Advertisement

Reduction operators in Alpha

  • H. Le Verge
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 605)

Abstract

This paper introduces reduction operators of Alpha. Alpha is the basis of the environment Alpha du Centaur, whose purpose is the design of systolic or more generally, regular arrays. Algorithms are transformed under the control of the designer, using a set of automated rewriting rules, to produce a new version in which all informations for regular array synthesizers or code generators can be easily extracted. The reduction operator is defined on unordered polyhedral convex sets, rather than on unidimensional or ordered sets as usually. Basic properties of this operator are presented and their use for the derivation of systolic algorithms are described.

Keywords

Parallel Languages extensions Programming environments for parallel languages Systolic arrays and regular computation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    M. Chen, Y.I. Choo, and J. Li. Compiling parallel programs by optimizing performance. The Journal of Supercomputing, 2, 1988.Google Scholar
  2. [2]
    P. Gachet, C. Mauras, P. Quinton, and Y. Saouter. Alpha du Centaur: an environment for the design of regular algorithms. In 1989 International Conference on Supercomputing, Crete, Greece, June 1989.Google Scholar
  3. [3]
    P. Gachet, C. Mauras, P. Quinton, and Y. Saouter. A language for the design of regular parallel algorithms. In First European Workshop on Hypercube and Distributed Computers, pages 189–202, North-Holland, Rennes, France, October 1989.Google Scholar
  4. [4]
    G. Jones and M. Sheeran. Circuit design in ruby. In J. Staunstrup, editor, Formal Methods for VLSI Design, pages 13–70, IFIP, Elsevier Science Publishers B.V. (North-Holland), 1990.Google Scholar
  5. [5]
    R.M. Karp, R.E. Miller, and S. Winograd. The organization of computations for uniform recurrence equations. Journal of the Association for Computing Machinery, 14(3):563–590, July 1967.Google Scholar
  6. [6]
    C.E. Leiserson, F.M. Rose, and J.B. Saxe. ”Optimizing synchronous circuitry by retiming,” Proc. Third Caltech Conf. on VLSI, R. Bryant Ed. (1983), 87–116.Google Scholar
  7. [7]
    H. Leverge, C. Mauras, and P. Quinton. A language-oriented approach to the design of systolic chips. In International Workshop on Algorithms and Parallel VLSI Architectures, Pont-à-Mousson, June 1990. Journal of VLSI Signal Processing, 1991.Google Scholar
  8. [8]
    C. Mauras. Alpha: un langage équationnel pour la conception et la programmation d'architectures parallèles synchrones. Thèse de l'Université de Rennes 1, IFSIC, Décembre 1989.Google Scholar
  9. [9]
    G. L. Nemhauser and L. A. Wolsey. Integer and Combinatorial Optimization. Wiley-Interscience series in Discrete Mathematics and Optimization, John Wiley and Sons, 1988.Google Scholar
  10. [10]
    P. Quinton and Y. Robert. Algorithmes et architectures systoliques.Masson, 1989. English translation by Prentice Hall, Systolic Algorithms and Architectures, Sept. 1991.Google Scholar
  11. [11]
    Roychowhdury. Derivation, extensions and Parallel Implementation of Regular Iterative Algorithms. PhD thesis, Stanford University, December 1988.Google Scholar
  12. [12]
    A. Schrijver. Theory of Linear and Integer Programming. Wiley-Interscience series in Discrete Mathematics, John Wiley and Sons, 1986.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • H. Le Verge
    • 1
  1. 1.IRISARennes CedexFrance

Personalised recommendations