Performance Engineering of the Kernel Polynomal Method on Large-Scale CPU-GPU Systems

Kreutzer M, Hager G, Wellein G, Alvermann A, Fehske H, Pieper A (2015)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2015

Pages Range: 417-426

Conference Proceedings Title: Proceedings of the 2015 IEEE International Parallel and Distributed Processing Symposium (IPDPS)

Event location: Hyderabad, India IN

URI: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7161530

DOI: 10.1109/IPDPS.2015.76

Abstract

The Kernel Polynomial Method (KPM) is a well-established scheme in quantum physics and quantum chemistry to determine the eigenvalue density and spectral properties of large sparse matrices. In this work we demonstrate the high optimization potential and feasibility of peta-scale heterogeneous CPU-GPU implementations of the KPM. At the node level we show that it is possible to decouple the sparse matrix problem posed by KPM from main memory bandwidth both on CPU and GPU. To alleviate the effects of scattered data access we combine loosely coupled outer iterations with tightly coupled block sparse matrix multiple vector operations, which enables pure data streaming. All optimizations are guided by a performance analysis and modelling process that indicates how the computational bottlenecks change with each optimization step. Finally we use the optimized node-level KPM with a hybrid-parallel framework to perform large scale heterogeneous electronic structure calculations for novel topological materials on a petascale-class Cray XC30 system.

Authors with CRIS profile

Moritz Kreutzer Regionales Rechenzentrum Erlangen (RRZE) Georg Hager Regionales Rechenzentrum Erlangen (RRZE) Gerhard Wellein Professur für Höchstleistungsrechnen Andreas Pieper Regionales Rechenzentrum Erlangen (RRZE)

Involved external institutions

Universität Greifswald DE Germany (DE)

How to cite

APA:

Kreutzer, M., Hager, G., Wellein, G., Alvermann, A., Fehske, H., & Pieper, A. (2015). Performance Engineering of the Kernel Polynomal Method on Large-Scale CPU-GPU Systems. In IEEE (Eds.), Proceedings of the 2015 IEEE International Parallel and Distributed Processing Symposium (IPDPS) (pp. 417-426). Hyderabad, India, IN.

MLA:

Kreutzer, Moritz, et al. "Performance Engineering of the Kernel Polynomal Method on Large-Scale CPU-GPU Systems." Proceedings of the Parallel and Distributed Processing Symposium (IPDPS), 2015 IEEE International, Hyderabad, India Ed. IEEE, 2015. 417-426.

BibTeX: Download