SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance

TL;DR

SPICEPilot introduces a Python-based dataset and framework to improve AI-driven SPICE code generation, addressing current limitations and providing standardized benchmarks for circuit simulation automation.

Contribution

The paper presents SPICEPilot, a novel dataset and framework that enhance LLMs' ability to generate accurate SPICE code for circuit design automation.

Findings

Automated SPICE script generation across various circuits.

Standardized benchmarking metrics for LLMs in circuit design.

Open-source toolkit available for the community.

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.