Performance portable Vlasov code with C++ parallel algorithm - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Performance portable Vlasov code with C++ parallel algorithm

Résumé

This paper presents the performance portable implementation of a kinetic plasma simulation code with C++ parallel algorithm to run across multiple CPUs and GPUs. Relying on the language standard parallelism stdpar and proposed language standard multi-dimensional array support mdspan, we demonstrate that a performance portable implementation is possible without harming the readability and productivity. We obtain a good overall performance for a mini-application in the range of 20 % to the Kokkos version on Intel Icelake, NVIDIA V100, and A100 GPUs. Our conclusion is that stdpar can be a good candidate to develop a performance portable and productive code targeting the Exascale era platform, assuming this approach will be available on AMD and/or Intel GPUs in the future.
Fichier non déposé

Dates et versions

hal-03976662 , version 1 (07-02-2023)

Identifiants

Citer

Yuuichi Asahi, Thomas Padioleau, Guillaume Latu, Julien Bigot, Virginie Grandgirard, et al.. Performance portable Vlasov code with C++ parallel algorithm. 2022 IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC), Nov 2022, Dallas, France. pp.68-80, ⟨10.1109/P3HPC56579.2022.00012⟩. ⟨hal-03976662⟩
42 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More