diff options
| author |   Noah Goldstein <goldstein.w.n@gmail.com> | 2022-06-14 15:37:28 -0700 |
|---|---|---|
| committer |   Andreas K. Hüttel <dilfridge@gentoo.org> | 2022-09-03 22:20:15 +0200 |
| commit | e83ba54d196d38effffac9b4143d5c5e50f23dc2 (patch) | |
| tree | 713c466742e5e179ee64401dc979accd1f5e9ea9 /sysdeps | |
| parent | x86: Fix misordered logic for setting `rep_movsb_stop_threshold` (diff) | |
| download | glibc-e83ba54d196d38effffac9b4143d5c5e50f23dc2.tar.gz glibc-e83ba54d196d38effffac9b4143d5c5e50f23dc2.tar.bz2 glibc-e83ba54d196d38effffac9b4143d5c5e50f23dc2.zip | |
x86: Add sse42 implementation to strcmp's ifunc
This has been missing since the the ifuncs where added.
The performance of SSE4.2 is preferable to to SSE2.
Measured on Tigerlake with N = 20 runs.
Geometric Mean of all benchmarks SSE4.2 / SSE2: 0.906
(cherry picked from commit ff439c47173565fbff4f0f78d07b0f14e4a7db05)
(cherry picked from commit 232b7adb14b7ce36f1c25a88dfc834392acac393)
Diffstat (limited to 'sysdeps')
| -rw-r--r-- | sysdeps/x86_64/multiarch/strcmp.c | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/sysdeps/x86_64/multiarch/strcmp.c b/sysdeps/x86_64/multiarch/strcmp.c index 68cb73baad..08638e2632 100644 --- a/sysdeps/x86_64/multiarch/strcmp.c +++ b/sysdeps/x86_64/multiarch/strcmp.c @@ -29,6 +29,7 @@ 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 (sse42) attribute_hidden; extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2) attribute_hidden; extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2_rtm) attribute_hidden; extern __typeof (REDIRECT_NAME) OPTIMIZE (evex) attribute_hidden; @@ -53,6 +54,10 @@ IFUNC_SELECTOR (void) return OPTIMIZE (avx2); } + if (CPU_FEATURE_USABLE_P (cpu_features, SSE4_2) + && !CPU_FEATURES_ARCH_P (cpu_features, Slow_SSE4_2)) + return OPTIMIZE (sse42); + if (CPU_FEATURES_ARCH_P (cpu_features, Fast_Unaligned_Load)) return OPTIMIZE (sse2_unaligned); |