H-GCN: A Graph Convolutional Network Accelerator on Versal ACAP Architecture

06/28/2022
by   Chengming Zhang, et al.
0

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.

READ FULL TEXT

page 4

page 7

research
08/04/2023

Exploiting On-chip Heterogeneity of Versal Architecture for GNN Inference Acceleration

Graph Neural Networks (GNNs) have revolutionized many Machine Learning (...
research
12/01/2022

Architectural Implications of Embedding Dimension during GCN on CPU and GPU

Graph Neural Networks (GNNs) are a class of neural networks designed to ...
research
10/15/2020

Bi-GCN: Binary Graph Convolutional Network

Graph Neural Networks (GNNs) have achieved tremendous success in graph r...
research
03/07/2022

I-GCN: A Graph Convolutional Network Accelerator with Runtime Locality Enhancement through Islandization

Graph Convolutional Networks (GCNs) have drawn tremendous attention in t...
research
10/24/2022

Binary Graph Convolutional Network with Capacity Exploration

The current success of Graph Neural Networks (GNNs) usually relies on lo...
research
03/01/2022

GROW: A Row-Stationary Sparse-Dense GEMM Accelerator for Memory-Efficient Graph Convolutional Neural Networks

Graph convolutional neural networks (GCNs) have emerged as a key technol...
research
09/26/2020

Rubik: A Hierarchical Architecture for Efficient Graph Learning

Graph convolutional network (GCN) emerges as a promising direction to le...

Please sign up or login with your details

Forgot password? Click here to reset