Detail publikace

Parallel Genetic Algorithm on the CUDA Architecture

POSPÍCHAL, P. JAROŠ, J. SCHWARZ, J.

Originální název

Parallel Genetic Algorithm on the CUDA Architecture

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This paper deals with the mapping of the parallel island-based genetic algorithm with unidirectional ring migrations to nVidia CUDA software model. The proposed mapping is tested using Rosenbrock's, Griewank's and Michalewicz's benchmark functions. The obtained results indicate that our approach leads to speedups up to seven thousand times higher compared to one CPU thread while maintaining a reasonable results quality. This clearly shows that GPUs have a potential for acceleration of GAs and allow to solve much complex tasks.

Klíčová slova

massively parallel, genetic algorithm, island model, CUDA, migrations

Autoři

POSPÍCHAL, P.; JAROŠ, J.; SCHWARZ, J.

Rok RIV

2010

Vydáno

9. 4. 2010

Nakladatel

Springer Verlag

Místo

Berlin Heidelberg

ISBN

978-3-642-12238-5

Kniha

Applications of Evolutionary Computation

Edice

Lecture Notes in Computer Science

Strany od

442

Strany do

451

Strany počet

10

URL

BibTex

@inproceedings{BUT34649,
  author="Petr {Pospíchal} and Jiří {Jaroš} and Josef {Schwarz}",
  title="Parallel Genetic Algorithm on the CUDA Architecture",
  booktitle="Applications of Evolutionary Computation",
  year="2010",
  series="Lecture Notes in Computer Science",
  volume="6024",
  pages="442--451",
  publisher="Springer Verlag",
  address="Berlin Heidelberg",
  doi="10.1007/978-3-642-12239-2\{_}46",
  isbn="978-3-642-12238-5",
  url="https://www.fit.vut.cz/research/publication/9184/"
}