glibc/sysdeps/powerpc/powerpc64/multiarch/Makefile
Amrita H S 23f0d81608 powerpc: Optimized strncmp for power10
This patch is based on __strcmp_power10.

Improvements from __strncmp_power9:

    1. Uses new POWER10 instructions
       - This code uses lxvp to decrease contention on load
	 by loading 32 bytes per instruction.

    2. Performance implication
       - This version has around 38% better performance on average.
       - Minor performance regression is seen for few small sizes
	 and specific combination of alignments.

Signed-off-by: Amrita H S <amritahs@linux.ibm.com>
Reviewed-by: Peter Bergner <bergner@linux.ibm.com>
2024-05-06 09:01:29 -05:00

46 lines
1.9 KiB
Makefile

ifeq ($(subdir),string)
sysdep_routines += memcpy-power8-cached memcpy-power7 memcpy-a2 memcpy-power6 \
memcpy-cell memcpy-power4 memcpy-ppc64 \
memcmp-power8 memcmp-power7 memcmp-power4 memcmp-ppc64 \
memset-power7 memset-power6 memset-power4 \
memset-ppc64 memset-power8 \
mempcpy-power7 mempcpy-ppc64 \
memchr-power8 memchr-power7 memchr-ppc64 \
memrchr-power8 memrchr-power7 memrchr-ppc64 \
rawmemchr-power7 rawmemchr-ppc64 \
strlen-power7 strlen-ppc64 \
strnlen-power8 strnlen-power7 strnlen-ppc64 \
strcasecmp-power7 strcasecmp_l-power7 \
strncase-power7 strncase_l-power7 \
strncmp-power8 strncmp-ppc64 \
strchr-power8 strchr-power7 strchr-ppc64 \
strchrnul-power8 strchrnul-power7 strchrnul-ppc64 \
strcpy-power8 strcpy-power7 strcpy-ppc64 stpcpy-power8 \
stpcpy-power7 stpcpy-ppc64 \
strrchr-power8 strrchr-power7 strrchr-ppc64 \
strncat-power8 strncat-power7 strncat-ppc64 \
strncpy-power7 strncpy-ppc64 \
stpncpy-power8 stpncpy-power7 stpncpy-ppc64 \
strcmp-power8 strcmp-power7 strcmp-ppc64 \
strcat-power8 strcat-power7 strcat-ppc64 \
memmove-power7 memmove-ppc64 wordcopy-ppc64 \
strncpy-power8 \
strspn-power8 strspn-ppc64 strcspn-power8 strcspn-ppc64 \
strlen-power8 \
strcasecmp-ppc64 strcasecmp-power8 strncase-ppc64 \
strncase-power8
ifneq (,$(filter %le,$(config-machine)))
sysdep_routines += memchr-power10 memcmp-power10 memcpy-power10 \
memmove-power10 memset-power10 rawmemchr-power9 \
rawmemchr-power10 strcmp-power9 strcmp-power10 \
strncmp-power9 strncmp-power10 strcpy-power9 stpcpy-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
# Called during static initialization
CFLAGS-strncmp-ppc64.c += $(no-stack-protector)