DocumentCode
247277
Title
Acceleration of the dual-field domain decomposition algorithm using GPU clusters
Author
Huan-Ting Meng ; Jian-Ming Jin
Author_Institution
Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
fYear
2014
fDate
6-11 July 2014
Firstpage
1381
Lastpage
1382
Abstract
The dual-field domain decomposition algorithm based on the element-level decomposition is accelerated using GPU clusters for electromagnetic analysis in the time domain. Various aspects of the implementation are investigated, and an optimal implementation strategy is proposed to utilize GPU´s parallelized architecture. An example shows that through careful arrangement of the GPU memory and thread allocation, a significant speedup can be achieved on a GPU cluster.
Keywords
computational electromagnetics; graphics processing units; time-domain analysis; GPU clusters; dual-field domain decomposition algorithm; electromagnetic analysis; element-level decomposition; finite element method; graphics processing units; parallelized architecture; Acceleration; Antennas; Dispersion; Finite element analysis; Graphics processing units; Instruction sets; Time-domain analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
Antennas and Propagation Society International Symposium (APSURSI), 2014 IEEE
Conference_Location
Memphis, TN
ISSN
1522-3965
Print_ISBN
978-1-4799-3538-3
Type
conf
DOI
10.1109/APS.2014.6905016
Filename
6905016
Link To Document