Detail publikačního výsledku

GPU-Based Acceleration of the Genetic Algorithm

POSPÍCHAL, P.

Originální název

GPU-Based Acceleration of the Genetic Algorithm

Anglický název

GPU-Based Acceleration of the Genetic Algorithm

Druh

Stať ve sborníku mimo WoS a Scopus

Originální abstrakt

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.

Anglický abstrakt

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.

Klíčová slova

genetic algorithm, CUDA, GPU, migrations, island model

Klíčová slova v angličtině

genetic algorithm, CUDA, GPU, migrations, island model

Autoři

POSPÍCHAL, P.

Rok RIV

2011

Vydáno

29.04.2010

Nakladatel

Faculty of Information Technology BUT

Místo

Brno

ISBN

978-80-214-4080-7

Kniha

Proceedings of the 16th Conference Student EEICT 2010 Volume 5

Strany od

234

Strany do

238

Strany počet

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"
}