Task-Based Parallelization of the Fast Multipole Method on NVIDIA GPUs and Multicore Processors - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

Task-Based Parallelization of the Fast Multipole Method on NVIDIA GPUs and Multicore Processors

Abstract

Fast Multipole Methods are a fundamental operation for the simulation of many physical problems. In this talk, we present a new approach for implementing these methods that achieves high performance across many different computer architectures. Our method consists of expressing the FMM algorithm as a task flow and employing a state-of-the-art runtime system, StarPU, to process the tasks on the different computing units.

Keywords

No file

Dates and versions

hal-01135258 , version 1 (25-03-2015)

Identifiers

  • HAL Id : hal-01135258 , version 1

Cite

Emmanuel Agullo, Bérenger Bramas, Olivier Coulaud, Eric Darve, Matthias Messner, et al.. Task-Based Parallelization of the Fast Multipole Method on NVIDIA GPUs and Multicore Processors. SIAM Conference on Computational Science and Engineering (SIAM CSE 2015), Mar 2015, Salt Lake City, United States. ⟨hal-01135258⟩
243 View
0 Download

Share

Gmail Facebook X LinkedIn More