Sparse matrix calculations on the CRAY-2

https://doi.org/10.1016/0167-8191(87)90006-8Get rights and content

Abstract

The CRAY-2 is sometimes viewed as a CRAY-1 with a faster cycle time. We show that this viewpoint is not completely appropriate by describing some of the important architectural differences between the machines and indicating how they can be used to facilitate numerical calculations.

We have been testing kernels and codes on a CRAY-2 prior to the delivery of a machine to Harwell in 1987 and report some results on the solution of sparse equations which indicate that high efficiency can be obtained. We give details of one of the techniques for attaining this performance.

We also comment on the use of parallelism in the solution of sparse linear equations on the CRAY-2.

References (15)

  • J.J Dongarra et al.

    Squeezing the most out of eigenvalue solvers on high-performance computers

    Linear Algebra Appl.

    (1986)
  • I.S Duff

    Parallel implementation of multifrontal schemes

    Parallel Comput.

    (1986)
  • D.A Calahan

    Block-oriented, local-memory-based linear equation solution on the CRAY-2: uniprocessor algorithms

  • Cray

    Introducing the CRAY-2 computer system

    CRAY Channels

    (Summer 1985)
  • J.J Dongarra et al.

    A proposal for an extended set of Fortran Basic Linear Algebra Subprograms

  • J.J Dongarra et al.

    Performance of vector computers for direct and indirect addressing in Fortran

    Harwell Report

    (1987)
  • J.J Dongarra et al.

    Squeezing the most of an algorithm in CRAY Fortran

    ACM Trans. Math. Software

    (1984)
There are more references available in the full text version of this article.

Cited by (0)

© United Kingdom Atomic Energy Authority.

View full text