On the Utility of Graphics Cards to Perform Massively Parallel Simulation of Advanced Monte Carlo Methods
Top Cited Papers
- 1 January 2010
- journal article
- research article
- Published by Informa UK Limited in Journal of Computational and Graphical Statistics
- Vol. 19 (4), 769-789
- https://doi.org/10.1198/jcgs.2010.10039
Abstract
We present a case study on the utility of graphics cards to perform massively parallel simulation of advanced Monte Carlo methods. Graphics cards, containing multiple Graphics Processing Units (GPUs), are self-contained parallel computational devices that can be housed in conventional desktop and laptop computers and can be thought of as prototypes of the next generation of many-core processors. For certain classes of population-based Monte Carlo algorithms they offer massively parallel simulation, with the added advantage over conventional distributed multicore processors that they are cheap, easily accessible, easy to maintain, easy to code, dedicated local devices with low power consumption. On a canonical set of stochastic simulation examples including population-based Markov chain Monte Carlo methods and Sequential Monte Carlo methods, we find speedups from 35- to 500-fold over conventional single-threaded computer code. Our findings suggest that GPUs have the potential to facilitate the growth of statistical modeling into complex data-rich domains through the availability of cheap and accessible many-core computation. We believe the speedup we observe should motivate wider use of parallelizable simulation methods and greater methodological attention to their design. This article has supplementary material online.Keywords
Other Versions
This publication has 19 references indexed in Scilit:
- Particle Markov Chain Monte Carlo MethodsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2010
- Many-core algorithms for statistical phylogeneticsBioinformatics, 2009
- Accelerating molecular dynamic simulation on graphics processing unitsJournal of Computational Chemistry, 2009
- Accelerating molecular modeling applications with graphics processorsJournal of Computational Chemistry, 2007
- Sequential Monte Carlo SamplersJournal of the Royal Statistical Society Series B: Statistical Methodology, 2006
- Markov Chain Monte Carlo Methods and the Label Switching Problem in Bayesian Mixture ModelingStatistical Science, 2005
- Parallel algorithms for Markov chain Monte Carlo methods in latent spatial Gaussian modelsStatistics and Computing, 2004
- Computational and Inferential Difficulties with Mixture Posterior DistributionsJournal of the American Statistical Association, 2000
- Blind Deconvolution via Sequential ImputationsJournal of the American Statistical Association, 1995
- Markov Chains for Exploring Posterior DistributionsThe Annals of Statistics, 1994