This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Data-Driven Parallel Production Systems
March 1990 (vol. 16 no. 3)
pp. 281-293

Much effort has been expended on developing special architectures dedicated to the efficient execution of production systems. While data-flow principles of execution offer the promise of high programmability for numerical computations, it is shown that the data-driven principles can also be applied to symbolic computations. In particular, a mapping of the RETE match algorithm along the line of production systems is considered. Bottlenecks of the RETE match algorithm in a multiprocessor environment are identified and possible solutions are suggested. The modifications to the actor set as well as the program graph design are shown for execution on the tagged data-flow computer. The results of a deterministic simulation of this multiprocessor architecture demonstrate that artificial intelligence production systems can be efficiently mapped on data-driven architectures.

[1] Arvind and K. P. Gostelow, "The U-interpreter,"Computer, vol. 15, pp. 42-49, Feb. 1982.
[2] Arvind and R. A. Iannucci, "Two fundamental issues in multiprocessing: The data-flow solutions," MIT Lab. Comput. Sci., Rep. TM- 241, Sept. 1983.
[3] Arvind, V. Kathail, and K. Pingali, "A processing element for a large multiprocessor data-flow machine," inProc. IEEE Int. Conf. Circuits and Computers, Oct. 1980.
[4] Arvind and R. E. Thomas, "I-structures: An efficient data type for functional languages," MIT Lab. Comput. Sci., Rep. TM-178, June 1980.
[5] 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.
[6] L. Bic, "Processing of semantic nets on data-flow architecture,"Artificial Intell., vol. 27, pp. 219-227, 1985.
[7] L. Brownston et al.,Programming Expert Systems in OPS5, An Introduction to Rule-Based Programming, Addison Wesley, Reading, Mass., 1985, Chapter 4, pp. 161- 164.
[8] B. G. Buchanan and E. H. Shortliffe,Rule-Based Expert System, Reading, MA: Addison-Wesley, 1984.
[9] C. L. Forgy, "Rete: A fast algorithm for the many pattern/many object pattern match problem,"Artificial Intell., vol. 19, pp. 17-37, 1982.
[10] C. L. Forgy and A. Gupta, "Preliminary architecture of the CMU production system machine," inProc. 19th Annu. Hawaii Int. Conf. System Sciences, Jan. 1986, pp. 194-299.
[11] C. L. Forgy, A. Gupta, A. Newell, and R. Wedig, "Initial assessment of architectures for production systems," inProc. Nat. Conf. Artificial Intelligence, Aug. 1984, pp. 116-120.
[12] K. Furukawa, Deputy Director, ICOT Inst. New Generation Computer Technology, personal communication on Parallel Inference Machine (PIM), Detroit, MI, Aug. 1989.
[13] J. Gaschnig, "An expert system for mineral exploration," Infotech State of the Art Rep., series 9, no. 3, 1981.
[14] J. -L. Gaudiot and M. D. Ercegovac, "Performance evaluation of a simulated dataflow computer with low-resolution actors,"J. Parallel Distributed Comput., vol. 2, pp. 321-351, 1985.
[15] J.-L. Gaudiot, "Structure handling in data-flow systems,"IEEE Trans. Computers, vol. C-35, pp. 489-501, June 1986.
[16] J. -L. Gaudiot, "Data-driven multicomputers in digital signal processing applications,"Proc. IEEE, vol. 75, pp. 1220-1234, Sept. 1987.
[17] J. -L. Gaudiot, S. Lee, and A. Sohn, "Data-driven multiprocessor implementation of the Rete match algorithm," inProc. Int. Conf. Parallel Processing, vol. 1, pp. 256-260, Aug. 1988.
[18] E. Eder, "Properties of substitutions and unifications,"J. Symbolic Comput., vol. 1, pp. 31-46, 1985.
[19] J. D. Musa, "Tools for Measuring Software Reliability,"IEEE Spectrum, Feb. 1989, pp. 39-42; correction, April 1989, p. 8.
[20] A. Gupta, "Implementing OPS5 production systems on DADO," inProc. Int. Conf. Parallel Processing, Aug. 1984, pp. 83-91.
[21] A. Gupta, "Parallelism in production systems, Ph.D. dissertation, Dep. Comput. Sci., Carnegie-Mellon Univ., 1986.
[22] A. Gupta and M. Tambe, "Suitability of message passing computers for implementing production systems," inProc. Nat. Conf. Artificial Intelligence, Aug. 1988, pp. 687-692.
[23] T. Ishida and S. J. Stolfo, " Towards the parallel execution of rules in production system programs," inProc. Int. Conf. Parallel Processing, Aug. 1985, pp. 568-575.
[24] M. A. Kelly and R. E. Seviora, "A multiprocessor architecture for production system matching," inProc. Nat. Conf. Artificial Intelligence, Aug. 1987, pp. 36-41.
[25] J. McDermott, "RI: A rule-based configurer of computer systems,"Artificial Intell., vol. 19, pp. 39-88, 1982.
[26] D. P. Miranker, "TREAT: A better match algorithm for AI production systems," inProc. Nat. Conf. Artificial Intelligence, Aug. 1987, pp. 42-47.
[27] D. I. Moldovan, "A model for parallel processing of production systems," inProc. IEEE Int., Conf. Systems, Man, and Cybernetics, Oct. 1986, pp. 568-573.
[28] K. Olfazer, "Partitioning in parallel processing of production systems," inProc. Int. Conf. Parallel Processing, Aug. 1984, pp. 92- 100.
[29] A. O. Oshisanwo, and P. P. Dasiewicz, "A parallel model and architecture for production systems," inProc. Int. Conf. Parallel Processing, Aug. 1987, pp. 166-169.
[30] J. Quinlan, "A comparative analysis of computer architectures for production systems machines," inProc. 19th Annu. Hawaii Int. Conf. Systems Sciences, Jan. 1986, pp. 187-193.
[31] F. Schreiner and G. Zimmermann, "PESA-1: A parallel architecture for production systems," inProc. Int. Conf. Parallel Processing, Aug. 1987, pp. 166-169.
[32] M. Schor, D. Daly, H. S. Lee, and R. Tibbitts, in "Advances in RETE pattern matching," inProc. Nat. Conf. Artificial Intelligence, Aug. 1986, pp. 226-232.
[33] D. E. Shaw, "On the range of applicability of an artificial intelligence machine,"Artificial Intell.vol. 32, pp. 151-172, 1987.
[34] A. Sohn and J. -L. Gaudiot, "Multilayer of ring-structured feedback network for production system processing," inProc. IEEE Int. Workshop Tools for AI, Oct. 1989.
[35] M. E. Kopache and E. P. Glinert, "C2: A mixed textual/graphical environment for C," inProc. IEEE Workshop Visual Languages. 1988, pp. 231-238.
[36] S. J. Stolfo, "Five parallel algorithms for production system execution on the DADO machine," inProc. Nat. Conf. Artificial Intelligence, Aug. 1984, pp. 300-307.
[37] S. Stolfo, "Initial performance of the DADO-2 prototype,"IEEE Comput. Mag., vol. 20, no. 1, pp. 75-83, 1987.
[38] S. J. Stolfo and D. P. Miranker, "DADO: A parallel processor for expert systems," inProc. Int. Conf. Parallel Processing, Aug. 1984, pp. 74-82.
[39] S.J. Stolfo and D.P. Miranker, "The DADO production system machine,"J. Parallel Distributed Comput., vol. 3, pp. 269-296, June 1986.
[40] M. F. M. Tenorio and D. I. Moldovan, "Mapping production systems into multiprocessors," inProc. Inf. Conf. Parallel Processing, Aug. 1985, pp. 56-62.
[41] B. W. Wah, M. B. Lowrie, and G. -J. Li, "Computers for symbolic processing,"Proc., IEEE, vol. 77, pp. 509-540, Apr. 1989.

Index Terms:
parallel production systems; data-flow principles; high programmability; numerical computations; data-driven principles; symbolic computations; RETE match algorithm; multiprocessor environment; actor set; program graph design; tagged data-flow computer; deterministic simulation; multiprocessor architecture; artificial intelligence production systems; data-driven architectures; expert systems; parallel architectures; parallel programming; symbol manipulation.
Citation:
J.L. Gaudiot, A. Sohn, "Data-Driven Parallel Production Systems," IEEE Transactions on Software Engineering, vol. 16, no. 3, pp. 281-293, March 1990, doi:10.1109/32.48936
Usage of this product signifies your acceptance of the Terms of Use.