Parallel Cellular Automata-based Simulation of Laser Dynamics using Dynamic Load Balancing
We present an analysis of the feasibility of executing a parallel bioinspired model of laser dynamics, based on cellular automata (CA), on the usual target platform of this kind of applications: a heterogeneous non-dedicated cluster. As this model employs a synchronous CA, using the single program,...
| Autores: | , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión enviada para evaluación y publicación |
| Fecha de publicación: | 2008 |
| País: | España |
| Institución: | Universidad de Sevilla (US) |
| Repositorio: | idUS. Depósito de Investigación de la Universidad de Sevilla |
| OAI Identifier: | oai:idus.us.es:11441/74223 |
| Acceso en línea: | https://hdl.handle.net/11441/74223 https://doi.org/10.1504/IJHPSA.2008.024209 |
| Access Level: | acceso abierto |
| id |
ES_231fa93b06375531a1e4b4dbc83900a9 |
|---|---|
| oai_identifier_str |
oai:idus.us.es:11441/74223 |
| network_acronym_str |
ES |
| network_name_str |
España |
| spelling |
Parallel Cellular Automata-based Simulation of Laser Dynamics using Dynamic Load Balancing Guisado Lizar, José Luis Fernández de Vega, Francisco Jiménez-Morales, Francisco de Paula Iskra, Kamil A. Sloot, Peter M.A. We present an analysis of the feasibility of executing a parallel bioinspired model of laser dynamics, based on cellular automata (CA), on the usual target platform of this kind of applications: a heterogeneous non-dedicated cluster. As this model employs a synchronous CA, using the single program, multiple data (SPMD) paradigm, it is not clear in advance if an appropriate efficiency can be obtained on this kind of platform. We have evaluated its performance including artificial load to simulate other tasks or jobs submitted by other users. A dynamic load balancing strategy with two main differences from most previous implementations of CA based models has been used. First, it is possible to migrate load to cluster nodes initially not belonging to the pool. Second, a modular approach is taken in which the model is executed on top of a dynamic load balancing tool – the Dynamite system – gaining flexibility. Very satisfactory results have been obtained, with performance increases from 60% to 80%. Ministerio de Ciencia e Innovación TIN2007-68083-C02 Junta de Extremadura PRI06A223 InderScience Publishers https://hdl.handle.net/11441/74223 https://doi.org/10.1504/IJHPSA.2008.024209 |
| title |
Parallel Cellular Automata-based Simulation of Laser Dynamics using Dynamic Load Balancing |
| spellingShingle |
Parallel Cellular Automata-based Simulation of Laser Dynamics using Dynamic Load Balancing Guisado Lizar, José Luis |
| title_short |
Parallel Cellular Automata-based Simulation of Laser Dynamics using Dynamic Load Balancing |
| title_full |
Parallel Cellular Automata-based Simulation of Laser Dynamics using Dynamic Load Balancing |
| title_fullStr |
Parallel Cellular Automata-based Simulation of Laser Dynamics using Dynamic Load Balancing |
| title_full_unstemmed |
Parallel Cellular Automata-based Simulation of Laser Dynamics using Dynamic Load Balancing |
| title_sort |
Parallel Cellular Automata-based Simulation of Laser Dynamics using Dynamic Load Balancing |
| author |
Guisado Lizar, José Luis |
| author_facet |
Guisado Lizar, José Luis Fernández de Vega, Francisco Jiménez-Morales, Francisco de Paula Iskra, Kamil A. Sloot, Peter M.A. |
| author_role |
author |
| author2 |
Fernández de Vega, Francisco Jiménez-Morales, Francisco de Paula Iskra, Kamil A. Sloot, Peter M.A. |
| author2_role |
author author author author |
| description |
We present an analysis of the feasibility of executing a parallel bioinspired model of laser dynamics, based on cellular automata (CA), on the usual target platform of this kind of applications: a heterogeneous non-dedicated cluster. As this model employs a synchronous CA, using the single program, multiple data (SPMD) paradigm, it is not clear in advance if an appropriate efficiency can be obtained on this kind of platform. We have evaluated its performance including artificial load to simulate other tasks or jobs submitted by other users. A dynamic load balancing strategy with two main differences from most previous implementations of CA based models has been used. First, it is possible to migrate load to cluster nodes initially not belonging to the pool. Second, a modular approach is taken in which the model is executed on top of a dynamic load balancing tool – the Dynamite system – gaining flexibility. Very satisfactory results have been obtained, with performance increases from 60% to 80%. |
| publishDate |
2008 |
| format |
article |
| status_str |
submittedVersion |
| url |
https://hdl.handle.net/11441/74223 https://doi.org/10.1504/IJHPSA.2008.024209 |
| eu_rights_str_mv |
openAccess |
| publisher |
InderScience Publishers |
| institution |
Universidad de Sevilla (US) |
| collection |
idUS. Depósito de Investigación de la Universidad de Sevilla |
| reponame_str |
idUS. Depósito de Investigación de la Universidad de Sevilla |
| instname_str |
Universidad de Sevilla (US) |
| _version_ |
1878432449011122177 |
| publishDateSort |
2008 |
| author_browse |
Fernández de Vega, Francisco Guisado Lizar, José Luis Iskra, Kamil A. Jiménez-Morales, Francisco de Paula Sloot, Peter M.A. |
| publisherStr |
InderScience Publishers |
| score |
6,924472 |