This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
[PATCH 5/7] Enable __mempcpy_sse2_unaligned
- From: "H.J. Lu" <hjl dot tools at gmail dot com>
- To: libc-alpha at sourceware dot org
- Cc: Ondrej Bilka <neleai at seznam dot cz>
- Date: Mon, 7 Mar 2016 09:36:28 -0800
- Subject: [PATCH 5/7] Enable __mempcpy_sse2_unaligned
- Authentication-results: sourceware.org; auth=none
- References: <1457372190-12196-1-git-send-email-hjl dot tools at gmail dot com>
Check Fast_Unaligned_Load for __mempcpy_sse2_unaligned. The new
selection order is:
1. __mempcpy_avx_unaligned if AVX_Fast_Unaligned_Load bit is set.
2. __mempcpy_sse2_unaligned if Fast_Unaligned_Load bit is set.
3. __mempcpy_sse2 if SSSE3 isn't available.
4. __mempcpy_ssse3_back if Fast_Copy_Backward bit it set.
5. __mempcpy_ssse3
[BZ #19776]
* sysdeps/x86_64/multiarch/mempcpy.S (__mempcpy): Check
Fast_Unaligned_Load to enable __mempcpy_sse2_unaligned.
---
sysdeps/x86_64/multiarch/mempcpy.S | 19 +++++++++++--------
1 file changed, 11 insertions(+), 8 deletions(-)
diff --git a/sysdeps/x86_64/multiarch/mempcpy.S b/sysdeps/x86_64/multiarch/mempcpy.S
index ed78623..1314d76 100644
--- a/sysdeps/x86_64/multiarch/mempcpy.S
+++ b/sysdeps/x86_64/multiarch/mempcpy.S
@@ -33,19 +33,22 @@ ENTRY(__mempcpy)
jz 1f
HAS_ARCH_FEATURE (Prefer_No_VZEROUPPER)
jz 1f
- leaq __mempcpy_avx512_no_vzeroupper(%rip), %rax
+ lea __mempcpy_avx512_no_vzeroupper(%rip), %RAX_LP
ret
#endif
-1: leaq __mempcpy_sse2(%rip), %rax
+1: lea __mempcpy_avx_unaligned(%rip), %RAX_LP
+ HAS_ARCH_FEATURE (AVX_Fast_Unaligned_Load)
+ jnz 2f
+ lea __mempcpy_sse2_unaligned(%rip), %RAX_LP
+ HAS_ARCH_FEATURE (Fast_Unaligned_Load)
+ jnz 2f
+ lea __mempcpy_sse2(%rip), %RAX_LP
HAS_CPU_FEATURE (SSSE3)
jz 2f
- leaq __mempcpy_ssse3(%rip), %rax
+ lea __mempcpy_ssse3_back(%rip), %RAX_LP
HAS_ARCH_FEATURE (Fast_Copy_Backward)
- jz 2f
- leaq __mempcpy_ssse3_back(%rip), %rax
- HAS_ARCH_FEATURE (AVX_Fast_Unaligned_Load)
- jz 2f
- leaq __mempcpy_avx_unaligned(%rip), %rax
+ jnz 2f
+ lea __mempcpy_ssse3(%rip), %RAX_LP
2: ret
END(__mempcpy)
--
2.5.0