SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance
This work addresses the challenge of automating circuit-level SPICE code generation for hardware designers, representing an incremental advancement by providing tools and benchmarks to improve LLM integration in this domain.
The paper tackles the problem of limited accuracy in LLM-generated SPICE code due to lack of hardware-specific knowledge by introducing SPICEPilot, a Python-based dataset and framework that automates SPICE simulation script creation and establishes benchmarking metrics for evaluation.
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.