Hybrid MPI/OpenMP parallelization of the explicit Volterra integral equation solver for multi-core computer architectures

Handle URI:
http://hdl.handle.net/10754/564408
Title:
Hybrid MPI/OpenMP parallelization of the explicit Volterra integral equation solver for multi-core computer architectures
Authors:
Al Jarro, Ahmed; Bagci, Hakan ( 0000-0003-3867-5786 )
Abstract:
A hybrid MPI/OpenMP scheme for efficiently parallelizing the explicit marching-on-in-time (MOT)-based solution of the time-domain volume (Volterra) integral equation (TD-VIE) is presented. The proposed scheme equally distributes tested field values and operations pertinent to the computation of tested fields among the nodes using the MPI standard; while the source field values are stored in all nodes. Within each node, OpenMP standard is used to further accelerate the computation of the tested fields. Numerical results demonstrate that the proposed parallelization scheme scales well for problems involving three million or more spatial discretization elements. © 2011 IEEE.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Electrical Engineering Program; Computational Electromagnetics Laboratory; Physical Sciences and Engineering (PSE) Division
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
CEM'11 Computational Electromagnetics International Workshop
Conference/Event name:
2011 Computational Electromagnetics International Workshop, CEM'11
Issue Date:
Aug-2011
DOI:
10.1109/CEM.2011.6047345
Type:
Conference Paper
ISBN:
9781457716874
Appears in Collections:
Conference Papers; Physical Sciences and Engineering (PSE) Division; Electrical Engineering Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorAl Jarro, Ahmeden
dc.contributor.authorBagci, Hakanen
dc.date.accessioned2015-08-04T06:26:37Zen
dc.date.available2015-08-04T06:26:37Zen
dc.date.issued2011-08en
dc.identifier.isbn9781457716874en
dc.identifier.doi10.1109/CEM.2011.6047345en
dc.identifier.urihttp://hdl.handle.net/10754/564408en
dc.description.abstractA hybrid MPI/OpenMP scheme for efficiently parallelizing the explicit marching-on-in-time (MOT)-based solution of the time-domain volume (Volterra) integral equation (TD-VIE) is presented. The proposed scheme equally distributes tested field values and operations pertinent to the computation of tested fields among the nodes using the MPI standard; while the source field values are stored in all nodes. Within each node, OpenMP standard is used to further accelerate the computation of the tested fields. Numerical results demonstrate that the proposed parallelization scheme scales well for problems involving three million or more spatial discretization elements. © 2011 IEEE.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.titleHybrid MPI/OpenMP parallelization of the explicit Volterra integral equation solver for multi-core computer architecturesen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentElectrical Engineering Programen
dc.contributor.departmentComputational Electromagnetics Laboratoryen
dc.contributor.departmentPhysical Sciences and Engineering (PSE) Divisionen
dc.identifier.journalCEM'11 Computational Electromagnetics International Workshopen
dc.conference.date10 August 2011 through 13 August 2011en
dc.conference.name2011 Computational Electromagnetics International Workshop, CEM'11en
dc.conference.locationIzmiren
kaust.authorAl Jarro, Ahmeden
kaust.authorBagci, Hakanen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.