arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.08709cs.AR
收藏

ZIPPER:利用瓦片级和运算符级的并行性实现通用和可扩展的图神经网络加速

ZIPPER: Exploiting Tile- and Operator-level Parallelism for General and Scalable Graph Neural Network Acceleration

Zhihui Zhang, Jingwen Leng, Shuwen Lu, Youshan Miao, Yijia Diao, Minyi Guo, Chao Li, Yuhao Zhu

摘要:

图神经网络(GNN)在包括分子科学、推荐和运输在内的各种领域显示出显着的性能改善后开始获得动力。将GNN的这种性能改进转化为实际应用依赖于有效和高效的执行,特别是对于推理。然而,如果同时考虑性能和能效,无论是CPU还是GPU都无法满足这些需求。这是因为加速GNN是具有挑战性的,因为它们过度使用内存和任意交错的不同操作。此外,高级GNN编程模型和高效硬件之间的语义鸿沟使得通用领域GNN的加速变得困难。为了应对这一挑战,我们提出了Zipper,这是一个高效而通用的GNN加速系统。Zipper的关键包括一个图形原生的中间表示(IR)和相关的编译器。通过捕获GNN原语操作并使用GNN IR表示,Zipper能够将GNN语义融入硬件结构以实现高效执行。IR还支持特定于GNN的优化,包括稀疏图拼接和冗余操作消除。我们进一步提出了一个硬件架构设计,由不同的原始操作的专用块,以及一个运行时调度器来映射一个IR程序的硬件块。我们的评估显示,Zipper平均比Intel Xeon CPU实现了93.6倍的加速和147倍的能耗降低,比NVIDIA V100 GPU实现了1.56倍的加速和4.85倍的能耗降低。

英文摘要:

Graph neural networks (GNNs) start to gain momentum after showing significant performance improvement in a variety of domains including molecular science, recommendation, and transportation. Turning such performance improvement of GNNs into practical applications relies on effective and efficient execution, especially for inference. However, neither CPU nor GPU can meet these needs if considering both performance and energy efficiency. That's because accelerating GNNs is challenging due to their excessive memory usage and arbitrary interleaving of diverse operations. Besides, the semantics gap between the high-level GNN programming model and efficient hardware makes it difficult in accelerating general-domain GNNs. To address the challenge, we propose Zipper, an efficient yet general acceleration system for GNNs. The keys to Zipper include a graph-native intermediate representation (IR) and the associated compiler. By capturing GNN primitive operations and representing with GNN IR, Zipper is able to fit GNN semantics into hardware structure for efficient execution. The IR also enables GNN-specific optimizations including sparse graph tiling and redundant operation elimination. We further present an hardware architecture design consisting of dedicated blocks for different primitive operations, along with a run-time scheduler to map a IR program to the hardware blocks. Our evaluation shows that Zipper achieves 93.6x speedup and 147x energy reduction over Intel Xeon CPU, and 1.56x speedup and 4.85x energy reduction over NVIDIA V100 GPU on averages.

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。

↑