EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Energy-Efficient FPGA-Based CNN Accelerator with Dual-Multiply Packing and Ping-Pong Buffering for Real-Time Object Detection

Wenrui Wang, Dong Zhou, Wenjie Xie, Wenshuai Zhang

Electronics · 03.06.2026 · 15 (11) · 2442

DOI: 10.3390/electronics15112442 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 03.06.2026. Verfasst von Wenrui Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time deployment of modern object-detection networks on edge devices is challenging because of limited compute resources, external-memory bandwidth, and strict power constraints. To address these issues, this paper presents a host–FPGA collaborative accelerator for quantized YOLOv5n on a Xilinx Zynq-7100 platform. The proposed design includes a modular multi-operator neural processing unit supporting seven atomic operators, a Dual-Multiply Packing (DMP) scheme to improve DSP48E1-based INT8 convolution density, a cache–compute–cache dataflow with global ping-pong buffering to overlap DMA transfers and computation, and a Multi-Quantization Domain Alignment (MQDA) pipeline to preserve accuracy at Add and Cat fusion nodes. Implemented at 200 MHz, the prototype achieves 24.617 ms FPGA-side forward-inference latency, 36.686 ms end-to-end single-frame latency, 27.2 FPS system-level performance, 182.8 GOPS equivalent throughput, and 8.536 W on-chip power consumption, corresponding to 21.42 GOPS/W. Experimental results also show that INT8 quantization causes only limited accuracy degradation, while MQDA improves quantized detection accuracy by reducing cross-domain fusion error. These results demonstrate that the proposed architecture provides an effective balance among throughput, energy efficiency, hardware cost, and quantized accuracy for real-time edge object detection.

Zitieren

APA

Wang, W., Zhou, D., Xie, W., & Zhang, W. (2026). An Energy-Efficient FPGA-Based CNN Accelerator with Dual-Multiply Packing and Ping-Pong Buffering for Real-Time Object Detection. Electronics, 15(11), 2442. https://doi.org/10.3390/electronics15112442

Vancouver

Wang W, Zhou D, Xie W, Zhang W. An Energy-Efficient FPGA-Based CNN Accelerator with Dual-Multiply Packing and Ping-Pong Buffering for Real-Time Object Detection. Electronics. 2026;15(11):2442. doi:10.3390/electronics15112442

BibTeX
@article{Wang2026,
  author = {Wang, Wenrui and Zhou, Dong and Xie, Wenjie and Zhang, Wenshuai},
  title = {An Energy-Efficient FPGA-Based CNN Accelerator with Dual-Multiply Packing and Ping-Pong Buffering for Real-Time Object Detection},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {11},
  pages = {2442},
  doi = {10.3390/electronics15112442}
}
Kostenlos starten →