Jaeyong Park

Computer Architecture & System Software Researcher

About Jaeyong Park

I am a 4th year integrated M.S/Ph.D course student at Korea University. My research focuses on cost-efficient DNN acceleration using tiered memory systems, NPU and GPU architectures, and memory systems for future data center servers.

Publications

IEEE CAL

Major journal in computer architecture

EONSim: An NPU Simulator for On-Chip Memory and Embedding Vector Operations
Sangun Choi, Jongmin Kim, Jaeyong Park, and Yunho Oh
IEEE Computer Architecture Letters, Vol. 25, pp. 73-76, 2026.

IEEE CAL

Major journal in computer architecture

MOST: Memory Oversubscription-aware Scheduling for Tensor Migration on GPU Unified Storage
Junsu Kim, Jaebeom Jeon, Jaeyong Park, Sangun Choi, Minseong Gil, Seokin Hong, Gunjae Koo, Myung Kuk Yoon, and Yunho Oh
IEEE Computer Architecture Letters, pp. 1-4, 2025.

ACM TOS

Major journal in computer architecture

TM-Training: An Energy-Efficient Tiered Memory System for Deep Learning Training in NPUs
Jaeyong Park, Sangun Choi, Jongmin Kim, Gunjae Koo, Myung Kuk Yoon, and Yunho Oh
ACM Transactions on Storage, Article No. 32, pp. 1-26, 2025.

IEEE Access

SCIE

SAVector: Vectored Systolic Arrays
Sangun Choi, Seongjun Park, Jaeyong Park, Jongmin Kim, Gunjae Koo, Seokin Hong, Myung Kuk Yoon, and Yunho Oh
IEEE Access, Vol. 12, pp. 44446-44461, 2024.

ICPP

Major conference in computer architecture

VitBit: Enhancing Embedded GPU Performance for AI Workloads through Register Operand Packing
Jaebeom Jeon, Junsu Kim, Jaeyong Park, Gunjae Koo, Myung Kuk Yoon, and Yunho Oh
The 53rd International Conference on Parallel Processing, Gotland, Sweden, 2024.

Skills

Language

  • Korean: Native
  • English: Professional

Programming Languages

  • C, C++
  • Verilog HDL
  • Python

Research Interests

DNN accelerator
Memory system for energy-efficient DNN acceleration