|
|
Digital Library of the
European Council for Modelling and Simulation |
|
Title: |
Towards
Ad-Hoc GPU Acceleration Of Parallel Eigensystem
Computations |
|
Authors: |
Michael T. Garba, Horacio González–Vélez |
|
Published in:
|
(2011).ECMS
2011 Proceedings edited by: T. Burczynski, J. Kolodziej, A. Byrski, M. Carvalho. European Council for Modeling and Simulation. doi:10.7148/2011 ISBN:
978-0-9564944-2-9 25th
European Conference on Modelling and Simulation, Jubilee Conference Krakow,
June 7-10, 2011
|
|
Citation
format: |
Garba, M. T., & Gonzalez-Velez, H.
(2011). Towards Ad-Hoc GPU Acceleration Of Parallel Eigensystem
Computations. ECMS 2011 Proceedings edited by: T. Burczynski,
J. Kolodziej, A. Byrski, M. Carvalho (pp. 534-538).
European Council for Modeling and Simulation. doi:10.7148/2011-0534-0538 |
|
DOI: |
http://dx.doi.org/10.7148/2011-0534-0538 |
|
Abstract: |
This
paper explores the early implementation of high- performance routines for the
solution of multiple large Hermitian eigenvector
and eigenvalue systems on a Graphics Processing
Unit (GPU). We report a perfor- mance
increase of up to two orders of magnitude over the original EISPACK routines with a NVIDIA Tesla C2050 GPU, potentially
allowing an order of magnitude in- crease in the complexity or resolution of
a neutron scat- tering modeling application. |
|
Full
text: |
|
