Adaptive parallelism in the Bulk-synchronous Parallel model
The Bulk-Synchronous Parallel (BSP) model is a universal abstraction of parallel computation that can be used to design portable parallel software. Advances in processor architecture and network communication enable clusters of workstations to be used as parallel computers. This paper focuses on using the idle computing power of a network of workstations to run parallel programs. The transient nature of the processors causes straightforward execution of synchronous BSP programs to perform poorly in such an environment. In this paper, we propose a scheme, based on the eager replication of state data and lazy replication of processes, that allows BSP programs to run efficiently on transient processors. The scheme is integrated into the Oxford BSP library.
KeywordsBSP Model Networks of Workstations Adaptive Parallel Computing
Unable to display preview. Download preview PDF.
- 1.C. K. Birdsall and A. B. Langdon. Plasma Physics via Computer Simulation. The Adam Hilger Series on Plasma Physics. Adam Hilger, New York, 1991.Google Scholar
- 2.A. Bricker, M. Litzkow, and M. Livny. Condor Technical Summary. Technical Report CS-TR-92-1069, Computer Sciences Department, University of Wisconsin-Madison, Jan 1992.Google Scholar
- 3.Pankaj Jalote. Fault Tolerance in Distributed Systems. Prentice Hall, Englewood Cliffs, New Jersey 07632, 1994.Google Scholar
- 5.W F McColl. BSP Programming. In G Bleiloch, M Chandy, and S Jagannathan, editors, Proc. DIMACS Workshop on Specification of Parallel Algorithms, Princeton, May 94. American Mathematical Society.Google Scholar
- 6.Richard Miller. A Library for Bulk-synchronous Parallel Programming. In British Computer Society Parallel Processing Specialist Group workshop on General Purpose Parallel Computing, December 1993.Google Scholar
- 7.Richard Miller and Joy Reed. The Oxford BSP Library Users' Guide, version 1.0. Technical report, Oxford Parallel, 1993.Google Scholar
- 8.Sape Mullender. Distributed Systems. ACM Press Frontier Series. ACM Press, New York, 2nd edition, 1993.Google Scholar
- 9.M. V. Nibhanupudi, C. D. Norton, and B. K. Szymanski. Plasma Simulation On Networks Of Workstations Using The Bulk-Synchronous Parallel Model. In Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA '95), pages 13–22, Athens, Georgia, November 3–4, 1995.Google Scholar
- 10.M. V. Nibhanupudi and B. K. Szymanski. Efficiency Of Parallel Computation Replication On A Network Of Transient Processors. Submitted to Eighth IEEE Symposium on Parallel and Distributed Processing to be held in October 1996.Google Scholar
- 11.C. D. Norton, B. K. Szymanski, and V. K. Decyk. Object Oriented Parallel Computation for Plasma PIC Simulation. Communications of the ACM, 38(10), October 1995.Google Scholar