RTLSquad: Multi-Agent Based Interpretable RTL Design
This addresses the issue of trust and integration for hardware engineers by providing interpretable RTL design, though it appears incremental as it builds on existing LLM methods with a multi-agent approach.
The paper tackles the problem of generating interpretable RTL code for hardware design by proposing RTLSquad, a multi-agent LLM-based system that divides the process into stages managed by specialized agents, resulting in functionally correct code with optimized PPA performance and decision interpretability.
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.