Supply-voltage optimization to account for process variations in high-volume manufacturing testing

In a high-volume manufacturing environment, it is difficult to set up test conditions, including supply-voltage levels, that can take into account the wide range of interdie process variations on a wafer. Test conditions that do not take into consideration these process variations can lead to either yield loss or poor quality control. In this work, we propose a method to identify supply-voltage levels to test semiconductor chips based on the process variations experienced by them, while also adapting these supply-voltage levels based on the chip locations on the wafer. For this purpose, we first identified various process zones on the wafer, based on frequencies of on-chip ring oscillators. Next we modeled the ring oscillator (RO) performance in terms of the variations in SPICE parameters using the design of experiments (DoE) method. The equation corresponding to the DoE model was solved for each process zone on the wafer in order to fit a set of independent SPICE parameters set for the corresponding zone. These independent SPICE parameters were then used to create an updated SPICE model for the ring oscillator corresponding to each zone, and these SPICE models were used to derive an appropriate supply-voltage level for each zone. The results were used to test 250 devices to identify chips that exhibit significant performance deviation compared to other chips from the same zone. Among these 250 devices, 89 belonged to the slow zone, 87 belonged to the medium-fast zone, and 74 belonged to the fast process zone. A total of seven devices from the medium-fast zone and nine devices from the fast zone showed performance deviations and they were successfully screened.