CRADLE: Conversational RTL Design Space Exploration with LLM-based Multi-Agent Systems
This addresses the need for more flexible and efficient hardware design optimization for engineers, though it appears incremental as it builds on existing LLM and multi-agent approaches.
The paper tackles the problem of rigid design space exploration for RTL designs by introducing CRADLE, a conversational framework using LLM-based multi-agent systems, which achieves average reductions of 48% in LUTs and 40% in FFs on the RTLLM benchmark.
This paper presents CRADLE, a conversational framework for design space exploration of RTL designs using LLM-based multi-agent systems. Unlike existing rigid approaches, CRADLE enables user-guided flows with internal self-verification, correction, and optimization. We demonstrate the framework with a generator-critic agent system targeting FPGA resource minimization using state-of-the-art LLMs. Experimental results on the RTLLM benchmark show that CRADLE achieves significant reductions in resource usage with averages of 48% and 40% in LUTs and FFs across all benchmark designs.