About Jaeyong Park
I am a 3rd year integrated M.S/Ph.D course student at Korea University. I’m conducting research focusing on cost-efficient deep neural network (DNN) acceleration using tiered memory systems, neural processing unit (NPU) architectures, and memory systems for future datacenter servers.
Publications
ACM TOS
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
Accepted at ACM Transactions on Storage.
ICPP 2024
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 (ICPP 2024), Gotland, Sweden, 2024.
IEEE Access
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.
Research Interests
DNN accelerator
Memory system for energy-efficient DNN acceleration