On The Utility of Threads for Data Parallel Programming.

Abstract

Threads provide a useful programming model for asynchronous behavior because of their ability to encapsulate units of work that can then be scheduled for execution at runtime, based on the dynamic state of a system. Recently, the threaded model has been applied to the domain of data parallel scientific codes, and initial reports indicate that the threaded model can produce performance gains over non-threaded approaches, primarily through the use of overlapping useful computation with communication latency. However, overlapping computation with communication is possible without the benefit of threads if the communication system supports asynchronous primitives, and this comparison has not been made in previous papers. This paper provides a critical look at the utility of lightweight threads as applied to data parallel scientific programming. (KAR) P. 2

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 1995
Accession Number
ADA295379

Entities

People

  • Matthew Haines
  • Piyush Mehrotra
  • Thomas Fahringer

Organizations

  • Langley Research Center

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Boundaries
  • Communication Systems
  • Computations
  • Computer Programming
  • Computers
  • Differential Equations
  • Engineering
  • Iterations
  • Language
  • Lightweight
  • Operating Systems
  • Partial Differential Equations
  • Particles
  • Programming Languages
  • Scheduling (Production)
  • Standards
  • Workload

Fields of Study

  • Computer science

Readers

  • Parallel and Distributed Computing.