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)

diff --git a/sysdeps/x86_64/multiarch/strcmp.c b/sysdeps/x86_64/multiarch/strcmp.c
index 7c2901bf444562596d7ba9c785adf05925356b04..b457fb4c150e44072ddecf5b181ef33f58e660f5 100644 (file)
--- 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);