Hierarchical parallelisation strategy for multilevel fast multipole algorithm in computational electromagnetics

被引:38
作者
Erguel, Oe. [1 ,2 ]
Guerel, L. [1 ,2 ]
机构
[1] Bilkent Univ, Computat Electromagnet Res Ctr, BiLCEM, TR-06800 Ankara, Turkey
[2] Bilkent Univ, Dept Elect & Elect Engn, TR-06800 Ankara, Turkey
关键词
D O I
10.1049/el:20082282
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 [电气工程]; 0809 [电子科学与技术];
摘要
A hierarchical parallelisation of the multilevel fast multipole algorithm (MLFMA) for the efficient solution of large-scale problems in computational electromagnetics is presented. The tree structure of MLFMA is distributed among the processors by partitioning both the clusters and the samples of the fields appropriately for each level. The parallelisation efficiency is significantly improved compared to previous approaches, where only the clusters or only the fields are partitioned in a level.
引用
收藏
页码:3 / 4
页数:2
相关论文
共 9 条
[1]
[Anonymous], THESIS U ILLINOIS UR
[2]
ERGUL O, 2006, P EUR C ANT PROP EUC
[3]
ERGUL O, 2007, P IEEE ANT PROP SOC, P3436
[4]
Fast and accurate solutions of extremely large integral-equation problems discretised with tens of millions of unknowns [J].
Gurel, L. ;
Ergul, O. .
ELECTRONICS LETTERS, 2007, 43 (09) :499-500
[5]
Poggio AJ, 1973, COMPUTER TECHNIQUES
[6]
Multilevel fast multipole algorithm for electromagnetic scattering by large complex objects [J].
Song, JM ;
Lu, CC ;
Chew, WC .
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, 1997, 45 (10) :1488-1493
[7]
Performance of a parallel implementation of the FMM for electromagnetics applications [J].
Sylvand, G .
INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN FLUIDS, 2003, 43 (08) :865-879
[8]
Analysis and performance of a distributed memory multilevel fast multipole algorithm [J].
Velamparambil, S ;
Chew, WC .
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, 2005, 53 (08) :2719-2727
[9]
10 million unknowns:: Is it that big? [J].
Velamparambil, S ;
Chew, WC ;
Song, JM .
IEEE ANTENNAS AND PROPAGATION MAGAZINE, 2003, 45 (02) :43-58