diff options
Diffstat (limited to 'Utilities/cmzstd/lib/compress/zstd_compress_sequences.c')
-rw-r--r-- | Utilities/cmzstd/lib/compress/zstd_compress_sequences.c | 36 |
1 files changed, 29 insertions, 7 deletions
diff --git a/Utilities/cmzstd/lib/compress/zstd_compress_sequences.c b/Utilities/cmzstd/lib/compress/zstd_compress_sequences.c index f9f8097c83..611eabdcbb 100644 --- a/Utilities/cmzstd/lib/compress/zstd_compress_sequences.c +++ b/Utilities/cmzstd/lib/compress/zstd_compress_sequences.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc. + * Copyright (c) Yann Collet, Facebook, Inc. * All rights reserved. * * This source code is licensed under both the BSD-style license (found in the @@ -51,6 +51,19 @@ static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) { } /** + * Returns true if we should use ncount=-1 else we should + * use ncount=1 for low probability symbols instead. + */ +static unsigned ZSTD_useLowProbCount(size_t const nbSeq) +{ + /* Heuristic: This should cover most blocks <= 16K and + * start to fade out after 16K to about 32K depending on + * comprssibility. + */ + return nbSeq >= 2048; +} + +/** * Returns the cost in bytes of encoding the normalized count header. * Returns an error if any of the helper functions return an error. */ @@ -60,7 +73,7 @@ static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max, BYTE wksp[FSE_NCOUNTBOUND]; S16 norm[MaxSeq + 1]; const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max); - FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max), ""); + FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max, ZSTD_useLowProbCount(nbSeq)), ""); return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog); } @@ -72,6 +85,8 @@ static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t { unsigned cost = 0; unsigned s; + + assert(total > 0); for (s = 0; s <= max; ++s) { unsigned norm = (unsigned)((256 * count[s]) / total); if (count[s] != 0 && norm == 0) @@ -219,6 +234,11 @@ ZSTD_selectEncodingType( return set_compressed; } +typedef struct { + S16 norm[MaxSeq + 1]; + U32 wksp[FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(MaxSeq, MaxFSELog)]; +} ZSTD_BuildCTableWksp; + size_t ZSTD_buildCTable(void* dst, size_t dstCapacity, FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type, @@ -239,13 +259,13 @@ ZSTD_buildCTable(void* dst, size_t dstCapacity, *op = codeTable[0]; return 1; case set_repeat: - memcpy(nextCTable, prevCTable, prevCTableSize); + ZSTD_memcpy(nextCTable, prevCTable, prevCTableSize); return 0; case set_basic: FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, entropyWorkspace, entropyWorkspaceSize), ""); /* note : could be pre-calculated */ return 0; case set_compressed: { - S16 norm[MaxSeq + 1]; + ZSTD_BuildCTableWksp* wksp = (ZSTD_BuildCTableWksp*)entropyWorkspace; size_t nbSeq_1 = nbSeq; const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max); if (count[codeTable[nbSeq-1]] > 1) { @@ -253,10 +273,12 @@ ZSTD_buildCTable(void* dst, size_t dstCapacity, nbSeq_1--; } assert(nbSeq_1 > 1); - FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max), ""); - { size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */ + assert(entropyWorkspaceSize >= sizeof(ZSTD_BuildCTableWksp)); + (void)entropyWorkspaceSize; + FORWARD_IF_ERROR(FSE_normalizeCount(wksp->norm, tableLog, count, nbSeq_1, max, ZSTD_useLowProbCount(nbSeq_1)), ""); + { size_t const NCountSize = FSE_writeNCount(op, oend - op, wksp->norm, max, tableLog); /* overflow protected */ FORWARD_IF_ERROR(NCountSize, "FSE_writeNCount failed"); - FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, entropyWorkspace, entropyWorkspaceSize), ""); + FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, wksp->norm, max, tableLog, wksp->wksp, sizeof(wksp->wksp)), ""); return NCountSize; } } |