Adaptive load balancing for long-range MD simulations in a distributed environment

J. V. Sumanth, David R Swanson, Hong Jiang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Molecular Dynamics, a computationally intensive application is used by researchers in various fields. The inherent parallelism [13] in the computations involved with this application can be exploited in parallel and distributed environments. However, in distributed environments such as the Grid [6], the available resources, namely the network and computational power, are continually changing with respect to every available node. To optimally utilize these dynamic resources, a scheduler should be able to continually adapt to the changes and suitably vary the load scheduled to every available node. We propose one such scheduling algorithm. The proposed scheduling algorithm builds and continually updates a model of the distributed system, which it then uses to make decisions about how to optimally redistribute the load in the system at every time step of the MD simulation. The scheduling algorithm can additionally handle dynamic changes in the number of nodes available for computation at runtime. We then demonstrate the efficiency of our scheduling algorithm when applied to MD simulations in a distributed environment.

Original languageEnglish (US)
Title of host publicationICPP 2006
Subtitle of host publicationProceedings of the 2006 International Conference on Parallel Processing
Pages135-144
Number of pages10
DOIs
StatePublished - Dec 1 2006
EventICPP 2006: 2006 International Conference on Parallel Processing - Columbus, OH, United States
Duration: Aug 14 2006Aug 18 2006

Publication series

NameProceedings of the International Conference on Parallel Processing
ISSN (Print)0190-3918

Conference

ConferenceICPP 2006: 2006 International Conference on Parallel Processing
CountryUnited States
CityColumbus, OH
Period8/14/068/18/06

Fingerprint

Scheduling algorithms
Resource allocation
Molecular dynamics

ASJC Scopus subject areas

  • Hardware and Architecture
  • Engineering(all)

Cite this

Sumanth, J. V., Swanson, D. R., & Jiang, H. (2006). Adaptive load balancing for long-range MD simulations in a distributed environment. In ICPP 2006: Proceedings of the 2006 International Conference on Parallel Processing (pp. 135-144). [1690614] (Proceedings of the International Conference on Parallel Processing). https://doi.org/10.1109/ICPP.2006.17

Adaptive load balancing for long-range MD simulations in a distributed environment. / Sumanth, J. V.; Swanson, David R; Jiang, Hong.

ICPP 2006: Proceedings of the 2006 International Conference on Parallel Processing. 2006. p. 135-144 1690614 (Proceedings of the International Conference on Parallel Processing).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sumanth, JV, Swanson, DR & Jiang, H 2006, Adaptive load balancing for long-range MD simulations in a distributed environment. in ICPP 2006: Proceedings of the 2006 International Conference on Parallel Processing., 1690614, Proceedings of the International Conference on Parallel Processing, pp. 135-144, ICPP 2006: 2006 International Conference on Parallel Processing, Columbus, OH, United States, 8/14/06. https://doi.org/10.1109/ICPP.2006.17
Sumanth JV, Swanson DR, Jiang H. Adaptive load balancing for long-range MD simulations in a distributed environment. In ICPP 2006: Proceedings of the 2006 International Conference on Parallel Processing. 2006. p. 135-144. 1690614. (Proceedings of the International Conference on Parallel Processing). https://doi.org/10.1109/ICPP.2006.17
Sumanth, J. V. ; Swanson, David R ; Jiang, Hong. / Adaptive load balancing for long-range MD simulations in a distributed environment. ICPP 2006: Proceedings of the 2006 International Conference on Parallel Processing. 2006. pp. 135-144 (Proceedings of the International Conference on Parallel Processing).
@inproceedings{0db22a462de646de8200e1200b9ef8f9,
title = "Adaptive load balancing for long-range MD simulations in a distributed environment",
abstract = "Molecular Dynamics, a computationally intensive application is used by researchers in various fields. The inherent parallelism [13] in the computations involved with this application can be exploited in parallel and distributed environments. However, in distributed environments such as the Grid [6], the available resources, namely the network and computational power, are continually changing with respect to every available node. To optimally utilize these dynamic resources, a scheduler should be able to continually adapt to the changes and suitably vary the load scheduled to every available node. We propose one such scheduling algorithm. The proposed scheduling algorithm builds and continually updates a model of the distributed system, which it then uses to make decisions about how to optimally redistribute the load in the system at every time step of the MD simulation. The scheduling algorithm can additionally handle dynamic changes in the number of nodes available for computation at runtime. We then demonstrate the efficiency of our scheduling algorithm when applied to MD simulations in a distributed environment.",
author = "Sumanth, {J. V.} and Swanson, {David R} and Hong Jiang",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/ICPP.2006.17",
language = "English (US)",
isbn = "0769526365",
series = "Proceedings of the International Conference on Parallel Processing",
pages = "135--144",
booktitle = "ICPP 2006",

}

TY - GEN

T1 - Adaptive load balancing for long-range MD simulations in a distributed environment

AU - Sumanth, J. V.

AU - Swanson, David R

AU - Jiang, Hong

PY - 2006/12/1

Y1 - 2006/12/1

N2 - Molecular Dynamics, a computationally intensive application is used by researchers in various fields. The inherent parallelism [13] in the computations involved with this application can be exploited in parallel and distributed environments. However, in distributed environments such as the Grid [6], the available resources, namely the network and computational power, are continually changing with respect to every available node. To optimally utilize these dynamic resources, a scheduler should be able to continually adapt to the changes and suitably vary the load scheduled to every available node. We propose one such scheduling algorithm. The proposed scheduling algorithm builds and continually updates a model of the distributed system, which it then uses to make decisions about how to optimally redistribute the load in the system at every time step of the MD simulation. The scheduling algorithm can additionally handle dynamic changes in the number of nodes available for computation at runtime. We then demonstrate the efficiency of our scheduling algorithm when applied to MD simulations in a distributed environment.

AB - Molecular Dynamics, a computationally intensive application is used by researchers in various fields. The inherent parallelism [13] in the computations involved with this application can be exploited in parallel and distributed environments. However, in distributed environments such as the Grid [6], the available resources, namely the network and computational power, are continually changing with respect to every available node. To optimally utilize these dynamic resources, a scheduler should be able to continually adapt to the changes and suitably vary the load scheduled to every available node. We propose one such scheduling algorithm. The proposed scheduling algorithm builds and continually updates a model of the distributed system, which it then uses to make decisions about how to optimally redistribute the load in the system at every time step of the MD simulation. The scheduling algorithm can additionally handle dynamic changes in the number of nodes available for computation at runtime. We then demonstrate the efficiency of our scheduling algorithm when applied to MD simulations in a distributed environment.

UR - http://www.scopus.com/inward/record.url?scp=34547491717&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547491717&partnerID=8YFLogxK

U2 - 10.1109/ICPP.2006.17

DO - 10.1109/ICPP.2006.17

M3 - Conference contribution

SN - 0769526365

SN - 9780769526362

T3 - Proceedings of the International Conference on Parallel Processing

SP - 135

EP - 144

BT - ICPP 2006

ER -