Merge pull request #1622 from facebook/nextToUpdate3

nextToUpdate3 does not need to be maintained outside of zstd_opt.c

lib/compress/zstd_compress.c

@@ -1290,7 +1290,6 @@ static void ZSTD_invalidateMatchState(ZSTD_matchState_t* ms)
     ZSTD_window_clear(&ms->window);
 
     ms->nextToUpdate = ms->window.dictLimit;
-    ms->nextToUpdate3 = ms->window.dictLimit;
     ms->loadedDictEnd = 0;
     ms->opt.litLengthSum = 0;  /* force reset of btopt stats */
     ms->dictMatchState = NULL;
@@ -1679,7 +1678,6 @@ static size_t ZSTD_resetCCtx_byCopyingCDict(ZSTD_CCtx* cctx,
         ZSTD_matchState_t* dstMatchState = &cctx->blockState.matchState;
         dstMatchState->window       = srcMatchState->window;
         dstMatchState->nextToUpdate = srcMatchState->nextToUpdate;
-        dstMatchState->nextToUpdate3= srcMatchState->nextToUpdate3;
         dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd;
     }
 
@@ -1759,7 +1757,6 @@ static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx,
         ZSTD_matchState_t* dstMatchState = &dstCCtx->blockState.matchState;
         dstMatchState->window       = srcMatchState->window;
         dstMatchState->nextToUpdate = srcMatchState->nextToUpdate;
-        dstMatchState->nextToUpdate3= srcMatchState->nextToUpdate3;
         dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd;
     }
     dstCCtx->dictID = srcCCtx->dictID;

lib/compress/zstd_compress_internal.h

@@ -134,9 +134,8 @@ typedef struct {
 typedef struct ZSTD_matchState_t ZSTD_matchState_t;
 struct ZSTD_matchState_t {
     ZSTD_window_t window;   /* State for window round buffer management */
-    U32 loadedDictEnd;      /* index of end of dictionary, within context's referential. When dict referential is copied into active context (i.e. not attached), effectively same value as dictSize, since referential starts at zero */
+    U32 loadedDictEnd;      /* index of end of dictionary, within context's referential. When dict referential is copied into active context (i.e. not attached), effectively same value as dictSize, since referential starts from zero */
     U32 nextToUpdate;       /* index from which to continue table update */
-    U32 nextToUpdate3;      /* index from which to continue table update of hashTable3 */
     U32 hashLog3;           /* dispatch table : larger == faster, more memory */
     U32* hashTable;
     U32* hashTable3;

lib/compress/zstd_lazy.c

@@ -653,7 +653,6 @@ size_t ZSTD_compressBlock_lazy_generic(
 
     /* init */
     ip += (dictAndPrefixLength == 0);
-    ms->nextToUpdate3 = ms->nextToUpdate;
     if (dictMode == ZSTD_noDict) {
         U32 const maxRep = (U32)(ip - prefixLowest);
         if (offset_2 > maxRep) savedOffset = offset_2, offset_2 = 0;
@@ -933,7 +932,6 @@ size_t ZSTD_compressBlock_lazy_extDict_generic(
     U32 offset_1 = rep[0], offset_2 = rep[1];
 
     /* init */
-    ms->nextToUpdate3 = ms->nextToUpdate;
     ip += (ip == prefixStart);
 
     /* Match Loop */

lib/compress/zstd_opt.c

@@ -255,13 +255,13 @@ static U32 ZSTD_litLengthPrice(U32 const litLength, const optState_t* const optP
  * to provide a cost which is directly comparable to a match ending at same position */
 static int ZSTD_litLengthContribution(U32 const litLength, const optState_t* const optPtr, int optLevel)
 {
-    if (optPtr->priceType >= zop_predef) return WEIGHT(litLength, optLevel);
+    if (optPtr->priceType >= zop_predef) return (int)WEIGHT(litLength, optLevel);
 
     /* dynamic statistics */
     {   U32 const llCode = ZSTD_LLcode(litLength);
-        int const contribution = (LL_bits[llCode] * BITCOST_MULTIPLIER)
+        int const contribution = (int)(LL_bits[llCode] * BITCOST_MULTIPLIER)
-                               + WEIGHT(optPtr->litLengthFreq[0], optLevel)   /* note: log2litLengthSum cancel out */
+                               + (int)WEIGHT(optPtr->litLengthFreq[0], optLevel)   /* note: log2litLengthSum cancel out */
-                               - WEIGHT(optPtr->litLengthFreq[llCode], optLevel);
+                               - (int)WEIGHT(optPtr->litLengthFreq[llCode], optLevel);
 #if 1
         return contribution;
 #else
@@ -278,7 +278,7 @@ static int ZSTD_literalsContribution(const BYTE* const literals, U32 const litLe
                                      const optState_t* const optPtr,
                                      int optLevel)
 {
-    int const contribution = ZSTD_rawLiteralsCost(literals, litLength, optPtr, optLevel)
+    int const contribution = (int)ZSTD_rawLiteralsCost(literals, litLength, optPtr, optLevel)
                            + ZSTD_litLengthContribution(litLength, optPtr, optLevel);
     return contribution;
 }
@@ -372,13 +372,15 @@ MEM_STATIC U32 ZSTD_readMINMATCH(const void* memPtr, U32 length)
 
 /* Update hashTable3 up to ip (excluded)
    Assumption : always within prefix (i.e. not within extDict) */
-static U32 ZSTD_insertAndFindFirstIndexHash3 (ZSTD_matchState_t* ms, const BYTE* const ip)
+static U32 ZSTD_insertAndFindFirstIndexHash3 (ZSTD_matchState_t* ms,
+                                              U32* nextToUpdate3,
+                                              const BYTE* const ip)
 {
     U32* const hashTable3 = ms->hashTable3;
     U32 const hashLog3 = ms->hashLog3;
     const BYTE* const base = ms->window.base;
-    U32 idx = ms->nextToUpdate3;
+    U32 idx = *nextToUpdate3;
-    U32 const target = ms->nextToUpdate3 = (U32)(ip - base);
+    U32 const target = (U32)(ip - base);
     size_t const hash3 = ZSTD_hash3Ptr(ip, hashLog3);
     assert(hashLog3 > 0);
 
@@ -387,6 +389,7 @@ static U32 ZSTD_insertAndFindFirstIndexHash3 (ZSTD_matchState_t* ms, const BYTE*
         idx++;
     }
 
+    *nextToUpdate3 = target;
     return hashTable3[hash3];
 }
 
@@ -531,11 +534,12 @@ void ZSTD_updateTree(ZSTD_matchState_t* ms, const BYTE* ip, const BYTE* iend) {
 
 FORCE_INLINE_TEMPLATE
 U32 ZSTD_insertBtAndGetAllMatches (
+                    ZSTD_match_t* matches,   /* store result (found matches) in this table (presumed large enough) */
                     ZSTD_matchState_t* ms,
+                    U32* nextToUpdate3,
                     const BYTE* const ip, const BYTE* const iLimit, const ZSTD_dictMode_e dictMode,
-                    U32 rep[ZSTD_REP_NUM],
+                    const U32 rep[ZSTD_REP_NUM],
                     U32 const ll0,   /* tells if associated literal length is 0 or not. This value must be 0 or 1 */
-                    ZSTD_match_t* matches,
                     const U32 lengthToBeat,
                     U32 const mls /* template */)
 {
@@ -627,7 +631,7 @@ U32 ZSTD_insertBtAndGetAllMatches (
 
     /* HC3 match finder */
     if ((mls == 3) /*static*/ && (bestLength < mls)) {
-        U32 const matchIndex3 = ZSTD_insertAndFindFirstIndexHash3(ms, ip);
+        U32 const matchIndex3 = ZSTD_insertAndFindFirstIndexHash3(ms, nextToUpdate3, ip);
         if ((matchIndex3 >= matchLow)
           & (current - matchIndex3 < (1<<18)) /*heuristic : longer distance likely too expensive*/ ) {
             size_t mlen;
@@ -653,9 +657,7 @@ U32 ZSTD_insertBtAndGetAllMatches (
                      (ip+mlen == iLimit) ) {  /* best possible length */
                     ms->nextToUpdate = current+1;  /* skip insertion */
                     return 1;
-                }
+        }   }   }
-            }
-        }
         /* no dictMatchState lookup: dicts don't have a populated HC3 table */
     }
 
@@ -760,10 +762,13 @@ U32 ZSTD_insertBtAndGetAllMatches (
 
 
 FORCE_INLINE_TEMPLATE U32 ZSTD_BtGetAllMatches (
+                        ZSTD_match_t* matches,   /* store result (match found, increasing size) in this table */
                         ZSTD_matchState_t* ms,
+                        U32* nextToUpdate3,
                         const BYTE* ip, const BYTE* const iHighLimit, const ZSTD_dictMode_e dictMode,
-                        U32 rep[ZSTD_REP_NUM], U32 const ll0,
+                        const U32 rep[ZSTD_REP_NUM],
-                        ZSTD_match_t* matches, U32 const lengthToBeat)
+                        U32 const ll0,
+                        U32 const lengthToBeat)
 {
     const ZSTD_compressionParameters* const cParams = &ms->cParams;
     U32 const matchLengthSearch = cParams->minMatch;
@@ -772,12 +777,12 @@ FORCE_INLINE_TEMPLATE U32 ZSTD_BtGetAllMatches (
     ZSTD_updateTree_internal(ms, ip, iHighLimit, matchLengthSearch, dictMode);
     switch(matchLengthSearch)
     {
-    case 3 : return ZSTD_insertBtAndGetAllMatches(ms, ip, iHighLimit, dictMode, rep, ll0, matches, lengthToBeat, 3);
+    case 3 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 3);
     default :
-    case 4 : return ZSTD_insertBtAndGetAllMatches(ms, ip, iHighLimit, dictMode, rep, ll0, matches, lengthToBeat, 4);
+    case 4 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 4);
-    case 5 : return ZSTD_insertBtAndGetAllMatches(ms, ip, iHighLimit, dictMode, rep, ll0, matches, lengthToBeat, 5);
+    case 5 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 5);
     case 7 :
-    case 6 : return ZSTD_insertBtAndGetAllMatches(ms, ip, iHighLimit, dictMode, rep, ll0, matches, lengthToBeat, 6);
+    case 6 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 6);
     }
 }
 
@@ -853,6 +858,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
 
     U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1);
     U32 const minMatch = (cParams->minMatch == 3) ? 3 : 4;
+    U32 nextToUpdate3 = ms->nextToUpdate;
 
     ZSTD_optimal_t* const opt = optStatePtr->priceTable;
     ZSTD_match_t* const matches = optStatePtr->matchTable;
@@ -862,7 +868,6 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
     DEBUGLOG(5, "ZSTD_compressBlock_opt_generic: current=%u, prefix=%u, nextToUpdate=%u",
                 (U32)(ip - base), ms->window.dictLimit, ms->nextToUpdate);
     assert(optLevel <= 2);
-    ms->nextToUpdate3 = ms->nextToUpdate;   /* note : why a separate nextToUpdate3 stored into cctx->ms if it's synchtonized from nextToUpdate anyway ? */
     ZSTD_rescaleFreqs(optStatePtr, (const BYTE*)src, srcSize, optLevel);
     ip += (ip==prefixStart);
 
@@ -873,7 +878,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
         /* find first match */
         {   U32 const litlen = (U32)(ip - anchor);
             U32 const ll0 = !litlen;
-            U32 const nbMatches = ZSTD_BtGetAllMatches(ms, ip, iend, dictMode, rep, ll0, matches, minMatch);
+            U32 const nbMatches = ZSTD_BtGetAllMatches(matches, ms, &nextToUpdate3, ip, iend, dictMode, rep, ll0, minMatch);
             if (!nbMatches) { ip++; continue; }
 
             /* initialize opt[0] */
@@ -970,7 +975,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
                 U32 const litlen = (opt[cur].mlen == 0) ? opt[cur].litlen : 0;
                 U32 const previousPrice = opt[cur].price;
                 U32 const basePrice = previousPrice + ZSTD_litLengthPrice(0, optStatePtr, optLevel);
-                U32 const nbMatches = ZSTD_BtGetAllMatches(ms, inr, iend, dictMode, opt[cur].rep, ll0, matches, minMatch);
+                U32 const nbMatches = ZSTD_BtGetAllMatches(matches, ms, &nextToUpdate3, inr, iend, dictMode, opt[cur].rep, ll0, minMatch);
                 U32 matchNb;
                 if (!nbMatches) {
                     DEBUGLOG(7, "rPos:%u : no match found", cur);
@@ -1094,7 +1099,7 @@ _shortestPath:   /* cur, last_pos, best_mlen, best_off have to be set */
     }   /* while (ip < ilimit) */
 
     /* Return the last literals size */
-    return iend - anchor;
+    return (size_t)(iend - anchor);
 }
 
 
@@ -1158,7 +1163,6 @@ ZSTD_initStats_ultra(ZSTD_matchState_t* ms,
     ms->window.dictLimit += (U32)srcSize;
     ms->window.lowLimit = ms->window.dictLimit;
     ms->nextToUpdate = ms->window.dictLimit;
-    ms->nextToUpdate3 = ms->window.dictLimit;
 
     /* re-inforce weight of collected statistics */
     ZSTD_upscaleStats(&ms->opt);