PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI
This work addresses the challenge of automated RTL generation for hardware design, offering a novel agentic approach that bridges performance gaps between open- and closed-source LLMs.
The paper tackles the problem of generating Register Transfer Level (RTL) code from natural language without human intervention by introducing an agentic flow with a progressive error feedback system, achieving state-of-the-art pass rates and efficiency in token counts on open-source datasets.
We present an agentic flow consisting of multiple agents that combine specialized LLMs and hardware simulation tools to collaboratively complete the complex task of Register Transfer Level (RTL) generation without human intervention. A key feature of the proposed flow is the progressive error feedback system of agents (PEFA), a self-correcting mechanism that leverages iterative error feedback to progressively increase the complexity of the approach. The generated RTL includes checks for compilation, functional correctness, and synthesizable constructs. To validate this adaptive approach to code generation, benchmarking is performed using two opensource natural language-to-RTL datasets. We demonstrate the benefits of the proposed approach implemented on an open source agentic framework, using both open- and closed-source LLMs, effectively bridging the performance gap between them. Compared to previously published methods, our approach sets a new benchmark, providing state-of-the-art pass rates while being efficient in token counts.