Title:
Efficient Programming on Heterogeneous Accelerators
Abstract:
In this talk, I will first discuss how new mapping solutions, i.e., composing heterogeneous accelerators within a system-on-chip with both FPGAs and AI tensor cores, achieve orders of magnitude energy efficiency gains when compared to monolithic accelerator mapping designs for deep learning applications. Then, I will apply such novel mapping solutions to show how design space explorations are performed when composing heterogeneous accelerators in latency-through tradeoff analysis. Finally, I will discuss how such heterogeneous computing approaches can be extended to a range of real-world application domains, including autonomous vehicles, privacy-preserving pedestrian detection, etc.
Speaker:
Peipei Zhou
Assistant Professor, School of Engineering, Brown University
Bio:
Peipei Zhou is currently an Assistant Professor at the School of Engineering, Brown University. She received her Ph.D. in Computer Science (2019) and M.S. in Electrical and Computer Engineering (2014) from UCLA, and her B.S. in Electrical and Computer Engineering (2012) from Southeast University. Her research investigates architecture, programming abstraction, and design automation tools for reconfigurable computing and heterogeneous computing. She has published over 40 papers in IEEE/ACM computer system and design automation conferences and journals. She is a recipient of the 2026 NSF CAREER Award. Her work has won the 2019 IEEE TCAD Donald O. Pederson Best Paper Award, 2025 IEEE/ACM ICCAD 10-Year Retrospective Most Influential Paper Award, and 2026 ACM International Green and Sustainable Computing (IGSC) Best Paper Award. Other awards include the 2024 IEEE IGSC Best Viewpoint Paper, the 2025 ACM/SIGDA FPGA Best Paper Nominee, the 2018 IEEE ISPASS Best Paper Nominee, and the 2018 IEEE/ACM ICCAD Best Paper Nominee.
Host: Professor John McNeill