A GPU Implementation of the 2-D Finite-Difference Time-Domain Code using High Level Shader Language
Keywords:
A GPU Implementation of the 2-D Finite-Difference Time-Domain Code using High Level Shader LanguageAbstract
The authors have applied a graphics processing unit (GPU) to the finite-difference timedomain (FDTD) method to realize a cost-effective and high-speed computation of an FDTD simulation. The authors used the plane wave scattering by a perfectly conducting rectangular cylinder as the model and investigated the performance of this implementation. The authors timed the computation time of the scattered electromagnetic field by the two-dimensional (2-D) FDTD method at 1,000 steps. Using a PC equipped with an Intel 3.4-GHz Pentium 4 processor and an nVIDIA Geforce 7800 GTX GPU, the authors achieved an approximately 10-fold improvement in computation speed compared with the speed of a conventional central processing unit (CPU) executing the same task.
Downloads
References
K. S. Yee, “Numerical solution of initial boundary
value problems involving Maxwell ́s equations in
isotropic media,” IEEE Trans. Antennas Propagat.,
vol. AP-14, no. 3, pp.302-307, May 1966.
A. Taflove, Computational electrodynamics: the
finite difference time domain method, Artech House,
Inc., 1995.
K. S. Kunz and R. J. Luebbers, The finite difference
time domain method for electromagnetics, CRC
Press, Inc., 1993.
T. Namiki, “A new FDTD algorithm based on
alternating direction implicit method,” IEEE Trans.
Microwave Theory Tech., vol. MTT-47, no. 10,
pp.1-5, Oct. 1999.
N. Takada, K. Ando, K. Motojima, T. Ito, and S.
Kozaki, “New Distributed implementation of the
FDTD method,” Electronics and Communications in
Japan, Part 2, vol. 80, no.5, pp.8-16, 1997.
D. P. Rodohan, S. R. Saunders, and R. J. Glover, “A
distributed implementation of the finite difference
time domain (FDTD) method,” Int. J. Numerical
Modeling: Electronic Networks, Devices and Fields,
vol. 8, no.3, pp.283-292, 1995.
D. B. Davidson and R. W. Ziolkowski, “A
connection machine (CM-2) implementation of
three-dimensional parallel finite difference time
domain code for electromagnetic field simulation,”
Int. J. Numerical Modeling: Electronic Networks,
Devices and Fields, vol. 8, no. 3, pp.221-232, 1995.
nVIDIA corporation, “GPU Gems” Addison-Wisley,
nVIDIA corporation, “GPU Gems 2” Addison-
Wisley, 2005.
J. Boltz, I. Farmer, E. Grinspun, P. Schröder,
“Sparse matrix solvers on the GPU: Conjugate
Gradients and Multigrid,” ACM SIGGRAPH 03
Proceedings, 2003.
C. Tompson, S. Hahn, and M. Oskin, “Using
modern graphics architectures for general-purpose
computing: a framework and analysis,” Proceedings
of the 35th International Symposium on
Microarchitecture, pp. 306-320, Nov. 2002.
J. Krüger and R. Westermann, “Linear algebra
operators for GPU implementation of numerical
algorithms,” ACM SIGGRAPH 03 Proceedings,
N. Masuda, T. Ito, T. Tanaka, A. Shiraki, and T.
Sugie, “Computer generated holography using a
graphics processing unit,” Opt. Express, vol. 14, no.
, pp.587-592, 2006.
M. J. Inman and A. Z. Elsherbeni, “Programming
video cards for computational electromagnetics
application,” IEEE Antennas and Propagation
Magazine, vol. 47, no. 6, pp.71-78, Dec. 2005.
G. S. Baron, C. D. Sarris, and E. Fiume, “Fast and
accurate time-domain simulations with commodity
graphics hardware,” Proceedings of Antennas and
Propagation Society International Symposium, July
J. Fang, “Time domain finite difference computation
for Maxwell’s equation,” Ph. D. thesis, University of
California at Berkley, 1989.
