Advertisement

Heuristics for 1D rectilinear partitioning as a low cost and high quality answer to dynamic load balancing

  • Serge Miguet
  • Jean-Marc Pierson
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1225)

Abstract

Several algorithms have been proposed for computing the optimal rectilinear partitioning of data to a linear array of processors. We introduce two fully parallel heuristics that compute sub-optimal partitions, in a more efficient way than the best known optimal algorithm. The goal of this paper is to compare our heuristics to an optimal partitioning, both in terms of execution time and accuracy of the partition. We give some very interesting theoritical bounds on the quality of our heuristics and we report results on numerical experiments and real applications.

Keywords

Dynamic Load Balancing Rectilinear Partitioning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Shahid H. Bokhari. Partitioning Problems in Parallel, Pipelined, and Distributed Computing. IEEE Transactions on Computers, 37(1):48–57, January 1988.Google Scholar
  2. 2.
    Michelangelo Grigni and Fredrik Manne. On the Complexity of the Generalized Block Distribution. In Ferreira, Rolim, Saad, and Yang, editors, Parallel Algorithms for Irregularly Structured Problems, number 1117 in Lecture Notes in Computer Science, pages 319–326. Springer, Santa Barbara, CA, USA, aug 1996. Proceedings of IR-REGULAR96.Google Scholar
  3. 3.
    Serge Miguet and Jean-Marc Pierson. Dynamic load balancing in a parallel particle simulation. In Proceedings of HPCS'95, pages 420–431, Montréal, July 1995.Google Scholar
  4. 4.
    Serge Miguet and Jean-Marc Pierson. Heuristics for 1D rectilinear partitioning. In Denis Tristram and Jacques Chassin de Kergom-meaux, editors, Parallel Programming Environments for High Performance Computing, pages 111–115, Alpe d'Huez, April 1996. 2nd European School of Computer Science.Google Scholar
  5. 5.
    Serge Miguet and Yves Robert. Elastic load balancing for image processing algorithms. In H.P. Zima, editor, Parallel Computation, Lecture Notes in Computer Science, pages 438–451, Salzburg, Austria, September 1991. 1st International ACPC Conference, Springer Verlag.Google Scholar
  6. 6.
    Jean-Marc Nicod. Extraction de surfaces en imagerie médicale: approches paralèles. Thèse, Ecole Normale Supérieure de Lyon, January 1994.Google Scholar
  7. 7.
    D. M. Nicol. Rectilinear Partitioning of Irregular Data Parallel Computations. Journal of Parallel and Distributed Computing, 23:119–134, 1994.Google Scholar
  8. 8.
    Bjorn Olstad and Fredrik Manne. Efficient Partitioning of Sequences. IEEE Transactions on Computers, 44(11):1322–1326, nov 1995.Google Scholar
  9. 9.
    Jean-Marc Pierson. Equilibrage de charge dirigé par les données: applications à la synthèse d'images. Thèse, LIP-Ecole Normale Supérieure de Lyon, 46 allée d'Italie, 69364 Lyon cedex 07, France, october 1996.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Serge Miguet
    • 1
  • Jean-Marc Pierson
    • 2
  1. 1.Laboratoire E.R.I.C.Université Lumière Lyon 2Bron Cedex
  2. 2.Laboratoire LSIITUniversité Louis PasteurStrasbourg

Personalised recommendations