about summary refs log tree commit diff
diff options
context:
space:
mode:
authorNoah Goldstein <goldstein.w.n@gmail.com>2022-06-14 15:37:28 -0700
committerSunil K Pandey <skpgkp2@gmail.com>2022-07-18 22:13:57 -0700
commitcfa13a8205092cd4216e65eddc19742be379aaea (patch)
tree31e66bd940ac2363ed48f286c6a5c4f96cdcd70f
parent20bfbb3a5789551a09b1ec4db97dcaed6f9180f0 (diff)
downloadglibc-cfa13a8205092cd4216e65eddc19742be379aaea.tar.gz
glibc-cfa13a8205092cd4216e65eddc19742be379aaea.tar.xz
glibc-cfa13a8205092cd4216e65eddc19742be379aaea.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)
-rw-r--r--sysdeps/x86_64/multiarch/strcmp.c5
1 files changed, 5 insertions, 0 deletions
diff --git a/sysdeps/x86_64/multiarch/strcmp.c b/sysdeps/x86_64/multiarch/strcmp.c
index 7c2901bf44..b457fb4c15 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);