Advanced partitioning and communication strategies for the efficient parallelization of the multilevel fast multipole algorithm

buir.contributor.authorGürel, Levent
dc.contributor.authorErgül O.en_US
dc.contributor.authorGürel, Leventen_US
dc.coverage.spatialToronto, ON, Canadaen_US
dc.date.accessioned2016-02-08T12:22:33Z
dc.date.available2016-02-08T12:22:33Z
dc.date.issued2010en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.departmentComputational Electromagnetics Research Center (BiLCEM)en_US
dc.descriptionDate of Conference: 11-17 July 2010en_US
dc.description.abstractLarge-scale electromagnetics problems can be solved efficiently with the multilevel fast multipole algorithm (MLFMA) [1], which reduces the complexity of matrix-vector multiplications required by iterative solvers from O(N 2) to O(N logN). Parallelization of MLFMA on distributed-memory architectures enables fast and accurate solutions of radiation and scattering problems discretized with millions of unknowns using limited computational resources. Recently, we developed a hierarchical partitioning strategy [2], which provides an efficient parallelization of MLFMA, allowing for the solution of very large problems involving hundreds of millions of unknowns. In this strategy, both clusters (sub-domains) of the multilevel tree structure and their samples are partitioned among processors, which leads to improved load-balancing. We also show that communications between processors are reduced and the communication time is shortened, compared to previous parallelization strategies in the literature. On the other hand, improved partitioning of the tree structure complicates the arrangement of communications between processors. In this paper, we discuss communications in detail when MLFMA is parallelized using the hierarchical partitioning strategy. We present well-organized arrangements of communications in order to maximize the efficiency offered by the improved partitioning. We demonstrate the effectiveness of the resulting parallel implementation on a very large scattering problem involving a conducting sphere discretized with 375 million unknowns. ©2010 IEEE.en_US
dc.identifier.doi10.1109/APS.2010.5561775en_US
dc.identifier.urihttp://hdl.handle.net/11693/28508
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/APS.2010.5561775en_US
dc.source.title2010 IEEE Antennas and Propagation Society International Symposiumen_US
dc.subjectCommunication strategyen_US
dc.subjectCommunication timeen_US
dc.subjectComputational resourcesen_US
dc.subjectConducting spheresen_US
dc.subjectDistributed memoryen_US
dc.subjectElectromagneticsen_US
dc.subjectHierarchical partitioningen_US
dc.subjectIterative solversen_US
dc.subjectLoad-Balancingen_US
dc.subjectMatrix vector multiplicationen_US
dc.subjectMulti-level fast multi-pole algorithmen_US
dc.subjectMultilevel fast multipole algorithmsen_US
dc.subjectParallel implementationsen_US
dc.subjectParallelization strategiesen_US
dc.subjectParallelizationsen_US
dc.subjectScattering problemsen_US
dc.subjectSub-domainsen_US
dc.subjectTree structuresen_US
dc.subjectAntennasen_US
dc.subjectSpheresen_US
dc.subjectTrees (mathematics)en_US
dc.subjectCommunicationen_US
dc.titleAdvanced partitioning and communication strategies for the efficient parallelization of the multilevel fast multipole algorithmen_US
dc.typeConference Paperen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
A hierarchical partitioning strategy for an efficient parallelization of the multilevel fast multipole algorithm.pdf
Size:
902.16 KB
Format:
Adobe Portable Document Format
Description:
Full printable version