Solution of finite element problems using hybrid parallelization with MPI and OpenMP Solution of finite element problems using hybrid parallelization with MPI and OpenMP
<p>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 o...
Main Authors: | , |
---|---|
Format: | Article |
Language: | Spanish |
Published: |
Universidad de Guanajuato
2012-11-01
|
Series: | Acta Universitaria |
Subjects: | |
Online Access: | http://www.actauniversitaria.ugto.mx/index.php/acta/article/view/391 |
id |
doaj-3456ba66bc2b4f42806ec555fb9d3334 |
---|---|
record_format |
Article |
spelling |
doaj-3456ba66bc2b4f42806ec555fb9d33342020-11-25T01:30:37ZspaUniversidad de GuanajuatoActa Universitaria0188-62662012-11-012271424Solution of finite element problems using hybrid parallelization with MPI and OpenMP Solution of finite element problems using hybrid parallelization with MPI and OpenMPJosé Miguel Vargas-FélixSalvador Botello-Rionda<p>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.</p><br><p>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.</p>http://www.actauniversitaria.ugto.mx/index.php/acta/article/view/391Cómputo en paralelomatrices dispersassolvers linealesecuaciones diferenciales parciales |
collection |
DOAJ |
language |
Spanish |
format |
Article |
sources |
DOAJ |
author |
José Miguel Vargas-Félix Salvador Botello-Rionda |
spellingShingle |
José Miguel Vargas-Félix Salvador Botello-Rionda Solution of finite element problems using hybrid parallelization with MPI and OpenMP Solution of finite element problems using hybrid parallelization with MPI and OpenMP Acta Universitaria Cómputo en paralelo matrices dispersas solvers lineales ecuaciones diferenciales parciales |
author_facet |
José Miguel Vargas-Félix Salvador Botello-Rionda |
author_sort |
José Miguel Vargas-Félix |
title |
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_short |
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_full |
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_fullStr |
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_full_unstemmed |
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_sort |
solution of finite element problems using hybrid parallelization with mpi and openmp solution of finite element problems using hybrid parallelization with mpi and openmp |
publisher |
Universidad de Guanajuato |
series |
Acta Universitaria |
issn |
0188-6266 |
publishDate |
2012-11-01 |
description |
<p>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.</p><br><p>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.</p> |
topic |
Cómputo en paralelo matrices dispersas solvers lineales ecuaciones diferenciales parciales |
url |
http://www.actauniversitaria.ugto.mx/index.php/acta/article/view/391 |
work_keys_str_mv |
AT josemiguelvargasfelix solutionoffiniteelementproblemsusinghybridparallelizationwithmpiandopenmpsolutionoffiniteelementproblemsusinghybridparallelizationwithmpiandopenmp AT salvadorbotellorionda solutionoffiniteelementproblemsusinghybridparallelizationwithmpiandopenmpsolutionoffiniteelementproblemsusinghybridparallelizationwithmpiandopenmp |
_version_ |
1725091034403176448 |