Advertisement

Explicit expression of multidimensional data parallelism

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 605)

Abstract

The vector/array processor system was the general model for most early supercomputers. In order to utilize the power of these new vector/array machines, statements were added to FORTRAN or other languages to specify data parallelism. In these extensions, language constructs extended for data parallelism are only considered for vector operations, that is, only for one-dimensional data parallelism. However, many elementary numerical algorithms contain not only one-dimensional but also two-dimensional data parallelism. Parallel architectures are also developed to support two-dimensional data parallelism. This paper will present an approach to express multidimensional data parallelism in a high-level language and will show that program constructs in the approach are concise and orthogonal.

Keywords

Aliasing 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    H. Bi: Exploiting Two-dimensional Explicit Parallelism on Vector Architectures. PhD Thesis, Technical University of Berlin, April 1991.Google Scholar
  2. 2.
    A. Böttcher: STARLET-II System Description & Programming Reference, presented at the GMD-First seminar “Pope and STARLET-II: Two Innovative Parallel Architecture”, Oct. 2, 1990, Berlin.Google Scholar
  3. 3.
    American National Standards Institute: FORTRAN-8x, Feb. 1987.Google Scholar
  4. 4.
    Burroughs Scientific Processor — implementation of FORTRAN Burroughs document 61391E, 1977.Google Scholar
  5. 5.
    W. K. Giloi and H. K. Berg: Introducing the Concept of Data Structure Architecture, Proc. 1977 Int. Conference on Parallel Processing, IEEE Catelog No. 77CH1253-4C, pp. 44–51.Google Scholar
  6. 6.
    W. K. Giloi and R. Güth: Concepts and Realization of a High-Performance Data Type Architecture, Int. Journal of Computer and Information Sciences 11, Jan. 1982, pp. 25–54.CrossRefGoogle Scholar
  7. 7.
    W. K. Giloi: Data Structure Architectures and Its Application, in “Berichte der Deutsch-Chinesischen Elektronik Woche in Peking 1987”, Teil 4, Data Processing. VDE vertag, offenbach, 1987.Google Scholar
  8. 8.
    M. D. Guzzi, et al.: Ceder FORTRAN* and other Vector and Parallel FORTRAN Dialects, The Journal of Supercomputing, 3, 1990, pp. 37–62.CrossRefGoogle Scholar
  9. 9.
    R. Hockney and C. Jesshope: Parallel Computers, Adm Hilger Ltd., Bristol, 1981.Google Scholar
  10. 10.
    G. Paul and M. W. Wilson: The VECTRAN language: an experiment language for vector/matrix array processing, IBM Research Rep., 1975.Google Scholar
  11. 11.
    R. H. Perrott, D. Crookes and P. Milligan: The Programming Language ACTUS, Software-Practice and Experience, Vol. 13, 1983, pp. 305–322.Google Scholar
  12. 12.
    R. H. Perrott: Parallel Programming, Addison-Wesley Publishing Company, 1987.Google Scholar

Copyright information

© Springer-Verlag 1992

Authors and Affiliations

  • Hua Bi
    • 1
  1. 1.GMD-TUB Research Center for Innovative Computer Systems and TechnologyBerlin 12Germany

Personalised recommendations