This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Source-to-Source Transformation for Increasing Rule-Based System Parallelism
August 1992 (vol. 4 no. 4)
pp. 336-343

Rule-based systems have been hypothesized to contain only minimal parallelism. However, techniques to extract more parallelism from existing systems are being investigated. Among these methods, it is desirable to find those which balance the work being performed in parallel evenly among the rules, while decreasing the amount of work being performed sequentially in each cycle. The automatic transformation of creating constrained copies of culprit rules accomplishes both of the above goals. Rule-based systems are plagued by occasional rules which slow slow down the entire execution. These culprit rules require much more processing than others, causing other processors to idle while they continue to match. By creating constrained copies of culprit rules and distributing them to their own processors, more parallelism is achieved, as evidenced by increased speed up. This effect is shown to be specific to rule-based systems with certain characteristics. These characteristics are identified as being common within an important class of rule-based systems: expert database systems.

[1] F. Barachini, "PAMELA: A rule-based AI Language for process-control applications," inProc. First Int. Conf. on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, 1988, pp. 860-867.
[2] C. L. Forgy, "On the efficient implementation of production systems," Ph.D. dissertation, Dept. Computer Science, Carnegie-Mellon Univ., Pittsburgh, PA, Feb. 1979.
[3] C. L. Forgy, "Rete: A fast algorithm for the many pattern/many object pattern match problem,"Artif. Intell.vol. 19, no. 1, pp. 17-37, 1982.
[4] C. L. Forgy and J. McDermott, "OPS, A domain-independent production system language," inProc Int. Joint Conf. on Artificial Intelligence, 1977.
[5] D. Gordin and C. Castillo, "OD: A generic interface between production systems and relational databases," inProc. IASTED Int. Symp. Expert Systems Theory and Applications, 1989.
[6] D. Gordin, D. Foxvog, J. Rowland, P. Surko, and G. T. Vesonder, "OKIES: A troubleshooter in the factory," inProc. First Int. Conf. on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, 1988.
[7] A. Gupta, "Parallelism in production systems: The sources and expected speed-up," Tech. Rep., Dep. Comput. Sci., Carnegie-Mellon Univ., 1984.
[8] A. Gupta, "Parallelism in production systems, Ph.D. dissertation, Dep. Comput. Sci., Carnegie-Mellon Univ., 1986.
[9] A. Gupta, C. L. Forgy, D. Kalp, A. Newell, and M. Tambe, "results of parallel implementation of OPS5 on the encore multiprocessor," Tech. Rep. CMU-CS-87-146, Dep. Comput. Sci., Carnegie-Mellon Univ., 1987.
[10] W. D. Hillis,The Connection Machine. Cambridge, MA: MIT Press, 1985.
[11] D. P. Miranker, "TREAT: A new and efficient match algorithm for AI production systems," Ph.D. dissertation, Dep. Comput. Sci., Columbia Univ., 1986.
[12] A. J. Pasik, "A methodology for programming production systems and its implications on parallelism," Ph.D. dissertation, Dep. Comput. Sci., Columbia Univ., 1989.
[13] A. J. Pasik and M. I. Schor, "Table-driven rules in expert systems,"SIGART Newslett.vol. 87, pp. 31-33, 1984.
[14] A. J. Pasik and S. J. Stolfo, "Improving production system performance on parallel architectures by creating constrained copies of rules," Tech. Rep. CUCS-313-87, Dep. Comput. Sci., Columbia Univ., 1987.
[15] D. Scales, "Efficient matching algorithms for the SOAR/OPS5 production system," Tech. Rep., Knowledge Systems Lab., Comput. Sci. Dep., Stanford Univ., 1986.
[16] M. I. Schor, T. P. Daly, H. S. Lee, and B. R. Tibbitts, "Advances in Rete pattern matching," inProc. American Association for Artificial Intelligence, 1986, pp. 226-232.
[17] T. K. Sellis, C.-C. Lin, and L. Raschid, "Implementing large production systems in a DBMS environment: Concepts and algorithms," inProc. ACM SIGMOD Int. Conf. Management Data, Chicago, IL, 1988.
[18] S. J. Stolfo, "Five parallel algorithms for production system execution on the DADO machine," inProc. American Association for Artificial Intelligence, 1984.
[19] S. J. Stolfo and D. P. Miranker, "DADO: A parallel processor for expert systems," inProc. IEEE Int. Conf. on Parallel Processing, 1984.
[20] S. J. Stolfo and D. P. Miranker, "DADO: A tree-structured architecture for artificial intelligence computation,"Ann. Rev. Comput. Sci.vol. 1, pp. 1-18, 1986.
[21] J. D. Ullman,Principles of Database DesignRockville, MD: Computer Science, 1982.
[22] G. T. Vesonder, "Rule-based programming in the Unix System,"AT&T Tech. J., vol. 67, no. 1, pp. 69-80, 1988.
[23] G. T. Vesonder, S. J. Stolfo, J. Zielinski, F. Miller, and D. Copp, "ACE: An expert system for telephone cable maintenance,Proc. Int. Joint Conf. on Artificial Intelligence, 1983.

Index Terms:
source-to-source transformation; rule-based system parallelism; minimal parallelism; automatic transformation; constrained copies; culprit rules; expert database systems; database management systems; knowledge based systems; logic programming; parallel programming
Citation:
A.J. Pasik, "A Source-to-Source Transformation for Increasing Rule-Based System Parallelism," IEEE Transactions on Knowledge and Data Engineering, vol. 4, no. 4, pp. 336-343, Aug. 1992, doi:10.1109/69.149929
Usage of this product signifies your acceptance of the Terms of Use.