LLMs For EDA, HW Design and Security


A new technical paper titled “Hardware Phi-1.5B: A Large Language Model Encodes Hardware Domain Specific Knowledge” was published by researchers at Kansas State University, University of Science and Technology of China, Michigan Technological University, Washington University in St. Louis and Silicon Assurance.

“In the rapidly evolving semiconductor industry, where research, design, verification, and manufacturing are intricately linked, the potential of Large Language Models to revolutionize hardware design and security verification is immense. The primary challenge, however, lies in the complexity of hardware specific issues that are not adequately addressed by the natural language or software code knowledge typically acquired during the pretraining stage. Additionally, the scarcity of datasets specific to the hardware domain poses a significant hurdle in developing a foundational model. Addressing these challenges, this paper introduces Hardware Phi 1.5B, an innovative large language model specifically tailored for the hardware domain of the semiconductor industry. We have developed a specialized, tiered dataset comprising small, medium, and large subsets and focused our efforts on pretraining using the medium dataset. This approach harnesses the compact yet efficient architecture of the Phi 1.5B model. The creation of this first pretrained, hardware domain specific large language model marks a significant advancement, offering improved performance in hardware design and verification tasks and illustrating a promising path forward for AI applications in the semiconductor sector.”

Find the technical paper here. Published January 2024.

Fu, Weimin, Shijie Li, Yifang Zhao, Haocheng Ma, Raj Dutta, Xuan Zhang, Kaichen Yang, Yier Jin, and Xiaolong Guo. “Hardware Phi-1.5 B: A Large Language Model Encodes Hardware Domain Specific Knowledge.” arXiv preprint arXiv:2402.01728 (2024).

Related Reading
EDA Pushes Deeper Into AI
AI is both evolutionary and revolutionary, making it difficult to assess where and how it will be used, and what problems may crop up.

Leave a Reply

(Note: This name will be displayed publicly)