An algorithm for computing short-range forces in molecular dynamics simulations with non-uniform particle densities

T. R. Law; J. Hancox; S. A. Wright; S. A. Jarvis

doi:10.1016/j.jpdc.2019.03.008

An algorithm for computing short-range forces in molecular dynamics simulations with non-uniform particle densities

T. R. Law^*, J. Hancox, S. A. Wright, S. A. Jarvis

^*Corresponding author for this work

Engineering and Physical Sciences

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

We present projection sorting, an algorithmic approach to determining pairwise short-range forces between particles in molecular dynamics simulations. We show it can be more effective than the standard approaches when particle density is non-uniform. We implement tuned versions of the algorithm in the context of a biophysical simulation of chromosome condensation, for the modern Intel Broadwell and Knights Landing architectures, across multiple nodes. We demonstrate up to 5× overall speedup and good scaling to large problem sizes and processor counts.

Original language	English
Pages (from-to)	1-11
Number of pages	11
Journal	Journal of Parallel and Distributed Computing
Volume	130
DOIs	https://doi.org/10.1016/j.jpdc.2019.03.008
Publication status	Published - Aug 2019

Bibliographical note

Funding Information:
This work was supported by the Francis Crick Institute which receives its core funding from Cancer Research UK ( FC001003 ), the UK Medical Research Council ( FC001003 ), and the Wellcome Trust, UK ( FC001003 ), and by the Engineering and Physical Sciences Research Council, UK and Intel Corporation, United States (CASE award 1365607 ). This work used the ARCHER UK National Supercomputing Service.

Funding Information:
This work was supported by the Francis Crick Institute which receives its core funding from Cancer Research UK (FC001003), the UK Medical Research Council (FC001003), and the Wellcome Trust, UK (FC001003), and by the Engineering and Physical Sciences Research Council, UK and Intel Corporation, United States (CASE award 1365607). This work used the ARCHER UK National Supercomputing Service.

Publisher Copyright:
© 2019 The Author(s)

Keywords

Algorithms
ARCHER
Many-core
Molecular dynamics
MPI
Simulation

ASJC Scopus subject areas

Software
Theoretical Computer Science
Hardware and Architecture
Computer Networks and Communications
Artificial Intelligence

Access to Document

10.1016/j.jpdc.2019.03.008

Cite this

@article{d32dae43b84e4394b5c652909c1ddca9,

title = "An algorithm for computing short-range forces in molecular dynamics simulations with non-uniform particle densities",

abstract = "We present projection sorting, an algorithmic approach to determining pairwise short-range forces between particles in molecular dynamics simulations. We show it can be more effective than the standard approaches when particle density is non-uniform. We implement tuned versions of the algorithm in the context of a biophysical simulation of chromosome condensation, for the modern Intel Broadwell and Knights Landing architectures, across multiple nodes. We demonstrate up to 5× overall speedup and good scaling to large problem sizes and processor counts.",

keywords = "Algorithms, ARCHER, Many-core, Molecular dynamics, MPI, Simulation",

author = "Law, {T. R.} and J. Hancox and Wright, {S. A.} and Jarvis, {S. A.}",

note = "Funding Information: This work was supported by the Francis Crick Institute which receives its core funding from Cancer Research UK ( FC001003 ), the UK Medical Research Council ( FC001003 ), and the Wellcome Trust, UK ( FC001003 ), and by the Engineering and Physical Sciences Research Council, UK and Intel Corporation, United States (CASE award 1365607 ). This work used the ARCHER UK National Supercomputing Service. Funding Information: This work was supported by the Francis Crick Institute which receives its core funding from Cancer Research UK (FC001003), the UK Medical Research Council (FC001003), and the Wellcome Trust, UK (FC001003), and by the Engineering and Physical Sciences Research Council, UK and Intel Corporation, United States (CASE award 1365607). This work used the ARCHER UK National Supercomputing Service. Publisher Copyright: {\textcopyright} 2019 The Author(s)",

year = "2019",

month = aug,

doi = "10.1016/j.jpdc.2019.03.008",

language = "English",

volume = "130",

pages = "1--11",

journal = "Journal of Parallel and Distributed Computing",

issn = "0743-7315",

publisher = "Elsevier",

}

TY - JOUR

T1 - An algorithm for computing short-range forces in molecular dynamics simulations with non-uniform particle densities

AU - Law, T. R.

AU - Hancox, J.

AU - Wright, S. A.

AU - Jarvis, S. A.

N1 - Funding Information: This work was supported by the Francis Crick Institute which receives its core funding from Cancer Research UK ( FC001003 ), the UK Medical Research Council ( FC001003 ), and the Wellcome Trust, UK ( FC001003 ), and by the Engineering and Physical Sciences Research Council, UK and Intel Corporation, United States (CASE award 1365607 ). This work used the ARCHER UK National Supercomputing Service. Funding Information: This work was supported by the Francis Crick Institute which receives its core funding from Cancer Research UK (FC001003), the UK Medical Research Council (FC001003), and the Wellcome Trust, UK (FC001003), and by the Engineering and Physical Sciences Research Council, UK and Intel Corporation, United States (CASE award 1365607). This work used the ARCHER UK National Supercomputing Service. Publisher Copyright: © 2019 The Author(s)

PY - 2019/8

Y1 - 2019/8

N2 - We present projection sorting, an algorithmic approach to determining pairwise short-range forces between particles in molecular dynamics simulations. We show it can be more effective than the standard approaches when particle density is non-uniform. We implement tuned versions of the algorithm in the context of a biophysical simulation of chromosome condensation, for the modern Intel Broadwell and Knights Landing architectures, across multiple nodes. We demonstrate up to 5× overall speedup and good scaling to large problem sizes and processor counts.

AB - We present projection sorting, an algorithmic approach to determining pairwise short-range forces between particles in molecular dynamics simulations. We show it can be more effective than the standard approaches when particle density is non-uniform. We implement tuned versions of the algorithm in the context of a biophysical simulation of chromosome condensation, for the modern Intel Broadwell and Knights Landing architectures, across multiple nodes. We demonstrate up to 5× overall speedup and good scaling to large problem sizes and processor counts.

KW - Algorithms

KW - ARCHER

KW - Many-core

KW - Molecular dynamics

KW - MPI

KW - Simulation

UR - http://www.scopus.com/inward/record.url?scp=85063869179&partnerID=8YFLogxK

U2 - 10.1016/j.jpdc.2019.03.008

DO - 10.1016/j.jpdc.2019.03.008

M3 - Article

AN - SCOPUS:85063869179

SN - 0743-7315

VL - 130

SP - 1

EP - 11

JO - Journal of Parallel and Distributed Computing

JF - Journal of Parallel and Distributed Computing

ER -

An algorithm for computing short-range forces in molecular dynamics simulations with non-uniform particle densities

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this