收藏切换
TH-FCAD: Automated Deployment Framework for Large-Scale Neural Networks on FPGA Clusters
收藏切换
Yankang Zhao, Yuan Li, Xingyun Qi, Yihang Lu, Puguang Liu, Qiang Wang, Min Xie, Lin Peng, Mingche Lai*
Journal of Computer Research and Development | 2026, 63(11) : 2788 - 2806
Less
收藏切换
Journal of Computer Research and Development | 2026, 63(11): 2788-2806
• Computer Architecture •
TH-FCAD: Automated Deployment Framework for Large-Scale Neural Networks on FPGA Clusters
Full
Yankang Zhao, Yuan Li, Xingyun Qi, Yihang Lu, Puguang Liu, Qiang Wang, Min Xie, Lin Peng, Mingche Lai*
Affiliations
  • College of Computer Science and Technology, National University of Defense Technology, Changsha 410073
  • born in 2000. PhD candidate. His main research interests include hardware acceleration and computer architecture

    born in 1984. PhD, associate professor. His main research interests include high performance computer architecture, high speed interconnection network, and artificial intelligence

    born in 1979. PhD, associate professor. His main research interests include high performance computer architecture and high speed interconnection network

    born in 1999. Master. His main research interests include computer architecture and artificial intelligence

    born in 1995. PhD, assistant professor. His main research interests include algorithm accelerator, reconfigurable computing, and high-performance network

    born in 1989. PhD, assistant professor. His main research interests include computer architecture, high speed interconnection network, and artificial intelligence

    born in 1972. PhD, professor. His main research interest includes parallel and distributed computing

    born in 1979. PhD, associate professor. His main research interest includes high performance computing

    born in 1982. PhD, professor. His main research interests include computer architecture, high performance interconnection, and VLSI design

About Author:

born in 2000. PhD candidate. His main research interests include hardware acceleration and computer architecture

born in 1984. PhD, associate professor. His main research interests include high performance computer architecture, high speed interconnection network, and artificial intelligence

born in 1979. PhD, associate professor. His main research interests include high performance computer architecture and high speed interconnection network

born in 1999. Master. His main research interests include computer architecture and artificial intelligence

born in 1995. PhD, assistant professor. His main research interests include algorithm accelerator, reconfigurable computing, and high-performance network

born in 1989. PhD, assistant professor. His main research interests include computer architecture, high speed interconnection network, and artificial intelligence

born in 1972. PhD, professor. His main research interest includes parallel and distributed computing

born in 1979. PhD, associate professor. His main research interest includes high performance computing

born in 1982. PhD, professor. His main research interests include computer architecture, high performance interconnection, and VLSI design

Published: 2026-11-01 doi: 10.7544/issn1000-1239.202550866
Outline
收藏切换

With the rapid growth of neural network model sizes, single FPGA resources have become insufficient for accelerating large-scale models, while FPGA clusters face critical challenges, including complex architecture design, inefficient task partitioning, and the lack of automated toolchains. To address these issues, an end-to-end automated deployment framework for neural networks on FPGA clusters, named TH-FCAD (automated deployment framework for large-scale neural networks on FPGA clusters) is proposed. First, a two-level interconnect FPGA cluster architecture based on TH-Express is constructed. By integrating a high-speed global GTH (gigabit transceiver high-speed) network with a local LVDS (low voltage differential signaling) full-mesh interconnect, it achieves high-bandwidth and low-latency cross-node communication. Second, a latency-balancing optimization and model partitioning method is introduced to evenly partition large-scale neural networks into multiple acceleration kernels while maintaining inter-kernel delay equilibrium, which is essential for pipeline efficiency. Finally, a cluster-aware mapping algorithm is designed to automatically generate optimal placement schemes by jointly considering FPGA resource constraints and the cluster communication topology, thereby minimizing communication overhead. Furthermore, a complete automated toolchain is developed to streamline the entire deployment process, enabling seamless compilation from PyTorch/TensorFlow trained models to FPGA cluster configurations. Evaluations on a built 16 node FPGA cluster demonstrate that when deploying ResNet-8, SqueezeNet, and ResNet-50, TH-FCAD achieves inference latencies of 0.051 ms, 1.24 ms, and 1.36 ms, respectively, alongside a peak computational performance of 5.95 TOPS. Compared with state-of-the-art multi-FPGA approaches, the proposed framework delivers a 28.4% performance improvement and outperforms corresponding CPU and GPU implementations.

neural network  /  hardware acceleration  /  FPGA cluster  /  task partition  /  automated deployment framework
赵言亢, 黎渊, 齐星云, 陆亿行, 刘谱光, 王强, 谢旻, 彭林, 赖明澈. TH-FCAD:面向FPGA集群的大规模神经网络自动化部署框架. 计算机研究与发展, 2026 , 63 (11) : 2788 -2806 . DOI: 10.7544/issn1000-1239.202550866
Yankang Zhao, Yuan Li, Xingyun Qi, Yihang Lu, Puguang Liu, Qiang Wang, Min Xie, Lin Peng, Mingche Lai. TH-FCAD: Automated Deployment Framework for Large-Scale Neural Networks on FPGA Clusters[J]. Journal of Computer Research and Development, 2026 , 63 (11) : 2788 -2806 . DOI: 10.7544/issn1000-1239.202550866
Year 2026 volume 63 Issue 11
89
39
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202550866
  • Receive Date:2025-12-05
  • Online Date:2026-11-17
  • Published:2026-11-01
Article Data
Affiliations
History
  • Received:2025-12-05
  • Revised:2026-07-09
Affiliations
    College of Computer Science and Technology, National University of Defense Technology, Changsha 410073
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550866
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT