High-Performance Pseudo-Random Number Generation on Graphics Processing Units

TL;DR

This paper presents a GPU-optimized pseudo-random number generator based on xorgens, achieving high speed and statistical quality, with configurable parameters for tuning to GPU architectures.

Contribution

It introduces a GPU-specific implementation of xorgens PRNG that outperforms existing GPU-based generators in speed and quality.

Findings

Favorable performance compared to other GPU PRNGs

Configurable state size and period for tuning

High statistical quality of generated numbers

Abstract

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 parallel, GPU-based PRNGs, demonstrating favourable performance of the xorgens-based approach.