Abstract
Computational fluid dynamics (CFD) is a Grand Challenge discipline whose typical application areas, like aerospace and automotive engineering, often require enormous amount of computations. Parallel processing offers very high performance potential, but irregular problems like CFD have proven difficult to map onto parallel machines. In such codes, access patterns to major data arrays are dependent on some runtime data, therefore runtime preprocessing must be applied on critical code segments. So, automatic parallelization of irregular codes is a challenging problem. In this paper we describe parallelizing techniques we have developed for processing irregular codes that include irregularly distributed data structures. These techniques have been fully implemented within the Vienna Fortran Compilation System. We have examined the AVL FIRE benchmark solver GCCG, to evaluate the influence of different kinds of data distributions on parallel-program execution time. Experiments were performed using the Tjunc dataset on the iPSC/860.
The work described in this paper was carried out as part of the European ESPRIT project PPPE and CEI-PACT project funded by the Austrian Science Foundation (FWF) and the Austrian Ministry for Science and Research (BMWF).
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
G. Bachler, R. Greimel. Parallel CFD in the Industrial Environment. Unicom Seminars, London, 1994.
S. Benkner, P. Brezany, H.P. Zima. Processing Array Statements and Procedure Interfaces in the Prepare High Performance Fortran Compiler. Proc. 5th International Conference on Compiler Construction, Edinburgh, U.K., April 1994, Springer-Verlag, LNCS 786, pp. 324–338.
P. Brezany, M. Gerndt, V. Sipkova, and H.P. Zima. SUPERB Support for Irregular Scientific Computations. In Proceedings of the SHPCC '92, Williamsburg, USA, April 1992, pp.314–321.
P. Brezany, B. Chapman, R. Ponnusamy, V. Sipkova, and H Zima, Study of Application Algorithms with Irregular Distributions, tech. report D1Z-3 of the CEI-PACT Project, University of Vienna, April 1994.
P. Brezany, O. Chéron, K. Sanjari, and E. van Konijnenburg, Processing Irregular Codes Containing Arrays with Multi-Dimensional Distributions by the PREPARE HPF Compiler, HPCN Europe'95, Milan, Springer-Verlag, 526–531.
P. Brezany, V. Sipkova. Coupling Parallel Data and Work Partitioners to VFCS. Submitted to the Conference EUROSIM-HPCN Challenges 1996, Delft.
R. Das, and J. Saltz. A manual for PARTI runtime primitives — Revision 2. Internal Research Report, University of Maryland, Dec. 1992.
N. Floros, J. Reeve. Domain Decomposition Tool (DDT). Esprit CAMAS 6756 Report, University of Southampton, March 1994.
R. van Hanxleden. Compiler Support for Machine-Independent Parallelization of Irregular Problems. Dr. Thesis, Center for Research on Parallel Computation, Rice University, December 1994.
C. Koelbel. Compiling Programs for Nonshared Memory Machines. Ph.D. Dissertation, Purdue University, West Lafayette, IN, November 1990.
R. Ponnusamy, J. Saltz, A. Choudhary, Y-S. Hwang, G. Fox. Runtime Support and Compilation Methods for User-Specified Data Distributions. Internal Research Report, University of Maryland, University of Syracuse, 1993.
H.D. Simon. Parallel CFD. The MIT Press, Cambridge, 1992.
P.K.W. Vinsome. ORTHOMIN, an iterative method for solving sparse sets of simultaneous linear equations. In Proc. Fourth Symp. on Reservoir Simulation, Society of Petroleum Engineers of AIME, pp. 149–159.
H. Zima, P. Brezany, B. Chapman, P. Mehrotra, A. Schwald. Vienna Fortran — A language Specification Version 1.1. University of Vienna, ACPC-TR 92-4, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Brezany, P., Sipkova, V., Chapman, B., Greimel, R. (1996). Automatic parallelization of the AVL FIRE benchmark for a distributed-memory system. In: Dongarra, J., Madsen, K., Waśniewski, J. (eds) Applied Parallel Computing Computations in Physics, Chemistry and Engineering Science. PARA 1995. Lecture Notes in Computer Science, vol 1041. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60902-4_7
Download citation
DOI: https://doi.org/10.1007/3-540-60902-4_7
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60902-5
Online ISBN: 978-3-540-49670-0
eBook Packages: Springer Book Archive