Massively Parallel Simulation of Structured Connectionist Networks: An Interim Report

We map structured connectionist models of knowledge representation and reasoning onto existing general purpose massively parallel architectures with the objective of developing and implementing practical, real-time knowledge base systems. Shruti, a connectionist knowledge representation and reasoning system which attempts to model reflexive reasoning, will serve as our representative connectionist model. Efficient simulation systems for shruti are developed on the Connection Machine CM-2 - an SIMD architecture - and on the Connection Machine CM-5 - an MIMD architecture. The resulting simulators are evaluated and tested using large, random knowledge bases with up to half a million rules and facts. Though SIMD simulations on the CM-2 are reasonably fast - requiring a few seconds to tens of seconds for answering simple queries - experiments indicate that MIMD simulations are vastly superior to SIMD simulations and offer hundred- to thousand-fold speedups. This work provides new insights into the simulation of structured connectionist networks on massively parallel machines and is a step toward developing large yet efficient knowledge representation and reasoning systems.