##// END OF EJS Templates
copies: no longer cache the ChangedFiles during copy tracing...
copies: no longer cache the ChangedFiles during copy tracing Now that the copies information for both parents are processed all at once, we no longer needs to cache this information, so we simplify the code. The simpler code is also a (tiny) bit faster overall. Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev --------------------------------------------------------------------------------------------------------------------------------------------------------------- mercurial x_revs_x_added_0_copies ad6b123de1c7 39cfcef4f463 : 1 revs, 0.000041 s, 0.000041 s, +0.000000 s, × 1.0000, 41 µs/rev mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 6 revs, 0.000102 s, 0.000096 s, -0.000006 s, × 0.9412, 16 µs/rev mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 1032 revs, 0.004254 s, 0.004039 s, -0.000215 s, × 0.9495, 3 µs/rev pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 9 revs, 0.000282 s, 0.000189 s, -0.000093 s, × 0.6702, 21 µs/rev pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 1 revs, 0.000048 s, 0.000047 s, -0.000001 s, × 0.9792, 47 µs/rev pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 7 revs, 0.000211 s, 0.000103 s, -0.000108 s, × 0.4882, 14 µs/rev pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 1 revs, 0.000375 s, 0.000286 s, -0.000089 s, × 0.7627, 286 µs/rev pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 6 revs, 0.010574 s, 0.010436 s, -0.000138 s, × 0.9869, 1739 µs/rev pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 4785 revs, 0.049974 s, 0.047465 s, -0.002509 s, × 0.9498, 9 µs/rev pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 6780 revs, 0.084300 s, 0.082351 s, -0.001949 s, × 0.9769, 12 µs/rev pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 5441 revs, 0.060128 s, 0.058757 s, -0.001371 s, × 0.9772, 10 µs/rev pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 43645 revs, 0.686542 s, 0.674129 s, -0.012413 s, × 0.9819, 15 µs/rev pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 2 revs, 0.009277 s, 0.009434 s, +0.000157 s, × 1.0169, 4717 µs/rev pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 11316 revs, 0.114733 s, 0.111935 s, -0.002798 s, × 0.9756, 9 µs/rev netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 2 revs, 0.000081 s, 0.000078 s, -0.000003 s, × 0.9630, 39 µs/rev netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 2 revs, 0.000107 s, 0.000106 s, -0.000001 s, × 0.9907, 53 µs/rev netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 3 revs, 0.000173 s, 0.000162 s, -0.000011 s, × 0.9364, 54 µs/rev netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 9 revs, 0.000698 s, 0.000695 s, -0.000003 s, × 0.9957, 77 µs/rev netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 1421 revs, 0.009248 s, 0.008901 s, -0.000347 s, × 0.9625, 6 µs/rev netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 1533 revs, 0.015446 s, 0.014333 s, -0.001113 s, × 0.9279, 9 µs/rev netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 5750 revs, 0.074373 s, 0.071998 s, -0.002375 s, × 0.9681, 12 µs/rev netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 66949 revs, 0.639870 s, 0.615346 s, -0.024524 s, × 0.9617, 9 µs/rev mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 2 revs, 0.000088 s, 0.000085 s, -0.000003 s, × 0.9659, 42 µs/rev mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 8 revs, 0.000199 s, 0.000199 s, +0.000000 s, × 1.0000, 24 µs/rev mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 9 revs, 0.000171 s, 0.000169 s, -0.000002 s, × 0.9883, 18 µs/rev mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 7 revs, 0.000592 s, 0.000590 s, -0.000002 s, × 0.9966, 84 µs/rev mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 3 revs, 0.003151 s, 0.003122 s, -0.000029 s, × 0.9908, 1040 µs/rev mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.061612 s, 0.061192 s, -0.000420 s, × 0.9932, 10198 µs/rev mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.005381 s, 0.005137 s, -0.000244 s, × 0.9547, 3 µs/rev mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.003742 s, 0.003585 s, -0.000157 s, × 0.9580, 87 µs/rev mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 7839 revs, 0.061983 s, 0.060592 s, -0.001391 s, × 0.9776, 7 µs/rev mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.019861 s, 0.019596 s, -0.000265 s, × 0.9867, 31 µs/rev mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 30263 revs, 0.188101 s, 0.183558 s, -0.004543 s, × 0.9758, 6 µs/rev mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 153721 revs, 1.806696 s, 1.758083 s, -0.048613 s, × 0.9731, 11 µs/rev mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 204976 revs, 2.682987 s, 2.592955 s, -0.090032 s, × 0.9664, 12 µs/rev mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 2 revs, 0.000852 s, 0.000844 s, -0.000008 s, × 0.9906, 422 µs/rev mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 2 revs, 0.000859 s, 0.000861 s, +0.000002 s, × 1.0023, 430 µs/rev mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 4 revs, 0.000150 s, 0.000150 s, +0.000000 s, × 1.0000, 37 µs/rev mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 2 revs, 0.001158 s, 0.001166 s, +0.000008 s, × 1.0069, 583 µs/rev mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 1 revs, 0.027240 s, 0.027359 s, +0.000119 s, × 1.0044, 27359 µs/rev mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.062824 s, 0.061848 s, -0.000976 s, × 0.9845, 10308 µs/rev mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.005463 s, 0.005110 s, -0.000353 s, × 0.9354, 3 µs/rev mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.004238 s, 0.004168 s, -0.000070 s, × 0.9835, 101 µs/rev mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 6657 revs, 0.064113 s, 0.063414 s, -0.000699 s, × 0.9891, 9 µs/rev mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 40314 revs, 0.294063 s, 0.288301 s, -0.005762 s, × 0.9804, 7 µs/rev mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 38690 revs, 0.281493 s, 0.275798 s, -0.005695 s, × 0.9798, 7 µs/rev mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.076323 s, 0.074640 s, -0.001683 s, × 0.9779, 8 µs/rev mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.020390 s, 0.020327 s, -0.000063 s, × 0.9969, 33 µs/rev mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 97052 revs, 3.023879 s, 2.970385 s, -0.053494 s, × 0.9823, 30 µs/rev mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 52031 revs, 0.735549 s, 0.719432 s, -0.016117 s, × 0.9781, 13 µs/rev mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 363753 revs, 18.568900 s, 18.165143 s, -0.403757 s, × 0.9783, 49 µs/rev mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.502584 s, 0.486769 s, -0.015815 s, × 0.9685, 14 µs/rev mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 362229 revs, 18.356645 s, 17.913924 s, -0.442721 s, × 0.9759, 49 µs/rev mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 359344 revs, 18.250393 s, 17.660113 s, -0.590280 s, × 0.9677, 49 µs/rev mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 192665 revs, 2.792459 s, 2.709446 s, -0.083013 s, × 0.9703, 14 µs/rev mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 228985 revs, 107.697264 s, 107.796891 s, +0.099627 s, × 1.0009, 470 µs/rev mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 382065 revs, 63.961040 s, 63.575217 s, -0.385823 s, × 0.9940, 166 µs/rev Differential Revision: https://phab.mercurial-scm.org/D9423

File last commit:

r43207:69de49c4 default
r46765:a132aa59 default
Show More
fastcover.c
747 lines | 27.4 KiB | text/x-c | CLexer
/*-*************************************
* Dependencies
***************************************/
#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 "cover.h"
#include "zstd_internal.h" /* includes zstd.h */
#ifndef ZDICT_STATIC_LINKING_ONLY
#define ZDICT_STATIC_LINKING_ONLY
#endif
#include "zdict.h"
/*-*************************************
* Constants
***************************************/
#define FASTCOVER_MAX_SAMPLES_SIZE (sizeof(size_t) == 8 ? ((unsigned)-1) : ((unsigned)1 GB))
#define FASTCOVER_MAX_F 31
#define FASTCOVER_MAX_ACCEL 10
#define DEFAULT_SPLITPOINT 0.75
#define DEFAULT_F 20
#define DEFAULT_ACCEL 1
/*-*************************************
* Console display
***************************************/
static int g_displayLevel = 2;
#define DISPLAY(...) \
{ \
fprintf(stderr, __VA_ARGS__); \
fflush(stderr); \
}
#define LOCALDISPLAYLEVEL(displayLevel, l, ...) \
if (displayLevel >= l) { \
DISPLAY(__VA_ARGS__); \
} /* 0 : no display; 1: errors; 2: default; 3: details; 4: debug */
#define DISPLAYLEVEL(l, ...) LOCALDISPLAYLEVEL(g_displayLevel, l, __VA_ARGS__)
#define LOCALDISPLAYUPDATE(displayLevel, l, ...) \
if (displayLevel >= l) { \
if ((clock() - g_time > refreshRate) || (displayLevel >= 4)) { \
g_time = clock(); \
DISPLAY(__VA_ARGS__); \
} \
}
#define DISPLAYUPDATE(l, ...) LOCALDISPLAYUPDATE(g_displayLevel, l, __VA_ARGS__)
static const clock_t refreshRate = CLOCKS_PER_SEC * 15 / 100;
static clock_t g_time = 0;
/*-*************************************
* Hash Functions
***************************************/
static const U64 prime6bytes = 227718039650203ULL;
static size_t ZSTD_hash6(U64 u, U32 h) { return (size_t)(((u << (64-48)) * prime6bytes) >> (64-h)) ; }
static size_t ZSTD_hash6Ptr(const void* p, U32 h) { return ZSTD_hash6(MEM_readLE64(p), h); }
static const U64 prime8bytes = 0xCF1BBCDCB7A56463ULL;
static size_t ZSTD_hash8(U64 u, U32 h) { return (size_t)(((u) * prime8bytes) >> (64-h)) ; }
static size_t ZSTD_hash8Ptr(const void* p, U32 h) { return ZSTD_hash8(MEM_readLE64(p), h); }
/**
* Hash the d-byte value pointed to by p and mod 2^f
*/
static size_t FASTCOVER_hashPtrToIndex(const void* p, U32 h, unsigned d) {
if (d == 6) {
return ZSTD_hash6Ptr(p, h) & ((1 << h) - 1);
}
return ZSTD_hash8Ptr(p, h) & ((1 << h) - 1);
}
/*-*************************************
* Acceleration
***************************************/
typedef struct {
unsigned finalize; /* Percentage of training samples used for ZDICT_finalizeDictionary */
unsigned skip; /* Number of dmer skipped between each dmer counted in computeFrequency */
} FASTCOVER_accel_t;
static const FASTCOVER_accel_t FASTCOVER_defaultAccelParameters[FASTCOVER_MAX_ACCEL+1] = {
{ 100, 0 }, /* accel = 0, should not happen because accel = 0 defaults to accel = 1 */
{ 100, 0 }, /* accel = 1 */
{ 50, 1 }, /* accel = 2 */
{ 34, 2 }, /* accel = 3 */
{ 25, 3 }, /* accel = 4 */
{ 20, 4 }, /* accel = 5 */
{ 17, 5 }, /* accel = 6 */
{ 14, 6 }, /* accel = 7 */
{ 13, 7 }, /* accel = 8 */
{ 11, 8 }, /* accel = 9 */
{ 10, 9 }, /* accel = 10 */
};
/*-*************************************
* Context
***************************************/
typedef struct {
const BYTE *samples;
size_t *offsets;
const size_t *samplesSizes;
size_t nbSamples;
size_t nbTrainSamples;
size_t nbTestSamples;
size_t nbDmers;
U32 *freqs;
unsigned d;
unsigned f;
FASTCOVER_accel_t accelParams;
} FASTCOVER_ctx_t;
/*-*************************************
* Helper functions
***************************************/
/**
* Selects the best segment in an epoch.
* Segments of are scored according to the function:
*
* Let F(d) be the frequency of all dmers with hash value d.
* Let S_i be hash value of the dmer at position i of segment S which has length k.
*
* Score(S) = F(S_1) + F(S_2) + ... + F(S_{k-d+1})
*
* Once the dmer with hash value d is in the dictionary we set F(d) = 0.
*/
static COVER_segment_t FASTCOVER_selectSegment(const FASTCOVER_ctx_t *ctx,
U32 *freqs, U32 begin, U32 end,
ZDICT_cover_params_t parameters,
U16* segmentFreqs) {
/* Constants */
const U32 k = parameters.k;
const U32 d = parameters.d;
const U32 f = ctx->f;
const U32 dmersInK = k - d + 1;
/* Try each segment (activeSegment) and save the best (bestSegment) */
COVER_segment_t bestSegment = {0, 0, 0};
COVER_segment_t activeSegment;
/* Reset the activeDmers in the segment */
/* The activeSegment starts at the beginning of the epoch. */
activeSegment.begin = begin;
activeSegment.end = begin;
activeSegment.score = 0;
/* Slide the activeSegment through the whole epoch.
* Save the best segment in bestSegment.
*/
while (activeSegment.end < end) {
/* Get hash value of current dmer */
const size_t idx = FASTCOVER_hashPtrToIndex(ctx->samples + activeSegment.end, f, d);
/* Add frequency of this index to score if this is the first occurrence of index in active segment */
if (segmentFreqs[idx] == 0) {
activeSegment.score += freqs[idx];
}
/* Increment end of segment and segmentFreqs*/
activeSegment.end += 1;
segmentFreqs[idx] += 1;
/* If the window is now too large, drop the first position */
if (activeSegment.end - activeSegment.begin == dmersInK + 1) {
/* Get hash value of the dmer to be eliminated from active segment */
const size_t delIndex = FASTCOVER_hashPtrToIndex(ctx->samples + activeSegment.begin, f, d);
segmentFreqs[delIndex] -= 1;
/* Subtract frequency of this index from score if this is the last occurrence of this index in active segment */
if (segmentFreqs[delIndex] == 0) {
activeSegment.score -= freqs[delIndex];
}
/* Increment start of segment */
activeSegment.begin += 1;
}
/* If this segment is the best so far save it */
if (activeSegment.score > bestSegment.score) {
bestSegment = activeSegment;
}
}
/* Zero out rest of segmentFreqs array */
while (activeSegment.begin < end) {
const size_t delIndex = FASTCOVER_hashPtrToIndex(ctx->samples + activeSegment.begin, f, d);
segmentFreqs[delIndex] -= 1;
activeSegment.begin += 1;
}
{
/* Zero the frequency of hash value of each dmer covered by the chosen segment. */
U32 pos;
for (pos = bestSegment.begin; pos != bestSegment.end; ++pos) {
const size_t i = FASTCOVER_hashPtrToIndex(ctx->samples + pos, f, d);
freqs[i] = 0;
}
}
return bestSegment;
}
static int FASTCOVER_checkParameters(ZDICT_cover_params_t parameters,
size_t maxDictSize, unsigned f,
unsigned accel) {
/* k, d, and f are required parameters */
if (parameters.d == 0 || parameters.k == 0) {
return 0;
}
/* d has to be 6 or 8 */
if (parameters.d != 6 && parameters.d != 8) {
return 0;
}
/* k <= maxDictSize */
if (parameters.k > maxDictSize) {
return 0;
}
/* d <= k */
if (parameters.d > parameters.k) {
return 0;
}
/* 0 < f <= FASTCOVER_MAX_F*/
if (f > FASTCOVER_MAX_F || f == 0) {
return 0;
}
/* 0 < splitPoint <= 1 */
if (parameters.splitPoint <= 0 || parameters.splitPoint > 1) {
return 0;
}
/* 0 < accel <= 10 */
if (accel > 10 || accel == 0) {
return 0;
}
return 1;
}
/**
* Clean up a context initialized with `FASTCOVER_ctx_init()`.
*/
static void
FASTCOVER_ctx_destroy(FASTCOVER_ctx_t* ctx)
{
if (!ctx) return;
free(ctx->freqs);
ctx->freqs = NULL;
free(ctx->offsets);
ctx->offsets = NULL;
}
/**
* Calculate for frequency of hash value of each dmer in ctx->samples
*/
static void
FASTCOVER_computeFrequency(U32* freqs, const FASTCOVER_ctx_t* ctx)
{
const unsigned f = ctx->f;
const unsigned d = ctx->d;
const unsigned skip = ctx->accelParams.skip;
const unsigned readLength = MAX(d, 8);
size_t i;
assert(ctx->nbTrainSamples >= 5);
assert(ctx->nbTrainSamples <= ctx->nbSamples);
for (i = 0; i < ctx->nbTrainSamples; i++) {
size_t start = ctx->offsets[i]; /* start of current dmer */
size_t const currSampleEnd = ctx->offsets[i+1];
while (start + readLength <= currSampleEnd) {
const size_t dmerIndex = FASTCOVER_hashPtrToIndex(ctx->samples + start, f, d);
freqs[dmerIndex]++;
start = start + skip + 1;
}
}
}
/**
* Prepare a context for dictionary building.
* The context is only dependent on the parameter `d` and can used multiple
* times.
* Returns 0 on success or error code on error.
* The context must be destroyed with `FASTCOVER_ctx_destroy()`.
*/
static size_t
FASTCOVER_ctx_init(FASTCOVER_ctx_t* ctx,
const void* samplesBuffer,
const size_t* samplesSizes, unsigned nbSamples,
unsigned d, double splitPoint, unsigned f,
FASTCOVER_accel_t accelParams)
{
const BYTE* const samples = (const BYTE*)samplesBuffer;
const size_t totalSamplesSize = COVER_sum(samplesSizes, nbSamples);
/* Split samples into testing and training sets */
const unsigned nbTrainSamples = splitPoint < 1.0 ? (unsigned)((double)nbSamples * splitPoint) : nbSamples;
const unsigned nbTestSamples = splitPoint < 1.0 ? nbSamples - nbTrainSamples : nbSamples;
const size_t trainingSamplesSize = splitPoint < 1.0 ? COVER_sum(samplesSizes, nbTrainSamples) : totalSamplesSize;
const size_t testSamplesSize = splitPoint < 1.0 ? COVER_sum(samplesSizes + nbTrainSamples, nbTestSamples) : totalSamplesSize;
/* Checks */
if (totalSamplesSize < MAX(d, sizeof(U64)) ||
totalSamplesSize >= (size_t)FASTCOVER_MAX_SAMPLES_SIZE) {
DISPLAYLEVEL(1, "Total samples size is too large (%u MB), maximum size is %u MB\n",
(unsigned)(totalSamplesSize >> 20), (FASTCOVER_MAX_SAMPLES_SIZE >> 20));
return ERROR(srcSize_wrong);
}
/* Check if there are at least 5 training samples */
if (nbTrainSamples < 5) {
DISPLAYLEVEL(1, "Total number of training samples is %u and is invalid\n", nbTrainSamples);
return ERROR(srcSize_wrong);
}
/* Check if there's testing sample */
if (nbTestSamples < 1) {
DISPLAYLEVEL(1, "Total number of testing samples is %u and is invalid.\n", nbTestSamples);
return ERROR(srcSize_wrong);
}
/* Zero the context */
memset(ctx, 0, sizeof(*ctx));
DISPLAYLEVEL(2, "Training on %u samples of total size %u\n", nbTrainSamples,
(unsigned)trainingSamplesSize);
DISPLAYLEVEL(2, "Testing on %u samples of total size %u\n", nbTestSamples,
(unsigned)testSamplesSize);
ctx->samples = samples;
ctx->samplesSizes = samplesSizes;
ctx->nbSamples = nbSamples;
ctx->nbTrainSamples = nbTrainSamples;
ctx->nbTestSamples = nbTestSamples;
ctx->nbDmers = trainingSamplesSize - MAX(d, sizeof(U64)) + 1;
ctx->d = d;
ctx->f = f;
ctx->accelParams = accelParams;
/* The offsets of each file */
ctx->offsets = (size_t*)calloc((nbSamples + 1), sizeof(size_t));
if (ctx->offsets == NULL) {
DISPLAYLEVEL(1, "Failed to allocate scratch buffers \n");
FASTCOVER_ctx_destroy(ctx);
return ERROR(memory_allocation);
}
/* Fill offsets from the samplesSizes */
{ U32 i;
ctx->offsets[0] = 0;
assert(nbSamples >= 5);
for (i = 1; i <= nbSamples; ++i) {
ctx->offsets[i] = ctx->offsets[i - 1] + samplesSizes[i - 1];
}
}
/* Initialize frequency array of size 2^f */
ctx->freqs = (U32*)calloc(((U64)1 << f), sizeof(U32));
if (ctx->freqs == NULL) {
DISPLAYLEVEL(1, "Failed to allocate frequency table \n");
FASTCOVER_ctx_destroy(ctx);
return ERROR(memory_allocation);
}
DISPLAYLEVEL(2, "Computing frequencies\n");
FASTCOVER_computeFrequency(ctx->freqs, ctx);
return 0;
}
/**
* Given the prepared context build the dictionary.
*/
static size_t
FASTCOVER_buildDictionary(const FASTCOVER_ctx_t* ctx,
U32* freqs,
void* dictBuffer, size_t dictBufferCapacity,
ZDICT_cover_params_t parameters,
U16* segmentFreqs)
{
BYTE *const dict = (BYTE *)dictBuffer;
size_t tail = dictBufferCapacity;
/* Divide the data into epochs. We will select one segment from each epoch. */
const COVER_epoch_info_t epochs = COVER_computeEpochs(
(U32)dictBufferCapacity, (U32)ctx->nbDmers, parameters.k, 1);
const size_t maxZeroScoreRun = 10;
size_t zeroScoreRun = 0;
size_t epoch;
DISPLAYLEVEL(2, "Breaking content into %u epochs of size %u\n",
(U32)epochs.num, (U32)epochs.size);
/* Loop through the epochs until there are no more segments or the dictionary
* is full.
*/
for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs.num) {
const U32 epochBegin = (U32)(epoch * epochs.size);
const U32 epochEnd = epochBegin + epochs.size;
size_t segmentSize;
/* Select a segment */
COVER_segment_t segment = FASTCOVER_selectSegment(
ctx, freqs, epochBegin, epochEnd, parameters, segmentFreqs);
/* If the segment covers no dmers, then we are out of content.
* There may be new content in other epochs, for continue for some time.
*/
if (segment.score == 0) {
if (++zeroScoreRun >= maxZeroScoreRun) {
break;
}
continue;
}
zeroScoreRun = 0;
/* Trim the segment if necessary and if it is too small then we are done */
segmentSize = MIN(segment.end - segment.begin + parameters.d - 1, tail);
if (segmentSize < parameters.d) {
break;
}
/* We fill the dictionary from the back to allow the best segments to be
* referenced with the smallest offsets.
*/
tail -= segmentSize;
memcpy(dict + tail, ctx->samples + segment.begin, segmentSize);
DISPLAYUPDATE(
2, "\r%u%% ",
(unsigned)(((dictBufferCapacity - tail) * 100) / dictBufferCapacity));
}
DISPLAYLEVEL(2, "\r%79s\r", "");
return tail;
}
/**
* Parameters for FASTCOVER_tryParameters().
*/
typedef struct FASTCOVER_tryParameters_data_s {
const FASTCOVER_ctx_t* ctx;
COVER_best_t* best;
size_t dictBufferCapacity;
ZDICT_cover_params_t parameters;
} FASTCOVER_tryParameters_data_t;
/**
* Tries a set of parameters and updates the COVER_best_t with the results.
* This function is thread safe if zstd is compiled with multithreaded support.
* It takes its parameters as an *OWNING* opaque pointer to support threading.
*/
static void FASTCOVER_tryParameters(void *opaque)
{
/* Save parameters as local variables */
FASTCOVER_tryParameters_data_t *const data = (FASTCOVER_tryParameters_data_t *)opaque;
const FASTCOVER_ctx_t *const ctx = data->ctx;
const ZDICT_cover_params_t parameters = data->parameters;
size_t dictBufferCapacity = data->dictBufferCapacity;
size_t totalCompressedSize = ERROR(GENERIC);
/* Initialize array to keep track of frequency of dmer within activeSegment */
U16* segmentFreqs = (U16 *)calloc(((U64)1 << ctx->f), sizeof(U16));
/* Allocate space for hash table, dict, and freqs */
BYTE *const dict = (BYTE * const)malloc(dictBufferCapacity);
COVER_dictSelection_t selection = COVER_dictSelectionError(ERROR(GENERIC));
U32 *freqs = (U32*) malloc(((U64)1 << ctx->f) * sizeof(U32));
if (!segmentFreqs || !dict || !freqs) {
DISPLAYLEVEL(1, "Failed to allocate buffers: out of memory\n");
goto _cleanup;
}
/* Copy the frequencies because we need to modify them */
memcpy(freqs, ctx->freqs, ((U64)1 << ctx->f) * sizeof(U32));
/* Build the dictionary */
{ const size_t tail = FASTCOVER_buildDictionary(ctx, freqs, dict, dictBufferCapacity,
parameters, segmentFreqs);
const unsigned nbFinalizeSamples = (unsigned)(ctx->nbTrainSamples * ctx->accelParams.finalize / 100);
selection = COVER_selectDict(dict + tail, dictBufferCapacity - tail,
ctx->samples, ctx->samplesSizes, nbFinalizeSamples, ctx->nbTrainSamples, ctx->nbSamples, parameters, ctx->offsets,
totalCompressedSize);
if (COVER_dictSelectionIsError(selection)) {
DISPLAYLEVEL(1, "Failed to select dictionary\n");
goto _cleanup;
}
}
_cleanup:
free(dict);
COVER_best_finish(data->best, parameters, selection);
free(data);
free(segmentFreqs);
COVER_dictSelectionFree(selection);
free(freqs);
}
static void
FASTCOVER_convertToCoverParams(ZDICT_fastCover_params_t fastCoverParams,
ZDICT_cover_params_t* coverParams)
{
coverParams->k = fastCoverParams.k;
coverParams->d = fastCoverParams.d;
coverParams->steps = fastCoverParams.steps;
coverParams->nbThreads = fastCoverParams.nbThreads;
coverParams->splitPoint = fastCoverParams.splitPoint;
coverParams->zParams = fastCoverParams.zParams;
coverParams->shrinkDict = fastCoverParams.shrinkDict;
}
static void
FASTCOVER_convertToFastCoverParams(ZDICT_cover_params_t coverParams,
ZDICT_fastCover_params_t* fastCoverParams,
unsigned f, unsigned accel)
{
fastCoverParams->k = coverParams.k;
fastCoverParams->d = coverParams.d;
fastCoverParams->steps = coverParams.steps;
fastCoverParams->nbThreads = coverParams.nbThreads;
fastCoverParams->splitPoint = coverParams.splitPoint;
fastCoverParams->f = f;
fastCoverParams->accel = accel;
fastCoverParams->zParams = coverParams.zParams;
fastCoverParams->shrinkDict = coverParams.shrinkDict;
}
ZDICTLIB_API size_t
ZDICT_trainFromBuffer_fastCover(void* dictBuffer, size_t dictBufferCapacity,
const void* samplesBuffer,
const size_t* samplesSizes, unsigned nbSamples,
ZDICT_fastCover_params_t parameters)
{
BYTE* const dict = (BYTE*)dictBuffer;
FASTCOVER_ctx_t ctx;
ZDICT_cover_params_t coverParams;
FASTCOVER_accel_t accelParams;
/* Initialize global data */
g_displayLevel = parameters.zParams.notificationLevel;
/* Assign splitPoint and f if not provided */
parameters.splitPoint = 1.0;
parameters.f = parameters.f == 0 ? DEFAULT_F : parameters.f;
parameters.accel = parameters.accel == 0 ? DEFAULT_ACCEL : parameters.accel;
/* Convert to cover parameter */
memset(&coverParams, 0 , sizeof(coverParams));
FASTCOVER_convertToCoverParams(parameters, &coverParams);
/* Checks */
if (!FASTCOVER_checkParameters(coverParams, dictBufferCapacity, parameters.f,
parameters.accel)) {
DISPLAYLEVEL(1, "FASTCOVER parameters incorrect\n");
return ERROR(parameter_outOfBound);
}
if (nbSamples == 0) {
DISPLAYLEVEL(1, "FASTCOVER must have at least one input file\n");
return ERROR(srcSize_wrong);
}
if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) {
DISPLAYLEVEL(1, "dictBufferCapacity must be at least %u\n",
ZDICT_DICTSIZE_MIN);
return ERROR(dstSize_tooSmall);
}
/* Assign corresponding FASTCOVER_accel_t to accelParams*/
accelParams = FASTCOVER_defaultAccelParameters[parameters.accel];
/* Initialize context */
{
size_t const initVal = FASTCOVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples,
coverParams.d, parameters.splitPoint, parameters.f,
accelParams);
if (ZSTD_isError(initVal)) {
DISPLAYLEVEL(1, "Failed to initialize context\n");
return initVal;
}
}
COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.nbDmers, g_displayLevel);
/* Build the dictionary */
DISPLAYLEVEL(2, "Building dictionary\n");
{
/* Initialize array to keep track of frequency of dmer within activeSegment */
U16* segmentFreqs = (U16 *)calloc(((U64)1 << parameters.f), sizeof(U16));
const size_t tail = FASTCOVER_buildDictionary(&ctx, ctx.freqs, dictBuffer,
dictBufferCapacity, coverParams, segmentFreqs);
const unsigned nbFinalizeSamples = (unsigned)(ctx.nbTrainSamples * ctx.accelParams.finalize / 100);
const size_t dictionarySize = ZDICT_finalizeDictionary(
dict, dictBufferCapacity, dict + tail, dictBufferCapacity - tail,
samplesBuffer, samplesSizes, nbFinalizeSamples, coverParams.zParams);
if (!ZSTD_isError(dictionarySize)) {
DISPLAYLEVEL(2, "Constructed dictionary of size %u\n",
(unsigned)dictionarySize);
}
FASTCOVER_ctx_destroy(&ctx);
free(segmentFreqs);
return dictionarySize;
}
}
ZDICTLIB_API size_t
ZDICT_optimizeTrainFromBuffer_fastCover(
void* dictBuffer, size_t dictBufferCapacity,
const void* samplesBuffer,
const size_t* samplesSizes, unsigned nbSamples,
ZDICT_fastCover_params_t* parameters)
{
ZDICT_cover_params_t coverParams;
FASTCOVER_accel_t accelParams;
/* constants */
const unsigned nbThreads = parameters->nbThreads;
const double splitPoint =
parameters->splitPoint <= 0.0 ? DEFAULT_SPLITPOINT : parameters->splitPoint;
const unsigned kMinD = parameters->d == 0 ? 6 : parameters->d;
const unsigned kMaxD = parameters->d == 0 ? 8 : parameters->d;
const unsigned kMinK = parameters->k == 0 ? 50 : parameters->k;
const unsigned kMaxK = parameters->k == 0 ? 2000 : parameters->k;
const unsigned kSteps = parameters->steps == 0 ? 40 : parameters->steps;
const unsigned kStepSize = MAX((kMaxK - kMinK) / kSteps, 1);
const unsigned kIterations =
(1 + (kMaxD - kMinD) / 2) * (1 + (kMaxK - kMinK) / kStepSize);
const unsigned f = parameters->f == 0 ? DEFAULT_F : parameters->f;
const unsigned accel = parameters->accel == 0 ? DEFAULT_ACCEL : parameters->accel;
const unsigned shrinkDict = 0;
/* Local variables */
const int displayLevel = parameters->zParams.notificationLevel;
unsigned iteration = 1;
unsigned d;
unsigned k;
COVER_best_t best;
POOL_ctx *pool = NULL;
int warned = 0;
/* Checks */
if (splitPoint <= 0 || splitPoint > 1) {
LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect splitPoint\n");
return ERROR(parameter_outOfBound);
}
if (accel == 0 || accel > FASTCOVER_MAX_ACCEL) {
LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect accel\n");
return ERROR(parameter_outOfBound);
}
if (kMinK < kMaxD || kMaxK < kMinK) {
LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect k\n");
return ERROR(parameter_outOfBound);
}
if (nbSamples == 0) {
LOCALDISPLAYLEVEL(displayLevel, 1, "FASTCOVER must have at least one input file\n");
return ERROR(srcSize_wrong);
}
if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) {
LOCALDISPLAYLEVEL(displayLevel, 1, "dictBufferCapacity must be at least %u\n",
ZDICT_DICTSIZE_MIN);
return ERROR(dstSize_tooSmall);
}
if (nbThreads > 1) {
pool = POOL_create(nbThreads, 1);
if (!pool) {
return ERROR(memory_allocation);
}
}
/* Initialization */
COVER_best_init(&best);
memset(&coverParams, 0 , sizeof(coverParams));
FASTCOVER_convertToCoverParams(*parameters, &coverParams);
accelParams = FASTCOVER_defaultAccelParameters[accel];
/* Turn down global display level to clean up display at level 2 and below */
g_displayLevel = displayLevel == 0 ? 0 : displayLevel - 1;
/* Loop through d first because each new value needs a new context */
LOCALDISPLAYLEVEL(displayLevel, 2, "Trying %u different sets of parameters\n",
kIterations);
for (d = kMinD; d <= kMaxD; d += 2) {
/* Initialize the context for this value of d */
FASTCOVER_ctx_t ctx;
LOCALDISPLAYLEVEL(displayLevel, 3, "d=%u\n", d);
{
size_t const initVal = FASTCOVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples, d, splitPoint, f, accelParams);
if (ZSTD_isError(initVal)) {
LOCALDISPLAYLEVEL(displayLevel, 1, "Failed to initialize context\n");
COVER_best_destroy(&best);
POOL_free(pool);
return initVal;
}
}
if (!warned) {
COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.nbDmers, displayLevel);
warned = 1;
}
/* Loop through k reusing the same context */
for (k = kMinK; k <= kMaxK; k += kStepSize) {
/* Prepare the arguments */
FASTCOVER_tryParameters_data_t *data = (FASTCOVER_tryParameters_data_t *)malloc(
sizeof(FASTCOVER_tryParameters_data_t));
LOCALDISPLAYLEVEL(displayLevel, 3, "k=%u\n", k);
if (!data) {
LOCALDISPLAYLEVEL(displayLevel, 1, "Failed to allocate parameters\n");
COVER_best_destroy(&best);
FASTCOVER_ctx_destroy(&ctx);
POOL_free(pool);
return ERROR(memory_allocation);
}
data->ctx = &ctx;
data->best = &best;
data->dictBufferCapacity = dictBufferCapacity;
data->parameters = coverParams;
data->parameters.k = k;
data->parameters.d = d;
data->parameters.splitPoint = splitPoint;
data->parameters.steps = kSteps;
data->parameters.shrinkDict = shrinkDict;
data->parameters.zParams.notificationLevel = g_displayLevel;
/* Check the parameters */
if (!FASTCOVER_checkParameters(data->parameters, dictBufferCapacity,
data->ctx->f, accel)) {
DISPLAYLEVEL(1, "FASTCOVER parameters incorrect\n");
free(data);
continue;
}
/* Call the function and pass ownership of data to it */
COVER_best_start(&best);
if (pool) {
POOL_add(pool, &FASTCOVER_tryParameters, data);
} else {
FASTCOVER_tryParameters(data);
}
/* Print status */
LOCALDISPLAYUPDATE(displayLevel, 2, "\r%u%% ",
(unsigned)((iteration * 100) / kIterations));
++iteration;
}
COVER_best_wait(&best);
FASTCOVER_ctx_destroy(&ctx);
}
LOCALDISPLAYLEVEL(displayLevel, 2, "\r%79s\r", "");
/* Fill the output buffer and parameters with output of the best parameters */
{
const size_t dictSize = best.dictSize;
if (ZSTD_isError(best.compressedSize)) {
const size_t compressedSize = best.compressedSize;
COVER_best_destroy(&best);
POOL_free(pool);
return compressedSize;
}
FASTCOVER_convertToFastCoverParams(best.parameters, parameters, f, accel);
memcpy(dictBuffer, best.dict, dictSize);
COVER_best_destroy(&best);
POOL_free(pool);
return dictSize;
}
}