EUVIMEDEUVIMED entdecken
Crossref

A Flexible FPGA-based Butterfly Engine for Accelerating Signal Processing and Machine Learning

Xueyuan Liu, Ruilin Wu, Philip H.W. Leong

ACM Transactions on Reconfigurable Technology and Systems · 18.07.2026

DOI: 10.1145/3831248 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Reconfigurable Technology and Systems, online erschienen am 18.07.2026. Verfasst von Xueyuan Liu und 2 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Field-programmable gate arrays (FPGAs) have emerged as efficient accelerators for both neural network (NN) inference and digital signal processing (DSP) tasks, particularly on resource-constrained edge devices. While previous NN accelerators based on butterfly operations demonstrate significant acceleration for inference, they are inadequately suited for long sequences and lack support for bit-reversed access patterns, limiting their applicability to variable-length DSP workloads. Based on prior butterfly accelerators, this paper presents flexible butterfly engine (FlexBE), together with a co-designed NN architecture, Butterfly-based Signal Processing Net (BSPNet). The proposed system jointly supports signal pre-processing and butterfly linear (BL)-based NN inference under stringent resource constraints. FlexBE incorporates novel adaptive data switching networks, dynamic access control mechanisms, and an efficient bit-reversal module, enabling runtime reconfiguration of sequence lengths and degrees of parallelism. Implemented on an AMD ZCU104 FPGA running at \(300\) MHz, FlexBE computes four \(32\) k-point fast Fourier transforms (FFTs) in approximately \(15,360\) clock cycles. On challenging automatic modulation classification (AMC) datasets, BSPNet achieves accuracy comparable to GPU baselines. For single-batch inference, BSPNet with FlexBE is \(2.2\sim 3.1\times\) faster than prior butterfly-based accelerators; on the ZCU104, the end-to-end latency achieves speedups of up to \(4.92\times\) and \(2.89\times\) compared to an Intel Core i9 CPU and an NVIDIA RTX 3090 GPU, respectively.

Zitieren

APA

Liu, X., Wu, R., & Leong, P. H. (2026). A Flexible FPGA-based Butterfly Engine for Accelerating Signal Processing and Machine Learning. ACM Transactions on Reconfigurable Technology and Systems. https://doi.org/10.1145/3831248

Vancouver

Liu X, Wu R, Leong PH. A Flexible FPGA-based Butterfly Engine for Accelerating Signal Processing and Machine Learning. ACM Transactions on Reconfigurable Technology and Systems. 2026. doi:10.1145/3831248

BibTeX
@article{Liu2026,
  author = {Liu, Xueyuan and Wu, Ruilin and Leong, Philip H.W.},
  title = {A Flexible FPGA-based Butterfly Engine for Accelerating Signal Processing and Machine Learning},
  journal = {ACM Transactions on Reconfigurable Technology and Systems},
  year = {2026},
  doi = {10.1145/3831248}
}
Kostenlos starten →