Performance results of LeanMD on the Joliot-Curie supercomputer using different load balancing algorithms

<p>This dataset contains the raw output files generated from the execution of LeanMD on the Joliot-Curie supercomputer (20 SKL Irene nodes), the scripts used to generate them, and the scripts used to parse these results for statistical analysis and plotting.</p> <p><strong>Software information</strong>:</p> <ul> <li>OS:&nbsp;Red Hat Enterprise Linux 7.6</li> <li>OpenMPI: version 2.0.4</li> <li>Compilers:&nbsp;C/C++ Intel 17.0.6.256</li> <li>Charm++ version:&nbsp;v6.9.0-rc3, build&nbsp;mpi-linux-x86_64&nbsp;--with-production</li> <li>LeanMD source:&nbsp;<a href="https://charm.cs.illinois.edu/gerrit/gitweb?p=benchmarks/leanmd.git">https://charm.cs.illinois.edu/gerrit/gitweb?p=benchmarks/leanmd.git</a></li> <li>Additional load balancers source:&nbsp;<a href="https://github.com/viniciusmctf/packing-schemes/tree/packs_2019-v1">https://github.com/viniciusmctf/packing-schemes/tree/packs_2019-v1</a></li> <li>Charm++, LeanMD, and the load balancers were&nbsp;compiled with -O3</li> </ul> <p><strong>File information</strong>:</p> <p>The raw result files are organized in four directories (oct18, oct23, oct24, and oct24_2).<br> Each directory contains the results of one batched execution in the supercomputer.<br> Each batch is composed of 10 repetitions of a set of experiments.<br> Each set of experiments includes different load balancing algorithms and different problem sizes.<br> Each set is randomly ordered to avoid interference coming from a specific order of execution.<br> Each raw file contains the appended output of the application and its load balancer for all 10 repetitions.<br> The name of the files indicate the load balancer and size of the problem.<br> For instance, `PackStealLB.240` means that the application was run with PackStealLB and the problem size parameter is 240.</p> <p><strong>Problem sizes</strong>:</p> <ul> <li>80: 80&times;11&times;5 cells of dimensions 15&times;15&times;30</li> <li>120: 120&times;11&times;5 cells of dimensions 15&times;15&times;30</li> <li>160: 160&times;11&times;5 cells of dimensions 15&times;15&times;30</li> <li>240: 240&times;11&times;5 cells of dimensions 15&times;15&times;30</li> <li>320: 320&times;11&times;5 cells of dimensions 15&times;15&times;30</li> </ul> <p>Each execution of LeanMD ran for 301 iterations with load balancing calls at iterations 40, 140, and 240.</p> <p><strong>Raw output files</strong>:</p> <p>Each raw output file starts with a Charm++ header providing information on the execution.</p> <p>For each step of the application, its execution time in ms is provided.</p> <p>Load balancing calls usually provide information about their start time, end time, and duration. Depending on the load balancer, more information is provided.</p> <p>Each raw file contains ten executions of the application with a given load balancer and input size.</p> <p><strong>Generating plots</strong>:</p> <p>The analysis of the results can be done by running the Jupyter notebook named &quot;Analysis of load balancing results.ipynb&quot;</p>