Driving Early Physical Synthesis Exploration through End-of-Flow Total Power Prediction

Leading-edge designs on advanced nodes are pushing physical design (PD) flow runtime into several weeks. Stringent time-to-market constraint necessitates efficient power, performance, and area (PPA) exploration by developing accurate models to evaluate netlist quality in early design stages. In this work, we propose PD-LSTM, a framework that leverages graph neural networks (GNNs) and long short-term memory (LSTM) networks to perform end-offlow power predictions in early PD stages. Experimental results on two commercial CPU designs and five OpenCore netlists demonstrate that PD-LSTM achieves high-fidelity total power prediction results within 4% normalized root-mean-squared error (NRMSE) on unseen netlists and a correlation coefficient score as high as 0.98.