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.
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/hal-01083180
Contributor : Jonathan Passerat-Palmbach <>
Submitted on : Monday, December 22, 2014 - 6:56:30 PM
Last modification on : Thursday, April 4, 2019 - 10:18:07 AM
Long-term archiving on : Friday, April 14, 2017 - 4:20:02 PM

Files

hpcs2011_frree.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Jonathan Passerat-Palmbach, Claude Mazel, Bruno Bachelet, David R.C. 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, ⟨10.1109/HPCSim.2011.5999805⟩. ⟨hal-01083180⟩

Share

Metrics

Record views

318

Files downloads

187