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
This commit is contained in:
Noah Goldstein 2022-06-14 15:37:28 -07:00
parent 0355915514
commit ff439c4717

View file

@ -28,6 +28,7 @@
extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2) attribute_hidden;
extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2_unaligned) 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;
@ -52,6 +53,10 @@ 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);