Experiments with Dataflow on a General-Purpose Parallel Computer.

Abstract

The MIT J-Machine, a massively-parallel computer, is an experiment in providing general-purpose mechanisms for communication, synchronization, and naming that will support a wide variety of parallel models of computation. Having universal mechanisms allows the separation of issues of language design and machine organization. We have developed two experimental dataflow programming systems for the J-Machine. For the first system, we adapted Papadopoulos' explicit token store to implement static and then dynamic dataflow. Each node in a dataflow graph is expanded into a sequence of code, each of which is scheduled individually at runtime. For a later system, we made use of Iannucci's hybrid execution model to combine several dataflow graph nodes into a single sequence, decreasing scheduling overhead. By combining the strengths of the two systems, it is possible to produce a system with competitive performance. We have demonstrated the feasibility of efficiently executing dataflow programs on a general purpose parallel computer.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1991
Accession Number
ADA235521

Entities

People

  • Bill Dally
  • Ellen Spertus

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • C4I

DTIC Thesaurus Topics

  • Abstracts
  • Artificial Intelligence
  • Availability
  • Compilers
  • Computations
  • Computer Languages
  • Computer Programming
  • Computer Programs
  • Computers
  • Hybrid Systems
  • Instructions
  • Language
  • Massachusetts
  • Object Oriented Programming
  • Operating Systems
  • Sequences
  • Simulators

Fields of Study

  • Computer science
  • Engineering

Readers

  • Database Systems and Applications
  • Materials Science.
  • Neural Network Machine Learning.