Hybrid MPI/OpenMP parallelization of the explicit Volterra integral equation solver for multi-core computer architectures
KAUST DepartmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Electrical Engineering Program
Computational Electromagnetics Laboratory
Physical Sciences and Engineering (PSE) Division
MetadataShow full item record
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.
Conference/Event name2011 Computational Electromagnetics International Workshop, CEM'11