A parallel algorithm for the non-symmetric eigenvalue problem
An algorithm is presented for the solution of the non-symmetric eigenvalue problem. The algorithm is based on a divide-and-conquer procedure that provides initial approximations to the eigenpairs, which are then refined using Newton iterations. Since the smaller subproblems can be solved independently, and since Newton iterations with different initial guesses can be started simultaneously, the algorithm - unlike the standard QR method - is ideal for parallel computers. The author also reports on his investigation of deflation methods designed to obtain further eigenpairs if needed. Numerical results from implementations on a host of parallel machines (distributed and shared-memory) are presented.
- Research Organization:
- Tennessee Univ., Knoxville, TN (United States)
- OSTI ID:
- 7158562
- Country of Publication:
- United States
- Language:
- English
Similar Records
A parallel algorithm for the non-symmetric eigenvalue problem
A parallel divide and conquer algorithm for the symmetric eigenvalue problem on distributed memory architectures