Parallel physical optimization algorithms for data mapping

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 634)


Parallel algorithms, based on simulated annealing, neural networks and genetic algorithms, for mapping irregular data to multicomputers are presented and compared. The three algorithms deviate from the sequential versions in order to achieve acceptable speed-ups. The parallel annealing and neural algorithms include communication schemes adapted to the properties of the mapping problem and of the algorithms themselves. These schemes arc found useful for providing both good solutions and reasonable execution times. The parallel genetic algorithm is based on a model of natural evolution. The three algorithms preserve the high quality solutions and the non-bias properties of their sequential counterparts. Further, the comparison results show their suitability for different requirements of mapping time and quality.


High Quality Solution Parallel Annealing Parallel Execution Time Sequential Genetic Algorithm Node Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    M. Berger and S. Bokhari: A partitioning strategy for nonuniform problems on multiprocessors. IEEE Trans. Comp., Vol C-36,No. 5, 1987, 570–580.Google Scholar
  2. 2.
    N.P. Chrisochoides, E.N. Houstis, and C.E. Houstis: Geometry based mapping strategies for PDE computations. Int. Conf. on Supercomputing, 115–127, ACM Press 1991.Google Scholar
  3. 3.
    F. Ercal: Heuristic approaches to task allocation for parallel computing. Doctoral Dissertation, Ohio State University, 1988.Google Scholar
  4. 4.
    G. C. Fox, S. Hiranandani, K. Kennedy, C. Koelbel, U. Kremer, C. Tseng, and M-Y. Wu: Fortran D language specification. Syracuse University, NPAC, SCCS-42, 1990.Google Scholar
  5. 5.
    G. C. Fox, M. Johnson, G. Lyzenga, S. Otto, J. Salmon, and D. Walker: Solving problems on concurrent processors. Prentice Hall 1988.Google Scholar
  6. 6.
    G. C. Fox and W. Furmanski: Load balancing loosely synchronous problems with a neural network. Proc 3rd Conf. Hypercube Concurrent Computers, and Applications, 1988, 241–278.Google Scholar
  7. 7.
    D. E. Goldberg: Genetic algorithms in search, optimization and machine learning. Addison-Wesley 1989.Google Scholar
  8. 8.
    J. Hopfield and D. Tank: Computing with neural circuits: a model. Science 233, 1986, 625–639.PubMedGoogle Scholar
  9. 9.
    S. Kirkpatrick, C. D. Gelatt, and M. P. Vecchi: Optimization by simulated annealing. Science 220, 1983, 671–680.Google Scholar
  10. 10.
    N. Mansour and G. C. Fox: A hybrid genetic algorithm for task allocation. Int. Conf. Genetic Algorithms, July 1991, 466–473.Google Scholar
  11. 11.
    N. Mansour and G. C. Fox: Allocating data to multicomputer nodes by physical optimization algorithms. To appear in Concurrency Practice and Experience.Google Scholar
  12. 12.
    N. Mansour and G.C. Fox: Parallel physical optimization algorithms for allocating data to multicomputer nodes. Syracuse University, NPAC, SCCS-305, 1992.Google Scholar
  13. 13.
    N. Mansour and G.C. Fox: For efficient mapping of large problems. In preparation.Google Scholar
  14. 14.
    H. Simon: Partitioning of unstructured mesh problems for parallel processing. Proc. Conf. Parallel Methods on Large Scale Structural Analysis and Physics Applications, Permagon 1991.Google Scholar
  15. 15.
    R. D. Williams: Performance of dynamic load balancing algorithms for unstructured mesh calculations. Concurrency Practice and Experience, 3(5), Oct. 1991, 457–481.Google Scholar
  16. 16.
    S. Wright Evolution and the genetics of populations. Vol. 3, Univ. of Chicago Press 1977.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  1. 1.Syracuse Ctr. for Computational Sc.USA
  2. 2.Beirut University CollegeLebanon
  3. 3.Northeast Parallel Architectures Ctr.Syracuse UniversitySyracuseUSA

Personalised recommendations