N-body simulations on GPUs

Abstract

Commercial graphics processors (GPUs) have high com- pute capacity at very low cost, which makes them at- tractive for general purpose scientific computing. In this paper we show how graphics processors can be used for N-body simulations to obtain improvements in perfor- mance over current generation CPUs. We have devel- oped a highly optimized algorithm for performing the O(N2) force calculations that constitute the major part of stellar and molecular dynamics simulations. In some of the calculations, we achieve sustained performance of nearly 100 GFlops on an ATI X1900XTX. The perfor- mance on GPUs is comparable to specialized processors such as GRAPE-6A and MDGRAPE-3, but at a frac- tion of the cost. Furthermore, the wide availability of GPUs has significant implications for cluster computing and distributed computing efforts like Folding@Home.