Channoh Kim
Presently, I am employed at Google in the capacity of an edge TPU architect, contributing to the development of Google's Pixels. Before my tenure at Google, I was a system architect for network offloading engine at Mangoboost and an SoC/hardware IP researcher at Samsung Advanced Institute of Technology (SAIT). At Samsung, I focused on designing hardware architectures for the NPU, which was integrated into the Exynos platform. I have a specialty in hardware‐software co‐design for emerging applications and optimizations across systems and architectures.
I was an M.S. / Ph.D. student at Electrical and Computer Engineering Department in SungKyunKwan University as a member of Architecture and Code Optimization (ARC) Lab in Seoul National University. My dissertation focused on architectural techniques to accelerate scripting languages, particularly extending in-order or out-of-order CPU pipeline to accelerate scripting engines efficiently.
- channoh (at) gmail (dot) com
Experience
Education
Publications [Google Scholar]
[ISCA '21] Jun-Woo Jang, Sehwan Lee, Dongyoung Kim, Hyunsun Park, Ali Shafiee Ardestani, Yeongjae Choi, Channoh Kim, Yoojin Kim, Hyeongseok Yu, Hamzah Abdel-Aziz, Jun-Seok Park, Heonsoo Lee, Dongwoo Lee, Myeong Woo Kim, Hanwoong Jung, Heewoo Nam, Dongguen Lim, Seungwon Lee, Joon-Ho Song, Suknam Kwon, Joseph Hassoun, SukHwan Lim, Changkyu Choi "Sparsity-Aware and Re-configurable NPU Architecture for Samsung Flagship Mobile SoC", 48th IEEE/ACM International Symposium on Computer Architecture (ISCA-48), Valencia, Spain, June 2021.
[ASPLOS '17] Channoh Kim, Jaehyeok Kim, Sungmin Kim, Dooyoung Kim, Namho Kim, Gitae Na, Young H. Oh, Hyeon Gyu Cho, and Jae W. Lee, "Typed Architectures: Architectural Support for Lightweight Scripting", 22nd ACM Architectural Support for Programming Languages and Operating Systems (ASPLOS), Xi'an, China, April 2017. [pptx] - Selected for ASPLOS Highlights session
[ISCA '16] Channoh Kim, Sungmin Kim, Hyeon Gyu Cho, Dooyoung Kim, Jaehyeok Kim, Young H. Oh, Hakbeom Jang, and Jae W. Lee, "Short-Circuit Dispatch: Accelerating Virtual Machine Interpreters on Embedded Processors", 43rd IEEE/ACM International Symposium on Computer Architecture (ISCA-43), Seoul, Korea. June 2016. [pptx]
[PPoPP-Poster '15] Xianglan Piao, Channoh Kim, Younghwan Oh, Huiying Li, Jin Cheon Kim, Hanjun Kim, and Jae W. Lee, "JAWS: A JavaScript Framework for Adaptive CPU-GPU Work Sharing", 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, San Francisco, California. February 2015.
[ISLPED '14] Wonjun Lee, Channoh Kim, and Jae W. Lee, "QPR.js: A Runtime Framework for QoS-Aware Power Optimization for Parallel JavaScript Programs", IEEE/ACM International Symposium on Low Power Electronics and Design, La Jolla, California. August 2014.
[WWW-Poster '14] Xianglan Piao, Channoh Kim, Younghwan Oh, Hanjun Kim, and Jae W. Lee, "Efficient CPU-GPU Work Sharing for Data-Parallel JavaScript Workloads", 23rd International World Wide Web Conference, Seoul, Korea. April 2014.
[PRISM '14] Younghwan Oh, Xianglan Piao, Channoh Kim, and Jae W Lee "Automatic Runtime Selection of Best Hardware for Data-Parallel JavaScript Kernels via Lifelong Profiling", 2nd International Workshop on Parallelism in Mobile Platforms, Minneapolis, Minnesota. June 2014. [pptx]
[LCTES '13] Hakbeom Jang, Channoh Kim, and Jae W. Lee, "Practical Speculative Parallelization of Variable-Length Decompression Algorithms", Proceedings of the 14th ACM SIGPLAN/SIGBED conference on Languages, compilers and tools for embedded systems, Seattle, Washington. July 2013.