Performance Comparison of Parallel Execution Using GPU and CPU in SVM Training Session

Nur Shakirah Md Salleh, Muhammad Fahim Baharim

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

3 Citations (Scopus)

Abstract

Support Vector Machine (SVM) is a machine learning approach, which is used in a growing number of applications. SVM is a useful technique for data classification. This machine learning approach has been optimized using two (2) parallel computing approaches. This includes symmetric multiprocessor (SMP) approach and vector processor approach. The outcome performance of the implementation of symmetric multiprocessor approach and vector processor approach on SVM training session is the focus of this paper. We have carried out a performance analysis to benchmark between Central Processing Unit (CPU) and Graphics Processing Units (GPUs) optimization. The result shows the GPU optimization of SVM training duration achieves better performance than the CPU optimized program by 3.11 of speedup.

Original languageEnglish
Title of host publicationProceedings - 2015 4th International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages214-217
Number of pages4
ISBN (Electronic)9781509004249
DOIs
Publication statusPublished - 25 May 2016
Event4th International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2015 - Kuala Lumpur, Malaysia
Duration: 08 Dec 201510 Dec 2015

Other

Other4th International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2015
CountryMalaysia
CityKuala Lumpur
Period08/12/1510/12/15

Fingerprint

Performance Comparison
Graphics Processing Unit
Program processors
Support vector machines
Support Vector Machine
Unit
Multiprocessor
Learning systems
Machine Learning
Data Classification
Optimization
Parallel processing systems
Parallel Computing
Performance Analysis
Speedup
Benchmark
Training
Graphics processing unit

All Science Journal Classification (ASJC) codes

  • Modelling and Simulation
  • Computer Science Applications

Cite this

Md Salleh, N. S., & Baharim, M. F. (2016). Performance Comparison of Parallel Execution Using GPU and CPU in SVM Training Session. In Proceedings - 2015 4th International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2015 (pp. 214-217). [7478746] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ACSAT.2015.31
Md Salleh, Nur Shakirah ; Baharim, Muhammad Fahim. / Performance Comparison of Parallel Execution Using GPU and CPU in SVM Training Session. Proceedings - 2015 4th International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2015. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 214-217
@inproceedings{7222413477ce40b79fbb31292db74f5f,
title = "Performance Comparison of Parallel Execution Using GPU and CPU in SVM Training Session",
abstract = "Support Vector Machine (SVM) is a machine learning approach, which is used in a growing number of applications. SVM is a useful technique for data classification. This machine learning approach has been optimized using two (2) parallel computing approaches. This includes symmetric multiprocessor (SMP) approach and vector processor approach. The outcome performance of the implementation of symmetric multiprocessor approach and vector processor approach on SVM training session is the focus of this paper. We have carried out a performance analysis to benchmark between Central Processing Unit (CPU) and Graphics Processing Units (GPUs) optimization. The result shows the GPU optimization of SVM training duration achieves better performance than the CPU optimized program by 3.11 of speedup.",
author = "{Md Salleh}, {Nur Shakirah} and Baharim, {Muhammad Fahim}",
year = "2016",
month = "5",
day = "25",
doi = "10.1109/ACSAT.2015.31",
language = "English",
pages = "214--217",
booktitle = "Proceedings - 2015 4th International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Md Salleh, NS & Baharim, MF 2016, Performance Comparison of Parallel Execution Using GPU and CPU in SVM Training Session. in Proceedings - 2015 4th International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2015., 7478746, Institute of Electrical and Electronics Engineers Inc., pp. 214-217, 4th International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2015, Kuala Lumpur, Malaysia, 08/12/15. https://doi.org/10.1109/ACSAT.2015.31

Performance Comparison of Parallel Execution Using GPU and CPU in SVM Training Session. / Md Salleh, Nur Shakirah; Baharim, Muhammad Fahim.

Proceedings - 2015 4th International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 214-217 7478746.

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

TY - GEN

T1 - Performance Comparison of Parallel Execution Using GPU and CPU in SVM Training Session

AU - Md Salleh, Nur Shakirah

AU - Baharim, Muhammad Fahim

PY - 2016/5/25

Y1 - 2016/5/25

N2 - Support Vector Machine (SVM) is a machine learning approach, which is used in a growing number of applications. SVM is a useful technique for data classification. This machine learning approach has been optimized using two (2) parallel computing approaches. This includes symmetric multiprocessor (SMP) approach and vector processor approach. The outcome performance of the implementation of symmetric multiprocessor approach and vector processor approach on SVM training session is the focus of this paper. We have carried out a performance analysis to benchmark between Central Processing Unit (CPU) and Graphics Processing Units (GPUs) optimization. The result shows the GPU optimization of SVM training duration achieves better performance than the CPU optimized program by 3.11 of speedup.

AB - Support Vector Machine (SVM) is a machine learning approach, which is used in a growing number of applications. SVM is a useful technique for data classification. This machine learning approach has been optimized using two (2) parallel computing approaches. This includes symmetric multiprocessor (SMP) approach and vector processor approach. The outcome performance of the implementation of symmetric multiprocessor approach and vector processor approach on SVM training session is the focus of this paper. We have carried out a performance analysis to benchmark between Central Processing Unit (CPU) and Graphics Processing Units (GPUs) optimization. The result shows the GPU optimization of SVM training duration achieves better performance than the CPU optimized program by 3.11 of speedup.

UR - http://www.scopus.com/inward/record.url?scp=84979074755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84979074755&partnerID=8YFLogxK

U2 - 10.1109/ACSAT.2015.31

DO - 10.1109/ACSAT.2015.31

M3 - Conference contribution

SP - 214

EP - 217

BT - Proceedings - 2015 4th International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Md Salleh NS, Baharim MF. Performance Comparison of Parallel Execution Using GPU and CPU in SVM Training Session. In Proceedings - 2015 4th International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 214-217. 7478746 https://doi.org/10.1109/ACSAT.2015.31