Abstract
Multi block solvers for the 2 and 3 Dimensional Euler Equations have been developed. The spatial discretization scheme is that of Jameson [1] using central differencing with added artificial dissipation. The resulting system of ODE’s is integrated in time using the explicit Runge Kutta procedure. The computational domain is split into multiple blocks, first of all to facilitate the grid generation for complex geometries, and secondly to allow the utilization of different parallel computers, on which this paper places the emphasis. The spectrum of parallel computers envisaged is broad, ranging from computers having only a relatively small number of processors to massively parallel computers. Results discussed in this paper includes the CRAY 2, ALLIANT FX/80 and the Intel iPSC/2 SX, while the implementation on the Connection Machine is briefly discussed. The multi block approach proved to be easily ported between these different computers, and - most important - attain high parallel efficiencies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Jameson, A., Steady state Solutions of the Euler Equations for Transonic Flow by a Multigrid Method, Advances in Scientific Computing, pp.37–70, Academic Press 1982
Jameson, A., 2nd Joint GAMNI/SMAI-IMA Conference on Computational Aeronautical Dynamics, May 17–19 1989, Antibes, France
Bergman, C.M., Development of Numerical Techniques for Inviscid Hypersonic Flows around Re-entry Vehicles, Ph.D thesis, INP Toulouse, 1990
McBryan, O.A., Overview of Current Developments in Parallel Architectures, Parallel Supercomputing, Wiley & Sons Inc., 1989
Bergman C.M. and Rizzi A.W., Implementation of an Multi Block Euler Solver on a Shared Memory MIMD Computer, International Workshop on Supercomputing Tools for Science and Engineering, Pisa, Italy, December 4–7,1989
CFT77 Compiling System: Fortran Reference Manual, SR-3071 4.0. Cray Research Inc., 1990
Bergman C.M. and Vos J.B., Parallelization of CFD Codes, Second World Congress on Computational Mechanics, August 27–31, 1990, Stuttgart
Bergman C.M., Wahlund P., Implementation of an Multi Block Euler Solver on the CM-2, Abstract submitted to Third Annual Conference on Parallel CFD, Stuttgart, Germany, June 10–12, 1991
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1991 Computational Mechanics Publications
About this chapter
Cite this chapter
Vos, J.B., Bergman, C.M. (1991). Multi Block Flow Solvers for Use on Parallel Computers. In: Brebbia, C.A., Peters, A., Howard, D. (eds) Applications of Supercomputers in Engineering II. Springer, Dordrecht. https://doi.org/10.1007/978-94-011-3660-0_1
Download citation
DOI: https://doi.org/10.1007/978-94-011-3660-0_1
Publisher Name: Springer, Dordrecht
Print ISBN: 978-1-85166-695-9
Online ISBN: 978-94-011-3660-0
eBook Packages: Springer Book Archive