diff options
author | H.J. Lu <hjl.tools@gmail.com> | 2021-03-05 06:24:52 -0800 |
---|---|---|
committer | H.J. Lu <hjl.tools@gmail.com> | 2021-03-29 07:40:17 -0700 |
commit | 1fd8c163a83d96ace1ff78fa6bac7aee084f6f77 (patch) | |
tree | f10a0556c0e7a8d1a97e4702568c4e88869ac168 /sysdeps/x86_64/multiarch/strcmp.c | |
parent | 1da50d4bda07f04135dca39f40e79fc9eabed1f8 (diff) | |
download | glibc-1fd8c163a83d96ace1ff78fa6bac7aee084f6f77.tar.gz glibc-1fd8c163a83d96ace1ff78fa6bac7aee084f6f77.tar.xz glibc-1fd8c163a83d96ace1ff78fa6bac7aee084f6f77.zip |
x86-64: Add ifunc-avx2.h functions with 256-bit EVEX
Update ifunc-avx2.h, strchr.c, strcmp.c, strncmp.c and wcsnlen.c to select the function optimized with 256-bit EVEX instructions using YMM16-YMM31 registers to avoid RTM abort with usable AVX512VL, AVX512BW and BMI2 since VZEROUPPER isn't needed at function exit. For strcmp/strncmp, prefer AVX2 strcmp/strncmp if Prefer_AVX2_STRCMP is set.
Diffstat (limited to 'sysdeps/x86_64/multiarch/strcmp.c')
-rw-r--r-- | sysdeps/x86_64/multiarch/strcmp.c | 15 |
1 files changed, 12 insertions, 3 deletions
diff --git a/sysdeps/x86_64/multiarch/strcmp.c b/sysdeps/x86_64/multiarch/strcmp.c index 6a9dca4389..1df75690d0 100644 --- a/sysdeps/x86_64/multiarch/strcmp.c +++ b/sysdeps/x86_64/multiarch/strcmp.c @@ -30,16 +30,25 @@ extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2) attribute_hidden; extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2_unaligned) attribute_hidden; extern __typeof (REDIRECT_NAME) OPTIMIZE (ssse3) attribute_hidden; extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2) attribute_hidden; +extern __typeof (REDIRECT_NAME) OPTIMIZE (evex) attribute_hidden; static inline void * IFUNC_SELECTOR (void) { const struct cpu_features* cpu_features = __get_cpu_features (); - if (!CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_VZEROUPPER) - && CPU_FEATURE_USABLE_P (cpu_features, AVX2) + if (CPU_FEATURE_USABLE_P (cpu_features, AVX2) && CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load)) - return OPTIMIZE (avx2); + { + if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL) + && CPU_FEATURE_USABLE_P (cpu_features, AVX512BW) + && CPU_FEATURE_USABLE_P (cpu_features, BMI2) + && !CPU_FEATURES_ARCH_P (cpu_features, Prefer_AVX2_STRCMP)) + return OPTIMIZE (evex); + + if (!CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_VZEROUPPER)) + return OPTIMIZE (avx2); + } if (CPU_FEATURES_ARCH_P (cpu_features, Fast_Unaligned_Load)) return OPTIMIZE (sse2_unaligned); |