A hybrid algorithm for parallel molecular dynamics simulations
MIRARCO Mining Innovation, Laurentian University, 935 Ramsey Lake Road, Sudbury, ON P3E 2C6, Canada
arXiv:1611.00075 [cond-mat.mtrl-sci], (31 Oct 2016)
@article{mangiardi2016hybrid,
title={A hybrid algorithm for parallel molecular dynamics simulations},
author={Mangiardi, Chris M. and Meyer, Ralf},
year={2016},
month={oct},
archivePrefix={"arXiv"},
primaryClass={cond-mat.mtrl-sci}
}
This article describes an algorithm for hybrid parallelization and SIMD vectorization of molecular dynamics simulations with short-ranged forces. The parallelization method combines domain decomposition with a thread-based parallelization approach. The goal of the work is to enable efficient simulations of very large (tens of millions of atoms) and inhomogeneous systems on many-core processors with hundreds or thousands of cores and SIMD units with large vector sizes. In order to test the efficiency of the method, simulations of a variety of configurations with up to 74 million atoms have been performed. Results are shown that were obtained on multi-core systems with AVX and AVX-2 processors as well as Xeon-Phi co-processors.
November 3, 2016 by hgpu
