ShoveRand: a Model-Driven Framework to Easily Generate Random Numbers on GP-GPU

Abstract : Stochastic simulations are often sensitive to the randomness source that character-izes the statistical quality of their results. Consequently, we need highly reliable Random Number Generators (RNGs) to feed such applications. Recent developments try to shrink the computation time by using more and more General Purpose Graphics Processing Units (GP-GPUs) to speed-up stochastic simulations. Such devices bring new parallelization possibilities, but they also introduce new programming difficulties. Since RNGs are at the base of any stochastic simulation, they also need to be ported to GP-GPU. There is still a lack of well-designed implementations of quality-proven RNGs on GP-GPU platforms. In this paper, we introduce ShoveRand, a framework defining common rules to generate random numbers uniformly on GP-GPU. Our framework is designed to cope with any GPU-enabled development platform and to expose a straightforward interface to users. We also provide an existing RNG implementation with this framework to demonstrate its efficiency in both development and ease of use.
Type de document :
Communication dans un congrès
IEEE/ACM International Conference on High Performance Computing and Simulation, Jul 2011, Istanbul, Turkey. pp.41 - 48, 2011, 〈10.1109/HPCSim.2011.5999805〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01083180
Contributeur : Jonathan Passerat-Palmbach <>
Soumis le : lundi 22 décembre 2014 - 18:56:30
Dernière modification le : mercredi 7 février 2018 - 16:20:01
Document(s) archivé(s) le : vendredi 14 avril 2017 - 16:20:02

Fichiers

hpcs2011_frree.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Jonathan Passerat-Palmbach, Claude Mazel, Bruno Bachelet, David Hill. ShoveRand: a Model-Driven Framework to Easily Generate Random Numbers on GP-GPU. IEEE/ACM International Conference on High Performance Computing and Simulation, Jul 2011, Istanbul, Turkey. pp.41 - 48, 2011, 〈10.1109/HPCSim.2011.5999805〉. 〈hal-01083180〉

Partager

Métriques

Consultations de la notice

275

Téléchargements de fichiers

102