EUVIMEDEUVIMED entdecken
Crossref

AutoSilicon: Scaling Up RTL Design Generation Capability of Large Language Models

Cangyuan Li, Chujie Chen, Yudong Pan, Wenjun Xu, Yiqi Liu, Kaiyan Chang, Yujie Wang, Mengdi Wang, Huawei Li, Yinhe Han, Ying Wang

ACM Transactions on Design Automation of Electronic Systems · 30.11.2025 · 30 (6) · 1-21

DOI: 10.1145/3737286 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 21.10.2025. Verfasst von Cangyuan Li und 10 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hardware description language (HDL) code designing is a critical component of the chip design process, requiring substantial engineering and time resources. Recent advancements in large language models (LLMs), such as GPT series, have shown promise in automating HDL code generation. However, current LLM-based approaches face significant challenges in meeting real-world hardware design requirements, particularly in handling complex designs and ensuring code correctness. Our evaluations reveal that the functional correctness rate of LLM-generated HDL code significantly decreases as design complexity increases. In this article, we propose the AutoSilicon framework, which aims to scale up the hardware design capability of LLMs. AutoSilicon incorporates an agent system, which (1) allows for the decomposition of large-scale, complex code design tasks into smaller, simpler tasks; (2) provides a compilation and simulation environment that enables LLMs to compile and test each piece of code it generates; and (3) introduces a series of optimization strategies. Experimental results demonstrate that AutoSilicon can scale hardware designs to projects with code equivalent to over 10,000 tokens. In terms of design quality, it further improves the syntax correctness rate and functional correctness rate compared with approaches that do not employ any extensions. For example, compared to directly generating HDL code using GPT-4-turbo, AutoSilicon enhances the syntax correctness rate by an average of 35.8% and improves functional correctness by an average of 35.6%.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China

Zitieren

APA

Li, C., Chen, C., Pan, Y., Xu, W., Liu, Y., Chang, K., Wang, Y., Wang, M., Li, H., Han, Y., & Wang, Y. (2025). AutoSilicon: Scaling Up RTL Design Generation Capability of Large Language Models. ACM Transactions on Design Automation of Electronic Systems, 30(6), 1-21. https://doi.org/10.1145/3737286

Vancouver

Li C, Chen C, Pan Y, Xu W, Liu Y, Chang K, et al. AutoSilicon: Scaling Up RTL Design Generation Capability of Large Language Models. ACM Transactions on Design Automation of Electronic Systems. 2025;30(6):1-21. doi:10.1145/3737286

BibTeX
@article{Li2025,
  author = {Li, Cangyuan and Chen, Chujie and Pan, Yudong and Xu, Wenjun and Liu, Yiqi and Chang, Kaiyan and Wang, Yujie and Wang, Mengdi and Li, Huawei and Han, Yinhe and Wang, Ying},
  title = {AutoSilicon: Scaling Up RTL Design Generation Capability of Large Language Models},
  journal = {ACM Transactions on Design Automation of Electronic Systems},
  year = {2025},
  volume = {30},
  number = {6},
  pages = {1--21},
  doi = {10.1145/3737286}
}
Kostenlos starten →