用于计算SSD的硬件/软件协同可编程框架，以加速大规模图上的深度学习服务
Hardware/Software Co-Programmable Framework for Computational SSDs to Accelerate Deep Learning Service on Large-Scale Graphs
摘要：
图神经网络（GNN）处理由一千亿条边组成的大规模图。与传统的深度学习相比，新兴GNN的独特行为涉及大量的图形和嵌入存储的数据，这表现出复杂和不规则的预处理。我们提出了一个新的大型图上的深度学习框架HolisticGNN，它提供了一个易于使用的，接近存储的推理基础设施，用于快速，节能的GNN处理。为了实现最佳的端到端延迟和高能效，HolisticGNN允许用户实现各种GNN算法，并以整体方式在实际数据存在的地方直接执行这些算法。它还支持PCIe上的RPC，这样用户就可以通过图形语义库简单地对GNN进行编程，而无需了解底层硬件或存储配置。我们制作了HolisticGNN的硬件RTL，并在基于FPGA的计算SSD（CSSD）上实现了其软件。我们的实证评估表明，HolisticGNN的推理时间比使用高性能现代GPU的GNN推理服务高出7.1倍，同时平均降低了33.2倍的能耗。
英文摘要：
Graph neural networks (GNNs) process large-scale graphs consisting of a hundred billion edges. In contrast to traditional deep learning, unique behaviors of the emerging GNNs are engaged with a large set of graphs and embedding data on storage, which exhibits complex and irregular preprocessing. We propose a novel deep learning framework on large graphs, HolisticGNN, that provides an easy-to-use, near-storage inference infrastructure for fast, energy-efficient GNN processing. To achieve the best end-to-end latency and high energy efficiency, HolisticGNN allows users to implement various GNN algorithms and directly executes them where the actual data exist in a holistic manner. It also enables RPC over PCIe such that the users can simply program GNNs through a graph semantic library without any knowledge of the underlying hardware or storage configurations. We fabricate HolisticGNN's hardware RTL and implement its software on an FPGA-based computational SSD (CSSD). Our empirical evaluations show that the inference time of HolisticGNN outperforms GNN inference services using high-performance modern GPUs by 7.1x while reducing energy consumption by 33.2x, on average.
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。
