This Article 
 Bibliographic References 
 Add to: 
Optimal Scheduling of Compute-Intensive Tasks on a Network of Workstations
June 1995 (vol. 6 no. 6)
pp. 668-673

Abstract—In a network of high performance workstations, many workstations are underutilized by their owners. The problem of using these idle cycles for solving computationally intensive tasks by executing a large task on many workstations has been addressed before [1] and algorithms with $O(N^2)$ time and $O(N)$ space for choosing the optimal subset of workstations out of $N$ workstations were presented. We improve these algorithms to reduce the running time to $O(N \log N)$, while keeping the space requirement the same. The proposed algorithms are particularly useful for SPMD parallelism where computation is the same for all workstations and the data space is partitioned between the workstations.

Index Terms—Task scheduling, SPMD computations, resource allocation, distributed operating systems, networks of workstations.

[1] M. J. Atallah, C. L. Black, D. C. Marinescu, H. J. Seigel, and T. L. Casavant,“Models and algorithms for coscheduling compute-intensive tasks on a network of workstations,”J. Parallel Distrib. Comput., vol. 16, pp. 319–327, 1992.
[2] S. B. Gershwin,“Hierarchical flow control: A framework for scheduling and planning discrete events in manufacturing systems,”Proc. IEEE, pp. 195–209, Jan. 1989.
[3] H. Clark and B. McMillin,“DAWGS—A distributed compute Srever utilizing idle workstations,”J. Parallel Distrib. Comput., pp. 175–186, Feb. 1992.
[4] F. Douglis and J. Ousterhout,“Process migration in the Sprite operating system,”inProc. 7th Int. Conf. Distrib. Comput. Syst., 1987, pp. 18–25.
[5] K. Efe and M. Schaar,“Performance of coscheduling on a network of workstations,”inProc. 13th Int. Conf. Distrib. Comput. Syst., 1993, pp. 525–531.
[6] G. P. Engelberg, J. A. Howard, and D. A. Mellichamp,“Job scheduling in a single-node hierarchical network for process control,”IEEE Trans. Comput., vol. C-29, pp. 710–719, Aug. 1980.
[7] R. Hagman,“Process server: Sharing processing power in a workstation environment,”inProc. 6th Int. Conf. Distrib. Comput. Syst., 1986, pp. 260–267.
[8] C. K. Koc and S. C. Gan,“Parallel matrix multiplication on networked microcomputers,”Comput. Elec. Eng., vol. 18, no. 2, pp. 145–152, 1992.
[9] L. Kleinrock and W. Korfhage,“Collecting unused processing capacity: An analysis of transient distributed system,”inProc. 9th Int. Conf. Distrib. Comput. Syst., June 1989, pp. 482–489.
[10] P. Krueger and R. Chawla,“The stealth distributed scheduler,”inProc. 11th Int. Conf. Distrib. Comput. Syst., 1991, pp. 336–343.
[11] M. J. Litzkow, M. Livny, and M. W. Mutka,“Condor—A hunter of the idle workstations,”inProc. 8th Int. Conf. Distrib. Comput. Syst., 1988, pp. 104–111
[12] J. K. Ousterhout,“Scheduling techniques for concurrent systems,”inProc. 3rd Int. Conf. Distrib. Comput. Syst., Oct. 1982, pp. 22–30
[13] J. K. Ousterhout, A. R. Cherenston, F. Douglis, M. N. Nelson, and B. B. Welch,“The Sprite network operating system,”Comput., pp. 23–36, Feb. 1988.
[14] S. Pulidas, D. Towsley, and J. A. Stankovic,“Imbedding gradient estimators in load balancing algorithms,”inProc. 8th Int. Conf. Distrib. Comput. Syst., San Jose, CA, June 13–17, 1988, pp. 482–490.
[15] M. C. Rinard, D. J. Scales and M. S. Lam,“Heterogeneous parallel programming in Jade,”inProc. Supercomputing '92, no. 16–20, 1992, pp. 245–256.
[16] W. Shang and J. A. B. Fortes,“Independent partitioning of uniform dependency algorithms,”IEEE Trans. Comput., vol. 41, pp. 190–206, Feb. 1992.
[17] A. S. Tanenbaum and S. J. Mullender,“An overview of the Amoeba distributed operating system,”ACM Oper. Syst. Rev., vol. 15, no. 3, pp. 51–64, July 1981.

Kemal Efe, Venkatesh Krishnamoorthy, "Optimal Scheduling of Compute-Intensive Tasks on a Network of Workstations," IEEE Transactions on Parallel and Distributed Systems, vol. 6, no. 6, pp. 668-673, June 1995, doi:10.1109/71.388049
Usage of this product signifies your acceptance of the Terms of Use.