Using Profile Information to Assist Classic Code Optimizations

This paper describes the design and implementation of an optimizing compiler that automatically generates profile information to assist classic code optimizations. This compiler contains two new components, an execution profiler and a profile-based code optimizer, which are not commonly found in traditional optimizing compilers. The execution profiler inserts probes into the input program, executes the input program for several inputs, accumulates profile information, and supplies this information to the optimizer. The profile-based code optimizer uses the profile information to expose new optimization opportunities that are not visible to traditional global optimization methods. Experimental results show that the profile-based code optimizer significantly improves the performance of production C programs that have already been optimized by a high-quality global code optimizer. Key Words: C, code optimization, compiler, profile-based code optimization, profiler INTRODUCTION The major objective of code optimizations is to reduce the execution time. Some classic code optimizations, such as dead code elimination, common subexpression elimination, and copy propagation, reduce the execution time by removing redundant computation. Other code optimizations, such as loop invariant code removal and loop induction variable elimination, reduce the execution time by moving instructions from frequently executed program regions to infrequently executed program regions. This paper describes an optimizing compiler that accurately identifies frequently executed program paths and optimizes them. To appear: Software - Practice & Experience 2 Static analysis, such as loop detection [1], can estimate execution counts, but the estimates are imprecise: outcome of conditional statements, loo..