In this work, we introduce CoJVM, a new distributed Java run-time system that enables concurrent Java programs to efficiently execute on clusters of personal computers or workstations. CoJVM implements Java’s shared memo-ry model by enabling multiple standard JVMs to work cooperatively and transparently to support a single distributed shared-memory across the cluster’s nodes. CoJVM requires no change to applications written in standard Java. Our experi-mental results using several Java benchmarks show that CoJVM performance is considerable with speed-ups ranging from 6.1 to 7.8 for an 8-node cluster.
ER -
%0 Journal Article
%1 DJVMforClusters
%A Lobosco, Marcelo
%A Silva, Anderson
%A Loques, Orlando
%A de Amorim, Claudio L.
%D 2003
%J Euro-Par 2003 Parallel Processing
%K DVM Distributed Java PhD Proposal VM
%P 1207--1215
%T A New Distributed JVM for Cluster Computing
%U http://www.springerlink.com/content/dmrrrn7fygb4qct3
%X In this work, we introduce CoJVM, a new distributed Java run-time system that enables concurrent Java programs to efficiently execute on clusters of personal computers or workstations. CoJVM implements Java’s shared memo-ry model by enabling multiple standard JVMs to work cooperatively and transparently to support a single distributed shared-memory across the cluster’s nodes. CoJVM requires no change to applications written in standard Java. Our experi-mental results using several Java benchmarks show that CoJVM performance is considerable with speed-ups ranging from 6.1 to 7.8 for an 8-node cluster.
ER -
@article{DJVMforClusters,
abstract = {In this work, we introduce CoJVM, a new distributed Java run-time system that enables concurrent Java programs to efficiently execute on clusters of personal computers or workstations. CoJVM implements Java’s shared memo-ry model by enabling multiple standard JVMs to work cooperatively and transparently to support a single distributed shared-memory across the cluster’s nodes. CoJVM requires no change to applications written in standard Java. Our experi-mental results using several Java benchmarks show that CoJVM performance is considerable with speed-ups ranging from 6.1 to 7.8 for an 8-node cluster.
ER -},
added-at = {2008-09-04T15:39:17.000+0200},
author = {Lobosco, Marcelo and Silva, Anderson and Loques, Orlando and de Amorim, Claudio L.},
biburl = {https://www.bibsonomy.org/bibtex/258aab9a5f33be634e6b4e93b08a0a6e8/gron},
description = {SpringerLink - Buchkapitel},
interhash = {be11f249a1d48c6a6f2f0e1d8923adbb},
intrahash = {58aab9a5f33be634e6b4e93b08a0a6e8},
journal = {Euro-Par 2003 Parallel Processing},
keywords = {DVM Distributed Java PhD Proposal VM},
pages = {1207--1215},
timestamp = {2008-09-04T15:39:17.000+0200},
title = {A New Distributed JVM for Cluster Computing},
url = {http://www.springerlink.com/content/dmrrrn7fygb4qct3},
year = 2003
}