about summary refs log tree commit diff
path: root/sysdeps/x86_64/multiarch/ifunc-strcasecmp.h
diff options
context:
space:
mode:
authorNoah Goldstein <goldstein.w.n@gmail.com>2022-03-24 18:56:12 -0500
committerNoah Goldstein <goldstein.w.n@gmail.com>2022-03-25 13:16:43 -0500
commitbbf81222343fed5cd704001a2ae0d86c71544151 (patch)
treebe61639b266f1452ecea891871f6f11482b0aa4c /sysdeps/x86_64/multiarch/ifunc-strcasecmp.h
parent39399913a244a911edb1ff1e31dfe38e64177bb5 (diff)
downloadglibc-bbf81222343fed5cd704001a2ae0d86c71544151.tar.gz
glibc-bbf81222343fed5cd704001a2ae0d86c71544151.tar.xz
glibc-bbf81222343fed5cd704001a2ae0d86c71544151.zip
x86: Add AVX2 optimized str{n}casecmp
geometric_mean(N=40) of all benchmarks AVX2 / SSE42: .702

All string/memory tests pass.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Diffstat (limited to 'sysdeps/x86_64/multiarch/ifunc-strcasecmp.h')
-rw-r--r--sysdeps/x86_64/multiarch/ifunc-strcasecmp.h12
1 files changed, 12 insertions, 0 deletions
diff --git a/sysdeps/x86_64/multiarch/ifunc-strcasecmp.h b/sysdeps/x86_64/multiarch/ifunc-strcasecmp.h
index 9e3cc61ac0..c4de111fd0 100644
--- a/sysdeps/x86_64/multiarch/ifunc-strcasecmp.h
+++ b/sysdeps/x86_64/multiarch/ifunc-strcasecmp.h
@@ -23,12 +23,24 @@ extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2) attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (ssse3) attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (sse42) attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (avx) attribute_hidden;
+extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2) attribute_hidden;
+extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2_rtm) attribute_hidden;
 
 static inline void *
 IFUNC_SELECTOR (void)
 {
   const struct cpu_features* cpu_features = __get_cpu_features ();
 
+  if (CPU_FEATURE_USABLE_P (cpu_features, AVX2)
+      && CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load))
+    {
+      if (CPU_FEATURE_USABLE_P (cpu_features, RTM))
+        return OPTIMIZE (avx2_rtm);
+
+      if (!CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_VZEROUPPER))
+        return OPTIMIZE (avx2);
+    }
+
   if (CPU_FEATURE_USABLE_P (cpu_features, AVX))
     return OPTIMIZE (avx);