English

Multi-GPU Hybrid Particle-in-Cell Monte Carlo Simulations for Exascale Computing Systems

Plasma Physics 2026-04-17 v2 Distributed, Parallel, and Cluster Computing Performance

Abstract

Particle-in-Cell (PIC) Monte Carlo (MC) simulations are central to plasma physics but face increasing challenges on heterogeneous HPC systems due to excessive data movement, synchronization overheads, and inefficient utilization of multiple accelerators. In this work, we present a portable, multi-GPU hybrid MPI+OpenMP implementation of BIT1 that enables scalable execution on both Nvidia and AMD accelerators through OpenMP target tasks with explicit dependencies to overlap computation and communication across devices. Portability is achieved through persistent device-resident memory, an optimized contiguous one-dimensional data layout, and a transition from unified to pinned host memory to improve large data-transfer efficiency, together with GPU Direct Memory Access (DMA) and runtime interoperability for direct device-pointer access. Standardized and scalable I/O is provided using openPMD and ADIOS2, supporting high-performance file I/O, in-memory data streaming, and in-situ analysis and visualization. Performance results on pre-exascale and exascale systems, including Frontier (OLCF-5) for up to 16,000 GPUs, demonstrate significant improvements in run time, scalability, and resource utilization for large-scale PIC MC simulations.

Keywords

Cite

@article{arxiv.2603.24508,
  title  = {Multi-GPU Hybrid Particle-in-Cell Monte Carlo Simulations for Exascale Computing Systems},
  author = {Jeremy J. Williams and Jordy Trilaksono and Stefan Costea and Yi Ju and Luca Pennati and Jonah Ekelund and David Tskhakaya and Leon Kos and Ales Podolnik and Jakub Hromadka and Allen D. Malony and Sameer Shende and Tilman Dannert and Frank Jenko and Erwin Laure and Stefano Markidis},
  journal= {arXiv preprint arXiv:2603.24508},
  year   = {2026}
}

Comments

Accepted by ICCS 2026 (The 26th International Conference on Computational Science), prepared in English, formatted according to the Springer LNCS templates and consists of 15 pages, which includes the main text, references, and figures

R2 v1 2026-07-01T11:37:37.896Z