An efficient parallel implementation of the multilevel fast multipole algorithm for rigorous solutions of large-scale scattering problems
Author
Ergül O.
Gürel, Levent
Date
2010Source Title
2010 URSI International Symposium on Electromagnetic Theory
Publisher
IEEE
Pages
616 - 619
Language
English
Type
Conference PaperItem Usage Stats
147
views
views
66
downloads
downloads
Abstract
We present the solution of large-scale scattering problems discretized with hundreds of millions of unknowns. The multilevel fast multipole algorithm (MLFMA) is parallelized using the hierarchical partitioning strategy on distributed-memory architectures. Optimizations and load-balancing algorithms are extensively used to improve parallel MLFMA solutions. The resulting implementation is successfully employed on modest parallel computers to solve scattering problems involving metallic objects larger than 1000λ and discretized with more than 300 million unknowns. © 2010 IEEE.
Keywords
Distributed memoryHierarchical partitioning
Large-scale scattering
Load-balancing algorithm
Metallic objects
Multi-level fast multi-pole algorithm
Multilevel fast multipole algorithms
Parallel computer
Parallel implementations
Rigorous solution
Scattering problems
Algorithms
Electric fields
Electromagnetism
Scattering
Problem solving
Permalink
http://hdl.handle.net/11693/28421Published Version (Please cite this version)
http://dx.doi.org/10.1109/URSI-EMTS.2010.5637203Collections
Related items
Showing items related by title, author, creator and subject.
-
Incremental k-core decomposition: algorithms and evaluation
Sarıyüce, A. E.; Gedik, B.; Jacques-Silva, G.; Wu, Kun-Lung; Catalyurek, U.V. (Association for Computing Machinery, 2016)A k-core of a graph is a maximal connected subgraph in which every vertex is connected to at least k vertices in the subgraph. k-core decomposition is often used in large-scale network analysis, such as community detection, ... -
Online balancing two independent criteria
Tse, Savio S.H. (Springer, 2008-10)We study the online bicriteria load balancing problem in this paper. We choose a system of distributed homogeneous file servers located in a cluster as the scenario and propose two online approximate algorithms for balancing ... -
Automatic detection of geospatial objects using multiple hierarchical segmentations
Akçay, H. G.; Aksoy, S. (Institute of Electrical and Electronics Engineers, 2008-07)The object-based analysis of remotely sensed imagery provides valuable spatial and structural information that is complementary to pixel-based spectral information in classification. In this paper, we present novel methods ...