Parallel FDTD simulation using Task Parallel Library (TPL)

• Autorzy: Bolesta I. , Demchuk A.
• Języki publikacji: EN

Abstrakty

EN

The finite-difference time-domain (FDTD) is a numerical analysis technique used for solving computational electrodynamic problems. The nature of the FDTD method is that simulation of big and complicated electromagnetic field problems requires a vast amount of computer operational memory and runtime. Parallel-processing techniques have been broadly applied to FDTD to accelerate the simulations. The parallelism of the FDTD algorithm is based on a fact that the computational domain can be divided into parts (sub-domains), and each processor in a parallel system deals with one or several sub-domains. The FDTD algorithm belongs to data parallelism model and can be effectively implemented on shared memory system architecture. The parallel FDTD method was implemented using TPL library. The Task Parallel Library (TPL) is a library for .NET that makes easy to parallelize the program using the advantages of .NET Framework. The speedup metrics of parallel FDTD algorithm were calculated and compared with Amdahl’s estimated speedup.

Słowa kluczowe

EN

FDTD; finite difference time domain method; Yee cell; data parallel model; shared memory system; task; speed up; Amdahl’s law

PL

FDTD; metoda różnic skończonych; komórka Yee; pamięć współdzielona; speedup; prawo Amdahla

• Wydawca: Wydawnictwo Politechniki Łódzkiej
• Czasopismo: Journal of Applied Computer Science
• Rocznik: 2016
• Tom: Vol. 24, nr 2
• Strony: 7--16
• Opis fizyczny: Bibliogr. 7 poz., il. kolor., 1 wykr.

Twórcy

autor

Bolesta I.

• Ivan Franko National University of Lviv, Department of Radiophysics and Computer Technologies, Generala Tarnavskogo Str. 107, Lviv, 79017, Ukraine

autor

Demchuk A.

• Ivan Franko National University of Lviv, Department of Radiophysics and Computer Technologies, Generala Tarnavskogo Str. 107, Lviv, 79017, Ukraine

Bibliografia

• [1] 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, No. 3, 1966, pp. 302–307.
• [2] Taflove, A. and Hagness, S., Computational Electrodynamics: The Finite- Difference Time Domain Method, Artech House, Norwood, 2006.
• [3] He, Z. L., Huang, K., Zhang, Y., Yan, Y., and Liang, C. H., Study on High Performance of MPI-Based Parallel FDTD fromWorkStation to Super Computer Platform, International Journal of Antennas and Propagation, Vol. 2012, 2012, Article ID 659509, 7 pages.
• [4] Guo, X. M., Guo, Q. X., Zhao,W., and Yu,W. H., Parallel FDTD simulation using NUMA acceleration technique, Progress In Electromagnetics Research Letters, Vol. 28, 2012, pp. 1–8.
• [5] Sen, R., Developing Parallel Programs, Advances in Computer Science: an International Journal, Vol. 1, No. 1, 2012, pp. 18–27, Available at: http://www.acsij.org/acsij/article/view/321.
• [6] Barney, B., Introduction to Parallel Computing, Lawrence Livermore National Laboratory, 2015, Available at: https://computing.llnl.gov/tutorials/parallel_comp/.
• [7] Demir, V. and Elsherbeni, A. Z., Compute Unified Device Architecture (CUDA) based Finite-Diffeerence Time-Domain (FDTD) implementation, ACES Journal, Vol. 25, No. 4, 2010, pp. 303–314.

Uwagi

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.