This Article 
 Bibliographic References 
 Add to: 
Noncontiguous Processor Allocation Algorithms for Mesh-Connected Multicomputers
July 1997 (vol. 8 no. 7)
pp. 712-726

Abstract—Current processor allocation techniques for highly parallel systems are typically restricted to contiguous allocation strategies for which performance suffers significantly due to the inherent problem of fragmentation. As a result, message-passing systems have yet to achieve the high utilization levels exhibited by traditional vector supercomputers. We are investigating processor allocation algorithms which lift the restriction on contiguity of processors in order to address the problem of fragmentation.

Three noncontiguous processor allocation strategies—Paging allocation, Random allocation, and the Multiple Buddy Strategy (MBS)—are proposed and studied in this paper. Simulations compare the performance of the noncontiguous strategies with that of several well-known contiguous algorithms. We show that noncontiguous allocation algorithms perform better overall than the contiguous ones, even when message-passing contention is considered. We also present the results of experiments on an Intel Paragon XP/S-15 with 208 nodes that show noncontiguous allocation is feasible with current technologies.

[1] A. Al-Dhelaan and B. Bose,“A new strategy for processor allocation in an n-cube multiprocessor,” Proc. Int’l Phoenix Conf. Computers and Comm., pp. 114-118, Mar. 1989.
[2] D.H. Bailey, E. Barszcz, L. Dagum, and H.D. Simon, "NAS Parallel Benchmark Results 3-94," Technical Report RNR-94-006, NASA Ames Research Center, Moffett Field, Calif., Mar. 1994.
[3] S. Bhattacharya, L.M. Ni, and W. Tsai, "Lookahead Processor Allocation in Mesh-Connected Massively Parallel Computers," technical report, Univ. of Minnesota (Bhattacharya and Tsai) and Michigan State Univ. (Ni), 1993.
[4] J. Carbajal, D. Cameron, and Y. Zhu, "Node Allocation for the Mesh-Connected Paragon Supercomputer," personal comm., Apr. 1994.
[5] M. S. Chen and K. G. Shin,“Processor allocation in an$N$-cube multiprocessor using gray codes,”IEEE Trans. Comput., vol. C-37, pp. 1396–1407, Dec. 1987.
[6] M. S. Chen and K. G. Shin,“Processor allocation in an$N$-cube multiprocessor using gray codes,”IEEE Trans. Comput., vol. C-37, pp. 1396–1407, Dec. 1987.
[7] P.J. Chuang and N.F. Tzeng, “An Efficient Submesh Allocation Strategy for Mesh Computer Systems,” Proc. Int'l Conf. Distributed Computing Systems, pp. 256-263, May 1991.
[8] Intel Corp., Paragon Network Queuing System Manual, Oct. 1993.
[9] W.J. Dally and C.L. Seitz, "The Torus Routing Chip," Distributed Computing, 1986.
[10] S. Dutt and J.P. Hayes, "Subcube Allocation in Hypercube Computers," IEEE Trans. Computers, vol. 40, no. 3, pp. 341-352, Mar. 1991.
[11] D.G. Feitelson, "A Survey of Scheduling in Multiprogrammed Parallel Systems," Technical Report RC 19790 (87657), IBM Research Division, T.J. Watson Research Center, Yorktown Heights, N.Y., Oct. 1994.
[12] M.L. Fulgham and L. Snyder, "Performance of Chaos and Oblivious Routers under Non-Uniform Traffic," technical report, Univ. of Washington, 1993.
[13] J. Kim, C.R. Das, and W. Lin, “A Top-Down Processor Allocation Scheme for Hypercube Computers,” IEEE Trans. Parallel and Distributed Systems, vol. 2, no. 1, pp. 20-30, Jan. 1991.
[14] D.E. Knuth, Fundamental Algorithms: Volume 1. Addison-Wesley, 1973.
[15] P. Krueger, T.H. Lai, and V.A. Radiya, “Job Scheduling Is More Important than Processor Allocation for Hypercube Computers,” IEEE Trans. Parallel and Distributed Systems, vol. 5, no. 5, pp. 488-497, May 1994.
[16] V. Kumar, A. Grama, A. Gupta, and G. Karypis, Introduction to Parallel Computing: Design and Analysis of Algorithms. Benjamin Cummings, 1994.
[17] K. Li and K.-H. Cheng, “A Two-Dimensional Buddy System for Dynamic Resource Allocation in a Partitionable Mesh Connected Systems,” J. Parallel and Distributed Computing, vol. 12, pp. 79-83, 1991.
[18] W. Liu, V. Lo, K. Windisch, and B. Nitzberg, "Non-Contiguous Processor Allocation Algorithm for Distributed Memory Multicomputers," Proc. Supercomputing '94, pp. 227-236,Washington D. C., 1994.
[19] B. MacCabe and K. McCurley, "SUNMOS for the Intel Paragon," unpublished, 1993.
[20] M. MacDougall, Simulating Computer Systems: Techniques and Tools,Cambridge, Mass.: MIT Press, 1987.
[21] P. Mohapatra, C. Yu, C.R. Das, and J. Kim, "A Lazy Scheduling Scheme for Improving Hypercube Performance," Proc. Int'l Conf. Parallel Processing, 1993.
[22] V. Naik, S. Setia, and M. Squillante, "Performance Analysis of Job Scheduling Policies in Parallel Supercomputing Environments," Supercomputing, pp. 824-833, 1993.
[23] B. Narahari and R. Krishnamurti, "Scheduling Independent Tasks on Partitionable Hypercube Multiprocessors," Proc. Int'l Parallel Processing Symp., 1993.
[24] L.M. Ni and P.K. McKinley, "A Survey of Wormhole Routing Techniques in Direct Networks," Computer, vol. 26, no. 2, pp. 62-76, Feb. 1993.
[25] J.L. Peterson and T.A. Norman,"Buddy Systems," Comm. ACM, vol. 20, pp. 421-431, June 1977.
[26] C. L. Seitz,“The cosmic cube,”CACM, vol. 28, pp. 22–33, Jan. 1985.
[27] B. VanVoorsst, S. Seidel, and E. Barszcz, "Profiling the Communication Workload of an iPSC/860," Proc. Scalable High Performance Computing Conf., May 1994.
[28] M. Wan, R. Moore, G. Kremenek, and K. Steube, "A Batch Scheduler for the Intel Paragon MPP System with a Non-Contiguous Node Allocation Algorithm," Proc. Second Workshop Job Scheduling Strategies for Parallel Processing, IPPS '96, 1996.
[29] K. Windisch, V.M. Lo, and B. Bose, "Contiguous and Non-Contiguous Processor Allocation Algorithms for k-ary n-cubes," Proc. Int'l Conf. Parallel Processing, 1995.
[30] K. Windisch, J.V. Miller, and V. Lo, “ProcSimity: An Experimental Tool for Processor Allocation and Scheduling in Highly Parallel Systems,” Proc. Fifth Symp. the Frontiers of Massively Parallel Computation, pp. 414–421, Feb. 1995.
[31] Y. Zhu, "Efficient Processor Allocation Strategies for Mesh-Connected Parallel Computers," J. Parallel and Distributed Computing, vol. 16, pp. 328-337, 1992.

Index Terms:
Resource management, scheduling, processor allocation, noncontiguous, fragmentation, mesh.
Virginia Lo, Kurt J. Windisch, Wanqian Liu, Bill Nitzberg, "Noncontiguous Processor Allocation Algorithms for Mesh-Connected Multicomputers," IEEE Transactions on Parallel and Distributed Systems, vol. 8, no. 7, pp. 712-726, July 1997, doi:10.1109/71.598346
Usage of this product signifies your acceptance of the Terms of Use.