diff options
| author | H.J. Lu <hjl.tools@gmail.com> | 2021-10-29 12:56:53 -0700 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2021-11-01 07:53:04 -0700 |
| commit | 14dbbf46a007ae5df36646b51ad0c9e5f5259f30 (patch) | |
| tree | 7e0470499bd6cea64b76b1f0392bf23aeea2a19e /sysdeps/x86_64 | |
| parent | c46e9afb2df5fc9e39ff4d13777e4b4c26e04e55 (diff) | |
| download | glibc-14dbbf46a007ae5df36646b51ad0c9e5f5259f30.tar.gz glibc-14dbbf46a007ae5df36646b51ad0c9e5f5259f30.tar.xz glibc-14dbbf46a007ae5df36646b51ad0c9e5f5259f30.zip | |
x86-64: Remove Prefer_AVX2_STRCMP
Remove Prefer_AVX2_STRCMP to enable EVEX strcmp. When comparing 2 32-byte strings, EVEX strcmp has been improved to require 1 load, 1 VPTESTM, 1 VPCMP, 1 KMOVD and 1 INCL instead of 2 loads, 3 VPCMPs, 2 KORDs, 1 KMOVD and 1 TESTL while AVX2 strcmp requires 1 load, 2 VPCMPEQs, 1 VPMINU, 1 VPMOVMSKB and 1 TESTL. EVEX strcmp is now faster than AVX2 strcmp by up to 40% on Tiger Lake and Ice Lake.
Diffstat (limited to 'sysdeps/x86_64')
| -rw-r--r-- | sysdeps/x86_64/multiarch/strcmp.c | 3 | ||||
| -rw-r--r-- | sysdeps/x86_64/multiarch/strncmp.c | 3 |
2 files changed, 2 insertions, 4 deletions
diff --git a/sysdeps/x86_64/multiarch/strcmp.c b/sysdeps/x86_64/multiarch/strcmp.c index 62b7abeeee..7c2901bf44 100644 --- a/sysdeps/x86_64/multiarch/strcmp.c +++ b/sysdeps/x86_64/multiarch/strcmp.c @@ -43,8 +43,7 @@ IFUNC_SELECTOR (void) { 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)) + && CPU_FEATURE_USABLE_P (cpu_features, BMI2)) return OPTIMIZE (evex); if (CPU_FEATURE_USABLE_P (cpu_features, RTM)) diff --git a/sysdeps/x86_64/multiarch/strncmp.c b/sysdeps/x86_64/multiarch/strncmp.c index 60ba0fe356..f94a421784 100644 --- a/sysdeps/x86_64/multiarch/strncmp.c +++ b/sysdeps/x86_64/multiarch/strncmp.c @@ -43,8 +43,7 @@ IFUNC_SELECTOR (void) { 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)) + && CPU_FEATURE_USABLE_P (cpu_features, BMI2)) return OPTIMIZE (evex); if (CPU_FEATURE_USABLE_P (cpu_features, RTM)) |