SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance
Document Type
Conference Proceeding
Publication Date
1-1-2024
Abstract
Large Language Models (LLMs) have shown great potential in automating code generation; however, their ability to generate accurate circuit-level SPICE code remains limited due to a lack of hardware-specific knowledge. In this paper, we analyze and identify the typical limitations of existing LLMs in SPICE code generation. To address these limitations, we present SPICEPilot—a novel Python-based dataset generated using PySpice, along with its accompanying framework. This marks a significant step forward in automating SPICE code generation across various circuit configurations. Our framework automates the creation of SPICE simulation scripts, introduces standardized benchmarking metrics to evaluate LLM’s ability for circuit generation, and outlines a roadmap for integrating LLMs into the hardware design process. SPICEPilot is open-sourced under the permissive MIT license at https://github.com/ACADLab/SPICEPilot.git.
Identifier
105002709169 (Scopus)
ISBN
[9798331541279]
Publication Title
2024 IEEE International Conference on Rebooting Computing, ICRC 2024
External Full Text Location
https://doi.org/10.1109/ICRC64395.2024.10937006
Grant
2216772
Fund Ref
Semiconductor Research Corporation
Recommended Citation
Vungarala, Deepak; Alam, Sakila; Ghosh, Arnob; and Angizi, Shaahin, "SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance" (2024). Faculty Publications. 1190.
https://digitalcommons.njit.edu/fac_pubs/1190