Abstract
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. © 2011 Elsevier B.V.
Original language | English (US) |
---|---|
Pages (from-to) | 353-361 |
Number of pages | 9 |
Journal | Computer Methods in Applied Mechanics and Engineering |
Volume | 213-216 |
DOIs | |
State | Published - Mar 2012 |
ASJC Scopus subject areas
- General Physics and Astronomy
- Mechanics of Materials
- Mechanical Engineering
- Computational Mechanics
- Computer Science Applications