diff --git a/lib/compress/huf_compress.c b/lib/compress/huf_compress.c index e94b398da87..9a4cde6f28e 100644 --- a/lib/compress/huf_compress.c +++ b/lib/compress/huf_compress.c @@ -1261,28 +1261,35 @@ unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxS if (depthMode == HUF_depth_optimal) { /** Test valid depths and return optimal **/ BYTE* dst = (BYTE*)workSpace + sizeof(HUF_WriteCTableWksp); size_t dstSize = wkspSize - sizeof(HUF_WriteCTableWksp); - size_t optSize = ((size_t) ~0); - unsigned huffLog; size_t maxBits, hSize, newSize; const unsigned symbolCardinality = HUF_cardinality(count, maxSymbolValue); + const unsigned minTableLog = HUF_minTableLog(symbolCardinality); + size_t optSize = ((size_t) ~0) - 1; + unsigned optLogGuess; - if (wkspSize < sizeof(HUF_buildCTable_wksp_tables)) return optLog; + if (wkspSize < sizeof(HUF_buildCTable_wksp_tables)) return optLog; /** Assert workspace is large enough **/ + + /* Search until size increases */ + for (optLogGuess = minTableLog; optLogGuess <= maxTableLog; optLogGuess++) { + maxBits = HUF_buildCTable_wksp(table, count, maxSymbolValue, optLogGuess, workSpace, wkspSize); - for (huffLog = HUF_minTableLog(symbolCardinality); huffLog <= maxTableLog; huffLog++) { - maxBits = HUF_buildCTable_wksp(table, count, - maxSymbolValue, huffLog, - workSpace, wkspSize); if (ERR_isError(maxBits)) continue; - hSize = HUF_writeCTable_wksp(dst, dstSize, table, maxSymbolValue, (U32)maxBits, - workSpace, wkspSize); + if (maxBits < optLogGuess && optLogGuess > minTableLog) break; + + hSize = HUF_writeCTable_wksp(dst, dstSize, table, maxSymbolValue, (U32)maxBits, workSpace, wkspSize); + if (ERR_isError(hSize)) continue; newSize = HUF_estimateCompressedSize(table, count, maxSymbolValue) + hSize; + if (newSize > optSize + 1) { + break; + } + if (newSize < optSize) { optSize = newSize; - optLog = huffLog; + optLog = optLogGuess; } } } diff --git a/tests/regression/results.csv b/tests/regression/results.csv index dee7d572169..4a44dbb0048 100644 --- a/tests/regression/results.csv +++ b/tests/regression/results.csv @@ -12,9 +12,9 @@ silesia.tar, level 7, compress silesia.tar, level 9, compress simple, 4552899 silesia.tar, level 13, compress simple, 4502956 silesia.tar, level 16, compress simple, 4360527 -silesia.tar, level 19, compress simple, 4266970 +silesia.tar, level 19, compress simple, 4267021 silesia.tar, uncompressed literals, compress simple, 4854086 -silesia.tar, uncompressed literals optimal, compress simple, 4266970 +silesia.tar, uncompressed literals optimal, compress simple, 4267021 silesia.tar, huffman literals, compress simple, 6179047 github.tar, level -5, compress simple, 52115 github.tar, level -3, compress simple, 45678 @@ -135,7 +135,7 @@ silesia.tar, level 7, zstdcli, silesia.tar, level 9, zstdcli, 4552903 silesia.tar, level 13, zstdcli, 4502960 silesia.tar, level 16, zstdcli, 4360531 -silesia.tar, level 19, zstdcli, 4266974 +silesia.tar, level 19, zstdcli, 4267025 silesia.tar, no source size, zstdcli, 4854160 silesia.tar, long distance mode, zstdcli, 4845745 silesia.tar, multithreaded, zstdcli, 4854164 @@ -283,7 +283,7 @@ silesia.tar, level 12 row 1, advanced silesia.tar, level 12 row 2, advanced one pass, 4513797 silesia.tar, level 13, advanced one pass, 4502956 silesia.tar, level 16, advanced one pass, 4360527 -silesia.tar, level 19, advanced one pass, 4266970 +silesia.tar, level 19, advanced one pass, 4267021 silesia.tar, no source size, advanced one pass, 4854086 silesia.tar, long distance mode, advanced one pass, 4840452 silesia.tar, multithreaded, advanced one pass, 4854160 @@ -601,7 +601,7 @@ silesia.tar, level 12 row 1, advanced silesia.tar, level 12 row 2, advanced one pass small out, 4513797 silesia.tar, level 13, advanced one pass small out, 4502956 silesia.tar, level 16, advanced one pass small out, 4360527 -silesia.tar, level 19, advanced one pass small out, 4266970 +silesia.tar, level 19, advanced one pass small out, 4267021 silesia.tar, no source size, advanced one pass small out, 4854086 silesia.tar, long distance mode, advanced one pass small out, 4840452 silesia.tar, multithreaded, advanced one pass small out, 4854160 @@ -919,7 +919,7 @@ silesia.tar, level 12 row 1, advanced silesia.tar, level 12 row 2, advanced streaming, 4513797 silesia.tar, level 13, advanced streaming, 4502956 silesia.tar, level 16, advanced streaming, 4360527 -silesia.tar, level 19, advanced streaming, 4266970 +silesia.tar, level 19, advanced streaming, 4267021 silesia.tar, no source size, advanced streaming, 4859267 silesia.tar, long distance mode, advanced streaming, 4840452 silesia.tar, multithreaded, advanced streaming, 4854160 @@ -1213,10 +1213,10 @@ silesia.tar, level 7, old stre silesia.tar, level 9, old streaming, 4552900 silesia.tar, level 13, old streaming, 4502956 silesia.tar, level 16, old streaming, 4360527 -silesia.tar, level 19, old streaming, 4266970 +silesia.tar, level 19, old streaming, 4267021 silesia.tar, no source size, old streaming, 4859267 silesia.tar, uncompressed literals, old streaming, 4859271 -silesia.tar, uncompressed literals optimal, old streaming, 4266970 +silesia.tar, uncompressed literals optimal, old streaming, 4267021 silesia.tar, huffman literals, old streaming, 6179056 github, level -5, old streaming, 204407 github, level -5 with dict, old streaming, 46718 @@ -1323,7 +1323,7 @@ silesia.tar, level 7, old stre silesia.tar, level 9, old streaming advanced, 4552900 silesia.tar, level 13, old streaming advanced, 4502956 silesia.tar, level 16, old streaming advanced, 4360527 -silesia.tar, level 19, old streaming advanced, 4266970 +silesia.tar, level 19, old streaming advanced, 4267021 silesia.tar, no source size, old streaming advanced, 4859267 silesia.tar, long distance mode, old streaming advanced, 4859271 silesia.tar, multithreaded, old streaming advanced, 4859271 @@ -1333,7 +1333,7 @@ silesia.tar, small hash log, old stre silesia.tar, small chain log, old streaming advanced, 4917021 silesia.tar, explicit params, old streaming advanced, 4806873 silesia.tar, uncompressed literals, old streaming advanced, 4859271 -silesia.tar, uncompressed literals optimal, old streaming advanced, 4266970 +silesia.tar, uncompressed literals optimal, old streaming advanced, 4267021 silesia.tar, huffman literals, old streaming advanced, 6179056 silesia.tar, multithreaded with advanced params, old streaming advanced, 4859271 github, level -5, old streaming advanced, 213265