Abstract

A Parallel State-of-the-Art Least-Squares Spectral Element Solver for Incompressible Flow Problems
Margreet Nool - CWI Michael M.J. Proot - Delft University of Technology
The paper deals with the efficient parallelization of least-squares 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) are presented.

A Parallel State-of-the-Art Least-Squares Spectral Element Solver for Incompressible Flow Problems

Margreet Nool - CWI
Michael M.J. Proot - Delft University of Technology

The paper deals with the efficient parallelization of
least-squares 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) are presented.

Last update: Wed Jun 12 14:26:52 2002 WEST