volume | PIER Journals

Abstract

Recently, many numerical methods that are developed for the solution of electromagnetic problems have greatly benefited from the hardware accelerated scientific computing capability provided by graphics processing units (GPUs) and orders of magnitude speed-up factors have been reported. Among these methods, the finite-difference frequency-domain (FDFD) method as well can be accelerated substantially by utilizing an efficient algorithm customized for GPU computing. In this contribution, an algorithm is presented that treats iterative solution of the FDFD linear equation system similar to solution of three-dimensional Finite-Difference Time-Domain (FDTD) method, which inherently yields itself to high level parallelization. The presented algorithm uses BICGSTAB iterative solver. Integrated with BICGSTAB, an efficient method of performing matrix-vector products for the linear system of FDFD equations is adapted and implemented in Compute Unified Device Architecture (CUDA). It is shown that FDFD can be solved with a speed-up factor of more than 20 on a GPU compared with the solution on a central processing unit (CPU), while memory usage as well can be reduced substantially with the presented algorithm.

1. Sypek, P., A. Dziekonski, and M. Mrozowski, "How to render FDTD computations more effective using a graphics accelerator," IEEE Transactions on Magnetics, Vol. 45, No. 3, 1324-1327, 2009.
doi:10.1109/TMAG.2009.2012614

2. Demir, V. and A. Z. Elsherbeni, "Compute unified device architecture (CUDA) based finite-difference time-domain (FDTD) implementation," Journal of the Applied Computational Electromagnetics Society (ACES), Vol. 25, No. 4, 303-314, April 2010.

3. Ong, C. Y., M. Weldon, S. Quiring, L. Maxwell, M. C. Hughes, C. Whelan, and M. Okoniewski, "Speed it up," IEEE Microwave Magazine, Vol. 11, No. 2, 70-78, April 2010.
doi:10.1109/MMM.2010.935776

4. De Donno, D., A. Esposito, L. Tarricone, and L. Catarinucci, "Introduction to GPU computing and CUDA programming: A case study on FDTD," IEEE Antennas and Propagation Magazine, EM Programmer's Notebook, Vol. 52, No. 3, 116-122, June 2010.

5. Godel, N., N. Nunn, T. Warburton, and T. Clemens, "Scalability of higher-order discontinuous galerkin FEM computations for solving electromagnetic wave propagation problems on GPU clusters," IEEE Transactions on Magnetics, Vol. 46, No. 8, August 2010.

6. De Donno, D., A. Esposito, G. Monti, and L. Tarricone, "GPU-based acceleration of the MPIE/MoM matrix calculation for the analysis of microstrip circuits," Proceedings of the European Conference on Antennas and Propagation (EuCAP 2011), Rome, Italy, April 2011.

7. Al Sharkawy, M. H., V. Demir, and A. Z. Elsherbeni, Electromagnetic Scattering Using the Iterative Multi-Region Technique (Synthesis Lectures on Computational Electromagnetics), Morgan and Claypool Publishers, November 2007.

8. Al Sharkawy, M. H., V. Demir, and A. Z. Elsherbeni, "The iterative multi-region algorithm using a hybrid finite difference frequency domain and method of moments techniques," Progress In Electromagnetics Research, Vol. 57, 19-32, 2006.
doi:10.2528/PIER05071001

9. Al Sharkawy, M. H., V. Demir, and A. Z. Elsherbeni, "Plane wave scattering from three dimensional multiple objects using the Iterative Multi-Region technique based on the FDFD method," IEEE Transactions on Antennas and Propagation, Vol. 54, No. 2, 666-673, February 2006.
doi:10.1109/TAP.2005.863129

10. Kuzu, L., V. Demir, A. Z. Elsherbeni, and E. Arvas, "Electromagnetic scattering from arbitrarily shaped chiral objects using the finite difference frequency domain method," Progress In Electromagnetics Research, Vol. 67, 1-24, 2007.
doi:10.2528/PIER06083104

11. Alkan, E., V. Demir, A. Z. Elsherbeni, and E. Arvas, "Double-grid finite-difference frequency-domain method for modeling chiral medium," IEEE Transactions on Antennas and Propagation, Vol. 58, No. 3, 817-823, March 2010.
doi:10.1109/TAP.2009.2039297

12. Zainud-Deen, S. H., E. El-Deen, M. S. Ibrahim, K. H. Awadalla, and A. Z. Botros, "Electromagnetic scattering using GPU-based finite difference frequency domain method," Progress In Electromagnetics Research B, Vol. 16, 351-369, 2009.
doi:10.2528/PIERB09060703

13. De Donno, D., A. Esposito, G. Monti, and L. Tarricone, "Iterative solution of linear systems in electromagnetics (and not only): Experiences with CUDA," UnConventional High Performance Computing, Lecture Notes in Computer Science (LNCS), Vol. 6586, Springer 2011.

14. Demir, V., E. Alkan, A. Z. Elsherbeni, and E. Arvas, "An algorithm for effcient solution of finite-difference frequency-domain (FDFD) methods," IEEE Antennas and Propagation Magazine, Vol. 61, No. 6, 143-150, December 2009.
doi:10.1109/MAP.2009.5433120

15. Kunz, K. S. and R. J. Luebbers, The Finite Difference Time Domain Method for Electromagnetics, CRC Press, 1993.

16. Berenger, J. P., "A perfectly matched layer for the absorption of electromagnetic waves," Journal of Computational Physics, Vol. 114, No. 2, 185-200, October 1994.
doi:10.1006/jcph.1994.1159

17. Yee, K. S., "Numerical solution of initial boundary value problems involving Maxwell's equations in isotropic media," IEEE Transactions on Antennas and Propagation, Vol. 14, 302-307, May 1966.

18. Saad, Y., Iterative Methods for Sparse Linear Systems, Society for Industrial and Applied Mathematics (SIAM), Philadelphia, PA, USA, 2003.
doi:10.1137/1.9780898718003

19. Barrett, R., M. Berry, T. F. Chan, J. Demmel, J. Donato, J. Dongarra, V. Eijkhout, R. Pozo, C. Romine, and H. Van der Vorst, Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods, 2nd Edition, Society for Industrial and Applied Mathematics (SIAM), Philadelphia, PA, USA, 1994.
doi:10.1137/1.9781611971538

20. Saad, Y. and M. H. Schultz, "GMRES: A generalized minimal residual algorithm for solving nonsymmetric linear systems," SIAM Journal on Scientific and Statistical Computing, Vol. 7, No. 3, 856-869, July 1986.
doi:10.1137/0907058

21. Van der Vorst, H. A., "BI-CGSTAB: A fast and smoothly converging variant of BI-CG for the solution of nonsymmetric linear systems," SIAM Journal on Scientific and Statistical Computing, Vol. 13, No. 2, 631-644, March 1992.
doi:10.1137/0913035

22. Sleijpen, G. L. G. and D. R. Fokkema, "BICGSTAB(l) for linear equations involving unsymmetric matrices with complex spectrum," Electronic Transactions on Numerical Analysis, Vol. 1, 11-32, 1993.

23., CUDA 2.1 Programming Guide, http://www.nvidia.com/object/-cuda develop.html..

24., http://www.staff.science.uu.nl/»vorst102/software.html..

25. Blackford, L. S., J. Demmel, J. Dongarra, I. Duff, S. Hammarling, G. Henry, M. Heroux, L. Kaufman, A. Lumsdaine, A. Petitet, R. Pozo, K. Remington, and R. C. Whaley, "An updated set of basic linear algebra subprograms (BLAS)," ACM Trans. Math. Soft., Vol. 28, No. 2, 135-151, 2002.
doi:10.1145/567806.567807

26. Demir, V., A. Z. Elsherbeni, D. Worasawate, and E. Arvas, "A graphical user interface (GUI) for plane wave scattering from a conducting, dielectric or a chiral sphere," IEEE Antennas and Propagation Magazine, Vol. 46, No. 5, 94-99, October 2004.
doi:10.1109/MAP.2004.1388838

27. Zubal, I. G., C. R. Harrell, E. O. Smith, Z. Rattner, G. R. Gindi, and P. B. Hoffer, "Computerized three-dimensional segmented human anatomy," Medical Physics, Vol. 21, No. 2, 299-302, February 1994.
doi:10.1118/1.597290

28., The Zubal Phantom, http://noodle.med.yale.edu/zubal/index.htm..
doi:10.1118/1.597290

29. "An internet resource for the calculation of the dielectric properties of body tissues in the frequency range 10 Hz-100 GHz,", 2011, http://niremf.ifac.cnr.it/tissprop/..
doi:10.1118/1.597290

30. Benzi, M., "Preconditioning techniques for large linear systems: A survey," Journal of Computational Physics, Vol. 182, No. 2, 418-477, November 2002.
doi:10.1006/jcph.2002.7176

31. Li, R. and Y. Saad, "GPU-accelerated preconditioned iterative linear solvers,", CUDA ITSOL Technical Report, available at http://www-users.cs.umn.edu/»rli/, 2011.

Dr. Veysel Demir