From 4412c21a9027bbe6546b2a329a741d26c2477136 Mon Sep 17 00:00:00 2001
From: Noah Goldstein <goldstein.w.n@gmail.com>
Date: Mon, 7 Feb 2022 00:32:23 -0600
Subject: [PATCH] x86: Remove SSSE3 instruction for broadcast in memset.S (SSE2
 Only)
 
commit b62ace2740a106222e124cc86956448fa07abf4d
Author: Noah Goldstein <goldstein.w.n@gmail.com>
Date:   Sun Feb 6 00:54:18 2022 -0600
 
    x86: Improve vec generation in memset-vec-unaligned-erms.S
 
Revert usage of 'pshufb' in broadcast logic as it is an SSSE3
instruction and memset.S is restricted to only SSE2 instructions.
 
(cherry picked from commit 1b0c60f95bbe2eded80b2bb5be75c0e45b11cde1)
---
 sysdeps/x86_64/memset.S | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
 
diff --git a/sysdeps/x86_64/memset.S b/sysdeps/x86_64/memset.S
index 27debd2b..4cb4aa71 100644
--- a/sysdeps/x86_64/memset.S
+++ b/sysdeps/x86_64/memset.S
@@ -30,9 +30,10 @@
 
 # define MEMSET_SET_VEC0_AND_SET_RETURN(d, r) \
   movd d, %xmm0; \
-  pxor %xmm1, %xmm1; \
-  pshufb %xmm1, %xmm0; \
-  movq r, %rax
+  movq r, %rax; \
+  punpcklbw %xmm0, %xmm0; \
+  punpcklwd %xmm0, %xmm0; \
+  pshufd $0, %xmm0, %xmm0
 
 # define WMEMSET_SET_VEC0_AND_SET_RETURN(d, r) \
   movd d, %xmm0; \
-- 
GitLab