Graph Neural Networks

SoftmaxPIM: An HBM-Based PIM Architecture for Accelerating GeMV--Softmax Execution Pipeline

Graph convolutional neural networks (GCNs) are representative graph neural network (GNN) models that can be used for analyzing and …

Taewoon Kang, Namhun Kim, Jihun Lee, Murali Annavaram, Gunjae Koo

SoftmaxPIM: An HBM-Based PIM Architecture for Accelerating GeMV--Softmax Execution Pipeline

BiKD: Bidirectional Kernel Decomposition for Large-Scale GCNs on GPU

Graph convolutional neural networks (GCNs) are representative graph neural network (GNN) models that can be used for analyzing and …

Inje Kim, Jihun Lee, Jonghyun Jeong, Geonwoo Choi, Myung Kuk Yoon, Yunho Oh, Gunjae Koo

BiKD: Bidirectional Kernel Decomposition for Large-Scale GCNs on GPU

Analyzing GCN Aggregation on GPU

Graph convolutional neural networks (GCNs) are emerging neural networks for graph structures that include large features associated …

Inje Kim, Jonghyun Jeong, Yunho Oh, Myung Kuk Yoon, Gunjae Koo