Analysis of Conductance Variability in RRAM for Accurate Neuromorphic Computing
Hassen Aziza (Aix Marseille Université)
J. Postel-Pellerin (Aix Marseille Université)
Moritz Fieback (TU Delft - Computer Engineering)
S. Hamdioui (TU Delft - Computer Engineering)
H. Xun (TU Delft - Computer Engineering)
Mottaqiallah Taouil (TU Delft - Computer Engineering)
Karine Coulié (Aix Marseille Université)
W. Rahajandraibe (Aix Marseille Université)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
While Resistive RRAM (RRAM) offers attractive features for artificial neural networks (NN) such as low power operation and high-density, its conductance variation can pose significant challenges when the storage of synaptic weights is concerned. This paper reports an experimental evaluation of the conductance variations of manufactured RRAMs at the memory array level. Working at the memory array level allows to catch cycle-to-cycle (C2C) as well as device-to-device (D2D) variability and, hence, to propose a realistic evaluation of the conductance variation. Variability is evaluated with respect to the RRAM low resistance state (LRS) and high resistance state (HRS) conductance ratio. This ratio is selected as the parameter of interest as it guarantees the proper operation of the RRAM: the larger the ratio, the more reliable and robust the RRAM cell is in storing and retrieving data. The measurement results show that the conductance ratio is heavily affected by variability. Large spatial and temporal variations are reported, making challenging RRAM-based analog weight storage.