Platform Architect at Apple, specializing in Neural Engine hardware architecture.
Former Postdoctoral Researcher at Georgia Tech with Prof. Tushar Krishna.
Received Ph.D. in Computer Science from KAIST, advised by Prof. Jaehyuk Huh.
Research interests include computer architecture, secure systems, and Trusted Execution Environments, with recent work spanning distributed ML simulation and high-performance computing architecture.
Email : jpark3234 [at] gatech.edu
Joongun Park, Yongqin Wang, Huan Xu, Hanjiang Wu, Mengyuan Li, Tushar Krishna, "SCALE: Tackling Communication Bottlenecks in Confidential Multi-GPU ML", The International Symposium on High-Performance Computer Architecture (HPCA) 2026
Zishen Wan, Hanchen Yang, Jiayi Qian, Ritik Raj, Joongun Park, Chenyu Wang, Arijit Raychowdhury, Tushar Krishna, "Compositional AI Beyond LLMs: System Implications of Neuro-Symbolic-Probabilistic Architectures", ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2026
Seokjin Go, Joongun Park, Spandan More, Hanjiang Wu, Irene Wang, Aaron Jezghani, Tushar Krishna, Divya Mahajan, "Characterizing the Efficiency of Distributed Training: A Power, Performance, and Thermal Perspective", IEEE/ACM International Symposium on Microarchitecture (MICRO) 2025
Changhai Man*, Joongun Park*, Hanjiang Wu, Huan Xu, Srinivas Sridharan and Tushar Krishna, "Scalable Synthesis of LLM Benchmarks through Symbolic Tensor Graphs", Symposium on Networked Systems Design and Implementation (NSDI) Poster 2025. *Equally Contributed
Hanchen Yang, Zishen Wan, Ritik Raj, Joongun Park, Ziwei Li, Ananda Samajdar, Arijit Raychowdhury and Tushar Krishna, “An End-to-End FPGA Framework with Scalable Dataflow Architecture for Neuro-Symbolic AI”, Design Automation Conference (DAC) 2025
Hanjiang Wu, Huan Xu, Joongun Park, Jesmin Jahan Tithi, Fabio Checconi, Jordi Wolfson-Pou, Fabrizio Petrini and Tushar Krishna, "Enhancing Scalability and Performance in Influence Maximization with Optimized Parallel Processing", Workshop on Irregular Applications: Architectures and Algorithms (IA3) 2024, In conjunction with SC24
Taekyung Heo, Seunghyo Kang, Sanghyeon Lee, Soojin Hwang, Joongun Park, and Jaehyuk Huh, "Supporting Trusted Virtual Machines with Hardware-based Secure Remote Memory", International Symposium on Memory Management (ISMM), 2024
Joongun Park, Seunghyo Kang, Sanghyeon Lee, Taehoon Kim, Jongse Park, Youngjin Kwon and Jaehyuk Huh, “Hardware Hardening for Distributed Trusted Sandboxes”, Transactions on Architecture and Code Optimization (TACO), 2023
Joongun Park, Naegyeong Kang, Taehoon Kim, Youngjin Kwon, and Jaehyuk Huh, "Nested Enclave: Supporting Fine-grained Hierarchical Isolation with SGX", International Symposium on Computer Architecure (ISCA) 2020
Taehoon Kim, Joongun Park, Jaewook Woo, Seungheun Jeon, and Jaehyuk Huh, "ShieldStore: Shielded In-memory Key-value Storage with SGX", European Conference on Computer Systems (EuroSys) 2019
Taehoon Kim, Joongun Park, Jaewook Woo, Seungheun Jeon, and Jaehyuk Huh, "Secure In-memory Key-Value Storage with SGX", Symposium on Cloud Computing (SoCC) poster 2018
Secure CXL protocol for cloud application
According to the most recent white papers, CXL is not sufficiently prepared for secure inter-device communication
Currently working on identifying potential performance problems in the setup and alleviating the problems in a simulator
Leading this ongoing project
Secure disaggregated memory management with FPGA
Although recent improvement of RDMA-based memory disaggregation systems, their security has not been thoroughly investigated.
Proposed combined system with trusted hardware-based virtual machine and a new hardware engine for trusted memory disaggregation.
Participated as the co-author to discuss the idea, security analysis, and write the paper.
Published in ISMM 2024.
TEE technology for serverless computing
Serverless applications consist of multiple functions provided by mutually distrustful parties.
Proposed an extended TEE model which supports trusted serverless applications hardened by hardware.
Participated as the first author leading the project.
Published in TACO 2023.
Supporting Multi-level security in TEE
Monolithic design of intel SGX is hard to represent complex software structure securely.
Designed and emulate new instructions in SGX SDK/Driver to provide fine-grained hierarchical isolation within TEE
Participated as the first author leading the project
Published in ISCA 2020.
Secure key-value storage with Intel SGX
Limited enclave protected memory significantly slows down in-memory key-value store
Proposed a secure key-value store that has a hash-based index structure and provides fine-grained data protection
Participated as the second author to discuss the idea, implement the key-value store, and motivational experiments.
Published in SoCC 2018 as a poster and published in EuroSys 2019.
Ph.D Candidate in School of Computing at KAIST 2018 - 2023 (Dissertation approved)
M.S. in School of Computing at KAIST 2016 - 2018
B.S. in School of Computing at KAIST 2012 - 2016
Gyeongnam Science High School 2010 - 2012
Apple Inc. 2025 - present
Georgia Tech 2023 - 2025
Post Doctoral Researcher
Omnious Corp. 2016
Software developer/Startup early member
Database architecture, Web crawler
Internship at NHN 2015
Team leader
Private cloud with OpenStack, Video encoding acceleration
Internship at Smilegate 2015
Software developer
Large scale backend server for online game
Software Maestro membership (Ministry of Science, ICT and Future Planning ) 2014 - 2015
Software developer
Mobile Dating App, Video encoding server with Hadoop and FFMPEG
Language - C / C++ / Python / Script
Simulator - Intel SGX SDK, ZSim, GEM5
System - Linux (Ubuntu), Linux SGX driver, QEMU
Tools - Git, Docker
Other experience (beginner) - Xilinx FPGA, Intel Optane persistent memory
Teaching Assistant at KAIST
System Programming (CS230) 2018 Fall, 2020 Fall
Practice: Bit-wise operation, GDB, Assembly, and Proxy server
Operating System (CS330) 2016 Spring, 2019 Spring
Practice: Interrupt, Scheduling
Computer Organization (CS300) 2019 Fall, 2020 Spring
Practice: MIPS simulator
Embedded Computing (SEP 561) 2020 Spring
Soft processor using Altera’s tool
Teaching at North Chungcheongk Province Office of Education
Basic programming algorithm Nov 2014 - Feb 2015
Presidential Science Scholarship 2012 - 2016
ACM - ICPC ( NHN special prize ) 2013
Dean's List in School of Computing at KAIST 2014, Spring
Magna Cum Laude at KAIST 2016