arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.06608cs.DC
收藏

GNNAvisor:一种自适应高效的GPU加速系统GNN

GNNAdvisor: An Adaptive and Efficient Runtime System for GNN Acceleration on GPUs

Yuke Wang, Boyuan Feng, Gushu Li, Shuangchen Li, Lei Deng, Yuan Xie, Yufei Ding

摘要:

作为基于图的深度学习的新兴趋势,图神经网络(GNN)因其生成高质量节点特征向量(嵌入)的能力而脱颖而出。然而,现有的一刀切的GNN实现不足以赶上不断发展的GNN架构,不断增加的图形大小和不同的节点嵌入维度。为此,我们提出了\textbf{GNNAdvisor},一个自适应和高效的运行时系统,以加速GPU平台上的各种GNN工作负载。首先,GNNAvisor从GNN模型和输入图中探索并识别出几个与性能相关的特征,并将其用作GNN加速的新驱动力。其次,GNNAvisor实现了一种新颖高效的2D工作负载管理,专为GNN计算量身定制,以提高不同应用设置下的GPU利用率和性能。第三,GNNAvisor利用GPU的存储层次结构,根据GPU内存结构和GNN工作负载的特点,优雅地协调GNN的执行,从而实现加速。此外,为了实现自动运行时优化,GNNAvisor集成了一个轻量级的分析模型,用于有效的设计参数搜索。广泛的实验表明,GNNAvisor在各种数据集的主流GNN架构上的性能优于最先进的GNN计算框架,例如Deep Graph Library(平均速度快于$3.02\times$)和NeuGraph(快于$4.10\times$)。

英文摘要:

As the emerging trend of graph-based deep learning, Graph Neural Networks (GNNs) excel for their capability to generate high-quality node feature vectors (embeddings). However, the existing one-size-fits-all GNN implementations are insufficient to catch up with the evolving GNN architectures, the ever-increasing graph sizes, and the diverse node embedding dimensionalities. To this end, we propose \textbf{GNNAdvisor}, an adaptive and efficient runtime system to accelerate various GNN workloads on GPU platforms. First, GNNAdvisor explores and identifies several performance-relevant features from both the GNN model and the input graph, and uses them as a new driving force for GNN acceleration. Second, GNNAdvisor implements a novel and highly-efficient 2D workload management, tailored for GNN computation to improve GPU utilization and performance under different application settings. Third, GNNAdvisor capitalizes on the GPU memory hierarchy for acceleration by gracefully coordinating the execution of GNNs according to the characteristics of the GPU memory structure and GNN workloads. Furthermore, to enable automatic runtime optimization, GNNAdvisor incorporates a lightweight analytical model for an effective design parameter search. Extensive experiments show that GNNAdvisor outperforms the state-of-the-art GNN computing frameworks, such as Deep Graph Library ($3.02\times$ faster on average) and NeuGraph (up to $4.10\times$ faster), on mainstream GNN architectures across various datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑