Evaluation of cube and data manipulator networks☆

https://doi.org/10.1016/0743-7315(85)90039-5Get rights and content

Abstract

The interconnection of a large number of processors and other devices to form a parallel/distributed computing system is a research area receiving a great deal of attention. One method is to use a multistage network. This paper compares two classes of multistage networks by examining two representative networks: the Generalized Cube and the Augmented Data Manipulator. The two topologies are compared using a graph model. By interpreting the graphical representations of the networks in different ways, different but functionally equivalent implementations result. The costs of the various implementations are compared taking VLSI considerations into account. Finally, the robustness (fault tolerance) of the different networks is measured and contrasted.

References (49)

  • G.B. Adams et al.

    On the number of permutations performable by the augmented data manipulator network

    IEEE Trans. Comput.

    (Apr. 1982)
  • G.B. Adams et al.

    The extra stage cube: A fault-tolerant interconnection network for supersystems

    IEEE Trans. Comput.

    (May 1982)
  • G.B. Adams et al.

    The use of 4 x 4 switching elements in the multistage cube networks

  • D.P. Agrawal

    Testing and fault-tolerance of multistage interconnection networks

    Computer

    (Apr. 1982)
  • D.P. Agrawal

    Graph theoretical analysis and design of multistage interconnection networks

    IEEE Trans. Comput.

    (July 1983)
  • G.A. Anderson et al.

    Computer interconnection structures: Taxonomy, characteristics, and examples

    ACM Comput. Surveys

    (Dec. 1975)
  • G.H. Barnes et al.

    Design and validation of a connection network for many-processor multiprocessor systems

    Computer

    (Dec. 1981)
  • K.E. Batcher

    STARAN parallel processor system hardware

  • K.E. Batcher

    The flip network in STARAN

  • F. Briggs et al.

    PUMPS architecture for pattern analysis and image data-base management

    IEEE Trans. Comput.

    (Oct. 1982)
  • L. Ciminiera et al.

    Modular interconnection networks with asynchronous control

  • L. Ciminiera et al.

    A fault-tolerant connecting network for multiprocessor systems

  • A.M. Despain et al.

    X-tree: A tree structured multi-processor computer architecture

  • D.M. Dias et al.

    Analysis and simulation of buffered delta networks

    IEEE Trans. Comput.

    (Apr. 1981)
  • T. Feng

    Data manipulating functions in parallel processors and their implementations

    IEEE Trans. Comput.

    (Mar. 1974)
  • T. Feng

    A survey of interconnection networks

    Computer

    (Dec. 1981)
  • T. Feng et al.

    Fault-diagnosis for a class of multistage interconnection networks

    IEEE Trans. Comput.

    (Oct. 1981)
  • M.J. Flynn

    Very high-speed computing systems

  • L.R. Goke et al.

    Banyan networks for partitioning multiprocessor systems

  • R.M. Jenevein et al.

    A control processor for a reconfigurable array computer

  • T. Lang et al.

    A shuffle-exchange network with simplified control

    IEEE Trans. Comput.

    (Jan. 1976)
  • D.H. Lawrie

    Access and alignment of data in an array processor

    IEEE Trans. Comput.

    (Dec. 1975)
  • M. Malek et al.

    A description method of interconnection networks

    IEEE Tech. Committee Distrib. Process. Quart.

    (Feb. 1981)
  • W.C. McDonald et al.

    The advanced data processing test bed

    • Cited by (6)

    ☆

    This work was supported by the United States Army Research Office, Department of the Army, under Grant DAAG29-82-K-0101; the National Science Foundation under Grant ECS 80-I6580; and the Air Force Office of Scientific Research, Air Force Systems Commands, USAF, under Grant AFOSR-78-3581. The U.S. Government's right to retain a nonexclusive royalty-free license in and to this paper, for governmental purposes, is acknowledged.

    View full text
    Copyright © 1985 Published by Elsevier Inc.