Skip to main navigation Skip to search Skip to main content

Accelerating FDTD algorithm using GPU computing

  • Beijing Institute of Technology

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

Abstract

Hardware acceleration of Finite-Difference Time-Domain (FDTD) algorithm has always been an important part of FDTD research. In this essay, we discussed the advantage and feasibility of accelerate FDTD algorithm using Graphics Processing Unit (GPU). With the implement of lattice-threads mapping and other techniques, we proposed a GPU FDTD programming model that is both efficient and accurate. Then we simulated two projects using proposed model, the result shows good agreement with CPU computing while simulation speedup is 20 at minimum, thus proves the efficiency and great potential of GPU accelerating in FDTD research.

Original languageEnglish
Title of host publicationICMTCE2011 - Proceedings 2011 IEEE International Conference on Microwave Technology and Computational Electromagnetics
Pages410-413
Number of pages4
DOIs
Publication statusPublished - 2011
Event2011 2nd IEEE International Conference on Microwave Technology and Computational Electromagnetics, ICMTCE2011 - Beijing, China
Duration: 22 May 201125 May 2011

Publication series

NameICMTCE2011 - Proceedings 2011 IEEE International Conference on Microwave Technology and Computational Electromagnetics

Conference

Conference2011 2nd IEEE International Conference on Microwave Technology and Computational Electromagnetics, ICMTCE2011
Country/TerritoryChina
CityBeijing
Period22/05/1125/05/11

Keywords

  • FDTD
  • GPU
  • Hardware Accelerating

Fingerprint

Dive into the research topics of 'Accelerating FDTD algorithm using GPU computing'. Together they form a unique fingerprint.

Cite this