about summary refs log tree commit diff
path: root/sysdeps/x86_64/multiarch/Makefile
diff options
context:
space:
mode:
authorAndrew Senkevich <andrew.senkevich@intel.com>2015-12-19 02:47:28 +0300
committerAndrew Senkevich <andrew.senkevich@intel.com>2015-12-19 02:47:28 +0300
commit83d776f979342f923b5c3d2a5b43afab841c6086 (patch)
tree180682939f88351b00817f2092e24817ddbdf07f /sysdeps/x86_64/multiarch/Makefile
parent794950ed1d29853158d783d57f72260f5665afe5 (diff)
downloadglibc-83d776f979342f923b5c3d2a5b43afab841c6086.tar.gz
glibc-83d776f979342f923b5c3d2a5b43afab841c6086.tar.xz
glibc-83d776f979342f923b5c3d2a5b43afab841c6086.zip
Added memset optimized with AVX512 for KNL hardware.
It shows improvement up to 28% over AVX2 memset (performance results
attached at <https://sourceware.org/ml/libc-alpha/2015-12/msg00052.html>).

    * sysdeps/x86_64/multiarch/memset-avx512-no-vzeroupper.S: New file.
    * sysdeps/x86_64/multiarch/Makefile (sysdep_routines): Added new file.
    * sysdeps/x86_64/multiarch/ifunc-impl-list.c: Added new tests.
    * sysdeps/x86_64/multiarch/memset.S: Added new IFUNC branch.
    * sysdeps/x86_64/multiarch/memset_chk.S: Likewise.
    * sysdeps/x86/cpu-features.h (bit_Prefer_No_VZEROUPPER,
    index_Prefer_No_VZEROUPPER): New.
    * sysdeps/x86/cpu-features.c (init_cpu_features): Set the
    Prefer_No_VZEROUPPER for Knights Landing.
Diffstat (limited to 'sysdeps/x86_64/multiarch/Makefile')
-rw-r--r--sysdeps/x86_64/multiarch/Makefile3
1 files changed, 2 insertions, 1 deletions
diff --git a/sysdeps/x86_64/multiarch/Makefile b/sysdeps/x86_64/multiarch/Makefile
index bb811c2dfb..b2e31efe02 100644
--- a/sysdeps/x86_64/multiarch/Makefile
+++ b/sysdeps/x86_64/multiarch/Makefile
@@ -18,7 +18,8 @@ sysdep_routines += strncat-c stpncpy-c strncpy-c strcmp-ssse3 \
 		   stpcpy-sse2-unaligned stpncpy-sse2-unaligned \
 		   strcat-sse2-unaligned strncat-sse2-unaligned \
 		   strchr-sse2-no-bsf memcmp-ssse3 strstr-sse2-unaligned \
-		   strcspn-c strpbrk-c strspn-c varshift memset-avx2
+		   strcspn-c strpbrk-c strspn-c varshift memset-avx2 \
+		   memset-avx512-no-vzeroupper
 CFLAGS-varshift.c += -msse4
 CFLAGS-strcspn-c.c += -msse4
 CFLAGS-strpbrk-c.c += -msse4