Investigation of statistical retention of filamentary analog RRAM for neuromophic computing

Abstract

The retention requirements of analog RRAM for neuromorphic computing applications are quite different from conventional RRAM for memory applications. Meanwhile, filamentary analog RRAM exhibits different retention behavior in comparison to strong-filament RRAM. For the first time, the statistical behaviors of read current noise and retention in a 1Kb filamentary analog RRAM array are investigated in this work. The conductance distribution of different levels is found to change with time, and the physical mechanism of the retention degradation is elucidated. From the experimental data, a compact model is developed in order to predict the statistical conductance evolution, which can effectively evaluate the impact of read noise and retention degradation in neuromorphic computing systems.