Accelerating Sparse Graph Neural Networks with Tensor Core Optimization

TL;DR

This paper introduces FTC-GNN, a novel GPU acceleration framework that effectively utilizes CUDA and Tensor Cores for sparse graph neural network computations, significantly improving speed and efficiency.

Contribution

FTC-GNN presents a collaborative design and sparse-to-dense transformation strategy to optimize GPU resource utilization for GNNs, addressing prior inefficiencies.

Findings

Achieves up to 7.10x speedup over existing frameworks for GCN.

Effectively accelerates AGNN with up to 5.32x speedup.

Demonstrates improved GPU resource utilization and computational efficiency.

Abstract

Graph neural networks (GNNs) have seen extensive application in domains such as social networks, bioinformatics, and recommendation systems. However, the irregularity and sparsity of graph data challenge traditional computing methods, which are insufficient to meet the performance demands of GNNs. Recent research has explored parallel acceleration using CUDA Cores and Tensor Cores, but significant challenges persist: (1) kernel fusion leads to false high utilization, failing to treat CUDA and Tensor Cores as independent resources, and (2) heterogeneous cores have distinct computation preferences, causing inefficiencies. To address these issues, this paper proposes FTC-GNN, a novel acceleration framework that efficiently utilizes CUDA and Tensor Cores for GNN computation. FTC-GNN introduces (1) a collaborative design that enables the parallel utilization of CUDA and Tensor Cores and (2) a sparse-to-dense transformation strategy that assigns dense matrix operations to Tensor Cores while leveraging CUDA Cores for data management and sparse edge processing. This design optimizes GPU resource utilization and improves computational efficiency. Experimental results demonstrate the effectiveness of FTC-GNN using GCN and AGNN models across various datasets. For GCN, FTC-GNN achieves speedups of 4.90x, 7.10x, and 1.17x compared to DGL, PyG, and TC-GNN, respectively. For AGNN, it achieves speedups of 5.32x, 2.92x, and 1.02x, establishing its superiority in accelerating GNN computations.