Particle swarm stepwise algorithm (PaSS) on multicore hybrid CPU-GPU clusters

Mu Yang, Ray-Bing Chen, I. Hsin Chung, Weichung Wang

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

Abstract

Variable (feature) selection is a key component in artificial intelligence. One way to perform variable selection is to solve the information-criterion-based optimization problems. These optimization problems arise from data mining, genomes analysis, machine learning, numerical simulations, and others. Particle Swarm Stepwise Algorithm (PaSS) is a stochastic search algorithm proposed to solve the information-criterion-based variable selection optimization problems. It has been shown recently that the PaSS outperforms several existed methods. However, to solve the target optimization problems remains a challenge due to the large search spaces. We tackle this issue by proposing a parallel version of the PaSS on clusters equipped with CPU and GPU to shorten the computational time without compromise in solution accuracy. We have successfully achieved near-linear scalability on CPU with single to 64 threads and gained further 7X faster timing performance by using GPU.

Original languageEnglish
Title of host publicationProceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages265-272
Number of pages8
ISBN (Electronic)9781509043149
DOIs
Publication statusPublished - 2017 Mar 10
Event16th IEEE International Conference on Computer and Information Technology, CIT 2016 - Nadi, Fiji
Duration: 2016 Dec 72016 Dec 10

Publication series

NameProceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016

Other

Other16th IEEE International Conference on Computer and Information Technology, CIT 2016
CountryFiji
CityNadi
Period16-12-0716-12-10

Fingerprint

Program processors
Artificial intelligence
Data mining
Learning systems
Scalability
Feature extraction
Genes
Graphics processing unit
Computer simulation

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Information Systems
  • Safety, Risk, Reliability and Quality

Cite this

Yang, M., Chen, R-B., Chung, I. H., & Wang, W. (2017). Particle swarm stepwise algorithm (PaSS) on multicore hybrid CPU-GPU clusters. In Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016 (pp. 265-272). [7876347] (Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIT.2016.101
Yang, Mu ; Chen, Ray-Bing ; Chung, I. Hsin ; Wang, Weichung. / Particle swarm stepwise algorithm (PaSS) on multicore hybrid CPU-GPU clusters. Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 265-272 (Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016).
@inproceedings{0dcd5c68049544f785f9c45e63d7a2da,
title = "Particle swarm stepwise algorithm (PaSS) on multicore hybrid CPU-GPU clusters",
abstract = "Variable (feature) selection is a key component in artificial intelligence. One way to perform variable selection is to solve the information-criterion-based optimization problems. These optimization problems arise from data mining, genomes analysis, machine learning, numerical simulations, and others. Particle Swarm Stepwise Algorithm (PaSS) is a stochastic search algorithm proposed to solve the information-criterion-based variable selection optimization problems. It has been shown recently that the PaSS outperforms several existed methods. However, to solve the target optimization problems remains a challenge due to the large search spaces. We tackle this issue by proposing a parallel version of the PaSS on clusters equipped with CPU and GPU to shorten the computational time without compromise in solution accuracy. We have successfully achieved near-linear scalability on CPU with single to 64 threads and gained further 7X faster timing performance by using GPU.",
author = "Mu Yang and Ray-Bing Chen and Chung, {I. Hsin} and Weichung Wang",
year = "2017",
month = "3",
day = "10",
doi = "10.1109/CIT.2016.101",
language = "English",
series = "Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "265--272",
booktitle = "Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016",
address = "United States",

}

Yang, M, Chen, R-B, Chung, IH & Wang, W 2017, Particle swarm stepwise algorithm (PaSS) on multicore hybrid CPU-GPU clusters. in Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016., 7876347, Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016, Institute of Electrical and Electronics Engineers Inc., pp. 265-272, 16th IEEE International Conference on Computer and Information Technology, CIT 2016, Nadi, Fiji, 16-12-07. https://doi.org/10.1109/CIT.2016.101

Particle swarm stepwise algorithm (PaSS) on multicore hybrid CPU-GPU clusters. / Yang, Mu; Chen, Ray-Bing; Chung, I. Hsin; Wang, Weichung.

Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 265-272 7876347 (Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016).

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

TY - GEN

T1 - Particle swarm stepwise algorithm (PaSS) on multicore hybrid CPU-GPU clusters

AU - Yang, Mu

AU - Chen, Ray-Bing

AU - Chung, I. Hsin

AU - Wang, Weichung

PY - 2017/3/10

Y1 - 2017/3/10

N2 - Variable (feature) selection is a key component in artificial intelligence. One way to perform variable selection is to solve the information-criterion-based optimization problems. These optimization problems arise from data mining, genomes analysis, machine learning, numerical simulations, and others. Particle Swarm Stepwise Algorithm (PaSS) is a stochastic search algorithm proposed to solve the information-criterion-based variable selection optimization problems. It has been shown recently that the PaSS outperforms several existed methods. However, to solve the target optimization problems remains a challenge due to the large search spaces. We tackle this issue by proposing a parallel version of the PaSS on clusters equipped with CPU and GPU to shorten the computational time without compromise in solution accuracy. We have successfully achieved near-linear scalability on CPU with single to 64 threads and gained further 7X faster timing performance by using GPU.

AB - Variable (feature) selection is a key component in artificial intelligence. One way to perform variable selection is to solve the information-criterion-based optimization problems. These optimization problems arise from data mining, genomes analysis, machine learning, numerical simulations, and others. Particle Swarm Stepwise Algorithm (PaSS) is a stochastic search algorithm proposed to solve the information-criterion-based variable selection optimization problems. It has been shown recently that the PaSS outperforms several existed methods. However, to solve the target optimization problems remains a challenge due to the large search spaces. We tackle this issue by proposing a parallel version of the PaSS on clusters equipped with CPU and GPU to shorten the computational time without compromise in solution accuracy. We have successfully achieved near-linear scalability on CPU with single to 64 threads and gained further 7X faster timing performance by using GPU.

UR - http://www.scopus.com/inward/record.url?scp=85017331494&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017331494&partnerID=8YFLogxK

U2 - 10.1109/CIT.2016.101

DO - 10.1109/CIT.2016.101

M3 - Conference contribution

AN - SCOPUS:85017331494

T3 - Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016

SP - 265

EP - 272

BT - Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Yang M, Chen R-B, Chung IH, Wang W. Particle swarm stepwise algorithm (PaSS) on multicore hybrid CPU-GPU clusters. In Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 265-272. 7876347. (Proceedings - 2016 16th IEEE International Conference on Computer and Information Technology, CIT 2016, 2016 6th International Symposium on Cloud and Service Computing, IEEE SC2 2016 and 2016 International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2016). https://doi.org/10.1109/CIT.2016.101