AuroraMiddleware/zstd
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #1798 from facebook/refac_fast

Browse Source 
minor refactor of ZSTD_fast
This commit is contained in:
Yann Collet 2019-09-17 14:54:23 -07:00 committed by GitHub
commit 5329de1f1e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 30 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
lib/compress/zstd_compress_internal.h
View File

@ -341,18 +341,18 @@ MEM_STATIC size_t ZSTD_minGain(size_t srcSize, ZSTD_strategy strat)
}
/*! ZSTD_storeSeq() :
* Store a sequence (literal length, literals, offset code and match length code) into seqStore_t.
* `offsetCode` : distance to match + 3 (values 1-3 are repCodes).
* Store a sequence (litlen, litPtr, offCode and mlBase) into seqStore_t.
* `offCode` : distance to match + ZSTD_REP_MOVE (values <= ZSTD_REP_MOVE are repCodes).
* `mlBase` : matchLength - MINMATCH
*/
MEM_STATIC void ZSTD_storeSeq(seqStore_t* seqStorePtr, size_t litLength, const void* literals, U32 offsetCode, size_t mlBase)
MEM_STATIC void ZSTD_storeSeq(seqStore_t* seqStorePtr, size_t litLength, const void* literals, U32 offCode, size_t mlBase)
{
#if defined(DEBUGLEVEL) && (DEBUGLEVEL >= 6)
static const BYTE* g_start = NULL;
if (g_start==NULL) g_start = (const BYTE*)literals; /* note : index only works for compression within a single segment */
{ U32 const pos = (U32)((const BYTE*)literals - g_start);
DEBUGLOG(6, "Cpos%7u :%3u literals, match%4u bytes at offCode%7u",
pos, (U32)litLength, (U32)mlBase+MINMATCH, (U32)offsetCode);
pos, (U32)litLength, (U32)mlBase+MINMATCH, (U32)offCode);
}
#endif
assert((size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart) < seqStorePtr->maxNbSeq);
@ -371,7 +371,7 @@ MEM_STATIC void ZSTD_storeSeq(seqStore_t* seqStorePtr, size_t litLength, const v
seqStorePtr->sequences[0].litLength = (U16)litLength;
/* match offset */
seqStorePtr->sequences[0].offset = offsetCode + 1;
seqStorePtr->sequences[0].offset = offCode + 1;
/* match Length */
if (mlBase>0xFFFF) {

59
lib/compress/zstd_fast.c
View File

@ -8,7 +8,7 @@
* You may select, at your option, one of the above-listed licenses.
*/
#include "zstd_compress_internal.h"
#include "zstd_compress_internal.h" /* ZSTD_hashPtr, ZSTD_count, ZSTD_storeSeq */
#include "zstd_fast.h"
@ -43,8 +43,8 @@ void ZSTD_fillHashTable(ZSTD_matchState_t* ms,
}
FORCE_INLINE_TEMPLATE
size_t ZSTD_compressBlock_fast_generic(
FORCE_INLINE_TEMPLATE size_t
ZSTD_compressBlock_fast_generic(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize,
U32 const mls)
@ -74,8 +74,7 @@ size_t ZSTD_compressBlock_fast_generic(
DEBUGLOG(5, "ZSTD_compressBlock_fast_generic");
ip0 += (ip0 == prefixStart);
ip1 = ip0 + 1;
{
U32 const maxRep = (U32)(ip0 - prefixStart);
{ U32 const maxRep = (U32)(ip0 - prefixStart);
if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0;
if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0;
}
@ -118,8 +117,7 @@ size_t ZSTD_compressBlock_fast_generic(
match0 = match1;
goto _offset;
}
{
size_t const step = ((ip0-anchor) >> (kSearchStrength - 1)) + stepSize;
{ size_t const step = ((size_t)(ip0-anchor) >> (kSearchStrength - 1)) + stepSize;
assert(step >= 2);
ip0 += step;
ip1 += step;
@ -138,7 +136,7 @@ _offset: /* Requires: ip0, match0 */
_match: /* Requires: ip0, match0, offcode */
/* Count the forward length */
mLength += ZSTD_count(ip0+mLength+4, match0+mLength+4, iend) + 4;
ZSTD_storeSeq(seqStore, ip0-anchor, anchor, offcode, mLength-MINMATCH);
ZSTD_storeSeq(seqStore, (size_t)(ip0-anchor), anchor, offcode, mLength-MINMATCH);
/* match found */
ip0 += mLength;
anchor = ip0;
@ -150,16 +148,15 @@ _match: /* Requires: ip0, match0, offcode */
hashTable[ZSTD_hashPtr(base+current0+2, hlog, mls)] = current0+2; /* here because current+2 could be > iend-8 */
hashTable[ZSTD_hashPtr(ip0-2, hlog, mls)] = (U32)(ip0-2-base);
while ( (ip0 <= ilimit)
&& ( (offset_2>0)
& (MEM_read32(ip0) == MEM_read32(ip0 - offset_2)) )) {
while ( ((ip0 <= ilimit) & (offset_2>0)) /* offset_2==0 means offset_2 is invalidated */
&& (MEM_read32(ip0) == MEM_read32(ip0 - offset_2)) ) {
/* store sequence */
size_t const rLength = ZSTD_count(ip0+4, ip0+4-offset_2, iend) + 4;
U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff; /* swap offset_2 <=> offset_1 */
{ U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff; } /* swap offset_2 <=> offset_1 */
hashTable[ZSTD_hashPtr(ip0, hlog, mls)] = (U32)(ip0-base);
ip0 += rLength;
ip1 = ip0 + 1;
ZSTD_storeSeq(seqStore, 0, anchor, 0, rLength-MINMATCH);
ZSTD_storeSeq(seqStore, 0 /*litLen*/, anchor, 0 /*offCode*/, rLength-MINMATCH);
anchor = ip0;
continue; /* faster when present (confirmed on gcc-8) ... (?) */
}
@ -179,8 +176,7 @@ size_t ZSTD_compressBlock_fast(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize)
{
ZSTD_compressionParameters const* cParams = &ms->cParams;
U32 const mls = cParams->minMatch;
U32 const mls = ms->cParams.minMatch;
assert(ms->dictMatchState == NULL);
switch(mls)
{
@ -348,8 +344,7 @@ size_t ZSTD_compressBlock_fast_dictMatchState(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize)
{
ZSTD_compressionParameters const* cParams = &ms->cParams;
U32 const mls = cParams->minMatch;
U32 const mls = ms->cParams.minMatch;
assert(ms->dictMatchState != NULL);
switch(mls)
{
@ -408,16 +403,17 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
const U32 repIndex = current + 1 - offset_1;
const BYTE* const repBase = repIndex < prefixStartIndex ? dictBase : base;
const BYTE* const repMatch = repBase + repIndex;
size_t mLength;
hashTable[h] = current; /* update hash table */
assert(offset_1 <= current +1); /* check repIndex */
if ( (((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > dictStartIndex))
&& (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
mLength = ZSTD_count_2segments(ip+1 +4, repMatch +4, iend, repMatchEnd, prefixStart) + 4;
size_t const rLength = ZSTD_count_2segments(ip+1 +4, repMatch +4, iend, repMatchEnd, prefixStart) + 4;
ip++;
ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, 0, mLength-MINMATCH);
ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, 0, rLength-MINMATCH);
ip += rLength;
anchor = ip;
} else {
if ( (matchIndex < dictStartIndex) ||
(MEM_read32(match) != MEM_read32(ip)) ) {
@ -427,19 +423,15 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
}
{ const BYTE* const matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend;
const BYTE* const lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart;
U32 offset;
mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4;
U32 const offset = current - matchIndex;
size_t mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4;
while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
offset = current - matchIndex;
offset_2 = offset_1;
offset_1 = offset;
offset_2 = offset_1; offset_1 = offset; /* update offset history */
ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
ip += mLength;
anchor = ip;
} }
/* found a match : store it */
ip += mLength;
anchor = ip;
if (ip <= ilimit) {
/* Fill Table */
hashTable[ZSTD_hashPtr(base+current+2, hlog, mls)] = current+2;
@ -448,13 +440,13 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
while (ip <= ilimit) {
U32 const current2 = (U32)(ip-base);
U32 const repIndex2 = current2 - offset_2;
const BYTE* repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2;
const BYTE* const repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2;
if ( (((U32)((prefixStartIndex-1) - repIndex2) >= 3) & (repIndex2 > dictStartIndex)) /* intentional overflow */
&& (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
U32 const tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */
ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH);
{ U32 const tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; } /* swap offset_2 <=> offset_1 */
ZSTD_storeSeq(seqStore, 0 /*litlen*/, anchor, 0 /*offcode*/, repLength2-MINMATCH);
hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;
ip += repLength2;
anchor = ip;
@ -476,8 +468,7 @@ size_t ZSTD_compressBlock_fast_extDict(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize)
{
ZSTD_compressionParameters const* cParams = &ms->cParams;
U32 const mls = cParams->minMatch;
U32 const mls = ms->cParams.minMatch;
switch(mls)
{
default: /* includes case 3 */