ON-state retention of Atom Switch eNVM for IoT/AI Inference Solution

An ON-state retention of a 40nm-node atom switch embedded nonvolatile memory (eNVM) has been carefully investigated for IoT/AI inference solution. Based on ON-conductance (G
_on
) tuning model of atom switch, one order of magnitude lower programming power is achieved while keeping the same G
_on
. Smaller ON-state retention dependences on temperature (E
_a
= 0.2eV) and time (n = 0.11) are experimentally clarified and the lifetime is predicted to be more than 10 years at 150°C under +20% shift criteria of G
_on
.