4 papers · 1 filter
Multilayer Dataflow: Orchestrate Butterfly Sparsity to Accelerate Attention Computation
Haibin Wu, Wenming Li, Kai Yan +9
Recent neural networks (NNs) with self-attention exhibit competitiveness across different AI domains, but the essential attention mechanism brings massive computation and memory de…
Accelerating Mini-batch HGNN Training by Reducing CUDA Kernels
Meng Wu, Jingkai Qiu, Mingyu Yan +5
Heterogeneous graph neural networks (HGNNs) are essential for capturing the structure and semantic information in heterogeneous graphs. However, existing GPU-based solutions, such…
Survey on Characterizing and Understanding GNNs from a Computer Architecture Perspective
Meng Wu, Mingyu Yan, Wenming Li +3
Characterizing and understanding graph neural networks (GNNs) is essential for identifying performance bottlenecks and facilitating their deployment in parallel and distributed sys…
ADE-HGNN: Accelerating HGNNs through Attention Disparity Exploitation
Dengke Han, Meng Wu, Runzhen Xue +3
Heterogeneous Graph Neural Networks (HGNNs) have recently demonstrated great power in handling heterogeneous graph data, rendering them widely applied in many critical real-world d…