Parallel random numbers as easy as 1, 2, 3

Most pseudorandom number generators (PRNGs) scale poorly to massively parallel high-performance computation because they are designed as sequentially dependent state transformations. We demonstrate that independent, keyed transformations of counters produce a large alternative class of PRNGs with ex...

Full description

Saved in:
Bibliographic Details
Published in:2011 International Conference for High Performance Computing, Networking, Storage and Analysis (SC) pp. 1 - 12
Main Authors: Salmon, John K., Moraes, Mark A., Dror, Ron O., Shaw, David E.
Format: Conference Proceeding
Language:English
Published: New York, NY, USA ACM 12.11.2011
IEEE
Series:ACM Conferences
Subjects:
Batteries
Computer systems organization > Dependable and fault-tolerant systems and networks
Cryptography
General and reference > Cross-computing tools and techniques > Performance
Generators
Hardware
Mathematics of computing > Probability and statistics > Probabilistic reasoning algorithms > Random number generation
Memory management
Networks > Network performance evaluation
Radiation detectors
Testing
Theory of computation > Models of computation > Concurrency
Theory of computation > Models of computation > Concurrency > Parallel computing models
ISBN:145030771X, 9781450307710
ISSN:2167-4329
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most pseudorandom number generators (PRNGs) scale poorly to massively parallel high-performance computation because they are designed as sequentially dependent state transformations. We demonstrate that independent, keyed transformations of counters produce a large alternative class of PRNGs with excellent statistical properties (long period, no discernable structure or correlation). These counter-based PRNGs are ideally suited to modern multi-core CPUs, GPUs, clusters, and special-purpose hardware because they vectorize and parallelize well, and require little or no memory for state. We introduce several counter-based PRNGs: some based on cryptographic standards (AES, Threefish) and some completely new (Philox). All our PRNGs pass rigorous statistical tests (including TestU01's BigCrush) and produce at least 264 unique parallel streams of random numbers, each with period 2128 or more. In addition to essentially unlimited parallel scalability, our PRNGs offer excellent single-chip performance: Philox is faster than the CURAND library on a single NVIDIA GPU.
ISBN:145030771X
9781450307710
ISSN:2167-4329
DOI:10.1145/2063384.2063405