Design of a meta-parallelizer for large scientific applications

  • Jean-Yves Berthou
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 854)


The ”classical parallelizers” integrate more and more sophisticated and costly parallelization techniques. As a result, they are limited by the size of the program they are able to compile and are not well suited to parallelize real scientific programs whose parallelism detection complexity may differ very much from one code fragment to another.

The goal of our work is the construction of a meta-parallelizer for shared memory MIMD machines, LPARAD (Large applications, PARallelizer, ADaptative), able to efficiently parallelize large scientific programs with minimum help from the user in a minimal time. The implementation of LPARAD within the scope of the PAF [PAF90] project validates our approach.


automatic parallelization meta-parallelizer adaptative and interactive parallelization performance measures subprograms inlining 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [ABC+87]
    F. Allen, M. Burke, P. Charles, R. Cytron, and J. Ferrante. An overview of the ptran analysis system for multiprocessing. Technical Report RC 13115 (#56866), New-York, September 1987.Google Scholar
  2. [Ber93]
    Jean-Yves Berthou. Construction d'un paralléliseur interactif de logiciels scientifiques de grande taille guídé par des mesures de performances. PhD thesis, Université P. et M. Curie, October 1993.Google Scholar
  3. [BK92]
    Jean-Yves Berthou and Philippe Klein. Estimating the effective performance of program parallelization on shared memory mimd multiprocessors. In Parallel Processing: CONPAR 92 — VAPP V, pages 701–706. Springer Verlag, 1992.Google Scholar
  4. [Col94]
    J.-F. Collard. Space-time transformation of while-loops using speculative execution. In Proc. of the 1994 Scalable High Performance Conputing Conf., Knoxville, Tenn., May 1994. To appear. Also available as LIP Report 93-38.Google Scholar
  5. [Dum92]
    Alain Dumay. Traitement des Indexations non linéaires en parallélisation automatique: une méthode de linéarisation contextuelle. PhD thesis, Université P. et M. Curie, December 1992.Google Scholar
  6. [Ema92]
    Nahid Emad. Détection de parallélisme à l'aide de paralléliseurs automatiques. Technical Report MASI 92-54, Institut Blaise Pascal, September 1992.Google Scholar
  7. [Fah93]
    T. Fahringer. Automatic Performance Prediction for Parallel Programs on Massively Parallel Computers. PhD thesis, Dept of Comp. Science., University of Vienna, November 1993.Google Scholar
  8. [Fea88]
    Paul Feautrier. Parametric integer programming. RAIRO Recherche Opérationnelle, 22:243–268, September 1988.Google Scholar
  9. [FH92]
    T. Fahringer and C. Huber. The weight finder, a profiler for fortran 77 programs. user manual. Technical report, Dept of Comp. Science., University of Vienna, September 1992.Google Scholar
  10. [IJT90]
    François Irigoin, Pierre Jouvelot, and Rémi Triolet. Overview of the pips project. In Paul Feautrier and François Irigoin, editors, Procs of the Int. Workshop on Compiler for Parallel Computers, Paris, pages 199–212, December 1990.Google Scholar
  11. [Pac86]
    Pacific Sierra Research Corporation. Vast2 Reference Manual, 1986.Google Scholar
  12. [PAF90]
    Manuel de référence de paf. Groupe “Calcul Parallèle” du MASI, January 1990. available on request from Paul Feautrier.Google Scholar
  13. [Pug91]
    William Pugh. Uniform techniques for loop optimization. ACM Conf. on Supercomputing, pages 341–352, January 1991.Google Scholar
  14. [Red92]
    Xavier Redon. Détection des réductions. Technical Report 92.52, IBP/MASI, September 1992.Google Scholar
  15. [RWF90]
    Mourad Raji-Werth and Paul Feautrier. Systematic construction of programs for distributed memory systems. In Paul Feautrier and François Irigoin, editors, Procs of the Int. Workshop on Compiler for Parallel Computers, Paris, December 1990.Google Scholar
  16. [TIF86]
    Rémi Triolet, François Irigoin, and Paul Feautrier. Direct parallization of call statements. In ACM Symposium on Compiler Construction, 1986.Google Scholar
  17. [Win92]
    D. Windheiser. Optimisation de la localité des données et du parallélisme à grain fin. PhD thesis, Rennes I, 1992.Google Scholar
  18. [WL91]
    M. E. Wolf and M. S. Lam. A loop transformation theory and an algorithm to maximize parallelism. Transactions on Parallel and Distributed Systems, 2(4), pages 452–470, October 1991.Google Scholar
  19. [Wol87]
    M. Wolfe. Iteration space tiling for memory hierarchies. In Parallel Processing for Scientific Computing, pages 357–361. SIAM, 1987.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Jean-Yves Berthou
    • 1
    • 2
  1. 1.Domaine de Voluceau-RocquencourtInstitut National de Recherche en Informatique et en AutomatiqueUSA
  2. 2.Laboratoire PRiSMUniversité de VersaillesSt Quentin

Personalised recommendations