ADS-CNN: Adaptive Dataflow Scheduling for lightweight CNN accelerator on FPGAs

Yi Wan, Xianzhong Xie, Junfan Chen, Kunpeng Xie, Dezhi Yi, Ye Lu*, Keke Gai*

*此作品的通讯作者

科研成果: 期刊稿件文章同行评审

1 引用 (Scopus)

摘要

Lightweight convolutional neural networks (CNNs) enable lower inference latency and data traffic, facilitating deployment on resource-constrained edge devices such as field-programmable gate arrays (FPGAs). However, CNNs inference requires access to off-chip synchronous dynamic random-access memory (SDRAM), which significantly degrades inference speed and system power efficiency. In this paper, we propose an adaptive dataflow scheduling method for lightweight CNN accelerator on FPGAs named ADS-CNN. The key idea of ADS-CNN is to efficiently utilize on-chip resources and reduce the amount of SDRAM access. To achieve the reuse of logical resources, we design a time division multiplexing calculation engine to be integrated in ADS-CNN. We implement a configurable module for the convolution controller to adapt to the data reuse of different convolution layers, thus reducing the off-chip access. Furthermore, we exploit on-chip memory blocks as buffers based on the configuration of different layers in lightweight CNNs. On the resource-constrained Intel CycloneV SoC 5CSEBA6 FPGA platform, we evaluated six common lightweight CNN models to demonstrate the performance advantages of ADS-CNN. The evaluation results indicate that, compared with accelerators that use traditional tiling strategy dataflow, our ADS-CNN can achieve up to 1.29× speedup with the overall dataflow scale compression of 23.7%.

源语言英语
页(从-至)138-149
页数12
期刊Future Generation Computer Systems
158
DOI
出版状态已出版 - 9月 2024

指纹

探究 'ADS-CNN: Adaptive Dataflow Scheduling for lightweight CNN accelerator on FPGAs' 的科研主题。它们共同构成独一无二的指纹。

引用此

Wan, Y., Xie, X., Chen, J., Xie, K., Yi, D., Lu, Y., & Gai, K. (2024). ADS-CNN: Adaptive Dataflow Scheduling for lightweight CNN accelerator on FPGAs. Future Generation Computer Systems, 158, 138-149. https://doi.org/10.1016/j.future.2024.04.038