The cost of continuity: a study of the performance of isogeometric finite elements using direct solvers

We study the performance of direct solvers on linear systems of equations resulting from isogeometric analysis. The problem of choice is the canonical Laplace equation in three dimensions. From this study we conclude that for a fixed number of unknowns and polynomial degree of approximation, a highe...

ver descrição completa

Detalhes bibliográficos
Autores: Collier, Nathan, Pardo, David, Dalcin, Lisandro Daniel, Paszynski, Maciej, Calo, V.M.
Tipo de documento: artigo
Estado:Versão publicada
Data de publicação:2012
País:Argentina
Recursos:Consejo Nacional de Investigaciones Científicas y Técnicas
Repositório:CONICET Digital (CONICET)
Idioma:inglês
OAI Identifier:oai:ri.conicet.gov.ar:11336/76419
Acesso em linha:http://hdl.handle.net/11336/76419
Access Level:Acceso aberto
Palavra-chave:Direct Solvers
Isogeometric Analysis
K-Refinement
Multi-Frontal Solvers
Performance
Descrição
Resumo:We study the performance of direct solvers on linear systems of equations resulting from isogeometric analysis. The problem of choice is the canonical Laplace equation in three dimensions. From this study we conclude that for a fixed number of unknowns and polynomial degree of approximation, a higher degree of continuity k drastically increases the CPU time and RAM needed to solve the problem when using a direct solver. This paper presents numerical results detailing the phenomenon as well as a theoretical analysis that explains the underlying cause.