Understanding the behavior of compiler optimizations

  • Authors:
  • Han Lee;Daniel von Dincklage;Amer Diwan;J. Eliot B. Moss

  • Affiliations:
  • Department of Computer Science, University of Colorado, Boulder, CO 80309, U.S.A.;Department of Computer Science, University of Colorado, Boulder, CO 80309, U.S.A.;Department of Computer Science, University of Colorado, Boulder, CO 80309, U.S.A.;Department of Computer Science, University of Massachusetts, Amherst, MA 01003, U.S.A.

  • Venue:
  • Software—Practice & Experience - Research Articles
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

Compiler optimizations are difficult to implement and add complexity to a compiler. For this reason, compiler writers are selective about implementing them: they implement only the ones that they believe will be beneficial. To support compiler writers in this, we describe a method for measuring the cost and benefits of compiler optimizations, both individually and in synergy with other optimizations. We demonstrate our method by presenting results for the optimizations implemented in the Jikes Research Virtual Machine on the PowerPC and IA32 platforms. Copyright © 2006 John Wiley & Sons, Ltd.