portableParallelSeeds-package: Creates, saves, reloads, and selects among streams of random...

In wjakethompson/portableParallelSeeds: Allow Replication of Simulations on Parallel and Serial Computers

Description

Creates, saves, reloads, and selects among streams of random numbers.

Details

Package:	portableParallelSeeds
Type:	Package
License:	GPL (v >= 2)

This demonstrates one way to create and use a collection of initializing values for the R random number generator to assure replication in a collection of runs, whether executed in parallel or in serial. Each individual run within a simulation project can be individually replicated and verfied. From a batch of thousands of simulations, one can select any arbritray "run" of the model and re-initialize it in isolation. Identical random number streams are assured whether a simulation is executed on one computer or 1000 nodes in a cluster. In addition, this framework allows each "run" to draw from several separate streams of random numbers. Please see the help file for the function initPortableSeeds for a full working example. A vignette called pps is also being prepared.

Author(s)

Paul E. Johnson <[e-mail]> Maintainer: Paul E. Johnson <[e-mail]>

References

Chambers, John M. (2008) Software for Data Analysis: Programming with R. New York: Springer.

L'Ecuyer, P. (1999). Good Parameters and Implementations for Combined Multiple Recursive Random Number Generators. Operations Research, 47(1), 159-164.

L'Ecuyer, P., Simard, R., Chen, E. J., & Kelton, W. D. (2002). An Object-Oriented Random-Number Package with Many Long Streams and Substreams. Operations Research, 50(6), 1073-1075.

Sevcikova, Hana and A. J. Rossini (2010). snowFT: Fault Tolerant Simple Network of Workstations. R package version 1.2-0. http://CRAN.R-project.org/package=snowFT

See Also

rstream snowft parallel SoDA

wjakethompson/portableParallelSeeds documentation built on Nov. 5, 2019, 12:22 p.m.