[Back]

F. Lübbe:
"Micro-benchmarking MPI Neighborhood Collective Operations";
Talk: Euro-Par 2017 23rd International European Conference on Parallel and Distributed Computing, Santiago de Compostela, Spain; 2017-08-28 - 2017-09-01; in: "Euro-Par 2017: Parallel Processing, 23rd International Conference on Parallel and Distributed Computing, Proceedings", F. Rivera, T. Pena, J. Cabaleiro (ed.); Springer, LNCS 10417 (2017), ISBN: 978-3-319-64202-4; 65 - 78.

In this article, performance expectations for MPI neighborhood collective operations are formulated as self-consistent performance guidelines. A microbenchmark and an experimental methodology are presented to assess these guidelines. Measurement results from a large, InfiniBand-based cluster, the Vienna Scientific Cluster (VSC), as well as from a small commodity cluster computer are shown and discussed to illustrate the methodology and to gain first insights into the performance of current MPI implementations. Results show that the examined libraries seem to be sensitive to the order in which topological neighbors are specified, and that in some cases Cartesian topologies can be outperformed by simulating them with distributed graph topologies.

MPI · Process topology · Neighborhood collectives · Performance guidelines · Benchmarking

http://dx.doi.org/10.1007/978-3-319-64203-1_5

Project Head Jesper Larsson Träff:
MPI