Just another WordPress site - Ruhr-Universität Bochum

Abstract

Large scale particle simulations like Molecular Dynamics can nowadays contain many million or even billion particles and are executed on thousands of processors in parallel. For such large systems it is important to develop scalable algorithms for parallel computer architectures that distribute the computational work well among the available processors to limit the simulation runtime. The typical parallelization strategies are domain-decomposition schemes, where the simulation volume is subdivided into equally sized domains, each handled by one processor.