A case against a divide and conquer approach to the nonsymmetric eigenvalue problem
Divide and conquer techniques based on rank-one updating have proven fast, accurate, and efficient in parallel for the real symmetric tridiagonal and unitary eigenvalue problems and for the bidiagonal singular value problem. Although the divide and conquer mechanism can also be adapted to the real nonsymmetric eigenproblem in a straightforward way, most of the desirable characteristics of the other algorithms are lost. In this paper, we examine the problems of accuracy and efficiency that can stand in the way of a nonsymmetric divide and conquer eigensolver based on low-rank updating. 31 refs., 2 figs.
- Research Organization:
- Oak Ridge National Lab., TN (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States); National Science Foundation, Washington, DC (United States)
- DOE Contract Number:
- AC05-84OR21400
- OSTI ID:
- 10108206
- Report Number(s):
- ORNL/TM--11903; ON: DE92004086; CNN: Grant CCR-9109785
- Country of Publication:
- United States
- Language:
- English
Similar Records
A case against a divide and conquer approach to the nonsymmetric eigenvalue problem
A divide and conquer approach to the nonsymmetric eigenvalue problem
A parallel divide and conquer algorithm for the symmetric eigenvalue problem on distributed memory architectures
Technical Report
·
Sat Nov 30 23:00:00 EST 1991
·
OSTI ID:5926172
A divide and conquer approach to the nonsymmetric eigenvalue problem
Conference
·
Mon Dec 31 23:00:00 EST 1990
·
OSTI ID:5903287
A parallel divide and conquer algorithm for the symmetric eigenvalue problem on distributed memory architectures
Journal Article
·
Thu Jul 01 00:00:00 EDT 1999
· SIAM Journal on Scientific Computing
·
OSTI ID:20005552