Please use this identifier to cite or link to this item:
For citation please use:
Main Title: AutoPas in ls1 mardyn: Massively parallel particle simulations with node-level auto-tuning
Author(s): Seckler, Steffen
Gratl, Fabio
Heinen, Matthias
Vrabec, Jadran
Bungartz, Hans-Joachim
Neumann, Philipp
Type: Article
Abstract: Due to computational cost, simulation software is confronted with the need to always use optimal building blocks — data structures, solver algorithms, parallelization schemes, and so forth — in terms of efficiency, while it typically needs to support a variety of hardware architectures. AutoPas implements the computationally most expensive molecular dynamics (MD) steps (e.g., force calculation) and chooses on-the-fly, i.e., at run time, the optimal combination of the previously mentioned building blocks. We detail decisions made in AutoPas to enable the interplay with MPI-parallel simulations and, to our knowledge, showcase the first MPI-parallel MD simulations that use dynamic tuning. We discuss the benefits of this approach for three simulation scenarios from process engineering, in which we obtain performance improvements of up to 50%, compared to the baseline performance of the highly optimized ls1 mardyn software.
Subject(s): AutoPas
ls1 mardyn
molecular dynamics
particle simulations
Issue Date: 7-Jan-2021
Date Available: 31-Mar-2021
Language Code: en
DDC Class: 620 Ingenieurwissenschaften und zugeordnete Tätigkeiten
Sponsor/Funder: BMBF, 01IH16008, TaLPas: Task-basierte Lastverteilung und Auto-Tuning in der Partikelsimulation
Journal Title: Journal of Computational Science
Publisher: Elsevier
Volume: 50
Article Number: 101296
Publisher DOI: 10.1016/j.jocs.2020.101296
ISSN: 1877-7503
TU Affiliation(s): Fak. 3 Prozesswissenschaften » Inst. Prozess- und Verfahrenstechnik » FG Thermodynamik und Thermische Verfahrenstechnik
Appears in Collections:Technische Universität Berlin » Publications

Files in This Item:
Format: Adobe PDF | Size: 1.84 MB
DownloadShow Preview

Item Export Bar

This item is licensed under a Creative Commons License Creative Commons