This research program highlights the importance of hardware in pushing the frontiers of artificial intelligence across a broad spectrum of applications from the edge to the cloud. The program has roots in two previous efforts: System Level Design (SLD) and Efficiency and Performance for Connectivity Constrained Computing (EP3C).
The AI Hardware research program is comprised of five major categories:
• Architectures for Power Efficient AI Acceleration
• Modeling, Analysis, and Simulation/Emulation of AI Hardware for Early System Exploration
• HW/SW Co-design of AI Compute Systems
• Fairness, Robustness, Privacy, and Explainability of Models and Algorithms for AI Hardware
• Interplay of AI and System Architecture/Microarchitecture Design
In each category, there may be research covering large systems to small (datacenter and the edge/end node) as well as a broad range of applications, including high-performance processors for data centers, automotive, industrial, mobile computing and communication, and healthcare.
Current33 Research Tasks25 Universities66 Students39 Faculty Researchers100 Liaison Personnel
This Year22 Task Starts156 Research Publications
Last Year3 Task Starts70 Research Publications
Since Inception48 Research Tasks35 Universities81 Students56 Faculty Researchers114 Liaison Personnel295 Research Publications