Additional ratio optimizations

This commit is contained in:
Danielle Rozenblit
2022-10-14 10:37:35 -07:00
parent 117fddcd81
commit e60cae33cf
2 changed files with 17 additions and 4 deletions
+2 -1
View File
@@ -173,7 +173,7 @@ size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
/* ****************************************
* HUF detailed API
* ****************************************/
#define HUF_OPTIMAL_DEPTH_THRESHOLD ZSTD_btlazy2
#define HUF_OPTIMAL_DEPTH_THRESHOLD 1
typedef enum {
HUF_depth_fast, /** Use heuristic to find the table depth**/
HUF_depth_optimal /** Test possible table depths to find the one that produces the smallest header + encoded size**/
@@ -191,6 +191,7 @@ typedef enum {
* or to save and regenerate 'CTable' using external methods.
*/
unsigned HUF_minTableLog(size_t srcSize, unsigned maxSymbolValue);
unsigned HUF_cardinality(const unsigned* count, unsigned maxSymbolValue);
unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, void* workSpace, size_t wkspSize, HUF_CElt* table, const unsigned* count, HUF_depth_mode depthMode);
size_t HUF_buildCTable (HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue, unsigned maxNbBits); /* @return : maxNbBits; CTable and count can overlap. In which case, CTable will overwrite count content */
size_t HUF_writeCTable (void* dst, size_t maxDstSize, const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog);
+15 -3
View File
@@ -1235,12 +1235,23 @@ typedef struct {
#define SUSPECT_INCOMPRESSIBLE_SAMPLE_SIZE 4096
#define SUSPECT_INCOMPRESSIBLE_SAMPLE_RATIO 10 /* Must be >= 2 */
unsigned HUF_cardinality(const unsigned* count, unsigned maxSymbolValue)
{
unsigned cardinality = 0;
unsigned i;
for (i = 0; i < maxSymbolValue + 1; i++) {
if (count[i] != 0) cardinality += 1;
}
return cardinality;
}
unsigned HUF_minTableLog(size_t srcSize, unsigned maxSymbolValue)
{
U32 minBitsSrc = ZSTD_highbit32((U32)(srcSize)) + 1;
U32 minBitsSymbols = ZSTD_highbit32(maxSymbolValue) + 2;
U32 minBitsSymbols = ZSTD_highbit32(maxSymbolValue) + 1;
U32 minBits = minBitsSrc < minBitsSymbols ? minBitsSrc : minBitsSymbols;
if (minBits < FSE_MIN_TABLELOG) minBits = FSE_MIN_TABLELOG;
assert(srcSize > 1); /* Not supported, RLE should be used instead */
return minBits;
}
@@ -1255,10 +1266,11 @@ unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxS
size_t optSize = ((size_t) ~0);
unsigned huffLog;
size_t maxBits, hSize, newSize;
unsigned cardinality = HUF_cardinality(count, maxSymbolValue);
if (wkspSize < sizeof(HUF_buildCTable_wksp_tables)) return optLog;
for (huffLog = HUF_minTableLog(srcSize, maxSymbolValue); huffLog <= maxTableLog; huffLog++) {
for (huffLog = HUF_minTableLog(srcSize, cardinality); huffLog <= maxTableLog; huffLog++) {
maxBits = HUF_buildCTable_wksp(table, count,
maxSymbolValue, huffLog,
workSpace, wkspSize);