EUVIMEDEUVIMED entdecken
Crossref

OptFuzz: Enhancing Compiler Testing via LLM-Powered Compilation Option Generation

Yifan Huang, Yibiao Yang, Maolin Sun, Jiangchang Wu, Qingyang Li, Zeyu Lu, Yuming Zhou

ACM Transactions on Software Engineering and Methodology · 23.05.2026

DOI: 10.1145/3817602 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 23.05.2026. Verfasst von Yifan Huang und 6 weiteren Autor:innen. Die Arbeit nennt 95 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Compiler testing is crucial, as compilers serve as foundational infrastructure in software development. Effective compiler testing necessitates not only the generation of diverse test programs but also the systematic specification of compilation options. While existing research predominantly emphasizes test program diversification, it largely overlooks the strategic selection of compilation options required for comprehensive testing. Compilers typically offer a wide range of fine-grained compilation options that allow for precise control over the compilation process, resulting in a vast combination space. Exhaustive enumeration of all option combinations is computationally infeasible, while the stochastic generation of conflictfree, semantically meaningful options presents significant methodological challenges. To address these limitations, we propose OptFuzz, an innovative compiler testing framework that harnesses the generative capabilities of Large Language Models (LLMs) alongside the effectiveness of historical bug-triggering test programs for a comprehensive exploration of the compilation space. OptFuzz leverages LLMs to extract historical bug-triggering test programs from diverse bug reports, which are demonstrated to be effective in uncovering compiler bugs. Therefore, it overcomes the limitations of existing regex-based extraction techniques. Subsequently, OptFuzz employs a code abstraction extraction method based on intermediate representation (IR) to tackle the constraints of LLM context length limitations. Finally, the extracted IR is fed into LLM to generate effective compilation options for compiler testing. Through extensive experiments on GCC and LLVM, OptFuzz demonstrated superior bug detection capability compared to the random compilation space exploration method and other existing technologies. Notably, OptFuzz discovered 64 new bugs in GCC and LLVM, with 53 confirmed or fixed, highlighting our method’s practical utility. The experimental outcomes also indicate that the IR-based analysis substantially decreases overhead and improves bug detection compared to direct utilization of source code.

Zitieren

APA

Huang, Y., Yang, Y., Sun, M., Wu, J., Li, Q., Lu, Z., & Zhou, Y. (2026). OptFuzz: Enhancing Compiler Testing via LLM-Powered Compilation Option Generation. ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3817602

Vancouver

Huang Y, Yang Y, Sun M, Wu J, Li Q, Lu Z, et al. OptFuzz: Enhancing Compiler Testing via LLM-Powered Compilation Option Generation. ACM Transactions on Software Engineering and Methodology. 2026. doi:10.1145/3817602

BibTeX
@article{Huang2026,
  author = {Huang, Yifan and Yang, Yibiao and Sun, Maolin and Wu, Jiangchang and Li, Qingyang and Lu, Zeyu and Zhou, Yuming},
  title = {OptFuzz: Enhancing Compiler Testing via LLM-Powered Compilation Option Generation},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2026},
  doi = {10.1145/3817602}
}
Kostenlos starten →