Title :
Parallelization and Acceleration Scheme of Multilevel Fast Multipole Method
Author :
Wang, Wu ; Feng, Yangde ; Chi, Xuebin
Author_Institution :
Supercomput. Center, Chinese Acad. of Sci., Beijing
Abstract :
The iterative methods such as BiCGStab for solving electromagnetic field integer equations have a complexity of O(N2), which can be reduced to O(N logN) by multilevel fast multipole method (MLFMM). For large scale problems, MLFMM should be parallelized, and the iterative convergence can be accelerated by preconditioners such as incomplete inverse triangular factorization preconditioner. The interpolation based on spherical harmonic transform at each level of MLFMMpsilas octree can be further accelerated by FFT. Based on this acceleration scheme tested on distributed cluster, the results show this algorithm is feasible.
Keywords :
computational complexity; computational electromagnetics; convergence of numerical methods; electromagnetic fields; fast Fourier transforms; harmonic analysis; interpolation; iterative methods; octrees; parallel processing; BiCGStab; acceleration scheme; distributed cluster; electromagnetic field integer equation; fast Fourier transform; inverse triangular factorization; iterative convergence; iterative method; multilevel fast multipole method; parallelization scheme; spherical harmonic transform; Acceleration; Clustering algorithms; Convergence; Electromagnetic fields; Equations; Interpolation; Iterative methods; Large-scale systems; Life estimation; Testing; electromagnetic field integer equation; incomplete inverse triangular factorization preconditioner; multilevel fast multipole method; parallelization scheme; spherical harmonic transform;
Conference_Titel :
Parallel and Distributed Computing, Applications and Technologies, 2008. PDCAT 2008. Ninth International Conference on
Conference_Location :
Otago
Print_ISBN :
978-0-7695-3443-5
DOI :
10.1109/PDCAT.2008.34
