An agent-based infrastructure for parallel Java on heterogeneous clusters

J. Ai-Jaroodi, N. Mohamed, H. Jiang, D. Swanson

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

In this paper, we introduce an agent-based infrastructure that provides software services and functions for developing and deploying high performance programming models and applications on clusters. A Java-based prototype, based on this architecture, has been developed. Since this system is written completely in Java, it is portable and allows executing programs in parallel across multiple heterogeneous platforms. With the agent-based infrastructure, users need not deal with the mechanisms of deploying and loading user classes on the heterogeneous cluster. Moreover, details of scheduling, controlling, monitoring, and executing user jobs are hidden. In addition, the management of system resources is made transparent to the user. Such uniform services, when rendered available in a ubiquitous manner, are essential for facilitating the development and deployment of scalable high performance Java applications on clusters. An initial deployment over a heterogeneous, distributed cluster results in significantly enhanced performance; absolute performance compared to C (MPI) improves with increased granularity of the algorithms.

Original languageEnglish (US)
Article number1137724
Pages (from-to)19-27
Number of pages9
JournalProceedings - IEEE International Conference on Cluster Computing, ICCC
Volume2002-January
DOIs
StatePublished - Jan 1 2002

Fingerprint

Scheduling
Monitoring

Keywords

  • Application software
  • Clustering algorithms
  • Computer architecture
  • Functional programming
  • Java
  • Monitoring
  • Prototypes
  • Resource management
  • Software performance
  • Software prototyping

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Signal Processing

Cite this

An agent-based infrastructure for parallel Java on heterogeneous clusters. / Ai-Jaroodi, J.; Mohamed, N.; Jiang, H.; Swanson, D.

In: Proceedings - IEEE International Conference on Cluster Computing, ICCC, Vol. 2002-January, 1137724, 01.01.2002, p. 19-27.

Research output: Contribution to journalArticle

@article{09feb8b5c3784505aaf26441e76b84a3,
title = "An agent-based infrastructure for parallel Java on heterogeneous clusters",
abstract = "In this paper, we introduce an agent-based infrastructure that provides software services and functions for developing and deploying high performance programming models and applications on clusters. A Java-based prototype, based on this architecture, has been developed. Since this system is written completely in Java, it is portable and allows executing programs in parallel across multiple heterogeneous platforms. With the agent-based infrastructure, users need not deal with the mechanisms of deploying and loading user classes on the heterogeneous cluster. Moreover, details of scheduling, controlling, monitoring, and executing user jobs are hidden. In addition, the management of system resources is made transparent to the user. Such uniform services, when rendered available in a ubiquitous manner, are essential for facilitating the development and deployment of scalable high performance Java applications on clusters. An initial deployment over a heterogeneous, distributed cluster results in significantly enhanced performance; absolute performance compared to C (MPI) improves with increased granularity of the algorithms.",
keywords = "Application software, Clustering algorithms, Computer architecture, Functional programming, Java, Monitoring, Prototypes, Resource management, Software performance, Software prototyping",
author = "J. Ai-Jaroodi and N. Mohamed and H. Jiang and D. Swanson",
year = "2002",
month = "1",
day = "1",
doi = "10.1109/CLUSTR.2002.1137724",
language = "English (US)",
volume = "2002-January",
pages = "19--27",
journal = "Proceedings - IEEE International Conference on Cluster Computing, ICCC",
issn = "1552-5244",

}

TY - JOUR

T1 - An agent-based infrastructure for parallel Java on heterogeneous clusters

AU - Ai-Jaroodi, J.

AU - Mohamed, N.

AU - Jiang, H.

AU - Swanson, D.

PY - 2002/1/1

Y1 - 2002/1/1

N2 - In this paper, we introduce an agent-based infrastructure that provides software services and functions for developing and deploying high performance programming models and applications on clusters. A Java-based prototype, based on this architecture, has been developed. Since this system is written completely in Java, it is portable and allows executing programs in parallel across multiple heterogeneous platforms. With the agent-based infrastructure, users need not deal with the mechanisms of deploying and loading user classes on the heterogeneous cluster. Moreover, details of scheduling, controlling, monitoring, and executing user jobs are hidden. In addition, the management of system resources is made transparent to the user. Such uniform services, when rendered available in a ubiquitous manner, are essential for facilitating the development and deployment of scalable high performance Java applications on clusters. An initial deployment over a heterogeneous, distributed cluster results in significantly enhanced performance; absolute performance compared to C (MPI) improves with increased granularity of the algorithms.

AB - In this paper, we introduce an agent-based infrastructure that provides software services and functions for developing and deploying high performance programming models and applications on clusters. A Java-based prototype, based on this architecture, has been developed. Since this system is written completely in Java, it is portable and allows executing programs in parallel across multiple heterogeneous platforms. With the agent-based infrastructure, users need not deal with the mechanisms of deploying and loading user classes on the heterogeneous cluster. Moreover, details of scheduling, controlling, monitoring, and executing user jobs are hidden. In addition, the management of system resources is made transparent to the user. Such uniform services, when rendered available in a ubiquitous manner, are essential for facilitating the development and deployment of scalable high performance Java applications on clusters. An initial deployment over a heterogeneous, distributed cluster results in significantly enhanced performance; absolute performance compared to C (MPI) improves with increased granularity of the algorithms.

KW - Application software

KW - Clustering algorithms

KW - Computer architecture

KW - Functional programming

KW - Java

KW - Monitoring

KW - Prototypes

KW - Resource management

KW - Software performance

KW - Software prototyping

UR - http://www.scopus.com/inward/record.url?scp=84948963769&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84948963769&partnerID=8YFLogxK

U2 - 10.1109/CLUSTR.2002.1137724

DO - 10.1109/CLUSTR.2002.1137724

M3 - Article

AN - SCOPUS:84948963769

VL - 2002-January

SP - 19

EP - 27

JO - Proceedings - IEEE International Conference on Cluster Computing, ICCC

JF - Proceedings - IEEE International Conference on Cluster Computing, ICCC

SN - 1552-5244

M1 - 1137724

ER -