Welcome!
To use the personalized features of this site, please log in or register.
If you have forgotten your username or password, we can help.
|
 |
A Parallel, State-of-the-Art, Least-Squares Spectral Element Solver for Incompressible Flow Problems
| |
|
A Parallel, State-of-the-Art, Least-Squares Spectral Element Solver for Incompressible Flow Problems
Margreet Nool7  and Michael M. J. Proot8
| (7) |
CWI, P.O. Box 94079, 1090 Amsterdam, GB, The Netherlands |
| (8) |
Delft University of Technology, Kluyverweg 1, Delft, The Netherlands |
Abstract
The paper deals with the efficient parallelization of leastsquares spectral element methods for incompressible flows. The
parallelization of this sort of problems requires two different strategies. On the one hand, the spectral element discretization
benefits from an element-by-element parallelization strategy. On the other hand, an efficient strategy to solve the large
sparse global systems benefits from a row-wise distribution of data. This requires two different kinds of data distributions
and the conversion between them is rather complicated. In the present paper, the different strategies together with its conversion
are discussed. Moreover, some results obtained on a distributed memory machine (Cray T3E) and on a virtual shared memory machine
(SGI Origin 3800) are presented.
Funding for this work was provided by the National Computing Facilities Foundation (NCF), under project numbers NRG-2000.07
and MP-068. Computing time was also provided by HPαC, Centre for High Performance Applied Computing at the Delft University
of Technology.
Fulltext Preview (Small, Large)
 References secured to subscribers.
|
|
|
|
|
|