LLM-Based Repair of C++ Implicit Data Loss Compiler Warnings: An Industrial Case Study

TL;DR

This paper introduces an automated LLM-based method to fix implicit data loss warnings in large C++ projects, significantly reducing manual effort and maintaining code quality.

Contribution

It presents a novel approach combining LSP, Tree-sitter, and LLMs to automatically generate fixes for compiler warnings in industrial-scale C++ code.

Findings

92.73% acceptance rate of fixes by developers

39.09% reduction in unnecessary warning fixes

13.56% behind human-optimized solutions

Abstract

This paper presents a method to automatically fix implicit data loss warnings in large C++ projects using Large Language Models (LLMs). Our approach uses the Language Server Protocol (LSP) to gather context, Tree-sitter to extract relevant code, and LLMs to make decisions and generate fixes. The method evaluates the necessity of range checks concerning performance implications and generates appropriate fixes. We tested this method in a large C++ project, resulting in a 92.73% acceptance rate of the fixes by human developers during the code review. Our LLM-generated fixes reduced the number of warning fix changes that introduced additional instructions due to range checks and exception handling by 39.09% compared to a baseline fix strategy. This result was 13.56% behind the optimal solutions created by human developers. These findings demonstrate that our LLM-based approach can reduce the manual effort to address compiler warnings while maintaining code quality and performance in a real-world scenario. Our automated approach shows promise for integration into existing development workflows, potentially improving code maintenance practices in complex C++ software projects.