[PATCH v1] x86: Remove SSE3 instruction for broadcast in memset.S (SSE2 Only)

[Noah Goldstein]

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 SSE3
instruction and memset.S is restricted to only SSE2 instructions.
---
 sysdeps/x86_64/memset.S | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/sysdeps/x86_64/memset.S b/sysdeps/x86_64/memset.S
index ccf036be53..148553cf3d 100644
--- a/sysdeps/x86_64/memset.S
+++ b/sysdeps/x86_64/memset.S
@@ -28,22 +28,23 @@
 #define VMOVU     movups
 #define VMOVA     movaps
 
-# define MEMSET_SET_VEC0_AND_SET_RETURN(d, r) \
+#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) \
+#define WMEMSET_SET_VEC0_AND_SET_RETURN(d, r) \
   movd d, %xmm0; \
   pshufd $0, %xmm0, %xmm0; \
   movq r, %rax
 
-# define MEMSET_VDUP_TO_VEC0_HIGH()
-# define MEMSET_VDUP_TO_VEC0_LOW()
+#define MEMSET_VDUP_TO_VEC0_HIGH()
+#define MEMSET_VDUP_TO_VEC0_LOW()
 
-# define WMEMSET_VDUP_TO_VEC0_HIGH()
-# define WMEMSET_VDUP_TO_VEC0_LOW()
+#define WMEMSET_VDUP_TO_VEC0_HIGH()
+#define WMEMSET_VDUP_TO_VEC0_LOW()
 
 #define SECTION(p)		p
 
-- 
2.25.1