Skip to main content

"Non-numerical aspects of computations on parallel hardware"

  • Systematic Design, Development, And Verification Of Parallel Algorithms
  • Conference paper
  • First Online:
  • 113 Accesses

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 111))

Abstract

The organization and interaction of data is important for both the natural expression and efficient execution of parallel computation. A set of basic non-numerical operations is outlined which is readily implemented on single instruction stream multiple data stream (SIMD) computers; the relevance of this to parallel processing is illustrated in a number of algorithms.

The problem of matching computations with parallel hardware is also discussed briefly from the point of view of the specification of data mapping. This gives greater insight into the efficient solution of certain problems on an array processor.

Finally some algorithms directly concerned with reorganizing data are considered in the context of the above ideas.

This is a preview of subscription content, log in via an institution.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. P.M. Flanders, "Fortran extensions for a highly parallel processor", Infotech State of the Art Report on Supercomputers, 1979.

    Google Scholar 

  2. DAP: FORTRAN Language — International Computers Ltd TP 6918.

    Google Scholar 

  3. S.R. House, "Compiling in Parallel", in these proceedings.

    Google Scholar 

  4. D.J. Hunt, "Application techniques for parallel hardware", Infotech State of the Art Report on Supercomputers, 1979.

    Google Scholar 

  5. R.W. Gostick, "Software and algorithms for the Distributed Array Processor", ICL Tech. J., Vol. 1, Issue 2, May 1979.

    Google Scholar 

  6. P.M. Flanders, D.J. Hunt, D. Parkinson, S.F. Reddaway, "Efficient high speed computing with the Distributed Array Processor", Symposium on High Speed Computer and Algorithm Organization, University of Illinois, 1977, Academic Press.

    Google Scholar 

  7. P. Marks, "Low-level vision using an array processor", Computer Graphics and Image Processing 14, 281–292 (1980).

    Article  Google Scholar 

  8. P.M. Flanders, "Musical bits — A generalised method for a class of data movements on the DAP", ICL, RADC CM70.

    Google Scholar 

  9. C.R. Jesshope, "Data routing and transpositions in processor arrays", ICL Tech. J., Vol. 2, Issue 2, Nov. 1980.

    Google Scholar 

  10. D.E. Knuth, "The art of computer programming, Vol. 3: Sorting and searching", Addison Wesley, 1973.

    Google Scholar 

  11. P.M. Flanders, S.F. Reddaway, "Sorting on DAP", ICL, RADC, CM72, to be produced.

    Google Scholar 

  12. D.J. Stanley, P.S. Redstone, "High throughput image preprocessing systems for earth resources imagery", Proceedings of the 3rd British Interplanetary Society computer and space technology conference, — "Image processing techniques applied to astronomy and space research", 1979.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

W. Brauer P. Brinch Hansen D. Gries C. Moler G. Seegmüller J. Stoer N. Wirth Wolfgang Händler

Rights and permissions

Reprints and permissions

Copyright information

© 1981 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Flanders, P.M. (1981). "Non-numerical aspects of computations on parallel hardware". In: Brauer, W., et al. Conpar 81. CONPAR 1981. Lecture Notes in Computer Science, vol 111. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0105125

Download citation

  • DOI: https://doi.org/10.1007/BFb0105125

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-10827-6

  • Online ISBN: 978-3-540-38715-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics