Fast Decoupling Capacitor Optimization for Power Delivery Network Based on Model and Data Fusion Method

Optimizing an appropriate design of decoupling capacitors (decaps) is a primary challenge in the field of power delivery network (PDN). A fast PDN impedance acquisition method will expedite the process and enhance the efficiency within an expansive search space for decaps optimization. In this paper, we propose a model and data fusion method to analyze the PDN impedance. The fusion method incorporates the polynomial similarity of the PDN impedance into the deep learning (DL) framework. Moreover, we reduce the dimensionality of the input to compact the network structure and decrease the training time. The experimental results demonstrate that our proposed method promotes the accuracy by 8% compared to other DL methods. In the time of generating outputs, our method is 80 times faster than conventional electronic design automation (EDA) simulation.