Change default splitPoint to 100

This commit is contained in:
Jennifer Liu 2018-07-10 11:19:33 -07:00
parent 456f290e31
commit 5021441d86
5 changed files with 6 additions and 6 deletions

View File

@ -39,7 +39,7 @@
* Constants
***************************************/
#define COVER_MAX_SAMPLES_SIZE (sizeof(size_t) == 8 ? ((U32)-1) : ((U32)1 GB))
#define DEFAULT_SPLITPOINT 0.8
#define DEFAULT_SPLITPOINT 1.0
/*-*************************************
* Console display
@ -497,7 +497,7 @@ static int COVER_checkParameters(ZDICT_cover_params_t parameters,
if (parameters.d > parameters.k) {
return 0;
}
/* 0 < splitPoint < 1 */
/* 0 < splitPoint <= 1 */
if (parameters.splitPoint <= 0 || parameters.splitPoint > 1){
return 0;
}

View File

@ -86,7 +86,7 @@ typedef struct {
unsigned d; /* dmer size : constraint: 0 < d <= k : Reasonable range [6, 16] */
unsigned steps; /* Number of steps : Only used for optimization : 0 means default (32) : Higher means more parameters checked */
unsigned nbThreads; /* Number of threads : constraint: 0 < nbThreads : 1 means single-threaded : Only used for optimization : Ignored if ZSTD_MULTITHREAD is not defined */
double splitPoint; /* Percentage of samples used for training: the first nbSamples * splitPoint samples will be used to training, 0 means default (0.8) */
double splitPoint; /* Percentage of samples used for training: the first nbSamples * splitPoint samples will be used to training, 0 means default (1.0) */
ZDICT_params_t zParams;
} ZDICT_cover_params_t;

View File

@ -218,7 +218,7 @@ A dictionary ID is a locally unique ID that a decoder can use to verify it is us
.
.TP
\fB\-\-train\-cover[=k#,d=#,steps=#,split=#]\fR
Select parameters for the default dictionary builder algorithm named cover\. If \fId\fR is not specified, then it tries \fId\fR = 6 and \fId\fR = 8\. If \fIk\fR is not specified, then it tries \fIsteps\fR values in the range [50, 2000]\. If \fIsteps\fR is not specified, then the default value of 40 is used\. If \fIsplit\fR is not specified or \fIsplit\fR <= 0 or \fIsplit\fR > 100, then the default value of 80 is used\. Requires that \fId\fR <= \fIk\fR\.
Select parameters for the default dictionary builder algorithm named cover\. If \fId\fR is not specified, then it tries \fId\fR = 6 and \fId\fR = 8\. If \fIk\fR is not specified, then it tries \fIsteps\fR values in the range [50, 2000]\. If \fIsteps\fR is not specified, then the default value of 40 is used\. If \fIsplit\fR is not specified or \fIsplit\fR <= 0 or \fIsplit\fR > 100, then the default value of 100 is used\. Requires that \fId\fR <= \fIk\fR\.
.
.IP
Selects segments of size \fIk\fR with highest score to put in the dictionary\. The score of a segment is computed by the sum of the frequencies of all the subsegments of size \fId\fR\. Generally \fId\fR should be in the range [6, 8], occasionally up to 16, but the algorithm will run faster with d <= \fI8\fR\. Good values for \fIk\fR vary widely based on the input data, but a safe range is [2 * \fId\fR, 2000]\. Supports multithreading if \fBzstd\fR is compiled with threading support\.

View File

@ -228,7 +228,7 @@ Compression of small files similar to the sample set will be greatly improved.
If _d_ is not specified, then it tries _d_ = 6 and _d_ = 8.
If _k_ is not specified, then it tries _steps_ values in the range [50, 2000].
If _steps_ is not specified, then the default value of 40 is used.
If _split_ is not specified or split <= 0 or split > 100, then the default value of 80 is used.
If _split_ is not specified or split <= 0 or split > 100, then the default value of 100 is used.
Requires that _d_ <= _k_.
Selects segments of size _k_ with highest score to put in the dictionary.

View File

@ -84,7 +84,7 @@ static U32 g_ldmMinMatch = 0;
static U32 g_ldmHashEveryLog = LDM_PARAM_DEFAULT;
static U32 g_ldmBucketSizeLog = LDM_PARAM_DEFAULT;
#define DEFAULT_SPLITPOINT 0.8
#define DEFAULT_SPLITPOINT 1.0
/*-************************************
* Display Macros