This title appears in the Scientific Report :
2012
Please use the identifier:
http://dx.doi.org/10.1016/j.amc.2012.05.020 in citations.
Solving dense generalized eigenproblems on multi-threaded architectures
Solving dense generalized eigenproblems on multi-threaded architectures
We compare two approaches to compute a fraction of the spectrum of dense symmetric definite generalized eigenproblems: one is based on the reduction to tridiagonal form, and the other on the Krylov-subspace iteration. Two large-scale applications, arising in molecular dynamics and material science,...
Saved in:
Personal Name(s): | Aliaga, J.I. |
---|---|
Bientinesi, P. / Davidovic, D. / Di Napoli, E. / Igual, F.D. / Quintana-Orti, E.S. | |
Contributing Institute: |
Jülich Supercomputing Center; JSC |
Published in: | Applied mathematics and computation, 218 (2012) S. 11279 - 11289 |
Imprint: |
New York, NY
Elsevier
2012
|
Physical Description: |
11279 - 11289 |
DOI: |
10.1016/j.amc.2012.05.020 |
Document Type: |
Journal Article |
Research Program: |
Simulation and Data Laboratory Quantum Materials (SDLQM) Computational Science and Mathematical Methods Scientific Computing |
Series Title: |
Applied Mathematics and Computation
218 |
Subject (ZB): | |
Publikationsportal JuSER |
We compare two approaches to compute a fraction of the spectrum of dense symmetric definite generalized eigenproblems: one is based on the reduction to tridiagonal form, and the other on the Krylov-subspace iteration. Two large-scale applications, arising in molecular dynamics and material science, are employed to investigate the contributions of the application, architecture, and parallelism of the method to the performance of the solvers. The experimental results on a state-of-the-art 8-core platform, equipped with a graphics processing unit (GPU), reveal that in realistic applications, iterative Krylov-subspace methods can be a competitive approach also for the solution of dense problems. (C) 2012 Elsevier Inc. All rights reserved. |