SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916456778694656 |
|---|---|
| author | Vungarala, Deepak Alam, Sakila Ghosh, Arnob Angizi, Shaahin |
| author_facet | Vungarala, Deepak Alam, Sakila Ghosh, Arnob Angizi, Shaahin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20553 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance Vungarala, Deepak Alam, Sakila Ghosh, Arnob Angizi, Shaahin Hardware Architecture Artificial Intelligence 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. |
| title | SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance |
| topic | Hardware Architecture Artificial Intelligence |
| url | https://arxiv.org/abs/2410.20553 |