An efficient FDTD algorithm for solving electromagnetic problems based on GPU and COW acceleration

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, the Graphics Processing Unit(GPU) computing and the Cluster of Workstations(COW) techniques have been discussed and introduced into computational electromagnetics. Based on the two hardware acceleration techniques, a high efficiency Finite-Difference Time-Domain (FDTD) algorithm has been developed and implemented in two nodes COW system with a GPU in each node. Three typical EM simulation examples have been executed following the proposed scheme, the simulation results show good agreement between the GPU+COW scheme and the traditional CPU computing while at least 60 times speedup has been achieved.

Original languageEnglish
Title of host publication2013 IEEE Antennas and Propagation Society International Symposium, APSURSI 2013 - Proceedings
Pages912-913
Number of pages2
DOIs
Publication statusPublished - 2013
Event2013 IEEE Antennas and Propagation Society International Symposium, APSURSI 2013 - Orlando, FL, United States
Duration: 7 Jul 201313 Jul 2013

Publication series

NameIEEE Antennas and Propagation Society, AP-S International Symposium (Digest)
ISSN (Print)1522-3965

Conference

Conference2013 IEEE Antennas and Propagation Society International Symposium, APSURSI 2013
Country/TerritoryUnited States
CityOrlando, FL
Period7/07/1313/07/13

Fingerprint

Dive into the research topics of 'An efficient FDTD algorithm for solving electromagnetic problems based on GPU and COW acceleration'. Together they form a unique fingerprint.

Cite this