# Bottleneck Analysis of Dynamic Graph Neural Network Inference on CPU and GPU

arXiv: https://arxiv.org/abs/2210.03900 · HTML: https://mlsanity.com/paper/2210.03900/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 54 references that are in the map.
- First posted on arXiv 8 Oct 2022.

## Builds on (most cited first, 26 of 26)

- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [Neural Relational Inference for Interacting Systems](https://mlsanity.com/paper/1802.04687/) (2018)
- [Recent Trends in Deep Learning Based Natural Language Processing](https://mlsanity.com/paper/1708.02709/) (2017)
- [Time2Vec: Learning a Vector Representation of Time](https://mlsanity.com/paper/1907.05321/) (2019)
- [Distilling Knowledge from Graph Convolutional Networks](https://mlsanity.com/paper/2003.10477/) (2020)
- [Deep Learning on Image Denoising: An overview](https://mlsanity.com/paper/1912.13171/) (2019)
- [Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey](https://mlsanity.com/paper/2005.07496/) (2020)
- [HyGCN: A GCN Accelerator with Hybrid Architecture](https://mlsanity.com/paper/2001.02514/) (2020)
- [TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs](https://mlsanity.com/paper/2203.14883/) (2022)
- [Binary Graph Neural Networks](https://mlsanity.com/paper/2012.15823/) (2020)
- [GraphACT: Accelerating GCN Training on CPU-FPGA Heterogeneous Platforms](https://mlsanity.com/paper/2001.02498/) (2019)
- [Accelerating Graph Sampling for Graph Machine Learning using GPUs](https://mlsanity.com/paper/2009.06693/) (2020)
- [I-GCN: A Graph Convolutional Network Accelerator with Runtime Locality Enhancement through Islandization](https://mlsanity.com/paper/2203.03606/) (2022)
- [Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGA](https://mlsanity.com/paper/2203.05095/) (2022)
- [Learning Temporal Attention in Dynamic Graphs with Bilinear Interactions](https://mlsanity.com/paper/1909.10367/) (2019)
- [Low-latency Mini-batch GNN Inference on CPU-FPGA Heterogeneous Platform](https://mlsanity.com/paper/2206.08536/) (2022)
- [GNNSampler: Bridging the Gap between Sampling Algorithms of GNN and Hardware](https://mlsanity.com/paper/2108.11571/) (2021)
- [VersaGNN: a Versatile accelerator for Graph neural networks](https://mlsanity.com/paper/2105.01280/) (2021)
- [Geometric learning of the conformational dynamics of molecules using dynamic graph neural networks](https://mlsanity.com/paper/2106.13277/) (2021)

## Built on by (most cited first, 2 of 2)

- [DGNN-Booster: A Generic FPGA Accelerator Framework For Dynamic Graph Neural Network Inference](https://mlsanity.com/paper/2304.06831/) (2023)
- [Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours](https://mlsanity.com/paper/2412.20256/) (2024)

## Abstract (arXiv)

Dynamic graph neural network (DGNN) is becoming increasingly popular because of its widespread use in capturing dynamic features in the real world. A variety of dynamic graph neural networks designed from algorithmic perspectives have succeeded in incorporating temporal information into graph processing. Despite the promising algorithmic performance, deploying DGNNs on hardware presents additional challenges due to the model complexity, diversity, and the nature of the time dependency. Meanwhile, the differences between DGNNs and static graph neural networks make hardware-related optimizations for static graph neural networks unsuitable for DGNNs. In this paper, we select eight prevailing DGNNs with different characteristics and profile them on both CPU and GPU. The profiling results are summarized and analyzed, providing in-depth insights into the bottlenecks of DGNNs on hardware and identifying potential optimization opportunities for future DGNN acceleration. Followed by a comprehensive survey, we provide a detailed analysis of DGNN performance bottlenecks on hardware, including temporal data dependency, workload imbalance, data movement, and GPU warm-up. We suggest several optimizations from both software and hardware perspectives. This paper is the first to provide an in-depth analysis of the hardware performance of DGNN Code is available at https://github.com/sharc-lab/DGNN_analysis.