This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Block Scheduling of Iterative Algorithms and Graph-Level Priority Scheduling in a Simulated Data-Flow Multiprocessor
April 1993 (vol. 4 no. 4)
pp. 398-413

Iterative methods for solving linear systems are discussed. Although these methods areinherently highly sequential, it is shown that much parallelism could be exploited in adata-flow system by scheduling the iterative part of the algorithms in blocks and bylooking ahead across several iterations. This approach is general and will apply to otheriterative and loop-based problems. It is also demonstrated by simulation that relyingsolely on data-driven scheduling of parallel and unrolled loops results in low resourceutilization and poor performance. A graph-level priority scheduling mechanism has beendeveloped that greatly improves resource utilization and yields higher performance.

[1] J. Backus, "Can programming be liberated from the von Neumann style? A functional style and its algebra of programs,"Commun. ACM, vol. 21, no. 8, pp. 613-641, Aug. 1978.
[2] Arvind and R. Iannucci, "Two fundamentals issues in multiprocessors: The Data-Flow solutions," Tech. Rep. LCS/TM-241, Lab. for Comput Sci., Massachusetts Instit. Technol., Cambridge, MA, Sept. 1983.
[3] J. B. Dennis,First Version of a Data Flow Procedure Language. New York: Springer-Verlag, Apr. 1974, pp. 362-376.
[4] Arvind, K. Gostelow, and W. Plouffe, "An asynchronous programming language and computing machine," Tech. Rep. TR-114a, Dep. Inform. Comput. Sci., Univ. California Irvine, Dec. 1978.
[5] I. Watson and J. Gurd, "A prototype dataflow computer with token labeling," inProc. Nat. Comput. Conf., AFIPS Proc., vol. 48, 1979.
[6] G. Dahliquist and A. Bjork,Numerical Methods. Englewood Cliffs, NJ: Prentice-Hall, 1974.
[7] Birkhoff and Lynch,Numerical Solutions of Elliptic Problems. SIAM studies in Applied Math, 1984.
[8] Arvind and R. A. Iannucci, "A critic of multiprocessing von Neumann style," inProc. 10th Annu. Symp. Comput. Architecture, June 1983, pp. 426-436.
[9] Arvind and K. Gostelow, "The U-Interpreter,"IEEE Comput. Mag., pp. 42-49, Feb. 1982.
[10] Arvind and R. S. Nikhil, "Executing a program on the MIT tagged-token dataflow architecture," inProc. Parallel Architectures and Languages in Europe (PARLE), Springer-Verlag LNCS no. 259, June 1987, pp. 1-29.
[11] J. R. Gurd, C. C. Kirkham, and I. Watson, "The Manchester prototype dataflow computer,"Commun. ACM, vol. 28, no. 1, pp. 34-52, Jan. 1985.
[12] D. P. Bertsekas and J. N. Tsitsiklis,Parallel and Distributed Computations. Englewood Cliffs, NJ: Prentice-Hall, 1989.
[13] E. Eder, "Properties of substitutions and unifications,"J. Symbolic Comput., vol. 1, pp. 31-46, 1985.
[14] D. E. Culler, "Resource management for the tagged token dataflow architecture," Lab. Comput. Sci., Mass. Inst. Technol., M.I.T./LCS/ TR-322, 1985.
[15] J. McGraw, S. Skedzielewski, S. Allan, D. Grit, R. Oldehoeft, J. Glauert, I. Dobes, and P. Hohensee, "SISAL-streams and iterations in a single assignement language, Language reference manual, version 1.2," Tech. Rep. TR M-146, Univ. California-Lawrence Livermore Laboratory, Mar. 1985.
[16] J.-L. Gaudiot, "Structure handling in data-flow systems,"IEEE Trans. Computers, vol. C-35, pp. 489-501, June 1986.
[17] Arvind and R. Thomas, "I-structures: An efficient data type for functional languages," Tech. Rep. LCS/TM-178, Massachusetts Instit. Technol., Lab. Comput. Sci., June 1980.
[18] P. Evripidou and J.-L. Gaudiot, "Iterative algorithms in a data-driven environment," inProc. 1988 Int. Conf. Parallel Processing, Aug. 1988.
[19] P. Evripidou and J.-L. Gaudiot, "Some scheduling techniques for numerical algorithms in a simulated Data-Flow multiprocessor," inProceedings of the Parallel Computing 89. Amsterdam: Elsevier Science Publishers B.V., Aug. 1989.
[20] G. Smith,Numerical Solution of Partial Differential Equations: Finite Difference Methods. Oxford, England: Clarendon, 1985.
[21] A. Bohm, J. Gurd, and Y. Teo, "The effect of iterative instructions in dataflow computers," inProc. 1989 Int. Conf. Parallel Processing, 1989.
[22] P. Evripidou and J.-L. Gaudiot, "A decoupled graph/computation data-driven architecture with variable resolution actors," inProc. 1990 Int. Conf. Parallel Processing, Aug. 1990.

Index Terms:
Index Termsblock scheduling; iterative algorithms; graph-level; priority scheduling; data-flowmultiprocessor; linear systems; parallelism; scheduling; iterative methods; parallelalgorithms; scheduling
Citation:
P. Evripidou, J.L. Gaudiot, "Block Scheduling of Iterative Algorithms and Graph-Level Priority Scheduling in a Simulated Data-Flow Multiprocessor," IEEE Transactions on Parallel and Distributed Systems, vol. 4, no. 4, pp. 398-413, April 1993, doi:10.1109/71.219755
Usage of this product signifies your acceptance of the Terms of Use.