zstd/lib/dictBuilder/cover.h

148 lines
4.5 KiB
C
Raw Normal View History

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
2018-08-23 19:06:20 +00:00
#include <stdio.h> /* fprintf */
#include <stdlib.h> /* malloc, free, qsort */
#include <string.h> /* memset */
#include <time.h> /* clock */
#include "mem.h" /* read */
#include "pool.h"
#include "threading.h"
#include "zstd_internal.h" /* includes zstd.h */
#ifndef ZDICT_STATIC_LINKING_ONLY
#define ZDICT_STATIC_LINKING_ONLY
#endif
#include "zdict.h"
/**
* COVER_best_t is used for two purposes:
* 1. Synchronizing threads.
* 2. Saving the best parameters and dictionary.
*
* All of the methods except COVER_best_init() are thread safe if zstd is
* compiled with multithreaded support.
*/
typedef struct COVER_best_s {
ZSTD_pthread_mutex_t mutex;
ZSTD_pthread_cond_t cond;
size_t liveJobs;
void *dict;
size_t dictSize;
ZDICT_cover_params_t parameters;
size_t compressedSize;
} COVER_best_t;
/**
* A segment is a range in the source as well as the score of the segment.
*/
typedef struct {
U32 begin;
U32 end;
U32 score;
} COVER_segment_t;
/**
*Number of epochs and size of each epoch.
*/
typedef struct {
U32 num;
U32 size;
} COVER_epoch_info_t;
/**
* Struct used for the dictionary selection function.
*/
typedef struct COVER_dictSelection {
BYTE* dictContent;
size_t dictSize;
size_t totalCompressedSize;
} COVER_dictSelection_t;
/**
* Computes the number of epochs and the size of each epoch.
* We will make sure that each epoch gets at least 10 * k bytes.
*
* The COVER algorithms divide the data up into epochs of equal size and
Spelling (#1582) * spelling: accidentally * spelling: across * spelling: additionally * spelling: addresses * spelling: appropriate * spelling: assumed * spelling: available * spelling: builder * spelling: capacity * spelling: compiler * spelling: compressibility * spelling: compressor * spelling: compression * spelling: contract * spelling: convenience * spelling: decompress * spelling: description * spelling: deflate * spelling: deterministically * spelling: dictionary * spelling: display * spelling: eliminate * spelling: preemptively * spelling: exclude * spelling: failure * spelling: independence * spelling: independent * spelling: intentionally * spelling: matching * spelling: maximum * spelling: meaning * spelling: mishandled * spelling: memory * spelling: occasionally * spelling: occurrence * spelling: official * spelling: offsets * spelling: original * spelling: output * spelling: overflow * spelling: overridden * spelling: parameter * spelling: performance * spelling: probability * spelling: receives * spelling: redundant * spelling: recompression * spelling: resources * spelling: sanity * spelling: segment * spelling: series * spelling: specified * spelling: specify * spelling: subtracted * spelling: successful * spelling: return * spelling: translation * spelling: update * spelling: unrelated * spelling: useless * spelling: variables * spelling: variety * spelling: verbatim * spelling: verification * spelling: visited * spelling: warming * spelling: workers * spelling: with
2019-04-12 18:18:11 +00:00
* select one segment from each epoch.
*
Spelling (#1582) * spelling: accidentally * spelling: across * spelling: additionally * spelling: addresses * spelling: appropriate * spelling: assumed * spelling: available * spelling: builder * spelling: capacity * spelling: compiler * spelling: compressibility * spelling: compressor * spelling: compression * spelling: contract * spelling: convenience * spelling: decompress * spelling: description * spelling: deflate * spelling: deterministically * spelling: dictionary * spelling: display * spelling: eliminate * spelling: preemptively * spelling: exclude * spelling: failure * spelling: independence * spelling: independent * spelling: intentionally * spelling: matching * spelling: maximum * spelling: meaning * spelling: mishandled * spelling: memory * spelling: occasionally * spelling: occurrence * spelling: official * spelling: offsets * spelling: original * spelling: output * spelling: overflow * spelling: overridden * spelling: parameter * spelling: performance * spelling: probability * spelling: receives * spelling: redundant * spelling: recompression * spelling: resources * spelling: sanity * spelling: segment * spelling: series * spelling: specified * spelling: specify * spelling: subtracted * spelling: successful * spelling: return * spelling: translation * spelling: update * spelling: unrelated * spelling: useless * spelling: variables * spelling: variety * spelling: verbatim * spelling: verification * spelling: visited * spelling: warming * spelling: workers * spelling: with
2019-04-12 18:18:11 +00:00
* @param maxDictSize The maximum allowed dictionary size.
* @param nbDmers The number of dmers we are training on.
* @param k The parameter k (segment size).
* @param passes The target number of passes over the dmer corpus.
* More passes means a better dictionary.
*/
COVER_epoch_info_t COVER_computeEpochs(U32 maxDictSize, U32 nbDmers,
U32 k, U32 passes);
/**
* Warns the user when their corpus is too small.
*/
void COVER_warnOnSmallCorpus(size_t maxDictSize, size_t nbDmers, int displayLevel);
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
2018-08-23 19:06:20 +00:00
/**
* Checks total compressed size of a dictionary
*/
size_t COVER_checkTotalCompressedSize(const ZDICT_cover_params_t parameters,
const size_t *samplesSizes, const BYTE *samples,
size_t *offsets,
size_t nbTrainSamples, size_t nbSamples,
BYTE *const dict, size_t dictBufferCapacity);
/**
* Returns the sum of the sample sizes.
*/
size_t COVER_sum(const size_t *samplesSizes, unsigned nbSamples) ;
/**
* Initialize the `COVER_best_t`.
*/
void COVER_best_init(COVER_best_t *best);
/**
* Wait until liveJobs == 0.
*/
void COVER_best_wait(COVER_best_t *best);
/**
* Call COVER_best_wait() and then destroy the COVER_best_t.
*/
void COVER_best_destroy(COVER_best_t *best);
/**
* Called when a thread is about to be launched.
* Increments liveJobs.
*/
void COVER_best_start(COVER_best_t *best);
/**
* Called when a thread finishes executing, both on error or success.
* Decrements liveJobs and signals any waiting threads if liveJobs == 0.
* If this dictionary is the best so far save it and its parameters.
*/
void COVER_best_finish(COVER_best_t *best, ZDICT_cover_params_t parameters,
COVER_dictSelection_t selection);
/**
* Error function for COVER_selectDict function. Checks if the return
* value is an error.
*/
unsigned COVER_dictSelectionIsError(COVER_dictSelection_t selection);
/**
* Error function for COVER_selectDict function. Returns a struct where
* return.totalCompressedSize is a ZSTD error.
*/
COVER_dictSelection_t COVER_dictSelectionError(size_t error);
/**
* Always call after selectDict is called to free up used memory from
* newly created dictionary.
*/
void COVER_dictSelectionFree(COVER_dictSelection_t selection);
/**
* Called to finalize the dictionary and select one based on whether or not
* the shrink-dict flag was enabled. If enabled the dictionary used is the
* smallest dictionary within a specified regression of the compressed size
* from the largest dictionary.
*/
COVER_dictSelection_t COVER_selectDict(BYTE* customDictContent,
size_t dictContentSize, const BYTE* samplesBuffer, const size_t* samplesSizes, unsigned nbFinalizeSamples,
size_t nbCheckSamples, size_t nbSamples, ZDICT_cover_params_t params, size_t* offsets, size_t totalCompressedSize);