VLab: collaborative Grid services and portals to support computational material science

Mehmet A. Nacar, Mehmet S. Aktas, Marlon Pierce, Zhenyu Lu, Gordon Erlebacher, Dan Kigelman, Evan F. Bollig, Cesar R. S. da Silva, Benny Sowell, David A. Yuen
2007 Concurrency and Computation  
We present the initial architecture and implementation of VLab, a Grid and Web Service-based system for enabling distributed and collaborative computational chemistry and material science applications for the study of planetary materials. The requirements of VLab include job preparation and submission, job monitoring, data storage and analysis, and distributed collaboration. These components are divided into client entry (input file creation, visualization of data, task requests) and backend
more » ... vices (storage, analysis, computation). Clients and services communicate through NaradaBrokering, a publish/subscribe Grid middleware system that abstracts specific hardware information through the use of topics. We describe two aspects of VLab in this paper: 1) data entry and submission, and 2) a visualization web client/service. Grid Web Portals, Java Server Faces (JSF) and JSF Grid Beans are used to build an interface that permits input file specification, multiple code submissions, and multiple job submissions (of a given code) with backend data persistence. In addition, to investigate our collaboration and visualization infrastructure, we have developed a service that transforms a scalar data set into its wavelet representation. A client (java applet) can retrieve the coordinates of the centers of the dominant fraction of the wavelets and display the results as a collection of spheres. General adaptors are placed between the endpoints and NaradaBrokering, which serve to isolate the clients/services from the middleware. This permits client and service development independently of potential changes to the middleware. From the Grid computing point of view, VLab presents several interesting problems that are the subject of this paper. Driving Grid research issues include the following: • Persistently managing user inputs as archived, hierarchical project metadata. This is described in Section 2. • Simplifying complicated, multi-staged job submissions and monitoring using Grid portal technology. Section 3 describes this work. • Integrating VLab applications with Grid messaging infrastructure [2] to virtualize resource usage, provide fault tolerance, and enable collaboration. This work is summarized in Section 4. Bullets 1 and 2 are essentially client-side operations, while bullet 3 is primarily concerned with abstracting serverside capabilities. In this paper, we report our initial approaches to solving these problems.
doi:10.1002/cpe.1199 fatcat:pqnnikmn7ze25egp4cuuivnjua