##// END OF EJS Templates
copies: iterate over children directly (instead of parents)...
copies: iterate over children directly (instead of parents) Before this change we would gather all parent → child edges and iterate on all parent, gathering copy information for children and aggregating them from there. They are not strict requirement for edges to be processed in that specific order. We could also simply iterate over all "children" revision and aggregate data from both parents at the same time. This patch does that. It make various things simpler: * since both parents are processed at the same time, we no longer need to cache data for merge (see next changeset for details), * we no longer need nested loop to process data, * we no longer need to store partial merge data for a rev from distinct loop interaction to another when processing merges, * we no longer need to build a full parent -> children mapping (we only rely on a simpler "parent -> number of children" map (for memory efficiency), * the data access pattern is now simpler (from lower revisions to higher revisions) and entirely predicable. That predictability open the way to prefetching and parallel processing. So that new iterations order requires simpler code and open the way to interesting optimisation. The effect on performance is quite good. In the worse case, we don't see any significant negative impact. And in the best case, the reduction of roundtrip to Python provide us with a significant speed. Some example below: Repo Case Source-Rev Dest-Rev # of revisions old time new time Difference Factor time per rev --------------------------------------------------------------------------------------------------------------------------------------------------------------- mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.962867 s, 0.502584 s, -0.460283 s, × 0.5220, 14 µs/rev mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.110717 s, 0.076323 s, -0.034394 s, × 0.6894, 8 µs/rev # full comparison between the previous changeset and this one 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, 0.000048 s, 0.000041 s, -0.000007 s, × 0.8542, 41 µs/rev mercurial x_revs_x_added_x_copies 2b1c78674230 0c1d10351869 : 6 revs, 0.000153 s, 0.000102 s, -0.000051 s, × 0.6667, 17 µs/rev mercurial x000_revs_x000_added_x_copies 81f8ff2a9bf2 dd3267698d84 : 1032 revs, 0.004209 s, 0.004254 s, +0.000045 s, × 1.0107, 4 µs/rev pypy x_revs_x_added_0_copies aed021ee8ae8 099ed31b181b : 9 revs, 0.000203 s, 0.000282 s, +0.000079 s, × 1.3892, 31 µs/rev pypy x_revs_x000_added_0_copies 4aa4e1f8e19a 359343b9ac0e : 1 revs, 0.000059 s, 0.000048 s, -0.000011 s, × 0.8136, 48 µs/rev pypy x_revs_x_added_x_copies ac52eb7bbbb0 72e022663155 : 7 revs, 0.000194 s, 0.000211 s, +0.000017 s, × 1.0876, 30 µs/rev pypy x_revs_x00_added_x_copies c3b14617fbd7 ace7255d9a26 : 1 revs, 0.000380 s, 0.000375 s, -0.000005 s, × 0.9868, 375 µs/rev pypy x_revs_x000_added_x000_copies df6f7a526b60 a83dc6a2d56f : 6 revs, 0.010588 s, 0.010574 s, -0.000014 s, × 0.9987, 1762 µs/rev pypy x000_revs_xx00_added_0_copies 89a76aede314 2f22446ff07e : 4785 revs, 0.048961 s, 0.049974 s, +0.001013 s, × 1.0207, 10 µs/rev pypy x000_revs_x000_added_x_copies 8a3b5bfd266e 2c68e87c3efe : 6780 revs, 0.083612 s, 0.084300 s, +0.000688 s, × 1.0082, 12 µs/rev pypy x000_revs_x000_added_x000_copies 89a76aede314 7b3dda341c84 : 5441 revs, 0.058579 s, 0.060128 s, +0.001549 s, × 1.0264, 11 µs/rev pypy x0000_revs_x_added_0_copies d1defd0dc478 c9cb1334cc78 : 43645 revs, 0.736783 s, 0.686542 s, -0.050241 s, × 0.9318, 15 µs/rev pypy x0000_revs_xx000_added_0_copies bf2c629d0071 4ffed77c095c : 2 revs, 0.022050 s, 0.009277 s, -0.012773 s, × 0.4207, 4638 µs/rev pypy x0000_revs_xx000_added_x000_copies 08ea3258278e d9fa043f30c0 : 11316 revs, 0.120800 s, 0.114733 s, -0.006067 s, × 0.9498, 10 µs/rev netbeans x_revs_x_added_0_copies fb0955ffcbcd a01e9239f9e7 : 2 revs, 0.000140 s, 0.000081 s, -0.000059 s, × 0.5786, 40 µs/rev netbeans x_revs_x000_added_0_copies 6f360122949f 20eb231cc7d0 : 2 revs, 0.000114 s, 0.000107 s, -0.000007 s, × 0.9386, 53 µs/rev netbeans x_revs_x_added_x_copies 1ada3faf6fb6 5a39d12eecf4 : 3 revs, 0.000224 s, 0.000173 s, -0.000051 s, × 0.7723, 57 µs/rev netbeans x_revs_x00_added_x_copies 35be93ba1e2c 9eec5e90c05f : 9 revs, 0.000723 s, 0.000698 s, -0.000025 s, × 0.9654, 77 µs/rev netbeans x000_revs_xx00_added_0_copies eac3045b4fdd 51d4ae7f1290 : 1421 revs, 0.009665 s, 0.009248 s, -0.000417 s, × 0.9569, 6 µs/rev netbeans x000_revs_x000_added_x_copies e2063d266acd 6081d72689dc : 1533 revs, 0.014820 s, 0.015446 s, +0.000626 s, × 1.0422, 10 µs/rev netbeans x000_revs_x000_added_x000_copies ff453e9fee32 411350406ec2 : 5750 revs, 0.076049 s, 0.074373 s, -0.001676 s, × 0.9780, 12 µs/rev netbeans x0000_revs_xx000_added_x000_copies 588c2d1ced70 1aad62e59ddd : 66949 revs, 0.683603 s, 0.639870 s, -0.043733 s, × 0.9360, 9 µs/rev mozilla-central x_revs_x_added_0_copies 3697f962bb7b 7015fcdd43a2 : 2 revs, 0.000161 s, 0.000088 s, -0.000073 s, × 0.5466, 44 µs/rev mozilla-central x_revs_x000_added_0_copies dd390860c6c9 40d0c5bed75d : 8 revs, 0.000234 s, 0.000199 s, -0.000035 s, × 0.8504, 24 µs/rev mozilla-central x_revs_x_added_x_copies 8d198483ae3b 14207ffc2b2f : 9 revs, 0.000247 s, 0.000171 s, -0.000076 s, × 0.6923, 19 µs/rev mozilla-central x_revs_x00_added_x_copies 98cbc58cc6bc 446a150332c3 : 7 revs, 0.000630 s, 0.000592 s, -0.000038 s, × 0.9397, 84 µs/rev mozilla-central x_revs_x000_added_x000_copies 3c684b4b8f68 0a5e72d1b479 : 3 revs, 0.003286 s, 0.003151 s, -0.000135 s, × 0.9589, 1050 µs/rev mozilla-central x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.062441 s, 0.061612 s, -0.000829 s, × 0.9867, 10268 µs/rev mozilla-central x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.005423 s, 0.005381 s, -0.000042 s, × 0.9923, 3 µs/rev mozilla-central x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.005919 s, 0.003742 s, -0.002177 s, × 0.6322, 91 µs/rev mozilla-central x000_revs_x000_added_x000_copies 7c97034feb78 4407bd0c6330 : 7839 revs, 0.062597 s, 0.061983 s, -0.000614 s, × 0.9902, 7 µs/rev mozilla-central x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.043551 s, 0.019861 s, -0.023690 s, × 0.4560, 32 µs/rev mozilla-central x0000_revs_xx000_added_x000_copies f78c615a656c 96a38b690156 : 30263 revs, 0.192475 s, 0.188101 s, -0.004374 s, × 0.9773, 6 µs/rev mozilla-central x00000_revs_x0000_added_x0000_copies 6832ae71433c 4c222a1d9a00 : 153721 revs, 1.955575 s, 1.806696 s, -0.148879 s, × 0.9239, 11 µs/rev mozilla-central x00000_revs_x00000_added_x000_copies 76caed42cf7c 1daa622bbe42 : 204976 revs, 2.886501 s, 2.682987 s, -0.203514 s, × 0.9295, 13 µs/rev mozilla-try x_revs_x_added_0_copies aaf6dde0deb8 9790f499805a : 2 revs, 0.001181 s, 0.000852 s, -0.000329 s, × 0.7214, 426 µs/rev mozilla-try x_revs_x000_added_0_copies d8d0222927b4 5bb8ce8c7450 : 2 revs, 0.001189 s, 0.000859 s, -0.000330 s, × 0.7225, 429 µs/rev mozilla-try x_revs_x_added_x_copies 092fcca11bdb 936255a0384a : 4 revs, 0.000563 s, 0.000150 s, -0.000413 s, × 0.2664, 37 µs/rev mozilla-try x_revs_x00_added_x_copies b53d2fadbdb5 017afae788ec : 2 revs, 0.001548 s, 0.001158 s, -0.000390 s, × 0.7481, 579 µs/rev mozilla-try x_revs_x000_added_x000_copies 20408ad61ce5 6f0ee96e21ad : 1 revs, 0.027782 s, 0.027240 s, -0.000542 s, × 0.9805, 27240 µs/rev mozilla-try x_revs_x0000_added_x0000_copies effb563bb7e5 c07a39dc4e80 : 6 revs, 0.062781 s, 0.062824 s, +0.000043 s, × 1.0007, 10470 µs/rev mozilla-try x000_revs_xx00_added_0_copies 6100d773079a 04a55431795e : 1593 revs, 0.005778 s, 0.005463 s, -0.000315 s, × 0.9455, 3 µs/rev mozilla-try x000_revs_x000_added_x_copies 9f17a6fc04f9 2d37b966abed : 41 revs, 0.006192 s, 0.004238 s, -0.001954 s, × 0.6844, 103 µs/rev mozilla-try x000_revs_x000_added_x000_copies 1346fd0130e4 4c65cbdabc1f : 6657 revs, 0.065391 s, 0.064113 s, -0.001278 s, × 0.9805, 9 µs/rev mozilla-try x0000_revs_x_added_0_copies 63519bfd42ee a36a2a865d92 : 40314 revs, 0.317216 s, 0.294063 s, -0.023153 s, × 0.9270, 7 µs/rev mozilla-try x0000_revs_x_added_x_copies 9fe69ff0762d bcabf2a78927 : 38690 revs, 0.303119 s, 0.281493 s, -0.021626 s, × 0.9287, 7 µs/rev mozilla-try x0000_revs_xx000_added_x_copies 156f6e2674f2 4d0f2c178e66 : 8598 revs, 0.110717 s, 0.076323 s, -0.034394 s, × 0.6894, 8 µs/rev mozilla-try x0000_revs_xx000_added_0_copies 9eec5917337d 67118cc6dcad : 615 revs, 0.045739 s, 0.020390 s, -0.025349 s, × 0.4458, 33 µs/rev mozilla-try x0000_revs_xx000_added_x000_copies 89294cd501d9 7ccb2fc7ccb5 : 97052 revs, 3.098021 s, 3.023879 s, -0.074142 s, × 0.9761, 31 µs/rev mozilla-try x0000_revs_x0000_added_x0000_copies e928c65095ed e951f4ad123a : 52031 revs, 0.771480 s, 0.735549 s, -0.035931 s, × 0.9534, 14 µs/rev mozilla-try x00000_revs_x_added_0_copies 6a320851d377 1ebb79acd503 : 363753 revs, 18.813422 s, 18.568900 s, -0.244522 s, × 0.9870, 51 µs/rev mozilla-try x00000_revs_x00000_added_0_copies dc8a3ca7010e d16fde900c9c : 34414 revs, 0.962867 s, 0.502584 s, -0.460283 s, × 0.5220, 14 µs/rev mozilla-try x00000_revs_x_added_x_copies 5173c4b6f97c 95d83ee7242d : 362229 revs, 18.684923 s, 18.356645 s, -0.328278 s, × 0.9824, 50 µs/rev mozilla-try x00000_revs_x000_added_x_copies 9126823d0e9c ca82787bb23c : 359344 revs, 18.296305 s, 18.250393 s, -0.045912 s, × 0.9975, 50 µs/rev mozilla-try x00000_revs_x0000_added_x0000_copies 8d3fafa80d4b eb884023b810 : 192665 revs, 3.061887 s, 2.792459 s, -0.269428 s, × 0.9120, 14 µs/rev mozilla-try x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 228985 revs, 103.869641 s, 107.697264 s, +3.827623 s, × 1.0369, 470 µs/rev mozilla-try x00000_revs_x00000_added_x000_copies 9b2a99adc05e 8e29777b48e6 : 382065 revs, 64.262957 s, 63.961040 s, -0.301917 s, × 0.9953, 167 µs/rev Differential Revision: https://phab.mercurial-scm.org/D9422

File last commit:

r44446:de783805 default
r46764:294d5aca default
Show More
zstd_fast.c
484 lines | 21.4 KiB | text/x-c | CLexer
/*
* Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
* All rights reserved.
*
* This source code is licensed under both the BSD-style license (found in the
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
* in the COPYING file in the root directory of this source tree).
* You may select, at your option, one of the above-listed licenses.
*/
#include "zstd_compress_internal.h" /* ZSTD_hashPtr, ZSTD_count, ZSTD_storeSeq */
#include "zstd_fast.h"
void ZSTD_fillHashTable(ZSTD_matchState_t* ms,
const void* const end,
ZSTD_dictTableLoadMethod_e dtlm)
{
const ZSTD_compressionParameters* const cParams = &ms->cParams;
U32* const hashTable = ms->hashTable;
U32 const hBits = cParams->hashLog;
U32 const mls = cParams->minMatch;
const BYTE* const base = ms->window.base;
const BYTE* ip = base + ms->nextToUpdate;
const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE;
const U32 fastHashFillStep = 3;
/* Always insert every fastHashFillStep position into the hash table.
* Insert the other positions if their hash entry is empty.
*/
for ( ; ip + fastHashFillStep < iend + 2; ip += fastHashFillStep) {
U32 const current = (U32)(ip - base);
size_t const hash0 = ZSTD_hashPtr(ip, hBits, mls);
hashTable[hash0] = current;
if (dtlm == ZSTD_dtlm_fast) continue;
/* Only load extra positions for ZSTD_dtlm_full */
{ U32 p;
for (p = 1; p < fastHashFillStep; ++p) {
size_t const hash = ZSTD_hashPtr(ip + p, hBits, mls);
if (hashTable[hash] == 0) { /* not yet filled */
hashTable[hash] = current + p;
} } } }
}
FORCE_INLINE_TEMPLATE size_t
ZSTD_compressBlock_fast_generic(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize,
U32 const mls)
{
const ZSTD_compressionParameters* const cParams = &ms->cParams;
U32* const hashTable = ms->hashTable;
U32 const hlog = cParams->hashLog;
/* support stepSize of 0 */
size_t const stepSize = cParams->targetLength + !(cParams->targetLength) + 1;
const BYTE* const base = ms->window.base;
const BYTE* const istart = (const BYTE*)src;
/* We check ip0 (ip + 0) and ip1 (ip + 1) each loop */
const BYTE* ip0 = istart;
const BYTE* ip1;
const BYTE* anchor = istart;
const U32 endIndex = (U32)((size_t)(istart - base) + srcSize);
const U32 maxDistance = 1U << cParams->windowLog;
const U32 validStartIndex = ms->window.dictLimit;
const U32 prefixStartIndex = (endIndex - validStartIndex > maxDistance) ? endIndex - maxDistance : validStartIndex;
const BYTE* const prefixStart = base + prefixStartIndex;
const BYTE* const iend = istart + srcSize;
const BYTE* const ilimit = iend - HASH_READ_SIZE;
U32 offset_1=rep[0], offset_2=rep[1];
U32 offsetSaved = 0;
/* init */
DEBUGLOG(5, "ZSTD_compressBlock_fast_generic");
ip0 += (ip0 == prefixStart);
ip1 = ip0 + 1;
{ U32 const maxRep = (U32)(ip0 - prefixStart);
if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0;
if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0;
}
/* Main Search Loop */
while (ip1 < ilimit) { /* < instead of <=, because check at ip0+2 */
size_t mLength;
BYTE const* ip2 = ip0 + 2;
size_t const h0 = ZSTD_hashPtr(ip0, hlog, mls);
U32 const val0 = MEM_read32(ip0);
size_t const h1 = ZSTD_hashPtr(ip1, hlog, mls);
U32 const val1 = MEM_read32(ip1);
U32 const current0 = (U32)(ip0-base);
U32 const current1 = (U32)(ip1-base);
U32 const matchIndex0 = hashTable[h0];
U32 const matchIndex1 = hashTable[h1];
BYTE const* repMatch = ip2-offset_1;
const BYTE* match0 = base + matchIndex0;
const BYTE* match1 = base + matchIndex1;
U32 offcode;
hashTable[h0] = current0; /* update hash table */
hashTable[h1] = current1; /* update hash table */
assert(ip0 + 1 == ip1);
if ((offset_1 > 0) & (MEM_read32(repMatch) == MEM_read32(ip2))) {
mLength = ip2[-1] == repMatch[-1] ? 1 : 0;
ip0 = ip2 - mLength;
match0 = repMatch - mLength;
offcode = 0;
goto _match;
}
if ((matchIndex0 > prefixStartIndex) && MEM_read32(match0) == val0) {
/* found a regular match */
goto _offset;
}
if ((matchIndex1 > prefixStartIndex) && MEM_read32(match1) == val1) {
/* found a regular match after one literal */
ip0 = ip1;
match0 = match1;
goto _offset;
}
{ size_t const step = ((size_t)(ip0-anchor) >> (kSearchStrength - 1)) + stepSize;
assert(step >= 2);
ip0 += step;
ip1 += step;
continue;
}
_offset: /* Requires: ip0, match0 */
/* Compute the offset code */
offset_2 = offset_1;
offset_1 = (U32)(ip0-match0);
offcode = offset_1 + ZSTD_REP_MOVE;
mLength = 0;
/* Count the backwards match length */
while (((ip0>anchor) & (match0>prefixStart))
&& (ip0[-1] == match0[-1])) { ip0--; match0--; mLength++; } /* catch up */
_match: /* Requires: ip0, match0, offcode */
/* Count the forward length */
mLength += ZSTD_count(ip0+mLength+4, match0+mLength+4, iend) + 4;
ZSTD_storeSeq(seqStore, (size_t)(ip0-anchor), anchor, iend, offcode, mLength-MINMATCH);
/* match found */
ip0 += mLength;
anchor = ip0;
ip1 = ip0 + 1;
if (ip0 <= ilimit) {
/* Fill Table */
assert(base+current0+2 > istart); /* check base overflow */
hashTable[ZSTD_hashPtr(base+current0+2, hlog, mls)] = current0+2; /* here because current+2 could be > iend-8 */
hashTable[ZSTD_hashPtr(ip0-2, hlog, mls)] = (U32)(ip0-2-base);
while ( ((ip0 <= ilimit) & (offset_2>0)) /* offset_2==0 means offset_2 is invalidated */
&& (MEM_read32(ip0) == MEM_read32(ip0 - offset_2)) ) {
/* store sequence */
size_t const rLength = ZSTD_count(ip0+4, ip0+4-offset_2, iend) + 4;
{ U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff; } /* swap offset_2 <=> offset_1 */
hashTable[ZSTD_hashPtr(ip0, hlog, mls)] = (U32)(ip0-base);
ip0 += rLength;
ip1 = ip0 + 1;
ZSTD_storeSeq(seqStore, 0 /*litLen*/, anchor, iend, 0 /*offCode*/, rLength-MINMATCH);
anchor = ip0;
continue; /* faster when present (confirmed on gcc-8) ... (?) */
}
}
}
/* save reps for next block */
rep[0] = offset_1 ? offset_1 : offsetSaved;
rep[1] = offset_2 ? offset_2 : offsetSaved;
/* Return the last literals size */
return (size_t)(iend - anchor);
}
size_t ZSTD_compressBlock_fast(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize)
{
U32 const mls = ms->cParams.minMatch;
assert(ms->dictMatchState == NULL);
switch(mls)
{
default: /* includes case 3 */
case 4 :
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4);
case 5 :
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5);
case 6 :
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6);
case 7 :
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7);
}
}
FORCE_INLINE_TEMPLATE
size_t ZSTD_compressBlock_fast_dictMatchState_generic(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize, U32 const mls)
{
const ZSTD_compressionParameters* const cParams = &ms->cParams;
U32* const hashTable = ms->hashTable;
U32 const hlog = cParams->hashLog;
/* support stepSize of 0 */
U32 const stepSize = cParams->targetLength + !(cParams->targetLength);
const BYTE* const base = ms->window.base;
const BYTE* const istart = (const BYTE*)src;
const BYTE* ip = istart;
const BYTE* anchor = istart;
const U32 prefixStartIndex = ms->window.dictLimit;
const BYTE* const prefixStart = base + prefixStartIndex;
const BYTE* const iend = istart + srcSize;
const BYTE* const ilimit = iend - HASH_READ_SIZE;
U32 offset_1=rep[0], offset_2=rep[1];
U32 offsetSaved = 0;
const ZSTD_matchState_t* const dms = ms->dictMatchState;
const ZSTD_compressionParameters* const dictCParams = &dms->cParams ;
const U32* const dictHashTable = dms->hashTable;
const U32 dictStartIndex = dms->window.dictLimit;
const BYTE* const dictBase = dms->window.base;
const BYTE* const dictStart = dictBase + dictStartIndex;
const BYTE* const dictEnd = dms->window.nextSrc;
const U32 dictIndexDelta = prefixStartIndex - (U32)(dictEnd - dictBase);
const U32 dictAndPrefixLength = (U32)(ip - prefixStart + dictEnd - dictStart);
const U32 dictHLog = dictCParams->hashLog;
/* if a dictionary is still attached, it necessarily means that
* it is within window size. So we just check it. */
const U32 maxDistance = 1U << cParams->windowLog;
const U32 endIndex = (U32)((size_t)(ip - base) + srcSize);
assert(endIndex - prefixStartIndex <= maxDistance);
(void)maxDistance; (void)endIndex; /* these variables are not used when assert() is disabled */
/* ensure there will be no no underflow
* when translating a dict index into a local index */
assert(prefixStartIndex >= (U32)(dictEnd - dictBase));
/* init */
DEBUGLOG(5, "ZSTD_compressBlock_fast_dictMatchState_generic");
ip += (dictAndPrefixLength == 0);
/* dictMatchState repCode checks don't currently handle repCode == 0
* disabling. */
assert(offset_1 <= dictAndPrefixLength);
assert(offset_2 <= dictAndPrefixLength);
/* Main Search Loop */
while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */
size_t mLength;
size_t const h = ZSTD_hashPtr(ip, hlog, mls);
U32 const current = (U32)(ip-base);
U32 const matchIndex = hashTable[h];
const BYTE* match = base + matchIndex;
const U32 repIndex = current + 1 - offset_1;
const BYTE* repMatch = (repIndex < prefixStartIndex) ?
dictBase + (repIndex - dictIndexDelta) :
base + repIndex;
hashTable[h] = current; /* update hash table */
if ( ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */
&& (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4;
ip++;
ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, mLength-MINMATCH);
} else if ( (matchIndex <= prefixStartIndex) ) {
size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls);
U32 const dictMatchIndex = dictHashTable[dictHash];
const BYTE* dictMatch = dictBase + dictMatchIndex;
if (dictMatchIndex <= dictStartIndex ||
MEM_read32(dictMatch) != MEM_read32(ip)) {
assert(stepSize >= 1);
ip += ((ip-anchor) >> kSearchStrength) + stepSize;
continue;
} else {
/* found a dict match */
U32 const offset = (U32)(current-dictMatchIndex-dictIndexDelta);
mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, prefixStart) + 4;
while (((ip>anchor) & (dictMatch>dictStart))
&& (ip[-1] == dictMatch[-1])) {
ip--; dictMatch--; mLength++;
} /* catch up */
offset_2 = offset_1;
offset_1 = offset;
ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
}
} else if (MEM_read32(match) != MEM_read32(ip)) {
/* it's not a match, and we're not going to check the dictionary */
assert(stepSize >= 1);
ip += ((ip-anchor) >> kSearchStrength) + stepSize;
continue;
} else {
/* found a regular match */
U32 const offset = (U32)(ip-match);
mLength = ZSTD_count(ip+4, match+4, iend) + 4;
while (((ip>anchor) & (match>prefixStart))
&& (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
offset_2 = offset_1;
offset_1 = offset;
ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
}
/* match found */
ip += mLength;
anchor = ip;
if (ip <= ilimit) {
/* Fill Table */
assert(base+current+2 > istart); /* check base overflow */
hashTable[ZSTD_hashPtr(base+current+2, hlog, mls)] = current+2; /* here because current+2 could be > iend-8 */
hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base);
/* check immediate repcode */
while (ip <= ilimit) {
U32 const current2 = (U32)(ip-base);
U32 const repIndex2 = current2 - offset_2;
const BYTE* repMatch2 = repIndex2 < prefixStartIndex ?
dictBase - dictIndexDelta + repIndex2 :
base + repIndex2;
if ( ((U32)((prefixStartIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
&& (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */
ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, repLength2-MINMATCH);
hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;
ip += repLength2;
anchor = ip;
continue;
}
break;
}
}
}
/* save reps for next block */
rep[0] = offset_1 ? offset_1 : offsetSaved;
rep[1] = offset_2 ? offset_2 : offsetSaved;
/* Return the last literals size */
return (size_t)(iend - anchor);
}
size_t ZSTD_compressBlock_fast_dictMatchState(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize)
{
U32 const mls = ms->cParams.minMatch;
assert(ms->dictMatchState != NULL);
switch(mls)
{
default: /* includes case 3 */
case 4 :
return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 4);
case 5 :
return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 5);
case 6 :
return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 6);
case 7 :
return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 7);
}
}
static size_t ZSTD_compressBlock_fast_extDict_generic(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize, U32 const mls)
{
const ZSTD_compressionParameters* const cParams = &ms->cParams;
U32* const hashTable = ms->hashTable;
U32 const hlog = cParams->hashLog;
/* support stepSize of 0 */
U32 const stepSize = cParams->targetLength + !(cParams->targetLength);
const BYTE* const base = ms->window.base;
const BYTE* const dictBase = ms->window.dictBase;
const BYTE* const istart = (const BYTE*)src;
const BYTE* ip = istart;
const BYTE* anchor = istart;
const U32 endIndex = (U32)((size_t)(istart - base) + srcSize);
const U32 lowLimit = ZSTD_getLowestMatchIndex(ms, endIndex, cParams->windowLog);
const U32 dictStartIndex = lowLimit;
const BYTE* const dictStart = dictBase + dictStartIndex;
const U32 dictLimit = ms->window.dictLimit;
const U32 prefixStartIndex = dictLimit < lowLimit ? lowLimit : dictLimit;
const BYTE* const prefixStart = base + prefixStartIndex;
const BYTE* const dictEnd = dictBase + prefixStartIndex;
const BYTE* const iend = istart + srcSize;
const BYTE* const ilimit = iend - 8;
U32 offset_1=rep[0], offset_2=rep[1];
DEBUGLOG(5, "ZSTD_compressBlock_fast_extDict_generic");
/* switch to "regular" variant if extDict is invalidated due to maxDistance */
if (prefixStartIndex == dictStartIndex)
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, mls);
/* Search Loop */
while (ip < ilimit) { /* < instead of <=, because (ip+1) */
const size_t h = ZSTD_hashPtr(ip, hlog, mls);
const U32 matchIndex = hashTable[h];
const BYTE* const matchBase = matchIndex < prefixStartIndex ? dictBase : base;
const BYTE* match = matchBase + matchIndex;
const U32 current = (U32)(ip-base);
const U32 repIndex = current + 1 - offset_1;
const BYTE* const repBase = repIndex < prefixStartIndex ? dictBase : base;
const BYTE* const repMatch = repBase + repIndex;
hashTable[h] = current; /* update hash table */
assert(offset_1 <= current +1); /* check repIndex */
if ( (((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > dictStartIndex))
&& (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
size_t const rLength = ZSTD_count_2segments(ip+1 +4, repMatch +4, iend, repMatchEnd, prefixStart) + 4;
ip++;
ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, rLength-MINMATCH);
ip += rLength;
anchor = ip;
} else {
if ( (matchIndex < dictStartIndex) ||
(MEM_read32(match) != MEM_read32(ip)) ) {
assert(stepSize >= 1);
ip += ((ip-anchor) >> kSearchStrength) + stepSize;
continue;
}
{ const BYTE* const matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend;
const BYTE* const lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart;
U32 const offset = current - matchIndex;
size_t mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4;
while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
offset_2 = offset_1; offset_1 = offset; /* update offset history */
ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
ip += mLength;
anchor = ip;
} }
if (ip <= ilimit) {
/* Fill Table */
hashTable[ZSTD_hashPtr(base+current+2, hlog, mls)] = current+2;
hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base);
/* check immediate repcode */
while (ip <= ilimit) {
U32 const current2 = (U32)(ip-base);
U32 const repIndex2 = current2 - offset_2;
const BYTE* const repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2;
if ( (((U32)((prefixStartIndex-1) - repIndex2) >= 3) & (repIndex2 > dictStartIndex)) /* intentional overflow */
&& (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
{ U32 const tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; } /* swap offset_2 <=> offset_1 */
ZSTD_storeSeq(seqStore, 0 /*litlen*/, anchor, iend, 0 /*offcode*/, repLength2-MINMATCH);
hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;
ip += repLength2;
anchor = ip;
continue;
}
break;
} } }
/* save reps for next block */
rep[0] = offset_1;
rep[1] = offset_2;
/* Return the last literals size */
return (size_t)(iend - anchor);
}
size_t ZSTD_compressBlock_fast_extDict(
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
void const* src, size_t srcSize)
{
U32 const mls = ms->cParams.minMatch;
switch(mls)
{
default: /* includes case 3 */
case 4 :
return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 4);
case 5 :
return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 5);
case 6 :
return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 6);
case 7 :
return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 7);
}
}