Multi-core and Multiprocessor Implementation of Numerical Integration in Finite Element Method

被引：0

作者：

Mamza, J. ^{[1
]}

Makyla, P. ^{[1
]}

Dziekonski, A. ^{[2
]}

Lamecki, A. ^{[2
]}

Mrozowski, M. ^{[2
]}

机构：

[1] Gdansk Univ Technol, Fac Elect Telecommun & Informat, Dept Metrol & Optoelect, Gdansk, Poland

[2] Gdansk Univ Technol, Fac Elect Telecommun & Informat, Dept Microwave & Antenna Engn, Gdansk, Poland

来源：

2012 19th International Conference on Microwave Radar and Wireless Communications (MIKON), Vols 1 and 2 | 2012年

关键词：

GPU; OpenMP; CUDA; numerical integration; FEM;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The paper presents techniques for accelerating a numerical integration process which appears in the Finite Element Method. The acceleration is achieved by taking advantages of multi-core and multiprocessor devices. It is shown that using multi-core implementation with OpenMP and a GPU acceleration using CUDA architecture allows one to achieve the speedups by a factor of 5 and 10 on a CPU and GPUs, respectively.

引用

页码：457 / 461

页数：5

共 15 条

[1]

[Anonymous], NUMERICAL TECHNIQUES

[2]

[Anonymous], 2011, PROGR GUID VER 4 0

[3]

[Anonymous], 2010, COMPUTATIONAL ELECTR, DOI DOI 10.1017/CBO9780511778117.022

[4]

Chapman B., 2008, USING OPENMP PORTABL

[5]

DEHNAVI MM, 2010, MAGNETICS IEEE T, V46, P2982, DOI DOI 10.1109/TMAG.2010.2043511

[6]

DZIEKONSKI A, 2011, ANTENNAS WIRELESS PR, V10, P619

[7] GPU Acceleration of Multilevel Solvers for Analysis of Microwave Components With Finite Element Method [J].

Dziekonski, Adam ;

Lamecki, Adam ;

Mrozowski, Michal .

IEEE MICROWAVE AND WIRELESS COMPONENTS LETTERS, 2011, 21 (01) :1-3

[8]

Ingelstrom P., 2006, IEEE T MICROWAVE THE, V54

[9]

Jin J., 2009, FINITE ELEMENT ANAL

[10]

Jin J-M, 2015, The finite element method in electromagnetics

← 1 2 →