Session H2: Evaluation of parallel system
Performance evaluation of transputer systems with linear algebra problems

https://doi.org/10.1016/0165-6074(91)90444-XGet rights and content

Abstract

In this paper we evaluate the performance of a Supernode (Transputer-based system) with some linear algebra problems. The Supernode has been evaluated as a linear multicomputer and as a mesh multicomputer. All the used parallel algorithms have been designed following the same strategy. We describe the design strategy with an example for LU decomposition. Finally, we evaluate two different programming models.

References (9)

  • C. Moler

    Matrix Computation on Distributed Memory Multiprocessors

    Hypercube Multiprocessors

    (1986)
  • G.A. Geist et al.

    Parallel Algorithms for Matrix Computations

  • Parsys Ltd.

    Hardware Reference for the Parsys SN100C Series

    (September 1989)
  • M. Homewood et al.

    The IMS T800 Transputer

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

Cited by (0)

View full text