PCGraph: Accelerating GNN Inference on Large Graphs via Partition Caching
Lizhi Zhang, Zhiquan Lai, Yu Hua Tang, Dongsheng Li, Feng Liu, Xiaochun Luo · 2021
Graph neural networks (GNNs) have been emerging as powerful learning tools for unstructured data and successfully applied to many graph-based application domains. Sampling-based GNN inference is commonly adopted in existing graph learning frameworks to handle large-scale graphs. However, this approach is restricted by the problems of redundant vertex embedding computation in GPU and inefficient loading of vertex features from CPU to GPU. In this paper, we propose PCGraph, a system that supports adaptive GNN inference and feature partition caching. PCGraph significantly reduces the vertex embedding computation time by adaptive GNN inference technology, which selects the optimal inference algorithm and minimizes vertex embedding computation. PCGraph also reduces the redundant data transfer between the CPU and GPU by partition the target vertices and caching their corresponding partitions in turn. We evaluate PCGraph against two state-of-the-art industrial GNN frameworks, i.e., PyG and DGL, on a diverse array of benchmarks. Experimental results show that PCGraph reduces up to 99% vertex embedding computation and 98.5% data loading time, and achieves up to 360× performance speedup over the state-of-the-art baselines.