Intelligent-Unrolling: Exploiting Regular Patterns in Irregular Applications

TL;DR

Intelligent-Unroll is a framework that automatically optimizes irregular applications for vectorization by modeling runtime patterns, leading to more efficient code generation compared to existing methods.

Contribution

It introduces a novel approach to optimize irregular applications using code seeds, feature tables, and information-code trees for better vectorization.

Findings

Outperforms state-of-the-art implementations in sparse matrix-vector multiplication.

Effectively optimizes reduction and gather/scatter operations.

Generates highly efficient vectorized code for irregular applications.

Abstract

Modern optimizing compilers are able to exploit memory access or computation patterns to generate vectorization codes. However, such patterns in irregular applications are unknown until runtime due to the input dependence. Thus, either compiler's static optimization or profile-guided optimization based on specific inputs cannot predict the patterns for any common input, which leads to suboptimal code generation. To address this challenge, we develop Intelligent-Unroll, a framework to automatically optimize irregular applications with vectorization. Intelligent-Unroll allows the users to depict the computation task using \textit{code seed} with the memory access and computation patterns represented in \textit{feature table} and \textit{information-code tree}, and generates highly efficient codes. Furthermore, Intelligent-Unroll employs several novel optimization techniques to optimize reduction operations and gather/scatter instructions. We evaluate Intelligent-Unroll with sparse matrix-vector multiplication (SpMV) and graph applications. Experimental results show that Intelligent-Unroll is able to generate more efficient vectorization codes compared to the state-of-the-art implementations.