Expressing direct simulation Monte Carlo methods in High Performance Fortran
D. B. Middleton, P. Mehrotra, J. Van Rosendale · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · 1995
High Performance Fortran (HPF) can readily express a broad spectrum of scientific applications and may achieve efficient parallel execution on most of them. However, the current language contains little support for programs whose data structures rely heavily on irregular or pointer-based data structures. In this paper, we look at Direct Simulation Monte Carlo methods, an important scientific application in this category. We focus first on an explicitly parallel implementation of this algorithm and then examine possible HPF expressions of this algorithm. The goal is to use HPF to achieve effective performance, while requiring as little reprogramming as possible.