Towards High-Performance Flexible FPGA-Based Accelerators for CNN Inference: General Hardware Architecture and End-to-End Deploying Toolflow
ACM Transactions on Reconfigurable Technology and Systems · 30.06.2026 · 19 (2) · 1-31
DOI: 10.1145/3800704 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Reconfigurable Technology and Systems, online erschienen am 27.05.2026. Verfasst von Gang Wu und 4 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
FPGAs are widely used for efficient CNN inference acceleration but designing high-performance accelerators demands significant hardware expertise. Existing solutions face limitations: hardware designs are often model/chip-specific with suboptimal resource efficiency, and compiler support is typically framework-restricted. To overcome these, we propose a generalized and flexible high-performance FPGA accelerator architecture and a flexible end-to-end compilation toolflow based on ONNX IR. The architecture features an optimized uint8 systolic array for high compute density and a dedicated X-bus module handling diverse convolution parameters. On-chip buffers and allocation algorithms enhance memory efficiency. Configurable design variables enable architectural adaptation and fine-tuning. Deploying four accelerator variants on a VCU118 board and compiling 17 CNN models demonstrated a peak convolutional throughput of 5,792.19 GOPS (99.82% of theoretical peak, 5,825.42 GOPS) and overall throughput up to 3,311.48 GOPS. Compared to prior work, our solution offers superior usability, greater flexibility, and higher performance under comparable DSP usage. Furthermore, across most tested models, it provides significantly lower latency and higher energy efficiency versus CPUs and GPUs.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Wu, G., Lv, J., Chen, Y., Yin, S., & Liu, Y. (2026). Towards High-Performance Flexible FPGA-Based Accelerators for CNN Inference: General Hardware Architecture and End-to-End Deploying Toolflow. ACM Transactions on Reconfigurable Technology and Systems, 19(2), 1-31. https://doi.org/10.1145/3800704
Vancouver
Wu G, Lv J, Chen Y, Yin S, Liu Y. Towards High-Performance Flexible FPGA-Based Accelerators for CNN Inference: General Hardware Architecture and End-to-End Deploying Toolflow. ACM Transactions on Reconfigurable Technology and Systems. 2026;19(2):1-31. doi:10.1145/3800704
BibTeX
@article{Wu2026,
author = {Wu, Gang and Lv, Jiankun and Chen, Yongzheng and Yin, Shuaibo and Liu, Ying},
title = {Towards High-Performance Flexible FPGA-Based Accelerators for CNN Inference: General Hardware Architecture and End-to-End Deploying Toolflow},
journal = {ACM Transactions on Reconfigurable Technology and Systems},
year = {2026},
volume = {19},
number = {2},
pages = {1--31},
doi = {10.1145/3800704}
}
EUVIMED