summaryrefslogtreecommitdiffstats
path: root/programs/bench.c
Commit message (Collapse)AuthorAgeFilesLines
* added test able to catch bug #1167Yann Collet2022-09-151-22/+36
| | | | also : errors during benchmark mode return an error code.
* fix benchmark more using DictionaryYann Collet2022-09-151-0/+2
| | | | | | | benchmark dictionary mode, implemented in #808, is incorrect. It would desynchronize compression and decompression as soon as 2+ files are dictionary compressed. Also : slightly improved traces system, to also include __LINE__ number
* fix: various typosDominique Pelle2022-07-311-1/+1
|
* fixed minor pedantic warningYann Collet2022-07-291-2/+4
|
* can select validation of CRC during benchmarkYann Collet2022-07-291-2/+11
| | | | | on command line, using existing long command --no-frame-crc. Note : it's effectively more than that, since _all_ checksums are disabled.
* implement decoder-only benchmark modeYann Collet2022-07-291-33/+112
| | | | requires an LZ4 Frame as input
* minor refactorYann Collet2022-07-291-122/+123
| | | | to prepare bench.c for multiple decoding functions.
* updated documentation of bench unitYann Collet2022-07-291-2/+2
|
* minor : fix conversion warningsYann Collet2022-07-291-25/+25
|
* updated license & header datesYann Collet2020-11-251-1/+1
|
* Make benchmark compatible with dictionary compressionReto Koradi2019-11-061-43/+233
| | | | | | | | | | | | | | | Support the -D command line option for running benchmarks. The benchmark code was slightly restructured to factor out the calls that need to be different for each benchmark scenario. Since there are now 4 scenarios (all combinations of fast/HC and with/without dictionary), the logic was getting somewhat convoluted otherwise. This was done by extending the compressionParameters struct that previously contained just a single function pointer. It now contains 4 function pointers for init/reset/compress/cleanup, with the related state. The functions get a pointer to the structure as their first argument (inspired by C++), so that they can access the state values in the struct.
* fix several minor static analyzer warningsYann Collet2019-04-181-6/+6
|
* fixed #560Yann Collet2018-09-051-1/+1
| | | | | | | it was a fairly complex scenario, involving source files > 64K and some extraordinary conditions related to specific layout of ranges of zeroes. and only on level 9.
* Fixed bugs about incorrect acceleration calculation and benchmarking ↵Jennifer Liu2018-06-271-1/+4
| | | | negative compresion level
* Fixed code based on comments from pull requestJennifer Liu2018-06-271-0/+2
|
* delete commented out code in bench.cJennifer Liu2018-06-261-2/+0
|
* Added --fast command to cliJennifer Liu2018-06-261-1/+1
|
* bench: introduced hidden command -SYann Collet2018-03-201-7/+27
| | | | to benchmark multiple files with separate results
* use TIMELOOP_NANOSEC,Yann Collet2018-02-201-2/+2
| | | | as suggested by @terrelln
* fixed minor conversion warningYann Collet2018-02-201-2/+2
|
* ensure bench speed measurement is more accurate for small inputsYann Collet2018-02-201-23/+34
| | | | | | | | | | | | Previous method would produce too many time() invocations, becoming a significant fraction of workload measured. The new strategy is to use time() only once per batch, and dynamically resize batch size so that each round lasts approximately 1 second. This only matters for small inputs. Measurement for large files (such as silesia.tar) are much less impacted (though decoding speed is so fast that even medium-size files will notice an improvement).
* update bench.c to use less time invocationsYann Collet2018-02-201-9/+9
| | | | translating into more accurate speed measurements for small sources
* [bench] Use higher resolution timer on POSIXNick Terrell2017-10-171-13/+11
| | | | | | | The timer used was only accurate up to 0.01 seconds. This timer is accurate up to 1 ns. It is a monotonic timer that measures the real time difference, not on CPU time. Copied the benchmark code from https://github.com/facebook/zstd/commit/6ab4d5e9041aba962a810ffee191f95897c6208e
* fixed a bunch of -Wcomma warningsYann Collet2017-09-101-1/+4
| | | | reported by @rvandermeulen (#398)
* bench : made decompression speed evaluation same time as compressionYann Collet2017-09-071-3/+3
| | | | minor : slightly modified an example do avoid disabling a gcc warning through #pragma
* bench.c: respect LZ4_MAX_INPUT_SIZE limitPrzemyslaw Skibinski2017-03-101-2/+7
|
* upgraded util.hPrzemyslaw Skibinski2017-02-151-1/+1
|
* Use logical or instead of bitwise orChocobo12017-01-121-1/+1
|
* Merge pull request #292 from inikep/devYann Collet2016-12-221-2/+11
|\ | | | | improved POSIX
| * test Large File support for Mac OS-X in 32-bits modePrzemyslaw Skibinski2016-12-211-0/+8
| |
| * executables use platform.hPrzemyslaw Skibinski2016-12-201-2/+3
| |
| * Merge remote-tracking branch 'refs/remotes/lz4/dev' into devPrzemyslaw Skibinski2016-11-161-0/+1
| |
* | updated a few macros namesYann Collet2016-12-221-3/+3
| |
* | fixed minor coverity warningsYann Collet2016-11-151-0/+1
|/
* custom block sizePrzemyslaw Skibinski2016-11-101-1/+5
|
* fixed some static analyzer warningYann Collet2016-11-101-1/+1
|
* fixed synthetic benchmark modeYann Collet2016-11-091-3/+2
| | | | slightly optimized test mode
* fixed Travis testsPrzemyslaw Skibinski2016-11-041-9/+15
|
* updated lz4cli.cPrzemyslaw Skibinski2016-11-041-2/+3
|
* bench.c based on zstdPrzemyslaw Skibinski2016-11-041-312/+400
|
* updated links to LZ4 repositoryPrzemyslaw Skibinski2016-11-031-1/+1
|
* lz4cli version number from lz4.hYann Collet2016-09-031-3/+3
|
* added <string.h> for strlen()inikep2016-09-021-0/+2
|
* -b# and -e# options from zstdinikep2016-09-021-13/+32
|
* fix mingw64 compilation warningsinikep2016-09-021-0/+4
|
* minor refactoring changesYann Collet2016-08-101-3/+0
|
* changed : default benchmark LZ4_decompress_safe()Yann Collet2016-06-291-4/+4
|
* fixed display result issue when benchmarking multiple filesYann Collet2016-06-291-1/+3
|
* minor code refactoringYann Collet2016-06-291-15/+10
|
* Reduced bench dependency to standard C <time.h>Yann Collet2016-06-291-68/+39
| | | | | Faster tests More accurate results on systems with high resolution clocks
generated by cgit v0.12 at 2024-07-03 11:43:50 (GMT)