Abstract
The work reported upon here has been carried out within a project one aim of which is to construct, for execution on the Cray T3D, 1,2 efficient implementations of certain key routines selected from the Harwell Subroutine Library 3. A second aim of the project is to establish guidelines pertaining to the re-engineering of sequential software for parallel execution on the Cray T3D which can be drawn upon by others engaged in similar activity.
In this paper, a method for the eigensolution of real symmetric matrices is addressed. The algorithm and its parallel implementation are described in some detail. Results indicating the quality of performance of the parallel implementation are presented and some observations are made about the efficiency with which certain kernel operations of the implementation may be executed. Some guidelines are provided for applications programmers wishing to exploit distributed memory machines.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Cray Research MPP Software Guide,Cray Research Inc. (1993) order number SG-2508.
S.P. Booth, J. Fisher, P.H. MacCallum and A.D. Simpson. Introduction to the Cray T3D at EPCC, University of Edinburgh (1996).
Anon. Harwell Subroutine Library (Release 11) Theoretical Studies Dept. AEA Technology, Didcot, Oxfordshire (1993).
K. Murphy, M. Clint, R.H. Perrott, D. McLaughlin and I. Carberry, Re-engineering mathematical library software for execution on high performance computers, in: High Performance Computing 1997, Proceedings of the 1997 Simulation Multiconference, Atlanta, Georgia, A. Tentner ed., SCS, pp 207–212 (1997).
T.L. Freeman and C. Phillips. Parallel Numerical Algorithms, Prentice Hall (1992).
J.H. Wilkinson. The Algebraic Eigenvalue Problem, Clarendon Press, Oxford (1965).
J.H. Wilkinson and C. Reinsch. Handbook for Automatic Computation, Volume II, Linear Algebra,Springer-Verlag, Berlin (1971).
Message Passing Interface Forum, MPI: a message-passing interface standard (version 1.1), Revision of article to appear in the International Journal of Supercomputing Applications, 8(3/4), 157–416 (1994, June 1995).
D. Elwood, G. Fann and R. Littlefield. Parallel Eigensolver System User Manual, available from anonymous@ftp://pnl.gov.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer Science+Business Media New York
About this chapter
Cite this chapter
Murphy, K., Clint, M., Perrott, R.H. (1999). Solving Dense Symmetric Eigenproblems on the Cray T3D. In: Allan, R.J., Guest, M.F., Simpson, A.D., Henty, D.S., Nicole, D.A. (eds) High-Performance Computing. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-4873-7_8
Download citation
DOI: https://doi.org/10.1007/978-1-4615-4873-7_8
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7211-0
Online ISBN: 978-1-4615-4873-7
eBook Packages: Springer Book Archive