329e925ee9
Upstream commit: 91c2e6c3db44297bf4cb3a2e3c40236c5b6a0b23 - dlfcn: Implement the RTLD_DI_PHDR request type for dlinfo - manual: Document the dlinfo function - x86: Fix fallback for wcsncmp_avx2 in strcmp-avx2.S [BZ #28896] - x86: Fix bug in strncmp-evex and strncmp-avx2 [BZ #28895] - x86: Set .text section in memset-vec-unaligned-erms - x86-64: Optimize bzero - x86: Remove SSSE3 instruction for broadcast in memset.S (SSE2 Only) - x86: Improve vec generation in memset-vec-unaligned-erms.S - x86-64: Fix strcmp-evex.S - x86-64: Fix strcmp-avx2.S - x86: Optimize strcmp-evex.S - x86: Optimize strcmp-avx2.S - manual: Clarify that abbreviations of long options are allowed - Add HWCAP2_AFP, HWCAP2_RPRES from Linux 5.17 to AArch64 bits/hwcap.h - aarch64: Add HWCAP2_ECV from Linux 5.16 - Add SOL_MPTCP, SOL_MCTP from Linux 5.16 to bits/socket.h - Update kernel version to 5.17 in tst-mman-consts.py - Update kernel version to 5.16 in tst-mman-consts.py - Update syscall lists for Linux 5.17 - Add ARPHRD_CAN, ARPHRD_MCTP to net/if_arp.h - Update kernel version to 5.15 in tst-mman-consts.py - Add PF_MCTP, AF_MCTP from Linux 5.15 to bits/socket.h
36 lines
1.1 KiB
Diff
36 lines
1.1 KiB
Diff
commit 190ea5f7e4e7e98b9b6e3f29835ae8b1f6a5442e
|
|
Author: Noah Goldstein <goldstein.w.n@gmail.com>
|
|
Date: Mon Feb 7 00:32:23 2022 -0600
|
|
|
|
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)
|
|
|
|
diff --git a/sysdeps/x86_64/memset.S b/sysdeps/x86_64/memset.S
|
|
index 34ee0bfdcb81fb39..954471e5a5bf225b 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; \
|