sharpetronics/zstd
1
0
Fork 0
mirror of https://github.com/facebook/zstd.git synced 2025-10-09 00:05:28 -04:00
Code Issues Projects Releases Wiki Activity

Simplify DMS Implementation by Removing noDict Support

Browse Source
This commit is contained in:
W. Felix Handte 2021-09-09 17:01:31 -04:00
parent 051b473e7e
commit 62536ef7da
1 changed files with 50 additions and 101 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

107
lib/compress/zstd_double_fast.c
View File

@ -254,10 +254,10 @@ _match_stored:
FORCE_INLINE_TEMPLATE FORCE_INLINE_TEMPLATE
size_t ZSTD_compressBlock_doubleFast_generic( size_t ZSTD_compressBlock_doubleFast_dictMatchState_generic(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize, void const* src, size_t srcSize,
U32 const mls /* template */, ZSTD_dictMode_e const dictMode) U32 const mls /* template */)
{ {
ZSTD_compressionParameters const* cParams = &ms->cParams; ZSTD_compressionParameters const* cParams = &ms->cParams;
U32* const hashLong = ms->hashTable; U32* const hashLong = ms->hashTable;
@ -278,54 +278,30 @@ size_t ZSTD_compressBlock_doubleFast_generic(
U32 offsetSaved = 0; U32 offsetSaved = 0;
const ZSTD_matchState_t* const dms = ms->dictMatchState; const ZSTD_matchState_t* const dms = ms->dictMatchState;
const ZSTD_compressionParameters* const dictCParams = const ZSTD_compressionParameters* const dictCParams = &dms->cParams;
dictMode == ZSTD_dictMatchState ? const U32* const dictHashLong = dms->hashTable;
&dms->cParams : NULL; const U32* const dictHashSmall = dms->chainTable;
const U32* const dictHashLong = dictMode == ZSTD_dictMatchState ? const U32 dictStartIndex = dms->window.dictLimit;
dms->hashTable : NULL; const BYTE* const dictBase = dms->window.base;
const U32* const dictHashSmall = dictMode == ZSTD_dictMatchState ? const BYTE* const dictStart = dictBase + dictStartIndex;
dms->chainTable : NULL; const BYTE* const dictEnd = dms->window.nextSrc;
const U32 dictStartIndex = dictMode == ZSTD_dictMatchState ? const U32 dictIndexDelta = prefixLowestIndex - (U32)(dictEnd - dictBase);
dms->window.dictLimit : 0; const U32 dictHBitsL = dictCParams->hashLog;
const BYTE* const dictBase = dictMode == ZSTD_dictMatchState ? const U32 dictHBitsS = dictCParams->chainLog;
dms->window.base : NULL;
const BYTE* const dictStart = dictMode == ZSTD_dictMatchState ?
dictBase + dictStartIndex : NULL;
const BYTE* const dictEnd = dictMode == ZSTD_dictMatchState ?
dms->window.nextSrc : NULL;
const U32 dictIndexDelta = dictMode == ZSTD_dictMatchState ?
prefixLowestIndex - (U32)(dictEnd - dictBase) :
0;
const U32 dictHBitsL = dictMode == ZSTD_dictMatchState ?
dictCParams->hashLog : hBitsL;
const U32 dictHBitsS = dictMode == ZSTD_dictMatchState ?
dictCParams->chainLog : hBitsS;
const U32 dictAndPrefixLength = (U32)((ip - prefixLowest) + (dictEnd - dictStart)); const U32 dictAndPrefixLength = (U32)((ip - prefixLowest) + (dictEnd - dictStart));
DEBUGLOG(5, "ZSTD_compressBlock_doubleFast_generic"); DEBUGLOG(5, "ZSTD_compressBlock_doubleFast_dictMatchState_generic");
assert(dictMode == ZSTD_noDict || dictMode == ZSTD_dictMatchState);
/* if a dictionary is attached, it must be within window range */ /* if a dictionary is attached, it must be within window range */
if (dictMode == ZSTD_dictMatchState) {
assert(ms->window.dictLimit + (1U << cParams->windowLog) >= endIndex); assert(ms->window.dictLimit + (1U << cParams->windowLog) >= endIndex);
}
/* init */ /* init */
ip += (dictAndPrefixLength == 0); ip += (dictAndPrefixLength == 0);
if (dictMode == ZSTD_noDict) {
U32 const curr = (U32)(ip - base);
U32 const windowLow = ZSTD_getLowestPrefixIndex(ms, curr, cParams->windowLog);
U32 const maxRep = curr - windowLow;
if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0;
if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0;
}
if (dictMode == ZSTD_dictMatchState) {
/* dictMatchState repCode checks don't currently handle repCode == 0 /* dictMatchState repCode checks don't currently handle repCode == 0
* disabling. */ * disabling. */
assert(offset_1 <= dictAndPrefixLength); assert(offset_1 <= dictAndPrefixLength);
assert(offset_2 <= dictAndPrefixLength); assert(offset_2 <= dictAndPrefixLength);
}
/* Main Search Loop */ /* Main Search Loop */
while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */ while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */
@ -341,15 +317,13 @@ size_t ZSTD_compressBlock_doubleFast_generic(
const BYTE* matchLong = base + matchIndexL; const BYTE* matchLong = base + matchIndexL;
const BYTE* match = base + matchIndexS; const BYTE* match = base + matchIndexS;
const U32 repIndex = curr + 1 - offset_1; const U32 repIndex = curr + 1 - offset_1;
const BYTE* repMatch = (dictMode == ZSTD_dictMatchState const BYTE* repMatch = (repIndex < prefixLowestIndex) ?
&& repIndex < prefixLowestIndex) ?
dictBase + (repIndex - dictIndexDelta) : dictBase + (repIndex - dictIndexDelta) :
base + repIndex; base + repIndex;
hashLong[h2] = hashSmall[h] = curr; /* update hash tables */ hashLong[h2] = hashSmall[h] = curr; /* update hash tables */
/* check dictMatchState repcode */ /* check repcode */
if (dictMode == ZSTD_dictMatchState if (((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */)
&& ((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */)
&& (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend; const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend;
mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixLowest) + 4; mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixLowest) + 4;
@ -358,15 +332,6 @@ size_t ZSTD_compressBlock_doubleFast_generic(
goto _match_stored; goto _match_stored;
} }
/* check noDict repcode */
if ( dictMode == ZSTD_noDict
&& ((offset_1 > 0) & (MEM_read32(ip+1-offset_1) == MEM_read32(ip+1)))) {
mLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4;
ip++;
ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, mLength-MINMATCH);
goto _match_stored;
}
if (matchIndexL > prefixLowestIndex) { if (matchIndexL > prefixLowestIndex) {
/* check prefix long match */ /* check prefix long match */
if (MEM_read64(matchLong) == MEM_read64(ip)) { if (MEM_read64(matchLong) == MEM_read64(ip)) {
@ -375,7 +340,7 @@ size_t ZSTD_compressBlock_doubleFast_generic(
while (((ip>anchor) & (matchLong>prefixLowest)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; } /* catch up */ while (((ip>anchor) & (matchLong>prefixLowest)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; } /* catch up */
goto _match_found; goto _match_found;
} }
} else if (dictMode == ZSTD_dictMatchState) { } else {
/* check dictMatchState long match */ /* check dictMatchState long match */
U32 const dictMatchIndexL = dictHashLong[dictHL]; U32 const dictMatchIndexL = dictHashLong[dictHL];
const BYTE* dictMatchL = dictBase + dictMatchIndexL; const BYTE* dictMatchL = dictBase + dictMatchIndexL;
@ -393,7 +358,7 @@ size_t ZSTD_compressBlock_doubleFast_generic(
if (MEM_read32(match) == MEM_read32(ip)) { if (MEM_read32(match) == MEM_read32(ip)) {
goto _search_next_long; goto _search_next_long;
} }
} else if (dictMode == ZSTD_dictMatchState) { } else {
/* check dictMatchState short match */ /* check dictMatchState short match */
U32 const dictMatchIndexS = dictHashSmall[dictHS]; U32 const dictMatchIndexS = dictHashSmall[dictHS];
match = dictBase + dictMatchIndexS; match = dictBase + dictMatchIndexS;
@ -426,7 +391,7 @@ _search_next_long:
while (((ip>anchor) & (matchL3>prefixLowest)) && (ip[-1] == matchL3[-1])) { ip--; matchL3--; mLength++; } /* catch up */ while (((ip>anchor) & (matchL3>prefixLowest)) && (ip[-1] == matchL3[-1])) { ip--; matchL3--; mLength++; } /* catch up */
goto _match_found; goto _match_found;
} }
} else if (dictMode == ZSTD_dictMatchState) { } else {
/* check dict long +1 match */ /* check dict long +1 match */
U32 const dictMatchIndexL3 = dictHashLong[dictHLNext]; U32 const dictMatchIndexL3 = dictHashLong[dictHLNext];
const BYTE* dictMatchL3 = dictBase + dictMatchIndexL3; const BYTE* dictMatchL3 = dictBase + dictMatchIndexL3;
@ -440,7 +405,7 @@ _search_next_long:
} } } } } }
/* if no long +1 match, explore the short match we found */ /* if no long +1 match, explore the short match we found */
if (dictMode == ZSTD_dictMatchState && matchIndexS < prefixLowestIndex) { if (matchIndexS < prefixLowestIndex) {
mLength = ZSTD_count_2segments(ip+4, match+4, iend, dictEnd, prefixLowest) + 4; mLength = ZSTD_count_2segments(ip+4, match+4, iend, dictEnd, prefixLowest) + 4;
offset = (U32)(curr - matchIndexS); offset = (U32)(curr - matchIndexS);
while (((ip>anchor) & (match>dictStart)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ while (((ip>anchor) & (match>dictStart)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
@ -472,12 +437,10 @@ _match_stored:
} }
/* check immediate repcode */ /* check immediate repcode */
if (dictMode == ZSTD_dictMatchState) {
while (ip <= ilimit) { while (ip <= ilimit) {
U32 const current2 = (U32)(ip-base); U32 const current2 = (U32)(ip-base);
U32 const repIndex2 = current2 - offset_2; U32 const repIndex2 = current2 - offset_2;
const BYTE* repMatch2 = dictMode == ZSTD_dictMatchState const BYTE* repMatch2 = repIndex2 < prefixLowestIndex ?
&& repIndex2 < prefixLowestIndex ?
dictBase + repIndex2 - dictIndexDelta : dictBase + repIndex2 - dictIndexDelta :
base + repIndex2; base + repIndex2;
if ( ((U32)((prefixLowestIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */) if ( ((U32)((prefixLowestIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
@ -493,22 +456,8 @@ _match_stored:
continue; continue;
} }
break; break;
} } }
}
if (dictMode == ZSTD_noDict) {
while ( (ip <= ilimit)
&& ( (offset_2>0)
& (MEM_read32(ip) == MEM_read32(ip - offset_2)) )) {
/* store sequence */
size_t const rLength = ZSTD_count(ip+4, ip+4-offset_2, iend) + 4;
U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff; /* swap offset_2 <=> offset_1 */
hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = (U32)(ip-base);
hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = (U32)(ip-base);
ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, rLength-MINMATCH);
ip += rLength;
anchor = ip;
continue; /* faster when present ... (?) */
} } }
} /* while (ip < ilimit) */ } /* while (ip < ilimit) */
/* save reps for next block */ /* save reps for next block */
@ -549,13 +498,13 @@ size_t ZSTD_compressBlock_doubleFast_dictMatchState(
{ {
default: /* includes case 3 */ default: /* includes case 3 */
case 4 : case 4 :
return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 4, ZSTD_dictMatchState); return ZSTD_compressBlock_doubleFast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 4);
case 5 : case 5 :
return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 5, ZSTD_dictMatchState); return ZSTD_compressBlock_doubleFast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 5);
case 6 : case 6 :
return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 6, ZSTD_dictMatchState); return ZSTD_compressBlock_doubleFast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 6);
case 7 : case 7 :
return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 7, ZSTD_dictMatchState); return ZSTD_compressBlock_doubleFast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 7);
} }
} }