GNNHLS: Evaluating Graph Neural Network Inference via High-Level Synthesis

Chenfeng Zhao, Zehao Dong, Yixin Chen, Xuan Zhang, Roger D. Chamberlain
9/27/2023
cs.LGcs.ARcs.PF

Official code: ChenfengZhao/GNNHLS (12 stars, MIT, last commit 2023-10-02).

Abstract

With the ever-growing popularity of Graph Neural Networks (GNNs), efficient GNN inference is gaining tremendous attention. Field-Programming Gate Arrays (FPGAs) are a promising execution platform due to their fine-grained parallelism, low-power consumption, reconfigurability, and concurrent execution. Even better, High-Level Synthesis (HLS) tools bridge the gap between the non-trivial FPGA development efforts and rapid emergence of new GNN models. In this paper, we propose GNNHLS, an open-source framework to comprehensively evaluate GNN inference acceleration on FPGAs via HLS, containing a software stack for data generation and baseline deployment, and FPGA implementations of 6 well-tuned GNN HLS kernels. We evaluate GNNHLS on 4 graph datasets with distinct topologies and scales. The results show that GNNHLS achieves up to 50.8x speedup and 423x energy reduction relative to the CPU baselines. Compared with the GPU baselines, GNNHLS achieves up to 5.16x speedup and 74.5x energy reduction.

View on arXivView PDF

Code Implementations(1)

ChenfengZhao/GNNHLSOfficial
MIT
122C, C++Sep 13, 20233 years agoMIT

Similar Papers

DGNN-Booster: A Generic FPGA Accelerator Framework For Dynamic Graph Neural Network Inference

91% match1 repo162023

AMPLE: Event-Driven Accelerator for Mixed-Precision Inference of Graph Neural Networks

87% match2025

A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware

87% match2023

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

85% match2023

GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization

84% match1 repo252023

HGNAS: Hardware-Aware Graph Neural Architecture Search for Edge Devices

84% match2024

Cite this paper

@article{zhao2023gnnhls,
  title  = {GNNHLS: Evaluating Graph Neural Network Inference via High-Level Synthesis},
  author = {Chenfeng Zhao and Zehao Dong and Yixin Chen and Xuan Zhang and Roger D. Chamberlain},
  year   = {2023},
  eprint = {2309.16022},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.16022v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.16022.svg)](https://codeofpaper.com/paper/2309.16022)

Discussion