1984 Reports
Performance Estimates tor the DADO Machine: A Comparison of TREAT and RETE
DADO is a highly parallel, VLSI-based, tree structured computer, intended (or the rapid execution of production system programs. In this paper we describe a new match algorithm for executing production systems on DADO that is capable of handling both temporally redundant and nontemporally redundant production systems. We argue that the new algorithm is faster than the original DADO algorithm intended for nontemporally redundant systems. We also show that the new algorithm executed on parallel hardware is faster and more space efficient than parallel implementations of the RETE match algorithm, which is appropriate for temporally redundant systems.
Subjects
Files
-
cucs-118-84.pdf application/pdf 559 KB Download File
More About This Work
- Academic Units
- Computer Science
- Publisher
- Department of Computer Science, Columbia University
- Series
- Columbia University Computer Science Technical Reports, CUCS-118-84
- Published Here
- February 17, 2012