Net2: A Graph Attention Network Method Customized for Pre-Placement Net Length Estimation
This work addresses the challenge of pre-placement net length estimation for digital design engineers, which is crucial for optimizing timing and power in early design stages.
This paper introduces Net2, a graph attention network method designed to estimate individual net lengths prior to cell placement. The accuracy-oriented version, Net2a, improves accuracy by approximately 15% in identifying long nets and critical paths compared to prior methods. The fast version, Net2f, is over 1000 times faster than placement while still outperforming previous works in accuracy.
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.