WeChat Mini Program
Old Version Features

Cambricon-DG: an Accelerator for Redundant-Free Dynamic Graph Neural Networks Based on Nonlinear Isolation

Zhifei Yue, Xinkai Song, Tianbo Liu,Xing Hu,Rui Zhang,Zidong Du,Wei Li,Qi Guo,Tianshi Chen

International Symposium on High-Performance Computer Architecture(2025)

University of Science and Technology of China

Cited 0|Views6
Abstract
Dynamic Graph Neural Networks (DGNNs) have demonstrated significant potential in handling temporal graph-structured data. Typical DGNNs combine GNNs to process the structural information of graph and RNNs to capture the dynamic temporal information of graphs. However, current GNN accelerators process DGNNs by treating graph snapshots as static entities, leading to substantial redundant computations and memory accesses. While some DGNN accelerators have attempted to mitigate this redundancy, they face the challenge of maintaining accuracy for incremental processing due to the nonlinear activation function in GNNs. To address these issues, we propose a novel nonlinear isolation mechanism for incremental processing of DGNNs, which eliminates all redundant operations without accuracy loss. Additionally, we introduce a vertex-wise computation scheme for RNNs to minimize redundancy and reduce off-chip memory access. To validate the effectiveness of the mechanism, we implemented software optimizations on GPUs, achieving an $8.53 \times$ performance improvement over full-graph computation schemes. To address the inefficiency of graph topology operations on GPUs, we propose the Cambricon-DG accelerator, which features a dedicated hardware pipeline, an efficient topology management engine for graph traversal and topology sorting, and a hybrid computation engine that supports both GNN and RNN computations, thus improving hardware utilization. We evaluate Cambricon-DG on seven real-world dynamic graph datasets using five representative DGNN models. The results show that Cambricon-DG achieves an average speedup of $49.73 \times, 12.15 \times$, and $7.03 \times$, and an average energy saving of $41.31 \times, 9.47 \times$, and $5.23 \times$ over the state-of-the-art static/dynamic GNN accelerators I-GCN, RACE, and DeltaGNN, respectively.
More
Translated text
Key words
Dynamic Graph,Dynamic Neural Network,Dynamic Graph Neural Networks,Real-world Datasets,Dynamic Information,Accuracy Loss,Computational Strategy,Graph Topology,Incremental Process,Nonlinear Mechanism,Dynamic Datasets,Graph Traversal,Weight Matrix,Calculation Process,Matrix Multiplication,Exhaustive Search,Graph Structure,Amount Of Computation,Complete Elimination,Topological Changes,Aggregation Operators,Graph Changes,Cache Hit,Source Vertex,Computing Units,Sign Bit,Additional Overhead,Recommender Systems,Software Solutions,Vector Operations
求助PDF
上传PDF
Bibtex
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
  • Pretraining has recently greatly promoted the development of natural language processing (NLP)
  • We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
  • We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
  • The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
  • Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
Summary is being generated by the instructions you defined