발행물

전체 논문

22

1

Enabling Fine-Grained Spatial Multitasking on Systolic-Array NPUs Using Dataflow Mirroring
이진호, Choi Jinwoo, Ha Yeonan, Lee Jounghoo, Lee Sangsu, Jang Hanhwi, Kim Youngsok
IEEE TRANSACTIONS ON COMPUTERS, 202312

2

Fast Adversarial Training with Dynamic Batch-level Attack Control
이진호, 최강현, 송재용, 이혜윤, 정재원, 장홍선, 박노성
Design Automation Conference, 202307

3

Design and Analysis of a Processing-in-DIMM Join Algorithm: A Case Study with UPMEM DIMMs
이진호, 박성연, 이수현, 김한준, 김영석, 최진우, 이정후, 임채민
International Conference on Management of Data, 202306

4

Pipe-BD: Pipelined Parallel Blockwise Distillation
이진호, 송재용, 정재원, 장홍선, 김영석, 유준상
Design Automation and Test in Europe Conference, 202304

5

SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators
이진호, 송재용, 유민기, 김남형, 김영석
IEEE International Symposium on High-Performance Computer Architecture, 202302

6

Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression
이진호, 송재용, 정재원, 장홍선, 김영석, 김형진
International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS, 202301

7

Decoupling Schedule, Topology Layout, and Algorithm to Easily Enlarge the Tuning Space of GPU Graph Processing
이진호, 정신녕, 이용우, 이재호, 최희림, 송승빈, 김한준, 김영석
International Conference on Parallel Architectures and Compilation Techniques, 202210

8

Slice-and-Forge: Making Better Use of Caches for Graph Convolutional Network Accelerators
이진호, 송재용, 이혜윤, 유민기, 김영석, 이정후, 김남형
International Conference on Parallel Architectures and Compilation Techniques, 202210

9

GuardiaNN: Fast and Secure On-Device Inference in TrustZone Using Embedded SRAM and Cryptographic Hardware
이진호, 최진우, 임채민, 김재연, 김영석, 송도경, 이수현
ACM/IFIP/USENIX International Middleware Conference, 202210

10

ComPreEND: Computation Pruning through Predictive Early Negative Detection for ReLU in a Deep Neural Network Accelerator
이진호, 김남형, 이동우, 강성범, 박한민, 최기영
IEEE TRANSACTIONS ON COMPUTERS, 202207