Using coordination to parallelize sparse-grid methods for 3-D CFD problems

In this paper, we investigate the good parallel computing properties of sparse-grid solution techniques. To this end, an existing sequential computational fluid dynamics (CFD) code for a standard 3-D problem from computational aerodynamics is restructured into a parallel application. The restructuring is organized according to a master/worker protocol. The coordinator modules developed thereby are implemented in the coordination language Manifold and are applicable to other problems than the present CFD problem only. Performance results are given for both the sequential and the parallel versions of the code. The results are promising. The paper contributes to the state-of-the-art in improving the efficiency of large-scale computations. We also present a theoretical analysis of speed-up through parallelization in a multi-user single-machine environment.