1# libCEED: Benchmarks 2 3This directory contains benchmark problems for performance evaluation of libCEED 4backends. 5 6## Running the Benchmarks 7 8Example: 9```sh 10benchmark.sh -c /cpu/self -r petsc-bpsraw.sh -b bp1 -n 16 -p 16 11``` 12where the option `-c <specs-list>` specifies a list of libCEED specs to 13benchmark, `-b <bp-list>` specifies a list of CEED benchmark problems to run, 14`-n 16` is the total number of processors and `-p 16` is the number 15of processors per node. 16 17Multiple backends, benchmark problems, and processor configurations can be 18benchmarked with: 19```sh 20benchmark.sh -c "/cpu/self/ref/serial /cpu/self/ref/blocked" -r petsc-bpsraw.sh -b "bp1 bp3" -n "16 32 64" -p "16 32 64" 21``` 22 23The results from the benchmarks are written to files named `*-output.txt`. 24 25For a short help message, use the option `-h`. 26 27When running the tests `petsc-bpsraw.sh`, the following 28variables can be set on the command line: 29* `max_dofs_node=<number>`, e.g. `max_dofs_node=1000000` - this sets the upper 30 bound of the problem sizes, per compute node; the default value is 3*2^20. 31* `max_p=<number>`, e.g. `max_p=12` - this sets the highest degree for which the 32 tests will be run (the lowest degree is 1); the default value is 8. 33 34## Post-processing the results 35 36After generating the results, use the `postprocess-plot.py` script (which 37requires the python package matplotlib) or the `postprocess-table.py` script, 38e.g.: 39```sh 40python postprocess-plot.py petsc-bpsraw-bp1-*-output.txt 41``` 42The plot ranges and some other options can be adjusted by editing the values 43in the beginning of the script `postprocess-plot.py`. 44 45Note that the `postprocess-*.py` scripts can read multiple files at a time just 46by listing them on the command line and also read the standard input if no files 47were specified on the command line. 48