1. [Publications](/publications) 2. GRANNITE: Graph Neural Network Inference for Transferable Power Estimation # GRANNITE: Graph Neural Network Inference for Transferable Power Estimation ![](/sites/default/files/styles/wide/public/publications/GRANNITE.PNG?itok=0VoD1fJg) This paper introduces GRANNITE, a GPU-accelerated novel graph neural network (GNN) model for fast, accurate, and transferable vector-based average power estimation. During training, GRANNITE learns how to propagate average toggle rates through combinational logic: a netlist is represented as a graph, register states and unit inputs from RTL simulation are used as features, and combinational gate toggle rates are used as labels. A trained GNN model can then infer average toggle rates on a new workload of interest or new netlists from RTL simulation results in a few seconds. Compared to traditional power analysis using gate-level simulations, GRANNITE achieves >18.7X speedup with an error of only <5.5% across a diverse set of benchmark circuits. Compared to a GPU-accelerated conventional probabilistic switching activity estimation approach, GRANNITE achieves much better accuracy (on average 25.9% lower error) at similar runtimes. ## Authors [Yanqing Zhang](/person/yanqing-zhang) Mark Haoxing Ren (NVIDIA) [Brucek Khailany](/person/brucek-khailany) ## Publication Date Tuesday, July 21, 2020 ## Published in [Design Automation Conference (DAC) 2020](https://www.dac.com/) ## Research Area [Circuits and VLSI Design](/research-area/circuits) [Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence) ## Uploaded Files [034\_2\_GRANNITE.pdf](https://research.nvidia.com/sites/default/files/pubs/2020-07_GRANNITE%3A-Graph-Neural//034_2_GRANNITE.pdf "Open file in new window")1.42 MB ## Copyright This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to .