Lab Seminar
Date , Category , Presenter , Title
23-02-24, GPU , Junhyeok Park , Access Pattern_Aware Cache Management for Improving Data Utilization in GPU PPT
23-02-17, Accelerator , Seongwook Kim , Rigid Deep Learning Accelerator Architectures with Sparsity Exploitation PPT
23-02-10, GPU , Sungbin Jang , Training Personalized Recommendation Systems from (GPU) Scratch Look.... PPT
23-02-03, Processing in Memory , Joseph Woo , Lacc: Exploiting lookup table-based fast and accurate vector multiplication in.... PPT
22-01-06, DNN , Seungtae Lee , Self-Supervised Learning PPT
22-12-23, Accelerator , Gwangeun Byeon , Energy-Efficient DNN Training Processors on Micro-AI Systems PPT
22-10-28, DNN , Seungtae Lee , LoRA: Low-Rank Adaptation of Large Language Models PPT
22-10-07, Non-volatile Memory , Yongho Lee , Rethinking DRAM’s page mode with STT-MRAM PPT
22-09-30, Memory Compression , Seongwook Kim , Application of Data Compression to Memory System PPT
22-09-23, SparseMatrixAccelerator , Gwangeun Byeon , Why Outer Product? PPT
22-09-16, GPU , Sungbin Jang , GPU Scheduling on the NVIDIA TX2: Hidden Details Revealed PPT
22-09-02, Virtual Memory , Osang Kwon , Enhancing and Exploiting Contiguity for Fast Memory Virtualization PPT
22-08-26, Virtual Memory , Junhyeok Park , Translation-Triggered Prefetching PPT
22-08-26, PIM , Joseph Woo , Neural Cache Bit-Serial In-Cache Acceleration of Deep Neural Networks PPT
22-08-19, Compression , Seongwook Kim , Compressing DMA Engine: Leveraging Activation Sparsity for Training Deep Neural Net.... PPT
22-08-19, GPU , Gwangeun Byeon , Tensor Core Advanced GPU architecture PPT
22-08-12, NPU , Yongjun Kim , Sparsity-Aware and Re-configurable NPU Architecture for Samsung Flagship Mobile SoC PPT
22-08-05, Memory System , Yongho Lee , Compute Express Link PPT
22-08-05, PIM , Osang Kwon , iMARS An In-Memory-Computing Architecture for Recommendation Systems PPT
22-07-01, Virtual Memory , Junhyeok Park , Interplay between Hardware Prefetcher and Page Eviction Policy in CPU-GPU Unified.... PPT
22-06-24, DNN , Jaeyoon Lee , Fast Lossless Neural Compression with Integer-Only Discrete Flows PPT
22-06-24, Memory Architecture , Seongwook Kim , Re-architecting the On-chip memory Sub-system of Machine-Learning Accelerator for.... PPT
22-06-17, DNN , Seungtae Lee , Attention is All You Need PPT
22-06-17, PIM , Joseph Woo , NNPIM A Processing In-Memory Architecture for Neural Network Acceleration PPT
22-04-08, Virtual Memory , Junhyeok Park , Improving GPU Multi-tenancy with Page Walk Stealing PPT
22-03-25, Non-volatile Memory , Yongho Lee , Don’t Open Row Rethinking Row Buffer Policy for Improving Performance of Non-Volatile.... PPT
22-03-18, Virtual Memory , Joseph Woo , The Virtual Block Interface: A Flexible Alternative to the Conventional Virtual Memory.... PPT
22-02-25, DNN , Osang Kwon , Deep learning based Recommendation Model PPT
22-02-18, NPU , Yongjun Kim , In-Datacenter Performance Analysis of a Tensor Processing Unit PPT
22-01-21, DNN , Seungtae Lee , Understanding the difficulty of training deep feedforward neural networks PPT
22-01-14, Accelerator , Gwangeun Byeon , Gamma:leveraging Gustavson’s algorithm to accelerate sparse matrix multiplication PPT
22-01-07, Non-volatile Memory , Yongho Lee , An Energy- and Performance-Aware DRAM Cache Architecture for Hybrid DRAM/PCM.... PPT
21-08-06, Accelerator , Gwangeun Byeon , Compensated-DNN: Energy Efficient Low-Precision Deep Neural Networks by.... PPT
21-07-30, Virtual Memroy , Osang Kwon , Dead Page and Dead Block Predictors Cleaning TLBs and Caches Together PPT
21-07-10, Non-volatile Memory , Yongho Lee , Revamping Storage Class Memory With Hardware Automated Memory-Over-Storage.... PPT