1. [Publications](/publications)
2. Placement Optimization via PPA-Directed Graph Clustering
 
 # Placement Optimization via PPA-Directed Graph Clustering

  ![](/sites/default/files/styles/wide/public/publications/PPA_clustering.JPG?itok=CIDc7fAw)

 In this paper, we present the first Power, Performance, and Area (PPA)-directed, end-to-end placement optimization framework that provides cell clustering constraints as placement guidance to advance commercial placers. Specifically, we formulate PPA metrics as Machine Learning (ML) loss functions, and use graph clustering techniques to optimize them by improving clustering assignments. Experimental results on 5 GPU/CPU designs in a 5nm technology not only show that our framework immediately improves the PPA metrics at the placement stage, but also demonstrate that the improvements last firmly to the post-route stage, where we observe improvements of 89% in total negative slack (TNS), 26% in effective frequency, 2.4% in wirelength, and 1.4% in clock power.



 ## Authors



Yi-Chen Lu (Georgia Institute of Technology)

Tian Yang (NVIDIA)

Sung Kyu Lim (Georgia Institute of Technology)

Mark Haoxing Ren (NVIDIA)

 

 

 ## Publication Date



Monday, September 12, 2022

 

 ## Published in



[MLCAD '22: Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD](https://mlcad-workshop.org/)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Circuits and VLSI Design](/research-area/circuits)

 

 

 ## External Links



[Paper](https://dl.acm.org/doi/10.1145/3551901.3556482)

 

 

 ## Uploaded Files



[Pdf](https://d1qx31qr3h6wln.cloudfront.net/publications/Lu.MLCAD22.pdf "Open file in new window")2.69 MB