Visual Environment for Rapid Composition of Parameter-Sweep Applications for Distributed Processing on Global Grids

TL;DR

This paper introduces VPT, a Java-based IDE that simplifies the development of parameter sweep applications for distributed Grid processing, enabling scientists to easily Grid-enable their applications without explicit parallel programming.

Contribution

The paper presents VPT, a novel IDE that automates parameter script creation and data file parameterization for rapid development of Grid-enabled applications.

Findings

VPT effectively simplifies creating parameter sweep applications.

Demonstrated successful deployment on clusters and global Grids.

Supports compatibility with Nimrod-G parameter specification language.

Abstract

Computational Grids are emerging as a platform for next-generation parallel and distributed computing. Large-scale parametric studies and parameter sweep applications find a natural place in the Grid?s distribution model. There is little or no communication between jobs. The task of parallelizing and distributing existing applications is conceptually trivial. These properties of parametric studies make it an ideal place to start developing integrated development environments (IDEs) for rapidly Grid-enabling applications. However, the availability of IDEs for scientists to Grid-enable their applications, without the need of developing them as parallel applications explicitly, is still lacking. This paper presents a Java based IDE called Visual Parametric Tool (VPT), developed as part of the Gridbus project, for rapid creation of parameter sweep (data parallel/SPMD) applications. It supports automatic creation of parameter script and parameterisation of the input data files, which is compatible with the Nimrod-G parameter specification language. The usefulness of VPT is demonstrated by a case study on composition of molecular docking application as a parameter sweep application. Such applications can be deployed on clusters using the Nimrod/enFuzion system and on global Grids using the Nimrod-G grid resource broker.