Net2: A Graph Attention Network Method Customized for Pre-Placement Net Length Estimation

TL;DR

This paper introduces Net2, a customized graph attention network that accurately estimates net lengths before cell placement, aiding early optimization in digital design flows.

Contribution

The paper presents Net2, a novel graph attention network method tailored for pre-placement net length estimation, significantly improving accuracy and speed over prior approaches.

Findings

Net2a achieves 15% better accuracy than previous methods.

Net2f is over 1000 times faster than placement and outperforms other neural networks.

Both versions effectively identify long nets and critical paths.

Abstract

Net length is a key proxy metric for optimizing timing and power across various stages of a standard digital design flow. However, the bulk of net length information is not available until cell placement, and hence it is a significant challenge to explicitly consider net length optimization in design stages prior to placement, such as logic synthesis. This work addresses this challenge by proposing a graph attention network method with customization, called Net2, to estimate individual net length before cell placement. Its accuracy-oriented version Net2a achieves about 15% better accuracy than several previous works in identifying both long nets and long critical paths. Its fast version Net2f is more than 1000 times faster than placement while still outperforms previous works and other neural network techniques in terms of various accuracy metrics.