Neuromorphic Computing Memristive Device
Qiangfei Xia and Joshua Yang
Resistance switching devices, also known as memristive devices, represent the next generation in computing. With a typical metal/insulator/metal structure, memristors change resistance based on past current flow and retain this new resistance even when turned off. This allows memristors to store data without needing constant power like in traditional computer memory. Memristors have other desirable properties such as low power consumption, fast switching speed, and great cycling ability. These properties open up next generation computing applications in non-volatile memory, reconfigurable switches, bio-inspired neuromorphic computing, and radiofrequency switches. Here, Dr. Qiangfei Xia and Dr. Joshua Yang have invented a Ta/HfO2/Pt memristive device that can be used for multilevel memory and for neuromorphic computing. The device exhibits bipolar resistive switching with low programming voltage (~1.5 V), high endurance (100 billion cycles), and long data retention time (37,000 years at 85 C). The device can be programmed to multiple resistance states with long retention time for each individual state. Finally, spike dependent plasticity (STDP) is also demonstrated for this device. The device also has the advantage of being able to be fabricated using traditional CMOS materials and techniques.
• Record high endurance: 100 billion cycles • Extremely long memory retention, estimated 37,000 years • Low programming voltage (~1.5 V) • Fast switching speeds (< 5 ns) • Up to 64 discrete resistance levels possible • Can be manufactured with existing CMOS materials and techniques
• Computer memory • Data storage, including long term • New computing hardware • Neuromorphic computing
Dr. Qiangfei Xia is a professor of Electrical & Computer Engineering at UMass Amherst and head of the Nanodevices and Integrated Systems Lab. He received his Ph.D. in Electrical Engineering in 2007 from Princeton University, where he was a recipient of the Guggenheim Fellowship in Engineering (a graduate fellowship from Princeton). He then spent three years as a research associate in the Hewlett Packard Laboratories in Palo Alto, California. In October 2010, he joined the faculty of UMass Amherst as an assistant professor. He became an associate professor with tenure in January 2016 and then a full professor in September 2018. Dr. Xia's research interests include beyond-CMOS devices, integrated systems and enabling technologies, with applications in machine intelligence, reconfigurable RF systems and hardware security. He has received a DARPA Young Faculty Award (YFA), an NSF CAREER Award, and the Barbara H. and Joseph I. Goldstein Outstanding Junior Faculty Award. Dr. Yang is a professor in the Department of Electrical and Computer Engineering at the University of Massachusetts, Amherst. Before Joining UMass in 2015, he spent over 8 years at HP Labs, leading the materials and devices team. His current research interests are Nanoelectronics and Nanoionics, especially for energy and computing applications, where he authored and co-authored over 140 papers in peer-reviewed academic journals, and holds 110 granted and about 55 pending US Patents. He obtained his B.A. degree in mechanical engineering from Southeast University in China and PhD from the University of Wisconsin – Madison in Material Science Program in 2007. He was a co-chair of the RRAM session of IEDM 2014. He was the chair of the 8th IEEE Nanotechnology SFBA Council Symposium on “Emerging Non-volatile Memory Technologies” and also the chair of the 10th symposium on “The Promise and Progress of Nanotech Enabled 2D Devices and Materials. He has guest-edited 6 journal special issues on Memory or unconventional computing. He was named as a Spotlight Scholar of UMass Amherst in 2017. Available for Licensing and/or Sponsored Research
UMA 15-050
Patent U.S. 10,186,660 Issued
|
