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

Ahmed Al Jarro, Hakan Bagci

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

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.
Original languageEnglish (US)
Title of host publicationCEM'11 Computational Electromagnetics International Workshop
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages128-131
Number of pages4
ISBN (Print)9781457716874
DOIs
StatePublished - Aug 2011

Fingerprint Dive into the research topics of 'Hybrid MPI/OpenMP parallelization of the explicit Volterra integral equation solver for multi-core computer architectures'. Together they form a unique fingerprint.

Cite this