Elsevier

Parallel Computing

Volume 22, Issue 12, February 1997, Pages 1563-1578
Parallel Computing

Paper
Parallel matrix product algorithm in the de Bruijn network using emulation of meshes of trees

https://doi.org/10.1016/S0167-8191(96)00064-6Get rights and content

Abstract

We present an algorithm computing the product of two square matrices in the de Bruijn network by using emulation: the algorithm is based on a [(d − 1)2]-embedding of meshes of d-ary trees into de Bruijn graphs and also on a mapping of particular trees.

References (20)

  • P. Fraigniaud et al.

    Methods and problems of communication in usual networks

    Discrete Appl. Math.

    (1994)
  • D. Barth

    Embedding meshes of d-ary trees into de Bruijn graphs

    Parallel Process. Lett.

    (1994)
  • D. Barth

    Réseaux d'interconnexion: Structures et communications

  • C. Berge
  • J.C. Bermond et al.

    Communications in interconnection networks

  • J.C. Bermond et al.

    De Bruijn and Kautz network: A competitor for the Hypercube?

  • J. Bernsten

    Communication efficient matrix multiplication on hypercubes

    Parallel Computing

    (1989)
  • S. Bettayeb et al.

    Embedding grids into hypercube

  • C. Calvin et al.

    Matrix transpose for block allocations on torus and de Bruijn networks

    J. Parallel Distributed Computing

    (1996)
  • L.E. Cannon

    A cellular computer to implement the Kalman filter algorithm

There are more references available in the full text version of this article.

This work was supported by the “Opération RUMEUR” of the French PRC PRS.

View full text