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

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

First Author

In preparation for submission to an international conference

Ongoing Submitted

Unified Address Translation for DNN Accelerators

Co-Author

In submission to an international conference

Ongoing Submitted

Accelerating K-Means Clustering in Mobile Platforms

Co-First 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 Submitted

Memory Oversubscription-Aware Scheduling for Tensor Migration on GPU Unified Storage

Co-Author

In submission to IEEE Computer Architecture Letters

Ongoing

A DNN Accelerator Supporting Arbitrary Numeric Formats

Co-Author

In preparation for submission to an international conference