Myoungsoo Jung
정명수, 鄭溟隨

Associate Professor with Tenure
Korea Advanced Institute of Science and Technology

School of Electrical Engineering & Semiconductor System Engineering
Computer Division (Ranking) | Office: N1, 411 | Phone: 82-42-352-7455

RECENT RELEASE: Revolutionizing Memory Capacity and Processing over Arrays

We are excited to announce the release of our latest innovation, the 4th generation high-performance accelerator and memory arrays. With this breakthrough technology, we can now support the world's largest memory capacity while enabling near data processing capability. This development marks a significant milestone in our pursuit of more advanced and practical hardware and system research, specifically in the areas of AI and ML acceleration, cache coherent interconnect, and memory expansion. We welcome individuals who are passionate about pioneering cutting-edge research on computer architecture and operating systems (OS) to join us on this exciting journey.

NEWS : (2020~2023)

One of our collaboration work (NoC with CSNL) has been accepted from ISCA'23 TOP-TIER
Junhyeok will have an opening invited talk for CXL-based deep learning recommendation systems at HCM@HPCA 2023
Hanyeoreum' computational SSD for zero-overhead journaling has been accepted by IEEE CAL 2023 SCI
Junhyeok's work for open-source GNN acceleration framework has been accepted by IEEE IPDPS 2023 MAJOR
Miryeong's work for key-value storage with strong determinism contract has been accepted by ACM ToS 2023 SCI
Miryeong's work entitled by failure tolerant training over CXL has been accepted by IEEE Micro 2023 SCI
Donghyun's memory pooling with CXL work has been invited and accepted by IEEE Micro 2023 SCI
One of our collaboration work (NVMe security with NCSU) has been accepted from HPCA'23 TOP-TIER
We are invited to have the Opening Distinguished Lecture, introducing the future of CXL at RESDIS of SC'22 (Dallas). [ Program ]
Miryoeng, Seungjun, and Hyunkyu received Samsung's Best Paper Award 2022 (The Grand Prize). [ Video (Korean) ]
CAMEL is invited by and will demonstrate two CXL platforms at the CXL Forum 2022. [ Full program ]
Miryeong won the NVMW memorable paper award 2022![ Winner list ]
Our CXL 2.0-based Memory Expander and End-to-End System are introduced by the Next Platform’s headline. [ Read here ]
Donghyun and Seungkwan's GNN preprocessing acceleration work has been accepted by IEEE CAL SCI
Miryeong's in-storage processing for GNN acceleration work has been accepted by HotChips34
Three hot papers, including our CXL-SSD work, have been accepted by ACM HotStorage'22 MAJOR
Donghyun and Sangwoon's memory pooling with compute express link (CXL) has been accepted from USENIX ATC'22 TOP-TIER
Miryeong's and Seungjoon's KVS SSDs with strong latency determinism has been accepted from USENIX ATC'22 TOP-TIER
We uncover a white paper that deals with the world-first CXL-based memory disaggregation hardware/software IPs
Sangwoon and Miryeong's full persistent system work has been accepted from ISCA'22 TOP-TIER
Our machine learning framework using computational SSDs for GNN acceleration has been accepted from FAST'22 TOP-TIER
Our PMEM-based in-memory graph study has been accepted from ICCD'21 MAJOR
Jie's optical network-based new memory for GPU has been accepted from MICRO'21 TOP-TIER
Dr. Zhang will join EECS of Peking University as a tenure-track professor. Congrats!
CAMEL has been awarded with software computing fundamental technology research from Ministory of Science and ICT
Prof. Jung is awarded ICT creative fusion research from Samsung Science & Technology Foundation
Jie's Memory over Storage solution has been accepted from ISCA'21 TOP-TIER
Prof. Jung is awarded the best young researcher and granted with mid-scale research
Wonil joins Hanyang University as a tenure-track professor
Our SSD read-latency relaxation work has been accepted from ASPLOS'21 TOP-TIER
Our 3D NAND flash work work has been accepted from HPCA'21 TOP-TIER
We will have a Keynote speech for Samsung Open Source Conference 2020
Our OpenExpress has debuted at more than 50 major press reports!
Gyuyoung's a design of PRAM-based SSD work has been accepted from ICCAD'20 TOP-TIER
Jie's NVMe work has been accepted from IEEE CAL SCI
Jung's full hardware automation work has been accepted from USENIX ATC'20 TOP-TIER
Jie's GPU multi-processor with new flash has been accepted from ISCA'20 TOP-TIER
Our collaborative work regarding 3D NAND Flash has been accpeted from SIGMETRICS'20 TOP-TIER
One of collaborative storage work has been accepted from ISPASS'20 MAJOR
Miryeong, Donghyun, and Changrim's DC-Store work has been accepted from FAST'20 TOP-TIER
Jie&Miryeong's scalable parallell flash firmware research has been accepted from FAST'20 TOP-TIER
Wonil's conslidated flash cache work has been accepted by ASPLOS'20 TOP-TIER
Jie and Gyuyoung's Hardware Accleartion with New Memory work has been accepted by HPCA'20 TOP-TIER

Detailed information is here

CAMEL Life at a Glance

    RELEASE NEWS: The World-First CXL-Based Disaggregated Storage Class Memory Pool

    CAMEL is proud to announce the world's first CXL controllers and SCM-based disaggregated memory cards (DMC) are now secure. Our team is currently designing a cutting-edge disaggregated memory switch, boasting over 500 storage class memory modules (SCM) that can be seamlessly scaled up by simply adding multiple pooling switches. If you share our passion for exploring the frontiers of reliable, robust, safe, and intelligent computer and memory architecture, we warmly invite you to join us on this exhilarating quest.


    Please check the introduction page for new member candidates [ JOIN! ] ; Busy? Here is 2 Mins Introduction Video for answering the question, "카멜랩은 뭐하는 곳 인가요?" [ Intro (Korean) ] and "구체적으로 진행중인 연구는?" [ Research Intro (Korean) ]


    • Korea Advanced Institute of Science and Technology (KAIST), Associate Professor (Tenured), 2019~present
    • Samsung Advanced Institute of Technology, Advisory Committee Member, 2020~2021
    • Red Hat Software, Advisory Board, 2018~2019
    • SK Hynix, Advisory Committee Member, 2016~2020
    • Yonsei University, Assistant Professor (Tenure-track), 2015~2019
    • The University of Texas at Dallas, Assistant Professor (Tenure-track), 2013~2016
    • Lawrence Berkeley National Laboratory, Guest Scientist, Computational Research Division, Computer Architecture Group 2011~2015
    • Samsung Electronics, Memory Division, Researcher/Engineer, 2006~2009
    • Pennsylvania State University at Ph.D. Computer Science, 2013

    Dr. Jung's research enjoys support and collaboration from various institutions, including the Department of Energy (DOE), the National Energy Research Scientific Computing Center of Lawrence Berkeley National Laboratory (LBNL), U.S. National Science Foundation (NSF), the Ministry of Science, ICT and Future Planning, and the National Research Foundation of Korea. His lab alone has secured more than $13M (USD) in funding. As a Guest Research Scientist with Lawrence Berkeley National Laboratory, Dr. Jung models and simulates diverse memory technologies on scientific applications to design energy-efficient Exascale computing systems. In addition to his academic pursuits, Dr. Jung brings with him several years of industry experience and has garnered several industrial U.S. patents related to multi-channel SSDs. He has also authored approximately more than hundreds of papers on SSD, flash, and kernel-level file systems. Dr. Jung holds a Ph.D. in Computer Science from Pennsylvania State University, an M.S. in Computer Science from Georgia Institute of Technology, and an M.S. in Embedded System from Korea University in Seoul. Dr. Jung's research has earned him several accolades, including the NVMW memorable paper award and multiple nominations for best papers from NVMW and IEEE/ACM Internal Conference for High-Performance Computing, Networking, Storage, and Analysis. He has also been the recipient of the LBNL Award of Excellence, the Samsung Flash Software Group Best Engineer and Product Planning awards, and the Future Scientist and Competitive Professional Development awards from South Korean federal agencies.


    • Computer Architecture and Operating Systems
    • Flash, Solid State Drive (SSD), Storage Systems, and Non-Volatile Memory (NVM)
    • File Systems, Parallel Processing, and Heterogenous Computing
    • Performance Modeling, System Analysis, and Scheduling Algorithms

    Introduction of CAMEL Research Interest

    Dr. Jung is deeply interested in and loves memory and storage systems. He has dedicated his career to exploring the possibilities of advanced computer architecture, operating systems, firmware, middleware, and memory controller design, incorporating cutting-edge new memory technologies such as DRAM-based memory expansion, memory disaggregation, low-level NAND flash, Resistive RAM (RRAM), Magnetic RAM (STT-RAM), and Phase-change RAM (PRAM). These emerging new memory technologies have the potential to redefine computer architecture and parallelism computing. Dr. Jung's research aims to leverage this potential to enhance system performance, reduce energy consumption, and improve reliability. He is currently leading several diverse emerging new memory projects that include new interface design, near-data processing hardware architecting, and development of an open-source-based hardware controller and software stack for efficient, large-scale data management. Dr. Jung's team also leads emerging cache coherent interconnects (CCI), including compute express link (CXL) and cache coherent interconnect for accelerators (CCIX). These interconnects enable composable architecture with an extremely large-scale memory space, allowing for even greater possibilities in memory and storage systems. In addition to his work in emerging memory technologies, Dr. Jung's research extends to introducing different types of new memory technology to machine learning (ML), artificial intelligent (AI), big-data processing, and scientific applications such as out-of-core computing, in-situ analysis and message logging. He is passionate about enabling NVM-based burst buffer/micro-check pointing in diverse high-performance computing (HPC) and data-center system organizations, recognizing the significant potential for enhancing the performance of these systems.


    Venue/AreaPublication Information
    ISCA'23Jiho Kim, Myoungsoo Jung, John Kim, "Decoupled SSD Architecture through Network-based Flash Controllers" (acceptance rate: 21%)
    HPCA'23Md Hafizul Islam Chowdhuryy, Myoungsoo Jung, Fan Yao, and Amro Awad, "D-Shield: Enabling Processor-Side Encryption and Integrity Verification for Secure NVMe Drives" (acceptance rate: 25%)
    USENIX ATC'22Donghyun Gouk, Sangwon Lee, Miryeong Kwon, Myoungsoo Jung, "Direct Access, High-Performance Memory Disaggregation with DirectCXL" (acceptance rate: 16%)
    USENIX ATC'22Miryeong Kwon, Seungjun Lee, Hyunkyu Choi, Jooyoung Hwang, Myoungsoo Jung, "Vigil-KV: Hardware-Software Co-Design to Integrate Strong Latency Determinism into Log-Structured Merge Key-Value Stores" (acceptance rate: 16%)
    ISCA'22Sangwon Lee, Miryeong Kwon, Gyuyoung Park, Myoungsoo Jung, "LightPC: Hardware and Software Co-Design for Energy-Efficient Full System Persistence" (acceptance rate: 16%) [ KR News 1 (Chosun) ] [ KR News 2 (ZDNet) ] [ KR News 3 (Donga) ] [ KR News 4 (Hankyung) ] [ KR News 5 (Herald) ] [ US News 1 ] [ US News 2 ] [ US News 3 ] [ US News 4 ] [ KAIST News (English) ] [ Naver headline +37 news ] [ Written paper + Press ] [ YTN main news (Video) ]
    ISCA'22Ahmed Abulila, Izzat El Hajj, Myoungsoo Jung, Nam Sung Kim, "ASAP: Architecture Support for Asynchronous Persistence" (acceptance rate: 16%)
    FAST'22Miryeong Kwon, Donghyun Gouk, Sangwon Lee, Myoungsoo Jung, "Hardware/Software Co-Programmable Framework for Computational SSDs to Accelerate Deep Learning Service on Large-Scale Graphs" (acceptance rate: 21%) [ Naver headline + 26 ] [ Press/Newspaper ][ Preprint paper ] [ Demo video ] [ Presentation video ]
    MICRO'21Jie Zhang, Myoungsoo Jung, "Ohm-GPU: Integrating New Optical Network and Heterogeneous Memory into GPU Multi-Processors" (acceptance rate: 22%)
    ISCA'21Jie Zhang, Miryeong Kwon, Donghyun Gouk, Sungjoon Koh, Nam Sung Kim, Mahmut Kandemir, Myoungsoo Jung, "Revamping Storage Class Memory With Hardware Automated Memory-Over-Storage Solution" (acceptance rate: 18%)
    ASPLOS'21Chun-Yi Liu, Yunju Lee, Myoungsoo Jung, Mahmut Kandemir, Wonil Choi, "Prolonging 3D NAND SSD Lifetime via Read Latency Relaxation" (acceptance rate: 18%)
    HPCA'21Chun-Yi Liu, Yunju Lee, Wonil Choi, Myoungsoo Jung, Mahmut Kandemir, Chita Das, "GSSA: A Resource Allocation Scheme Customized for 3D NAND SSDs" (acceptance rate: 24%)
    USENIX ATC'20Myoungsoo Jung, "OpenExpress: Fully Hardware Automated Open Research Framework for Future Fast NVMe Devices" (acceptance rate: 18%) [ paper ] [ download ] [ US news1 (ZDNet) ] [ US news2 (Registers) ] [ US news3 (Tom's Hardware) ] [ US news4 ] [ US news5 ] [ US news6 ] [ KR news 45+ (Naver) ] [ KR major print press/newspaper 5+ ]
    ISCA'20Jie Zhang and Myoungsoo Jung, "ZnG: Architecting GPU Multi-Processors with New Flash for Scalable Data Analysis" (acceptance rate: 18%)
    SIGMETRICS'20Chun-Yi Liu, Jagadish Kotra, Myoungsoo Jung, Mahmut Taylan Kandemir, "Centaur: A Novel Architecture for Reliable, Low-Wear, High-Density 3D NAND Storage" (acceptance rate: 15%)
    FAST'20Miryeong Kwon, Donghyun Gouk, Changrim Lee, ByoungGeun Kim, Jooyoung Hwang, Myoungsoo Jung, "DC-Store: Eliminating Noisy Neighbor Containers using Deterministic I/O Performance and Resource Isolation" (acceptance rate: 16%)
    FAST'20Jie Zhang, Miryeong Kwon, Michael Swift, Myoungsoo Jung, "Scalable Parallel Flash Firmware for Many-core Architectures" (acceptance rate: 16%)
    ASPLOS'20Wonil Choi, Bhuvan Urgaonka, Mahmut Kandemir, Myoungsoo Jung, David Evans, "Fair Write Attribution and Allocation for Consolidated Flash Cache" (acceptance rate: 18%)
    HPCA'20Jie Zhang, Gyuyoung Park, David Donofrio, John Shalf, Myoungsoo Jung , "DRAM-less: Hardware Acceleration of Data Processing with New Memory" (acceptance rate: 19%)
    DAC'19Jie Zhang, Miryeong Kwon, Hyojong Kim, Hyesoon Kim, Myoungsoo Jung, "FlashGPU: Placing New Flash Next to GPU Cores" (acceptance rate: 24%)
    DAC'19Choungki Song, Woo Young Cho, Jian Huang, Myoungsoo Jung, Nam Sung Kim, "LL-PCM: Low-Latency Phase Change Memory Architecture" (acceptance rate: 24%)
    HPCA'19Jie Zhang, Myoungsoo Jung, Mahmut Kandemir, "FUSE: Fusing STT-MRAM into GPUs to Alleviate Off-Chip Memory Access Overheads" (acceptance rate: 19%)
    ASPLOS'19Chun-Yi Liu, Jagadish B. Kotra, Myoungsoo Jung, Mahmut Kandemir, Chita R. Das, "SOML Read: Rethinking the Read Operation Granularity of 3D NAND SSDs" (acceptance rate: 21%)
    SIGMETRICS'19Xulong Tang, Mahmut Kandemir, Hui Zhao , Myoungsoo Jung, Mustafa Karakoy, "Computing with Near Data" (acceptance rate: 8%)
    OSDI'18Jie Zhang, Miryeong Kwon, Donghyun Gouk, Changlim Lee, Mohammad Alian, Myoungjun Chun, Mahmut Kandemir, Nam Sung Kim, Jihong Kim, Myoungsoo Jung, "FlashShare: Punching Through Server Storage Stack from Kernel to Firmware for Ultra-Low Latency SSDs" (acceptance rate: 17%)
    MICRO'18Donghyun Gouk, Miryeong Kwon, Jie Zhang, Sungjoon Koh, Wonil Choi, Nam Sung Kim, Mahmut Kandemir, Myoungsoo Jung, "Amber: Enabling Precise Full-System Simulation with Detailed Modeling of All SSD Resources" (acceptance rate: 21%)
    MICRO'18Wonil Choi, Myoungsoo Jung, Mahmut Kandemir, "Invalid Data-Aware Coding to Enhance the Read Performance of High-Density Flash Memories" (acceptance rate: 21%)
    PLDI'18Orhan Kislal, Jagadish Kotra, Xulong Tang, Mahmut Kandemir, Myoungsoo Jung, "Enhancing Computation-to-Core Assignment with Physical Location Information" (acceptance rate: 21%)
    EUROSYS'18Jie Zhang, Myoungsoo Jung, "FlashAbacus: A Self-governing Flash-based Accelerator for Low-power Systems" (acceptance rate: 16%)
    FAST'18Chun-yi Liu, Jagadish Kotra, Myoungsoo Jung, Mahmut Kandemir, "PEN: Design and Evaluation of Partial-Erase for 3D NAND-Based High Density SSDs" (acceptance rate: 16%)
    SIGMETRICS'17Wonil Choi, Mohammad Arjomand, Myoungsoo Jung, Mahmut Kandemir, "Exploiting Data Longevity for Enhancing the Lifetime of Flash-based Storage Class Memory" [ paper ] (acceptance rate: 13%)
    ASPLOS'17Nima Elyasi, Mohammad Arjomand, Anand Sivasubramaniam, Mahmut Kandemir, Chita Das, Myoungsoo Jung, "Exploiting Intra-Request Slack to Improve SSD Performance" [ paper ] (acceptance rate: 17%)
    SC'16Narges Shahidi, Mohammad Arjomand, Myoungsoo Jung, Mahmut Kandemir, Chita Das, Anand Sivasubramaniam, "Exploring the Potentials of Parallel Garbage Collection in SSDs for Enterprise Storage Systems" [ paper ] (acceptance rate: 18%)
    HPCA'16Hao Wang, Jie Zhang, Gieseo Park, Sharmila Shridhar, Myoungsoo Jung, Nam Sung Kim, "DUANG: Fast and Lightweight Page Migration in Asymmetric Memory Systems" (acceptance rate: 22%) [ paper ] [ slides ]
    PACT'15           Jie Zhang, David Donofrio, John Shalf, Mahmut Kandemir and Myoungsoo Jung, “NVMMU: A Non-Volatile Memory Management Unit for Heterogeneous GPU-SSD Architectures", (acceptance rate: 21%) [ paper ] [ slides ]
    ISCA'14Myoungsoo Jung, Wonil Choi, Shekhar Srikantaiah, Joonhyuk Yoo, Mahmut Kandemir, "HIOS: A Host Interface I/O Scheduler for Solid State Disks" (acceptance rate: 17%) [ ieee ]
    HPCA'14Myoungsoo Jung, Mahmut Kandemir, "Sprinkler: Maximizing Resource Utilization in Many-Chip Solid State Disks" (acceptance rate: 25%) [ paper ] [ slides ]
    ASPLOS'14Myoungsoo Jung, Wonil Choi, John Shalf, Mahmut Kandemir, "Triple-A: A Non-SSD Based Autonomic All-Flash Array for Scalable High Performance Computing Storage Systems" (acceptance rate: 22%) [ paper ] [ slides ]
    SIGMETRICS'13Myoungsoo Jung, Mahmut Kandemir, "Revisiting Widely-held Expectations of SSD and Rethinking Implications for Systems" (acceptance rate: 13%) [ paper ] [ slides ]
    SC'13Myoungsoo Jung, Ellis Wilson, Wonil Choi, John Shalf, Metin Aktulga, Chao Yang, Erik Saule, Umit V. Catalyurek, Mahmut Kandemir, "Exploring the Future of Out-Of-Core Computing with Compute-Local Non-Volatile Memory" (acceptance rate: 20%) [ paper ] [ slides ]
    ISCA'12              Myoungsoo Jung, Ellis Herbert Wilson III, Mahmut Kandemir, “Physically Addressed Queueing (PAQ): Improving Parallelism in Solid State Disks" (acceptance rate: 17%) [ paper ]

    The full paper list is here


    • SimpleSSD -- Open-Source Licenced Educational SSD Simulatior for High-Performance Storage and Full-System Evaluations
    • OpenExpress -- Fully Hardware Automated Open Research Framework for Future Fast NVMe Devices
    • OpenNVM -- An Open-Sourced FPGA-based NVM Controller for Low Level Memory Characterization
    • Open Storage Trace -- Storage Traces Extracted CAMEL owned Mini-Supercomputing, All-Flash Array, and Parallel Systems
    • NANDFlashSim -- A cycle-accurate and hardware-validated NAND flash simulation model

    The full list of our tools is here


    • The Memorable Paper Award Winner, HolisticGNN: Geometric Deep Learning Engines for Computational SSDs, NVMW, 2022
    • Samsung Best Paper Award Winner (Grand Prize), Hardware-Software Co-Design to Integrate Strong Latency Determinism into Log-Structured Merge Key-Value Stores, Samsung Electronics, 2022
    • Award of Excellence, The Best Lecturer (Undergraduate Operating System), KAIST, 2021
    • Distinguished Program Committee Members, USENIX 13th Workshop on Hot Topics in Storage and File Systems (HotStorage), 2021
    • Award of Excellence, Engineering School Technology Innovation Award, KAIST, 2020
    • Award of Excellence, RNN-based Machine Learning Methods in an SSD for Efficient Data Reduction and Compression, SK Semiconductor Innovation, 2018
    • Award of Excellence, Introducing a Hybrid Non-Volatile Memory Systems for High-Performance GPGPU-based Graph Processing, SK Semiconductor Innovation, 2018
    • U.S. LBNL/DOE, Design and Implementation of FPGA-based Non-Volatile Memory Controllers, DE-AC02-05CH 11231, 2017.
    • National Research Foundation, 5 Years Young Researcher Career Program, R1C1B2015312, 2016 (Single PI).
    • U.S. National Science Foundation, CNS Core Programs Award, CNS-1422923, 2014 (Single PI).
    • U.S. Department of Energy and Lawrence Berkeley National Laboratory, CoDEx Award, DE-AC02-05CH1123, 2014.
    • Award of Excellence, Lawrence Berkeley National Laboratory, Computer Sciences Summer Student Program, 2012.

    The full award list is here


    • Invited Speaker, "What is CXL, Why Does It Matter, and Where Are We?", CXL Industry Symposium (Intel, AMD, Panmnesia, Samsung, SK-Hynix Consortium), 2023
    • Keynote, Process-in-Memory and AI-semiconductor Strategic Technology Symposium 2022, IITP, Ministry of Science/Industry
    • Distinguished Lecture, " Putting Memory and Computing in a Single Pool over Compute Express Link (CXL)", RESDIS held together with The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC'22),
    • Invited Speaker, "Memory Expansion over Cache Coherent Interconnect (CXL)", LX Semiconductor, 2022
    • Invited Speaker, "Future Hardware Acceleration with CXL", Fuiosa AI, 2022
    • Invited Speaker, "High-Performance Memory Expansion and Scalable CXL Network", Samsung Electronics, 2022
    • Invited Program Speaker, "CXL-SSD: Expanding PCIe Storage as Working Memory over CXL", CXL Forum at Flash Memory Summit, 2022
    • Invited Program Speaker, "CXL 2.0-based End-to-end System for High-Performance Memory Disaggregation", CXL Forum at Flash Memory Summit, 2022
    • Featured Lecture, "The Future of CXL Interconnect Technologies", SK-Hynix C-level Memory Summit, 2022
    • Invited Program Speaker, "Is Memory Becoming Indistinguishable from Storage?", ISC, 2021
    • Keynote Speech, " System Platform Revolution over Open-licensed Hardware", Samsung Open Source Conference, 2020
    • Invitation Talk, "NVM for HPC: from Ultra-Fast Storage to Compute Accelerator to Checkpoint-Free Persistent CPUs", Samsung Advanced Institute of Technology, 2020
    • Invitation Talk, "Exploring Full Design Spaces for Microscale Performance Storage", ETRI, 2020
    • Invited Program Speaker, " Is Memory Becoming Indistinguishable from Storage?", Lawrence Berkeley National Laboratory (LBNL)/ISC, 2020


    The full service list is here