Using Profile Information to Assist Advanced Compiler Optimization and Scheduling
| Citations: | 11 - 2 self |
BibTeX
@MISC{Chen_usingprofile,
author = {William Y. Chen and Scott A. Mahlke and Nancy J. Warter and Richard E. Hank and Roger A. Bringmann and Sadun Anik and Wen-mei W. Hwu},
title = {Using Profile Information to Assist Advanced Compiler Optimization and Scheduling},
year = {}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Compilers for superscalar and VLIW processors must expose sufficient instruction-level parallelism in order to achieve high performance. Compiletime code transformations which expose instruction-level parallelism typically take into account the constraints imposed by all execution scenarios in the program. However, there are additional opportunities to increase instruction-level parallelism along the frequent execution scenario at the expense of the less frequent execution sequences. Profile information identifies these important execution sequences in a program. In this paper, two major categories of profile information are studied: control-flow and memory-dependence. Profile-based transformations have been incorporated into the IMPACT compiler. These transformations include global optimization, acyclic global scheduling, and software pipelining. The effectiveness of these profile-based techniques is evaluated for a range of superscalar and VLIW processors.
