论文标题
H-GCN：Versal ACAP体系结构上的图形卷积网络加速器
H-GCN: A Graph Convolutional Network Accelerator on Versal ACAP Architecture
论文作者
论文摘要
图形神经网络（GNN）由于其独特的能力扩展了机器学习的能力（ML）方法，因此引起了极大的关注，该应用程序广泛定义为具有非结构化数据，尤其是图形。与其他机器学习（ML）模式相比，由于源自图类型的不规则性和异质性，图形神经网络（GNN）的加速度更具挑战性。但是，现有的努力主要集中在处理图形的不规则性上，而没有研究其异质性。 为此，我们提出了H-GCN，PL（可编程逻辑）和AIE（AI引擎）的混合加速器，该混合加速器利用了Xilinx Versal自适应计算加速度平台（ACAPS）的新兴异质性（ACAPS）以实现高表现GNN的选择。特别是，H-GCN根据其固有的异质性将每个图分为三个子图，并分别使用PL和AIE处理它们。为了进一步提高性能，我们探索了AIE的稀疏支持，并开发了一种有效的密度感知方法，以自动将稀疏矩阵矩阵乘法（SPMM）的瓷砖自动映射到收缩张量量阵列上。与最先进的GCN加速器相比，H-GCN平均达到1.1〜2.3倍的速度。
Graph Neural Networks (GNNs) have drawn tremendous attention due to their unique capability to extend Machine Learning (ML) approaches to applications broadly-defined as having unstructured data, especially graphs. Compared with other Machine Learning (ML) modalities, the acceleration of Graph Neural Networks (GNNs) is more challenging due to the irregularity and heterogeneity derived from graph typologies. Existing efforts, however, have focused mainly on handling graphs' irregularity and have not studied their heterogeneity. To this end we propose H-GCN, a PL (Programmable Logic) and AIE (AI Engine) based hybrid accelerator that leverages the emerging heterogeneity of Xilinx Versal Adaptive Compute Acceleration Platforms (ACAPs) to achieve high-performance GNN inference. In particular, H-GCN partitions each graph into three subgraphs based on its inherent heterogeneity, and processes them using PL and AIE, respectively. To further improve performance, we explore the sparsity support of AIE and develop an efficient density-aware method to automatically map tiles of sparse matrix-matrix multiplication (SpMM) onto the systolic tensor array. Compared with state-of-the-art GCN accelerators, H-GCN achieves, on average, speedups of 1.1~2.3X.
