Detail publikace
Accelerating Cellular Automata Evolution on Graphics Processing Units
ŽALOUDEK, L. SEKANINA, L. ŠIMEK, V.
Originální název
Accelerating Cellular Automata Evolution on Graphics Processing Units
Typ
článek v časopise - ostatní, Jost
Jazyk
angličtina
Originální abstrakt
As design of cellular automata rules using
conventional methods is a difficult task, evolutionary
algorithms are often utilized in this area. However, in that
case, high computational demands need to be met. This
problem may be partially solved by parallelization. Since
parallel supercomputers and server clusters are expensive and
often overburdened, this paper proposes the evolution of
cellular automata rules on small and inexpensive graphic
processing units. The main objective of this paper is to
demonstrate that evolution of cellular automata rules can be
accelerated significantly using graphics processing units.
Several methods of speeding-up the evolution of cellular
automata rules are proposed, evaluated and compared, some
with very good results. Also a comparison is made between
mid-end and high-end graphics accelerator card based on the
results of evolution speedup. The proposed methods are
evaluated using two benchmark problems.
Klíčová slova
cellular automata, parallel computing, GPU, CUDA, genetic alghorithm
Autoři
ŽALOUDEK, L.; SEKANINA, L.; ŠIMEK, V.
Rok RIV
2010
Vydáno
12. 9. 2010
ISSN
1942-2628
Periodikum
International Journal on Advances in Software
Ročník
3
Číslo
1
Stát
Spojené státy americké
Strany od
294
Strany do
303
Strany počet
10
URL
BibTex
@article{BUT50515,
author="Luděk {Žaloudek} and Lukáš {Sekanina} and Václav {Šimek}",
title="Accelerating Cellular Automata Evolution on Graphics Processing Units",
journal="International Journal on Advances in Software",
year="2010",
volume="3",
number="1",
pages="294--303",
issn="1942-2628",
url="https://www.fit.vut.cz/research/publication/9315/"
}Dokumenty