GPU cluster for accelerated processing and visualisation of scientific and engineering data

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The ability to process, visualise, and work with large volumes of data in a way that is fast, meaningful, and accurate is an essential part of many fields of scientific research today. The success of video game industry has resulted in ongoing developments in the complexity of Graphical Processing Units (GPU), as well as rapidly falling cost per core. Their characteristics make them excellently suited to any task exhibiting a high level of data parallelism. Recent development of GPU architectures is aimed at HPC systems and applications. In this paper we are presenting our experience in designing and deploying a small dedicated GPU based cluster for processing and visualising data generated by engineering and scientific application. This GPU cluster is helping our researchers to analyse complex data using visualisation, and to accelerate large data processing. We have shown that our GPU cluster solution can achieve five to ten times speed up compared to the CPU system. As a result of our work we can demonstrate that even a small GPU cluster can benefit Higher Education institutions.

Original languageEnglish
Title of host publicationProceedings of 2014 Science and Information Conference, SAI 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages140-145
Number of pages6
ISBN (Electronic)9780989319317
DOIs
Publication statusPublished - 7 Oct 2014
Event2014 Science and Information Conference - Park Inn by Radisson Hotel, London, United Kingdom
Duration: 27 Aug 201429 Aug 2014
http://saiconference.com/Conferences/SAIConference2014 (Link to Conference Details )

Conference

Conference2014 Science and Information Conference
Abbreviated titleSAI 2014
CountryUnited Kingdom
CityLondon
Period27/08/1429/08/14
Internet address

Fingerprint

Visualization
Processing
Data visualization
Program processors
Education
Costs
Industry

Cite this

Newall, M., Holmes, V., & Lunn, P. (2014). GPU cluster for accelerated processing and visualisation of scientific and engineering data. In Proceedings of 2014 Science and Information Conference, SAI 2014 (pp. 140-145). [6918182] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SAI.2014.6918182
Newall, Matthew ; Holmes, Violeta ; Lunn, Paul. / GPU cluster for accelerated processing and visualisation of scientific and engineering data. Proceedings of 2014 Science and Information Conference, SAI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 140-145
@inproceedings{fd8d3439b96447ffae86cce242dd4491,
title = "GPU cluster for accelerated processing and visualisation of scientific and engineering data",
abstract = "The ability to process, visualise, and work with large volumes of data in a way that is fast, meaningful, and accurate is an essential part of many fields of scientific research today. The success of video game industry has resulted in ongoing developments in the complexity of Graphical Processing Units (GPU), as well as rapidly falling cost per core. Their characteristics make them excellently suited to any task exhibiting a high level of data parallelism. Recent development of GPU architectures is aimed at HPC systems and applications. In this paper we are presenting our experience in designing and deploying a small dedicated GPU based cluster for processing and visualising data generated by engineering and scientific application. This GPU cluster is helping our researchers to analyse complex data using visualisation, and to accelerate large data processing. We have shown that our GPU cluster solution can achieve five to ten times speed up compared to the CPU system. As a result of our work we can demonstrate that even a small GPU cluster can benefit Higher Education institutions.",
keywords = "CUDA, GPU, GPU Cluster, Visualisation",
author = "Matthew Newall and Violeta Holmes and Paul Lunn",
year = "2014",
month = "10",
day = "7",
doi = "10.1109/SAI.2014.6918182",
language = "English",
pages = "140--145",
booktitle = "Proceedings of 2014 Science and Information Conference, SAI 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Newall, M, Holmes, V & Lunn, P 2014, GPU cluster for accelerated processing and visualisation of scientific and engineering data. in Proceedings of 2014 Science and Information Conference, SAI 2014., 6918182, Institute of Electrical and Electronics Engineers Inc., pp. 140-145, 2014 Science and Information Conference, London, United Kingdom, 27/08/14. https://doi.org/10.1109/SAI.2014.6918182

GPU cluster for accelerated processing and visualisation of scientific and engineering data. / Newall, Matthew; Holmes, Violeta; Lunn, Paul.

Proceedings of 2014 Science and Information Conference, SAI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 140-145 6918182.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - GPU cluster for accelerated processing and visualisation of scientific and engineering data

AU - Newall, Matthew

AU - Holmes, Violeta

AU - Lunn, Paul

PY - 2014/10/7

Y1 - 2014/10/7

N2 - The ability to process, visualise, and work with large volumes of data in a way that is fast, meaningful, and accurate is an essential part of many fields of scientific research today. The success of video game industry has resulted in ongoing developments in the complexity of Graphical Processing Units (GPU), as well as rapidly falling cost per core. Their characteristics make them excellently suited to any task exhibiting a high level of data parallelism. Recent development of GPU architectures is aimed at HPC systems and applications. In this paper we are presenting our experience in designing and deploying a small dedicated GPU based cluster for processing and visualising data generated by engineering and scientific application. This GPU cluster is helping our researchers to analyse complex data using visualisation, and to accelerate large data processing. We have shown that our GPU cluster solution can achieve five to ten times speed up compared to the CPU system. As a result of our work we can demonstrate that even a small GPU cluster can benefit Higher Education institutions.

AB - The ability to process, visualise, and work with large volumes of data in a way that is fast, meaningful, and accurate is an essential part of many fields of scientific research today. The success of video game industry has resulted in ongoing developments in the complexity of Graphical Processing Units (GPU), as well as rapidly falling cost per core. Their characteristics make them excellently suited to any task exhibiting a high level of data parallelism. Recent development of GPU architectures is aimed at HPC systems and applications. In this paper we are presenting our experience in designing and deploying a small dedicated GPU based cluster for processing and visualising data generated by engineering and scientific application. This GPU cluster is helping our researchers to analyse complex data using visualisation, and to accelerate large data processing. We have shown that our GPU cluster solution can achieve five to ten times speed up compared to the CPU system. As a result of our work we can demonstrate that even a small GPU cluster can benefit Higher Education institutions.

KW - CUDA

KW - GPU

KW - GPU Cluster

KW - Visualisation

UR - http://www.scopus.com/inward/record.url?scp=84909638476&partnerID=8YFLogxK

U2 - 10.1109/SAI.2014.6918182

DO - 10.1109/SAI.2014.6918182

M3 - Conference contribution

SP - 140

EP - 145

BT - Proceedings of 2014 Science and Information Conference, SAI 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Newall M, Holmes V, Lunn P. GPU cluster for accelerated processing and visualisation of scientific and engineering data. In Proceedings of 2014 Science and Information Conference, SAI 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 140-145. 6918182 https://doi.org/10.1109/SAI.2014.6918182