Architecture of a Reduction-Based Parallel Inference Machine: PIM-R

Rikio Onai, Moritoshi Aso, Hajime Shimizu, Kanae Masuda, Akira Matsumoto

Research output: Contribution to journalArticlepeer-review

15 Citations (Scopus)

Abstract

This paper presents a highly parallel machine architecture for logic programs. We propose a Reduction-Based Parallel Inference Machine: PIM-R and describe the parallel execution mechanisms for PIM-R to run Prolog and Concurrent Prolog programs and sofware simulation results. PIM-R uses the structure-copy method. It also uses the only reducible goal copy method, a unique process-structuring method, and the reverse compaction method to decrease the amount, of copying and various copyingrelated operations and the number of packets passing through the network. PIM-R architecture features include the distributed shared memory for Concurrent Prolog, network nodes for efficient packet distribution, and the structure memory to store a part of structured data for reducing the copying overhead.

Original languageEnglish
Pages (from-to)197-228
Number of pages32
JournalNew Generation Computing
Volume3
Issue number2
DOIs
Publication statusPublished - 1985 Jun
Externally publishedYes

Keywords

  • AND Parallel
  • Concurrent Prolog
  • OR Parallel
  • Parallel Inference Machine
  • Prolog
  • Reduction

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'Architecture of a Reduction-Based Parallel Inference Machine: PIM-R'. Together they form a unique fingerprint.

Cite this