RTLSquad: Multi-Agent Based Interpretable RTL Design
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910778655768576 |
|---|---|
| author | Wang, Bowei Xiong, Qi Xiang, Zeqing Wang, Lei Chen, Renzhi |
| author_facet | Wang, Bowei Xiong, Qi Xiang, Zeqing Wang, Lei Chen, Renzhi |
| contents | Optimizing Register-Transfer Level (RTL) code is crucial for improving hardware PPA performance. Large Language Models (LLMs) offer new approaches for automatic RTL code generation and optimization. However, existing methods often lack decision interpretability (sufficient, understandable justification for decisions), making it difficult for hardware engineers to trust the generated results, thus preventing these methods from being integrated into the design process. To address this, we propose RTLSquad, a novel LLM-Based Multi-Agent system for interpretable RTL code generation. RTLSquad divides the design process into exploration, implementation, and verification & evaluation stages managed by specialized agent squads, generating optimized RTL code through inter-agent collaboration, and providing decision interpretability through the communication process. Experiments show that RTLSquad excels in generating functionally correct RTL code and optimizing PPA performance, while also having the capability to provide decision paths, demonstrating the practical value of our system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05470 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RTLSquad: Multi-Agent Based Interpretable RTL Design Wang, Bowei Xiong, Qi Xiang, Zeqing Wang, Lei Chen, Renzhi Hardware Architecture Artificial Intelligence Software Engineering Optimizing Register-Transfer Level (RTL) code is crucial for improving hardware PPA performance. Large Language Models (LLMs) offer new approaches for automatic RTL code generation and optimization. However, existing methods often lack decision interpretability (sufficient, understandable justification for decisions), making it difficult for hardware engineers to trust the generated results, thus preventing these methods from being integrated into the design process. To address this, we propose RTLSquad, a novel LLM-Based Multi-Agent system for interpretable RTL code generation. RTLSquad divides the design process into exploration, implementation, and verification & evaluation stages managed by specialized agent squads, generating optimized RTL code through inter-agent collaboration, and providing decision interpretability through the communication process. Experiments show that RTLSquad excels in generating functionally correct RTL code and optimizing PPA performance, while also having the capability to provide decision paths, demonstrating the practical value of our system. |
| title | RTLSquad: Multi-Agent Based Interpretable RTL Design |
| topic | Hardware Architecture Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2501.05470 |