Layerweaver+: A QoS-Aware Layer-Wise DNN Scheduler for Multi-Tenant Neural Processing Units von OH, Young H., JIN, Yunho, HAM, Tae Jun, LEE, Jae W.

Volltext

Eager Memory Management for In-Memory Data Analytics von JANG, Hakbeom, BAE, Jonghyun, HAM, Tae Jun, LEE, Jae W.

Volltext

Erratum: Eager Memory Management for In-Memory Data Analytics [IEICE Transactions on Information and Systems Vol.E102.D (2019) , No.3 pp.632-636] von JANG, Hakbeom, BAE, Jonghyun, HAM, Tae Jun, LEE, Jae W.

Volltext

Disintegrated control for energy-efficient and heterogeneous memory systems von Tae Jun Ham, Chelepalli, B. K., Neng Xue, Lee, B. C.

Volltext

Architecting a Flash-Based Storage System for Low-Cost Inference of Extreme-Scale DNNs von Jin, Yunho, Kim, Shine, Ham, Tae Jun, Lee, Jae W.

Volltext

An LSM Tree Augmented with B+ Tree on Nonvolatile Memory von Kim, Donguk, Lee, Jongsung, Lim, Keun Soo, Heo, Jun, Ham, Tae Jun, Lee, Jae W.

Volltext

MaPHeA: A Framework for Lightweight Memory Hierarchy-aware Profile-guided Heap Allocation von Oh, Deok-Jae, Moon, Yaebin, Ham, Do Kyu, Ham, Tae Jun, Park, Yongjun, Lee, Jae W., Ahn, Jung Ho, Lee, Eojin

Volltext

Accelerating Genomic Data Analytics With Composable Hardware Acceleration Framework von Ham, Tae Jun, Lee, Yejin, Seo, Seong Hoon, Song, U Gyeong, Lee, Jae W., Bruns-Smith, David, Sweeney, Brendan, Asanovic, Krste, Oh, Young H., Wills, Lisa Wu

Volltext

SSDStreamer: Specializing I/O Stack for Large-Scale Machine Learning von Bae, Jonghyun, Jang, Hakbeom, Gong, Jeonghun, Jin, Wenjing, Kim, Shine, Jang, Jaeyoung, Ham, Tae Jun, Jeong, Jinkyu, Lee, Jae W.

Volltext

Efficient Data Supply for Parallel Heterogeneous Architectures von Ham, Tae Jun, Aragón, Juan L., Martonosi, Margaret

Volltext

Decoupling Data Supply from Computation for Latency-Tolerant Communication in Heterogeneous Architectures von Ham, Tae Jun, Aragón, Juan L., Martonosi, Margaret

Volltext

L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training von Bae, Jonghyun, Baek, Woohyeon, Ham, Tae Jun, Lee, Jae W.

Volltext

L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training von Bae, Jonghyun, Baek, Woohyeon, Ham, Tae Jun, Lee, Jae W

Volltext bestellen

PROCESSOR, METHOD OF OPERATING THE PROCESSOR, AND ELECTRONIC DEVICE INCLUDING THE SAME von Lee, Jae Wook, Lee, Seung Wook, Ham, Tae Jun, Won, Jaeyeon

Volltext bestellen

Mithril: Cooperative Row Hammer Protection on Commodity DRAM Leveraging Managed Refresh von Kim, Michael Jaemin, Park, Jaehyun, Park, Yeonhong, Doh, Wanju, Kim, Namhoon, Ham, Tae Jun, Lee, Jae W, Ahn, Jung Ho

Volltext bestellen

L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training von Bae, Jonghyun, Baek, Woohyeon, Ham, Tae Jun, Lee, Jae W

Volltext

METHOD FOR PROCESSING PAGE FAULT BY PROCESSOR von LEE, Gyu Sun, HAM, Tae Jun, LEE, Jae Wook, JEONG, Jin Kyu, JIN, Wenjing

Volltext bestellen

ACCELERATOR SYSTEM FOR TRAINING DEEP NEURAL NETWORK MODEL USING NAND FLASH MEMORY AND OPERATING METHOD THEREOF von Jin, Yunho, Bae, Jong Hyun, Sohn, Gin A, Ham, Tae Jun, Lee, Jae W

Volltext bestellen

Hardware accelerator performing search using inverted index structure and search system including the hardware accelerator von Lee, Jae Wook, Jang, Jaeyoung, Lee, Yejin, Heo, Jun, Ham, Tae Jun, Won, Jaeyeon

Volltext bestellen

APPARATUS AND METHOD WITH SCHEDULING von OH, Younghwan, JIN, Yunho, HAM, Tae Jun, LEE, Jae Wook

Volltext bestellen