＃일시: 1월 25일 오전 11시 

＃장소: AS관 510호 

＃주제: Energy-Efficient AI Hardware 

＃연사: 석민구 교수(Columbia University)

＃Abstract: It is exciting to see state-of-the-art artificial intelligence (AI) models achieving human-level performance. But it is also deeply concerning that those models come with tremendous computational complexity, putting significant pressure on the hardware community to make more energy-efficient hardware. Traditionally, device scaling (Moore’s law), Dennard’s scaling, dynamic voltage frequency scaling (DVFS), pipelining, and parallel architecture are the most effective tool for extracting energy efficiency. However, in the last ten years, their efficacy has largely waned. For this reason, recently, hardware researchers have tried various alternative approaches to continue energy efficiency improvement in computing hardware. This seminar will introduce the four most prominent directions: non-von-Neumann architecture, in-memory-computing (IMC), analog-mixed-signal (AMS) computing, and energy-efficient algorithms. In the introduction, we will use the recent hardware prototypes as examples.  

＃Bio: Mingoo Seok is an associate professor of Electrical Engineering at Columbia University. He received his B.S. from Seoul National University, South Korea, in 2005 and his M.S. and Ph.D. degree from the University of Michigan in 2007 and 2011, respectively, all in electrical engineering. His research interests are various aspects of VLSI circuits and architecture, including ultra-low-power integrated systems, cognitive and machine-learning computing, an adaptive technique for the process, voltage, temperature variations, transistor wear-out, integrated power management circuits, event-driven controls, and hybrid continuous and discrete computing. He won the 2015 NSF CAREER award and the 2019 Qualcomm Faculty Award. He is the technical program committee member for multiple conferences, including IEEE International Solid-State Circuits Conference (ISSCC). In addition, he has been an associate editor for IEEE Transactions on Circuits and Systems Part I (TCAS-I) (2014-2016), IEEE Transactions on VLSI Systems (TVLSI) (2015-present), IEEE Solid-State Circuits Letter (SSCL) (2017-present), and as a guest associate editor for IEEE Journal of Solid-State Circuits (JSSC) (2019). 

＃주관: 강석주 교수 연구실