The Design and Implementation of a Data Flow Multiprocessor.

Abstract

This report presents a data flow multiprocessor designed and implemented with standard laboratory microcomputer boards. Intel SBC 80/20 small board computers were used since their design supported a multibus structure required for multiprocessing. Current data flow techniques were researched in order to find a technique that could be implemented through software. A packet communication architecture was chosen for implementation since other data flow techniques required specialized hardware. The requirements of the multiprocessor were defined using structured analysis techniques. these requirements were then translated into structured modulas. The software modules were then implemented and tested in a top down approach. The data flow multiprocessor software was tested by executing complete data flow programs. The results of the tests demonstrated the functionality of the multiprocessor. However, the multiprocessor software was limited in some respects. The memory allocated for the storage of data flow programs limited the maximum number of data flow instructions that could be represented to only 128. The mathematical operations were also limited in that only 8 bit computations were allowed.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1981
Accession Number
ADA115616

Entities

People

  • Michael W. Bray

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • C4I
  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Air Force
  • Assembly Languages
  • Computer Programming
  • Computer Programs
  • Computer Science
  • Computers
  • Electrical Engineering
  • Language
  • Lists (Data Structures)
  • Machine Languages
  • Microarchitecture
  • Operating Systems
  • Parallel Computing
  • Parallel Processing
  • Programming Languages
  • Simulations
  • Standards

Fields of Study

  • Computer science
  • Engineering

Readers

  • Computational Modeling and Simulation
  • Parallel and Distributed Computing.