You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
45 lines
1.6 KiB
45 lines
1.6 KiB
9 months ago
|
From a35a59036ebae3efcdf5e8167610e0656fca9770 Mon Sep 17 00:00:00 2001
|
||
|
|
From: "H.J. Lu" <hjl.tools@gmail.com>
|
||
|
|
Date: Thu, 11 Jun 2020 12:41:18 -0700
|
||
|
|
Subject: [PATCH] x86_64: Use %xmmN with vpxor to clear a vector register
|
||
|
|
Content-type: text/plain; charset=UTF-8
|
||
|
|
|
||
|
|
Since "vpxor %xmmN, %xmmN, %xmmN" clears the whole vector register, use
|
||
|
|
%xmmN, instead of %ymmN, with vpxor to clear a vector register.
|
||
|
|
---
|
||
|
|
sysdeps/x86_64/multiarch/strcmp-avx2.S | 4 ++--
|
||
|
|
sysdeps/x86_64/multiarch/strrchr-avx2.S | 2 +-
|
||
|
|
2 files changed, 3 insertions(+), 3 deletions(-)
|
||
|
|
|
||
|
|
diff --git a/sysdeps/x86_64/multiarch/strcmp-avx2.S b/sysdeps/x86_64/multiarch/strcmp-avx2.S
|
||
|
|
index 433ae047..70d8499b 100644
|
||
|
|
--- a/sysdeps/x86_64/multiarch/strcmp-avx2.S
|
||
|
|
+++ b/sysdeps/x86_64/multiarch/strcmp-avx2.S
|
||
|
|
@@ -105,8 +105,8 @@ ENTRY (STRCMP)
|
||
|
|
# endif
|
||
|
|
movl %edi, %eax
|
||
|
|
xorl %edx, %edx
|
||
|
|
- /* Make %ymm7 all zeros in this function. */
|
||
|
|
- vpxor %ymm7, %ymm7, %ymm7
|
||
|
|
+ /* Make %xmm7 (%ymm7) all zeros in this function. */
|
||
|
|
+ vpxor %xmm7, %xmm7, %xmm7
|
||
|
|
orl %esi, %eax
|
||
|
|
andl $(PAGE_SIZE - 1), %eax
|
||
|
|
cmpl $(PAGE_SIZE - (VEC_SIZE * 4)), %eax
|
||
|
|
diff --git a/sysdeps/x86_64/multiarch/strrchr-avx2.S b/sysdeps/x86_64/multiarch/strrchr-avx2.S
|
||
|
|
index 9f22a15e..c949410b 100644
|
||
|
|
--- a/sysdeps/x86_64/multiarch/strrchr-avx2.S
|
||
|
|
+++ b/sysdeps/x86_64/multiarch/strrchr-avx2.S
|
||
|
|
@@ -48,7 +48,7 @@ ENTRY (STRRCHR)
|
||
|
|
movl %edi, %ecx
|
||
|
|
/* Broadcast CHAR to YMM4. */
|
||
|
|
VPBROADCAST %xmm4, %ymm4
|
||
|
|
- vpxor %ymm0, %ymm0, %ymm0
|
||
|
|
+ vpxor %xmm0, %xmm0, %xmm0
|
||
|
|
|
||
|
|
/* Check if we may cross page boundary with one vector load. */
|
||
|
|
andl $(2 * VEC_SIZE - 1), %ecx
|
||
|
|
--
|
||
|
|
GitLab
|
||
|
|
|