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

Merge pull request #1396 from facebook/huf_refactor

Browse Source 
refactor HUF_compress_internal for clarity
This commit is contained in:
Yann Collet
2018-10-29 13:06:45 -07:00
committed by GitHub
parent fc20b3c441 1866bd374a
commit ea966c8fb1
6 changed files with 87 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/compress/fse_compress.c
+1 -1
View File
@@ -672,7 +672,7 @@ size_t FSE_compress_wksp (void* dst, size_t dstSize, const void* src, size_t src
if (!tableLog) tableLog = FSE_DEFAULT_TABLELOG; if (!tableLog) tableLog = FSE_DEFAULT_TABLELOG;
/* Scan input and build symbol stats */ /* Scan input and build symbol stats */
{ CHECK_V_F(maxCount, HIST_count_wksp(count, &maxSymbolValue, src, srcSize, (unsigned*)scratchBuffer) ); { CHECK_V_F(maxCount, HIST_count_wksp(count, &maxSymbolValue, src, srcSize, scratchBuffer, scratchBufferSize) );
if (maxCount == srcSize) return 1; /* only a single symbol in src : rle */ if (maxCount == srcSize) return 1; /* only a single symbol in src : rle */
if (maxCount == 1) return 0; /* each symbol present maximum once => not compressible */ if (maxCount == 1) return 0; /* each symbol present maximum once => not compressible */
if (maxCount < (srcSize >> 7)) return 0; /* Heuristic : not compressible enough */ if (maxCount < (srcSize >> 7)) return 0; /* Heuristic : not compressible enough */
lib/compress/hist.c
+19 -11
View File
@@ -73,6 +73,7 @@ unsigned HIST_count_simple(unsigned* count, unsigned* maxSymbolValuePtr,
return largestCount; return largestCount;
} }
typedef enum { trustInput, checkMaxSymbolValue } HIST_checkInput_e;
/* HIST_count_parallel_wksp() : /* HIST_count_parallel_wksp() :
* store histogram into 4 intermediate tables, recombined at the end. * store histogram into 4 intermediate tables, recombined at the end.
@@ -85,8 +86,8 @@ unsigned HIST_count_simple(unsigned* count, unsigned* maxSymbolValuePtr,
static size_t HIST_count_parallel_wksp( static size_t HIST_count_parallel_wksp(
unsigned* count, unsigned* maxSymbolValuePtr, unsigned* count, unsigned* maxSymbolValuePtr,
const void* source, size_t sourceSize, const void* source, size_t sourceSize,
unsigned checkMax, HIST_checkInput_e check,
unsigned* const workSpace) U32* const workSpace)
{ {
const BYTE* ip = (const BYTE*)source; const BYTE* ip = (const BYTE*)source;
const BYTE* const iend = ip+sourceSize; const BYTE* const iend = ip+sourceSize;
@@ -137,7 +138,7 @@ static size_t HIST_count_parallel_wksp(
/* finish last symbols */ /* finish last symbols */
while (ip<iend) Counting1[*ip++]++; while (ip<iend) Counting1[*ip++]++;
if (checkMax) { /* verify stats will fit into destination table */ if (check) { /* verify stats will fit into destination table */
U32 s; for (s=255; s>maxSymbolValue; s--) { U32 s; for (s=255; s>maxSymbolValue; s--) {
Counting1[s] += Counting2[s] + Counting3[s] + Counting4[s]; Counting1[s] += Counting2[s] + Counting3[s] + Counting4[s];
if (Counting1[s]) return ERROR(maxSymbolValue_tooSmall); if (Counting1[s]) return ERROR(maxSymbolValue_tooSmall);
@@ -157,14 +158,18 @@ static size_t HIST_count_parallel_wksp(
/* HIST_countFast_wksp() : /* HIST_countFast_wksp() :
* Same as HIST_countFast(), but using an externally provided scratch buffer. * Same as HIST_countFast(), but using an externally provided scratch buffer.
* `workSpace` size must be table of >= HIST_WKSP_SIZE_U32 unsigned */ * `workSpace` is a writable buffer which must be 4-bytes aligned,
* `workSpaceSize` must be >= HIST_WKSP_SIZE
*/
size_t HIST_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr, size_t HIST_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
const void* source, size_t sourceSize, const void* source, size_t sourceSize,
unsigned* workSpace) void* workSpace, size_t workSpaceSize)
{ {
if (sourceSize < 1500) /* heuristic threshold */ if (sourceSize < 1500) /* heuristic threshold */
return HIST_count_simple(count, maxSymbolValuePtr, source, sourceSize); return HIST_count_simple(count, maxSymbolValuePtr, source, sourceSize);
return HIST_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, 0, workSpace); if ((size_t)workSpace & 3) return ERROR(GENERIC); /* must be aligned on 4-bytes boundaries */
if (workSpaceSize < HIST_WKSP_SIZE) return ERROR(workSpace_tooSmall);
return HIST_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, trustInput, (U32*)workSpace);
} }
/* fast variant (unsafe : won't check if src contains values beyond count[] limit) */ /* fast variant (unsafe : won't check if src contains values beyond count[] limit) */
@@ -172,24 +177,27 @@ size_t HIST_countFast(unsigned* count, unsigned* maxSymbolValuePtr,
const void* source, size_t sourceSize) const void* source, size_t sourceSize)
{ {
unsigned tmpCounters[HIST_WKSP_SIZE_U32]; unsigned tmpCounters[HIST_WKSP_SIZE_U32];
return HIST_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, tmpCounters); return HIST_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, tmpCounters, sizeof(tmpCounters));
} }
/* HIST_count_wksp() : /* HIST_count_wksp() :
* Same as HIST_count(), but using an externally provided scratch buffer. * Same as HIST_count(), but using an externally provided scratch buffer.
* `workSpace` size must be table of >= HIST_WKSP_SIZE_U32 unsigned */ * `workSpace` size must be table of >= HIST_WKSP_SIZE_U32 unsigned */
size_t HIST_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr, size_t HIST_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
const void* source, size_t sourceSize, unsigned* workSpace) const void* source, size_t sourceSize,
void* workSpace, size_t workSpaceSize)
{ {
if ((size_t)workSpace & 3) return ERROR(GENERIC); /* must be aligned on 4-bytes boundaries */
if (workSpaceSize < HIST_WKSP_SIZE) return ERROR(workSpace_tooSmall);
if (*maxSymbolValuePtr < 255) if (*maxSymbolValuePtr < 255)
return HIST_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, 1, workSpace); return HIST_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, checkMaxSymbolValue, (U32*)workSpace);
*maxSymbolValuePtr = 255; *maxSymbolValuePtr = 255;
return HIST_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, workSpace); return HIST_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, workSpace, workSpaceSize);
} }
size_t HIST_count(unsigned* count, unsigned* maxSymbolValuePtr, size_t HIST_count(unsigned* count, unsigned* maxSymbolValuePtr,
const void* src, size_t srcSize) const void* src, size_t srcSize)
{ {
unsigned tmpCounters[HIST_WKSP_SIZE_U32]; unsigned tmpCounters[HIST_WKSP_SIZE_U32];
return HIST_count_wksp(count, maxSymbolValuePtr, src, srcSize, tmpCounters); return HIST_count_wksp(count, maxSymbolValuePtr, src, srcSize, tmpCounters, sizeof(tmpCounters));
} }
lib/compress/hist.h
+11 -8
View File
@@ -41,11 +41,11 @@
/*! HIST_count(): /*! HIST_count():
* Provides the precise count of each byte within a table 'count'. * Provides the precise count of each byte within a table 'count'.
* 'count' is a table of unsigned int, of minimum size (*maxSymbolValuePtr+1). * 'count' is a table of unsigned int, of minimum size (*maxSymbolValuePtr+1).
* Updates *maxSymbolValuePtr with actual largest symbol value detected. * Updates *maxSymbolValuePtr with actual largest symbol value detected.
* @return : count of the most frequent symbol (which isn't identified). * @return : count of the most frequent symbol (which isn't identified).
* or an error code, which can be tested using HIST_isError(). * or an error code, which can be tested using HIST_isError().
* note : if return == srcSize, there is only one symbol. * note : if return == srcSize, there is only one symbol.
*/ */
size_t HIST_count(unsigned* count, unsigned* maxSymbolValuePtr, size_t HIST_count(unsigned* count, unsigned* maxSymbolValuePtr,
const void* src, size_t srcSize); const void* src, size_t srcSize);
@@ -56,14 +56,16 @@ unsigned HIST_isError(size_t code); /**< tells if a return value is an error co
/* --- advanced histogram functions --- */ /* --- advanced histogram functions --- */
#define HIST_WKSP_SIZE_U32 1024 #define HIST_WKSP_SIZE_U32 1024
#define HIST_WKSP_SIZE (HIST_WKSP_SIZE_U32 * sizeof(unsigned))
/** HIST_count_wksp() : /** HIST_count_wksp() :
* Same as HIST_count(), but using an externally provided scratch buffer. * Same as HIST_count(), but using an externally provided scratch buffer.
* Benefit is this function will use very little stack space. * Benefit is this function will use very little stack space.
* `workSpace` must be a table of unsigned of size >= HIST_WKSP_SIZE_U32 * `workSpace` is a writable buffer which must be 4-bytes aligned,
* `workSpaceSize` must be >= HIST_WKSP_SIZE
*/ */
size_t HIST_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr, size_t HIST_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
const void* src, size_t srcSize, const void* src, size_t srcSize,
unsigned* workSpace); void* workSpace, size_t workSpaceSize);
/** HIST_countFast() : /** HIST_countFast() :
* same as HIST_count(), but blindly trusts that all byte values within src are <= *maxSymbolValuePtr. * same as HIST_count(), but blindly trusts that all byte values within src are <= *maxSymbolValuePtr.
@@ -74,11 +76,12 @@ size_t HIST_countFast(unsigned* count, unsigned* maxSymbolValuePtr,
/** HIST_countFast_wksp() : /** HIST_countFast_wksp() :
* Same as HIST_countFast(), but using an externally provided scratch buffer. * Same as HIST_countFast(), but using an externally provided scratch buffer.
* `workSpace` must be a table of unsigned of size >= HIST_WKSP_SIZE_U32 * `workSpace` is a writable buffer which must be 4-bytes aligned,
* `workSpaceSize` must be >= HIST_WKSP_SIZE
*/ */
size_t HIST_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr, size_t HIST_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
const void* src, size_t srcSize, const void* src, size_t srcSize,
unsigned* workSpace); void* workSpace, size_t workSpaceSize);
/*! HIST_count_simple() : /*! HIST_count_simple() :
* Same as HIST_countFast(), this function is unsafe, * Same as HIST_countFast(), this function is unsafe,
lib/compress/huf_compress.c
+21 -20
View File
@@ -610,13 +610,14 @@ size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, si
return HUF_compress4X_usingCTable_internal(dst, dstSize, src, srcSize, CTable, /* bmi2 */ 0); return HUF_compress4X_usingCTable_internal(dst, dstSize, src, srcSize, CTable, /* bmi2 */ 0);
} }
typedef enum { HUF_singleStream, HUF_fourStreams } HUF_nbStreams_e;
static size_t HUF_compressCTable_internal( static size_t HUF_compressCTable_internal(
BYTE* const ostart, BYTE* op, BYTE* const oend, BYTE* const ostart, BYTE* op, BYTE* const oend,
const void* src, size_t srcSize, const void* src, size_t srcSize,
unsigned singleStream, const HUF_CElt* CTable, const int bmi2) HUF_nbStreams_e nbStreams, const HUF_CElt* CTable, const int bmi2)
{ {
size_t const cSize = singleStream ? size_t const cSize = (nbStreams==HUF_singleStream) ?
HUF_compress1X_usingCTable_internal(op, oend - op, src, srcSize, CTable, bmi2) : HUF_compress1X_usingCTable_internal(op, oend - op, src, srcSize, CTable, bmi2) :
HUF_compress4X_usingCTable_internal(op, oend - op, src, srcSize, CTable, bmi2); HUF_compress4X_usingCTable_internal(op, oend - op, src, srcSize, CTable, bmi2);
if (HUF_isError(cSize)) { return cSize; } if (HUF_isError(cSize)) { return cSize; }
@@ -635,14 +636,14 @@ typedef struct {
/* HUF_compress_internal() : /* HUF_compress_internal() :
* `workSpace` must a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */ * `workSpace` must a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */
static size_t HUF_compress_internal ( static size_t
void* dst, size_t dstSize, HUF_compress_internal (void* dst, size_t dstSize,
const void* src, size_t srcSize, const void* src, size_t srcSize,
unsigned maxSymbolValue, unsigned huffLog, unsigned maxSymbolValue, unsigned huffLog,
unsigned singleStream, HUF_nbStreams_e nbStreams,
void* workSpace, size_t wkspSize, void* workSpace, size_t wkspSize,
HUF_CElt* oldHufTable, HUF_repeat* repeat, int preferRepeat, HUF_CElt* oldHufTable, HUF_repeat* repeat, int preferRepeat,
const int bmi2) const int bmi2)
{ {
HUF_compress_tables_t* const table = (HUF_compress_tables_t*)workSpace; HUF_compress_tables_t* const table = (HUF_compress_tables_t*)workSpace;
BYTE* const ostart = (BYTE*)dst; BYTE* const ostart = (BYTE*)dst;
@@ -651,7 +652,7 @@ static size_t HUF_compress_internal (
/* checks & inits */ /* checks & inits */
if (((size_t)workSpace & 3) != 0) return ERROR(GENERIC); /* must be aligned on 4-bytes boundaries */ if (((size_t)workSpace & 3) != 0) return ERROR(GENERIC); /* must be aligned on 4-bytes boundaries */
if (wkspSize < sizeof(*table)) return ERROR(workSpace_tooSmall); if (wkspSize < HUF_WORKSPACE_SIZE) return ERROR(workSpace_tooSmall);
if (!srcSize) return 0; /* Uncompressed */ if (!srcSize) return 0; /* Uncompressed */
if (!dstSize) return 0; /* cannot fit anything within dst budget */ if (!dstSize) return 0; /* cannot fit anything within dst budget */
if (srcSize > HUF_BLOCKSIZE_MAX) return ERROR(srcSize_wrong); /* current block size limit */ if (srcSize > HUF_BLOCKSIZE_MAX) return ERROR(srcSize_wrong); /* current block size limit */
@@ -664,11 +665,11 @@ static size_t HUF_compress_internal (
if (preferRepeat && repeat && *repeat == HUF_repeat_valid) { if (preferRepeat && repeat && *repeat == HUF_repeat_valid) {
return HUF_compressCTable_internal(ostart, op, oend, return HUF_compressCTable_internal(ostart, op, oend,
src, srcSize, src, srcSize,
singleStream, oldHufTable, bmi2); nbStreams, oldHufTable, bmi2);
} }
/* Scan input and build symbol stats */ /* Scan input and build symbol stats */
{ CHECK_V_F(largest, HIST_count_wksp (table->count, &maxSymbolValue, (const BYTE*)src, srcSize, table->count) ); { CHECK_V_F(largest, HIST_count_wksp (table->count, &maxSymbolValue, (const BYTE*)src, srcSize, workSpace, wkspSize) );
if (largest == srcSize) { *ostart = ((const BYTE*)src)[0]; return 1; } /* single symbol, rle */ if (largest == srcSize) { *ostart = ((const BYTE*)src)[0]; return 1; } /* single symbol, rle */
if (largest <= (srcSize >> 7)+4) return 0; /* heuristic : probably not compressible enough */ if (largest <= (srcSize >> 7)+4) return 0; /* heuristic : probably not compressible enough */
} }
@@ -683,7 +684,7 @@ static size_t HUF_compress_internal (
if (preferRepeat && repeat && *repeat != HUF_repeat_none) { if (preferRepeat && repeat && *repeat != HUF_repeat_none) {
return HUF_compressCTable_internal(ostart, op, oend, return HUF_compressCTable_internal(ostart, op, oend,
src, srcSize, src, srcSize,
singleStream, oldHufTable, bmi2); nbStreams, oldHufTable, bmi2);
} }
/* Build Huffman Tree */ /* Build Huffman Tree */
@@ -706,7 +707,7 @@ static size_t HUF_compress_internal (
if (oldSize <= hSize + newSize || hSize + 12 >= srcSize) { if (oldSize <= hSize + newSize || hSize + 12 >= srcSize) {
return HUF_compressCTable_internal(ostart, op, oend, return HUF_compressCTable_internal(ostart, op, oend,
src, srcSize, src, srcSize,
singleStream, oldHufTable, bmi2); nbStreams, oldHufTable, bmi2);
} } } }
/* Use the new huffman table */ /* Use the new huffman table */
@@ -718,7 +719,7 @@ static size_t HUF_compress_internal (
} }
return HUF_compressCTable_internal(ostart, op, oend, return HUF_compressCTable_internal(ostart, op, oend,
src, srcSize, src, srcSize,
singleStream, table->CTable, bmi2); nbStreams, table->CTable, bmi2);
} }
@@ -728,7 +729,7 @@ size_t HUF_compress1X_wksp (void* dst, size_t dstSize,
void* workSpace, size_t wkspSize) void* workSpace, size_t wkspSize)
{ {
return HUF_compress_internal(dst, dstSize, src, srcSize, return HUF_compress_internal(dst, dstSize, src, srcSize,
maxSymbolValue, huffLog, 1 /*single stream*/, maxSymbolValue, huffLog, HUF_singleStream,
workSpace, wkspSize, workSpace, wkspSize,
NULL, NULL, 0, 0 /*bmi2*/); NULL, NULL, 0, 0 /*bmi2*/);
} }
@@ -740,7 +741,7 @@ size_t HUF_compress1X_repeat (void* dst, size_t dstSize,
HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2) HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2)
{ {
return HUF_compress_internal(dst, dstSize, src, srcSize, return HUF_compress_internal(dst, dstSize, src, srcSize,
maxSymbolValue, huffLog, 1 /*single stream*/, maxSymbolValue, huffLog, HUF_singleStream,
workSpace, wkspSize, hufTable, workSpace, wkspSize, hufTable,
repeat, preferRepeat, bmi2); repeat, preferRepeat, bmi2);
} }
@@ -762,7 +763,7 @@ size_t HUF_compress4X_wksp (void* dst, size_t dstSize,
void* workSpace, size_t wkspSize) void* workSpace, size_t wkspSize)
{ {
return HUF_compress_internal(dst, dstSize, src, srcSize, return HUF_compress_internal(dst, dstSize, src, srcSize,
maxSymbolValue, huffLog, 0 /*4 streams*/, maxSymbolValue, huffLog, HUF_fourStreams,
workSpace, wkspSize, workSpace, wkspSize,
NULL, NULL, 0, 0 /*bmi2*/); NULL, NULL, 0, 0 /*bmi2*/);
} }
@@ -777,7 +778,7 @@ size_t HUF_compress4X_repeat (void* dst, size_t dstSize,
HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2) HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2)
{ {
return HUF_compress_internal(dst, dstSize, src, srcSize, return HUF_compress_internal(dst, dstSize, src, srcSize,
maxSymbolValue, huffLog, 0 /* 4 streams */, maxSymbolValue, huffLog, HUF_fourStreams,
workSpace, wkspSize, workSpace, wkspSize,
hufTable, repeat, preferRepeat, bmi2); hufTable, repeat, preferRepeat, bmi2);
} }
lib/compress/zstd_compress.c
+31 -21
View File
@@ -1679,7 +1679,8 @@ static size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
ZSTD_strategy strategy, int disableLiteralCompression, ZSTD_strategy strategy, int disableLiteralCompression,
void* dst, size_t dstCapacity, void* dst, size_t dstCapacity,
const void* src, size_t srcSize, const void* src, size_t srcSize,
U32* workspace, const int bmi2) void* workspace, size_t wkspSize,
const int bmi2)
{ {
size_t const minGain = ZSTD_minGain(srcSize, strategy); size_t const minGain = ZSTD_minGain(srcSize, strategy);
size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB); size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
@@ -1708,9 +1709,9 @@ static size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0; int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1; if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11, cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
workspace, HUF_WORKSPACE_SIZE, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2) workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2)
: HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11, : HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
workspace, HUF_WORKSPACE_SIZE, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2); workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
if (repeat != HUF_repeat_none) { if (repeat != HUF_repeat_none) {
/* reused the existing table */ /* reused the existing table */
hType = set_repeat; hType = set_repeat;
@@ -2186,11 +2187,13 @@ static size_t ZSTD_encodeSequences(
sequences, nbSeq, longOffsets); sequences, nbSeq, longOffsets);
} }
MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr, MEM_STATIC size_t
ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
ZSTD_entropyCTables_t const* prevEntropy, ZSTD_entropyCTables_t const* prevEntropy,
ZSTD_entropyCTables_t* nextEntropy, ZSTD_entropyCTables_t* nextEntropy,
ZSTD_CCtx_params const* cctxParams, ZSTD_CCtx_params const* cctxParams,
void* dst, size_t dstCapacity, U32* workspace, void* dst, size_t dstCapacity,
void* workspace, size_t wkspSize,
const int bmi2) const int bmi2)
{ {
const int longOffsets = cctxParams->cParams.windowLog > STREAM_ACCUMULATOR_MIN; const int longOffsets = cctxParams->cParams.windowLog > STREAM_ACCUMULATOR_MIN;
@@ -2222,7 +2225,8 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
cctxParams->cParams.strategy, disableLiteralCompression, cctxParams->cParams.strategy, disableLiteralCompression,
op, dstCapacity, op, dstCapacity,
literals, litSize, literals, litSize,
workspace, bmi2); workspace, wkspSize,
bmi2);
if (ZSTD_isError(cSize)) if (ZSTD_isError(cSize))
return cSize; return cSize;
assert(cSize <= dstCapacity); assert(cSize <= dstCapacity);
@@ -2250,7 +2254,7 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
ZSTD_seqToCodes(seqStorePtr); ZSTD_seqToCodes(seqStorePtr);
/* build CTable for Literal Lengths */ /* build CTable for Literal Lengths */
{ U32 max = MaxLL; { U32 max = MaxLL;
size_t const mostFrequent = HIST_countFast_wksp(count, &max, llCodeTable, nbSeq, workspace); /* can't fail */ size_t const mostFrequent = HIST_countFast_wksp(count, &max, llCodeTable, nbSeq, workspace, wkspSize); /* can't fail */
DEBUGLOG(5, "Building LL table"); DEBUGLOG(5, "Building LL table");
nextEntropy->fse.litlength_repeatMode = prevEntropy->fse.litlength_repeatMode; nextEntropy->fse.litlength_repeatMode = prevEntropy->fse.litlength_repeatMode;
LLtype = ZSTD_selectEncodingType(&nextEntropy->fse.litlength_repeatMode, count, max, mostFrequent, nbSeq, LLFSELog, prevEntropy->fse.litlengthCTable, LL_defaultNorm, LL_defaultNormLog, ZSTD_defaultAllowed, strategy); LLtype = ZSTD_selectEncodingType(&nextEntropy->fse.litlength_repeatMode, count, max, mostFrequent, nbSeq, LLFSELog, prevEntropy->fse.litlengthCTable, LL_defaultNorm, LL_defaultNormLog, ZSTD_defaultAllowed, strategy);
@@ -2259,7 +2263,7 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
{ size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_LitLength, LLFSELog, (symbolEncodingType_e)LLtype, { size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_LitLength, LLFSELog, (symbolEncodingType_e)LLtype,
count, max, llCodeTable, nbSeq, LL_defaultNorm, LL_defaultNormLog, MaxLL, count, max, llCodeTable, nbSeq, LL_defaultNorm, LL_defaultNormLog, MaxLL,
prevEntropy->fse.litlengthCTable, sizeof(prevEntropy->fse.litlengthCTable), prevEntropy->fse.litlengthCTable, sizeof(prevEntropy->fse.litlengthCTable),
workspace, HUF_WORKSPACE_SIZE); workspace, wkspSize);
if (ZSTD_isError(countSize)) return countSize; if (ZSTD_isError(countSize)) return countSize;
if (LLtype == set_compressed) if (LLtype == set_compressed)
lastNCount = op; lastNCount = op;
@@ -2267,7 +2271,7 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
} } } }
/* build CTable for Offsets */ /* build CTable for Offsets */
{ U32 max = MaxOff; { U32 max = MaxOff;
size_t const mostFrequent = HIST_countFast_wksp(count, &max, ofCodeTable, nbSeq, workspace); /* can't fail */ size_t const mostFrequent = HIST_countFast_wksp(count, &max, ofCodeTable, nbSeq, workspace, wkspSize); /* can't fail */
/* We can only use the basic table if max <= DefaultMaxOff, otherwise the offsets are too large */ /* We can only use the basic table if max <= DefaultMaxOff, otherwise the offsets are too large */
ZSTD_defaultPolicy_e const defaultPolicy = (max <= DefaultMaxOff) ? ZSTD_defaultAllowed : ZSTD_defaultDisallowed; ZSTD_defaultPolicy_e const defaultPolicy = (max <= DefaultMaxOff) ? ZSTD_defaultAllowed : ZSTD_defaultDisallowed;
DEBUGLOG(5, "Building OF table"); DEBUGLOG(5, "Building OF table");
@@ -2277,7 +2281,7 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
{ size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_OffsetBits, OffFSELog, (symbolEncodingType_e)Offtype, { size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_OffsetBits, OffFSELog, (symbolEncodingType_e)Offtype,
count, max, ofCodeTable, nbSeq, OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff, count, max, ofCodeTable, nbSeq, OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff,
prevEntropy->fse.offcodeCTable, sizeof(prevEntropy->fse.offcodeCTable), prevEntropy->fse.offcodeCTable, sizeof(prevEntropy->fse.offcodeCTable),
workspace, HUF_WORKSPACE_SIZE); workspace, wkspSize);
if (ZSTD_isError(countSize)) return countSize; if (ZSTD_isError(countSize)) return countSize;
if (Offtype == set_compressed) if (Offtype == set_compressed)
lastNCount = op; lastNCount = op;
@@ -2285,7 +2289,7 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
} } } }
/* build CTable for MatchLengths */ /* build CTable for MatchLengths */
{ U32 max = MaxML; { U32 max = MaxML;
size_t const mostFrequent = HIST_countFast_wksp(count, &max, mlCodeTable, nbSeq, workspace); /* can't fail */ size_t const mostFrequent = HIST_countFast_wksp(count, &max, mlCodeTable, nbSeq, workspace, wkspSize); /* can't fail */
DEBUGLOG(5, "Building ML table"); DEBUGLOG(5, "Building ML table");
nextEntropy->fse.matchlength_repeatMode = prevEntropy->fse.matchlength_repeatMode; nextEntropy->fse.matchlength_repeatMode = prevEntropy->fse.matchlength_repeatMode;
MLtype = ZSTD_selectEncodingType(&nextEntropy->fse.matchlength_repeatMode, count, max, mostFrequent, nbSeq, MLFSELog, prevEntropy->fse.matchlengthCTable, ML_defaultNorm, ML_defaultNormLog, ZSTD_defaultAllowed, strategy); MLtype = ZSTD_selectEncodingType(&nextEntropy->fse.matchlength_repeatMode, count, max, mostFrequent, nbSeq, MLFSELog, prevEntropy->fse.matchlengthCTable, ML_defaultNorm, ML_defaultNormLog, ZSTD_defaultAllowed, strategy);
@@ -2293,7 +2297,7 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
{ size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_MatchLength, MLFSELog, (symbolEncodingType_e)MLtype, { size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_MatchLength, MLFSELog, (symbolEncodingType_e)MLtype,
count, max, mlCodeTable, nbSeq, ML_defaultNorm, ML_defaultNormLog, MaxML, count, max, mlCodeTable, nbSeq, ML_defaultNorm, ML_defaultNormLog, MaxML,
prevEntropy->fse.matchlengthCTable, sizeof(prevEntropy->fse.matchlengthCTable), prevEntropy->fse.matchlengthCTable, sizeof(prevEntropy->fse.matchlengthCTable),
workspace, HUF_WORKSPACE_SIZE); workspace, wkspSize);
if (ZSTD_isError(countSize)) return countSize; if (ZSTD_isError(countSize)) return countSize;
if (MLtype == set_compressed) if (MLtype == set_compressed)
lastNCount = op; lastNCount = op;
@@ -2331,16 +2335,20 @@ MEM_STATIC size_t ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
return op - ostart; return op - ostart;
} }
MEM_STATIC size_t ZSTD_compressSequences(seqStore_t* seqStorePtr, MEM_STATIC size_t
const ZSTD_entropyCTables_t* prevEntropy, ZSTD_compressSequences(seqStore_t* seqStorePtr,
ZSTD_entropyCTables_t* nextEntropy, const ZSTD_entropyCTables_t* prevEntropy,
const ZSTD_CCtx_params* cctxParams, ZSTD_entropyCTables_t* nextEntropy,
void* dst, size_t dstCapacity, const ZSTD_CCtx_params* cctxParams,
size_t srcSize, U32* workspace, int bmi2) void* dst, size_t dstCapacity,
size_t srcSize,
void* workspace, size_t wkspSize,
int bmi2)
{ {
size_t const cSize = ZSTD_compressSequences_internal( size_t const cSize = ZSTD_compressSequences_internal(
seqStorePtr, prevEntropy, nextEntropy, cctxParams, dst, dstCapacity, seqStorePtr, prevEntropy, nextEntropy, cctxParams,
workspace, bmi2); dst, dstCapacity,
workspace, wkspSize, bmi2);
if (cSize == 0) return 0; if (cSize == 0) return 0;
/* When srcSize <= dstCapacity, there is enough space to write a raw uncompressed block. /* When srcSize <= dstCapacity, there is enough space to write a raw uncompressed block.
* Since we ran out of space, block must be not compressible, so fall back to raw uncompressed block. * Since we ran out of space, block must be not compressible, so fall back to raw uncompressed block.
@@ -2495,7 +2503,9 @@ static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc,
&zc->blockState.prevCBlock->entropy, &zc->blockState.nextCBlock->entropy, &zc->blockState.prevCBlock->entropy, &zc->blockState.nextCBlock->entropy,
&zc->appliedParams, &zc->appliedParams,
dst, dstCapacity, dst, dstCapacity,
srcSize, zc->entropyWorkspace, zc->bmi2); srcSize,
zc->entropyWorkspace, HUF_WORKSPACE_SIZE /* statically allocated in resetCCtx */,
zc->bmi2);
out: out:
if (!ZSTD_isError(cSize) && cSize != 0) { if (!ZSTD_isError(cSize) && cSize != 0) {
tests/decodecorpus.c
+4 -4
View File
@@ -437,7 +437,7 @@ static size_t writeHufHeader(U32* seed, HUF_CElt* hufTable, void* dst, size_t ds
U32 count[HUF_SYMBOLVALUE_MAX+1]; U32 count[HUF_SYMBOLVALUE_MAX+1];
/* Scan input and build symbol stats */ /* Scan input and build symbol stats */
{ size_t const largest = HIST_count_wksp (count, &maxSymbolValue, (const BYTE*)src, srcSize, WKSP); { size_t const largest = HIST_count_wksp (count, &maxSymbolValue, (const BYTE*)src, srcSize, WKSP, sizeof(WKSP));
assert(!HIST_isError(largest)); assert(!HIST_isError(largest));
if (largest == srcSize) { *ostart = ((const BYTE*)src)[0]; return 0; } /* single symbol, rle */ if (largest == srcSize) { *ostart = ((const BYTE*)src)[0]; return 0; } /* single symbol, rle */
if (largest <= (srcSize >> 7)+1) return 0; /* Fast heuristic : not compressible enough */ if (largest <= (srcSize >> 7)+1) return 0; /* Fast heuristic : not compressible enough */
@@ -836,7 +836,7 @@ static size_t writeSequences(U32* seed, frame_t* frame, seqStore_t* seqStorePtr,
/* CTable for Literal Lengths */ /* CTable for Literal Lengths */
{ U32 max = MaxLL; { U32 max = MaxLL;
size_t const mostFrequent = HIST_countFast_wksp(count, &max, llCodeTable, nbSeq, WKSP); /* cannot fail */ size_t const mostFrequent = HIST_countFast_wksp(count, &max, llCodeTable, nbSeq, WKSP, sizeof(WKSP)); /* cannot fail */
assert(!HIST_isError(mostFrequent)); assert(!HIST_isError(mostFrequent));
if (mostFrequent == nbSeq) { if (mostFrequent == nbSeq) {
/* do RLE if we have the chance */ /* do RLE if we have the chance */
@@ -868,7 +868,7 @@ static size_t writeSequences(U32* seed, frame_t* frame, seqStore_t* seqStorePtr,
/* CTable for Offsets */ /* CTable for Offsets */
/* see Literal Lengths for descriptions of mode choices */ /* see Literal Lengths for descriptions of mode choices */
{ U32 max = MaxOff; { U32 max = MaxOff;
size_t const mostFrequent = HIST_countFast_wksp(count, &max, ofCodeTable, nbSeq, WKSP); /* cannot fail */ size_t const mostFrequent = HIST_countFast_wksp(count, &max, ofCodeTable, nbSeq, WKSP, sizeof(WKSP)); /* cannot fail */
assert(!HIST_isError(mostFrequent)); assert(!HIST_isError(mostFrequent));
if (mostFrequent == nbSeq) { if (mostFrequent == nbSeq) {
*op++ = ofCodeTable[0]; *op++ = ofCodeTable[0];
@@ -896,7 +896,7 @@ static size_t writeSequences(U32* seed, frame_t* frame, seqStore_t* seqStorePtr,
/* CTable for MatchLengths */ /* CTable for MatchLengths */
/* see Literal Lengths for descriptions of mode choices */ /* see Literal Lengths for descriptions of mode choices */
{ U32 max = MaxML; { U32 max = MaxML;
size_t const mostFrequent = HIST_countFast_wksp(count, &max, mlCodeTable, nbSeq, WKSP); /* cannot fail */ size_t const mostFrequent = HIST_countFast_wksp(count, &max, mlCodeTable, nbSeq, WKSP, sizeof(WKSP)); /* cannot fail */
assert(!HIST_isError(mostFrequent)); assert(!HIST_isError(mostFrequent));
if (mostFrequent == nbSeq) { if (mostFrequent == nbSeq) {
*op++ = *mlCodeTable; *op++ = *mlCodeTable;