Efficient Programming on Heterogeneous Accelerators

Abstract

How to map deep learning workloads onto heterogeneous SoCs with FPGAs and tensor cores? How to explore latency-throughput tradeoffs? How to extend these strategies to GPUs?

Date
May 9, 2025 12:00 PM — 4:00 PM
Location
Sharp Laboratory, University of Delaware, Newark, DE 19716, USA
Peipei Zhou
Peipei Zhou
Assistant Professor of Engineering

My research interests include Customized Computer Architecture and Programming Abstraction for Health & AI Applications