Exploiting the advantages of object-based DSM in a heterogeneous cluster environment

Xuli Liu, Hong Jiang, Leen-Kiat Soh

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

2 Citations (Scopus)

Abstract

In recent years, increasing effort has been made by the cluster and grid computing community to build object-based Distributed Shared Memory systems (DSM) in a cluster environment. In most of these systems, a shared object is simply used as a data-exchanging unit so as to alleviate the false-sharing problem, and the advantages of sharing objects remain to be fully exploited. Thus, this paper is motivated to investigate the potential advantages of object-based DSM. For example, the performance of a distributed application may be significantly improved by adoptively and judiciously setting the size of the shared-objects, i.e., granularity. This paper, in addition to investigating the advantages of sharing objects, particularly focuses on observing how the performance of a distributed application changes with varied granularity, obtaining the optimal granularity through curve fitting, studying the factors that affect the optimal granularity, and predicting this optimal granularity in a changing runtime environment.

Original languageEnglish (US)
Title of host publication2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005
Pages800-807
Number of pages8
DOIs
StatePublished - Dec 1 2005
Event2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005 - Cardiff, Wales, United Kingdom
Duration: May 9 2005May 12 2005

Publication series

Name2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005
Volume2

Conference

Conference2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005
CountryUnited Kingdom
CityCardiff, Wales
Period5/9/055/12/05

Fingerprint

Cluster computing
Data storage equipment
Grid computing
Curve fitting

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Liu, X., Jiang, H., & Soh, L-K. (2005). Exploiting the advantages of object-based DSM in a heterogeneous cluster environment. In 2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005 (pp. 800-807). [1558644] (2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005; Vol. 2). https://doi.org/10.1109/CCGRID.2005.1558644

Exploiting the advantages of object-based DSM in a heterogeneous cluster environment. / Liu, Xuli; Jiang, Hong; Soh, Leen-Kiat.

2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005. 2005. p. 800-807 1558644 (2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005; Vol. 2).

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

Liu, X, Jiang, H & Soh, L-K 2005, Exploiting the advantages of object-based DSM in a heterogeneous cluster environment. in 2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005., 1558644, 2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005, vol. 2, pp. 800-807, 2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005, Cardiff, Wales, United Kingdom, 5/9/05. https://doi.org/10.1109/CCGRID.2005.1558644
Liu X, Jiang H, Soh L-K. Exploiting the advantages of object-based DSM in a heterogeneous cluster environment. In 2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005. 2005. p. 800-807. 1558644. (2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005). https://doi.org/10.1109/CCGRID.2005.1558644
Liu, Xuli ; Jiang, Hong ; Soh, Leen-Kiat. / Exploiting the advantages of object-based DSM in a heterogeneous cluster environment. 2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005. 2005. pp. 800-807 (2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005).
@inproceedings{e69b43d7796a4656859cb37eef331e4a,
title = "Exploiting the advantages of object-based DSM in a heterogeneous cluster environment",
abstract = "In recent years, increasing effort has been made by the cluster and grid computing community to build object-based Distributed Shared Memory systems (DSM) in a cluster environment. In most of these systems, a shared object is simply used as a data-exchanging unit so as to alleviate the false-sharing problem, and the advantages of sharing objects remain to be fully exploited. Thus, this paper is motivated to investigate the potential advantages of object-based DSM. For example, the performance of a distributed application may be significantly improved by adoptively and judiciously setting the size of the shared-objects, i.e., granularity. This paper, in addition to investigating the advantages of sharing objects, particularly focuses on observing how the performance of a distributed application changes with varied granularity, obtaining the optimal granularity through curve fitting, studying the factors that affect the optimal granularity, and predicting this optimal granularity in a changing runtime environment.",
author = "Xuli Liu and Hong Jiang and Leen-Kiat Soh",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/CCGRID.2005.1558644",
language = "English (US)",
isbn = "0780390741",
series = "2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005",
pages = "800--807",
booktitle = "2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005",

}

TY - GEN

T1 - Exploiting the advantages of object-based DSM in a heterogeneous cluster environment

AU - Liu, Xuli

AU - Jiang, Hong

AU - Soh, Leen-Kiat

PY - 2005/12/1

Y1 - 2005/12/1

N2 - In recent years, increasing effort has been made by the cluster and grid computing community to build object-based Distributed Shared Memory systems (DSM) in a cluster environment. In most of these systems, a shared object is simply used as a data-exchanging unit so as to alleviate the false-sharing problem, and the advantages of sharing objects remain to be fully exploited. Thus, this paper is motivated to investigate the potential advantages of object-based DSM. For example, the performance of a distributed application may be significantly improved by adoptively and judiciously setting the size of the shared-objects, i.e., granularity. This paper, in addition to investigating the advantages of sharing objects, particularly focuses on observing how the performance of a distributed application changes with varied granularity, obtaining the optimal granularity through curve fitting, studying the factors that affect the optimal granularity, and predicting this optimal granularity in a changing runtime environment.

AB - In recent years, increasing effort has been made by the cluster and grid computing community to build object-based Distributed Shared Memory systems (DSM) in a cluster environment. In most of these systems, a shared object is simply used as a data-exchanging unit so as to alleviate the false-sharing problem, and the advantages of sharing objects remain to be fully exploited. Thus, this paper is motivated to investigate the potential advantages of object-based DSM. For example, the performance of a distributed application may be significantly improved by adoptively and judiciously setting the size of the shared-objects, i.e., granularity. This paper, in addition to investigating the advantages of sharing objects, particularly focuses on observing how the performance of a distributed application changes with varied granularity, obtaining the optimal granularity through curve fitting, studying the factors that affect the optimal granularity, and predicting this optimal granularity in a changing runtime environment.

UR - http://www.scopus.com/inward/record.url?scp=33845330593&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845330593&partnerID=8YFLogxK

U2 - 10.1109/CCGRID.2005.1558644

DO - 10.1109/CCGRID.2005.1558644

M3 - Conference contribution

AN - SCOPUS:33845330593

SN - 0780390741

SN - 9780780390744

T3 - 2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005

SP - 800

EP - 807

BT - 2005 IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2005

ER -