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 language||English (US)|
|Title of host publication||CEM'11 Computational Electromagnetics International Workshop|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|Number of pages||4|
|State||Published - Aug 2011|