Language Models for Code Optimization: Survey, Challenges and Future Directions

TL;DR

This paper surveys the use of language models in code optimization, highlighting current challenges and proposing future research directions to improve efficiency, robustness, and trust in AI-driven software performance enhancements.

Contribution

It provides the first comprehensive review of LM-based code optimization, identifying key challenges and outlining future research avenues in this emerging field.

Findings

Identified five critical open challenges in LM-based code optimization.

Highlighted the need for balancing model complexity with usability.

Outlined eight future research directions for advancing the field.

Abstract

Language models (LMs) built upon deep neural networks (DNNs) have recently demonstrated breakthrough effectiveness in software engineering tasks such as code generation, completion, and repair. This has paved the way for the emergence of LM-based code optimization techniques, which are crucial for enhancing the performance of existing programs, such as accelerating program execution time. However, a comprehensive survey dedicated to this specific application has been lacking. To fill this gap, we present a systematic literature review of over 50 primary studies, identifying emerging trends and addressing 11 specialized questions. Our findings reveal five critical open challenges, such as balancing model complexity with practical usability, cross-language/performance generalizability, and building trust in AI-driven solutions. Furthermore, we provide eight future research directions to facilitate more efficient, robust, and reliable LM-based code optimization. Thereby, this study aims to provide actionable insights and foundational references for both researchers and practitioners in this rapidly evolving field.