Parallel execution of SVM training using graphics processing units (SVMTrGPUs)
Parallel computing is a simultaneous use of multiple compute resources, for example, processors to solve complex computational problems. It has been used in high-end computing areas such as pattern recognition, medical diagnosis, national defense, and web search engine. This paper focuses on the imp...
Saved in:
Main Authors: | , |
---|---|
Format: | |
Published: |
2018
|
Online Access: | http://dspace.uniten.edu.my/jspui/handle/123456789/7252 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uniten.dspace-7252 |
---|---|
record_format |
dspace |
spelling |
my.uniten.dspace-72522018-01-11T09:14:50Z Parallel execution of SVM training using graphics processing units (SVMTrGPUs) Salleh, N.S.M. Baharim, M.F. Parallel computing is a simultaneous use of multiple compute resources, for example, processors to solve complex computational problems. It has been used in high-end computing areas such as pattern recognition, medical diagnosis, national defense, and web search engine. This paper focuses on the implementation of pattern classification technique, Support Vector Machine (SVM) using vector processor approach. We have carried out a performance analysis to benchmark the sequential SVM program against the Graphics Processing Units (GPUs) optimization. The result shows that the parallelization of SVM training duration achieves a better performance than the sequential code speedups by 6.40. © 2015 IEEE. 2018-01-11T09:14:50Z 2018-01-11T09:14:50Z 2016 http://dspace.uniten.edu.my/jspui/handle/123456789/7252 |
institution |
Universiti Tenaga Nasional |
building |
UNITEN Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Tenaga Nasional |
content_source |
UNITEN Institutional Repository |
url_provider |
http://dspace.uniten.edu.my/ |
description |
Parallel computing is a simultaneous use of multiple compute resources, for example, processors to solve complex computational problems. It has been used in high-end computing areas such as pattern recognition, medical diagnosis, national defense, and web search engine. This paper focuses on the implementation of pattern classification technique, Support Vector Machine (SVM) using vector processor approach. We have carried out a performance analysis to benchmark the sequential SVM program against the Graphics Processing Units (GPUs) optimization. The result shows that the parallelization of SVM training duration achieves a better performance than the sequential code speedups by 6.40. © 2015 IEEE. |
format |
|
author |
Salleh, N.S.M. Baharim, M.F. |
spellingShingle |
Salleh, N.S.M. Baharim, M.F. Parallel execution of SVM training using graphics processing units (SVMTrGPUs) |
author_facet |
Salleh, N.S.M. Baharim, M.F. |
author_sort |
Salleh, N.S.M. |
title |
Parallel execution of SVM training using graphics processing units (SVMTrGPUs) |
title_short |
Parallel execution of SVM training using graphics processing units (SVMTrGPUs) |
title_full |
Parallel execution of SVM training using graphics processing units (SVMTrGPUs) |
title_fullStr |
Parallel execution of SVM training using graphics processing units (SVMTrGPUs) |
title_full_unstemmed |
Parallel execution of SVM training using graphics processing units (SVMTrGPUs) |
title_sort |
parallel execution of svm training using graphics processing units (svmtrgpus) |
publishDate |
2018 |
url |
http://dspace.uniten.edu.my/jspui/handle/123456789/7252 |
_version_ |
1644494147356196864 |
score |
13.160551 |