Extending Cache Coherence to Support Thread-Level Data Speculation on a Single Chip and Beyond

Abstract

Thread Level Data Speculation (TLDS) is a technique which enables the optimistic parallelization of applications despite ambiguous data dependences between the resulting threads. Although TLDS is mostly managed by software, hardware provides two key pieces of functionality: (1) detecting dependence violations, and (2) buffering speculative side effects until they can be safely committed to memory. To provide this functionality we present an extension to invalidation based cache coherence which is both scalable and has a minimal impact on hardware complexity. We explore the design space in depth and find that our baseline architecture is sufficient to exploit speculative parallelism.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1998
Accession Number
ADA363528

Entities

People

  • Christopher B. Colohan
  • J. Gregory Steffan
  • Todd C. Mowry

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Bandwidth
  • Coding
  • Computer Science
  • Computers
  • Data Sets
  • Instructions
  • Iterations
  • Multiprocessors
  • Multithreading
  • Numbers
  • Operating Systems
  • Parallel Processors
  • Simulations
  • Simulators
  • Standards
  • Transitions

Fields of Study

  • Computer science

Readers

  • Parallel and Distributed Computing.
  • ballistics.

Technology Areas

  • Space