Research

Speech and NLP

We explore efficient computations of natural language processing (NLP) and speech recognition applications from software and hardware perspectives.

Probabilistic AI

Etiam ultricies nisi vel augue. Ut tincidunt tincidunt erat. Cras ultricies mi eu turpis hendrerit fringilla.

RecSys Figure 1

RecSys

Recommendation systems form the backbone of popular internet services like entertainment streaming, e-commerce and social media (e.g., Netflix, Amazon, Facebook).

heterogeneous sys modeling optimizations

Heterogeneous System Modeling and Optimization

With Moore's law ending, there is a major push towards heterogeneity, where the modern SoCs consist of general-purpose CPUs, specialized hardware accelerators, GPUs, and FPGAs.

Accelerator Discovery and Programmability

Etiam ultricies nisi vel augue. Ut tincidunt tincidunt erat. Cras ultricies mi eu turpis hendrerit fringilla.

NVMExplorer

eNVM

In the face of the memory wall, DRAM technology scaling issues, the exploration and evaluation of emerging, alternative memory technologies is an essential pursuit for enabling efficient future memory systems.

Privacy-Preserving Machine Learning

We characterize performance overhead of privacy-preserving computation techniques, focusing on homomorphic encryption (HE) technique.

“Agile” Chip Building (CRAFT, ChipKit, Chip Gallery)

Research test chips are the ultimate experiment to demonstrate the true value of novel computer architecture innovations.

Climate/Carbon

Etiam ultricies nisi vel augue. Ut tincidunt tincidunt erat. Cras ultricies mi eu turpis hendrerit fringilla.

Robobees 2.0/Drones

Aerial robots or drones have a variety of applications, such as package delivery, search and rescue, surveillance, sports photography, and more.