diff options
| author | Noah Goldstein <goldstein.w.n@gmail.com> | 2021-04-19 19:36:07 -0400 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2021-04-19 18:03:49 -0700 |
| commit | aaa23c35071537e2dcf5807e956802ed215210aa (patch) | |
| tree | b8ae81bc8ee47ef38abe7a0a8e6907559acae98c /sysdeps/x86_64/multiarch/ifunc-impl-list.c | |
| parent | 4ba65586847751372520a36757c17f114588794e (diff) | |
| download | glibc-aaa23c35071537e2dcf5807e956802ed215210aa.tar.gz glibc-aaa23c35071537e2dcf5807e956802ed215210aa.tar.xz glibc-aaa23c35071537e2dcf5807e956802ed215210aa.zip | |
x86: Optimize strlen-avx2.S
No bug. This commit optimizes strlen-avx2.S. The optimizations are mostly small things but they add up to roughly 10-30% performance improvement for strlen. The results for strnlen are bit more ambiguous. test-strlen, test-strnlen, test-wcslen, and test-wcsnlen are all passing. Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Diffstat (limited to 'sysdeps/x86_64/multiarch/ifunc-impl-list.c')
| -rw-r--r-- | sysdeps/x86_64/multiarch/ifunc-impl-list.c | 16 |
1 files changed, 12 insertions, 4 deletions
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c index c377cab629..651b32908e 100644 --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c @@ -293,10 +293,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, /* Support sysdeps/x86_64/multiarch/strlen.c. */ IFUNC_IMPL (i, name, strlen, IFUNC_IMPL_ADD (array, i, strlen, - CPU_FEATURE_USABLE (AVX2), + (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2)), __strlen_avx2) IFUNC_IMPL_ADD (array, i, strlen, (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (RTM)), __strlen_avx2_rtm) IFUNC_IMPL_ADD (array, i, strlen, @@ -309,10 +311,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, /* Support sysdeps/x86_64/multiarch/strnlen.c. */ IFUNC_IMPL (i, name, strnlen, IFUNC_IMPL_ADD (array, i, strnlen, - CPU_FEATURE_USABLE (AVX2), + (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2)), __strnlen_avx2) IFUNC_IMPL_ADD (array, i, strnlen, (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (RTM)), __strnlen_avx2_rtm) IFUNC_IMPL_ADD (array, i, strnlen, @@ -654,10 +658,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, /* Support sysdeps/x86_64/multiarch/wcslen.c. */ IFUNC_IMPL (i, name, wcslen, IFUNC_IMPL_ADD (array, i, wcslen, - CPU_FEATURE_USABLE (AVX2), + (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2)), __wcslen_avx2) IFUNC_IMPL_ADD (array, i, wcslen, (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (RTM)), __wcslen_avx2_rtm) IFUNC_IMPL_ADD (array, i, wcslen, @@ -670,10 +676,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, /* Support sysdeps/x86_64/multiarch/wcsnlen.c. */ IFUNC_IMPL (i, name, wcsnlen, IFUNC_IMPL_ADD (array, i, wcsnlen, - CPU_FEATURE_USABLE (AVX2), + (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2)), __wcsnlen_avx2) IFUNC_IMPL_ADD (array, i, wcsnlen, (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (RTM)), __wcsnlen_avx2_rtm) IFUNC_IMPL_ADD (array, i, wcsnlen, |