Prof. Jiang Hu Visited the HES Group
Prof. Jiang Hu from Texas A&M University visited the HES group on Friday, June 12, 2026, and gave a presentation titled “Optimizing AI Workload Mapping for Custom Accelerators and FPGAs” in meeting room 1.4 - Alan Turing at iGent.
Abstract
AI computing has become a central pillar of the modern high-tech industry. Beyond hardware design, the performance and energy efficiency of AI systems critically depend on how workloads are mapped onto the underlying hardware.
The talk presented several recent advances in this area. First, Prof. Hu introduced an analytical performance and energy model, together with an associated optimization technique, for CNN inference on systolic array-based accelerators. He then described an extension to attention computations, discussed mapping attention workloads onto AI engine-based FPGAs, and concluded with a brief overview of recent efforts in applying AI techniques to chip design.
Speaker Bio
Jiang Hu is the Eric Rubin Professor in the Department of Electrical and Computer Engineering at Texas A&M University. His research interests include optimization and machine learning techniques for chip and AI hardware design automation, approximate computing, and hardware security.
He has co-authored more than 280 technical papers, co-invented 10 patents, and co-edited a book. He received best paper awards at DAC 2001, ICCAD 2011, IEEE International Conference on Vehicular Electronics and Safety 2018, MICRO 2021, ASPDAC 2023, and MLCAD 2024. He served as technical program chair and general chair of the ACM International Symposium on Physical Design in 2011 and 2012, respectively, and was named an IEEE Fellow in 2016.
He was technical program co-chair of the ACM/IEEE Workshop on Machine Learning for CAD 2023 and general co-chair in 2024 and 2025. He is currently Editor-in-Chief of ACM Transactions on Design Automation of Electronic Systems.