This article summarizes our recent work and developments on SMPI, a flexible simulator of MPI applications. In this tool, we took a particular care to ensure our simulator could be used to produce fast and accurate predictions in a wide variety of situations. Although we did build SMPI on SimGrid whose speed and accuracy had already been assessed in other contexts, moving such techniques to a HPC workload required significant additional effort. Obviously, an accurate modeling of communications and network topology was one of the key to such achievements. Another less obvious key was the choice to combine in a single tool the possibility to do both offline and online simulation.
|Original language||English (US)|
|Number of pages||14|
|Journal||IEEE Transactions on Parallel and Distributed Systems|
|State||Published - Aug 1 2017|
Bibliographical noteKAUST Repository Item: Exported on 2020-10-01
Acknowledgements: The authors would like to thank the SimGrid team members and collaborators who contributed to SMPI: P. Bedaride, H. Casanova, P.-N. Clauss, F. Desprez, S. Genaud, A. Gupta, and B. Videau. This work is partially supported by the Hac Specis Inria Project Lab, the ANR SONGS (11- ANR-INFR-13), CNRS PICS N degree 5473, and European Mont-Blanc (EC grant 288777) projects. Experiments were carried out on a PRACE (EC grants RI-261557 and RI283493) prototype and the Grid’5000 experimental testbed, supported by a scientific interest group hosted by Inria and including CNRS, RENATER, and other Universities and organizations.