Publication detail

Multi-GPU Island-Based Genetic Algorithm Solving the Knapsack Problem

JAROŠ, J.

Original Title

Multi-GPU Island-Based Genetic Algorithm Solving the Knapsack Problem

Type

conference paper

Language

English

Original Abstract

This paper introduces a novel implementation of the genetic algorithm exploiting a multi-GPU cluster. The proposed implementation employs an island-based genetic algorithm where every GPU evolves a single island. The individuals are treated by CUDA warps enabling to solve large knapsack instances and eliminate undesirable thread divergence. The OpenMPI interface is used to exchange genetic material among different islands and to collect statistical data. The implementation characteristics are investigated on a cluster composed of 14 GPUs and 4 six-core Intel Xeon processors.

Keywords

GPU; CUDA; MPI; GA; island model; knapsack

Authors

JAROŠ, J.

RIV year

2012

Released

11. 6. 2012

Publisher

Institute of Electrical and Electronics Engineers

Location

CA

ISBN

978-1-4673-1508-1

Book

2012 IEEE Congress on Evolutionary Computation, CEC 2012

Pages from

217

Pages to

224

Pages count

8

URL

BibTex

@inproceedings{BUT96925,
  author="Jiří {Jaroš}",
  title="Multi-GPU Island-Based Genetic Algorithm Solving the Knapsack Problem",
  booktitle="2012 IEEE Congress on Evolutionary Computation, CEC 2012",
  year="2012",
  pages="217--224",
  publisher="Institute of Electrical and Electronics Engineers",
  address="CA",
  doi="10.1109/CEC.2012.6256131",
  isbn="978-1-4673-1508-1",
  url="https://www.fit.vut.cz/research/publication/9860/"
}