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

Adding shrinking flag for cover and fastcover (#1656)

Browse Source 
* Changed ERROR(GENERIC) excluding inits

* editing git ignore

* Edited init functions to size_t returns

* moved declarations earlier

* resolved issues with changes to init functions

* fixed style and an error check

* attempting to add tests that might trigger changes

* added && die to cases expecting to fail

* resolved no die on expected failed command

* fixed accel to be incorrect value

* Adding an automated shrinking option

* Fixing build

* finalizing fixes

* fix?

* Removing added comment in cover.h

* Styling fixes

* Merging with fb dev

* removing megic number for default regression

* Requested revisions

* fixing support for fast cover

* fixing casting errors

* parenthesis fix

* fixing some build nits

* resolving travis ci syntax

* might resolve all compilation issues

* removed unused variable

* remodeling the selectDict function

* fixing bad memory access

* fixing error checks

* fixed erroring check in selectDict

* fixing mixed declarations

* modify mixed declaration

* fixing nits and adding test cases

* Adding requested changes + fixed bug for error checking

* switched double comparison from != to <

* fixed declaration typing

* refactoring COVER_best_finish() and changing shrinkDict

* removing the const's

* modifying ZDICT_optimizeTrainFromBuffer_cover functions

* fixing potential bad memcpy

* fixing the error function for dict size
This commit is contained in:
Tyler-Tran
2019-06-27 16:26:57 -07:00
committed by Nick Terrell
parent 9038579ab2
commit c55d2e7ba3
7 changed files with 259 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/fuzzer.c
+32
View File
@@ -1104,6 +1104,22 @@ static int basicUnitTests(U32 seed, double compressibility)
}
DISPLAYLEVEL(3, "OK, created dictionary of size %u \n", (unsigned)dictSize);
DISPLAYLEVEL(3, "test%3i : COVER dictBuilder with shrinkDict: ", testNb++);
{ U32 u; for (u=0; u<nbSamples; u++) samplesSizes[u] = sampleUnitSize; }
{ ZDICT_cover_params_t coverParams;
memset(&coverParams, 0, sizeof(coverParams));
coverParams.steps = 8;
coverParams.nbThreads = 4;
coverParams.shrinkDict = 1;
coverParams.shrinkDictMaxRegression = 1;
dictSize = ZDICT_optimizeTrainFromBuffer_cover(
dictBuffer, dictBufferCapacity,
CNBuffer, samplesSizes, nbSamples/8, /* less samples for faster tests */
&coverParams);
if (ZDICT_isError(dictSize)) goto _output_error;
}
DISPLAYLEVEL(3, "OK, created dictionary of size %u \n", (unsigned)dictSize);
DISPLAYLEVEL(3, "test%3i : Multithreaded FASTCOVER dictBuilder : ", testNb++);
{ U32 u; for (u=0; u<nbSamples; u++) samplesSizes[u] = sampleUnitSize; }
{ ZDICT_fastCover_params_t fastCoverParams;
@@ -1118,6 +1134,22 @@ static int basicUnitTests(U32 seed, double compressibility)
}
DISPLAYLEVEL(3, "OK, created dictionary of size %u \n", (unsigned)dictSize);
DISPLAYLEVEL(3, "test%3i : FASTCOVER dictBuilder with shrinkDict: ", testNb++);
{ U32 u; for (u=0; u<nbSamples; u++) samplesSizes[u] = sampleUnitSize; }
{ ZDICT_fastCover_params_t fastCoverParams;
memset(&fastCoverParams, 0, sizeof(fastCoverParams));
fastCoverParams.steps = 8;
fastCoverParams.nbThreads = 4;
fastCoverParams.shrinkDict = 1;
fastCoverParams.shrinkDictMaxRegression = 1;
dictSize = ZDICT_optimizeTrainFromBuffer_fastCover(
dictBuffer, dictBufferCapacity,
CNBuffer, samplesSizes, nbSamples,
&fastCoverParams);
if (ZDICT_isError(dictSize)) goto _output_error;
}
DISPLAYLEVEL(3, "OK, created dictionary of size %u \n", (unsigned)dictSize);
DISPLAYLEVEL(3, "test%3i : check dictID : ", testNb++);
dictID = ZDICT_getDictID(dictBuffer, dictSize);
if (dictID==0) goto _output_error;
tests/playTests.sh
+8
View File
@@ -499,6 +499,10 @@ $ZSTD --train-fastcover=k=56,d=8 && die "Create dictionary without input file"
println "- Create dictionary with short dictID"
$ZSTD --train-fastcover=k=46,d=8,f=15,split=80 "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpDict1
cmp tmpDict tmpDict1 && die "dictionaries should have different ID !"
println "- Create dictionaries with shrink-dict flag enabled"
$ZSTD --train-fastcover=steps=256,shrink "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpShrinkDict
$ZSTD --train-fastcover=steps=256,shrink=1 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpShrinkDict1
$ZSTD --train-fastcover=steps=256,shrink=5 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpShrinkDict2
println "- Create dictionary with size limit"
$ZSTD --train-fastcover=steps=8 "$TESTDIR"/*.c "$PRGDIR"/*.c -o tmpDict2 --maxdict=4K
println "- Compare size of dictionary from 90% training samples with 80% training samples"
@@ -989,6 +993,10 @@ $ZSTD --train-cover=k=56,d=8 && die "Create dictionary without input file (shoul
println "- Create second (different) dictionary"
$ZSTD --train-cover=k=56,d=8 "$TESTDIR"/*.c "$PRGDIR"/*.c "$PRGDIR"/*.h -o tmpDictC
$ZSTD -d tmp.zst -D tmpDictC -fo result && die "wrong dictionary not detected!"
println "- Create dictionary using shrink-dict flag"
$ZSTD --train-cover=steps=256,shrink "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpShrinkDict
$ZSTD --train-cover=steps=256,shrink=1 "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpShrinkDict1
$ZSTD --train-cover=steps=256,shrink=5 "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpShrinkDict2
println "- Create dictionary with short dictID"
$ZSTD --train-cover=k=46,d=8,split=80 "$TESTDIR"/*.c "$PRGDIR"/*.c --dictID=1 -o tmpDict1
cmp tmpDict tmpDict1 && die "dictionaries should have different ID !"