Abstract

In this research, a signal-integrity control strategy of a through-silicon via (TSV) array for a Chiplet-based system is developed, based on the backpropagation neural network (BP-NN) model and particle swarm optimization algorithm with linear decreasing inertia weight (PSO-LDIW). Based on the HFSS software, the simulation results of the TSV array are obtained. The irregular relationship between design parameters (TSV pitches, height of TSV, radius of TSV, thickness of oxide layer, and offset angle) and signal indexes (return loss, insertion loss, near-end, and far-end crosstalk) is established by the BP-NN model. Then, the design parameters of the TSV array are optimized by the PSO-LDIW algorithm to obtain the desired signal indexes. Based on the optimized design parameters, the effectiveness of the developed signal-integrity control strategy is verified by HFSS simulations. For the three verification cases, the relative errors between the BP-NN-predicted values and the corresponding HFSS simulation values range from 0.31% to 5.02%. The relative deviations of the HFSS results from the desired NEXT, FEXT, and return-loss targets are no greater than 5.72%, while the maximum absolute deviation from the desired insertion-loss target is 0.0160 dB. These results demonstrate the feasibility of the developed strategy for controlling the signal indexes of the TSV array in the tested cases.

IPC Classification

Keywords