GPU Performance and Power Tuning Using Regression Trees

Abstract

GPU performance and power tuning is difficult, requiring extensive user expertise and time-consuming trial and error. To accelerate design tuning, statistical design space exploration methods have been proposed. This article presents Starchart, a novel design space partitioning tool that uses regression trees to approach GPU tuning problems. Improving on prior work, Starchart offers more automation in identifying key design trade-offs and models design subspaces with distinctly different behaviors. Starchart achieves good model accuracy using very few random samples: less than 0.3% of a given design space; iterative sampling can more quickly target subspaces of interest.

Document Details

Document Type
Pub Defense Publication
Publication Date
May 11, 2015
Source ID
10.1145/2736287

Entities

People

  • Elba Garza
  • Kelly A. Shaw
  • Margaret Martonosi
  • Wenhao Jia

Organizations

  • Defense Advanced Research Projects Agency
  • National Science Foundation
  • Princeton University
  • University of Richmond

Tags

Readers

  • Computational Modeling and Simulation
  • Operations Research
  • Parallel and Distributed Computing.

Technology Areas

  • Space