about summary refs log tree commit diff
path: root/sysdeps/x86_64/fpu
diff options
context:
space:
mode:
authorH.J. Lu <hjl.tools@gmail.com>2017-09-12 07:46:11 -0700
committerH.J. Lu <hjl.tools@gmail.com>2017-09-12 07:54:47 -0700
commitef8adeb0416309082c41a1518caee6961b5c42e8 (patch)
tree1907bd459f82a962252cc5852bbee9025b3a99ad /sysdeps/x86_64/fpu
parenta166531fdf601560a0005479427f60d3173f8257 (diff)
downloadglibc-ef8adeb0416309082c41a1518caee6961b5c42e8.tar.gz
glibc-ef8adeb0416309082c41a1518caee6961b5c42e8.tar.xz
glibc-ef8adeb0416309082c41a1518caee6961b5c42e8.zip
x86: Add MathVec_Prefer_No_AVX512 to cpu-features [BZ #21967]
AVX512 functions in mathvec are used on machines with AVX512.  An AVX2
wrapper is also provided and it can be used when the AVX512 version
isn't profitable.  MathVec_Prefer_No_AVX512 is addded to cpu-features.
If glibc.tune.hwcaps=MathVec_Prefer_No_AVX512 is set in GLIBC_TUNABLES
environment variable, the AVX2 wrapper will be used.

Tested on x86-64 machines with and without AVX512.  Also verified
glibc.tune.hwcaps=MathVec_Prefer_No_AVX512 on AVX512 machine.

	[BZ #21967]
	* sysdeps/x86/cpu-features.h (bit_arch_MathVec_Prefer_No_AVX512):
	New.
	(index_arch_MathVec_Prefer_No_AVX512): Likewise.
	* sysdeps/x86/cpu-tunables.c (TUNABLE_CALLBACK (set_hwcaps)):
	Handle MathVec_Prefer_No_AVX512.
	* sysdeps/x86_64/fpu/multiarch/ifunc-mathvec-avx512.h
	(IFUNC_SELECTOR): Return AVX2 version if MathVec_Prefer_No_AVX512
	is set.
Diffstat (limited to 'sysdeps/x86_64/fpu')
-rw-r--r--sysdeps/x86_64/fpu/multiarch/ifunc-mathvec-avx512.h13
1 files changed, 8 insertions, 5 deletions
diff --git a/sysdeps/x86_64/fpu/multiarch/ifunc-mathvec-avx512.h b/sysdeps/x86_64/fpu/multiarch/ifunc-mathvec-avx512.h
index 1857e1f760..fffc9da114 100644
--- a/sysdeps/x86_64/fpu/multiarch/ifunc-mathvec-avx512.h
+++ b/sysdeps/x86_64/fpu/multiarch/ifunc-mathvec-avx512.h
@@ -32,11 +32,14 @@ IFUNC_SELECTOR (void)
 {
   const struct cpu_features* cpu_features = __get_cpu_features ();
 
-  if (CPU_FEATURES_ARCH_P (cpu_features, AVX512DQ_Usable))
-    return OPTIMIZE (skx);
-
-  if (CPU_FEATURES_ARCH_P (cpu_features, AVX512F_Usable))
-    return OPTIMIZE (knl);
+  if (!CPU_FEATURES_ARCH_P (cpu_features, MathVec_Prefer_No_AVX512))
+    {
+      if (CPU_FEATURES_ARCH_P (cpu_features, AVX512DQ_Usable))
+	return OPTIMIZE (skx);
+
+      if (CPU_FEATURES_ARCH_P (cpu_features, AVX512F_Usable))
+	return OPTIMIZE (knl);
+    }
 
   return OPTIMIZE (avx2_wrapper);
 }