OpenROAD-Assistant: An Open-Source Large Language Model for Physical Design Tasks

被引:0
作者
Sharma, Utsav [1 ]
Wu, Bing-Yue [2 ]
Kankipati, Sai Rahul Dhanvi [2 ]
Chhabria, Vidya A. [2 ]
Rovinski, Austin [1 ]
机构
[1] NYU, New York, NY 10003 USA
[2] Arizona State Univ, Tempe, AZ 85287 USA
来源
2024 ACM/IEEE 6TH SYMPOSIUM ON MACHINE LEARNING FOR CAD, MLCAD 2024 | 2024年
关键词
D O I
暂无
中图分类号
学科分类号
摘要
Large language models (LLMs) have shown significant potential in serving as domain-specific chatbots. Recently, these models have emerged as powerful tools for chip design, providing both natural language responses and script generation for domain-specific inquiries. Previous work has demonstrated the effectiveness of LLMs in assisting with physical design automation; however, these approaches often rely on proprietary tools, APIs, technologies, and designs. As a result, access to these models is extremely limited, particularly for new chip designers who could greatly benefit from a design assistant. This paper introduces OpenROAD-Assistant, an open-source chatbot for OpenROAD that relies only on public data and responds to queries in either prose or Python script using the OpenROAD APIs. OpenROAD-Assistant leverages the Llama3-8B foundation model and employs retrieval-aware fine-tuning (RAFT) to respond to physical design-specific questions for OpenROAD. Notably, OpenROAD-Assistant outperforms other foundational models such as ChaIGPI3.5, ChaIGPT4, Code Llama, Claude3, and other ablation study baselines on the measured metrics (pass@k for scripting and BERTScore/BARTScore for question-answering). OpenROAD-Assistant achieves a 77% pass@1 score, 80% pass@3 score for scripting, and it achieves a 98% BERTScore and 96% BARTScore on question-answering.
引用
收藏
页数:7
相关论文
共 29 条
[1]  
AI@Meta, 2024, Llama3
[2]  
Ajayi T., GOMACTECH 2019 P
[3]   INVITED: Toward an Open-Source Digital Flow: First Learnings from the OpenROAD Project [J].
Ajayi, Tutu ;
Chhabria, Vidya A. ;
Fogaca, Mateus ;
Hashemi, Soheil ;
Hosny, Abdelrahman ;
Kahng, Andrew B. ;
Kim, Minsoo ;
Lee, Jeongsup ;
Mallappa, Uday ;
Neseem, Marina ;
Pradipta, Geraldo ;
Reda, Sherief ;
Saligane, Mehdi ;
Sapatnekar, Sachin S. ;
Sechen, Carl ;
Shalan, Mohamed ;
Swartz, William ;
Wang, Lutong ;
Wang, Zhehong ;
Woo, Mingyu ;
Xu, Bangqi .
PROCEEDINGS OF THE 2019 56TH ACM/EDAC/IEEE DESIGN AUTOMATION CONFERENCE (DAC), 2019,
[4]  
[Anonymous], 2023, OpenROAD-Assistant Pre -trained Model
[5]  
[Anonymous], 2023, ChatGPT
[6]  
[Anonymous], 2024, OpenROAD-Assistant
[7]  
[Anonymous], 2024, ChatEDAv1
[8]  
[Anonymous], 2024, Claude
[9]  
Blocklove J., 2023, MLCAD
[10]  
Dettmers T., 2024, P NEURIPS