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 a long time. In this paper, I study possibility of utilization consumer-level graphics cards for acceleration of GA's. A mapping of parallel island genetic algorithm to CUDA software model is designed and tested on GeForce 8800GTX, GTX260-SP216 and GTX285 GPU's using Rosenbrock's, Griewank's and Michalewicz's benchmark functions. Results indicates that this 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 a long time. In this paper, I study possibility of utilization consumer-level graphics cards for acceleration of GA's. A mapping of parallel island genetic algorithm to CUDA software model is designed and tested on GeForce 8800GTX, GTX260-SP216 and GTX285 GPU's using Rosenbrock's, Griewank's and Michalewicz's benchmark functions. Results indicates that this optimization leads to speedups up to seven thousand times compared to single CPU thread while maintaing reasonable results quality.

Keywords

Parallel Genetic Algorithm, PGA, CUDA, Island Model, Galib, Speedup, GPU

Key words in English

Parallel Genetic Algorithm, PGA, CUDA, Island Model, Galib, Speedup, GPU

Authors

POSPÍCHAL, P.

RIV year

2012

Released

16.09.2010

Publisher

Faculty of Information Technology BUT

Location

Brno

ISBN

978-80-214-4140-8

Book

Počítačové architektury a diagnostika 2010

Pages from

75

Pages to

80

Pages count

6

BibTex

@inproceedings{BUT34930,
  author="Petr {Pospíchal}",
  title="GPU-Based Acceleration of the Genetic Algorithm",
  booktitle="Počítačové architektury a diagnostika 2010",
  year="2010",
  pages="75--80",
  publisher="Faculty of Information Technology BUT",
  address="Brno",
  isbn="978-80-214-4140-8"
}