A parallel implementation of the fast multipole method for Maxwell's equations

It is well known that the resolution of Maxwell equations may provide large dense matrices, being thus a computer intensive problem. Even small problems require a huge amount of memory to manipulate matrices during the O(N-3) involved operations. The fast multipole method enables to compress and approximate matrices. Coupled with an iterative resolution of the linear system the complexity reduces to O(N-iter N log N) operations. In order to use multiprocessors machine and to reduce computation times, we propose here a parallel implementation of the fast multiple method. This article relates our first results, as well as the difficulties encountered. Copyright (C) 2003 John Wiley Sons, Ltd.