PIMPAL: Accelerating LLM Inference on Edge Devices via In-DRAM Arithmetic Lookup
Yoonho Jang, Hyeongjun Cho, Yesin Ryu, Jungrae Kim, and Seokin Hong
Design Automation Conference (DAC), acceptance rate = 23%, June. 2025
RowHammer 공격과 방어: 기술적 진화와 도전 과제
Yesin Ryu, Jungrae Kim
Communications of the Korean Institute of Information Scientists and Engineers, Apr. 2025
컨볼루션 뉴럴 네트워크 실행 가속화를 위한 실시간 데이터 전처리 장치
Jungrae Kim, Seokin Hong, Taehee Han, Mingu Kang
KR(10-2763260), 2025.
C4ECC: Data Compression for Bandwidth Efficiency Under ECC Protection in GPUs
Sanghyun Park, Boyeol Choi, and Jungrae Kim
International Conference on Electronics, Information, and Communication (ICEIC), Jan. 2025
CacheCraft: Enhancing GPU Performance under Memory Protection through Reconstructed Caching
Soyoung Park, Hojung Namkoong, Boyeol Choi, Michael Sullivan, and Jungrae Kim
The IEEE/ACM International Symposium on Microarchitecture (MICRO), acceptance rate = 22.7%, Nov. 2024
Link: [Paper
]
[Slides(ppt)
]
동적 수리 메모리 디바이스
Jungrae Kim, Sangje Park
KR(#10-2716293), 2024.
LEAP: LLW RowHammer Mitigation System
Yoojin Kim, Yesin Ryu, and Jungrae Kim
The International SoC Conference (ISOCC), Aug. 2024
INC: In channel Crossing ECC for LPDDR Compression Attached Memory Module
Yoonyul Yoo and Jungrae Kim
The International SoC Conference (ISOCC), Aug. 2024
Evaluating the Impact of In-band ECC on GPU Performance
Soyoung Park and Jungrae Kim
The International SoC Conference (ISOCC), Aug. 2024
Native DRAM Cache: Re-architecting DRAM as a Large-Scale Cache for Data Centers
Yesin Ryu, Yoojin Kim, Giyong Jung, Jungho Ahn, and Jungrae Kim
The International Symposium on Computer Architecture (ISCA), acceptance rate = 19.6%, July, 2024
IEEE Micro Top Picks in Computer Architecture (Honorable Mention)
Link: [Paper
]
[Slides(ppt)
]
Agile-DRAM: Agile Trade-Offs in Memory Capacity, Latency, and Energy for Data Centers
Synergizing CXL With Unified Memory for Scalable GPU Memory Expansion
Junseung Lee and Jungrae Kim
The International Conference on Electronics, Information, and Communication (ICEIC), Jan. 2024
CPR: Correlation-based Page Remapping
Hojung Namkoong, and Jungrae Kim
The International SoC Conference (ISOCC), Oct. 2023
UVMMU: Hardware-Offloaded Page Migration for Heterogeneous Computing
Jihun Park, Donghun Jeong, and Jungrae Kim
The Design, Automation and Test in Europe Conference (DATE), acceptance rate = 25%, Apr. 2023
Link: [Paper
]
[Slides(pptx)
]
Demand MemCpy: Overlapping of Computation and Data Transfer for Heterogeneous Computing
Multi-Prediction Compression: An Efficient and Scalable Memory Compression Framework for GP-GPU
ERUCA: Efficient DRAM Resource Utilization and Resource Conflict Avoidance for Memory System Parallelism
Bit-Plane Compression: Transforming Data for Better Compression in Many-core Architectures
Electronic Device Controller for Improving Performance of Electronic Device
Jungrae Kim
KR/JP/CN/US(#8,625,439), 2014.
Method and System Controlling Page Open Time for Memory Device
Jungrae Kim, and Wooil Kim
KR/EU/US(#8,688,942) / 2014.
Device and Method for Testing Semiconductor Device
Jungrae Kim
KR/US(#8,621,292) / 2013.
Method of Correcting a Duty Ratio of a Data Strobe Signal
KyongMook Lim, Jinsu Jung, Kwanho Kim, Jungrae Kim, Taesun Kim
KR/US(#US20130219208A1), 2012.
Hybrid Image Data Processing System and Method
Jungrae Kim, Jinpyo Park, Jaehong Park, Youngjun Kwon
KR/TW/CN/US(#8,229,235), 2012.
Data Processing Apparatus for Compressing Data According to Improved Variable Length Coding Method
Jungrae Kim, Jinpyo Park, Jaehong Park, Youngjun Kwon
KR(#10-20,070,075,100), 2006.
Lazy Register Reconcile for Local Register Allocation
Jungrae Kim
MS Thesis / Seoul National University, Aug. 2003.