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

Merge fastCover into DictBuilder (#1274)

Browse Source 
* 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:
Jennifer Liu
2018-08-23 12:06:20 -07:00
committed by Nick Terrell
parent 1af27a7ed7
commit 9d6ed9def3
26 changed files with 1999 additions and 246 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/dictBuilder/cover.c
+68 -79
View File
@@ -29,6 +29,7 @@
#include "mem.h" /* read */
#include "pool.h"
#include "threading.h"
#include "cover.h"
#include "zstd_internal.h" /* includes zstd.h */
#ifndef ZDICT_STATIC_LINKING_ONLY
#define ZDICT_STATIC_LINKING_ONLY
@@ -185,7 +186,7 @@ static void COVER_map_remove(COVER_map_t *map, U32 key) {
}
/**
* Destroyes a map that is inited with COVER_map_init().
* Destroys a map that is inited with COVER_map_init().
*/
static void COVER_map_destroy(COVER_map_t *map) {
if (map->data) {
@@ -223,7 +224,7 @@ static COVER_ctx_t *g_ctx = NULL;
/**
* Returns the sum of the sample sizes.
*/
static size_t COVER_sum(const size_t *samplesSizes, unsigned nbSamples) {
size_t COVER_sum(const size_t *samplesSizes, unsigned nbSamples) {
size_t sum = 0;
unsigned i;
for (i = 0; i < nbSamples; ++i) {
@@ -380,14 +381,6 @@ static void COVER_group(COVER_ctx_t *ctx, const void *group,
ctx->suffix[dmerId] = freq;
}
/**
* 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;
/**
* Selects the best segment in an epoch.
@@ -691,7 +684,7 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover(
BYTE* const dict = (BYTE*)dictBuffer;
COVER_ctx_t ctx;
COVER_map_t activeDmers;
parameters.splitPoint = 1.0;
parameters.splitPoint = parameters.splitPoint <= 0.0 ? DEFAULT_SPLITPOINT : parameters.splitPoint;
/* Initialize global data */
g_displayLevel = parameters.zParams.notificationLevel;
/* Checks */
@@ -737,28 +730,65 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover(
}
}
/**
* 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;
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) {
size_t totalCompressedSize = ERROR(GENERIC);
/* Pointers */
ZSTD_CCtx *cctx;
ZSTD_CDict *cdict;
void *dst;
/* Local variables */
size_t dstCapacity;
size_t i;
/* Allocate dst with enough space to compress the maximum sized sample */
{
size_t maxSampleSize = 0;
i = parameters.splitPoint < 1.0 ? nbTrainSamples : 0;
for (; i < nbSamples; ++i) {
maxSampleSize = MAX(samplesSizes[i], maxSampleSize);
}
dstCapacity = ZSTD_compressBound(maxSampleSize);
dst = malloc(dstCapacity);
}
/* Create the cctx and cdict */
cctx = ZSTD_createCCtx();
cdict = ZSTD_createCDict(dict, dictBufferCapacity,
parameters.zParams.compressionLevel);
if (!dst || !cctx || !cdict) {
goto _compressCleanup;
}
/* Compress each sample and sum their sizes (or error) */
totalCompressedSize = dictBufferCapacity;
i = parameters.splitPoint < 1.0 ? nbTrainSamples : 0;
for (; i < nbSamples; ++i) {
const size_t size = ZSTD_compress_usingCDict(
cctx, dst, dstCapacity, samples + offsets[i],
samplesSizes[i], cdict);
if (ZSTD_isError(size)) {
totalCompressedSize = ERROR(GENERIC);
goto _compressCleanup;
}
totalCompressedSize += size;
}
_compressCleanup:
ZSTD_freeCCtx(cctx);
ZSTD_freeCDict(cdict);
if (dst) {
free(dst);
}
return totalCompressedSize;
}
/**
* Initialize the `COVER_best_t`.
*/
static void COVER_best_init(COVER_best_t *best) {
void COVER_best_init(COVER_best_t *best) {
if (best==NULL) return; /* compatible with init on NULL */
(void)ZSTD_pthread_mutex_init(&best->mutex, NULL);
(void)ZSTD_pthread_cond_init(&best->cond, NULL);
@@ -772,7 +802,7 @@ static void COVER_best_init(COVER_best_t *best) {
/**
* Wait until liveJobs == 0.
*/
static void COVER_best_wait(COVER_best_t *best) {
void COVER_best_wait(COVER_best_t *best) {
if (!best) {
return;
}
@@ -786,7 +816,7 @@ static void COVER_best_wait(COVER_best_t *best) {
/**
* Call COVER_best_wait() and then destroy the COVER_best_t.
*/
static void COVER_best_destroy(COVER_best_t *best) {
void COVER_best_destroy(COVER_best_t *best) {
if (!best) {
return;
}
@@ -802,7 +832,7 @@ static void COVER_best_destroy(COVER_best_t *best) {
* Called when a thread is about to be launched.
* Increments liveJobs.
*/
static void COVER_best_start(COVER_best_t *best) {
void COVER_best_start(COVER_best_t *best) {
if (!best) {
return;
}
@@ -816,7 +846,7 @@ static void COVER_best_start(COVER_best_t *best) {
* Decrements liveJobs and signals any waiting threads if liveJobs == 0.
* If this dictionary is the best so far save it and its parameters.
*/
static void COVER_best_finish(COVER_best_t *best, size_t compressedSize,
void COVER_best_finish(COVER_best_t *best, size_t compressedSize,
ZDICT_cover_params_t parameters, void *dict,
size_t dictSize) {
if (!best) {
@@ -847,10 +877,10 @@ static void COVER_best_finish(COVER_best_t *best, size_t compressedSize,
best->parameters = parameters;
best->compressedSize = compressedSize;
}
ZSTD_pthread_mutex_unlock(&best->mutex);
if (liveJobs == 0) {
ZSTD_pthread_cond_broadcast(&best->cond);
}
ZSTD_pthread_mutex_unlock(&best->mutex);
}
}
@@ -904,51 +934,10 @@ static void COVER_tryParameters(void *opaque) {
}
}
/* Check total compressed size */
{
/* Pointers */
ZSTD_CCtx *cctx;
ZSTD_CDict *cdict;
void *dst;
/* Local variables */
size_t dstCapacity;
size_t i;
/* Allocate dst with enough space to compress the maximum sized sample */
{
size_t maxSampleSize = 0;
i = parameters.splitPoint < 1.0 ? ctx->nbTrainSamples : 0;
for (; i < ctx->nbSamples; ++i) {
maxSampleSize = MAX(ctx->samplesSizes[i], maxSampleSize);
}
dstCapacity = ZSTD_compressBound(maxSampleSize);
dst = malloc(dstCapacity);
}
/* Create the cctx and cdict */
cctx = ZSTD_createCCtx();
cdict = ZSTD_createCDict(dict, dictBufferCapacity,
parameters.zParams.compressionLevel);
if (!dst || !cctx || !cdict) {
goto _compressCleanup;
}
/* Compress each sample and sum their sizes (or error) */
totalCompressedSize = dictBufferCapacity;
i = parameters.splitPoint < 1.0 ? ctx->nbTrainSamples : 0;
for (; i < ctx->nbSamples; ++i) {
const size_t size = ZSTD_compress_usingCDict(
cctx, dst, dstCapacity, ctx->samples + ctx->offsets[i],
ctx->samplesSizes[i], cdict);
if (ZSTD_isError(size)) {
totalCompressedSize = ERROR(GENERIC);
goto _compressCleanup;
}
totalCompressedSize += size;
}
_compressCleanup:
ZSTD_freeCCtx(cctx);
ZSTD_freeCDict(cdict);
if (dst) {
free(dst);
}
}
totalCompressedSize = COVER_checkTotalCompressedSize(parameters, ctx->samplesSizes,
ctx->samples, ctx->offsets,
ctx->nbTrainSamples, ctx->nbSamples,
dict, dictBufferCapacity);
_cleanup:
COVER_best_finish(data->best, totalCompressedSize, parameters, dict,