UVLLM: An Automated Universal RTL Verification Framework using LLMs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909403753480192 |
|---|---|
| author | Hu, Yuchen Ye, Junhao Xu, Ke Sun, Jialin Zhang, Shiyue Jiao, Xinyao Pan, Dingrong Zhou, Jie Wang, Ning Shan, Weiwei Fang, Xinwei Wang, Xi Guan, Nan Jiang, Zhe |
| author_facet | Hu, Yuchen Ye, Junhao Xu, Ke Sun, Jialin Zhang, Shiyue Jiao, Xinyao Pan, Dingrong Zhou, Jie Wang, Ning Shan, Weiwei Fang, Xinwei Wang, Xi Guan, Nan Jiang, Zhe |
| contents | Verifying hardware designs in embedded systems is crucial but often labor-intensive and time-consuming. While existing solutions have improved automation, they frequently rely on unrealistic assumptions. To address these challenges, we introduce a novel framework, UVLLM, which combines Large Language Models (LLMs) with the Universal Verification Methodology (UVM) to relax these assumptions. UVLLM significantly enhances the automation of testing and repairing error-prone Register Transfer Level (RTL) codes, a critical aspect of verification development. Unlike existing methods, UVLLM ensures that all errors are triggered during verification, achieving a syntax error fix rate of 86.99% and a functional error fix rate of 71.92% on our proposed benchmark. These results demonstrate a substantial improvement in verification efficiency. Additionally, our study highlights the current limitations of LLM applications, particularly their reliance on extensive training data. We emphasize the transformative potential of LLMs in hardware design verification and suggest promising directions for future research in AI-driven hardware design methodologies. The Repo. of dataset and code: https://anonymous.4open.science/r/UVLLM/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_16238 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | UVLLM: An Automated Universal RTL Verification Framework using LLMs Hu, Yuchen Ye, Junhao Xu, Ke Sun, Jialin Zhang, Shiyue Jiao, Xinyao Pan, Dingrong Zhou, Jie Wang, Ning Shan, Weiwei Fang, Xinwei Wang, Xi Guan, Nan Jiang, Zhe Hardware Architecture Verifying hardware designs in embedded systems is crucial but often labor-intensive and time-consuming. While existing solutions have improved automation, they frequently rely on unrealistic assumptions. To address these challenges, we introduce a novel framework, UVLLM, which combines Large Language Models (LLMs) with the Universal Verification Methodology (UVM) to relax these assumptions. UVLLM significantly enhances the automation of testing and repairing error-prone Register Transfer Level (RTL) codes, a critical aspect of verification development. Unlike existing methods, UVLLM ensures that all errors are triggered during verification, achieving a syntax error fix rate of 86.99% and a functional error fix rate of 71.92% on our proposed benchmark. These results demonstrate a substantial improvement in verification efficiency. Additionally, our study highlights the current limitations of LLM applications, particularly their reliance on extensive training data. We emphasize the transformative potential of LLMs in hardware design verification and suggest promising directions for future research in AI-driven hardware design methodologies. The Repo. of dataset and code: https://anonymous.4open.science/r/UVLLM/. |
| title | UVLLM: An Automated Universal RTL Verification Framework using LLMs |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2411.16238 |