GPU-based asynchronous particle swarm optimization

Luca Mussi; Youssef S G Nashed; Stefano Cagnoni

doi:10.1145/2001576.2001786

GPU-based asynchronous particle swarm optimization

Luca Mussi^*, Youssef S G Nashed, Stefano Cagnoni

^*Corresponding author for this work

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

33 Scopus citations

Abstract

This paper describes our latest implementation of Particle Swarm Optimization (PSO) with simple ring topology for modern Graphic Processing Units (GPUs). To achieve both the fastest execution time and the best performance, we designed a parallel version of the algorithm, as fine-grained as possible, without introducing explicit synchronization mechanisms among the particles' evolution processes. The results we obtained show a significant speed-up with respect to both the sequential version of the algorithm run on an up-to-date CPU and our previously developed parallel implementation within the nVIDIA™ CUDA™ architecture.

Original language	English (US)
Title of host publication	Genetic and Evolutionary Computation Conference, GECCO'11
Pages	1555-1562
Number of pages	8
DOIs	https://doi.org/10.1145/2001576.2001786
State	Published - Aug 24 2011
Event	13th Annual Genetic and Evolutionary Computation Conference, GECCO'11 - Dublin, Ireland Duration: Jul 12 2011 → Jul 16 2011

Other

Other	13th Annual Genetic and Evolutionary Computation Conference, GECCO'11
Country/Territory	Ireland
City	Dublin
Period	7/12/11 → 7/16/11

Keywords

Implementation
Parallelization
Particle Swarm Optimization
Speed-up technique

ASJC Scopus subject areas

Computational Theory and Mathematics
Theoretical Computer Science

Access to Document

10.1145/2001576.2001786

Cite this

@inproceedings{5c7ccb48422d4b16a3768439e13e77be,

title = "GPU-based asynchronous particle swarm optimization",

abstract = "This paper describes our latest implementation of Particle Swarm Optimization (PSO) with simple ring topology for modern Graphic Processing Units (GPUs). To achieve both the fastest execution time and the best performance, we designed a parallel version of the algorithm, as fine-grained as possible, without introducing explicit synchronization mechanisms among the particles' evolution processes. The results we obtained show a significant speed-up with respect to both the sequential version of the algorithm run on an up-to-date CPU and our previously developed parallel implementation within the nVIDIA{\texttrademark} CUDA{\texttrademark} architecture.",

keywords = "Implementation, Parallelization, Particle Swarm Optimization, Speed-up technique",

author = "Luca Mussi and Nashed, {Youssef S G} and Stefano Cagnoni",

year = "2011",

month = aug,

day = "24",

doi = "10.1145/2001576.2001786",

language = "English (US)",

isbn = "9781450305570",

pages = "1555--1562",

booktitle = "Genetic and Evolutionary Computation Conference, GECCO'11",

note = "13th Annual Genetic and Evolutionary Computation Conference, GECCO'11 ; Conference date: 12-07-2011 Through 16-07-2011",

}

TY - GEN

T1 - GPU-based asynchronous particle swarm optimization

AU - Mussi, Luca

AU - Nashed, Youssef S G

AU - Cagnoni, Stefano

PY - 2011/8/24

Y1 - 2011/8/24

N2 - This paper describes our latest implementation of Particle Swarm Optimization (PSO) with simple ring topology for modern Graphic Processing Units (GPUs). To achieve both the fastest execution time and the best performance, we designed a parallel version of the algorithm, as fine-grained as possible, without introducing explicit synchronization mechanisms among the particles' evolution processes. The results we obtained show a significant speed-up with respect to both the sequential version of the algorithm run on an up-to-date CPU and our previously developed parallel implementation within the nVIDIA™ CUDA™ architecture.

AB - This paper describes our latest implementation of Particle Swarm Optimization (PSO) with simple ring topology for modern Graphic Processing Units (GPUs). To achieve both the fastest execution time and the best performance, we designed a parallel version of the algorithm, as fine-grained as possible, without introducing explicit synchronization mechanisms among the particles' evolution processes. The results we obtained show a significant speed-up with respect to both the sequential version of the algorithm run on an up-to-date CPU and our previously developed parallel implementation within the nVIDIA™ CUDA™ architecture.

KW - Implementation

KW - Parallelization

KW - Particle Swarm Optimization

KW - Speed-up technique

UR - http://www.scopus.com/inward/record.url?scp=84860390548&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860390548&partnerID=8YFLogxK

U2 - 10.1145/2001576.2001786

DO - 10.1145/2001576.2001786

M3 - Conference contribution

AN - SCOPUS:84860390548

SN - 9781450305570

SP - 1555

EP - 1562

BT - Genetic and Evolutionary Computation Conference, GECCO'11

T2 - 13th Annual Genetic and Evolutionary Computation Conference, GECCO'11

Y2 - 12 July 2011 through 16 July 2011

ER -

GPU-based asynchronous particle swarm optimization

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this