Parallel and distributed processing for h-p adaptive finite-element analysis: a comparison of simulated and empirical studies

Parallel processing techniques have been widely promoted as a feasible, and even promising, solution to the very high computational costs associated with practical h-p adaptive finite-element analysis software tools for electromagnetic device design and system performance simulation. A combination of emulated and empirical studies designed to explore the validity of these claims are presented and compared. Practical parallel processing efficiency results, computed for Sun E450 and v880 parallel workstation platforms (four processors each), are reported.