Hardware Acceleration of Inference on Dynamic GNNs
Pages 1 - 6
Abstract
Dynamic graph neural networks (DGNNs) play a crucial role in applications that require inferencing on graph-structured data, where the connectivity and features of the graph evolve over time. The proposed platform integrates graph neural network (GNN) and recurrent neural network (RNN) components of DGNNs, providing a unified platform that captures spatial and temporal information. Novel contributions include optimized cache reuse, a novel caching policy, and efficient GNN-RNN pipelining. Average energy efficiency gains of 8393X, 183x, and 87X -- 10X, and inference speedups of 1796X, 77X, and 21x -- 2.4X, over Intel Xeon Gold CPU, NVIDIA V100 GPU, and prior approaches, respectively, are demonstrated across multiple graph datasets and multiple DGNNs.
References
[1]
S. Mondal et al. GNNIE: GNN Inference Engine with Load-Balancing and Graph-Specific Caching. In DAC, 2022.
[2]
E. Rossi et al. Temporal Graph Networks for Deep Learning on Dynamic Graphs. ICML, 2020.
[3]
S.M. Kazemi et al. Representation Learning for Dynamic Graphs: A Survey. J. Mach. Learn. Re., 2020.
[4]
C. Wang et al. PiPAD: Pipelined and Parallel Dynamic GNN Training on GPUs. In PPoPP, 2023.
[5]
M. Zhang et al. DeepCPU: Serving RNN-based Deep Learning Models 10x Faster. In USENIX ATC 18, 2018.
[6]
V. T. Chakaravarthy et al. Efficient Scaling of Dynamic Graph Neural Networks. In SC, 2021.
[7]
X. Song et al. Cambricon-G: A Polyvalent Energy-Efficient Accelerator for Dynamic Gaph Neural Networks. IEEE T. Comput. Aid. D., 2022.
[8]
H. Chen et al. DGNN-Booster: A Generic FPGA Accelerator Framework For Dynamic Graph Neural Network Inference. In FCCM, 2023.
[9]
Y. Huang et al. ReaDy: A ReRAM-Based Processing-in-Memory Accelerator for Dynamic Graph Convolutional Networks. IEEE T. Comput. Aid. D., 2022.
[10]
Y. Huang et al. Accelerating Graph Convolutional Networks Using Crossbar-based Processing-In-Memory Architectures. In HPCA, 2022.
[11]
G. Panagopoulos et al. Transfer Graph Neural Networks for Pandemic Forecasting. In AAAI, 2021.
[12]
A. Pareja et al. EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs. In AAAI, 2020.
[13]
L. Zhao et al. T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction. IEEE T. Intell. Tra. Sys., 2019.
[14]
S. Guo et al. Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting. In AAAI, 2019.
[15]
S. Mondal et al. A Unified Engine for Accelerating GNN Weighting/Aggregation Operations, with Efficient Load Balancing and Graph-Specific Caching. IEEE T. Comput. Aid. D., 2022.
[16]
M. Yan et al. HyGCN: A GCN Accelerator with Hybrid Architecture. In HPCA, 2020.
[17]
T. Geng et al. AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing. In MICRO, 2020.
[18]
J.R. Stevens et al. GNNerator: A Hardware/Software Framework for Accelerating Graph Neural Networks. In DAC, 2021.
[19]
Z. Zhou et al. BlockGNN: Towards Efficient GNN Acceleration Using Block-Circulant Weight Matrices. In DAC, 2021.
[20]
C. Chen et al. DyGNN: Algorithm and Architecture Support of Dynamic Pruning for Graph Neural Networks. In DAC, 2021.
[21]
H. Zhou et al. TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs. VLDB, 2022.
[22]
CACTI 6.5. https://github.com/Chun-Feng/CACTI-6.5.
[23]
Y. Kim et al. Ramulator: A Fast and Extensible DRAM Simulator. IEEE Comp. Arch. Lett., 15(1), 2015.
[24]
M. O'Connor et al. Fine-Grained DRAM: Energy-Efficient DRAM for Extreme Bandwidth Systems. In ISCA, 2017.
[25]
B. Rozemberczki et al. PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models. In CIKM, 2021.
Index Terms
- Hardware Acceleration of Inference on Dynamic GNNs
Recommendations
Parallel ant colony for nonlinear function optimization with graphics hardware acceleration
SMC'09: Proceedings of the 2009 IEEE international conference on Systems, Man and CyberneticsThis paper presents a massively parallel Ant Colony Optimization - Pattern Search (ACO-PS) algorithm with graphics hardware acceleration on nonlinear function optimization problems. The objective of this study is to determine the effectiveness of using ...
Performance Evaluation of Feed-Forward Backpropagation Neural Network for Classification on a Reconfigurable Hardware Architecture
Proceedings of the 12th International Symposium on Applied Reconfigurable Computing - Volume 9625Performance of classification using Feed-Forward Backpropagation Neural Network FFBPNN on a reconfigurable hardware architecture is evaluated in this paper. The hardware architecture used for implementation of FFBPNN in this paper is a set of ...
Massively parallel differential evolution--pattern search optimization with graphics hardware acceleration: an investigation on bound constrained optimization problems
This paper presents a novel parallel Differential Evolution (DE) algorithm with local search for solving function optimization problems, utilizing graphics hardware acceleration. As a population-based meta-heuristic, DE was originally designed for ...
Comments
Information & Contributors
Information
Published In
August 2024
384 pages
ISBN:9798400706882
DOI:10.1145/3665314
- Chair:
- Pascal Meinerzhagen,
- Program Chair:
- Kapil Dev,
- Program Co-chair:
- Jerald Yoo
Copyright © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
- SIGDA: ACM Special Interest Group on Design Automation
- IEEE CAS
- IEEE EDA
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 09 September 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
Conference
ISLPED '24
Sponsor:
ISLPED '24: 29th ACM/IEEE International Symposium on Low Power Electronics and Design
August 5 - 7, 2024
CA, Newport Beach, USA
Acceptance Rates
Overall Acceptance Rate 398 of 1,159 submissions, 34%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 77Total Downloads
- Downloads (Last 12 months)77
- Downloads (Last 6 weeks)28
Reflects downloads up to 22 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in