Merge fastCover into DictBuilder (#1274)
* Minor fix * Run non-optimize FASTCOVER 5 times in benchmark * Merge fastCover into dictBuilder * Fix mixed declaration issue * Add fastcover to symbol.c * Add fastCover.c and cover.h to build * Change fastCover.c to fastcover.c * Update benchmark to run FASTCOVER in dictBuilder * Undo spliting fastcover_param into cover_param and f * Remove convert param functions * Assign f to parameter * Add zdict.h to Makefile in lib * Add cover.h to BUCK * Cast 1 to U64 before shifting * Remove trimming of zero freq head and tail in selectSegment and rebenchmark * Remove f as a separate parameter of tryParam * Read 8 bytes when d is 6 * Add trimming off zero frequency head and tail * Use best functions from COVER and remove trimming part(which leads to worse compression ratio after previous bugs were fixed) * Add finalize= argument to FASTCOVER to specify percentage of training samples passed to ZDICT_finalizeDictionary * Change nbDmer to always read 8 bytes even when d=6 * Add skip=# argument to allow skipping dmers in computeFrequency in FASTCOVER * Update comments and benchmarking result * Change default method of ZDICT_trainFromBuffer to ZDICT_optimizeTrainFromBuffer_fastCover * Add dictType enum and fix bug about passing zParam when converting to coverParam * Combine finalize and skip into a single parameter * Update acceleration parameters and benchmark on 3 sample sets * Change default splitPoint of FASTCOVER to 0.75 and benchmark first 3 sample sets * Initialize variables outside of for loop in benchmark.c * Update benchmark result for hg-manifest * Remove cover.h from install-includes * Add explanation of f * Set default compression level for trainFromBuffer to 3 * Add assertion of fastCoverParams in DiB_trainFromFiles * Add checkTotalCompressedSize function + some minor fixes * Add test for multithreading fastCovr * Initialize segmentFreqs in every FASTCOVER_selectSegment and move mutex_unnlock to end of COVER_best_finish * Free segmentFreqs * Initialize segmentFreqs before calling FASTCOVER_buildDictionary instead of in FASTCOVER_selectSegment * Add FASTCOVER_MEMMULT * Minor fix * Update benchmarking result
This commit is contained in:
committed by
Nick Terrell
parent
1af27a7ed7
commit
9d6ed9def3
@@ -863,8 +863,8 @@ _cleanup:
|
||||
|
||||
size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity,
|
||||
const void* customDictContent, size_t dictContentSize,
|
||||
const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
|
||||
ZDICT_params_t params)
|
||||
const void* samplesBuffer, const size_t* samplesSizes,
|
||||
unsigned nbSamples, ZDICT_params_t params)
|
||||
{
|
||||
size_t hSize;
|
||||
#define HBUFFSIZE 256 /* should prove large enough for all entropy headers */
|
||||
@@ -1078,17 +1078,17 @@ size_t ZDICT_trainFromBuffer_legacy(void* dictBuffer, size_t dictBufferCapacity,
|
||||
size_t ZDICT_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
|
||||
const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples)
|
||||
{
|
||||
ZDICT_cover_params_t params;
|
||||
ZDICT_fastCover_params_t params;
|
||||
DEBUGLOG(3, "ZDICT_trainFromBuffer");
|
||||
memset(¶ms, 0, sizeof(params));
|
||||
params.d = 8;
|
||||
params.steps = 4;
|
||||
/* Default to level 6 since no compression level information is available */
|
||||
params.zParams.compressionLevel = 6;
|
||||
params.zParams.compressionLevel = 3;
|
||||
#if defined(DEBUGLEVEL) && (DEBUGLEVEL>=1)
|
||||
params.zParams.notificationLevel = DEBUGLEVEL;
|
||||
#endif
|
||||
return ZDICT_optimizeTrainFromBuffer_cover(dictBuffer, dictBufferCapacity,
|
||||
return ZDICT_optimizeTrainFromBuffer_fastCover(dictBuffer, dictBufferCapacity,
|
||||
samplesBuffer, samplesSizes, nbSamples,
|
||||
¶ms);
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user