Characterizing and Understanding HGNNs on GPUs

TL;DR

This paper provides a detailed characterization of heterogeneous graph neural networks (HGNNs) during inference on GPUs, revealing execution patterns and offering optimization guidelines for improved performance.

Contribution

It is the first to analyze HGNN workloads on GPUs, uncovering execution semantics and proposing optimization strategies for software and hardware.

Findings

Disclosed execution patterns of HGNNs on GPUs

Provided guidelines for software optimizations

Suggested hardware optimization strategies

Abstract

Heterogeneous graph neural networks (HGNNs) deliver powerful capacity in heterogeneous graph representation learning. The execution of HGNNs is usually accelerated by GPUs. Therefore, characterizing and understanding the execution pattern of HGNNs on GPUs is important for both software and hardware optimizations. Unfortunately, there is no detailed characterization effort of HGNN workloads on GPUs. In this paper, we characterize HGNN workloads at inference phase and explore the execution of HGNNs on GPU, to disclose the execution semantic and execution pattern of HGNNs. Given the characterization and exploration, we propose several useful guidelines for both software and hardware optimizations for the efficient execution of HGNNs on GPUs.