This work considers the deployment of pseudo-random number generators (PRNGs) on graphics processing units (GPUs), developing an approach based on the xorgens generator to rapidly produce pseudo-random numbers of high statistical quality. The chosen algorithm has configurable state size and period, making it ideal for tuning to the GPU architecture. We present a comparison of both speed and statistical quality with other common GPU-based PRNGs, demonstrating favourable performance of the xorgens-based approach.
N. Nandapalan, R. Brent, L.M. Murray and A. Rendell (2012). High-Performance Pseudo-Random Number Generation on Graphics Processing Units. Parallel Processing and Applied Mathematics. 7203:609-618.
N. Nandapalan, R. Brent, L.M. Murray and A. Rendell (2012). <a href="https://indii.org/research/high-performance-pseudo-random-number-generation-on-graphics-processing-units/">High-Performance Pseudo-Random Number Generation on Graphics Processing Units</a>. <em>Parallel Processing and Applied Mathematics</em>. <strong>7203</strong>:609-618.@Article{Nandapalan2011,
title = {High-Performance Pseudo-Random Number Generation on Graphics Processing Units},
author = {Nima Nandapalan and Richard Brent and Lawrence M. Murray and Alistair Rendell},
journal = {Parallel Processing and Applied Mathematics},
year = {2012},
volume = {7203},
pages = {609-618},
doi = {10.1007/978-3-642-31464-3_62}
}