Search

Abstract Despite the astonishing increases in processor performance over the last 40 years, delivered application performance remains a critical issue for many important problems. Compilers play a critical role in […]

Operator strength reduction is a technique that improves compiler-generated code by reformulating certain costly computations in terms of less expensive ones. A common case arises in array addressing expressions used in loops. The compiler can replace the sequence of multiplies generated by a direct translation of the address expression with an equivalent sequence of additions. When combined with linear function test replacement, strength reduction can speed up the execution of loops containing array references. The improvement comes from two sources: a reduction in the number of operations needed to implement the loop and the use of less costly operations. This paper presents a new algorithm for operator strength reduction, called OSR. OSR improves upon an earlier algorithm of Allen, Cocke, and Kennedy [Allen et al. 1981]. OSR operates on the static single assignment (SSA) form of a procedure [Cytron et al. 1991]. By taking advantage of the properties of SSA form, we have derived an algorithm that is simple to understand, quick to implement, and, in practice, fast to run. Its asymptotic complexity is, in the worst case, the same as the Allen, Cocke, and Kennedy algorithm (ACK). OSR achieves optimization results that are equivalent to those obtained with the ACK algorithm. OSR has been implemented in several research and production compilers. Categories and Subject Descriptors: D.3.4 [Programming Languages]: Processors--Compilers, Optimization General Terms: Algorithms, Languages Additional Key Words and Phrases: loops, strength reduction, static single assignment form

The compiler forms specialized copies of procedure bodies during procedure cloning, which is an interprocedural transformation. The compiler separates the incoming calls between the original procedure and the copies. The inheritance of an environment by each clone enables better code optimization. The clone procedure is decided by a three-phase algorithm. Unnecessary code growth is avoided by the algorithm by considering the information exposure of cloning during optimization.