Detail výsledku

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

JAROŠ, J. Multi-GPU Island-Based Genetic Algorithm Solving the Knapsack Problem. In 2012 IEEE Congress on Evolutionary Computation, CEC 2012. CA: Institute of Electrical and Electronics Engineers, 2012. p. 217-224. ISBN: 978-1-4673-1508-1.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Jaroš Jiří, prof. Ing., Ph.D., UPSY (FIT)
Abstrakt

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.

Klíčová slova

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

Rok
2012
Strany
217–224
Sborník
2012 IEEE Congress on Evolutionary Computation, CEC 2012
Konference
IEEE World Congress on Computational Intelligence
ISBN
978-1-4673-1508-1
Vydavatel
Institute of Electrical and Electronics Engineers
Místo
CA
DOI
10.1109/CEC.2012.6256131
UT WoS
000312859301057
EID Scopus
2-s2.0-84866858943
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/"
}
Soubory
Projekty
Natural computing na nekonvenčních platformách, GAČR, Standardní projekty, GAP103/10/1517, zahájení: 2010-01-01, ukončení: 2013-12-31, řešení
Výzkumné skupiny
Výzkumná skupina Superpočítačových technologií SC@FIT (VZ SC@FIT)
Výzkumná skupina aplikovaných evolučních algoritmů (VZ EVA)
Pracoviště
Ústav počítačových systémů (UPSY)
Nahoru