Redundant Array Computation Elimination

TL;DR

RACE is a novel, general redundancy elimination technique for array computations in loop nests, improving compiler optimization by hierarchically detecting redundancies efficiently and supporting aggressive expression reassociation.

Contribution

It introduces a two-level scheme for identifying data reuse and computation redundancies, enabling more universal redundancy elimination in array computations.

Findings

Effective redundancy detection in linear time

Improved code efficiency with auxiliary arrays

Supports aggressive expression reassociation

Abstract

Redundancy elimination is a key optimization direction, and loop nests are the main optimization target in modern compilers. Previous work on redundancy elimination of array computations in loop nests lacks universality. These approaches either focus on specific computation patterns or fail to recognize redundancies with complex structures. This paper proposes RACE (Redundant Array Computation Elimination), a more general redundancy elimination technique. RACE utilizes a novel two-level scheme to identify the data reuse between array references and the computation redundancies between expressions. It traverses the expression trees in loop nests to detect redundancies hierarchically in linear time and generates efficient code with optimized auxiliary arrays that store redundant computation results. Furthermore, RACE supports the expression reassociation with various aggressive strategies to improve the redundancy opportunities. Experimental results demonstrate the effectiveness of RACE.