Scalable communication for high-order stencil computations using CUDA-aware MPI

Johannes Pekkilä, Miikka S. Väisälä, Maarit J. Käpylä, Matthias Rheinhardt, Oskar Lappi
Department of Computer Science, Aalto University, Konemiehentie 2, 02150 Espoo, Finland
arXiv:2103.01597 [cs.DC], (2 Mar 2021)


   title={Scalable communication for high-order stencil computations using CUDA-aware MPI},

   author={Johannes Pekkilä and Miikka S. Väisälä and Maarit J. Käpylä and Matthias Rheinhardt and Oskar Lappi},






Download Download (PDF)   View View   Source Source   



Modern compute nodes in high-performance computing provide a tremendous level of parallelism and processing power. However, as arithmetic performance has been observed to increase at a faster rate relative to memory and network bandwidths, optimizing data movement has become critical for achieving strong scaling in many communication-heavy applications. This performance gap has been further accentuated with the introduction of graphics processing units, which can provide by multiple factors higher throughput in data-parallel tasks than central processing units. In this work, we explore the computational aspects of iterative stencil loops and implement a generic communication scheme using CUDA-aware MPI, which we use to accelerate magnetohydrodynamics simulations based on high-order finite differences and third-order Runge-Kutta integration. We put particular focus on improving intra-node locality of workloads. In comparison to a theoretical performance model, our implementation exhibits strong scaling from one to 64 devices at 50%–87% efficiency in sixth-order stencil computations when the problem domain consists of 256^3–1024^3 cells.
No votes yet.
Please wait...

Recent source codes

* * *

* * *

HGPU group © 2010-2023 hgpu.org

All rights belong to the respective authors

Contact us: