Parallelization of unstructured mesh computations using data structure formalization

  • Rainer Koppler
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1470)


This paper introduces a concept for semi-automatic parallelization of unstructured mesh computations called data structure formalization. Unlike existing concepts it does not expect knowledge about parallelism but just enough knowledge about the application semantics such that a formal description of the data structure implementation can be given. The parallelization tool Parlamat uses this description for deduction of additional information about arrays and loops such that more efficient parallelization can be achieved than with general tools. We give a brief overview of our data structure modelling language and first experiences with Parlamat’s capabilities by means of the translation of some real-size applications from Fortran 77 to HPF.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Banerjee, U.: Dependence Analysis for Supercomputing. Reading, Kluwer Academic Publishers, Boston (1988)Google Scholar
  2. 2.
    Blume, W., Eigenmann, R., Hoeflinger, J., Padua, D., Petersen, P., Rauchwerger, L., Tu, P.: Automatic Detection of Parallelism. IEEE Parallel and Distributed Technology 2 (1994) 37–47CrossRefGoogle Scholar
  3. 3.
    Benkner, S., Pantano, M., Sanjari, K., Sipkova, V., Velkow, B., Wender, B.: VFC — Compilation System for HPF+ — Release Notes 0.91. University of Vienna (1997)Google Scholar
  4. 4.
    Brandes, T.: ADAPTOR Programmer’s Guide Version 4.0. GMD Technical Report, German National Research Center for Information Technology (1996)Google Scholar
  5. 5.
    Chapman, B., Zima, H., Mehrotra, P.: Extending HPF for Advanced Data-Parallel Applications. IEEE Parallel And Distributed Technology 2 (1994) 59–70CrossRefGoogle Scholar
  6. 6.
    Cross, M., Ierotheou, C., Johnson, S., Leggett, P.: CAPTools — semiautomatic parallelisation of mesh based computational mechanics codes. Proc. HPCN ’94 2 (1994) 241–246Google Scholar
  7. 7.
    Das, R., Mavriplis, D., Saltz, J., Gupta, S., Ponnusamy, R.: The Design and Implementation of a Parallel Unstructured Euler Solver Using Software Primitives. AIAA Journal 32 (1994) 489–496MATHCrossRefGoogle Scholar
  8. 8.
    Hascoet, L.: Automatic Placement of Communications in Mesh-Partitioning Parallelization. ACM SIGPLAN Notices 32 (1997) 136–144CrossRefGoogle Scholar
  9. 9.
    High-Performance Fortran Forum: High Performance Fortran Language Specification — Version 2.0. Technical Report, Rice University, TX (1997)Google Scholar
  10. 10.
    Kallinderis, Y., Vijayan, P.: Adaptive Refinement-Coarsening Scheme for Three-Dimensional Unstructured Meshes. AIAA Journal 31 (1993) 1140–1447Google Scholar
  11. 11.
    Mavriplis, D.J.: Three-Dimensional Multigrid for the Euler Equations. AIAA Paper 91-1549CP, American Institute of Aeronautics and Astronautics (1991) 824–831Google Scholar
  12. 12.
    Mathur, K.: Unstructured Three Dimensional Finite Element Simulations on Data Parallel Architectures. In: Mehrotra, P., Saltz, J., Voigt, R. (eds.): Unstructured Scientific Computation on Scalable Multiprocessors. MIT Press (1992) 65–79Google Scholar
  13. 13.
    McManus, K.: A Strategy for Mapping Unstructured Mesh Computational Mechanics Programs onto Distributed Memory Parallel Architectures. Ph.D. thesis, University of Greenwich (1996)Google Scholar
  14. 14.
    Mohammadi, B.: Fluid Dynamics Computations with NSC2KE — A User Guide. Technical Report RT-0164, INRIA (1994)Google Scholar
  15. 15.
    Mirchandaney, R., Saltz, J., Smith, R., Nicol, D., Crowley, K.: Principles of runtime support for parallel processors. Proc. 1988 ACM International Conference on Supercomputing (1988) 140–152Google Scholar
  16. 16.
    Ponnusamy, R., Hwang, Y.-S., Das, R., Saltz, J., Choudhary, A., Fox, G.: Supporting Irregular Distributions Using Data-Parallel Languages. IEEE Parallel and Distributed Technology 3 (1995) 12–14CrossRefGoogle Scholar
  17. 17.
    The Portland Group, Inc.: pghpf User’s Guide. Wilsonville, OR (1992)Google Scholar
  18. 18.
    Ponnusamy, R., Saltz, J., Das, R., Koelbel, Ch., Choudhary, A.: Embedding Data Mappers with Distributed Memory Machine Compilers ACM SIGPLAN Notices 28 (1993) 52–55CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Rainer Koppler
    • 1
  1. 1.Department of Computer Graphics and Parallel Processing (GUP)Johannes Kepler UniversityLinzAustria/Europe

Personalised recommendations