GPU-Accelerated LOBPCG Method with Inexact Null-Space Filtering for Solving Generalized Eigenvalue Problems in Computational Electromagnetics Analysis with Higher-Order FEM - Publication - MOST Wiedzy

Search

GPU-Accelerated LOBPCG Method with Inexact Null-Space Filtering for Solving Generalized Eigenvalue Problems in Computational Electromagnetics Analysis with Higher-Order FEM

Abstract

This paper presents a GPU-accelerated implementation of the Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG) method with an inexact nullspace filtering approach to find eigenvalues in electromagnetics analysis with higherorder FEM. The performance of the proposed approach is verified using the Kepler (Tesla K40c) graphics accelerator, and is compared to the performance of the implementation based on functions from the Intel MKL on the Intel Xeon (E5-2680 v3, 12 threads) central processing unit (CPU) executed in parallel mode. Compared to the CPU reference implementation based on the Intel MKL functions, the proposed GPUbased LOBPCG method with inexact nullspace filtering allowed us to achieve up to 2.9-fold acceleration.

Citations

  • 0

    CrossRef

  • 5

    Web of Science

  • 0

    Scopus

Details

Category:
Articles
Type:
artykuł w czasopiśmie wyróżnionym w JCR
Published in:
Communications in Computational Physics no. 22, edition 04, pages 997 - 1014,
ISSN: 1815-2406
Language:
English
Publication year:
2017
Bibliographic description:
Dziekoński A., Rewieński M., Sypek P., Lamęcki A., Mrozowski M.: GPU-Accelerated LOBPCG Method with Inexact Null-Space Filtering for Solving Generalized Eigenvalue Problems in Computational Electromagnetics Analysis with Higher-Order FEM// Communications in Computational Physics. -Vol. 22, iss. 04 (2017), s.997-1014
DOI:
Digital Object Identifier (open in new tab) 10.4208/cicp.oa-2016-0168
Verified by:
Gdańsk University of Technology

seen 37 times

Recommended for you

Meta Tags