Type-migrating C-to-Rust translation using a large language model
Open Access
- 17 October 2024
- journal article
- research article
- Published by Springer Nature in Empirical Software Engineering
- Vol. 30 (1) , 1-38
Abstract
Rust, a modern system programming language, introduces new types that prevent memory bugs and data races. This makes translating legacy system programs from C to Rust a promising approach to enhance their reliability. Since manual code translation is time-consuming, it is desirable to automate the translation. To yield satisfactory results, the translator should have the ability to perform type migration, i.e., removing C types and introducing Rust types in the code. In this work, we aim to automatically port an entire C program to Rust by translating each C function to a Rust function with a signature containing proper Rust types through type migration. This goal is challenging because (1) type migration cannot be achieved through syntactic mappings between type names, and (2) after type migration, function bodies should be correctly restructured based on the precise understanding of the functions’ behavior. To address these difficulties, we leverage large language models (LLMs), which possess knowledge of program semantics and programming idioms. However, naïvely instructing LLMs to translate each function produces unsatisfactory Rust code, containing unmigrated or improperly migrated types and a huge number of type errors. To resolve these issues, we propose three techniques: (1) generating candidate signatures, (2) providing translated callees’ signatures to LLMs, and (3) iteratively fixing type errors using compiler feedback. Our evaluation shows that the proposed approach yields a 63.5% increase in migrated types and a 71.5% decrease in type errors compared to the baseline (the naïve LLM-based translation) with modest performance overhead.Keywords
Funding Information
- National Research Foundation of Korea (2022R1A2C200366011, 2021R1A5A1021944)
- Institute for Information and Communications Technology Promotion (2022-0-00460)
- Samsung Electronics Co., Ltd (G01210570)
- Korea Advanced Institute of Science and Technology
This publication has 23 references indexed in Scilit:
- Improving domain-specific neural code generation with few-shot meta-learningInformation and Software Technology, 2023
- Ownership Guided C to Rust Translation2023
- Automated Repair of Programs from Large Language Models2023
- Automated Program Repair in the Era of Large Pre-trained Language Models2023
- Concrat: An Automatic C-to-Rust Lock API Translator for Concurrent Programs2023
- Syntax and Domain Aware Model for Unsupervised Program Translation2023
- Divide-and-Conquer Approach for Multi-phase Statistical Migration for Source Code (T)2015
- Lexical statistical machine translation for language migration2013
- Linux kernel vulnerabilities2011
- Mining API mapping for language migration2010