Sangun Choi

Latest

• TM-Training: An Energy-Efficient Tiered Memory System for Deep Learning Training in NPUs
• HALO: Hybrid Systolic Arrays via Logical Partitioning for Acceleration of Complex-Valued Neural Networks
• MOST: Memory Oversubscription-Aware Scheduling for Tensor Migration on GPU Unified Storage
• TLP Balancer: Predictive Thread Allocation for Multitenant Inference in Embedded GPUs
• SAVector: Vectored Systolic Arrays