Machine Learning Based Fast Power Integrity Classifier
This work addresses power integrity issues in chip design, but it appears incremental as it compares existing machine learning models without introducing a fundamentally new approach.
The paper tackled the problem of quickly identifying electromagnetic and IR hotspots in power grids by proposing a machine learning classifier, achieving promising prediction accuracy on an open-source benchmark.
In this paper, we proposed a new machine learning based fast power integrity classifier that quickly flags the EM/IR hotspots. We discussed the features to extract to describe the power grid, cell power density, routing impact and controlled collapse chip connection (C4) bumps, etc. The continuous and discontinuous cases are identified and treated using different machine learning models. Nearest neighbors, random forest and neural network models are compared to select the best performance candidates. Experiments are run on open source benchmark, and result is showing promising prediction accuracy.