CRADLE: Conversational RTL Design Space Exploration with LLM-based Multi-Agent Systems
By Lukas Krupp, Maximilian Schoffel, Elias Biehl, and Norbert Wehn ¨
RPTU University of Kaiserslautern-Landau, Kaiserslautern, Germany
Abstract
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 selfverification, 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.
Index Terms—LLM, Agents, Design Space Exploration, RTL
To read the full article, click here
Related Semiconductor IP
- USB 20Gbps Device Controller
- AGILEX 7 R-Tile Gen5 NVMe Host IP
- 100G PAM4 Serdes PHY - 14nm
- Bluetooth Low Energy Subsystem IP
- Multi-core capable 64-bit RISC-V CPU with vector extensions
Related White Papers
- Simultaneous Exploration of Power, Physical Design and Architectural Performance Dimensions of the SoC Design Space using SEAS
- Simultaneous Exploration of Power, Physical Design and Architectural Performance Dimensions of the SoC Design Space using SEAS
- SoC RTL Signoff: Divide & Conquer with Abstract Models
- Implementing Ultra Low Latency Data Center Services with Programmable Logic
Latest White Papers
- CRADLE: Conversational RTL Design Space Exploration with LLM-based Multi-Agent Systems
- On the Thermal Vulnerability of 3D-Stacked High-Bandwidth Memory Architectures
- OmniSim: Simulating Hardware with C Speed and RTL Accuracy for High-Level Synthesis Designs
- Balancing Power and Performance With Task Dependencies in Multi-Core Systems
- LLM Inference with Codebook-based Q4X Quantization using the Llama.cpp Framework on RISC-V Vector CPUs