Journal

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, 2025

Conference Major

Kubism: Disassembling and Reassembling K-Means Clustering for Mobile Heterogeneous Platforms

Seondeok Kim*, Sangun Choi*, Jaebeom Jeon, Junsu Kim, Minseong Gil, Jaehyeok Ryu, and Yunho Oh (Co-First Author)

26th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES 2025)

Journal

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 of Storage, 2025

Journal

TLP Balancer: Predictive Thread Allocation for Multi-Tenant Inference in Embedded GPUs

Minseong Gil*, Jaebeom Jeon, Junsu Kim, Sangun Choi, Gunjae Koo, Myung Kuk Yoon, and Yunho Oh

IEEE Embedded Systems Letters, 2024

Journal

SAVector: Vectored Systolic Arrays

Sangun Choi*, Seongjun Park, Jaeyong Park, Jongmin Kim, Gunjae Koo, Seokin Hong, Myung Kuk Yoon, and Yunho Oh

IEEE Access, 2024

Ongoing Submitted

Energy-Efficient On-Chip Memory Management for Embedding Vector Operation

First Author

In submission to an international conference

Ongoing Submitted

Unified Address Translation for DNN Accelerators

Co-Author

In submission to an international conference

Ongoing Submitted

A Behavioral Analysis of Memory Management Software in CXL Memory Systems

Co-Author

In submission to an international conference

Ongoing

A DNN Accelerator Supporting Arbitrary Numeric Formats

Co-Author

In preparation for submission to an international conference