| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | make the whole project more python idiomatic | Florian Fischer | 2020-06-02 | 1 | -126/+0 |
| | | | | | | | | | | * rename src directory to allocbench * make global variable names UPPERCASE * format a lot of code using yapf * use lowercase ld_preload and ld_library_path as Allocator members * name expected Errors 'err' and don't raise a new Exception * disable some pylint messages | ||||
| * | fix syntax after plot changes | Florian Fischer | 2020-04-07 | 1 | -2/+1 |
| | | |||||
| * | unify plotting code | Florian Fischer | 2020-04-07 | 1 | -27/+21 |
| | | | | | | Now there is only a single plot function which takes a plot type as well as some plot and figure options. | ||||
| * | improve matplotlib code | Florian Fischer | 2020-03-09 | 1 | -4/+4 |
| | | | | | | | add new helper functions to get all y_values for a plot use seperate figures for each plot s/filepostfix/file_postfix/ to be consistent | ||||
| * | add falsesharing pgfplot | Florian Fischer | 2020-02-20 | 1 | -9/+24 |
| | | |||||
| * | cleanup plot code | Florian Fischer | 2020-02-11 | 1 | -6/+6 |
| | | | | | | | | * use str.format instead of eval for plot labels * use meaningful variable names * add license header * add some doc strings | ||||
| * | move plotting code from src.benchmark to src.plots | Florian Fischer | 2020-02-11 | 1 | -18/+21 |
| | | |||||
| * | fmt benchmark definitions with yapf | Florian Fischer | 2019-12-11 | 1 | -26/+34 |
| | | |||||
| * | calculate speedup and use it for multiple summaries | Florian Fischer | 2019-11-28 | 1 | -23/+23 |
| | | |||||
| * | add and use write_tex_table function | Florian Fischer | 2019-10-30 | 1 | -1/+8 |
| | | |||||
| * | introduce a global summary file extension | Florian Fischer | 2019-10-30 | 1 | -1/+3 |
| | | |||||
| * | increase workload size for bigger max speedup | Florian Fischer | 2019-10-16 | 1 | -2/+4 |
| | | | | | | | | | | | | with the current workload size of 100K allocations the parallel part (worker) takes on my development laptop 96% of the single threaded execution time resulting in a maximal speedup of 25. (Amdahl: 1/(1-0.96) ~= 25) Increasing the the workload to 1M allocations ups the parallel portion to ~99% which gives us a max speedup of ~295 enough for all our test machines. With the new workload the single threaded execution time is ~100s on my laptop and ~30s on one of the test servers which is tolerable in my opinion. | ||||
| * | require a name in Benchmark.__init__ | Florian Fischer | 2019-08-29 | 1 | -2/+2 |
| | | |||||
| * | add license header comments to benchmark definitions | Florian Fischer | 2019-08-28 | 1 | -0/+17 |
| | | |||||
| * | remove verbosity argument from hooks | Florian Fischer | 2019-08-27 | 1 | -1/+2 |
| | | |||||
| * | improve benchmark code quality using pylint | Florian Fischer | 2019-08-27 | 1 | -16/+20 |
| | | | | | The description Benchmark member is replaced with class docstrings | ||||
| * | apply some flake8 hints | Florian Fischer | 2019-06-19 | 1 | -1/+1 |
| | | |||||
| * | fix ylabel for llc miss plot | Florian Fischer | 2019-05-14 | 1 | -1/+1 |
| | | |||||
| * | move benchmark definitions into src/benchmarks | Florian Fischer | 2019-03-25 | 1 | -0/+74 |
| bench now loads all *.py files from src/benchmarks as benchmarks | |||||
 |
index : allocbench | |
| benchmark tool for POSIX memory allocators |
| aboutsummaryrefslogtreecommitdiff |