ddidderr/zstd-rs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #2965 from facebook/offbase

Browse Source 
Converge sumtype (offset | repcode) numeric representation towards offBase
This commit is contained in:
Yann Collet
2022-01-24 15:47:42 -08:00
committed by GitHub
parent 70df5de1b2 03903f5701
commit cc7d23bcec
12 changed files with 275 additions and 218 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/compress/zstd_opt.c
+30 -30
View File
@@ -294,17 +294,17 @@ static U32 ZSTD_litLengthPrice(U32 const litLength, const optState_t* const optP
/* ZSTD_getMatchPrice() :
* Provides the cost of the match part (offset + matchLength) of a sequence
* Must be combined with ZSTD_fullLiteralsCost() to get the full cost of a sequence.
* @offcode : expects a scale where 0,1,2 are repcodes 1-3, and 3+ are real_offsets+2
* @offBase : sumtype, representing an offset or a repcode, and using numeric representation of ZSTD_storeSeq()
* @optLevel: when <2, favors small offset for decompression speed (improved cache efficiency)
*/
FORCE_INLINE_TEMPLATE U32
ZSTD_getMatchPrice(U32 const offcode,
ZSTD_getMatchPrice(U32 const offBase,
U32 const matchLength,
const optState_t* const optPtr,
int const optLevel)
{
U32 price;
U32 const offCode = ZSTD_highbit32(STORED_TO_OFFBASE(offcode));
U32 const offCode = ZSTD_highbit32(offBase);
U32 const mlBase = matchLength - MINMATCH;
assert(matchLength >= MINMATCH);
@@ -328,10 +328,10 @@ ZSTD_getMatchPrice(U32 const offcode,
}
/* ZSTD_updateStats() :
* assumption : literals + litLengtn <= iend */
* assumption : literals + litLength <= iend */
static void ZSTD_updateStats(optState_t* const optPtr,
U32 litLength, const BYTE* literals,
U32 offsetCode, U32 matchLength)
U32 offBase, U32 matchLength)
{
/* literals */
if (ZSTD_compressedLiterals(optPtr)) {
@@ -348,7 +348,7 @@ static void ZSTD_updateStats(optState_t* const optPtr,
}
/* offset code : expected to follow storeSeq() numeric representation */
{ U32 const offCode = ZSTD_highbit32(STORED_TO_OFFBASE(offsetCode));
{ U32 const offCode = ZSTD_highbit32(offBase);
assert(offCode <= MaxOff);
optPtr->offCodeFreq[offCode]++;
optPtr->offCodeSum++;
@@ -647,7 +647,7 @@ U32 ZSTD_insertBtAndGetAllMatches (
DEBUGLOG(8, "found repCode %u (ll0:%u, offset:%u) of length %u",
repCode, ll0, repOffset, repLen);
bestLength = repLen;
matches[mnum].off = STORE_REPCODE(repCode - ll0 + 1); /* expect value between 1 and 3 */
matches[mnum].off = REPCODE_TO_OFFBASE(repCode - ll0 + 1); /* expect value between 1 and 3 */
matches[mnum].len = (U32)repLen;
mnum++;
if ( (repLen > sufficient_len)
@@ -676,7 +676,7 @@ U32 ZSTD_insertBtAndGetAllMatches (
bestLength = mlen;
assert(curr > matchIndex3);
assert(mnum==0); /* no prior solution */
matches[0].off = STORE_OFFSET(curr - matchIndex3);
matches[0].off = OFFSET_TO_OFFBASE(curr - matchIndex3);
matches[0].len = (U32)mlen;
mnum = 1;
if ( (mlen > sufficient_len) |
@@ -709,13 +709,13 @@ U32 ZSTD_insertBtAndGetAllMatches (
}
if (matchLength > bestLength) {
DEBUGLOG(8, "found match of length %u at distance %u (offCode=%u)",
(U32)matchLength, curr - matchIndex, STORE_OFFSET(curr - matchIndex));
DEBUGLOG(8, "found match of length %u at distance %u (offBase=%u)",
(U32)matchLength, curr - matchIndex, OFFSET_TO_OFFBASE(curr - matchIndex));
assert(matchEndIdx > matchIndex);
if (matchLength > matchEndIdx - matchIndex)
matchEndIdx = matchIndex + (U32)matchLength;
bestLength = matchLength;
matches[mnum].off = STORE_OFFSET(curr - matchIndex);
matches[mnum].off = OFFSET_TO_OFFBASE(curr - matchIndex);
matches[mnum].len = (U32)matchLength;
mnum++;
if ( (matchLength > ZSTD_OPT_NUM)
@@ -757,12 +757,12 @@ U32 ZSTD_insertBtAndGetAllMatches (
if (matchLength > bestLength) {
matchIndex = dictMatchIndex + dmsIndexDelta;
DEBUGLOG(8, "found dms match of length %u at distance %u (offCode=%u)",
(U32)matchLength, curr - matchIndex, STORE_OFFSET(curr - matchIndex));
DEBUGLOG(8, "found dms match of length %u at distance %u (offBase=%u)",
(U32)matchLength, curr - matchIndex, OFFSET_TO_OFFBASE(curr - matchIndex));
if (matchLength > matchEndIdx - matchIndex)
matchEndIdx = matchIndex + (U32)matchLength;
bestLength = matchLength;
matches[mnum].off = STORE_OFFSET(curr - matchIndex);
matches[mnum].off = OFFSET_TO_OFFBASE(curr - matchIndex);
matches[mnum].len = (U32)matchLength;
mnum++;
if ( (matchLength > ZSTD_OPT_NUM)
@@ -963,7 +963,7 @@ static void ZSTD_optLdm_maybeAddMatch(ZSTD_match_t* matches, U32* nbMatches,
const ZSTD_optLdm_t* optLdm, U32 currPosInBlock)
{
U32 const posDiff = currPosInBlock - optLdm->startPosInBlock;
/* Note: ZSTD_match_t actually contains offCode and matchLength (before subtracting MINMATCH) */
/* Note: ZSTD_match_t actually contains offBase and matchLength (before subtracting MINMATCH) */
U32 const candidateMatchLength = optLdm->endPosInBlock - optLdm->startPosInBlock - posDiff;
/* Ensure that current block position is not outside of the match */
@@ -974,11 +974,11 @@ static void ZSTD_optLdm_maybeAddMatch(ZSTD_match_t* matches, U32* nbMatches,
}
if (*nbMatches == 0 || ((candidateMatchLength > matches[*nbMatches-1].len) && *nbMatches < ZSTD_OPT_NUM)) {
U32 const candidateOffCode = STORE_OFFSET(optLdm->offset);
DEBUGLOG(6, "ZSTD_optLdm_maybeAddMatch(): Adding ldm candidate match (offCode: %u matchLength %u) at block position=%u",
candidateOffCode, candidateMatchLength, currPosInBlock);
U32 const candidateOffBase = OFFSET_TO_OFFBASE(optLdm->offset);
DEBUGLOG(6, "ZSTD_optLdm_maybeAddMatch(): Adding ldm candidate match (offBase: %u matchLength %u) at block position=%u",
candidateOffBase, candidateMatchLength, currPosInBlock);
matches[*nbMatches].len = candidateMatchLength;
matches[*nbMatches].off = candidateOffCode;
matches[*nbMatches].off = candidateOffBase;
(*nbMatches)++;
}
}
@@ -1101,14 +1101,14 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
/* large match -> immediate encoding */
{ U32 const maxML = matches[nbMatches-1].len;
U32 const maxOffcode = matches[nbMatches-1].off;
DEBUGLOG(6, "found %u matches of maxLength=%u and maxOffCode=%u at cPos=%u => start new series",
nbMatches, maxML, maxOffcode, (U32)(ip-prefixStart));
U32 const maxOffBase = matches[nbMatches-1].off;
DEBUGLOG(6, "found %u matches of maxLength=%u and maxOffBase=%u at cPos=%u => start new series",
nbMatches, maxML, maxOffBase, (U32)(ip-prefixStart));
if (maxML > sufficient_len) {
lastSequence.litlen = litlen;
lastSequence.mlen = maxML;
lastSequence.off = maxOffcode;
lastSequence.off = maxOffBase;
DEBUGLOG(6, "large match (%u>%u), immediate encoding",
maxML, sufficient_len);
cur = 0;
@@ -1125,15 +1125,15 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
opt[pos].price = ZSTD_MAX_PRICE; /* mlen, litlen and price will be fixed during forward scanning */
}
for (matchNb = 0; matchNb < nbMatches; matchNb++) {
U32 const offcode = matches[matchNb].off;
U32 const offBase = matches[matchNb].off;
U32 const end = matches[matchNb].len;
for ( ; pos <= end ; pos++ ) {
U32 const matchPrice = ZSTD_getMatchPrice(offcode, pos, optStatePtr, optLevel);
U32 const matchPrice = ZSTD_getMatchPrice(offBase, pos, optStatePtr, optLevel);
U32 const sequencePrice = literalsPrice + matchPrice;
DEBUGLOG(7, "rPos:%u => set initial price : %.2f",
pos, ZSTD_fCost(sequencePrice));
opt[pos].mlen = pos;
opt[pos].off = offcode;
opt[pos].off = offBase;
opt[pos].litlen = litlen;
opt[pos].price = (int)sequencePrice;
} }
@@ -1233,7 +1233,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
U32 const startML = (matchNb>0) ? matches[matchNb-1].len+1 : minMatch;
U32 mlen;
DEBUGLOG(7, "testing match %u => offCode=%4u, mlen=%2u, llen=%2u",
DEBUGLOG(7, "testing match %u => offBase=%4u, mlen=%2u, llen=%2u",
matchNb, matches[matchNb].off, lastML, litlen);
for (mlen = lastML; mlen >= startML; mlen--) { /* scan downward */
@@ -1299,7 +1299,7 @@ _shortestPath: /* cur, last_pos, best_mlen, best_off have to be set */
for (storePos=storeStart; storePos <= storeEnd; storePos++) {
U32 const llen = opt[storePos].litlen;
U32 const mlen = opt[storePos].mlen;
U32 const offCode = opt[storePos].off;
U32 const offBase = opt[storePos].off;
U32 const advance = llen + mlen;
DEBUGLOG(6, "considering seq starting at %zi, llen=%u, mlen=%u",
anchor - istart, (unsigned)llen, (unsigned)mlen);
@@ -1311,8 +1311,8 @@ _shortestPath: /* cur, last_pos, best_mlen, best_off have to be set */
}
assert(anchor + llen <= iend);
ZSTD_updateStats(optStatePtr, llen, anchor, offCode, mlen);
ZSTD_storeSeq(seqStore, llen, anchor, iend, offCode, mlen);
ZSTD_updateStats(optStatePtr, llen, anchor, offBase, mlen);
ZSTD_storeSeq(seqStore, llen, anchor, iend, offBase, mlen);
anchor += advance;
ip = anchor;
} }