# Static IR Drop Prediction with Attention U-Net and Saliency-Based Explainability

arXiv: https://arxiv.org/abs/2408.03292 · HTML: https://mlsanity.com/paper/2408.03292/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 6 Aug 2024.

## Builds on (most cited first, 8 of 8)

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Embedded Encoder-Decoder in Convolutional Networks Towards Explainable AI](https://mlsanity.com/paper/2007.06712/) (2020)
- [PowerNet: Transferable Dynamic IR Drop Estimation via Maximum Convolutional Neural Network](https://mlsanity.com/paper/2011.13494/) (2020)
- [Thermal and IR Drop Analysis Using Convolutional Encoder-Decoder Networks](https://mlsanity.com/paper/2009.09009/) (2020)
- [Unsupervised Learning of Neural Networks to Explain Neural Networks](https://mlsanity.com/paper/1805.07468/) (2018)

## Abstract (arXiv)

There has been significant recent progress to reduce the computational effort of static IR drop analysis using neural networks, and modeling as an image-to-image translation task. A crucial issue is the lack of sufficient data from real industry designs to train these networks. Additionally, there is no methodology to explain a high-drop pixel in a predicted IR drop image to its specific root-causes. In this work, we first propose a U-Net neural network model with attention gates which is specifically tailored to achieve fast and accurate image-based static IR drop prediction. Attention gates allow selective emphasis on relevant parts of the input data without supervision which is desired because of the often sparse nature of the IR drop map. We propose a two-phase training process which utilizes a mix of artificially-generated data and a limited number of points from real designs. The results are, on-average, 18% (53%) better in MAE and 14% (113%) in F1 score compared to the winner of the ICCAD 2023 contest (and U-Net only) when tested on real designs. Second, we propose a fast method using saliency maps which can explain a predicted IR drop in terms of specific input pixels contributing the most to a drop. In our experiments, we show the number of high IR drop pixels can be reduced on-average by 18% by mimicking upsize of a tiny portion of PDN's resistive edges.