Abstract
Partitioning of processors on a multiprocessor system involves logically dividing the system into processor partitions. Programs can be executed in the different partitions in parallel. Optimally setting the partition size can significantly improve the throughput of multiprocessor systems. The speedup characteristics of parallel programs can be defined by execution signatures. The execution signature of a parallel program on a multiprocessor system is the rate at which the program executes in the absence of other programs and depends upon the number of allocated processors, the specific architecture, and the specific program implementation. Based on the execution signatures, this paper analyzes simple Markovian models of dynamic partitioning. From the analysis, when there are at most two multiprocessor partitions, the optimal dynamic partition size can be found which maximizes throughput. Compared against other partitioning schemes, the dynamic partitioning scheme is shown to be the best in terms of throughput when thereconfiguration overhead is low. If the reconfiguration overhead is high, dynamic partitioning is to be avoided. An expression for the reconfiguration overhead threshold is derived. A general iterative partitioning technique is presented. It is shown that the technique gives maximum throughput forn partions.
Similar content being viewed by others
References
S. H. Bokhari, Partitioning problems in parallel, pipelined, and distributed computing,IEEE Trans. Computers,37(1):48–57 (January 1988).
T. C. K. Chou and J. A. Abraham, Load balancing in distributed systems,IEEE Trans. S.E.,SE-8(4):401–412 (July 1982).
E. G. Coffman Jr, Ed.,Computer and Job-Shop Scheduling Theory, John Wiley & Sons, New York (1976).
D. M. Nicol, Optimal partitioning of random programs across two processors,IEEE Trans. S.E.,15(2):134–141 (February 1989).
D. M. Nicol and J. H. Saltz, Dynamic remapping of parallel computations with varying resource demands,IEEE Trans. Computers,37(9):1073–1087 (September 1988).
A. N. Tantawi and D. Towsley, Optimal static load balancing in distributed computer systems,J. ACM,32:445–565 (April 1985).
L. W. Dowdy, On the partitioning of multiprocessor systems, (submitted for publication). Also,Technical Report, Department of Computer Science, Vanderbilt University, Nashville, TN 37235 (March 1988).
G. M. Amdahl, Validity of the single-processor approach to achieving large scale computing capabilities,Proc. AFIPS Conf.,30:483–485 (1967).
D. L. Eager, J. Zahorjan, and E. D. Lazowska, Speedup versus efficiency in parallel systems,IEEE Trans. Computers,38(3):408–423 (March 1989).
M. R. Leuze, L. W. Dowdy, and K. H. Park,Multiprogramming a distributed-memory multiprocessor, Concurrency: Practice and Experience,1(1):19–33 (September 1989).
S. D. Conte and C. de Boor,Elementary Numerical Analysis: An Algorithmic Approach, 3rd. ed., McGraw-Hill (1980).
B. Fox, Discrete optimization via marginal analysis,Management Science,13(3):210–216 (November 1966).
G. N. Frederickson and D. B. Johnson, The complexity of selection and ranking inX+Y and matrices with sorted columns,J. of Computer and System Sciences,24:197–208 (1982).
K. Dussa, B. Carlson, L. Dowdy, and K-H Park,Dynamic Partitioning in a Transputer Environment, To appear in ACM Sigmetrics Conference (1990).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Park, KH., Dowdy, L.W. Dynamic partitioning of multiprocessor systems. Int J Parallel Prog 18, 91–120 (1989). https://doi.org/10.1007/BF01491212
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01491212