Quantitative Analysis and Performance Optimization of Graph Neural Networks on Multi-core CPUs

Graph Neural Networks (GNNs) are becoming increasingly popular in graph data processing due to their excellent performance in feature extraction on graph datasets. Compared to GPUs, CPUs are more widely accessible and serve as a practical platform for GNN inference. However, achieving efficient GNN execution on CPUs remains a challenge. We first comprehensively evaluate and quantitatively analyze the performance of GNN inference on multi-core CPUs using the state-of-the-art frameworks, identifying four key performance bottlenecks: inefficient sparse computation, poor data locality, workload imbalance, and inefficient General Matrix Multiplication (GEMM). To tackle these issues, we introduce a set of joint optimizations. Specifically, for the aggregation phase, we propose three optimizations: a register padding and tiling Graph Sparse-dense Matrix Multiplication (GSpMM) algorithm that leverages the computation capability of long vector processing units on modern multi-core CPUs, a destination node-oriented indexes reorganization to enhance data locality, and a boundary buffer-based method to balance the workloads. Additionally, for the update phase, we develop an efficient bias fusion GEMM algorithm, tailored for the irregular matrices. We evaluate the proposed optimizations extensively with three popular GNN models on three typical multi-core CPU platforms. Experimental results on Intel, AMD, and ARM platforms show that our optimizations outperform the state-of-the-art GNN framework DGL by an average factor of 2.41 ×, 1.58 ×, and 2.04 × (up to 4.75 ×, 2.70 ×, and 3.55 ×), respectively. Compared to PyG, our implementations achieve an average speedup of 1.70 ×, 1.86 ×, and 2.44 ×, respectively.