Fast division-free parallel structure for convolution perfectly matched layer in finite difference time domain method

doi:10.1016/S1005-8885(15)60627-6

中国邮电高校学报(英文) ›› 2015, Vol. 22 ›› Issue (1): 72-76.doi: 10.1016/S1005-8885(15)60627-6

Fast division-free parallel structure for convolution perfectly matched layer in finite difference time domain method

白冰,牛中奇,牛毅,魏兵,赵钢

西安电子科技大学

收稿日期:2014-10-26 修回日期:2014-11-24 出版日期:2015-02-28 发布日期:2015-02-28
通讯作者: 白冰 E-mail:baibing_xdu@qq.com
基金资助:
国家自然科学基金;国家自然科学基金;中央高校基本科研业务费;中央高校基本科研业务费

Fast division-free parallel structure for convolution perfectly matched layer in finite difference time domain method

Received:2014-10-26 Revised:2014-11-24 Online:2015-02-28 Published:2015-02-28
Supported by:
National Natural Science Foundation of China;National Natural Science Foundation of China;the Fundamental Research Funds for the Central Universities;the Fundamental Research Funds for the Central Universities

摘要/Abstract

摘要： Parallel acceleration of convolution perfectly matched layer (CPML) algorithm suffers from massive division operation which is widely accepted as one of the most expensive operations for the equipment such as graphic processing unit (GPU), field programmable gate array (FPGA) etc. In pursuit of higher efficiency and lower power consumption, this article revisited the CPML theory and proposed a new fast division-free parallel CPML structure. By optimally rearranging the CPML inner iteration process, all the division operators can be eliminated and replaced by recalculating the related field updating coefficients offline. Experiments show that the proposed division-free structure can save more than 50% arithmetic instructions and 25% execution time of the traditional parallel CPML structure without any accuracy loss.

关键词: division elimination, convolution perfectly matched layer, finit difference time domain, parallel computing, graphic processing unit

Abstract: Parallel acceleration of convolution perfectly matched layer (CPML) algorithm suffers from massive division operation which is widely accepted as one of the most expensive operations for the equipment such as graphic processing unit (GPU), field programmable gate array (FPGA) etc. In pursuit of higher efficiency and lower power consumption, this article revisited the CPML theory and proposed a new fast division-free parallel CPML structure. By optimally rearranging the CPML inner iteration process, all the division operators can be eliminated and replaced by recalculating the related field updating coefficients offline. Experiments show that the proposed division-free structure can save more than 50% arithmetic instructions and 25% execution time of the traditional parallel CPML structure without any accuracy loss.

Key words: division elimination, convolution perfectly matched layer, finit difference time domain, parallel computing, graphic processing unit

中图分类号:

TP391.9

参考文献

1. Taflove A, Hagness S C. Computational electrodynamics: The finite-difference time-domain method. 3rd ed. Boston, MA, USA: Artech House Publishers, 2005

2. Berenger J P. A perfectly matched layer for the absorption of electromagnetic waves. Journal of Computational Physics,1994,114(2): 185-200

3. Sacks Z S, Kingsland D M, Lee R, et al. A perfectly matched anisotropic absorber for use as an absorbing boundary condition. IEEE Transactions on Antennas and Propagation, 1995, 43(12): 1460-1463

4. Gedney S D. An anisotropic perfectly matched layer-absorbing medium for the truncation of FDTD lattices. IEEE Transactions on Antennas and Propagation, 1996, 44(12): 1630-1639

5. Kuzuoglu M, Mittra R. Frequency dependence of the constitutive parameters of causal perfectly matched anisotropic absorbers. IEEE Microwave and Guided Wave Letters, 1996, 6(12): 447-449

6. Roden J A, Gedney S D. Convolutional PML (CPML): An efficient FDTD implementation of the CFS-PML for arbitrary media. Microwave and Optical Technology Letters, 2000, 27(5): 334-339

7. Sypek P, Dziekonski A, Mrozowski M. How to render FDTD computations more effective using a graphics accelerator. IEEE Transactions on Magnetics, 2009, 45(3): 1324-1327

8. Shahmansouri A, Rashidian B. GPU implementation of split-field finite-difference time-domain method for Drude-Lorentz dispersive media. Progress in Electromagnetics Research, 2012, 125: 55-77

9. Zygiridis T T, Kantartzis N V, Tsiboukis T D. GPU--Accelerated efficient implementation of FDTD methods with optimum time-step selection. IEEE Transactions on Magnetics, 2014, 50(2): 477-480

10. Inman M J, Elsherbeni A Z, Maloney J G, et al. GPU based FDTD solver with CPML boundaries. Proceedings of the Antennas and Propagation Society International Symposium, Jun 9-15, 2007, Honolulu, WI, USA. Piscataway, NJ, USA: IEEE, 2007: 5255-5258

11. Hu Y, Li K, Kong F M, et al. Three dimensional CPML-FDTD parallel algorithm based on CUDA. Computer Engineering and Applications, 2011, 47(25): 220-223 (in Chinese)

12. Nagaoka T, Watanabe S. Multi-GPU accelerated three-dimensional FDTD method for electromagnetic simulation. Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’11), Aug 30-Sept 3, 2011, Boston, MA, USA. Piscataway, NJ, USA: IEEE, 2011: 401-404

13. Chew W C, Weedon W H. A 3D perfectly matched medium from modified maxwell’s equations with stretched coordinates. Microwave and Optical Technology Letters, 1994, 7(13): 590-604

Fast division-free parallel structure for convolution perfectly matched layer in finite difference time domain method

Fast division-free parallel structure for convolution perfectly matched layer in finite difference time domain method

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价