2000 character limit reached
GDR-HGNN: A Heterogeneous Graph Neural Networks Accelerator Frontend with Graph Decoupling and Recoupling (2404.04792v1)
Published 7 Apr 2024 in cs.AR
Abstract: Heterogeneous Graph Neural Networks (HGNNs) have broadened the applicability of graph representation learning to heterogeneous graphs. However, the irregular memory access pattern of HGNNs leads to the buffer thrashing issue in HGNN accelerators. In this work, we identify an opportunity to address buffer thrashing in HGNN acceleration through an analysis of the topology of heterogeneous graphs. To harvest this opportunity, we propose a graph restructuring method and map it into a hardware frontend named GDR-HGNN. GDR-HGNN dynamically restructures the graph on the fly to enhance data locality for HGNN accelerators. Experimental results demonstrate that, with the assistance of GDR-HGNN, a leading HGNN accelerator achieves an average speedup of 14.6 times and 1.78 times compared to the state-of-the-art software framework running on A100 GPU and itself, respectively.
- [n. d.]. CACTI. http://www.hpl.hp.com/research/cacti/
- Dan Chen, et al. 2023. MetaNMP: Leveraging Cartesian-Like Product to Accelerate HGNNs with Near-Memory Processing. In Proceedings of the 50th Annual International Symposium on Computer Architecture. 1–13.
- Tong Geng, et al. 2021. I-GCN: A Graph Convolutional Network Accelerator with Runtime Locality Enhancement through Islandization. In MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO ’21). Association for Computing Machinery, New York, NY, USA, 1051–1063.
- Weihua Hu, et al. 2020. Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems 33 (2020).
- Yoongu Kim, et al. 2015. Ramulator: A fast and extensible DRAM simulator. IEEE Computer architecture letters 15, 1 (2015), 45–49.
- Harold W Kuhn. 1955. The Hungarian method for the assignment problem. Naval research logistics quarterly 2, 1-2 (1955), 83–97.
- Ansong Li, et al. 2022. Disentangled graph neural networks for session-based recommendation. IEEE Transactions on Knowledge and Data Engineering (2022).
- Feng Luo, et al. 2021. IMAS++ An Intelligent Medical Analysis System Enhanced with Deep Graph Neural Networks. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 4754–4758.
- Qingsong Lv, et al. 2021. Are we really making much progress? Revisiting, benchmarking and refining heterogeneous graph neural networks. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.
- Ruibin Mao, et al. 2023. ReRAM-based graph attention network with node-centric edge searching and hamming similarity. In 60th ACM/IEEE Design Automation Conference, DAC 2023, San Francisco, CA, USA, July 9-13, 2023. IEEE, 1–6.
- R. Sarkar, et al. 2023. FlowGNN: A Dataflow Architecture for Real-Time Workload-Agnostic Graph Neural Network Inference. In 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA). IEEE Computer Society, Los Alamitos, CA, USA, 1099–1112.
- Michael Schlichtkrull, et al. 2018. Modeling relational data with graph convolutional networks. In European semantic web conference. Springer, 593–607.
- Chuan Shi, et al. 2016. A survey of heterogeneous information network analysis. IEEE Transactions on Knowledge and Data Engineering 29, 1 (2016), 17–37.
- Hanrui Wang, et al. 2020a. GCN-RL circuit designer: Transferable transistor sizing with graph neural networks and reinforcement learning. In 2020 57th ACM/IEEE Design Automation Conference (DAC). IEEE, 1–6.
- Kai Wang, et al. 2020b. Relational Graph Attention Network for Aspect-based Sentiment Analysis. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 3229–3238.
- Minjie Yu Wang. 2019. Deep graph library: Towards efficient and scalable deep learning on graphs. In ICLR workshop.
- Runzhen Xue, et al. 2023. HiHGNN: Accelerating HGNNs through Parallelism and Data Reusability Exploitation. arXiv preprint arXiv:2307.12765 (2023).
- Mingyu Yan, et al. 2020. Hygcn: A gcn accelerator with hybrid architecture. In 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE, 15–29.
- Mingyu Yan, et al. 2022. Characterizing and Understanding HGNNs on GPUs. IEEE Computer Architecture Letters 21, 2 (2022), 69–72.
- Michihiro Yasunaga, et al. 2019. Scisummnet: A large annotated corpus and content-impact models for scientific paper summarization with citation networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 7386–7393.
- Runzhen Xue (8 papers)
- Mingyu Yan (39 papers)
- Dengke Han (6 papers)
- Yihan Teng (1 paper)
- Zhimin Tang (9 papers)
- Xiaochun Ye (37 papers)
- Dongrui Fan (36 papers)