Joonsung Kim Assistant Professor Department of Semiconductor Systems Engineering College of Information and Communication Engineering Sungkyunkwan University Lab: Computer Infrastructure System Architecture (CISA) Lab Email: joonsungkim@skku.edu Office: #400602, Semiconductor Bldg Google Scholar, Linkedin

Research Interests

• Computer Architecture
• System Performance Modeling
• Datacenter-scale Storage System Architecture
• AI Accelerator Architecture
• Deep Learning System Software
• Computer System Security

Education

• Seoul National University, Seoul, Republic of Korea
  • Ph.D in Electrical and Computer Engineering (Advisor: Prof. Jangwoo Kim)
  • Mar. 2017 ~ Feb. 2021


• POSTECH, Pohang, Republic of Korea
  • M.S. in Computer Science and Engineering
  • Mar. 2014 ~ Feb. 2017


• POSTECH, Pohang, Republic of Korea
  • B.S. in Computer Science and Engineering
  • Mar. 2009 ~ Feb. 2014


• Seoul Science High School, Seoul, Republic of Korea
  • Mar. 2006 ~ Feb. 2009

Employment

• Sungkyunkwan University, Suwon, Republic of Korea
  • Assistant Professor
  • Mar. 2024 ~ Current


• Google, Sunnyvale, CA, USA
  • System Software Engineer (Database, Analytics, and Storage Performance Team)
  • Apr. 2022 ~ Mar. 2024


• Seoul National University, Seoul, Republic of Korea
  • Post-doc Researcher (Advisor: Prof. Jangwoo Kim)
  • Mar. 2021 ~ Mar. 2022


• Kakao, Pangyo, Republic of Korea
  • Senior System Engineer (Full-Time), Datacenter-scale storage system design/implementation
  • Feb. 2019 ~ Aug. 2020

Publications

• GCStack: A GPU Cycle Accounting Mechanism for Providing Accurate Insight into GPU Performance
  Hanna Cha, Sungchul Lee, Yeonan Ha, Hanhwi Jang, Joonsung Kim*, and Youngsok Kim*
  IEEE Computer Architecture Letters (CAL) (to appear)


• A Fast and Flexible FPGA-based Accelerator for Natural Language Processing Neural Networks
  Suyeon Hur, Seongmin Na, Dongup Kwon, Joonsung Kim, Eriko Nurvitadhi, Andrew Boutros, and Jangwoo Kim
  ACM Transactions on Architecture and Code Optimization (TACO), Feb. 2023


• 3D-FPIM: An Extreme Energy-Efficient DNN Acceleration System Using 3D NAND Flash-Based In-Situ PIM Unit
  Hunjun Lee, Minseop Kim, Dongmoon Min, Joonsung Kim, Jongwon Back, Honam Yoo, Jongho Lee, and Jangwoo Kim
  Proceedings of the 55th IEEE/ACM International Symposium on Microarchitecture (MICRO), Oct. 2022


• LSim: Fine-Grained Simulation Framework for Large-Scale Performance Evaluation
  Hamin Jang, Taehun Kang, Joonsung Kim, Jaeyong Cho, Jae-Eon Jo, Seungwook Lee, Wooseok Chang, Jangwoo Kim, and Hanhwi Jang
  IEEE Computer Architecture Letters (CAL), Apr. 2022


• UC-Check: Characterizing Micro-operation Caches in x86 Processors and Implications in Security and Performance [Main Talk] [Lightning Talk] [GitHub Repo]
  *Joonsung Kim, *Hamin Jang, Hunjun Lee, Seungho Lee, Jangwoo Kim (* both authors equally contributed to this work.)
  Proceedings of the 54th IEEE/ACM International Symposium on Microarchitecture (MICRO), Oct. 2021


• NLP-Fast: A Fast, Scalable, and Flexible System to Accelerate Large-Scale Heterogeneous NLP Models [Main Talk] [GitHub Repo]
  Joonsung Kim, Suyeon Hur, Eunbok Lee, Seungho Lee, Jangwoo Kim
  Proceedings of the 30th International Conference on Parallel Architectures and Compilation Techniques (PACT), Sep. 2021


• Performance Modeling and Practical Use Cases for Black-Box SSDs
  Joonsung Kim, Kanghyun Choi, Wonsik Lee, and Jangwoo Kim
  ACM Transactions on Storage (TOS), June. 2021


• FIDR: A Scalable Storage System for Fine-Grain Inline Data Reduction with Efficient Memory Handling
  Mohammadamin Ajdari, Wonsik Lee, Pyeongsu Park, Joonsung Kim, and Jangwoo Kim
  Proceedings of the 52nd IEEE/ACM International Symposium on Microarchitecture (MICRO), Oct. 2019


• Enforcing Last-Level Cache Partitioning through Memory Virtual Channels
  Jongwook Chung, Yuhwan Ro, Joonsung Kim, Jaehyung Ahn, Jangwoo Kim, John Kim, Jae W. Lee, and Jung Ho Ahn
  Proceedings of the 28th International Conference on Parallel Architecture and Compilation Techniques (PACT), Sep. 2019


• MnnFast: A Fast and Scalable System Architecture for Memory-Augmented Neural Networks [Lightning Talk]
  *Hanhwi Jang, *Joonsung Kim, Jae-Eon Jo, Jaewon Lee, and Jangwoo Kim (* both authors equally contributed to this work.)
  Proceedings of the 46th International Symposium on Computer Architecture (ISCA), June. 2019


• μLayer: Low Latency On-Device Inference Using Cooperative Single-Layer Acceleration and Processor-Friendly Quantization
  Youngsok Kim, Joonsung Kim, Dongju Chae, Daehyun Kim, and Jangwoo Kim
  Proceedings of the 14th ACM European Conference on Computer Systems (EuroSys), Mar. 2019


• CIDR: A Cost-Effective In-line Data Reduction System for Terabit-per-Second Scale SSD Arrays
  Mohammadamin Ajdari, Pyeongsu Park, Joonsung Kim, Dongup Kwon, Jangwoo Kim
  Proceedings of the 25th IEEE International Symposium on High-Performance Computer Architecture (HPCA), Feb. 2019
  Best Paper Runnuer-Up in HPCA 2019
  Honorable Mention in IEEE MICRO Top Picks 2020
  


• SSDcheck: Timely and Accurate Prediction of Irregular Behaviors in Black-Box SSDs [Lightning Talk] [GitHub Repo]
  Joonsung Kim, Pyeongsu Park, Jaehyung Ahn, Jihun Kim, Jong Kim, Jangwoo Kim
  Proceedings of the 51st IEEE/ACM International Symposium on Microarchitecture (MICRO), Oct. 2018


• DynaMix: Dynamic Mobile Device Integration for Efficient Cross-device Resource Sharing
  Dongju Chae, Joonsung Kim, Gwangmu Lee, Hanjun Kim, Kyung-Ah Chang, Hyogun Lee, and Jangwoo Kim
  Proceedings of the 2018 conference on USENIX Annual technical conference (USENIX ATC '18), July 2018


• SSD Performance Modeling Using Bottleneck Analysis
  *Jihun Kim, *Joonsung Kim, Pyeongsu Park, Jong Kim, and Jangwoo Kim (* both authors equally contributed to this work.)
  IEEE Computer Architecture Letters (CAL), Jan. 2018
  


• A Scalable HW-Based Inline Deduplication for SSD Arrays
  Mohammadamin Ajdari, Pyeongsu Park, Dongup Kwon, Joonsung Kim, and Jangwoo Kim
  IEEE Computer Architecture Letters (CAL), Jan. 2018
  


• CloudSwap: A Cloud-Assisted Swap Mechanism for Mobile Devices
  Dongju Chae, Joonsung Kim, Youngsok Kim, Jangwoo Kim, Kyung-Ah Chang, Sang-Bum Suh, Hyogun Lee
  16th IEEE/ACM International Sympsium on Cluster, Cloud and Grid Computing (CCGrid), May 2016
  

Professional Service

• Program Committee
  • NVMSA 2024
  • ISPASS 2024
  • NAS 2024
• Journal Reviewer
  • IEEE Micro 2023
  • IEEE TC 2024
  • IEEE CAL 2021, 2022, 2023, 2024
  • IEEE TCAD 2021, 2023
  • ACM TACO 2021, 2022, 2023
  • IEEE TMC 2022
  • ACM ToMPECS 2022
  • IEEE TETC 2021, 2024
  • ACM TECS 2024
  • CCPE 2021, 2022

Honors and Awards

• National Science and Engineering Scholarship
  
  • Korea Student Aid Foundation (KOSAF)
  • Mar. 2009 ~ Feb. 2013


• The final round at DEFCON 19 CTF (2011)
  
  • A member of team PLUS@postech
  • Las Vegas, NV


• The final round at DEFCON 20 CTF (2012)
  
  • A member of team PLUS@postech
  • Las Vegas, NV

Teaching Experience

• Teaching Assistant
  • Computer Architecture (SNU), Spring 2017
  • Computer Architecture (POSTECH), Spring 2014
  • Computer Architecture (POSTECH), Spring 2015