A Framework for Analysis of Legacy Code Migration to Grid Environment
Enterprises are looking at Grid computing as a technology of enormous potential. However, there are several issues which require immediate attention before Grid can become an important component of the IT infrastructure. One such issue is migration of legacy applications to the Grid environment. In such cases, it becomes imperative to understand whether the application performance would significantly improve on migration. In this paper an attempt is made to provide a systematic framework called the Grid Application Migration Framework (GAMF) for handling the migration process. The framework consists of Grid Code Analyzer (GCA), an independently deployable component which generates a Directed Acyclic Graph (DAG). The paper also proposes a DAG reducer algorithm for reducing the DAG. The framework is tested with several proprietary and open source C as well as Java codes. In the paper, we take three sample open source applications and demonstrate the usefulness of the framework. Finally, a small sample is analyzed and recoded to show that validity of the proposed mechanisms.
KeywordsDirected Acyclic Graph Performance Gain Message Passing Interface Grid Environment Task Graph
Unable to display preview. Download preview PDF.
- W. Gropp, E. Lusk and A. Skjellum. Using MPI, 2nd edition MIT Press, Nov 1999.Google Scholar
- A. Geist, A. Beguelin, J. Dongarra, W. Jiang, R. Manchek, and V. Sunderam. PVM: Parallel Virtual Machine - A User’s Guide and Tutorial for Networked Parallel Programming MIT Press, May 1994.Google Scholar
- L. Dagum and R. Menon. OpenMP: An Industry-Standard API for Shared-Memory Programming IEEE Computational Science and Engineering vol. 5, no. 1, Jan 1998.Google Scholar
- V. Sarkar. Patitioning and Scheduling Parallel Programs for Multiprocessors May 1989.Google Scholar
- J.J. Hwang, Y-C. Chow, F.D. Anger and C.Y. Lee. Scheduling precedence graphs in systems with interprocessor communication times. SIAM J. Comput., vol. 18, Apr 1989.Google Scholar
- Y-K. Kwok and I. Ahmed. Static Scheduling Algorithms for Allocating Directed Task Graphs to Multiprocessors. ACM Computing Surveys, vol. 31, no. 4, Dec 1999.Google Scholar
- T. Yang and A. Gerasoulis. PYRROS: Static Task Scheduling and Code Generation for Message-Passing Multiprocessors. Proc. 6th ACM Int’l Conf. SuperComputing, pages 428-433, ACM Press, New York, 1992.Google Scholar
- P-Grade Team. Parallel Grid Runtime and Application Development Environment. User’s Manual Version 8.4.2, http://www.lpds.sztaki.hu/smith/pgrade-manual/manual.html, accessed on 21st April, 2006.
- I. Ahmed, Y-K. Kwok, M-Y. Wu, and W. Shu. CASCH: A Tool for Computer-Aided Scheduling IEEE Concurrency, Oct 2000.Google Scholar
- R. Nallan, A. Chakrabarti, S. Sengupta, and A. Upadhyay. A Systematic Approach for Application Migration in a Grid Computing Environment. Asia Pacific Services Computing Conf.(APSCC), China, Dec 2006.Google Scholar
- A.Gerasoulis and T. Yang. On the granularity and clustering of directed acyclic task graphs. IEEE Transactions on Parallel and Distributed Systems, vol. 4, no. 6, June 1993.Google Scholar
- Javasim available at http://javasim.ncl.ac.uk/