about summary refs log tree commit diff
path: root/sysdeps/x86_64/multiarch/ifunc-strcpy.h
diff options
context:
space:
mode:
authorH.J. Lu <hjl.tools@gmail.com>2021-03-05 07:26:42 -0800
committerH.J. Lu <hjl.tools@gmail.com>2021-03-29 07:40:17 -0700
commit7ebba91361badf7531d4e75050627a88d424872f (patch)
treed99781a37b47b95441ad358d119ec3741960d405 /sysdeps/x86_64/multiarch/ifunc-strcpy.h
parent91264fe3577fe887b4860923fa6142b5274c8965 (diff)
downloadglibc-7ebba91361badf7531d4e75050627a88d424872f.tar.gz
glibc-7ebba91361badf7531d4e75050627a88d424872f.tar.xz
glibc-7ebba91361badf7531d4e75050627a88d424872f.zip
x86-64: Add AVX optimized string/memory functions for RTM
Since VZEROUPPER triggers RTM abort while VZEROALL won't, select AVX
optimized string/memory functions with

	xtest
	jz	1f
	vzeroall
	ret
1:
	vzeroupper
	ret

at function exit on processors with usable RTM, but without 256-bit EVEX
instructions to avoid VZEROUPPER inside a transactionally executing RTM
region.
Diffstat (limited to 'sysdeps/x86_64/multiarch/ifunc-strcpy.h')
-rw-r--r--sysdeps/x86_64/multiarch/ifunc-strcpy.h4
1 files changed, 4 insertions, 0 deletions
diff --git a/sysdeps/x86_64/multiarch/ifunc-strcpy.h b/sysdeps/x86_64/multiarch/ifunc-strcpy.h
index f31f436adf..39568f480f 100644
--- a/sysdeps/x86_64/multiarch/ifunc-strcpy.h
+++ b/sysdeps/x86_64/multiarch/ifunc-strcpy.h
@@ -25,6 +25,7 @@ extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2_unaligned)
   attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (ssse3) 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;
 
 static inline void *
@@ -39,6 +40,9 @@ IFUNC_SELECTOR (void)
 	  && CPU_FEATURE_USABLE_P (cpu_features, AVX512BW))
 	return OPTIMIZE (evex);
 
+      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);
     }