Solution of finite element problems using hybrid parallelization with MPI and OpenMP

The Finite Element Method (FEM) is used to solve problems like solid deformation and heat diffusion in domains with complex geometries. This kind of geometries requires discretization with millions of elements; this is equivalent to solve systems of equations with sparse matrices and tens or hundred...

Descripción completa

Detalles Bibliográficos
Autores: Vargas-Félix, José Miguel, Botello-Rionda, Salvador
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2012
País:México
Institución:UNIVERSIDAD DE GUANAJUATO
Repositorio:Acta Universitaria
Idioma:español
OAI Identifier:oai:www.actauniversitaria.ugto.mx:article/391
Acceso en línea:https://www.actauniversitaria.ugto.mx/index.php/acta/article/view/391
Access Level:acceso abierto
Palabra clave:Parallel computing
linear solvers
partial differential equations
Cómputo en paralelo
matrices dispersas
solvers lineales
ecuaciones diferenciales parciales
id MX_71822190885549fb78bc9fed2c418e19
oai_identifier_str oai:www.actauniversitaria.ugto.mx:article/391
network_acronym_str MX
network_name_str México
repository_id_str
spelling Solution of finite element problems using hybrid parallelization with MPI and OpenMPSolution of finite element problems using hybrid parallelization with MPI and OpenMPVargas-Félix, José MiguelBotello-Rionda, SalvadorParallel computinglinear solverspartial differential equationsCómputo en paralelomatrices dispersassolvers linealesecuaciones diferenciales parcialesThe Finite Element Method (FEM) is used to solve problems like solid deformation and heat diffusion in domains with complex geometries. This kind of geometries requires discretization with millions of elements; this is equivalent to solve systems of equations with sparse matrices and tens or hundreds of millions of variables. The aim is to use computer clusters to solve these systems. The solution method used is Schur substructuration. Using it is possible to divide a large system of equations into many small ones to solve them more efficiently. This method allows parallelization. MPI (Message Passing Interface) is used to distribute the systems of equations to solve each one in a computer of a cluster. Each system of equations is solved using a solver implemented to use OpenMP as a local parallelization method.The Finite Element Method (FEM) is used to solve problems like solid deformation and heat diffusion in domains with complex geometries. This kind of geometries requires discretization with millions of elements; this is equivalent to solve systems of equations with sparse matrices and tens or hundreds of millions of variables. The aim is to use computer clusters to solve these systems. The solution method used is Schur substructuration. Using it is possible to divide a large system of equations into many small ones to solve them more efficiently. This method allows parallelization. MPI (Message Passing Interface) is used to distribute the systems of equations to solve each one in a computer of a cluster. Each system of equations is solved using a solver implemented to use OpenMP as a local parallelization method.Universidad de Guanajuato2012-11-15info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionArtículo revisado por paresapplication/pdfhttps://www.actauniversitaria.ugto.mx/index.php/acta/article/view/39110.15174/au.2012.391Acta Universitaria; Vol. 22 Núm. 7 (2012); 14-24Acta Universitaria; Vol. 22 No. 7 (2012); 14-242007-96210188-6266reponame:Acta Universitariainstname:UNIVERSIDAD DE GUANAJUATOinstacron:UGTOspahttps://www.actauniversitaria.ugto.mx/index.php/acta/article/view/391/pdfinfo:eu-repo/semantics/openAccessoai:www.actauniversitaria.ugto.mx:article/3912024-08-16T21:06:31Z
dc.title.none.fl_str_mv Solution of finite element problems using hybrid parallelization with MPI and OpenMP
Solution of finite element problems using hybrid parallelization with MPI and OpenMP
title Solution of finite element problems using hybrid parallelization with MPI and OpenMP
spellingShingle Solution of finite element problems using hybrid parallelization with MPI and OpenMP
Vargas-Félix, José Miguel
Parallel computing
linear solvers
partial differential equations
Cómputo en paralelo
matrices dispersas
solvers lineales
ecuaciones diferenciales parciales
title_short Solution of finite element problems using hybrid parallelization with MPI and OpenMP
title_full Solution of finite element problems using hybrid parallelization with MPI and OpenMP
title_fullStr Solution of finite element problems using hybrid parallelization with MPI and OpenMP
title_full_unstemmed Solution of finite element problems using hybrid parallelization with MPI and OpenMP
title_sort Solution of finite element problems using hybrid parallelization with MPI and OpenMP
dc.creator.none.fl_str_mv Vargas-Félix, José Miguel
Botello-Rionda, Salvador
author Vargas-Félix, José Miguel
author_facet Vargas-Félix, José Miguel
Botello-Rionda, Salvador
author_role author
author2 Botello-Rionda, Salvador
author2_role author
dc.subject.none.fl_str_mv Parallel computing
linear solvers
partial differential equations
Cómputo en paralelo
matrices dispersas
solvers lineales
ecuaciones diferenciales parciales
topic Parallel computing
linear solvers
partial differential equations
Cómputo en paralelo
matrices dispersas
solvers lineales
ecuaciones diferenciales parciales
description The Finite Element Method (FEM) is used to solve problems like solid deformation and heat diffusion in domains with complex geometries. This kind of geometries requires discretization with millions of elements; this is equivalent to solve systems of equations with sparse matrices and tens or hundreds of millions of variables. The aim is to use computer clusters to solve these systems. The solution method used is Schur substructuration. Using it is possible to divide a large system of equations into many small ones to solve them more efficiently. This method allows parallelization. MPI (Message Passing Interface) is used to distribute the systems of equations to solve each one in a computer of a cluster. Each system of equations is solved using a solver implemented to use OpenMP as a local parallelization method.
publishDate 2012
dc.date.none.fl_str_mv 2012-11-15
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Artículo revisado por pares
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://www.actauniversitaria.ugto.mx/index.php/acta/article/view/391
10.15174/au.2012.391
url https://www.actauniversitaria.ugto.mx/index.php/acta/article/view/391
identifier_str_mv 10.15174/au.2012.391
dc.language.none.fl_str_mv spa
language spa
dc.relation.none.fl_str_mv https://www.actauniversitaria.ugto.mx/index.php/acta/article/view/391/pdf
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidad de Guanajuato
publisher.none.fl_str_mv Universidad de Guanajuato
dc.source.none.fl_str_mv Acta Universitaria; Vol. 22 Núm. 7 (2012); 14-24
Acta Universitaria; Vol. 22 No. 7 (2012); 14-24
2007-9621
0188-6266
reponame:Acta Universitaria
instname:UNIVERSIDAD DE GUANAJUATO
instacron:UGTO
instname_str UNIVERSIDAD DE GUANAJUATO
instacron_str UGTO
institution UGTO
reponame_str Acta Universitaria
collection Acta Universitaria
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1858175690912825344
score 15,811543

Similares en LA Referencia