A parallel, state-of-the-art, least-squares spectral element solver for incompressible flow problems

Authors:
Margreet Nool;Michael M. J. Proot
Affiliations:
CWI, GB Amsterdam, The Netherlands;Delft University of Technology, Delft, The Netherlands
Venue:
VECPAR'02 Proceedings of the 5th international conference on High performance computing for computational science
Year:
2002

Citing 5
Cited 1

Iterative Substructuring Methods for Spectral Element Discretizations of Elliptic Systems I: Compressible Linear Elasticity

SIAM Journal on Numerical Analysis
Iterative Substructuring Methods for Spectral Element Discretizations of Elliptic Systems. II: Mixed Methods for Linear Elasticity and Stokes Flow

SIAM Journal on Numerical Analysis
MPI: The Complete Reference

MPI: The Complete Reference
A Least-Squares Spectral Element Formulation for the Stokes Problem

Journal of Scientific Computing
Parallel Implementation of a Least-Squares Spectral Element Solver for Incompressible Flow Problems

The Journal of Supercomputing

A parallel least-squares spectral element solver for incompressible flow problems on unstructured grids

Parallel Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

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) and on a virtual shared memory machine (SGI Origin 3800) are presented.