Area Director, Integrated Circuits & Embedded Systems, National University of Singapore
Massimo Alioto is a Professor at the ECE Department of the National University of Singapore, where he leads the Green IC group, and is the Director of the Integrated Circuits and Embedded Systems area. He held positions at the University of Siena, Intel Labs CRL, University of Michigan Ann Arbor, University of California Berkeley, EPFL - Lausanne.
He is (co)author of >350 publications on journals and conference proceedings, and five books with Springer. His primary research interests include widely energy-scalable circuits and systems, green & sustainable silicon systems, circuits for machine intelligence, hardware security, among the others.
He was the Editor in Chief of the IEEE Transactions on VLSI Systems, Deputy Editor in Chief of the IEEE Journal on Emerging and Selected Topics in Circuits and Systems, and Distinguished Lecturer for both the IEEE Solid-State Circuits and the Circuits and Systems Society. He has led numerous journal special issues (e.g., JSSC, TCAS-I, JETCAS), IEEE conferences (e.g., ISCAS 2023, SOCC, ICECS), and has been TPC member of ISSCC and ASSCC. In the last five years, he has given 50+ invited talks in top conferences and leading semiconductor companies, and his Green IC research group has spurred more than 100 silicon chip demonstrations. His research has received various best paper awards (e.g., ISSCC 2023) and public recognition from industry (e.g., among 10 technology highlights from TSMC annual report in 2020). Prof. Alioto is an IEEE Fellow.
Presentation Title: Enabling Next-Generation Attentive & Intelligent AI Systems - At the Edge, at Scale
The on-going trend of distributed and decentralized AI mandates relentless innovation to embed intelligence in edge devices at an uncompromised level of system attention (nearly always-on). In this talk, key enablers for sustainable and scalable growth of AI at the edge are presented and supported with a wide range of innovative silicon designs with unprecedented capabilities. As key message, building and scaling up next-generation distributed attentive & intelligent AI will need both fundamental rethinking and the removal of the (artificial) design barriers we are used to, before it can be built in the first place.