Yuchen Gui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuchen Gui has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Huawen Liang
USTC, Hefei, China
1 shared publication - Letian Zhao
University of Science and Technology of China, Hefei, China
1 shared publication - Qizhe Wu
USTC, Hefei, China
1 shared publication - Xi Jin
Department of Physics, University of Science and Technology of China, Hefei, China
1 shared publication - Xiaotian Wang
University of Science and Technology of China Hefei China
1 shared publication
Latest Publications
- Open Access
- 2 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 187
Efficient Message Passing Architecture for GCN Training on HBM-based FPGAs with Orthogonal Topology On-Chip Networks
Graph Convolutional Networks (GCNs) are state-of-the-art deep learning models for representation learning on graphs. However, the efficient training of GCNs is hampered by constraints in memory capacity and bandwidth, compounded by the irregular data flow that results in communication bottlenecks. To address these challenges, we propose a message-passing architecture that leverages NUMA-based memory access properties and employs a parallel multicast routing algorithm based on a 4-D hypercube network within the accelerator for efficient message passing in graphs. Additionally, we have re-engineered the backpropagation algorithm specific to GCNs within our proposed accelerator. This redesign strategically mitigates the memory demands prevalent during the training phase and diminishes the computational overhead associated with the transposition of extensive matrices. Compared to the state-of-the-art HP-GNN architecture we achieved a performance improvement of 1.03×~1.81×.
- 2 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 187
Open AccessEfficient Message Passing Architecture for GCN Training on HBM-based FPGAs with Orthogonal Topology On-Chip Networks
Graph Convolutional Networks (GCNs) are state-of-the-art deep learning models for representation learning on graphs. However, the efficient training of GCNs is hampered by constraints in memory capacity and bandwidth, compounded by the irregular data flow that results in communication bottlenecks. To address these challenges, we propose a message-passing architecture that leverages NUMA-based memory access properties and employs a parallel multicast routing algorithm based on a 4-D hypercube network within the accelerator for efficient message passing in graphs. Additionally, we have re-engineered the backpropagation algorithm specific to GCNs within our proposed accelerator. This redesign strategically mitigates the memory demands prevalent during the training phase and diminishes the computational overhead associated with the transposition of extensive matrices. Compared to the state-of-the-art HP-GNN architecture we achieved a performance improvement of 1.03×~1.81×.