AutoSilicon: Scaling Up RTL Design Generation Capability of Large Language Models
Open Access
- 21 October 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 30 (6) , 1-21
Abstract
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%.Keywords
Funding Information
- National Natural Science Foundation of China (62025404, 62222411)
- National Key Research and Development Program of China (2023YFB4404400)
This publication has 16 references indexed in Scilit:
- LLM Voting: Human Choices and AI Collective Decision-MakingProceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 2024
- AutoBench: Automatic Testbench Generation and Evaluation Using LLMs for HDL Design2024
- AssertLLM: Generating Hardware Verification Assertions from Design Specifications via Multi-LLMs2024
- RTLCoder: Outperforming GPT-3.5 in Design RTL Generation with Our Open-Source Dataset and Lightweight Solution2024
- GPT4AIGChip: Towards Next-Generation AI Accelerator Design Automation via Large Language Models2023
- ChatEDA: A Large Language Model Powered Autonomous Agent for EDA2023
- Chip-Chat: Challenges and Opportunities in Conversational Hardware Design2023
- On the Viability of Using LLMs for SW/HW Co-Design: An Example in Designing CiM DNN Accelerators2023
- Avoiding game over2012
- Chisel2012