Přístupnostní navigace
E-application
Search Search Close
Publication detail
ŽALOUDEK, L. SEKANINA, L. ŠIMEK, V.
Original Title
Accelerating Cellular Automata Evolution on Graphics Processing Units
Type
journal article - other
Language
English
Original Abstract
As design of cellular automata rules usingconventional methods is a difficult task, evolutionaryalgorithms are often utilized in this area. However, in thatcase, high computational demands need to be met. Thisproblem may be partially solved by parallelization. Sinceparallel supercomputers and server clusters are expensive andoften overburdened, this paper proposes the evolution ofcellular automata rules on small and inexpensive graphicprocessing units. The main objective of this paper is todemonstrate that evolution of cellular automata rules can beaccelerated significantly using graphics processing units.Several methods of speeding-up the evolution of cellularautomata rules are proposed, evaluated and compared, somewith very good results. Also a comparison is made betweenmid-end and high-end graphics accelerator card based on theresults of evolution speedup. The proposed methods areevaluated using two benchmark problems.
Keywords
cellular automata, parallel computing, GPU, CUDA, genetic alghorithm
Authors
ŽALOUDEK, L.; SEKANINA, L.; ŠIMEK, V.
RIV year
2010
Released
12. 9. 2010
ISBN
1942-2628
Periodical
International Journal on Advances in Software
Year of study
3
Number
1
State
United States of America
Pages from
294
Pages to
303
Pages count
10
URL
https://www.fit.vut.cz/research/publication/9315/
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/" }
Documents
zaloudek.pdf