Towards LLM-based Root Cause Analysis of Hardware Design Failures
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916834194751488 |
|---|---|
| author | Qiu, Siyu Wang, Muzhi Afsharmazayejani, Raheel Shahmiri, Mohammad Moradi Tan, Benjamin Pearce, Hammond |
| author_facet | Qiu, Siyu Wang, Muzhi Afsharmazayejani, Raheel Shahmiri, Mohammad Moradi Tan, Benjamin Pearce, Hammond |
| contents | With advances in large language models (LLMs), new opportunities have emerged to develop tools that support the digital hardware design process. In this work, we explore how LLMs can assist with explaining the root cause of design issues and bugs that are revealed during synthesis and simulation, a necessary milestone on the pathway towards widespread use of LLMs in the hardware design process and for hardware security analysis. We find promising results: for our corpus of 34 different buggy scenarios, OpenAI's o3-mini reasoning model reached a correct determination 100% of the time under pass@5 scoring, with other state of the art models and configurations usually achieving more than 80% performance and more than 90% when assisted with retrieval-augmented generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_06512 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards LLM-based Root Cause Analysis of Hardware Design Failures Qiu, Siyu Wang, Muzhi Afsharmazayejani, Raheel Shahmiri, Mohammad Moradi Tan, Benjamin Pearce, Hammond Hardware Architecture Artificial Intelligence With advances in large language models (LLMs), new opportunities have emerged to develop tools that support the digital hardware design process. In this work, we explore how LLMs can assist with explaining the root cause of design issues and bugs that are revealed during synthesis and simulation, a necessary milestone on the pathway towards widespread use of LLMs in the hardware design process and for hardware security analysis. We find promising results: for our corpus of 34 different buggy scenarios, OpenAI's o3-mini reasoning model reached a correct determination 100% of the time under pass@5 scoring, with other state of the art models and configurations usually achieving more than 80% performance and more than 90% when assisted with retrieval-augmented generation. |
| title | Towards LLM-based Root Cause Analysis of Hardware Design Failures |
| topic | Hardware Architecture Artificial Intelligence |
| url | https://arxiv.org/abs/2507.06512 |