Efficient simulation execution of cellular automata on GPU

Graphics Processing Units (GPUs) can be used as convenient hardware accelerators to speed up Cellular Automata (CA) simulations, which are employed in many scientific areas. However, an important set of CA have performance constraints due to GPU memory bandwidth. Few studies have fully explored how...

ver descrição completa

Detalhes bibliográficos
Autores: Cagigas Muñiz, Daniel, Díaz del Río, Fernando, Sevillano Ramos, José Luis, Guisado Lizar, José Luis
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:España
Recursos:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/131065
Acesso em linha:https://hdl.handle.net/11441/131065
https://doi.org/10.1016/j.simpat.2022.102519
Access Level:acceso abierto
Palavra-chave:Cellular automata
Parallel Computing
Performance optimization
Stencil computation
Graphics Processing Units
id ES_7fa42fe888cc6ea553cb55d2b782be55
oai_identifier_str oai:idus.us.es:11441/131065
network_acronym_str ES
network_name_str España
repository_id_str
spelling Efficient simulation execution of cellular automata on GPUCagigas Muñiz, DanielDíaz del Río, FernandoSevillano Ramos, José LuisGuisado Lizar, José LuisCellular automataParallel ComputingPerformance optimizationStencil computationGraphics Processing UnitsGraphics Processing Units (GPUs) can be used as convenient hardware accelerators to speed up Cellular Automata (CA) simulations, which are employed in many scientific areas. However, an important set of CA have performance constraints due to GPU memory bandwidth. Few studies have fully explored how CA implementations can take advantage of modern GPU architectures, mainly in the case of intensive memory usage. In this paper, we make a thorough study of techniques (stencil computing framework, look-up tables, and packet coding) to efficiently implement CA on GPU, taking into account its detailed architecture. Exhaustive experiments to validate these implementation techniques for a number of significant memory bounded CA are performed. The CA analysed include the classical Game of Life, a Forest Fire model, a Cyclic cellular automaton, and the WireWorld CA. The experimental results show that implementations using the presented techniques can significantly outperform a baseline standard GPU implementation. The best performance results of all known implementations of memory bounded CA were obtained. Moreover, some of the techniques, like look-up tables or temporal blocking, are indeed relatively easy to implement or to apply when the transition rules are simple. Finally, detailed descriptions and discussions of the indicated techniques are included, which may be useful to practitioners interested in developing high performance simulations in efficient languages based on CA on GPU.Agencia Estatal de Investigación PID2019-110455GB-I00)Junta de Andalucía CIUCAP-HSF:US-1381077ElsevierArquitectura y Tecnología de ComputadoresTEP-108: Robótica y Tecnología de ComputadoresAgencia Estatal de Investigación. EspañaJunta de Andalucía2022info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/131065https://doi.org/10.1016/j.simpat.2022.102519reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésSimulation Modelling Practice and Theory, 118 (July 2022, nº102519)PID2019-110455GB-I00CIUCAP-HSF:US-1381077https://www.sciencedirect.com/science/article/pii/S1569190X22000259?via%3Dihubinfo:eu-repo/semantics/openAccessoai:idus.us.es:11441/1310652026-06-17T12:51:07Z
dc.title.none.fl_str_mv Efficient simulation execution of cellular automata on GPU
title Efficient simulation execution of cellular automata on GPU
spellingShingle Efficient simulation execution of cellular automata on GPU
Cagigas Muñiz, Daniel
Cellular automata
Parallel Computing
Performance optimization
Stencil computation
Graphics Processing Units
title_short Efficient simulation execution of cellular automata on GPU
title_full Efficient simulation execution of cellular automata on GPU
title_fullStr Efficient simulation execution of cellular automata on GPU
title_full_unstemmed Efficient simulation execution of cellular automata on GPU
title_sort Efficient simulation execution of cellular automata on GPU
dc.creator.none.fl_str_mv Cagigas Muñiz, Daniel
Díaz del Río, Fernando
Sevillano Ramos, José Luis
Guisado Lizar, José Luis
author Cagigas Muñiz, Daniel
author_facet Cagigas Muñiz, Daniel
Díaz del Río, Fernando
Sevillano Ramos, José Luis
Guisado Lizar, José Luis
author_role author
author2 Díaz del Río, Fernando
Sevillano Ramos, José Luis
Guisado Lizar, José Luis
author2_role author
author
author
dc.contributor.none.fl_str_mv Arquitectura y Tecnología de Computadores
TEP-108: Robótica y Tecnología de Computadores
Agencia Estatal de Investigación. España
Junta de Andalucía
dc.subject.none.fl_str_mv Cellular automata
Parallel Computing
Performance optimization
Stencil computation
Graphics Processing Units
topic Cellular automata
Parallel Computing
Performance optimization
Stencil computation
Graphics Processing Units
description Graphics Processing Units (GPUs) can be used as convenient hardware accelerators to speed up Cellular Automata (CA) simulations, which are employed in many scientific areas. However, an important set of CA have performance constraints due to GPU memory bandwidth. Few studies have fully explored how CA implementations can take advantage of modern GPU architectures, mainly in the case of intensive memory usage. In this paper, we make a thorough study of techniques (stencil computing framework, look-up tables, and packet coding) to efficiently implement CA on GPU, taking into account its detailed architecture. Exhaustive experiments to validate these implementation techniques for a number of significant memory bounded CA are performed. The CA analysed include the classical Game of Life, a Forest Fire model, a Cyclic cellular automaton, and the WireWorld CA. The experimental results show that implementations using the presented techniques can significantly outperform a baseline standard GPU implementation. The best performance results of all known implementations of memory bounded CA were obtained. Moreover, some of the techniques, like look-up tables or temporal blocking, are indeed relatively easy to implement or to apply when the transition rules are simple. Finally, detailed descriptions and discussions of the indicated techniques are included, which may be useful to practitioners interested in developing high performance simulations in efficient languages based on CA on GPU.
publishDate 2022
dc.date.none.fl_str_mv 2022
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/131065
https://doi.org/10.1016/j.simpat.2022.102519
url https://hdl.handle.net/11441/131065
https://doi.org/10.1016/j.simpat.2022.102519
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Simulation Modelling Practice and Theory, 118 (July 2022, nº102519)
PID2019-110455GB-I00
CIUCAP-HSF:US-1381077
https://www.sciencedirect.com/science/article/pii/S1569190X22000259?via%3Dihub
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869411839753846784
score 15.301603

Registos relacionados