No abstract

In this work, the thermal effect in the dynamic on-resistance (R on) degradation of normally-off p-GaN AlGaN/GaN HEMTs on SiC substrates has been analyzed using pulse-mode voltage stress. Compare to the significant degradation characteristics of GaN-on-Si HEMTs, a suppressed dynamic R on degradation is achieved in GaN-on-SiC due to higher thermal boundary conduction with less ionized acceptor-like buffer traps. Different electrical characteristics have been discussed to reveal the traps mechanisms related to thermal effect. Finally, two-dimension device simulation has been carried out to probe the physical insight into the thermal effect on the dynamic R on degradation.

Non-ideal effects of ReRAM are the major limitations of deploying crossbar based neural network accelerator in the real world. Noise injection could effectively mitigate the non-ideal effects because it is equivalent to an adaptive regularization to the neural network. However, software-based noise injection involves computation-hungry retraining and data extraction. In this paper, we propose a ReRAM crossbar based neural network accelerator with current injection to adapt non-ideal effects in the ReRAM crossbar. We inject current into the crossbar through randomly set ReRAM cells to add the adaptive regularization, and no retraining and data extraction is needed in our proposal. We evaluate our method on three neural networks: LeNet-5, ResNet-20 and ResNet-50. Results show that current injection can reduce the accuracy degradation due to Stuck at Fault (SAF) and IR drop to 1%, and 5%, respectively.

No abstract