Efficient message passing architecture for GCN training on HBM-based FPGAs with orthogonal topology on-chip networks

Graphical abstract

References

[1] Yang H. AliGraph: a comprehensive graph neural network platform. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019, 3165−3166

[2] Zhou Z, Shi B, Zhang Z, Guan Y, Sun G, Luo G. BlockGNN: towards efficient GNN acceleration using block-circulant weight matrices. In: Proceedings of the 58th ACM/IEEE Design Automation Conference (DAC). 2021, 1009−1014

[3] Zhang B, Kannan R, Prasanna V. BoostGCN: a framework for optimizing GCN inference on FPGA. In: Proceedings of the IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). 2021, 29−39

[4] Li J, Louri A, Karanth A, Bunescu R. GCNAX: a flexible and energy-efficient accelerator for graph convolutional neural networks. In: Proceedings of 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA). 2021, 775−788

[5] Lin Y C, Zhang B, Prasanna V. HP-GNN: generating high throughput GNN training implementation on CPU-FPGA heterogeneous platform. In: Proceedings of 2022 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays. 2022, 123−133

RIGHTS & PERMISSIONS

Higher Education Press