论文标题
HYGCN：混合体系结构的GCN加速器
HyGCN: A GCN Accelerator with Hybrid Architecture
论文作者
论文摘要
在这项工作中，我们首先表征了Intel Xeon CPU上GCN的混合执行模式。在表征的指导下，我们使用混合体系结构设计了GCN加速器HYGCN来有效执行GCN。具体来说，首先，我们建立了一个新的编程模型，以利用硬件设计的细粒度并行性。其次，我们提出了一种具有两个有效处理引擎的硬件设计，以减轻聚合阶段的不规则性并利用组合阶段的规律性。此外，这些发动机可以利用各种并行性，并有效地重复使用高度重复使用的数据。第三，我们通过发动机间管道优化整体系统，以进行相之间融合和基于优先级的芯片内存访问协调，以改善芯片外带宽利用率。与在Intel Xeon CPU和NVIDIA V100 GPU上运行的最先进的软件框架相比，我们的工作平均达到了1509美元$ \ times $速度，而2500 $ \ times $ \ times $降低能源减少和平均6.5 $ \ timess $速度，分别为10 $ \ times $ \ times $降低能源$。
In this work, we first characterize the hybrid execution patterns of GCNs on Intel Xeon CPU. Guided by the characterization, we design a GCN accelerator, HyGCN, using a hybrid architecture to efficiently perform GCNs. Specifically, first, we build a new programming model to exploit the fine-grained parallelism for our hardware design. Second, we propose a hardware design with two efficient processing engines to alleviate the irregularity of Aggregation phase and leverage the regularity of Combination phase. Besides, these engines can exploit various parallelism and reuse highly reusable data efficiently. Third, we optimize the overall system via inter-engine pipeline for inter-phase fusion and priority-based off-chip memory access coordination to improve off-chip bandwidth utilization. Compared to the state-of-the-art software framework running on Intel Xeon CPU and NVIDIA V100 GPU, our work achieves on average 1509$\times$ speedup with 2500$\times$ energy reduction and average 6.5$\times$ speedup with 10$\times$ energy reduction, respectively.
