Task-Based FMM for Multicore Architectures

Abstract : Fast Multipole Methods (FMM) are a fundamental operation for the simulation of many physical problems. The high performance design of such methods usually requires to carefully tune the algorithm for both the targeted physics and hardware. In this paper, we propose a new approach that achieves high performance across 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. We carefully design the task flow, the mathematical operators, their implementations as well as scheduling schemes. Potentials and forces on 200 million particles are computed in 42.3 seconds on a homogeneous 160 cores SGI Altix UV 100 and good scalability is shown.
Type de document :
Article dans une revue
SIAM Journal on Scientific Computing, Society for Industrial and Applied Mathematics, 2014, 36 (1), pp.66-93. <10.1137/130915662>
Liste complète des métadonnées


https://hal.inria.fr/hal-00911856
Contributeur : Olivier Coulaud <>
Soumis le : samedi 30 novembre 2013 - 14:59:13
Dernière modification le : jeudi 10 septembre 2015 - 01:08:45
Document(s) archivé(s) le : samedi 1 mars 2014 - 04:05:14

Fichier

sisc-cpu.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

Citation

Emmanuel Agullo, Bérenger Bramas, Olivier Coulaud, Eric Darve, Matthias Messner, et al.. Task-Based FMM for Multicore Architectures. SIAM Journal on Scientific Computing, Society for Industrial and Applied Mathematics, 2014, 36 (1), pp.66-93. <10.1137/130915662>. <hal-00911856>

Partager

Métriques

Consultations de
la notice

405

Téléchargements du document

221