Advertisement

VLSI systems for matrix multiplication

  • Kam Hoi Cheng
  • Sartaj Sahni
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 206)

Abstract

We examine several VLSI architectures and compare these for their suitability for various forms of the matrix multiplication problem. The following architectures are considered: chain, broadcast chain, mesh, broadcast mesh and hexagonally connected. The forms of the matrix multiplication problem that are considered are: matrix × vector, band matrix × vector, matrix × matrix and band matrix × band matrix.

Keywords and Phrases

VLSI systems systolic systems matrix multiplication 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

7. References

  1. [CANN69]
    L. Cannon, A cellular computer to implement the Kalman filter algorithm, PhD Thesis, Montana State University, 1969.Google Scholar
  2. [CHENG84]
    K. Cheng and S. Sahni, VLSI architectures for matrix multiplication, University of Minnesota, Technical Report, 1984.Google Scholar
  3. [DEKE81]
    E. Dekel, D. Nassimi and S. Sahni, Parallel matrix and graph algorithms, SICOMP 1981, 10, 4, pp. 657–675.Google Scholar
  4. [FLYN76]
    M. Flynn and R. Kosaraju, Processes and their interactions, Kybernetics, 5, 1976, pp. 159–163.Google Scholar
  5. [HORO79]
    E. Horowitz, VLSI architectures for matrix computations, IEEE International Conference On Parallel Processing, 1979, pp. 124–127.Google Scholar
  6. [HUAN82]
    K.H. Huang and J.A. Abraham, Efficient parallel algorithms for processor arrays, IEEE International Conference On Parallel Processing, 1982, pp. 271–279.Google Scholar
  7. [JOHN81a]
    L. Johnsson and D. Cohen, A mathematical approach to modeling the flow of data and control in computational networks, in VLSI Systems and Computations, Kung et al. editors, Computer Science Press, 1981, pp. 213–225.Google Scholar
  8. [JOHN81b]
    L. Johnsson, D. Cohen, U. Weiser and A. Davis, Towards a formal treatment of VLSI arrays, CALTECH Conference on VLSI, 1981, pp. 375–398.Google Scholar
  9. [KUNG78]
    H.T. Kung and C.E. Leiserson, Systolic arrays for VLSI, Department of Computer Science, Carnegie-Mellon University, April 1978.Google Scholar
  10. [KUNG79]
    H.T. Kung, Let's design algorithms for VLSI systems, Proceedings CALTECH Conference on VLSI, Jan. 1979, pp. 65–90.Google Scholar
  11. [KUNG83a]
    H.T. Kung, A Listing of Systolic Papers, Department of Computer Science, Carnegie-Mellon University, May 1984.Google Scholar
  12. [KUNG83b]
    H.T. Kung and W.T. Lin, An algebra for VLSI algorithm design, Carnegie-Mellon University, Technical report, April 1983.Google Scholar
  13. [KUNG83c]
    H.T. Kung, A. Nowatzyk, M. Ravisharkar, The Universal Host: Architectures and System configuration, Carnegie-Mellon University, Technical report, October 1983.Google Scholar
  14. [LEIS83]
    C.E. Leiserson, Area-Efficient VLSI Computation, MIT Press, 1983.Google Scholar
  15. [MELH84]
    R. Melhem and W. Rheinboldt, A mathematical model for the verification of systolic networks, SIAM J. Comput., 1984, 13, 3, pp. 541–565.CrossRefGoogle Scholar
  16. [PRIE81]
    R.W. Priester, H.J. Whitehouse, K. Bromley and J.B. Clary, Signal Processing With Systolic Arrays, IEEE International Conference on Parallel Processing, 1981, pp. 207–215.Google Scholar
  17. [VANS76]
    F. Van Scoy, Parallel algorithms in cellular spaces, PhD thesis, University of Virginia, 1976.Google Scholar
  18. [WEIS81]
    U. Weiser and Al Davis, A Wavefront notation tool for VLSI array design, in VLSI Systems and Computations, Kung et al. editors, Computer Science Press, 1981, pp. 226–234.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1985

Authors and Affiliations

  • Kam Hoi Cheng
    • 1
  • Sartaj Sahni
    • 1
  1. 1.University of MinnesotaUSA

Personalised recommendations