Investigation of multithread FDTD schemes for faster analysis on multiprocessor PCs

摘要

Although the finite difference time domain method is a robust and efficient technique in the class of 30 electromagnetic solvers [1], many practical problems of microwave and antenna engineering still remain beyond reach because of long CPU times required. One idea to accelerate FDTD is though parallel implementations for multiprocessor computers. This idea has been exploited by many authors ([2][3] and references therein), but all these works share two assumptions. Firstly, they are concerned with massively parallel computer systems. Such systems operate at large research institutions, but are not generally available to design engineers worldwide. Secondly, the only considered concept for parallelisation has been spatial decomposition. Recently multiprocessor personal computers have been gaining popularity. A single-processor PC can now be upgraded to two processors at less than double price, and we can predict that four or eight processors will become a standard in desktop and laptop computers within the next few years. The target of our work is to develop FDTD schemes for such systems, making use of multithread programming techniques. In this paper, we develop and investigate multithread FDTD schemes for PC, Windows NT, based on the original concept of field vector decomposition.