A Timing Engine Inspired Graph Neural Network Model for Pre-Routing Slack Prediction

Abstract

Fast and accurate pre-routing timing prediction is essential for timing-driven placement since repetitive routing and static timing analysis (STA) iterations are expensive and unacceptable. Prior work on timing prediction aims at estimating net delay and slew, lacking the ability to model global timing metrics. In this work, we present a timing engine inspired graph neural network (GNN) to predict arrival time and slack at timing endpoints. We further leverage edge delays as local auxiliary tasks to facilitate model training with increased model performance. Experimental results on real-world open-source designs demonstrate improved model accuracy and explainability when compared with vanilla deep GNN models.

Publication
59th ACM/IEEE Design Automation Conference (DAC) 2022
Zizheng Guo
Zizheng Guo
Ph.D. Student

I am a Ph.D. candidate at Peking University. My research interests include data structures, algorithm design and GPU acceleration for combinatorial optimization problems.