Solving Large Sparse Linear Systems on Grid Computers using an Asynchronous Iterative Method as a Preconditioner
Tijmen Collignon (Delft University of Technology)Martin van Gijzen (Delft University of Technology)
Abstract:
In this paper we describe an efficient iterative algorithm for solving large sparse linear systems on Grid computers and review some of its advantages and disadvantages. The algorithm is a combination of a synchronous flexible outer iterative method and a coarse--grain asynchronous inner iterative method as a preconditioner. We present results of a complete implementation using mature Grid middleware, applied to a 3D convection--diffusion problem. Experiments are performed in a heterogeneous computing environment.
Keywords:
Parallel and Distributed Computing, Cluster Computing, Grid Computing (middleware, algorithms, performance evaluation, ...), Numerical Algorithms for CS&E
