Accelerating molecular dynamics computing using iteration space slicing

Molecular dynamics is an important computational tool to simulate and understand biochemical processes at the atomic level. Accurate modelling of processes such as simulation of the Newtonian equations of motion requires a large number of computation steps for systems with hundreds to millions of particles. In this paper, we present an approach to accelerate molecular dynamics simulations by means of automatic program loop parallelization. To parallelize code of applications, we have used the Iteration Space Slicing framework. The scope of the applicability of the approach is illustrated using the Gromacs package. Results of a performance analysis for parallelized loops executed on a multi-core computer are presented. The future work is discussed.