Cambricon-DG: An Accelerator for Redundant-Free Dynamic Graph Neural Networks Based on Nonlinear Isolation

Dynamic Graph Neural Networks (DGNNs) have demonstrated significant potential in handling temporal graph-structured data. Typical DGNNs combine GNNs to process the structural information of graph and RNNs to capture the dynamic temporal information of graphs. However, current GNN accelerators process DGNNs by treating graph snapshots as static entities, leading to substantial redundant computations and memory accesses. While some DGNN accelerators have attempted to mitigate this redundancy, they face the challenge of maintaining accuracy for incremental processing due to the nonlinear activation function in GNNs. To address these issues, we propose a novel nonlinear isolation mechanism for incremental processing of DGNNs, which eliminates all redundant operations without accuracy loss. Additionally, we introduce a vertex-wise computation scheme for RNNs to minimize redundancy and reduce off-chip memory access. To validate the effectiveness of the mechanism, we implemented software optimizations on GPUs, achieving an $8.53 \times$ performance improvement over full-graph computation schemes. To address the inefficiency of graph topology operations on GPUs, we propose the Cambricon-DG accelerator, which features a dedicated hardware pipeline, an efficient topology management engine for graph traversal and topology sorting, and a hybrid computation engine that supports both GNN and RNN computations, thus improving hardware utilization. We evaluate Cambricon-DG on seven real-world dynamic graph datasets using five representative DGNN models. The results show that Cambricon-DG achieves an average speedup of $49.73 \times, 12.15 \times$, and $7.03 \times$, and an average energy saving of $41.31 \times, 9.47 \times$, and $5.23 \times$ over the state-of-the-art static/dynamic GNN accelerators I-GCN, RACE, and DeltaGNN, respectively.