Abstract
The electromagnetic behavior of plasmonic structures can be predicted after discretizing and solving a linear system of equations, derived from a continuous surface integral equation (SIE) and the appropriate boundary conditions, using a method of moments (MoM) methodology. In realistic large-scale optical problems, a direct inversion of the SIE–MoM matrix cannot be performed due to its large size, and an iterative solver must be used instead. This paper investigates the performance of four iterative solvers (GMRES, TFQMR, CGS, and BICGSTAB) for five different SIE–MoM formulations (PMCHWT, JMCFIE, CTF, CNF, and MNMF). Moreover, under this plasmonic context, a set of suggested guidelines are provided to choose a suitable SIE formulation and iterative solver depending on the desired simulation error and available runtime resources.
Acknowledgements
The authors especially thank the company Appentra Solutions, developers of the automatic parallelizing source-to-source compiler Parallware (www.appentra.com), for assisting us in the analysis and parallelization of some parts of our C codes.
Notes
No potential conflict of interest was reported by the authors.