As the size of base station antenna arrays continues to grow, even with linear processing algorithms, the computational complexity and power consumption required for massive MIMO equalization or precoding (EoP) matrix computation increase exponentially. This paper proposes an inverse matrix minibatch gradient descent (IM-MBGD) method for MIMO EoP. The proposed method leverages minibatch gradient descent to compute the pseudo-inverse of the Gram matrix instead of directly calculating the EoP matrix. Since the pseudo-inverse matrix has significantly lower dimensions compared to the EoP matrix, this approach effectively reduces computational complexity and accelerates convergence. Based on our convergence analysis, to further minimize the iteration time and improve the accuracy of the EoP matrix, we optimize the IM-MBGD method using a finite-alphabet neighborhood search. The finite-alphabet search performs neighborhood optimization to achieve the optimal solution. Compared to state-of-the-art alphabet-based equalizers, our proposed method achieves a 14-fold reduction in computational complexity for EoP matrix calculation. Furthermore, in terms of storage and the overall equalization process, our method reduces overhead by 80% compared to linear equalizers.

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.