[2607.25651] Demystifying Deep Learning Compiler Frontend Bugs: An LLM-Aided Empirical Study

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Programming Languages

arXiv:2607.25651 (cs)

[Submitted on 28 Jul 2026]

Title:Demystifying Deep Learning Compiler Frontend Bugs: An LLM-Aided Empirical Study

Authors:Xinyi Yuan, Wei Chen, Jinyi Liu, Pengyu Chen, Jun Wei, Guoquan Wu, Jiaxin Zhu, Tao Huang<br>View a PDF of the paper titled Demystifying Deep Learning Compiler Frontend Bugs: An LLM-Aided Empirical Study, by Xinyi Yuan and 7 other authors

View PDF<br>HTML (experimental)

Abstract:Deep learning compilers (DLCs) are designed to translate deep learning programs into optimized, hardware-specific code. Typically, DLC frontends translate programs into graph-based intermediate representations (IRs) to enable optimizations. Defects introduced during this stage (termed \emph{fBug}s) are severe yet understudied, as prior work predominantly focuses on low-level APIs and operators or treats DLCs as monolithic entities.

To bridge this gap, we conduct the first systematic empirical study of \emph{fBug}s in TorchDynamo, the default DLC frontend for PyTorch 2, the most popular DL framework. Leveraging a domain-knowledge-enhanced LLM-aided methodology, we analyze 123 \emph{fBug}s and construct a taxonomy comprising 7 root cause categories and 15 subcategories. Our findings provide actionable insights for DLC development and testing. Furthermore, we leverage the LLM to generate targeted, root cause-aware test cases to detect new bugs. We uncovered 23 previously unknown \emph{fBug}s in recent releases (15 confirmed) across eight (sub)categories, demonstrating the efficacy of our methodology in testing and hardening DLC frontends.

Subjects:

Programming Languages (cs.PL); Software Engineering (cs.SE)

Cite as:<br>arXiv:2607.25651 [cs.PL]

(or<br>arXiv:2607.25651v1 [cs.PL] for this version)

https://doi.org/10.48550/arXiv.2607.25651

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Xinyi Yuan [view email]<br>[v1]<br>Tue, 28 Jul 2026 12:38:50 UTC (2,939 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Demystifying Deep Learning Compiler Frontend Bugs: An LLM-Aided Empirical Study, by Xinyi Yuan and 7 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.PL

next >

new<br>recent<br>| 2026-07

Change to browse by:

cs<br>cs.SE

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)

Major funding support from