Parallel Implementation of OPS5 on the Encore Multiprocessor: Results and Analysis

Abstract

Until now, most results reported for parallelism in production systems (rule-based systems) have been simulation results - very few real parallel implementations exist. In this paper, we present results from our parallel implementation of OPS5 on the Encore multiprocessor. The implementation exploits very-fine-grained parallelism to achieve significant speed-ups. For one of the applications, we achieve 12.4 fold speed-up using 13 processes. Our implementation is also distinct from other parallel implementations in that we parallelize a highly optimized C-based implementation of OPS5. Running on uniprocessor, our C-based implementation is 10-20 times faster than the standard lisp implementation distributed by Carnegie Mellon University. In addition to presenting the performance numbers, the paper discusses the details of the parallel implementation - the data structures used, the amount of contention observed for shared data structures, and the techniques used to reduce such contention.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1988
Accession Number
ADA207320

Entities

People

  • Allen Newell
  • Anoop Gupta
  • Charles Forgy
  • Dirk Kalp
  • Miland Tambe

Organizations

  • Stanford University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Computer Programming
  • Computer Science
  • Computers
  • Expert Systems
  • Flow Network
  • Graphs
  • Hash Tables
  • Machine Languages
  • Multiprocessors
  • Operating Systems
  • Parallel Computing
  • Parallel Processing
  • Production
  • Scheduling (Production)
  • Statistics
  • System Software

Fields of Study

  • Computer science

Readers

  • Parallel and Distributed Computing.
  • Software Engineering.