In Search of Speculative Thread-Level Parallelism

Abstract

This paper focuses on the problem of how to find and effectively exploit speculative thread-level parallelism. Our studies show that speculating only on loops does not yield sufficient parallelism. We propose the use of speculative procedure execution as a means to increase the available parallelism. An additional technique, data value prediction, has the potential to greatly improve the peformance of speculative execution. in particular return value prediction improves the success of procedural speculation, and stride value prediction improves the success of loop speculation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1999
Accession Number
ADA419602

Entities

People

  • David L. Heine
  • Jeffrey T. Oplinger
  • Monica S. Lam

Organizations

  • Stanford University

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Boundaries
  • Compilers
  • Compression
  • Computations
  • Computer Programming
  • Computers
  • Image Compression
  • Instructions
  • Iterations
  • Language
  • Multiprocessors
  • Optimization
  • Side Effects
  • Simulations
  • Simulators
  • Statistical Data

Readers

  • Graph Algorithms and Convex Optimization.
  • Systems Analysis and Design