{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:22:45Z","timestamp":1772205765455,"version":"3.50.1"},"reference-count":46,"publisher":"Association for Computing Machinery (ACM)","issue":"6","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62025404, 62222411"],"award-info":[{"award-number":["62025404, 62222411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key Research and Development Program of China","award":["2023YFB4404400"],"award-info":[{"award-number":["2023YFB4404400"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2025,11,30]]},"abstract":"<jats:p>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%.<\/jats:p>","DOI":"10.1145\/3737286","type":"journal-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T07:45:54Z","timestamp":1747986354000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["AutoSilicon: Scaling Up RTL Design Generation Capability of Large Language Models"],"prefix":"10.1145","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7193-464X","authenticated-orcid":false,"given":"Cangyuan","family":"Li","sequence":"first","affiliation":[{"name":"Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences","place":["Beijing, China"]},{"name":"University of Chinese Academy of Sciences","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8094-0615","authenticated-orcid":false,"given":"Chujie","family":"Chen","sequence":"additional","affiliation":[{"name":"Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences","place":["Hangzhou, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0012-4113","authenticated-orcid":false,"given":"Yudong","family":"Pan","sequence":"additional","affiliation":[{"name":"Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences","place":["Beijing, China"]},{"name":"University of Chinese Academy of Sciences","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9565-0015","authenticated-orcid":false,"given":"Wenjun","family":"Xu","sequence":"additional","affiliation":[{"name":"Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences","place":["Hangzhou, China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8717-068X","authenticated-orcid":false,"given":"Yiqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences","place":["Beijing, China"]},{"name":"University of Chinese Academy of Sciences","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1920-0101","authenticated-orcid":false,"given":"Kaiyan","family":"Chang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences","place":["Beijing, China"]},{"name":"University of Chinese Academy of Sciences","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0646-4183","authenticated-orcid":false,"given":"Yujie","family":"Wang","sequence":"additional","affiliation":[{"name":"Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7012-2308","authenticated-orcid":false,"given":"Mengdi","family":"Wang","sequence":"additional","affiliation":[{"name":"Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8082-4218","authenticated-orcid":false,"given":"Huawei","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5113-8067","authenticated-orcid":false,"given":"Yinhe","family":"Han","sequence":"additional","affiliation":[{"name":"Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5172-4736","authenticated-orcid":false,"given":"Ying","family":"Wang","sequence":"additional","affiliation":[{"name":"Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences","place":["Beijing, China"]}]}],"member":"320","published-online":{"date-parts":[[2025,10,21]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"OpenAI. 2023. GPT-4 technical report. arXiv:2303.08774. Retrieved from https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_3_2","article-title":"HuggingGPT: Solving AI tasks with ChatGPT and its friends in hugging face","author":"Shen Yongliang","year":"2024","unstructured":"Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, and Yueting Zhuang. 2024. HuggingGPT: Solving AI tasks with ChatGPT and its friends in hugging face. In Proceedings of the 37th International Conference on Neural Information Processing Systems .","journal-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems"},{"key":"e_1_3_2_4_2","unstructured":"Baptiste Roziere Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing Ellen Tan Yossi Adi Jingyu Liu Tal Remez J\u00e9r\u00e9my Rapin et\u00a0al. 2023. Code Llama: Open foundation models for code. arXiv:2308.12950. Retrieved from https:\/\/arxiv.org\/abs\/2308.12950"},{"key":"e_1_3_2_5_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv:2307.09288. Retrieved from https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_6_2","unstructured":"Thomas Dohmke. 2022. (2022). Retrieved June 1 2024 from https:\/\/github.blog\/2022-06-21-github-copilot-is-generally-available-toall-developers\/"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Yao Lu Shang Liu Qijun Zhang and Zhiyao Xie. 2024. Rtllm: An open-source benchmark for design rtl generation with large language model. In 2024 29th Asia and South Pacific Design Automation Conference (ASP-DAC). IEEE 722\u2013727.","DOI":"10.1109\/ASP-DAC58780.2024.10473904"},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Joshua C. Yang Marcin Korecki Damian Dailisan Carina I. Hausladen and Dirk Helbing. 2024. LLM voting: Human choices and AI collective decision making. In Proceedings of the AAAI\/ACM Conference on AI Ethics and Society 7 (2024) 1696\u20131708.","DOI":"10.1609\/aies.v7i1.31758"},{"key":"e_1_3_2_9_2","unstructured":"Xudong Guo Kaixuan Huang Jiale Liu Wenhui Fan Natalia V\u00e9lez Qingyun Wu Huazheng Wang Thomas L. Griffiths and Mengdi Wang. 2024. Embodied LLM agents learn to cooperate in organized teams. arXiv:2403.12482. Retrieved from https:\/\/arxiv.org\/abs\/2403.12482"},{"key":"e_1_3_2_10_2","article-title":"Tree of thoughts: Deliberate problem solving with large language models","author":"Yao Shunyu","year":"2024","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2024. Tree of thoughts: Deliberate problem solving with large language models. In Proceedings of the 37th International Conference on Neural Information Processing Systems .","journal-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems"},{"key":"e_1_3_2_11_2","article-title":"Response length perception and sequence scheduling: An LLM-empowered LLM inference pipeline","author":"Zheng Zangwei","year":"2024","unstructured":"Zangwei Zheng, Xiaozhe Ren, Fuzhao Xue, Yang Luo, Xin Jiang, and Yang You. 2024. Response length perception and sequence scheduling: An LLM-empowered LLM inference pipeline. In Proceedings of the 37th International Conference on Neural Information Processing Systems .","journal-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems"},{"key":"e_1_3_2_12_2","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et\u00a0al. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Proceedings of the 34th International Conference on Neural Information Processing Systems . 9459\u20139474.","journal-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems"},{"key":"e_1_3_2_13_2","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yi Dai Jiawei Sun and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv:2312.10997. Retrieved from https:\/\/arxiv.org\/abs\/2312.10997"},{"key":"e_1_3_2_14_2","unstructured":"Himanshu Rai. 2018. MonoPong. Retrieved June 2 2024 from https:\/\/github.com\/himanshu520\/MonoPong"},{"key":"e_1_3_2_15_2","unstructured":"pikamon. 2022. UART-Controller. Retrieved June 2 2024 from https:\/\/github.com\/pikamonvvs\/UART-Controller"},{"key":"e_1_3_2_16_2","unstructured":"Ha Nguyen. 2022. HCMUT-CO1025-LogicDesignHDL. Retrieved June 2 2024 from https:\/\/github.com\/meterglost\/HCMUT-CO1025-LogicDesignHDL"},{"key":"e_1_3_2_17_2","unstructured":"Franco Garcia. 2021. Digital-Clock-FPGA. Retrieved June 2 2024 from https:\/\/github.com\/FrancoGP1\/Digital-Clock-FPGA"},{"key":"e_1_3_2_18_2","unstructured":"freecores. 2009. spi. Retrieved June 2 2024 from https:\/\/github.com\/freecores\/spi"},{"key":"e_1_3_2_19_2","unstructured":"Aditya Tripathi. 2020. RISCV Three Stage. Retrieved June 2 2024 from https:\/\/github.com\/adityatripathiiit\/RISCV_Three_Stage"},{"key":"e_1_3_2_20_2","unstructured":"Debtanu Mukherjee. 2020. systolic array matrix multiplier. Retrieved June 2 2024 from https:\/\/github.com\/debtanu09\/systolic_array_matrix_multiplier"},{"key":"e_1_3_2_21_2","unstructured":"Wenxi Yang. 2024. FFT-ChipDesign. Retrieved June 2 2024 from https:\/\/github.com\/VenciFreeman\/FFT_ChipDesign"},{"key":"e_1_3_2_22_2","unstructured":"Trond Danielsen. 2011. oc-i2c. Retrieved June 2 2024 from https:\/\/github.com\/trondd\/oc-i2c"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3670474.3685956"},{"key":"e_1_3_2_24_2","first-page":"1","volume-title":"Proceedings of the 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD\u201923)","author":"Liu Mingjie","year":"2023","unstructured":"Mingjie Liu, Nathaniel Pinckney, Brucek Khailany, and Haoxing Ren. 2023. VerilogEval: Evaluating large language models for verilog code generation. In Proceedings of the 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD\u201923). IEEE, 1\u20138."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691788"},{"key":"e_1_3_2_26_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde de Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman et\u00a0al. 2021. Evaluating large language models trained on code. arXiv:2107.03374. Retrieved from https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2023.111734"},{"key":"e_1_3_2_28_2","unstructured":"Raymond Li Loubna Ben Allal Yangtian Zi Niklas Muennighoff Denis Kocetkov Chenghao Mou Marc Marone Christopher Akiki Jia Li Jenny Chim et\u00a0al. 2023. StarCoder: May the source be with you! arXiv:2305.06161. Retrieved from https:\/\/arxiv.org\/abs\/2305.06161"},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Kechi Zhang Jia Li Ge Li Xianjie Shi and Zhi Jin. 2024. CodeAgent: Enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges. arXiv:2401.07339. Retrieved from https:\/\/arxiv.org\/abs\/2401.07339","DOI":"10.18653\/v1\/2024.acl-long.737"},{"key":"e_1_3_2_30_2","unstructured":"AMD. 2024. AMD Vivado High-Level Design. (2024). Retrieved June 1 2024 from https:\/\/www.amd.com\/"},{"key":"e_1_3_2_31_2","unstructured":"Intel. 2024. Intel High Level Synthesis Compiler. (2024). Retrieved June 1 2024 from https:\/\/www.intel.com\/"},{"key":"e_1_3_2_32_2","unstructured":"MathWorks. 2024. HDL Coder. (2024). Retrieved June 1 2024 from https:\/\/www.mathworks.com\/"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/2228360.2228472"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/2228360.2228584"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Jason Blocklove Siddharth Garg Ramesh Karri and Hammond Pearce. 2023. Chip-Chat: Challenges and opportunities in conversational hardware design. In 2023 ACM\/IEEE 5th Workshop on Machine Learning for CAD (MLCAD). IEEE 1\u20136.","DOI":"10.1109\/MLCAD58807.2023.10299874"},{"key":"e_1_3_2_36_2","unstructured":"Kaiyan Chang Ying Wang Haimeng Ren Mengdi Wang Shengwen Liang Yinhe Han Huawei Li and Xiaowei Li. 2023. ChipGPT: How far are we from natural language hardware design. arXiv:2305.14019. Retrieved from https:\/\/arxiv.org\/abs\/2305.14019"},{"key":"e_1_3_2_37_2","unstructured":"Shailja Thakur Jason Blocklove Hammond Pearce Benjamin Tan Siddharth Garg and Ramesh Karri. 2023. AutoChip: Automating HDL generation using LLM feedback. arXiv:2311.04887. Retrieved from https:\/\/arxiv.org\/abs\/2311.04887"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643681"},{"key":"e_1_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Sneha Swaroopa Rijoy Mukherjee Anushka Debnath and Rajat Subhra Chakraborty. 2025. Evaluating large language models for automatic register transfer logic generation via high-level synthesis. Foundations and Trends\u00ae in Electronic Design Automation 14 4 (2025) 315\u2013337.","DOI":"10.1561\/1000000063-3"},{"key":"e_1_3_2_40_2","unstructured":"YunDa Tsai Mingjie Liu and Haoxing Ren. 2023. RTLFixer: Automatically fixing RTL syntax errors with large language models. arXiv:2311.16543. Retrieved from https:\/\/arxiv.org\/abs\/2311.16543"},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Wenji Fang Mengming Li Min Li Zhiyuan Yan Shang Liu Hongce Zhang and Zhiyao Xie. 2024. AssertLLM: Generating and evaluating hardware verification assertions from design specifications via multi-LLMs. arXiv:2402.00386. Retrieved from https:\/\/arxiv.org\/abs\/2402.00386","DOI":"10.1109\/LAD62341.2024.10691792"},{"key":"e_1_3_2_42_2","unstructured":"Marcelo Orenes-Vera Margaret Martonosi and David Wentzlaff. 2023. From RTL to SVA: LLM-assisted generation of formal verification testbenches. arXiv:2309.09437. Retrieved from https:\/\/arxiv.org\/abs\/2309.09437"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD58807.2023.10299852"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323953"},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Zheyu Yan Yifan Qin Xiaobo Sharon Hu and Yiyu Shi. 2023. On the viability of using LLMs for SW\/HW co-design: An example in designing CiM DNN accelerators. In 2023 IEEE 36th International System-on-Chip Conference (SOCC). IEEE 1\u20136.","DOI":"10.1109\/SOCC58585.2023.10256783"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10137086"},{"key":"e_1_3_2_47_2","unstructured":"Mingjie Liu Teodor-Dumitru Ene Robert Kirby Chris Cheng Nathaniel Pinckney Rongjian Liang Jonah Alben Himyanshu Anand Sanmitra Banerjee Ismet Bayraktaroglu et\u00a0al. 2023. ChipNeMo: Domain-adapted LLMs for chip design. arXiv:2311.00176. Retrieved from https:\/\/arxiv.org\/abs\/2311.00176"}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3737286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T12:22:02Z","timestamp":1761135722000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3737286"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"references-count":46,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11,30]]}},"alternative-id":["10.1145\/3737286"],"URL":"https:\/\/doi.org\/10.1145\/3737286","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]},"assertion":[{"value":"2024-09-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-12","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}