“Integrated Spintronics for Artificial Intelligence Applications”
Thursday, Oct. 24 at 1:00pm
MALA 5050
Add to Calendar
Abstract
The history of AI and neuromorphics will be briefly reviewed. Spintronic devices/technology provide an energy-efficient high-speed nonvolatile approach for next-generation memory, information processing, and AI applications in integration with CMOS technology. Among many spintronic devices include those based on spin-transfer torque, spin-orbit torque, and magnetic anisotropy. In particular, we will discuss voltage-controlled spintronic mechanisms including those using magnetic anisotropy (VCMA), exchange, and the Dzyaloshinskii-Moriya Interaction (DMI) for voltage-controlled memories to achieve among the lowest switching energy. These physical mechanisms also enable other additional functionalities. For example, the advantage of stochasticity in these devices via voltage control may offer new opportunities for applications in computing and information processing to alleviate some of today’s challenges of advanced CMOS architectures. The talk will also discuss the challenge in integration of spintronics on CMOS, with respective of e.g., maintaining VCMA coefficient and TMR (Tunnelling Magneto Resistance) in a lab-to-fab effort. Additional case studies to be discussed include stochastic information processing, neuromorphic, generative artificial intelligence, among others. A prospect in using interactions among devices will be discussed as a potential avenue to go beyond today’s simply scaling of density for performance enhancement while with much reduced energy dissipation.
Biography
Dr. Kang L. Wang is currently a Distinguished Professor and the Raytheon Chair Professor in Physical Science and Electronics at the University of California, Los Angeles (UCLA). He is affiliated with the Departments of ECE, MSE, and Physics/Astronomy. He is also the Co-Director of UCLA Quantum Science and Engineering and the Director of the Joint Center of Green Nanotechnology—between UCLA and the King Abdulaziz City for Science and Technology, Saudi Arabia. He received his M.S. and Ph.D. degrees from the Massachusetts Institute of Technology and his B.S. degree from National Cheng Kung University (Taiwan). He was with HKUST as the Dean of School of Engineering from 2000-2003. Previously, he also served as the Chair of Electrical and Computer Engineering of UCLA from 1992-1996. His research areas include earlier in semiconductors, MBE, spintronics/magnetics, nonvolatile electronics, and more recently in topological matters, and quantum information.