Merge fastCover into DictBuilder (#1274)

* Minor fix

* Run non-optimize FASTCOVER 5 times in benchmark

* Merge fastCover into dictBuilder

* Fix mixed declaration issue

* Add fastcover to symbol.c

* Add fastCover.c and cover.h to build

* Change fastCover.c to fastcover.c

* Update benchmark to run FASTCOVER in dictBuilder

* Undo spliting fastcover_param into cover_param and f

* Remove convert param functions

* Assign f to parameter

* Add zdict.h to Makefile in lib

* Add cover.h to BUCK

* Cast 1 to U64 before shifting

* Remove trimming of zero freq head and tail in selectSegment and rebenchmark

* Remove f as a separate parameter of tryParam

* Read 8 bytes when d is 6

* Add trimming off zero frequency head and tail

* Use best functions from COVER and remove trimming part(which leads to worse compression ratio after previous bugs were fixed)

* Add finalize= argument to FASTCOVER to specify percentage of training samples passed to ZDICT_finalizeDictionary

* Change nbDmer to always read 8 bytes even when d=6

* Add skip=# argument to allow skipping dmers in computeFrequency in FASTCOVER

* Update comments and benchmarking result

* Change default method of ZDICT_trainFromBuffer to ZDICT_optimizeTrainFromBuffer_fastCover

* Add dictType enum and fix bug about passing zParam when converting to coverParam

* Combine finalize and skip into a single parameter

* Update acceleration parameters and benchmark on 3 sample sets

* Change default splitPoint of FASTCOVER to 0.75 and benchmark first 3 sample sets

* Initialize variables outside of for loop in benchmark.c

* Update benchmark result for hg-manifest

* Remove cover.h from install-includes

* Add explanation of f

* Set default compression level for trainFromBuffer to 3

* Add assertion of fastCoverParams in DiB_trainFromFiles

* Add checkTotalCompressedSize function + some minor fixes

* Add test for multithreading fastCovr

* Initialize segmentFreqs in every FASTCOVER_selectSegment and move mutex_unnlock to end of COVER_best_finish

* Free segmentFreqs

* Initialize segmentFreqs before calling FASTCOVER_buildDictionary instead of in FASTCOVER_selectSegment

* Add FASTCOVER_MEMMULT

* Minor fix

* Update benchmarking result
This commit is contained in:
Jennifer Liu
2018-08-23 12:06:20 -07:00
committed by Nick Terrell
parent 1af27a7ed7
commit 9d6ed9def3
26 changed files with 1999 additions and 246 deletions
+8
View File
@@ -336,6 +336,10 @@
RelativePath="..\..\..\lib\dictBuilder\cover.c"
>
</File>
<File
RelativePath="..\..\..\lib\dictBuilder\fastcover.c"
>
</File>
<File
RelativePath="..\..\..\lib\dictBuilder\divsufsort.c"
>
@@ -482,6 +486,10 @@
RelativePath="..\..\..\lib\dictBuilder\zdict.h"
>
</File>
<File
RelativePath="..\..\..\lib\dictBuilder\cover.h"
>
</File>
<File
RelativePath="..\..\..\lib\dictBuilder\zdict_static.h"
>
+8
View File
@@ -348,6 +348,10 @@
RelativePath="..\..\..\lib\dictBuilder\cover.c"
>
</File>
<File
RelativePath="..\..\..\lib\dictBuilder\fastcover.c"
>
</File>
<File
RelativePath="..\..\..\lib\dictBuilder\divsufsort.c"
>
@@ -522,6 +526,10 @@
RelativePath="..\..\..\lib\dictBuilder\zdict.h"
>
</File>
<File
RelativePath="..\..\..\lib\dictBuilder\cover.h"
>
</File>
<File
RelativePath="..\..\..\lib\dictBuilder\zdict_static.h"
>
+8
View File
@@ -332,6 +332,10 @@
RelativePath="..\..\..\lib\dictBuilder\cover.c"
>
</File>
<File
RelativePath="..\..\..\lib\dictBuilder\fastcover.c"
>
</File>
<File
RelativePath="..\..\..\lib\dictBuilder\divsufsort.c"
>
@@ -502,6 +506,10 @@
RelativePath="..\..\..\lib\dictBuilder\zdict.h"
>
</File>
<File
RelativePath="..\..\..\lib\dictBuilder\cover.h"
>
</File>
<File
RelativePath="..\..\..\lib\dictBuilder\zdict_static.h"
>
+2
View File
@@ -176,6 +176,7 @@
<ClCompile Include="..\..\..\lib\decompress\huf_decompress.c" />
<ClCompile Include="..\..\..\lib\decompress\zstd_decompress.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\cover.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\fastcover.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\divsufsort.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\zdict.c" />
<ClCompile Include="..\..\..\programs\datagen.c" />
@@ -199,6 +200,7 @@
<ClInclude Include="..\..\..\lib\compress\zstdmt_compress.h" />
<ClInclude Include="..\..\..\lib\dictBuilder\divsufsort.h" />
<ClInclude Include="..\..\..\lib\dictBuilder\zdict.h" />
<ClInclude Include="..\..\..\lib\dictBuilder\cover.h" />
<ClInclude Include="..\..\..\lib\legacy\zstd_legacy.h" />
<ClInclude Include="..\..\..\programs\datagen.h" />
<ClInclude Include="..\..\..\programs\util.h" />
@@ -43,6 +43,7 @@
<ClCompile Include="..\..\..\lib\deprecated\zbuff_compress.c" />
<ClCompile Include="..\..\..\lib\deprecated\zbuff_decompress.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\cover.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\fastcover.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\divsufsort.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\zdict.c" />
<ClCompile Include="..\..\..\lib\legacy\zstd_v01.c" />
+1
View File
@@ -43,6 +43,7 @@
<ClCompile Include="..\..\..\lib\deprecated\zbuff_compress.c" />
<ClCompile Include="..\..\..\lib\deprecated\zbuff_decompress.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\cover.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\fastcover.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\divsufsort.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\zdict.c" />
<ClCompile Include="..\..\..\lib\legacy\zstd_v01.c" />
+2
View File
@@ -40,6 +40,7 @@
<ClCompile Include="..\..\..\lib\decompress\huf_decompress.c" />
<ClCompile Include="..\..\..\lib\decompress\zstd_decompress.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\cover.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\fastcover.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\divsufsort.c" />
<ClCompile Include="..\..\..\lib\dictBuilder\zdict.c" />
<ClCompile Include="..\..\..\lib\legacy\zstd_v01.c" />
@@ -61,6 +62,7 @@
<ClInclude Include="..\..\..\lib\common\xxhash.h" />
<ClInclude Include="..\..\..\lib\compress\zstdmt_compress.h" />
<ClInclude Include="..\..\..\lib\dictBuilder\zdict.h" />
<ClInclude Include="..\..\..\lib\dictBuilder\cover.h" />
<ClInclude Include="..\..\..\lib\dictBuilder\divsufsort.h" />
<ClInclude Include="..\..\..\lib\common\fse.h" />
<ClInclude Include="..\..\..\lib\common\huf.h" />
+3
View File
@@ -47,6 +47,7 @@ SET(Sources
${LIBRARY_DIR}/decompress/huf_decompress.c
${LIBRARY_DIR}/decompress/zstd_decompress.c
${LIBRARY_DIR}/dictBuilder/cover.c
${LIBRARY_DIR}/dictBuilder/fastcover.c
${LIBRARY_DIR}/dictBuilder/divsufsort.c
${LIBRARY_DIR}/dictBuilder/zdict.c
${LIBRARY_DIR}/deprecated/zbuff_common.c
@@ -74,6 +75,7 @@ SET(Headers
${LIBRARY_DIR}/compress/zstd_ldm.h
${LIBRARY_DIR}/compress/zstdmt_compress.h
${LIBRARY_DIR}/dictBuilder/zdict.h
${LIBRARY_DIR}/dictBuilder/cover.h
${LIBRARY_DIR}/deprecated/zbuff.h)
IF (ZSTD_LEGACY_SUPPORT)
@@ -178,6 +180,7 @@ INSTALL(FILES
${LIBRARY_DIR}/zstd.h
${LIBRARY_DIR}/deprecated/zbuff.h
${LIBRARY_DIR}/dictBuilder/zdict.h
${LIBRARY_DIR}/dictBuilder/cover.h
${LIBRARY_DIR}/common/zstd_errors.h
DESTINATION "include")