GNN Acceleration

GNN acceleration focuses on improving the speed and efficiency of Graph Neural Network (GNN) computations, crucial for handling the large-scale datasets common in applications like recommender systems and bioinformatics. Current research emphasizes developing specialized hardware accelerators, often leveraging techniques like decoupled computation, optimized dataflow architectures, and efficient graph partitioning to overcome the challenges posed by sparse graph data. These advancements are vital for enabling the wider adoption of GNNs in computationally demanding real-world applications, improving performance and energy efficiency compared to traditional CPU and GPU implementations.

Papers

April 23, 2024

NeuraChip: Accelerating GNN Computations with a Hash-based Decoupled Spatial Accelerator
Kaustubh Shivdikar, Nicolas Bohm Agostini, Malith Jayaweera, Gilbert Jonatan, Jose L. Abellan, Ajay Joshi, John Kim, David Kaeli
Graph Neural Network Large Scale Graph Datasets GNN Acceleration GNN Computation Spatial Accelerator

February 21, 2024

Linear-Time Graph Neural Networks for Scalable Recommendations
Jiahao Zhang, Rui Xue, Wenqi Fan, Xin Xu, Qing Li, Jian Pei, Xiaorui Liu
Graph Neural Network Large Scale Recommendation GNN Acceleration

October 18, 2023

Architectural Implications of GNN Aggregation Programming Abstractions
Yingjie Qi, Jianlei Yang, Ao Zhou, Tong Qiao, Chunming Hu
Graph Neural Network GNN Framework GNN Aggregation GNN Acceleration GNN Computation

August 16, 2023

Accelerating Generic Graph Neural Networks via Architecture, Compiler, Partition Method Co-Design
Shuwen Lu, Zhihui Zhang, Cong Guo, Jingwen Leng, Yangjie Zhou, Minyi Guo
Graph Neural Network Architecture Design Hardware Accelerator GNN Model Graph Partitioning End to End Compiler GNN Acceleration Technology Co Optimization

June 24, 2023

A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware
Shichang Zhang, Atefeh Sohrabizadeh, Cheng Wan, Zijie Huang, Ziniu Hu, Yewen Wang, Yingyan, Lin, Jason Cong, Yizhou Sun
Neural Network Graph Neural Network Timely Survey Practical Algorithm System Description Graph Structured Data GNN Acceleration

April 13, 2023

DGNN-Booster: A Generic FPGA Accelerator Framework For Dynamic Graph Neural Network Inference
Hanqiu Chen, Cong Hao
FPGA Accelerator GNN Acceleration

December 7, 2022

PyGFI: Analyzing and Enhancing Robustness of Graph Neural Networks Against Hardware Errors
Ruixuan Wang, Fred Lin, Daniel Moore, Sriram Sankar, Xun Jiao
Graph Neural Network Native Robustness Hardware Error GNN Acceleration Resilient Algorithm

September 7, 2022

Hardware Acceleration of Sampling Algorithms in Sample and Aggregate Graph Neural Networks
Yuchen Gui, Boyi Wei, Wei Yuan, Xi Jin
External Sample GNN Architecture Hardware Acceleration Sampling Based Algorithm GNN Acceleration

April 27, 2022

FlowGNN: A Dataflow Architecture for Real-Time Workload-Agnostic Graph Neural Network Inference
Rishov Sarkar, Stefan Abi-Karam, Yuqi He, Lakshmi Sathidevi, Cong Hao
GNN Model Message Passing Graph Neural Network Dataflow Architecture GNN Inference GNN Acceleration Graph Neural Network Inference

January 20, 2022

GenGNN: A Generic FPGA Framework for Graph Neural Network Acceleration
Stefan Abi-Karam, Yuqi He, Rishov Sarkar, Lakshmi Sathidevi, Zihang Qiao, Cong Hao
Graph Neural Network GNN Model GNN Inference GNN Acceleration

December 3, 2021

TC-GNN: Bridging Sparse GNN Computation and Dense Tensor Cores on GPUs
Yuke Wang, Boyuan Feng, Zheng Wang, Guyue Huang, Yufei Ding
Single GPU GNN Framework Tensor Core DNN Workload GNN Acceleration

GNN Acceleration

Papers

NeuraChip: Accelerating GNN Computations with a Hash-based Decoupled Spatial Accelerator

Linear-Time Graph Neural Networks for Scalable Recommendations

Architectural Implications of GNN Aggregation Programming Abstractions

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

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

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

PyGFI: Analyzing and Enhancing Robustness of Graph Neural Networks Against Hardware Errors

Hardware Acceleration of Sampling Algorithms in Sample and Aggregate Graph Neural Networks

FlowGNN: A Dataflow Architecture for Real-Time Workload-Agnostic Graph Neural Network Inference

GenGNN: A Generic FPGA Framework for Graph Neural Network Acceleration

TC-GNN: Bridging Sparse GNN Computation and Dense Tensor Cores on GPUs