diff options
Diffstat (limited to 'sysdeps/x86_64/multiarch/memcpy.S')
-rw-r--r-- | sysdeps/x86_64/multiarch/memcpy.S | 22 |
1 files changed, 15 insertions, 7 deletions
diff --git a/sysdeps/x86_64/multiarch/memcpy.S b/sysdeps/x86_64/multiarch/memcpy.S index 27fca2957e..64a1bcd137 100644 --- a/sysdeps/x86_64/multiarch/memcpy.S +++ b/sysdeps/x86_64/multiarch/memcpy.S @@ -30,19 +30,27 @@ ENTRY(__new_memcpy) .type __new_memcpy, @gnu_indirect_function LOAD_RTLD_GLOBAL_RO_RDX - leaq __memcpy_avx_unaligned(%rip), %rax +#ifdef HAVE_AVX512_ASM_SUPPORT + HAS_ARCH_FEATURE (AVX512F_Usable) + jz 1f + HAS_ARCH_FEATURE (Prefer_No_VZEROUPPER) + jz 1f + leaq __memcpy_avx512_no_vzeroupper(%rip), %rax + ret +#endif +1: leaq __memcpy_avx_unaligned(%rip), %rax HAS_ARCH_FEATURE (AVX_Fast_Unaligned_Load) - jz 1f + jz 2f ret -1: leaq __memcpy_sse2(%rip), %rax +2: leaq __memcpy_sse2(%rip), %rax HAS_ARCH_FEATURE (Slow_BSF) - jnz 2f + jnz 3f leaq __memcpy_sse2_unaligned(%rip), %rax ret -2: HAS_CPU_FEATURE (SSSE3) - jz 3f +3: HAS_CPU_FEATURE (SSSE3) + jz 4f leaq __memcpy_ssse3(%rip), %rax -3: ret +4: ret END(__new_memcpy) # undef ENTRY |