제목Compiler Techniques for Machine Learning
연사연세대학교 김한준 교수
This talk consists of three parts. The first part briefly explains existing DNN compiler frameworks such as TVM and MLIR. Then, the second part introduces a DNN compiler framework developed by Corelab at Yonsei University. Finally, the third part introduces a paper about real-time object detection that was recently published at RTAS 2020.
Hanjun Kim is an associative professor in the Department of Electrical and Electronic Engineering at Yonsei University. He received his B.S. in electrical engineering from Seoul National University in 2007, and his M.A. and Ph.D. in computer science from Princeton University in 2009 and 2013. From 2013 to 2018, he was an assistant and associate professor at the Departments of Creative IT Engineering and Computer Science and Engineering at POSTECH. He was awarded the Intel Corporation Ph.D. Fellowship and the Siebel Scholarship in 2012, and the KIISE/IEEE-CS Young Computer Researcher Award in 2020. His research interests include computer architecture and compiler optimization for distributed and emerging systems.