3D Floorplanning

3D floorplanning is the process of optimally arranging components within a three-dimensional space, a crucial step in designing integrated circuits and systems-on-chips. Current research focuses on improving efficiency and accuracy through advanced algorithms, including reinforcement learning and memetic algorithms that incorporate both discrete and continuous optimization techniques, often leveraging large datasets of real-world designs to train these models. These advancements aim to reduce the computational cost and improve the quality of floorplans, leading to faster and more efficient chip design processes. The development of improved floorplanning techniques is vital for creating more powerful and energy-efficient electronic devices.

Papers

June 15, 2024

Large Reasoning Models for 3D Floorplanning in EDA: Learning from Imperfections
Fin Amin, Nirjhor Rouf, Tse-Han Pan, Md Kamal Ibn Shafi, Paul D. Franzon
Reinforcement Learning Electronic Design Automation Large Knowledge Model 3D Floorplanning

May 9, 2024

FloorSet -- a VLSI Floorplanning Dataset with Design Constraints of Real-World SoCs
Uday Mallappa, Hesham Mostafa, Mikhail Galkin, Mariano Phielipp, Somdeb Majumdar
Floor Plan System on Chip 3D Floorplanning

January 27, 2024

Floorplanning of VLSI by Mixed-Variable Optimization
Jian Sun, Huabin Cheng, Jian Wu, Zhanyang Zhu, Yu Chen
Mixed Variable 3D Floorplanning

December 28, 2023

RLPlanner: Reinforcement Learning based Floorplanning for Chiplets with Fast Thermal Analysis
Yuanyuan Duan, Xingchen Liu, Zhiping Yu, Hanming Wu, Leilai Shao, Xiaolei Zhu
Reinforcement Learning Thermal Simulation Modern Chip Fast Thermal 3D Floorplanning

3D Floorplanning

Papers

Large Reasoning Models for 3D Floorplanning in EDA: Learning from Imperfections

FloorSet -- a VLSI Floorplanning Dataset with Design Constraints of Real-World SoCs

Floorplanning of VLSI by Mixed-Variable Optimization

RLPlanner: Reinforcement Learning based Floorplanning for Chiplets with Fast Thermal Analysis