This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Parallel Knowledge Processing on SNAP
February 1993 (vol. 5 no. 1)
pp. 65-75

The semantic network array processor (SNAP) is a specialized, highly parallel architecture for knowledge representation and reasoning. The instruction set has been carefully designed to reflect the requirements of semantic network processing. SNAP is a marker propagation architecture, where the passing of markers between cells plays a fundamental role. The movement of markers between cells is controlled by a set of propagation rules. Various reasoning mechanisms were implemented using these propagation rules. A simulator was developed, and knowledge processing examples, such as inheritance, recognition, and classification, were tested. By comparing the simulation results with the same examples run on the Connection Machine, it was found that SNAP outperforms the Connection Machine over a broad range of knowledge processing examples by a factor of 1000 or more.

[1] R. J. Brachman and J. G. Schmolze, "An overview of the KL-ONE knowledge representation system,"Cognitive Sci., vol. 9, pp. 171-216, 1985.
[2] M. H. Chung and D. Moldovan, "SNAP simulation of the connectionist approach to knowledge representation and reasoning," Tech. Rep. PKPLab-90-12, Dep. of Elect. Eng.-Syst., Univer of Southern California, 1990.
[3] S. Chung and D. Moldovan, "Modeling semantic networks on the Connection Machine," Tech. Rep. PKPLab-90-2, Dep. of Elect. Eng.- Syst, Univ. of Southern California, 1990.
[4] M. Evett, J. Hendler, and L. Spector, "PARKA: Parallel knowledge representation on the Connection Machine," Tech. Rep. UMIACS-TR- 90-22, Univ. of Maryland, 1990.
[5] S. E. Fahlman,NETL: A System for Representing and Using Real-World Knowledge. Cambridge, MA: MIT, 1979.
[6] J.A. Hendler,Integrating Marker-Passing and Problem-Solving, Lawrence Erlbaum Associates, Hillsdale, N.J., 1988.
[7] W. D. Hillis,The Connection Machine. Cambridge, MA: MIT Press, 1985.
[8] H. Kitano, "A massively parallel model of simultaneous interpretaion: The DmDialog system," Tech. Rep. CMU-CMT-89-116. Carnegie Mellon Univ., 1989.
[9] W. Lee, "Bandwidth analysis of message passing networks," Tech. Rep. PKPLab-90-6, Dep. of Electrical Eng.-Syst., Univ. of Southern California, 1990.
[10] W. Lee and D. Moldovan, "The design of a marker passing architecuturefor knowledge processing," inProc. Nat. Con. on Artificial Intelligence, 1990.
[11] T. A. Lipkis and J. G. Schmolze, "Classification in the KL-ONE knowledge representation system," inProc. Eighth Int. Joint Con. on Artificial Intelligence, vol. 1, 1983, pp. 330-332.
[12] D. Moldovan, "An associative array architecture for semantic network processing," Tech. Rep. PPP-83-8. Dep. of Elect. Eng.-Syst., Univ. of Southern California, 1983.
[13] D. Moldovan and Y. Tung, "SNAP: A VLSI architecture for artificial intelligence,"J. Parallel Distributed Comput., May 1985.
[14] D. Moldovan, W. Lee, and C. Lin, "Parallel knowledge processing on SNAP," inProc. Int. Conf. on Parallel Processing, 1990.
[15] D. Moldovan, S. Cha, I. T. Um, R. DeMara, and J. T. Kim, "Direct memory access translation on SNAP," Tech. Rep. PKPLab-90-10, Dep. of Elect. Eng.-Syst, Univ. of Southern California, 1990.
[16] M. R. Quillian, "Semantic memory," Ph.D. dissertation, Carnegie Institute of Technology Carnegie Mellon Univ., 1966.
[17] C. Riesbeck and C. Martin, "Direct memory access parsing," Yale Univ. Rep. 354, 1985.
[18] H. Tomabechi, "Direct memory access translation," inProc. IJCAI-87, 1987.

Index Terms:
semantic network array processor; highly parallel architecture; knowledge representation; reasoning; instruction set; marker propagation architecture; markers; reasoning mechanisms; simulator; inheritance; recognition; classification; Connection Machine; digital simulation; instruction sets; parallel architectures; semantic networks
Citation:
D.I. Moldovan, W. Lee, C. Lin, "Parallel Knowledge Processing on SNAP," IEEE Transactions on Knowledge and Data Engineering, vol. 5, no. 1, pp. 65-75, Feb. 1993, doi:10.1109/69.204092
Usage of this product signifies your acceptance of the Terms of Use.