Optimization and performance evaluation of the IDR iterative Krylov solver on GPUs

Journal article


Publication Details

Author(s): Anzt H, Kreutzer M, Ponce E, Peterson GD, Wellein G, Dongarra J
Journal: International Journal of High Performance Computing Applications
Publisher: SAGE PUBLICATIONS LTD
Publication year: 2018
Volume: 32
Journal issue: 2
Pages range: 220-230
ISSN: 1094-3420


Abstract

In this paper, we present an optimized GPU implementation for the induced dimension reduction algorithm. We improve data locality, combine it with an efficient sparse matrix vector kernel, and investigate the potential of overlapping computation with communication as well as the possibility of concurrent kernel execution. A comprehensive performance evaluation is conducted using a suitable performance model. The analysis reveals efficiency of up to 90%, which indicates that the implementation achieves performance close to the theoretically attainable bound.


FAU Authors / FAU Editors

Kreutzer, Moritz
Professur für Höchstleistungsrechnen
Wellein, Gerhard Prof. Dr.
Professur für Höchstleistungsrechnen


External institutions with authors

Oak Ridge National Laboratory


Research Fields

Performance Engineering
Professur für Höchstleistungsrechnen
Hardwareeffiziente Bausteine für dünn besetzte lineare Algebra und stencil-basierten Verfahren
Professur für Höchstleistungsrechnen


How to cite

APA:
Anzt, H., Kreutzer, M., Ponce, E., Peterson, G.D., Wellein, G., & Dongarra, J. (2018). Optimization and performance evaluation of the IDR iterative Krylov solver on GPUs. International Journal of High Performance Computing Applications, 32(2), 220-230. https://dx.doi.org/10.1177/1094342016646844

MLA:
Anzt, Hartwig, et al. "Optimization and performance evaluation of the IDR iterative Krylov solver on GPUs." International Journal of High Performance Computing Applications 32.2 (2018): 220-230.

BibTeX: 

Last updated on 2019-11-04 at 15:10