ECE Seminar Series – Nov 22 (Fri) @ 2:00pm: "Analog vs. Digital Computing: Revisiting the Old to Innovate the New," Nikhil Shukla, Assoc. Prof., ECE, U. of Virginia

Come at 1:30p for Cookies, Coffee and Conversation!
DISTINGUISHED LECTURE at the ECE SEMINAR SERIES

Abstract

Digital computing has enjoyed tremendous success and has become the backbone of the modern information revolution. However, the slowing down of one of its primary drivers, the Moore’s law, and the increasing application-driven necessity to compute problems that have been traditionally challenging to solve on digital machines, has created a convergent need to expand the boundaries of current computing platforms. Non-von Neumann analog computing platforms capable of harnessing the physics of natural systems offer a promising paradigm. 

In this presentation, I will first address the opportunities as well as the challenges of this computing paradigm. Against this backdrop, I will describe some of my lab’s recent experimental and theoretical results on implementing oscillator-based dynamical systems. Specifically, I will present the design and implementation of oscillator Ising machines (and their extensions) to solve hard combinatorial optimization problems. Subsequently, I will also discuss the lab’s ongoing efforts to leverage oscillator dynamics in other computing paradigms, such as probabilistic computing. Finally, I will conclude by identifying some crucial performance metrics that would need to be achieved for such systems to become competitive computing platforms in the future, along with potential pathways to accomplish them.

Bio

Nikhil Shukla is currently an Associate Professor at the University of Virginia in the Department of Electrical & Computer Engineering. He also serves as the UVA deputy site director of the MIST (Multifunctional Integrated System Technology) center, an industry-university cooperative research center. He received his PhD from the University of Notre Dame in 2017. His research interests lie in the general area of the physics of computing, and he is presently interested in exploring opportunities for efficient computation through device-circuit-and computing model co-design. He has authored/co-authored over 85 journal and conference papers. He is a member of IEEE Nanotechnology Council Committee on Quantum, Neuromorphic and Unconventional Computing. He has served as a session chair as well as a technical program committee member for various conferences in the computing and VLSI area such as DAC (Design Automation Conference), ISVLSI (IEEE Computer Society Annual Symposium on VLSI), CICC (Custom Integrated Circuits Conference).

Hosted by: Distinguished Lecture at the ECE Seminar Series

Submitted by: Prof. Kerem Camsari <camsari@ucsb.edu>