Change default f to 20

lib/dictBuilder/fastcover.c

@@ -24,7 +24,7 @@
 #define FASTCOVER_MAX_F 31
 #define FASTCOVER_MAX_ACCEL 10
 #define DEFAULT_SPLITPOINT 0.75
-#define DEFAULT_F 18
+#define DEFAULT_F 20
 #define DEFAULT_ACCEL 1
 
 

lib/dictBuilder/zdict.h

@@ -40,7 +40,7 @@ extern "C" {
 /*! ZDICT_trainFromBuffer():
  *  Train a dictionary from an array of samples.
  *  Redirect towards ZDICT_optimizeTrainFromBuffer_fastCover() single-threaded, with d=8, steps=4,
- *  f=18, and accel=1.
+ *  f=20, and accel=1.
  *  Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
  *  supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
  *  The resulting dictionary will be saved into `dictBuffer`.
@@ -94,7 +94,7 @@ typedef struct {
 typedef struct {
     unsigned k;                  /* Segment size : constraint: 0 < k : Reasonable range [16, 2048+] */
     unsigned d;                  /* dmer size : constraint: 0 < d <= k : Reasonable range [6, 16] */
-    unsigned f;                  /* log of size of frequency array : constraint: 0 < f <= 31 : 1 means default(18)*/
+    unsigned f;                  /* log of size of frequency array : constraint: 0 < f <= 31 : 1 means default(20)*/
     unsigned steps;              /* Number of steps : Only used for optimization : 0 means default (40) : 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: Only used for optimization : the first nbSamples * splitPoint samples will be used to training, the last nbSamples * (1 - splitPoint) samples will be used for testing, 0 means default (0.75), 1.0 when all samples are used for both training and testing */
@@ -170,7 +170,7 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_fastCover(void *dictBuffer,
  * If d is non-zero then we don't check multiple values of d, otherwise we check d = {6, 8}.
  * if steps is zero it defaults to its default value.
  * If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [50, 2000].
- * If f is zero, default value of 18 is used.
+ * If f is zero, default value of 20 is used.
  * If accel is zero, default value of 1 is used.
  *
  * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)

programs/zstd.1

@@ -244,7 +244,7 @@ Examples:
 Same as cover but with extra parameters \fIf\fR and \fIaccel\fR and different default value of split
 .
 .IP
-If \fIsplit\fR is not specified, then it tries \fIsplit\fR = 75. If \fIf\fR is not specified, then it tries \fIf\fR = 18. Requires that 0 < \fIf\fR < 32. If \fIaccel\fR is not specified, then it tries \fIaccel\fR = 1. Requires that 0 < \fIaccel\fR <= 10. Requires that \fId\fR = 6 or \fId\fR = 8.
+If \fIsplit\fR is not specified, then it tries \fIsplit\fR = 75. If \fIf\fR is not specified, then it tries \fIf\fR = 20. Requires that 0 < \fIf\fR < 32. If \fIaccel\fR is not specified, then it tries \fIaccel\fR = 1. Requires that 0 < \fIaccel\fR <= 10. Requires that \fId\fR = 6 or \fId\fR = 8.
 .
 .IP
 \fIf\fR is log of size of array that keeps track of frequency of subsegments of size \fId\fR. The subsegment is hashed to an index in the range [0,2^\fIf\fR - 1]. It is possible that 2 different subsegments are hashed to the same index, and they are considered as the same subsegment when computing frequency. Using a higher \fIf\fR reduces collision but takes longer.

programs/zstd.1.md

@@ -258,7 +258,7 @@ Compression of small files similar to the sample set will be greatly improved.
 * `--train-fastcover[=k#,d=#,f=#,steps=#,split=#,accel=#]`:
     Same as cover but with extra parameters _f_ and _accel_ and different default value of split
     If _split_ is not specified, then it tries _split_ = 75.
-    If _f_ is not specified, then it tries _f_ = 18.
+    If _f_ is not specified, then it tries _f_ = 20.
     Requires that 0 < _f_ < 32.
     If _accel_ is not specified, then it tries _accel_ = 1.
     Requires that 0 < _accel_ <= 10.

programs/zstdcli.c

@@ -356,7 +356,7 @@ static ZDICT_fastCover_params_t defaultFastCoverParams(void)
     ZDICT_fastCover_params_t params;
     memset(&params, 0, sizeof(params));
     params.d = 8;
-    params.f = 18;
+    params.f = 20;
     params.steps = 4;
     params.splitPoint = 0.75; /* different from default splitPoint of cover */
     params.accel = DEFAULT_ACCEL;