Research Overview: Explore the boundary and beyond

​Our research generally covers the area of energy efficient computing with exploratory approaches.

​Mission: With several years' industry experience in both large and startup companies, my research combines the "realistic" practice with "futuristic" developments. As conventional design methodology has reached several bottlenecks, we dedicate our efforts to explore the "unknown territories" at the boundary and/or beyond the existing technologies.

Approach: As AI, 5G, IoT technologies are just around the corner, we are at an exciting time where many new opportunites in computing hardware are appearing. Compared with a decade ago when CMOS technology scaling provides us sufficient steam for improvement, we are at a critical point where revolutionary circuit, architecture, and system solutions are urgently needed to meet the ever-increasing demands on computing power. To achieve this goal, we explore novel solutions such as neural network based general purpose computer architecture or time-based circuits techniques to many challenging computing jobs, e.g. machine learning algorithms, advanced AI tasks, etc. At system level, we use "cross-layer" design approaches at conjunctions of the hardware and software and leverage both digital and analog techniques to achieve higher efficiency in computing. Below summarizes a few topics that we are currently working on.


Novel Computing Architecture for Edge AI Devices

We are developing novel computing architectures to resolve bottleneck at resource limited edge devices. For instance, we demonstrated the first deep neural network based CPU with significant area, power and performance benefits.



Time-domain Mixed-signal Processing and Neuromorphic Computing

As conventional digital computing based on Boolean logic is reaching its energy bottleneck, we are looking for new ways of processing information. In this thrust, we are exploring a "time-domain computing" where time is used as an information carrier. In essence, it is a mixed-signal approach where high efficiency is achieved combining operation at different dimensions, including both time and voltage domains. To certain extents, this is similar as spiking based neuromorphic operations, but at more deliberate levels. We demonstrate such techniques on emerging machine learning applications.


Neural Processing for Biomedical Application and AI based Human Machine Interface

Collaborated with Ryan Shirley Ability Lab (Formerly Rehab Center of Chicago), we are designing AI empowered neural processing devices for biomedical applications with 1,000X saving on power consumption. The applications extend into robotics, virtual reality, intelligient human machine interface, etc.


Greybox Computing: Instruction and Computing-Adaptive Hardware Management

In this thrust, we "fuse" the software-level computing knowledge, i.e. instruction of the program or arithmetic operands with associated hardware units. An integrated clock and power management methods are created where fine-grained computing tasks dictate hardware operation, e.g. clock phase scaling, for energy efficient computing. The techniques have been applied to CPU, GPU, and CNN accelerators.



Fully Integrated Power Management Circuits with Digital Assistance and Machine Learning

In this project, we are designing fast fully-integrated power converters with digital machine learning techniques to achieve the state-of-the-art power efficiency and power integrity.