Thursday, January 26th
02:00-3:20 PM
C-202: Highlights from University Research on Chiplets (Academic Track)
Paper Title: AI Chiplet Set for Inference and Training with Supply Chain Security

Paper Abstract: We designed, built, and tested the following chiplets: RISC-V controller, Sparese CNN inference engine, and a multi-purpose RNN / MLP / training engine. The chiplets are coordinated via instructions from the software. The system can be scaled by adding identical chiplets. An embedded RFID macro secures the supply chain against counterfeiits.

Paper Author: Paul Franzon, Professor, North Carolina State University

Author Bio: Paul Franzon is a professor and Director of Graduate Programs at North Carolina State University (NCSU). He is also the Site Director Center for Advanced Electronics through Machine Learning (CAEML). A well-known researcher, he has over 400 published papers in such journals as IEEE Transactions on VLSI Systems, IEEE Transactions on Circuits and Systems, and IEEE Electron Device Letters and at important conferences such as ECTC, 3DIC, IEDM, ICCAD, EPEPS, and SOCC. He has also written books and contributed chapters to them. Before joining the NCSU faculty, he worked at AT&T Bell Laboratories and Australia Telecom. He has also founded four technology companies. He earned a PhD from the University of Adelaide (Adelaide, Australia). He is an IEEE Fellow and has received many research and teaching awards.