Large Reasoning Models for 3D Floorplanning in EDA: Learning from Imperfections
This work addresses high computational costs in integrated circuit design, offering a domain-specific incremental improvement.
The paper tackles 3D floorplanning in electronic design automation by introducing Dreamweaver, a large reasoning model that improves performance over a state-of-the-art method, even when trained on random trajectories.
In this paper, we introduce Dreamweaver, which belongs to a new class of auto-regressive decision-making models known as large reasoning models (LRMs). Dreamweaver is designed to improve 3D floorplanning in electronic design automation (EDA) via an architecture that melds advancements in sequence-to-sequence reinforcement learning algorithms. A significant advantage of our approach is its ability to effectively reason over large discrete action spaces, which is essential for handling the numerous potential positions for various functional blocks in floorplanning. Additionally, Dreamweaver demonstrates strong performance even when trained on entirely random trajectories, showcasing its capacity to leverage sub-optimal or non-expert trajectories to enhance its results. This innovative approach contributes to streamlining the integrated circuit (IC) design flow and reducing the high computational costs typically associated with floorplanning. We evaluate its performance against a current state-of-the-art method, highlighting notable improvements.