Parallelization of Molecular-Dynamics Simulations Using Tasks. Issue 1753 (12th February 2015)

• Record Type: Journal Article
• Authors: Meyer, Ralf; Mangiardi, Chris M.
• Editors: Calderer, C.; Lipton, R.; Margetis, D.; Otto, F.
• Is Part Of: MRS proceedings. Issue 1753:(2015)
• Publication Date: 2015-02-12
• Subjects: simulation, -- structural, -- metal; Electrical engineering -- Congresses; Physics -- Congresses; Materials -- Research -- Congresses; Materials science -- Congresses; 620.11
• DOI: 10.1557/opl.2015.113
• Languages: English
• ISSNs: 0272-9172

Abstract

ABSTRACT: This article discusses novel algorithms for molecular-dynamics (MD) simulations with short-ranged forces on modern multi- and many-core processors like the Intel Xeon Phi. A task-based approach to the parallelization of MD on shared-memory computers and a tiling scheme to facilitate the SIMD vectorization of the force calculations is described. The algorithms have been tested with three different potentials and the resulting speed-ups on Intel Xeon Phi coprocessors are shown.