diff options
Diffstat (limited to 'sysdeps/x86_64/multiarch/memset.S')
-rw-r--r-- | sysdeps/x86_64/multiarch/memset.S | 45 |
1 files changed, 24 insertions, 21 deletions
diff --git a/sysdeps/x86_64/multiarch/memset.S b/sysdeps/x86_64/multiarch/memset.S index c5f1fb340e..8e3b9b9764 100644 --- a/sysdeps/x86_64/multiarch/memset.S +++ b/sysdeps/x86_64/multiarch/memset.S @@ -1,6 +1,6 @@ /* Multiple versions of memset All versions must be listed in ifunc-impl-list.c. - Copyright (C) 2014-2015 Free Software Foundation, Inc. + Copyright (C) 2014-2016 Free Software Foundation, Inc. This file is part of the GNU C Library. The GNU C Library is free software; you can redistribute it and/or @@ -17,45 +17,48 @@ License along with the GNU C Library; if not, see <http://www.gnu.org/licenses/>. */ -#ifdef HAVE_AVX2_SUPPORT #include <sysdep.h> #include <shlib-compat.h> #include <init-arch.h> /* Define multiple versions only for the definition in lib. */ -# if IS_IN (libc) +#if IS_IN (libc) ENTRY(memset) .type memset, @gnu_indirect_function - cmpl $0, __cpu_features+KIND_OFFSET(%rip) - jne 1f - call __init_cpu_features -1: leaq __memset_sse2(%rip), %rax - testl $bit_AVX2_Usable, __cpu_features+FEATURE_OFFSET+index_AVX2_Usable(%rip) + LOAD_RTLD_GLOBAL_RO_RDX + leaq __memset_sse2(%rip), %rax + HAS_ARCH_FEATURE (AVX2_Usable) jz 2f leaq __memset_avx2(%rip), %rax +#ifdef HAVE_AVX512_ASM_SUPPORT + HAS_ARCH_FEATURE (AVX512F_Usable) + jz 2f + HAS_ARCH_FEATURE (Prefer_No_VZEROUPPER) + jz 2f + leaq __memset_avx512_no_vzeroupper(%rip), %rax +#endif 2: ret END(memset) -# endif +#endif -# if IS_IN (libc) -# undef memset -# define memset __memset_sse2 +#if IS_IN (libc) +# undef memset +# define memset __memset_sse2 -# undef __memset_chk -# define __memset_chk __memset_chk_sse2 +# undef __memset_chk +# define __memset_chk __memset_chk_sse2 -# ifdef SHARED -# undef libc_hidden_builtin_def +# ifdef SHARED +# undef libc_hidden_builtin_def /* It doesn't make sense to send libc-internal memset calls through a PLT. The speedup we get from using GPR instruction is likely eaten away by the indirect call in the PLT. */ -# define libc_hidden_builtin_def(name) \ +# define libc_hidden_builtin_def(name) \ .globl __GI_memset; __GI_memset = __memset_sse2 -# endif - -# undef strong_alias -# define strong_alias(original, alias) # endif + +# undef strong_alias +# define strong_alias(original, alias) #endif #include "../memset.S" |