A Deterministic Portable Parallel Pseudo-Random Number Generator for Pattern-Based Programming of Heterogeneous Parallel Systems

SkePU is a pattern-based high-level programming model for transparent program execution on heterogeneous parallel computing systems. A key feature of SkePU is that, in general, the selection of the execution platform for a skeleton-based function call need not be determined statically. On single-nod...

Full description

Saved in:
Bibliographic Details
Published in:International journal of parallel programming Vol. 50; no. 3-4; pp. 319 - 340
Main Authors: Ernstsson, August, Vandenbergen, Nicolas, Keller, Jörg, Kessler, Christoph
Format: Journal Article
Language:English
Published: New York Springer US 01.08.2022
Springer Nature B.V
Subjects:
Central processing units
Computer programming
Computer Science
CPUs
Generators
Graphics processing units
Numbers
Portability
Processor Architectures
Pseudorandom
Random numbers
Software Engineering/Programming and Operating Systems
Software upgrading
Source code
Special Issue on High-Level Parallel Programming and Applications 2021
Theory of Computation
Parallelizable algorithmic pattern
Heterogeneous system
Deterministic parallel pseudo-random number generator
Skeleton programming
GPGPU
ISSN:0885-7458, 1573-7640, 1573-7640
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:SkePU is a pattern-based high-level programming model for transparent program execution on heterogeneous parallel computing systems. A key feature of SkePU is that, in general, the selection of the execution platform for a skeleton-based function call need not be determined statically. On single-node systems, SkePU can select among CPU, multithreaded CPU, single or multi-GPU execution. Many scientific applications use pseudo-random number generators (PRNGs) as part of the computation. In the interest of correctness and debugging, deterministic parallel execution is a desirable property, which however requires a deterministically parallelized pseudo-random number generator. We present the API and implementation of a deterministic, portable parallel PRNG extension to SkePU that is scalable by design and exhibits the same behavior regardless where and with how many resources it is executed. We evaluate it with four probabilistic applications and show that the PRNG enables scalability on both multi-core CPU and GPU resources, and hence supports the universal portability of SkePU code even in the presence of PRNG calls, while source code complexity is reduced.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0885-7458
1573-7640
1573-7640
DOI:10.1007/s10766-022-00726-5