Design space exploration of Ferroelectric FET based Processing-in-Memory DNN Accelerator

08/12/2019
by   Insik Yoon, et al.
0

In this letter, we quantify the impact of device limitations on the classification accuracy of an artificial neural network, where the synaptic weights are implemented in a Ferroelectric FET (FeFET) based in-memory processing architecture. We explore a design-space consisting of the resolution of the analog-to-digital converter, number of bits per FeFET cell, and the neural network depth. We show how the system architecture, training models and overparametrization can address some of the device limitations.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset