Bongjun Kim

Bongjun Kim [김봉준]

Staff Researcher

Computing S/W TU, Samsung Advanced Institute of Technology (SAIT)

Personal Profile

I am currently a Staff Researcher at Samsung Advanced Institute of Technology (SAIT). My primary research interests lie in the design of universal compilers for diverse computing platforms, leveraging compiler infrastructures such as LLVM and MLIR. I focus on enhancing computational efficiency and performance by integrating cutting-edge compiler technologies across various hardware architectures.

Computing S/W TU (System Research Center) (CSTU at SAIT)
Samsung Advanced Institute of Technology [삼성종합기술원] (SAIT)
Samsung Electronics [삼성전자] (Samsung)

Education

2016.03 ~ 2021.08

Pohang University of Science and Technology, POSTECH

Ph.D. in Department of Computer Science and Engineering, August 2021
Dissertation: "Semantic-aware Automatic Program Partitioning and Privacy-preserving Selective Encryption for Fog Computing"
Advisor: Prof. Hanjun Kim and Prof. Jong Kim

2009.03 ~ 2016.02

Pohang University of Science and Technology, POSTECH

B.S. in Department of Computer Science and Engineering, February 2016

Experience

2021.09 ~ Present

Staff Researcher, Computing S/W TU, Samsung Advanced Institute of Technology (SAIT)

2016.03 ~ 2021.08

Research Assistant, Compiler Optimization Research Laboratory (CoreLab), POSTECH / Yonsei University

2019.09 ~ 2020.01

Research Intern, Samsung Advanced Institute of Technology (SAIT)

2014.03 ~ 2016.02

Undergraduate Research Assistant, Compiler Optimization Research Laboratory (CoreLab), POSTECH

Recognition

  • Silver Medal, Graduate Student Research Competition at International Symposium on Code Generation and Optimization (CGO), February 2020 (Winners, SRC 2019-2020)

  • Best Oral Presentation Award, Student Workshop at Department of Computer Science and Engineering (POSTECH), September 2016

Publications

    Refereed International Conference Publications

    [ISC-HPC'24] Programming Model Extensions for General-Purpose Processing-In-Memory [abstract] (IEEE Xplore)
    Hyesun Hong, Lukas Sommer, Bongjun Kim (Oral Presenter), Mikhail Kashkarov, Kumudha Narasimhan, Ilya Veselov, Mehdi Goli, Jaeyeon Kim, Ruyman Reyes Castro, and Hanwoong Jung
    Proceedings of the 39th International Conference on High Performance Computing, ISC High Performance 2024 (ISC-HPC), May 2024.

    [FCCM'24] MPC-Wrapper: Fully Harnessing the Potential of Samsung Aquabolt-XL HBM2-PIM on FPGAs [abstract] (IEEE Xplore)
    Jinwoo Choi, Yeonan Ha, Hanna Cha, Seil Lee, Sungchul Lee, Jounghoo Lee, Shin-haeng Kang, Bongjun Kim, Hanwoong Jung, Hanjun Kim, and Youngsok Kim
    The 32nd IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM), May 2024.

    [EMSOFT'21] Precise Correlation Extraction for IoT Fault Detection with Concurrent Activities [abstract] (ACM DL, PDF)
    Gyeongmin Lee, Bongjun Kim, Seungbin Song, Changsu Kim, Jong Kim, and Hanjun Kim
    Proceedings of the International Conference on Embedded Software (EMSOFT), October 2021.

    [RTAS'20] Sharing-aware Data Acquisition Scheduling for Multiple Rules in the IoT [abstract] (IEEE Xplore, DATASET, PDF)
    Seonyeong Heo, Seungbin Song, Bongjun Kim, and Hanjun Kim
    Proceedings of the IEEE Real-Time And Embedded Technology And Applications Symposium (RTAS), April 2020.

    [CC'19] Spinal Code: Automatic Code Extraction for Near-User Computation in Fogs [abstract] ( ACM DL, PDF)
    Bongjun Kim (Oral Presenter), Seonyeong Heo, Gyeongmin Lee, Seungbin Song, Jong Kim, and Hanjun Kim
    Proceedings of the 28th International Conference on Compiler Construction (CC), February 2019.

    [RSP'17] Rapid prototyping of IoT applications with Esperanto compiler [abstract] (ACM DL, PDF)
    Gyeongmin Lee, Seonyeong Heo, Bongjun Kim, Jong Kim, and Hanjun Kim
    Proceedings of the 28th International Symposium on Rapid System Prototyping (RSP), October 2017. Invited.

    [LCTES'17] Integrated IoT Programming with Selective Abstraction [abstract] (ACM DL, PDF)
    Gyeongmin Lee, Seonyeong Heo, Bongjun Kim, Jong Kim, and Hanjun Kim
    Proceedings of the 18th ACM SIGPLAN/SIGBAD Conference on Languages, Compilers, Tools, and Theory for Embedded Systems (LCTES), June 2017.

    Refereed International Journal Publications

    [IEEE IoT-J'21] ComFlex: Composable and Flexible Resource Management for the IoT [abstract] ( IEEE Xplore, PDF)
    Gyeongmin Lee, Bongjun Kim, Seungbin Song, Seonyeong Heo, and Hanjun Kim
    IEEE Internet of Things Journal, Volume 8, Issue 22, November 2021.
    IF=9.936, Q1 (JCR 2019)

    [IEEE IoT-J'21] Compiler-assisted Semantic-aware Encryption for Efficient and Secure Serverless Computing [abstract] (SelectiveCrypt, IEEE Xplore, PDF)
    Bongjun Kim, Seonyeong Heo, Jaeho Lee, Shinnung Jeong, Yongwoo Lee, and Hanjun Kim
    IEEE Internet of Things Journal, Volume 8, Issue 7, April 2021.
    IF=9.936, Q1 (JCR 2019)

    [IEEE Micro'16] Heterogeneous Distributed Shared Memory for Lightweight Internet-of-Things Devices [abstract] (IEEE Xplore, PDF)
    Bongjun Kim, Seonyeong Heo, Gyeongmin Lee, Soyeon Park, Hanjun Kim, and Jong Kim
    IEEE Micro, Volume 36, Issue 6, November 2016.
    IF=1.933, Q2 (JCR 2016)

    Patents

    Electronic device and method with processing in memory operation
    Youngsok Kim, Sungchul Lee, Seil Lee, Suhyun Lee, Jounghoo Lee, Chaemin Lim, Hanna Cha, Jinwoo Choi, Yeonan Ha, Bongjun Kim, and Hanwoong Jung
    US Patent App. US19/060889, Feb 2025.

    Method and device with iterative compilation for deep learning
    Gyeongmin Lee, Bongjun Kim, and Hanwoong Jung
    US Patent App. US18/668580, May 2024.

    Electric device and method with hardware-optimized compilation
    Bongjun Kim, Gyeongmin Lee and Hanwoong Jung
    US Patent App. US18/657062, May 2024.

    Near-memory operator and method with accelerator performance improvement [google patents]
    Gyeongmin Lee, Bongjun Kim, Seungwon Lee and Hanwoong Jung
    US Patent App. US20240256277A1, August 2023.

    IoT Service Providing Method Based on Adaptive Encryption and IoT Apparatus [google patents]
    Hanjun Kim, Bongjun Kim, Jaeho Lee, Seonyeong Heo, Shinnung Jeong, and Yongwoo Lee
    KR Patent Number 10-2508448-0000, March 2023.

    Scheduling Apparatus and Method based on Data Sharing between Multiple Rules in IoT Environment [google patents]
    Hanjun Kim, Seungbin Song, Bongjun Kim, and Seonyeong Heo
    KR Patent Number 10-2382328-0000, March 2022.

    Write Control Method and Disk Controller for Automated Backup and Recovery [google patents]
    Hanjun Kim, Seonyeong Heo, Jong Kim, and Bongjun Kim
    KR Patent Number 10-21896070000, December 2020.

    Heterogeneous Distributed Shared Memory For IoT Devices [google patents]
    Bongjun Kim, Jong Kim, Soyeon Park, Hanjun Kim, Seonyeong Heo, and Gyeongmin Lee
    KR Patent Number 10-18579070000, May 2018.

Services

  • Journal Reviewer, The Journal of Supercomputing (3 papers), 2024

  • Journal Reviewer, Cluster Computing, 2024

  • Journal Reviewer, IEEE Transactions on Cloud Computing (TCC), 2021

Teaching

  • Lecturer, LLVM Tutorial on Program Analysis & Optimization, LIG Nex1, Feburary 2018

  • Teaching Assistant, CSED 423: Compiler Design, POSTECH, Spring 2017

  • Teaching Assistant, CSED 312: Operating System, POSTECH, Fall 2017