Abstract
An implementation of a real symmetric eigensolver on parallel nodes is described and evaluated. To achieve better performance in the inverse iteration part, a multi-color framework is introduced, in which the orders of the orthogonalizations are rescheduled so that the inverse iterations are executed concurrently. With the blocked tridiagonalization and backtransformation, our real symmetric eigensolver shows good performance and accuracy both on the MPP SR2201 and on the newly developed hybrid machine SR8000.
Chapter PDF
Keywords
- Speedup Rate
- Inverse Iteration
- Symmetric Eigenvalue Problem
- Computer Science Division
- Symmetric Tridiagonal Matrix
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
SR8000 HOMEPAGE: http://www.hitachi.co.jp/Prod/comp/hpc/eng/sr81e.html
J. J. Dongarra and R. A. van de Geijn: Reduction to condensed form for the Eigenvalue problem on distributed architectures, Parallel Computing Vol. 18, No. 9, pp. 973–982, 1992.
H. Y. Chang, S. Utku, M. Salama and D. Rapp: A parallel Householder tridiagonalization stratagem using scattered square decomposition, Parallel Computing Vol. 6, No. 3, pp. 297–311, 1988.
K. Naono, Y. Yamamoto, M. Igai, H. Hirayama: High performance implementation of tridiagonalization on the SR8000, Proceedings of the Fourth International Conference/Exhibition on High Performance Computing in Asia-Pacific Region (HPC-ASIA2000), Beijing, China, pp. 206–219, 2000.
J. Demmel, I. Dhillon, and H. Ren: On the correctness of some bisection-like parallel eigenvalue algorithms in floating point arithmetic, Electronic Trans. Numer. Anal. 3, 116–149, Dec. 1995.
J. Choi, J. Demmel, I. Dhillon, J. Dongarra, S. Ostrouchov, A. Petitet, K. Stanley, D. Walker, R.C. Whaley: LAPACK Working Note 95, ScaLAPACK: A Potable Linear Algebra Library for Distributed Memory Computers-Design Issues and Performance, 1995.
I. S. Dhillon: A New O(n2) Algorithm for the Symmetric Tridiagonal Eigenvalue/Eigenvector Problem, Ph.D. thesis, Computer Science Division, University of California, Berkeley, May 1997.
LAPACK: http://www.netlib.org/lapack
ScaLAPACK: http://www.netlib.org/scalapack
K. Naono, M. Igai, Y. Yamamoto: Development of a Parallel Eigensolver and its Evaluation, Proceedings of the Joint Symposium on Parallel Processing 1996, Waseda, Japan, pp9–16, 1996(in Japanese).
G. Peters and J.H. Wilkinson: The Calculation of Specified Eigenvectors by Inverse Iteration pp. 418–439, in book ‘Linear Algebra’ edited by J.H. Wilkinson and C. Reinsch, Springer-Verlag, 1971.
B. Parlett: The symmetric Eigenvalue Problem, Prentice Hall, Englewood Cliffs, NJ, 1980.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Naono, K., Yamamoto, Y., Igai, M., Hirayama, H., Ioki, N. (2000). A Multi-color Inverse Iteration for a High Performance Real Symmetric Eigensolver. In: Bode, A., Ludwig, T., Karl, W., Wismüller, R. (eds) Euro-Par 2000 Parallel Processing. Euro-Par 2000. Lecture Notes in Computer Science, vol 1900. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44520-X_70
Download citation
DOI: https://doi.org/10.1007/3-540-44520-X_70
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67956-1
Online ISBN: 978-3-540-44520-3
eBook Packages: Springer Book Archive