Path-Based Pre-Routing Timing Prediction for Modern Very Large-Scale Integration Designs
Journal
Proceedings - International Symposium on Quality Electronic Design, ISQED
Journal Volume
2022-April
ISBN
9781665494663
Date Issued
2022-01-01
Author(s)
Chen, Li Wei
Sui, Yao Nien
Li, Yih Lang
Chao, Mango C.T.
Tsai, I. Ching
Kung, Tai Wei
Liu, En Cheng
Chang, Yun Chih
Abstract
Timing closure is crucial to successful very large-scale integration designs. In the physical design stage, designers must iterate their design to develop a layout that can resolve timing violations, which is relatively time consuming. The challenges of pre-routing timing prediction include delay prediction for routed wires and behavior analysis for post-route timing optimization. We present a path-based, pre-routing timing prediction mechanism using a machine-learning methodology and extracted features, which are the essential properties associated with path delay and timing optimization. Experimental results demonstrated that the slack values of the timing paths predicted using the proposed model are much closer to those at the post-route stage reported by an electronic design automation (EDA) tool, with R-square scores ranging from 0.994 to 0.998. Moreover, the proposed model exhibits considerable superiority in predicting the n most-timing-critical paths compared with the EDA tool at the post-clock tree synthesis (CTS) stage. The number of timing-critical paths that were the same as the 100 most-timing-critical paths reported by an EDA tool at the post-route stage is 63 to 86, whereas only 1 to 54 paths are reported at the post-CTS stage.
Subjects
Path-based analysis | post-clock tree synthesis (CTS) | post-route | random forest regression | timing prediction
Type
conference paper