(Invited) Development, Characterization, and Modeling of a TaOx ReRAM for a Neuromorphic Accelerator

• Published in: ECS transactions Vol. 64; no. 14; pp. 37 - 42
• Main Authors: Marinella, Matthew J., Mickel, Patrick R, Lohn, Andrew J, Hughart, David R., Bondi, Robert, Mamaluy, Denis, Hjalmarson, Harold P., Stevens, James E, Decker, Seth, Apodaca, Roger T, Evans, Brian, Aimone, James Bradley, Rothganger, Fred, James, Conrad D., DeBenedictis, Erik P
• Format: Journal Article Conference Proceeding
• Language: English
• Published: United States The Electrochemical Society, Inc 01.01.2014
• ISSN: 1938-5862; 1938-6737; 1938-6737
• DOI: 10.1149/06414.0037ecst

Resistive random access memory (ReRAM), or memristors, may be capable of significantly improving the efficiency of neuromorphic computing, when used as a central component of an analog hardware accelerator. However, the significant electrical variation within a single device and between devices degrades the maximum efficiency and accuracy which can be achieved by a ReRAM-based neuromorphic accelerator. In this report, the electrical variability is characterized, with a particular focus on that which is due to fundamental, intrinsic factors. Analytical and ab initio models are presented which offer insight into the factors responsible for this variability.