tinyMD: Mapping Molecular Dynamics Simulations to Heterogeneous Hardware using Partial Evaluation

Rafael Ravedutti Lucio Machado, Jonas Schmitt, Sebastian Eibl, Jan Eitzinger, Roland Leißa, Sebastian Hack, Arsène Pérard-Gayot, Richard Membarth, Harald Köstler

In: Journal of Computational Science (JOCS) 54 101425 Pages 1-11 Elsevier 7/2021.


This paper investigates the suitability of the AnyDSL partial evaluation framework to implement tinyMD: an efficient, scalable, and portable simulation of pairwise interactions among particles. We compare tinyMD with the miniMD proxy application that scales very well on parallel supercomputers. We discuss the differences between both implementations and contrast miniMD’s performance for single-node CPU and GPU targets, as well as its scalability on SuperMUC-NG and Piz Daint supercomputers. Additionally, we demonstrate tinyMD’s flexibility by coupling it with the waLBerla multi-physics framework. This allow us to execute tinyMD simulations using the load-balancing mechanism implemented in waLBerla.


German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz