krak/zstd
1
0
Fork 0
mirror of https://github.com/facebook/zstd.git synced 2025-09-16 09:36:32 +02:00
Code Issues Releases 1 Activity

AArch64: Use better block copy8

Browse Source 
The vector copy is only necessary for 16-byte blocks on AArch64.

Decompression uplifts on a Neoverse V2 system, using Zstd-1.5.8
compiled with "-O3 -march=armv8.2-a+sve2":

                 Clang-19  Clang-20    GCC-14    GCC-15
 1#silesia.tar:   +0.316%   +0.865%   +0.025%   +0.096%
 2#silesia.tar:   +0.689%   +1.374%   +0.027%   +0.065%
 3#silesia.tar:   +0.811%   +1.654%   +0.034%   +0.033%
 4#silesia.tar:   +0.912%   +1.755%   +0.027%   +0.042%
 5#silesia.tar:   +0.995%   +1.826%   +0.062%   +0.094%
 6#silesia.tar:   +0.976%   +1.777%   +0.065%   +0.104%
 7#silesia.tar:   +0.910%   +1.738%   +0.077%   +0.110%
This commit is contained in:
Arpad Panyik
2025-06-20 14:48:33 +00:00
parent 7eefc22169
commit 1e9d2006ae
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
lib/common/zstd_internal.h
View File

@@ -168,7 +168,7 @@ static UNUSED_ATTR const U32 OF_defaultNormLog = OF_DEFAULTNORMLOG;
* Shared functions to include for inlining
*********************************************/
static void ZSTD_copy8(void* dst, const void* src) {
#if defined(ZSTD_ARCH_ARM_NEON)
#if defined(ZSTD_ARCH_ARM_NEON) && !defined(__aarch64__)
vst1_u8((uint8_t*)dst, vld1_u8((const uint8_t*)src));
#else
ZSTD_memcpy(dst, src, 8);