diff options
| author | Noah Goldstein <goldstein.w.n@gmail.com> | 2022-02-07 00:32:23 -0600 |
|---|---|---|
| committer | Noah Goldstein <goldstein.w.n@gmail.com> | 2022-02-07 14:18:29 -0600 |
| commit | 1b0c60f95bbe2eded80b2bb5be75c0e45b11cde1 (patch) | |
| tree | 35485d9f7af9015366c8f98714d271ce51e6944f | |
| parent | 03c9c4fce4fefbb34e65723467d86cb68739a9d1 (diff) | |
| download | glibc-1b0c60f95bbe2eded80b2bb5be75c0e45b11cde1.tar.gz glibc-1b0c60f95bbe2eded80b2bb5be75c0e45b11cde1.tar.xz glibc-1b0c60f95bbe2eded80b2bb5be75c0e45b11cde1.zip | |
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.
| -rw-r--r-- | sysdeps/x86_64/memset.S | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/sysdeps/x86_64/memset.S b/sysdeps/x86_64/memset.S index ccf036be53..3f0517bbfc 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; \ |