Publication result detail

GPU-Based Acceleration of the Genetic Algorithm

POSPÍCHAL, P.

Original Title

GPU-Based Acceleration of the Genetic Algorithm

English Title

GPU-Based Acceleration of the Genetic Algorithm

Type

Paper in proceedings outside WoS and Scopus

Original Abstract

Genetic algorithm, a robust, stochastic optimization technique, is effective in solving many

practical problems in science, engineering, and business domains. Unfortunatelly, execution

usually takes long time. In this paper, we study a possibility of utilization consumer-level

graphics cards for acceleration of GAs. We have designed a mapping of the parallel island

genetic algorithm to the CUDA software model and tested our implementation on GeForce

8800GTX and GTX285 GPUs using a Rosenbrock's, Griewank's and Michalewicz's benchmark

functions. Results indicates that our optimization leads to speedups up to seven thousand times

compared to single CPU thread while maintaing reasonable results quality.

English abstract

Genetic algorithm, a robust, stochastic optimization technique, is effective in solving many

practical problems in science, engineering, and business domains. Unfortunatelly, execution

usually takes long time. In this paper, we study a possibility of utilization consumer-level

graphics cards for acceleration of GAs. We have designed a mapping of the parallel island

genetic algorithm to the CUDA software model and tested our implementation on GeForce

8800GTX and GTX285 GPUs using a Rosenbrock's, Griewank's and Michalewicz's benchmark

functions. Results indicates that our optimization leads to speedups up to seven thousand times

compared to single CPU thread while maintaing reasonable results quality.

Keywords

genetic algorithm, CUDA, GPU, migrations, island model

Key words in English

genetic algorithm, CUDA, GPU, migrations, island model

Authors

POSPÍCHAL, P.

RIV year

2011

Released

29.04.2010

Publisher

Faculty of Information Technology BUT

Location

Brno

ISBN

978-80-214-4080-7

Book

Proceedings of the 16th Conference Student EEICT 2010 Volume 5

Pages from

234

Pages to

238

Pages count

5

URL

http://www.feec.vutbr.cz/EEICT/2010/sbornik/03-Doktorske_projekty/09-Pocitacove_systemy/03-xpospi45.pdf

BibTex

@inproceedings{BUT35531,
  author="Petr {Pospíchal}",
  title="GPU-Based Acceleration of the Genetic Algorithm",
  booktitle="Proceedings of the 16th Conference Student EEICT 2010 Volume 5",
  year="2010",
  pages="234--238",
  publisher="Faculty of Information Technology BUT",
  address="Brno",
  isbn="978-80-214-4080-7",
  url="http://www.feec.vutbr.cz/EEICT/2010/sbornik/03-Doktorske_projekty/09-Pocitacove_systemy/03-xpospi45.pdf"
}