sharpetronics/zstd
1
0
Fork 0
mirror of https://github.com/facebook/zstd.git synced 2025-10-15 00:02:02 -04:00
Code Issues Projects Releases Wiki Activity

Merge pull request #3141 from JunHe77/seqDec

Browse Source 
dec: adjust seqSymbol load on aarch64
This commit is contained in:
Nick Terrell 2022-06-09 13:40:51 -07:00 committed by GitHub
commit 3b1bd91852
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 18 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
lib/decompress/zstd_decompress_block.c
View File

@ -1170,9 +1170,27 @@ FORCE_INLINE_TEMPLATE seq_t
ZSTD_decodeSequence(seqState_t* seqState, const ZSTD_longOffset_e longOffsets)
{
seq_t seq;
/*
* ZSTD_seqSymbol is a structure with a total of 64 bits wide. So it can be
* loaded in one operation and extracted its fields by simply shifting or
* bit-extracting on aarch64.
* GCC doesn't recognize this and generates more unnecessary ldr/ldrb/ldrh
* operations that cause performance drop. This can be avoided by using this
* ZSTD_memcpy hack.
*/
#if defined(__aarch64__) && (defined(__GNUC__) && !defined(__clang__))
ZSTD_seqSymbol llDInfoS, mlDInfoS, ofDInfoS;
ZSTD_seqSymbol* const llDInfo = &llDInfoS;
ZSTD_seqSymbol* const mlDInfo = &mlDInfoS;
ZSTD_seqSymbol* const ofDInfo = &ofDInfoS;
ZSTD_memcpy(llDInfo, seqState->stateLL.table + seqState->stateLL.state, sizeof(ZSTD_seqSymbol));
ZSTD_memcpy(mlDInfo, seqState->stateML.table + seqState->stateML.state, sizeof(ZSTD_seqSymbol));
ZSTD_memcpy(ofDInfo, seqState->stateOffb.table + seqState->stateOffb.state, sizeof(ZSTD_seqSymbol));
#else
const ZSTD_seqSymbol* const llDInfo = seqState->stateLL.table + seqState->stateLL.state;
const ZSTD_seqSymbol* const mlDInfo = seqState->stateML.table + seqState->stateML.state;
const ZSTD_seqSymbol* const ofDInfo = seqState->stateOffb.table + seqState->stateOffb.state;
#endif
seq.matchLength = mlDInfo->baseValue;
seq.litLength = llDInfo->baseValue;
{ U32 const ofBase = ofDInfo->baseValue;