Abstract
We present a parallel computation model that is appropriate for the derivation of parallel numerical algorithms for nonlinear differential equations executed on distributed memory machines. A parallel implementation for a numerical method results from an abstract specification by choosing a data distribution, a load balancing strategy, and a schedule for those parts that may be executed in parallel. We give several examples for the derivation of parallel implementations in the proposed model that show its usefulness.
author supported by DFG, SFB 124
Preview
Unable to display preview. Download preview PDF.
References
T. Hey and J. Ferrante, editors. Portability and Performance for Parallel Processing. Wiley, 1994.
T. Rauber and G. Rünger. Load Balancing for Extrapolation Methods on Distributed Memory Multiprocessors. In Proceedings of the PARLE'94, Springer LNCS 817, pages 277–288, Athens, Greece, 1994.
T. Rauber and G. Rünger. Iterated Runge-Kutta Methods on Distributed Memory Multiprocessors. In Proceedings of the 3nd Euromicro Workshop on Parallel and Distributed Processing, pages 12–19, 1995.
T. Rauber and G. Rünger. Runtime Predictions for Parallel Runge-Kutta Methods. In 9th Workshop on Parallel and Distributed Simulation, Lake Placid, USA, 1995.
R. Wilhelm and D. Maurer. Compiler Design. Addison Wesley, 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rauber, T., Rünger, G., Wilhelm, R. (1995). An application specific parallel programming paradigm. In: Hertzberger, B., Serazzi, G. (eds) High-Performance Computing and Networking. HPCN-Europe 1995. Lecture Notes in Computer Science, vol 919. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0046708
Download citation
DOI: https://doi.org/10.1007/BFb0046708
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59393-5
Online ISBN: 978-3-540-49242-9
eBook Packages: Springer Book Archive