Accelerating Generic Graph Neural Networks via Architecture, Compiler, Partition Method Co-Design

TL;DR

This paper presents SwitchBlade, a hardware-software co-design framework that accelerates various GNN models by reducing bandwidth needs and improving hardware utilization, achieving significant speedups and energy savings.

Contribution

The paper introduces a novel partition-level operator fusion, multi-threading, and fine-grained graph partitioning to support diverse GNN models efficiently.

Findings

Achieves 1.85x speedup over NVIDIA V100 GPU

Reduces energy consumption by 19.03x

Performs comparably to specialized GNN accelerators

Abstract

Graph neural networks (GNNs) have shown significant accuracy improvements in a variety of graph learning domains, sparking considerable research interest. To translate these accuracy improvements into practical applications, it is essential to develop high-performance and efficient hardware acceleration for GNN models. However, designing GNN accelerators faces two fundamental challenges: the high bandwidth requirement of GNN models and the diversity of GNN models. Previous works have addressed the first challenge by using more expensive memory interfaces to achieve higher bandwidth. For the second challenge, existing works either support specific GNN models or have generic designs with poor hardware utilization. In this work, we tackle both challenges simultaneously. First, we identify a new type of partition-level operator fusion, which we utilize to internally reduce the high bandwidth requirement of GNNs. Next, we introduce partition-level multi-threading to schedule the concurrent processing of graph partitions, utilizing different hardware resources. To further reduce the extra on-chip memory required by multi-threading, we propose fine-grained graph partitioning to generate denser graph partitions. Importantly, these three methods make no assumptions about the targeted GNN models, addressing the challenge of model variety. We implement these methods in a framework called SwitchBlade, consisting of a compiler, a graph partitioner, and a hardware accelerator. Our evaluation demonstrates that SwitchBlade achieves an average speedup of $1.85\times$ and energy savings of $19.03\times$ compared to the NVIDIA V100 GPU. Additionally, SwitchBlade delivers performance comparable to state-of-the-art specialized accelerators.