Publication
IEDM 2021
Conference paper

Temperature sensitivity of analog in-memory computing using phase-change memory

Abstract

Can analog in-memory accelerators provide sufficient accuracy for AI applications under ambient temperature variations? Here, we answer this question by focusing on phase-change memory (PCM)-based deep learning acceleration. We investigate for the first time the impact of temperature on multi-level PCM conductance states used to store the synaptic weights. First, we characterize the temperature and drift behavior of 10,000 doped Ge2Sb2Te5 (GST)-based mushroom PCM. Next, we present a model which can capture this behavior and faithfully reproduce the complete time-temperature dependence of the conductance states. Finally, we experimentally study the sensitivity of various network architectures to ambient temperature variations. For this, we employ a multi-layer perceptron, a convolutional neural network and a recurrent neural network, with more than 1.1M PCM weights. We demonstrate that a simple array-level scaling could correct for the conductance shift due to temperature and drift and prevent any significant accuracy drop for all the studied networks during inference.

Date

13 Dec 2021

Publication

IEDM 2021

Authors

Tags

Share