Matrix computations on an associative processor

  • P. A. Gilmore
Session 8: Computation Algorithms
Part of the Lecture Notes in Computer Science book series (LNCS, volume 24)


Stationary iterative techniques for solving systems of linear equations are reviewed, and an accelerated form of the Point-Jacobi method (referred to as parallel relaxation) is developed. Associative processors are introduced, and operational characteristics are described. The parallel relaxation method is structured for parallel execution on an associative processor, and parallel and sequential computational requirements are compared. The comparison shows a potential advantage for parallel execution which increases with the size of the system of equations. The results are extended to arbitrary stationary iterative techniques, and a practical parallel approach to SOR suggested.

Key Words and Phrases

Parallel processors associative processors parallel execution linear equations stationary iteration iterative techniques 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    R.S. Varga, "Matrix Iterative Analysis," Prentice-Hall, Inc., Englewood Cliffs, N.J., (1962).Google Scholar
  2. [2]
    E.L. Wachspress, "Iterative Solution of Elliptic Systems", Prentice-Hall Inc. Englewood Cliffs, N.J. (1960).Google Scholar
  3. [3]
    G. Forsyth, and W. Wasow, "Finite Difference Methods for Partial Differential Equations," John Wiley and Sons, New York, N.Y., (1960).Google Scholar
  4. [4]
    John Holland, "A Universal Computer Capable of Executing an Arbitrary Number of Subprograms Simultaneously," Eastern Joint Computer Conference (1959).Google Scholar
  5. [5]
    D.L. Slotnick, "The Fastest Computer," Scientific American, vol. 224, No. 2, (February 1971).Google Scholar
  6. [6]
    K.E. Batcher, "Sorting Networks and Their Application," Proceedings of the Spring Joint Computer Conference, (1968).Google Scholar
  7. [7]
    H.S. Stone, "Parallel Processing with the Perfect Shuffle," IEEE Trans. on Computers, C-20, No. 2, (February 1971).Google Scholar
  8. [8]
    J.A. Rudolph, "STARAN, A Production Implementation of an Associative Array Processor," Proc. of the 1972 Fall Joint Computer Conference.Google Scholar
  9. [9]
    GER-15636A, "STARAN Reference Manual," Goodyear Aerospace Corporation, Akron, Ohio, (September 1973).Google Scholar
  10. [10]
    P.A. Gilmore, "Structuring of Parallel Algorithms," J. of ACM, 15, No. 2 (April 1968).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1975

Authors and Affiliations

  • P. A. Gilmore
    • 1
  1. 1.Goodyear Aerospace CorporationAkron

Personalised recommendations