基于分布式平台的FDTD并行算法

冯圆; 代小霞; 唐晓斌; 龚晓燕

doi:10.13700/j.bh.1001-5965.2015.0593

基于分布式平台的FDTD并行算法

doi: 10.13700/j.bh.1001-5965.2015.0593

冯圆^1,2,
代小霞¹,
唐晓斌^1, ,,
龚晓燕³

1.
中国电子科学研究院预警机研究所, 北京 100041
2. 空军预警学院雷达技术系, 武汉 430019
3. 火箭军指挥学院指挥系, 武汉 430013

基金项目: 国家“863”计划（2012AA01A308）；国家“973”计划（613206）

详细信息

作者简介:
冯圆,男,博士研究生,讲师。主要研究方向:计算电磁学。Tel.:010-68893271,E-mail:fy-zbh@163.com;代小霞,女,硕士研究生。主要研究方向:雷达信号处理。Tel.:17090084855,E-mail:daixiaoxia5221@163.com;唐晓斌,女,研究员。主要研究方向:电磁兼容测试。Tel.:010-68893613,E-mail:science_xiaoxiao@163.com;龚晓燕女,硕士,讲师。主要研究方向:战役指挥。Tel.:15926498355,E-mail:2228730463@qq.com

通讯作者:
唐晓斌,Tel.:010-68893613,E-mail:science_xiaoxiao@163.com

中图分类号: TP393.027
计量
- 文章访问数: 844
- HTML全文浏览量: 54
- PDF下载量: 675
- 被引次数: 0
出版历程
- 收稿日期: 2015-09-10
- 网络出版日期: 2016-09-20

FDTD parallel algorithm based on distributed platform

1.
Institute of Early Warning Aircraft, China Academy of Electronics and Information Technology, Beijing 100041
2. Department of Radar Technology, Academy of Air Force Early Warning, Wuhan 430019
3. Department of Command, Rocket Army Command Academy, Wuhan 430012

Funds: National High-tech Research and Development Program of China (2012AA01A308); National Basic Research Program of China (613206)

摘要

摘要: 基于分布式平台开展一种新的时域有限差分（FDTD）并行算法研究，该算法基于VC++、CUDA5.0平台开发，调用Intel MPI 4.1.0库进行测试，在上海交通大学高性能计算中心图形处理单元（GPU）集群、上海超级计算机中心的“魔方”商用超级计算机以及国家超级计算济南中心的“神威蓝光”国产超级计算机等平台开展软件调试。通过对纯CPU、GPU以及CPU和GPU的混合测试，线程调度水平、核心函数处理速度得到明显提升，同时减少了通信执行时间比例，提高了加速比和并行效率，最后以2×2微带阵列为验证模型进行拓扑优化测试，结果证明该算法准确、有效。
- Mur /
- 消息传递接口 /
- 图形处理单元(GPU) /
- 时域有限差分(FDTD) /
- 分布式平台
Abstract: A new finite difference time domain (FDTD) parallel algorithm is developed based on distributed platform, which is based on VC++, CUDA5.0 development platform, calling Intel MPI 4.1.0 library for testing, developing software debugging on the platforms of high performance computing center graphics processing units (GPU) cluster in Shanghai Jiao Tong University, "Rubik's Cube" commercial super computer at Shanghai Supercomputer Center, and "Divinity Blue" domestic super computer at the National Supercomputing Center in Jinan. By pure CPU, GPU, and CPU and GPU hybrid test, thread scheduling level and kernel function processing speed improve significantly, while the proportion of the execution time of communication reduces, and the acceleration ratio and operation efficiency improve. Finally, the topology optimization of the model is verified by 2×2 micro-strip arrays. The results show that the algorithm is accurate and effective.
- Mur /
- message passing interface /
- graphics processing units (GPU) /
- finite difference time domain (FDTD) /
- distributed platform

HTML全文

参考文献(16)

[1]	YEE K S.Numerical solution of initial boundary value problems involving Maxwell's equations in isotropic media[J].IEEE Transactions on Antennas and Propagation,1966,4(14):302-307.
[2]	SU M F,EI-KADY I,BADER D A,et al.A novel FDTD application featuring OpenMP-MPI hybrid parallelization[C]//Proceedings of the International Conference on Parallel Processing,2004 ICPP 2004.Piscataway,NJ:IEEE Press,2004:373-379.
[3]	YU W H,Y J,SU T,et al.A robust parallel conformal finite-difference time-domain processing package us in the MPI library[J].IEEE Antennas and Propagation,2005,47(3):39-59.
[4]	KRAKIWSKY S E,TURNER L E,OKONIEWSKI M M.Acceleration of finite-difference time-domain (FDTD) using graphics processor units (GPU) [C]//Proceedings of the IEEE MITTS International Microwave Symposium Digest.Piscataway,NJ:IEEE Press,2004,2:1033-1036.
[5]	ADAMS S,PAYNE J,BOPPANA R.Finite difference time domain (FDTD) simulations using graphics processors[C]//Proceedings of the DoD High Performance Computing Modernization Program Users Group Conference.Piscataway,NJ:IEEE Press,2007:334-338.
[6]	DU L G,LI K,KONG F M.Parallel 3D finite difference time domain simulations on graphics processors with CUDA[C]//Proceedings of the International Conference on Computational Intelligence and Software Engineering (CISE '09).Piscataway,NJ:IEEE Press,2009:145-147.
[7]	LIU Y,LIANG Z,YANG Z Q.A novel FDTD approach featuring two-level parallelization on PC cluster[J].Progress in Electromagnetics Research-Pier,2008,80:393-408.
[8]	KOMATITSCH D,GODDEKE D,ERLEBACHER G,et al.Modeling the propagation of elastic waves using spectral elements on a cluster of 192 GPUs[J].Computer Science-Research and Development,2010,25(1-2):75-82.
[9]	JACOBSEN D A,THIBAULT J C,SENOCAK I.An MPI-CUDA implementation for massively parallel incompressible flow computations on multi-GPU clusters [C]//Proceedings of 48th AIAA Aerospace Sciences Meeting.Piscataway,NJ:IEEE Press,2010:1-16.
[10]	NAGAOKA T,WATANABE S.Accelerating three-dimensional FDTD calculations on GPU clusters for electromagnetic field simulation[C]//Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society(EMBC12).Piscataway,NJ:IEEE Press,2012:5691-5694.
[11]	YANG C T,HUANG C L,LIN C F.Hybrid CUDA,OpenMP,and MPI parallel programming on multi-core GPU clusters[J].Computer Physics Communications,2011,182(1):266-269.
[12]	KIM K H,PARK Q H.Overlapping computation and communication of three-dimensional FDTD on a GPU cluster[J].Computer Physics Communications,2012,183(11):2364-2369.
[13]	XU L,XU Y,JIANG R L,et al.Implementation and optimization of three-dimensional UPML-FDTD algorithm on GPU cluster[J].Computer Engineering & Science,2013,35(11):160-167.
[14]	TAFLOVE A,BRODWIN M E.Numerical solution of steady-state electromagnetic scattering problems using the time-dependent Maxwell's equation[J].IEEE Transactions on Microware Theory Techniques,1995,23(8):623-630.
[15]	GE D B,YAN Y B.Finite-difference time-domain method for electromagnetic wavess[M].3rd ed.Xi'an:Xidian University Press,2011:37-38.
[16]	ENGQUIST B,MAJDA A.Absorbing boundary conditions for the numerical simulation of waves[J].Mathematics of Computation,1977,31(139):629-651.