Load Balancing for Particle-in-Cell Plasma Simulation on Multicore Systems
- 1.1k Downloads
Particle-in-cell plasma simulation is an important area of computational physics. The particle-in-cell method naturally allows parallel processing on distributed and shared memory. In this paper we address the problem of load balancing on multicore systems. While being well-studied for many traditional applications of the method, it is a relevant problem for the emerging area of particle-in-cell simulations with account for effects of quantum electrodynamics. Such simulations typically produce highly non-uniform, and sometimes volatile, particle distributions, which could require custom load balancing schemes. In this paper we present a computational evaluation of several standard and custom load balancing schemes for the particle-in-cell method on a high-end system with 96 cores on shared memory. We use a test problem with static non-uniform particle distribution and a real problem with account for quantum electrodynamics effects, which produce dynamically changing highly non-uniform distributions of particles and workload. For these problems the custom schemes result in increase of scaling efficiency by up to 20% compared to the standard OpenMP schemes.
KeywordsParallel processing Load balancing OpenMP Particle-in-cell Plasma simulation Quantum electrodynamics
The authors (A.L., S.B., A.B., E.E., A.G.) acknowledge the support from the Russian Science Foundation project No. 16-12-10486. We are grateful to Intel Corporation for access to the system used for performing computational experiments presented in this paper. The authors are also grateful to A. Bobyr, S. Egorov, I. Lopatin, and Z. Matveev from Intel Corporation for technical consultations.
- 2.Vay, J.-L., Bruhwiler, D.L., Geddes, C.G.R., Fawley, W.M., Martins, S.F., Cary, J.R., Cormier-Michel, E., Cowan, B., Fonseca, R.A., Furman, M.A., Lu, W., Mori, W.B., Silva, L.O.: Simulating relativistic beam and plasma systems using an optimal boosted frame. J. Phys: Conf. Ser. 180(1), 012006 (2009)Google Scholar
- 8.Nakashima, H., Miyake, Y., Usui, H., Omura, Y.: OhHelp: a scalable domain-decomposing dynamic load balancing for particle-in-cell simulations. In: 23rd International Conference on Supercomputing, pp. 90–99. ACM, New York (2009)Google Scholar
- 10.Surmin, I., Bashinov, A., Bastrakov, S., Efimenko, E., Gonoskov, A., Meyerov, I.: Dynamic load balancing based on rectilinear partitioning in particle-in-cell plasma simulation. In: Malyshkin, V. (ed.) PaCT 2015. LNCS, vol. 9251, pp. 107–119. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-21909-7_12 CrossRefGoogle Scholar
- 20.Gonoskov, A., Bashinov, A., Bastrakov, S., Efimenko, E., Ilderton, A., Kim, A., Marklund, M., Meyerov, I., Muraviev, A., Sergeev, A.: Ultra-bright GeV photon source via controlled electromagnetic cascades in laser-dipole waves. Phys. Rev. X. 7, 041003 (2017)Google Scholar