발행물

전체 논문

22

11

Enabling hard constraints in differentiable neural network and accelerator co-exploration
이진호, 최강현, 이혜윤, 박노성, 홍덕기, 김영석, 유준상
Design Automation Conference, 202207

12

It’s All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher
이진호, 최강현, 이혜윤, 김영석, 박노성, 홍덕기, 유준상
Conference on Computer Vision and Pattern Recognition, 202207

13

GCoM: A Detailed GPU Core Model for Accurate Analytical Modeling of Modern GPUs
이진호, 이정후, 김영석, 이수현, 하연안, 장한휘, 우진영
International Symposium on Computer Architecture, 202206

14

SALoBa: Maximizing Data Locality and Workload Balance for Fast Sequence Alignment on GPUs
이진호, 박성연, 김하진, Tanveer Ahmad, Nauman Ahmed, Zaid Al-Ars, H Peter Hofstee, 김영석
IEEE International Parallel and Distributed Processing Symposium, 202205

15

DANCE: Differentiable Accelerator/Network Co-Exploration
Choi, K., Hong, D., Yoon, H., Yu, J., 김영석, 이진호
Proceedings - Design Automation Conference, 202112

16

Dataflow Mirroring: Architectural Support for Highly Efficient Fine-Grained Spatial Multitasking on Systolic-Array NPUs
이정후, 최진우, 김재연, 이진호, 김영석
Proceedings - Design Automation Conference, 202111

17

Making a Better Use of Caches for GCN Accelerators with Feature Slicing and Automatic Tile Morphing
유민기, 송재용, 이정후, 김남형, 김영석, 이진호
IEEE COMPUTER ARCHITECTURE LETTERS, 202107

18

GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descent
Kim, H., Park, H., Kim, T., Cho, K., Lee, E., Ryu, S., Lee, H.-J., Choi, K., 이진호
Proceedings - International Symposium on High-Performance Computer Architecture, 202104

19

An Efficient High-Throughput LZ77-Based Decompressor in Reconfigurable Logic
Jian Fang, Jianyu Chen, 이진호, Zaid Al-Ars, Peter Hofstee
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 202009

20

FlexReduce: Flexible all-reduce for distributed deep learning on asymmetric network topology
이진호, Hwang, I., Shah, S., Cho, M.
Proceedings - Design Automation Conference, 202007