Hybrid Hotspot Detection Using Regression Model And Lithography Simulation

As minimum feature sizes shrink, unexpected hotspots appear on wafers. Therefore, it is critical to detect and fix these hotspots at design stage to reduce development time and manufacturing cost. Currently, the most accurate approach to detect such hotspots is lithography simulation. However, it is known to be time-consuming. This paper proposes a new hotspot detection method with both a regression model and lithography simulation. Experimental results show that the proposed detection method is able to reduce computational time without accuracy loss compared to the conventional lithography simulation based hotspot detection method.