The Platform-Aware Compilation Environment (PACE)

Abstract

The PACE Project investigated the feasibility of using a combination of characterization-driven optimization, feedback-directed optimization, and automatic selection of transformations to retarget an optimizing compiler to new computer systems. This report provides an overview of the design, the implementation, and the ways in which the PACE components advanced the state of the art in compilation, in performance measurement and attribution, in portable measurement of system characteristics, and in machine learning.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2012
Accession Number
ADA569973

Entities

People

  • Erzsebet Merenyi
  • John Mellor-crummey
  • Keith D. Cooper
  • Krishna Palem
  • Linda Torczon
  • P. Sadayappan
  • Vivek Sarkar

Organizations

  • Rice University

Tags

Communities of Interest

  • Autonomy
  • Engineered Resilient Systems
  • Materials and Manufacturing Processes
  • Space

DTIC Thesaurus Topics

  • Accuracy
  • Air Force
  • Air Force Research Laboratories
  • Algorithms
  • Application Software
  • C Programming Language
  • Compilers
  • Computer Program Documentation
  • Computer Program Reliability
  • Computer Programming
  • Computer Programs
  • Computers
  • Instruction Set Architecture
  • Machine Learning
  • Measurement
  • Neural Networks
  • Optimization

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Software Verification and Validation.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Machine Learning Algorithms