This Article 
 Bibliographic References 
 Add to: 
Performance Evaluation of Scheduling Precedence-Constrained Computations on Message-Passing Systems
December 1994 (vol. 5 no. 12)
pp. 1317-1321

Using knowledge on computation, communication, and multiprocessor topology, a class of global priority-based scheduling heuristics, called generalized list scheduling (GLS) isproposed. Task-priority is defined as the completion time of the task following backwardscheduling the computation over the multiprocessor by using the best local heuristic. GLS scheduling consists of using the task-priority in forward, graph-driven scheduling.Evaluation of local (ETF) and GLS heuristics is carried out by altering over thecommunication, parallelism, and system topology. Analysis shows that local heuristics rely on locally maximizing the efficiency and gives acceptable solutions only when theparallelism is large enough to cover the communication (bounded speedup). GLSscheduling outperforms the local approaches versus change in parallelism, communication, and network topology. The time complexity of GLS heuristics is O(pn/sup 2/), where p and n are the number of processors and that of the tasks, respectively.

[1] T. L. Adam, K. M. Chandy, and J. R. Dickson, "A comparison of list schedules for parallel processing systems,"Commun. ACM, vol. 17, no. 12, pp. 685-690, Dec. 1974.
[2] M. Al-Mouhamed, "Analysis of macro-dataflow dynamic scheduling on non-uniform memory access architectures,"IEEE Trans. Parallel Distrib. Syst., vol. 19, no. 3, pp. 875-888, Nov. 1993.
[3] E. G. Coffman, al., Computer and Job-Shop Scheduling Theory. New York: John Willy, 1976.
[4] J.-J. Hwang, Y.-C. Chow, F. D. Anger, and C. Y. Lee, "Scheduling precedence graphs in systems with interprocessor communication times,"SIAM Computing, pp. 244-257, Apr. 1988.
[5] S. J. Kim and J. C. Browne, "A general approach to mapping of parallel computation upon multiprocessor architectures," inProc. Int. Conf. Parallel Processing, vol. 3, pp. 1-8, Aug. 1988.
[6] B. Kruatrachue, "Static task scheduling and grain packing in parallel processing systems," Ph.D. thesis, Dep. of Comput. Sci., Oregon State Univ., 1987.
[7] D. M. Pase, "A comparative analysis of static parallel schedulers where communication costs are significant," Ph.D. thesis, Oregon Graduate Inst. of Sci. and Technol., July 1989.
[8] V. Sarkar and J. Hennessy, "Compile-time partitioning and scheduling of parallel programs," inProc. SIGPLAN Symp. Compiler Construction, July 1986, pp. 17-26.
[9] G. C. Sih and E. A. Lee, "Scheduling to account for interprocessor communication within interconnection constrained processing network," inInt. Conf. Parallel Processing, vol. 1, 1990, 9-16.
[10] M.-Y. Wu and D. Gajski, "Hypertool: A programming aid for message-passing systems,"IEEE Trans. Parallel Distrib. Syst., vol. 1, no. 3, pp. 330-343, July 1990.

Index Terms:
Index Termsperformance evaluation; computational complexity; scheduling; message passing;performance evaluation; scheduling precedence-constrained computations;message-passing systems; multiprocessor topology; global priority-based schedulingheuristics; generalized list scheduling; backward scheduling; multiprocessor; graph-driven scheduling; network topology; time complexity
M. Al-Mouhamed, A. Al-Maasarani, "Performance Evaluation of Scheduling Precedence-Constrained Computations on Message-Passing Systems," IEEE Transactions on Parallel and Distributed Systems, vol. 5, no. 12, pp. 1317-1321, Dec. 1994, doi:10.1109/71.334905
Usage of this product signifies your acceptance of the Terms of Use.