MACHINE LEARNING INSIDE THE CELL TO SOLVE COMPLEX FINFET DEFECT MECHANISMS WITH VOLUME SCAN DIAGNOSIS

摘要

Device complexity is reaching an all-time high with the adoption of high aspect ratio FinFETs created using multi-patterning process technologies. Simultaneously, new product segments such as artificial intelligence (AI) and automotive are targeting advanced processes. In this dynamic environment, new and complex defect modes are threatening the ability of manufacturers to ramp up and sustain semiconductor quality and yield. A growing source of quality and yield problems stems from the effect of process variability on standard cells, which introduces new transistor-level defect modes. Meanwhile, the cost of traditional failure analysis (FA) continues to skyrocket. This article details a new breakthrough in the field of scan diagnosis and machine learning. For the first time, cell-internal defects not only can be detected and diagnosed, but also refined, clarified, and resolved with a root cause deconvolution (RCD) algorithm. Experimental FA results show that RCD is very effective at increasing the resolution of the diagnosis by reducing the number of suspects in cell-internal defect data.