An adaptive load balancing method for parallel molecular dynamics simulations

Yuefan Deng; Ronald F. Peierls; Carlos Rivera

doi:10.1006/jcph.2000.6501

An adaptive load balancing method for parallel molecular dynamics simulations

Yuefan Deng
, Ronald F. Peierls
, Carlos Rivera

Applied Mathematics and Statistics

Stony Brook University

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

35 Scopus citations

Abstract

We describe an adaptive method for achieving load balance in parallel computations simulating phenomena which are distributed over a spatially extended region, but are local in nature. We have tested the method on standard short-ranged parallel molecular dynamics calculations. The performance gain we observe confirms the value of the method for this type of calculation. We discuss possible generalizations of the method, for example, to higher dimensions.

Original language	English
Pages (from-to)	250-263
Number of pages	14
Journal	Journal of Computational Physics
Volume	161
Issue number	1
DOIs	https://doi.org/10.1006/jcph.2000.6501
State	Published - Jun 10 2000

Keywords

Load balance
Molecular dynamics
Parallel computing

Access to Document

10.1006/jcph.2000.6501

Cite this

@article{eb17cc866f2c41b9a0c8b1c054a0e288,

title = "An adaptive load balancing method for parallel molecular dynamics simulations",

abstract = "We describe an adaptive method for achieving load balance in parallel computations simulating phenomena which are distributed over a spatially extended region, but are local in nature. We have tested the method on standard short-ranged parallel molecular dynamics calculations. The performance gain we observe confirms the value of the method for this type of calculation. We discuss possible generalizations of the method, for example, to higher dimensions.",

keywords = "Load balance, Molecular dynamics, Parallel computing",

author = "Yuefan Deng and Peierls, \{Ronald F.\} and Carlos Rivera",

year = "2000",

month = jun,

day = "10",

doi = "10.1006/jcph.2000.6501",

language = "English",

volume = "161",

pages = "250--263",

journal = "Journal of Computational Physics",

issn = "0021-9991",

number = "1",

}

TY - JOUR

T1 - An adaptive load balancing method for parallel molecular dynamics simulations

AU - Deng, Yuefan

AU - Peierls, Ronald F.

AU - Rivera, Carlos

PY - 2000/6/10

Y1 - 2000/6/10

N2 - We describe an adaptive method for achieving load balance in parallel computations simulating phenomena which are distributed over a spatially extended region, but are local in nature. We have tested the method on standard short-ranged parallel molecular dynamics calculations. The performance gain we observe confirms the value of the method for this type of calculation. We discuss possible generalizations of the method, for example, to higher dimensions.

AB - We describe an adaptive method for achieving load balance in parallel computations simulating phenomena which are distributed over a spatially extended region, but are local in nature. We have tested the method on standard short-ranged parallel molecular dynamics calculations. The performance gain we observe confirms the value of the method for this type of calculation. We discuss possible generalizations of the method, for example, to higher dimensions.

KW - Load balance

KW - Molecular dynamics

KW - Parallel computing

UR - https://www.scopus.com/pages/publications/0345847527

U2 - 10.1006/jcph.2000.6501

DO - 10.1006/jcph.2000.6501

M3 - Article

AN - SCOPUS:0345847527

SN - 0021-9991

VL - 161

SP - 250

EP - 263

JO - Journal of Computational Physics

JF - Journal of Computational Physics

IS - 1

ER -

An adaptive load balancing method for parallel molecular dynamics simulations

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this