Delivering faster results through parallelisation and GPU acceleration

Matthew Newall, Violeta Holmes, Colin Venters, Paul Lunn

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The rate of scientific discovery depends on the speed at which accurate results and analysis can be obtained. The use of parallel co-processors such as Graphical Processing Units (GPUs) is becoming more and more important in meeting this demand as improvements in serial data processing speed become increasingly difficult to sustain. However, parallel data processing requires more complex programming compared to serial processing. Here we present our methods for parallelising two pieces of scientific software, leveraging multiple GPUs to achieve up to thirty times speed up.

Original languageEnglish
Pages (from-to)309-320
Number of pages12
JournalStudies in Computational Intelligence
Volume591
DOIs
Publication statusPublished - 2015

Fingerprint

Processing
Coprocessor

Cite this

@article{a6cf39ac171045a5b2f5be19c3bab981,
title = "Delivering faster results through parallelisation and GPU acceleration",
abstract = "The rate of scientific discovery depends on the speed at which accurate results and analysis can be obtained. The use of parallel co-processors such as Graphical Processing Units (GPUs) is becoming more and more important in meeting this demand as improvements in serial data processing speed become increasingly difficult to sustain. However, parallel data processing requires more complex programming compared to serial processing. Here we present our methods for parallelising two pieces of scientific software, leveraging multiple GPUs to achieve up to thirty times speed up.",
keywords = "CUDA, GPU, GPU cluster, Parallelisation",
author = "Matthew Newall and Violeta Holmes and Colin Venters and Paul Lunn",
year = "2015",
doi = "10.1007/978-3-319-14654-6_19",
language = "English",
volume = "591",
pages = "309--320",
journal = "Studies in Computational Intelligence",
issn = "1860-949X",
publisher = "Springer Verlag",

}

Delivering faster results through parallelisation and GPU acceleration. / Newall, Matthew; Holmes, Violeta; Venters, Colin; Lunn, Paul.

In: Studies in Computational Intelligence, Vol. 591, 2015, p. 309-320.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Delivering faster results through parallelisation and GPU acceleration

AU - Newall, Matthew

AU - Holmes, Violeta

AU - Venters, Colin

AU - Lunn, Paul

PY - 2015

Y1 - 2015

N2 - The rate of scientific discovery depends on the speed at which accurate results and analysis can be obtained. The use of parallel co-processors such as Graphical Processing Units (GPUs) is becoming more and more important in meeting this demand as improvements in serial data processing speed become increasingly difficult to sustain. However, parallel data processing requires more complex programming compared to serial processing. Here we present our methods for parallelising two pieces of scientific software, leveraging multiple GPUs to achieve up to thirty times speed up.

AB - The rate of scientific discovery depends on the speed at which accurate results and analysis can be obtained. The use of parallel co-processors such as Graphical Processing Units (GPUs) is becoming more and more important in meeting this demand as improvements in serial data processing speed become increasingly difficult to sustain. However, parallel data processing requires more complex programming compared to serial processing. Here we present our methods for parallelising two pieces of scientific software, leveraging multiple GPUs to achieve up to thirty times speed up.

KW - CUDA

KW - GPU

KW - GPU cluster

KW - Parallelisation

UR - http://www.scopus.com/inward/record.url?scp=84922937926&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-14654-6_19

DO - 10.1007/978-3-319-14654-6_19

M3 - Article

VL - 591

SP - 309

EP - 320

JO - Studies in Computational Intelligence

JF - Studies in Computational Intelligence

SN - 1860-949X

ER -