IX SUPERCOMPUTER FOR KNOWLEDGE BASED SYSTEMS.

Tetsuya Higuchi, Tatsumi Furuya, Hiroyuki Kusumoto, Ken'ichi Handa, Akio Kokubu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

A description is given of an IXM machine for the parallel processing of large knowledge-based systems written in a semantic network language, IXL. The potential performance of IXM is thousands of times faster than conventional machines, as IXM can find all the solutions of the query simultaneously. IXM consists of a pyramid-shaped network (PYN) and 1000 processing elements (PEs). IXM utilizes 2000 concurrencies in the fundamental operations of the semantic network: association, set operation, and marker propagation. A network processor at each node of the PYN has an associative memory for parallel marker propagation. Each PE also has two types of associative memories; one for the parallel processing of association and set operation, the other for utilizing the parallelisms in IXL language interpreter described in nonprocedural instructions.

Original languageEnglish
Title of host publicationUnknown Host Publication Title
EditorsHarold S. Stone
PublisherIEEE
Pages1041-1049
Number of pages9
ISBN (Print)0818607432
Publication statusPublished - 1986 Dec 1
Externally publishedYes

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint

Dive into the research topics of 'IX SUPERCOMPUTER FOR KNOWLEDGE BASED SYSTEMS.'. Together they form a unique fingerprint.

Cite this