines += memcpy-power8-cached memcpy-power7 memcpy-a2 memcpy-power6 \
|
|
memcpy-cell memcpy-power4 memcpy-ppc64 \
|
|
memcmp-power8 memcmp-power7 memcmp-power4 memcmp-ppc64 \
|
|
memset-power7 memset-power6 memset-power4 \
|
|
memset-ppc64 memset-power8 \
|
|
mempcpy-power7 mempcpy-ppc64 \
|
|
memchr-power8 memchr-power7 memchr-ppc64 \
|
|
memrchr-power8 memrchr-power7 memrchr-ppc64 \
|
|
rawmemchr-power7 rawmemchr-ppc64 \
|
|
strlen-power7 strlen-ppc64 \
|
|
strnlen-power8 strnlen-power7 strnlen-ppc64 \
|
|
strcasecmp-power7 strcasecmp_l-power7 \
|
|
strncase-power7 strncase_l-power7 \
|
|
strncmp-power8 strncmp-power7 \
|
|
strncmp-power4 strncmp-ppc64 \
|
|
strchr-power8 strchr-power7 strchr-ppc64 \
|
|
strchrnul-power8 strchrnul-power7 strchrnul-ppc64 \
|
|
strcpy-power8 strcpy-power7 strcpy-ppc64 stpcpy-power8 \
|
|
stpcpy-power7 stpcpy-ppc64 \
|
|
strrchr-power8 strrchr-power7 strrchr-ppc64 \
|
|
strncat-power8 strncat-power7 strncat-ppc64 \
|
|
strncpy-power7 strncpy-ppc64 \
|
|
stpncpy-power8 stpncpy-power7 stpncpy-ppc64 \
|
|
strcmp-power8 strcmp-power7 strcmp-ppc64 \
|
|
strcat-power8 strcat-power7 strcat-ppc64 \
|
|
memmove-power7 memmove-ppc64 wordcopy-ppc64 bcopy-ppc64 \
|
|
strncpy-power8 strstr-power7 strstr-ppc64 \
|
|
strspn-power8 strspn-ppc64 strcspn-power8 strcspn-ppc64 \
|
|
strlen-power8 strcasestr-power8 strcasestr-ppc64 \
|
|
strcasecmp-ppc64 strcasecmp-power8 strncase-ppc64 \
|
|
strncase-power8
|
|
|
|
ifneq (,$(filter %le,$(config-machine)))
|
|
sysdep_routines += memcpy-power10 memmove-power10 memset-power10 \
|
|
strcmp-power9 strncmp-power9 strcpy-power9 stpcpy-power9 \
|
|
rawmemchr-power9 strlen-power9 strncpy-power9 stpncpy-power9 \
|
|
strlen-power10
|
|
endif
|
|
CFLAGS-strncase-power7.c += -mcpu=power7 -funroll-loops
|
|
CFLAGS-strncase_l-power7.c += -mcpu=power7 -funroll-loops
|
|
endif
|