理解空间加速器上稀疏/密集多相GNN流的设计空间
Understanding the Design-Space of Sparse/Dense Multiphase GNN dataflows on Spatial Accelerators
摘要：
图神经网络（GNN）最近引起了人们的广泛兴趣，因为它们成功地从云和HPC中的几个关键应用程序的图结构数据中学习表示。由于其独特的计算和存储器特性来自计算的密集和稀疏阶段之间的相互作用，可重新配置的空间流（又名空间）加速器的出现通过映射优化的空间流（即，计算顺序和并行性）。这项工作的目标是描述和理解在空间加速器上运行GNN的设计空间，以便映射器或设计空间探索工具根据工作负载优化设计空间。具体来说，我们提出了一种分类法来描述所有可能的选择，用于在空间加速器上在空间和时间上映射GNN推理的密集和稀疏阶段，捕获阶段内的最低和阶段间的最低（流水线）。使用这种分类法，我们做深入的成本和效益的几个并行执行和执行的硬件参数的并行执行的影响和价值的灵活性，以支持流水线执行的案例研究。
英文摘要：
Graph Neural Networks (GNNs) have garnered a lot of recent interest because of their success in learning representations from graph-structured data across several critical applications in cloud and HPC. Owing to their unique compute and memory characteristics that come from an interplay between dense and sparse phases of computations, the emergence of reconfigurable dataflow (aka spatial) accelerators offers promise for acceleration by mapping optimized dataflows (i.e., computation order and parallelism) for both phases. The goal of this work is to characterize and understand the design-space of dataflow choices for running GNNs on spatial accelerators in order for mappers or design-space exploration tools to optimize the dataflow based on the workload. Specifically, we propose a taxonomy to describe all possible choices for mapping the dense and sparse phases of GNN inference, spatially and temporally over a spatial accelerator, capturing both the intra-phase dataflow and the inter-phase (pipelined) dataflow. Using this taxonomy, we do deep-dives into the cost and benefits of several dataflows and perform case studies on implications of hardware parameters for dataflows and value of flexibility to support pipelined execution.
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。
