PowerNet: Transferable Dynamic IR Drop Estimation via Maximum Convolutional Neural Network

TL;DR

PowerNet is a CNN-based method that provides fast, accurate, and transferable dynamic IR drop estimation for chip designs, significantly reducing analysis time and aiding in hotspot mitigation.

Contribution

It introduces a transferable CNN model for IR drop estimation that works across different designs, unlike existing design-specific ML approaches.

Findings

Outperforms existing ML methods by 9% in accuracy for vectorless IR drop.

Achieves 30x speedup over commercial IR drop tools.

Reduces IR drop hotspots by over 25% on industrial designs.

Abstract

IR drop is a fundamental constraint required by almost all chip designs. However, its evaluation usually takes a long time that hinders mitigation techniques for fixing its violations. In this work, we develop a fast dynamic IR drop estimation technique, named PowerNet, based on a convolutional neural network (CNN). It can handle both vector-based and vectorless IR analyses. Moreover, the proposed CNN model is general and transferable to different designs. This is in contrast to most existing machine learning (ML) approaches, where a model is applicable only to a specific design. Experimental results show that PowerNet outperforms the latest ML method by 9% in accuracy for the challenging case of vectorless IR drop and achieves a 30 times speedup compared to an accurate IR drop commercial tool. Further, a mitigation tool guided by PowerNet reduces IR drop hotspots by 26% and 31% on two industrial designs, respectively, with very limited modification on their power grids.