This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Rough Grammar for Efficient and Fault-Tolerant Computing on a Distributed System
July 1991 (vol. 17 no. 7)
pp. 652-668

A method that combines global load balancing with dynamic task scheduling on a multiprocessor machine is presented. This method does not require prior knowledge of the run times of tasks, and is based on a rough grammar representing distributed computation is presented. Production rules are dynamically constructed when a concurrent program is run. The set of the rough grammar production rules is updated and rolled in a pipeline fashion, together with codes of the processes. This pipeline fashion of rolling the jobs defines the global job balancing. The rough grammar uses any operators and metrics, not only concatenation, inside its production rules. Performance parameters for the combination of a global load balancing and decentralized dynamic task scheduling are derived and compared with those for a statically scheduled multiprocessor. Based on these parameters, the decentralized methodology is shown to attain a much higher performance level and a highly improved fault tolerance.

[1] I. Ahmad, "A semi distributed load balancing scheme for large multicomputer system," inProc. 2nd IEEE Symp. Parallel and Distributed Processing(Dallas, TX), Dec. 1990, pp. 562-569.
[2] D. H. Ballard and C. M. Brown,Computer Vision. Englewood Cliffs, NJ: Prentice-Hall, 1982.
[3] J. Barhen and E. C. Halbert, "Roses: An efficient scheduler for precedence-constraint processes on concurrent multiprocessors," inHypercube Multiprocessors 1986, M. T. Heath, Ed. Philadelphia: 1986, pp. 123-147.
[4] R. Bettati and J. W. Liu, "Algorithms for end-to-end scheduling to meet deadlines," inProc. 2nd IEEE Symp. Parallel and Distributed Processing(Dallas, TX), Dec. 1990, pp. 62-67.
[5] H. A. Choi and B. Narahari, "Scheduling precedence graphs to minimize total system time in partitionable parallel architectures," inProc. 2nd IEEE Symp. Parallel and Distributed Processing(Dallas, TX), Dec. 1990, pp. 402-406.
[6] D. I. A. Cohen,Introduction to Computer Theory.New York: Wiley, 1988.
[7] G. R. Dattatreya and R. Venkatesh, "Average response time minimization in star-connected computer network," inProc. 2nd IEEE Symp. Parallel and Distributed Processing(Dallas, TX), Dec. 1990, pp. 591-594.
[8] E. W. Dijkstra and C. S. Scholten, "Termination detection for diffusing computation,"Inf. Process. Lett., vol. 11, pp. 1-4, Aug. 1980.
[9] J. R. Einstein, J. Barhen, and D. Jefferson, "Virtual time operating system functions for robotics applications on a hvpercube," inHypercube Multiprocessors 1987.Philadelphia: SIAM, 1987, pp. 100-107.
[10] G. C. Fox, A. Kolawa, and R. Williams, "The implementation of a dynamic load balancer," inHypercube Multiprocessors 1987. M.T. Heath, Ed. Philadelphia: SIAM, 1987, pp. 114-121.
[11] G. A. Geist and M. T. Heath, "Matrix factorization on a hypercube multiprocessor," inHypercube Multiprocessors 1986, M. T. Heath, Ed. Philadelphia: SIAM, 1986, pp. 161-180.
[12] E. Gelembe,Multiprocessor Performance. New York: Wiley, 1989.
[13] D. W. Gillies and J. W. S. Liu, "Scheduling tasks with AND/OR precedence constraints," inProc. 2nd IEEE Symp. Parallel and Distributed Processing(Dallas, TX), Dec. 1990, pp. 394-401.
[14] M. J. Gonzalez and C. V. Ramamoorthy, "Parallel process execution in a decentralized system,"IEEE Trans. Comput., vol. C-21, pp. 1310-1322, 1972.
[15] E.K. Haddad, "Optimal partitioning of random workloads in homogeneous multiprocessor and distributed systems," inProc. 2nd IEEE Symp. Parallel and Distributed Processing(Dallas, TX), Dec. 1990, pp. 386-393.
[16] C. A. R. Hoare, "Communicating sequential processes,"Commun. ACM, vol. 21, pp. 666-677, 1978.
[17] J. Ji and K. Jeng, "Bin packing adjustable rectangles and applications to task scheduling on partitionable parallel computers," inProc. 2nd IEEE Symp. Parallel and Distributed Processing(Dallas, TX), Dec. 1990, pp. 312-315.
[18] D. Jefferson and B. Beckman, "Virtual time and time warp on the JPL hypercube," inHypercube Multiprocessors, M. T. Heath, Ed. Philadelphia: SIAM, 1986, p. 111-122.
[19] H. P. Katseff, "Incomplete hypercubes," inHypercube Multiprocessors 1987.Philadelphia: SIAM, 1987, pp. 258-264.
[20] M. L. Mathews, "Hypercube software performance metrics," inHypercube Multiprocessors, M. T. Heath, Ed. Philadelphia: SIAM, 1986, pp. 155-160.
[21] Z. Pawlak, "Rough classification,"Int. J. Man-Machine Studies, vol. 20, pp. 469-483, 1984.
[22] C. V. Ramamoorthy and M. J. Gonzalez, "A survey techniques for recognizing parallel processable streams in computer programs," in1969 Fall Joint Comput. Conf., AFIPS Conf. Proc., pp. 1-17.
[23] G. C. Sih and E. A. Lee, "Dynamic-level scheduling for heterogeneous processor networks," inProc. 2nd IEEE Symp. Parallel and Distributed Processing(Dallas, TX), Dec. 1990, pp. 42-49.
[24] H. Sulivan and T. R. Bashkov, "A large scale homogeneous, fully distributed parallel machine, I," inProc. 4th Symp. Comput. Arch., March 1977, pp. 105-117.
[25] W. I. Williams, "Load balancing and hypercubes: A preliminary look," inHypercube Multiprocessors 1987, M. T. Heath, Ed. Philadelphia: SIAM, 1987, pp. 108-113.
[26] Z. M. Wójcik, "Rough approximation of shapes in pattern recognition,"CVGIP, vol. 40, pp. 228-249, 1987.
[27] Z. M. Wójcik, "The rough grammar for the parallel shape coding," inProc. ACM South Central Regional Conf. (Tulsa), Nov. 1989, pp. 84-90.
[28] B. E. Wójcik and Z. M. Wójcik, "Sufficient condition for a communication deadlock and distributed deadlock detection,"IEEE Trans. Software Eng., vol. 15, pp. 1587-1595, Dec. 1989.
[29] Z. M. Wójcik and B. E. Wójcik, "Fault tolerant distributed computing using atomic send-receive checkpoints," inProc. 2nd IEEE Symp. Parallel and Distributed Processing(Dallas, TX), Dec. 1990, pp. 212-222.
[30] Z. M. Wójcik and B. E. Wójcik, "A rough grammar for a linguistic recognition of image patches,"Signal Processing, vol. 19, pp. 119-138, 1990.
[31] J. Xu and K. Hwang, "Dynamic balancing for parallel program execution on a message-passing multicomputer," inProc. 2nd IEEE Symp. Parallel and Distributed Processing(Dallas, TX), Dec. 1990, pp. 402-406.

Index Terms:
fault-tolerant computing; global load balancing; dynamic task scheduling; multiprocessor machine; rough grammar; distributed computation; concurrent program; rough grammar production rules; pipeline fashion; statically scheduled multiprocessor; decentralized methodology; fault tolerance; fault tolerant computing; grammars; parallel processing; pipeline processing; scheduling
Citation:
Z.M. Wojcik, B.E. Wojcik, "Rough Grammar for Efficient and Fault-Tolerant Computing on a Distributed System," IEEE Transactions on Software Engineering, vol. 17, no. 7, pp. 652-668, July 1991, doi:10.1109/32.83902
Usage of this product signifies your acceptance of the Terms of Use.