HOT Jcluster toolkit V 1.0.5 releases!  The source code is open under GPL licence! - Oct. 25, 2004

 

---

 

We present Jcluster toolkit, a high-performance Java parallel environment, implemented entirely in pure Java. Jcluster automatically balances resource load across the large-scale heterogeneous cluster with a transitive random stealing algorithm and provides simple high-performance PVM-like and MPI-like message passing interfaces with multithreaded communications using UDP protocol.

The availability of high-speed networks and increasingly powerful commodity microprocessors is making the usage of clusters of computers an appealing vehicle for cost effective parallel computing. Clusters, built using commodity-of-the-shelf (COTS) hardware components, are playing a major role in redefining the concept of supercomputing. 

 

At the same time, Java has emerged as attractive platform allowing heterogeneous resources to be harnessed for large-scale computation. Java's object orientation, type and reference safety, exception handling model, code mobility, and distributed computing primitives all contribute to its popularity as a base upon which novel, component-based applications can be readily deployed. Increasingly, Java is becoming pervasive as a core technology supporting applications such as high-performance numerical computing, database connectivity, and scalable Internet services. 

 

 

Realizing the performance potential of clusters as a platform for incrementally scalable computing presents many challenges, while the performance aspects of communication and the resource balance have been addressed in specific settings. 

 

In Jcluster toolkit, we implement an improved random stealing algorithm, called transitive random stealing algorithm, to schedule the tasks and reach a load-balancing in the large-scale heterogeneous cluster. In the performance aspects of communication, we use efficient UDP protocol instead of TCP protocol and implement a reliable, high-performance message passing with multithreaded communications.

 

Last, we provide simple PVM-like and MPI-like message passing interface, which will ease your programming. 

 

 

Online documentation is available at:

 

http://vip.6to23.com/jcluster/docs/userguide.html  A copy of this documentation is also found in the /docs directory of the current release.

 

I am very pleased that you contact me by email, talking about all general questions / comments and sending me bug reports.