Parallel Higher-Order Method of Moments with Efficient Out-of-GPU Memory Schemes for Solving Electromagnetic Problems

作者

  • Zhongchao Lin School of Electronic Engineering Xidian University, Xi’an, Shaanxi 710071, China
  • Yan Chen School of Electronic Engineering Xidian University, Xi’an, Shaanxi 710071, China
  • Xunwang Zhao School of Electronic Engineering Xidian University, Xi’an, Shaanxi 710071, China
  • Daniel Garcia-Donoro School of Electronic Engineering Xidian University, Xi’an, Shaanxi 710071, China
  • Yu Zhang School of Electronic Engineering Xidian University, Xi’an, Shaanxi 710071, China
  • Huanhuan Zhang School of Electronic Engineering Xidian University, Xi’an, Shaanxi 710071, China

关键词:

GPU-based HoMoM, GPU context, outof-GPU memory, overlapping, parallel framework

摘要

A distributed parallel Higher-order Method of Moments (HoMoM) for solving electromagnetic problems on CPU/GPU clusters is presented. An MPI/ OpenMP/CUDA parallel framework based on the GPU context technique is designed. An out-of-GPU memory scheme is employed to break the limitation of the GPU memory. To improve the performance of data transferring between main memory and GPU memory, an overlapping scheme based on asynchronous technique and CUDA streams is adopted. In comparison with the parallel CPU version only, numerical results including a metallic airplane and an airborne array with dielectric structures demonstrate the high performance of the proposed method.

##plugins.generic.usageStats.downloads##

##plugins.generic.usageStats.noStats##

参考

Y. Zhang and T. K. Sarkar, Parallel Solution of Integral Equation Based EM Problems in the Frequency Domain. Hoboken, NJ: Wiley, 2009.

“NVIDIA GeForce 8800 GPU architecture overview,” NVIDIA Corporation, Santa Clara, CA, Tech. Brief TB-02787-001_v0.9, Nov. 2006.

S. E. Krakiwsky, L. E. Turner, and M. M. M. Okoniewski, “Acceleration of finite-difference time-domain (FDTD) using graphics processor units (GPU),” in IEEE MTT-S Int. Microwave Symp. Digest, pp. 1033-1036, 2004.

M. J. Inman and A. Z. Elsherbeni, “Programming video cards for computational electromagnetics applications,” IEEE Antennas Propag. Mag., vol. 47, pp. 71-78, 2005.

M. J. Inman, A. Z. Elsherbeni, J. G. Maloney, and B. N. Baker, “Practical implementation of a CPML absorbing boundary for GPU accelerated FDTD technique,” ACES Journal, vol. 23, no. 1, pp. 16- 22, Dec. 2008.

T. Takahashi and T. Hamada, “GPU-accelerated boundary element method for Helmholtz’ equation in three dimensions,” International Journal for Numerical Methods in Engineering, vol. 80, pp. 1295-1321, 2009.

S. Peng and Z. Nie, “Acceleration of the method of moments calculations by using graphics processing units,” IEEE Trans. Antennas Propag., vol. 56, no. 7, pp. 2130-2133, May 2008.

M. J. Inman, A. Z. Elsherbeni, and C. J. Reddy, “CUDA based LU decomposition solvers for CEM applications,” ACES Journal, vol. 25, no. 4, pp. 339-347, Dec. 2010.

E. Lezar and D. Davidson, “GPU acceleration of method of moments matrix assembly using RaoWilton-Glisson basis functions,” in Proc. ICEIE, Kyoto, Japan, pp. V1-56-V1-60, 2010.

E. Lezar and D. Davidson, “GPU-accelerated method of moments by example: Monostatic scattering,” IEEE Antennas Propag. Mag., vol. 52, no. 6, pp. 120-135, Dec. 2010.

E. Lezar and D. B. Davidson, ‘GPU-based LU decomposition for large method of moments problems,” Electronics Letters, vol. 46, no. 17, pp. 1194-1196, 2010.

S. M. Rao, D. R. Wilton, and A. W. Glisson, “Electromagnetic scattering by surfaces of arbitrary shape,” IEEE Trans. Antennas Propag., vol. AP30, no. 3, pp. 409-418, May 1982.

Innovative Computing Laboratory, University Tennessee, Knoxville, “MAGMA: Matrix Algebra on GPU and Multicore Architectures,” 2009. [Online]. Available: http://icl.cs.utk.edu/magma/index.html

E. DAzevedo and JC Hill, ‘Parallel LU factorization on GPU cluster,” Procedia Computer Science, 9, pp. 67-75, 2012.

P. Du, S. Tomov, and J. Dongarra, “Providing GPU Capability to LU and QR within the ScaLAPACK Framework,” 2012. [Online] Available: http://www. netlib.org/lapack/lawnspdf/ lawn272.pdf

T. Topa, “Efficient out-of-GPU memory strategies for solving matrix equation generated by method of moments,” Electronics Letters, vol. 51, no. 19, pp. 1542-1544, 2015.

X. Mu, H.-X. Zhou, K. Chen, and W. Hong, “Higher order method of moments with a parallel out-of-core LU solver on GPU/CPU platform,” IEEE Trans. Antennas Propag., vol. 62, no. 11, pp. 5634-5646, 2014.

P. Ylä-Oijala, M. Taskinen, and S. Järvenpää, “Analysis of surface integral equations in electromagnetic scattering and radiation problems,” Engineering Analysis with Boundary Elements, vol. 32, no. 3, pp. 196-209, 2008.

R. F. Harrington, “Boundary integral formulations for homogenous material bodies,” Journal of Electromagnetic Waves and Applications, vol. 3, no. 1, pp. 1-15, 1989.

John L. Volakis and Kubilay Sertel, Integral Equation Methods for Electromagnetics. Raleigh, NC: SciTech Pub., 2012.

NVIDIA Corporation, ‘CUDA API REFERENCE MANUAL Version 5.0’, Oct. 2012.

##submission.downloads##

已出版

2021-07-30

##submission.howToCite##

[1]
Zhongchao Lin, Yan Chen, Xunwang Zhao, Daniel Garcia-Donoro, Yu Zhang, 和 Huanhuan Zhang, 《Parallel Higher-Order Method of Moments with Efficient Out-of-GPU Memory Schemes for Solving Electromagnetic Problems》, ACES Journal, 卷 32, 期 09, 页 781–788, 7月 2021.

期

2017: Vol 32 Iss 9

栏目

General Submission