Random Numbers for Parallel Computers: Requirements and Methods, with emphasis on GPUs

Pierre l'Ecuyer; David Munger; Boris Oreshkin; Richard Simard

doi:10.1016/j.matcom.2016.05.005

Journal articles

Random Numbers for Parallel Computers: Requirements and Methods, with emphasis on GPUs

Pierre l'Ecuyer ^{1, 2, *} David Munger ¹ Boris Oreshkin ¹ Richard Simard ¹

* Corresponding author

1 DIRO - Département d'Informatique et de Recherche Opérationnelle [Montreal]

2 DIONYSOS - Dependability Interoperability and perfOrmance aNalYsiS Of networkS

Inria Rennes – Bretagne Atlantique , IRISA-D2 - RÉSEAUX, TÉLÉCOMMUNICATION ET SERVICES

Abstract : We examine the requirements and the available methods and software to provide (or imitate) uniform random numbers in parallel computing environments. In this context, for the great majority of applications, independent streams of random numbers are required, each being computed on a single processing element at a time. Sometimes, thousands or even millions of such streams are needed. We explain how they can be produced and managed. We devote particular attention to multiple streams for GPU devices.

Keywords : Monte Carlo Simulation Parallel computing Multiple streams Random number generators

Document type :

Journal articles

Domain :

Computer Science [cs] / Operations Research [cs.RO]

Complete list of metadata

https://hal.inria.fr/hal-01399537
Contributor : Bruno Tuffin <>
Submitted on : Saturday, November 19, 2016 - 1:37:07 PM
Last modification on : Friday, February 26, 2021 - 3:30:36 PM

Random Numbers for Parallel Computers: Requirements and Methods, with emphasis on GPUs

Links full text

Identifiers

Collections

Citation

Export

Metrics

344

Contact Legal Notice Personal Data

Random Numbers for Parallel Computers: Requirements and Methods, with emphasis on GPUs

Links full text

Identifiers

Collections

Citation

Export

Share

Metrics

344

Contact Legal Notice Personal Data