A Space and Bandwidth Efficient Multicore Algorithm for the Particle-in-Cell Method

Yann Barsamian 1, 2 Arthur Charguéraud 1, 2 Alain Ketterlin 2, 1
1 CAMUS - Compilation pour les Architectures MUlti-coeurS
Inria Nancy - Grand Est, ICube - Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie
Abstract : The Particle-in-Cell (PIC) method allows solving partial differential equation through simulations, with important applications in plasma physics. To simulate thousands of billions of particles on clusters of multicore machines, prior work has proposed hybrid algorithms that combine domain decomposition and particle decomposition with carefully optimized algorithms for handling particles processed on each multicore socket. Regarding the multicore processing, existing algorithms either suffer from suboptimal execution time, due to sorting operations or use of atomic instructions, or suffer from suboptimal space usage. In this paper, we propose a novel parallel algorithm for two-dimensional PIC simulations on multicore hardware that features asymptotically-optimal memory consumption, and does not perform unnecessary accesses to the main memory. In practice, our algorithm reaches 65% of the maximum bandwidth, and shows excellent scalability on the classical Landau damping and two-stream instability test cases.
Document type :
Conference papers
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.inria.fr/hal-01649172
Contributor : Arthur Charguéraud <>
Submitted on : Monday, November 27, 2017 - 12:07:01 PM
Last modification on : Monday, November 26, 2018 - 1:28:02 PM

File

PIC-chunks.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01649172, version 1

Citation

Yann Barsamian, Arthur Charguéraud, Alain Ketterlin. A Space and Bandwidth Efficient Multicore Algorithm for the Particle-in-Cell Method. PPAM 2017 - 12th International Conference on Parallel Processing and Applied Mathematics, Sep 2017, Lublin, Poland. pp.1-12. ⟨hal-01649172⟩

Share

Metrics

Record views

195

Files downloads

172