Parallel point defect identification in molecular dynamics simulations without post-processing: A compute and dump style for LAMMPS

Two classes for the molecular dynamics program LAMMPS - one compute style and one dump style - are presented that are designed to identify, count, and output point defects in cascade damage and related molecular dynamics simulations. The calculations are done in parallel across multiple MPI processes, and can be done at the same time as the original simulation. This drastically reduces storage requirements by eliminating the need to post-process every atom in the system. Non-cubic lattices, free surfaces, and large voids can be eliminated from the output by suitable choices of the reference lattice. The classes are derived from LAMMPS's Dump and Compute classes, and pose no additional overhead to LAMMPS if they are not used. PROGRAM SUMMARY Program Title: Compute style frenkel and dump style frenkel Program Files doi: http://dx.doi.org/10.176.32/p39kb4fshj.1 Licensing provisions: GPLv2 Programming language: C++ Nature of problem: Identify and count point defects (interstitials and vacancies) in metals created by high-energy cascade damage, in parallel, without post-processing, relative to an arbitrary defect-free crystal lattice. Solution method: Defects are identified and counted in parallel, across an arbitrary number of processors, through LAMMPS's domain decomposition techniques [1]. Defects are counted according to the occupancy of the Wigner-Seitz cell of each lattice site, but can be visualized by either WignerSeitz cell occupancy or by Lindemann sphere analysis. Results are then shared across all processes by message-passing. Restrictions: This implementation is likely restricted to orthorhombic domains. It is also inadvisable to use this software in the presence of grain boundaries. It is possible (with care) to use it with free surfaces. (C) 2019 Elsevier B.V. All rights reserved.