Share Email Print
cover

Proceedings Paper

FDTD multi-GPU implementation of Maxwell's equations in dispersive media
Author(s): Mohammad R. Zunoubi; Jason Payne; Michael Knight
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this research, we present the first multi-GPU FDTD implementation of Maxwell's equations in dispersive media that uses the Open-MP API to synchronize the operation of GPUs and their corresponding CPUs. By taking advantage of the CUDA programming model, we present a unique implementation of the FDTD scheme that exploits the memory hierarchy of GPUs, including the global, texture, and shared memory. This enables us to tackle problems that are otherwise computationally prohibitive. Practical results will be presented along with a measure of speedup factors achieved when using multiple GPU processors.

Paper Details

Date Published: 19 February 2011
PDF: 6 pages
Proc. SPIE 7897, Optical Interactions with Tissue and Cells XXII, 78971S (19 February 2011); doi: 10.1117/12.875528
Show Author Affiliations
Mohammad R. Zunoubi, SUNY, New Paltz (United States)
Jason Payne, Air Force Research Lab. (United States)
Michael Knight, Air Force Research Lab. (United States)


Published in SPIE Proceedings Vol. 7897:
Optical Interactions with Tissue and Cells XXII
E. Duco Jansen; Robert J. Thomas, Editor(s)

© SPIE. Terms of Use
Back to Top