Résumé
Monolithic 3D (M3D) integration offers significant performance, power, and area benefits. However, the design of a reliable power-delivery network (PDN) is challenging for M3D ICs due to high power density and current demand per unit area. In addition, the higher susceptibility of interconnects to electromigra-tion and stress migration increases the complexity of PDN design. We propose a framework to design a reliable PDN for M3D ICs using accurate electrical and reliability models. We leverage genetic programming to explore the design space to optimize the resources dedicated for power delivery in order to achieve reliable operation. We also analyze power-supply noise (PSN) during scan-based testing and compare it with that observed during functional operation. We quantify the impact of PSN during scan-based testing on yield loss. Our results show that the PDN design obtained using the proposed approach significantly increases the reliability of at least 40% of the wire segments in the PDN. In addition, the proposed PDN design reduces the worst-case power-supply droop by 52.5% compared to a baseline PDN. The yield loss due to power-supply droop for the proposed design is also significantly lower compared to a baseline PDN.