EUVIMEDSkopri EUVIMED
Open access · CC BY 4.0

A2SPM: A Memory Access Acceleration for Neuromorphic Processing with the SPM

Yi Wei, Xiangyu Wang, Chao Xiao, Xun Xiao, Zhijie Yang, Rui Gong, Lei Wang

ACM Transactions on Embedded Computing Systems · 2026-07-31 · 25 (4) · 1-21

DOI: 10.1145/3816142 ↗

At a glance

Journal article in ACM Transactions on Embedded Computing Systems, published online on 2026-06-30. Written by Yi Wei and 6 co-authors. 31 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China, National Defense Key Laboratory Project of the State Administration of Science and Industry for National Defense, Key Laboratory of Advanced Microprocessor Chips and Systems.

AstrattDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Owing to their low power consumption and high energy efficiency, neuromorphic processors have found extensive applications across various intelligent computing domains, including artificial intelligence (AI) and low-power edge computing. Homogeneous neuromorphic processors demonstrate a unique integration of general-purpose computing versatility and neuromorphic computing acceleration capabilities. These processors effectively address the intensive memory access demands inherent in neuromorphic computing through the implementation of tightly coupled local memory, specifically Scratchpad Memory (SPM). This article presents the design of SPM-based memory access acceleration mechanisms, which have been specifically developed and optimized to accommodate the data characteristics and computational processes of typical Spiking Neural Networks (SNNs). The proposed scheme significantly enhances computational efficiency by reducing both memory access operations and computational instruction processing. Comparative performance evaluations reveal that the proposed design achieves a 28.99% speedup in Liquid State Machine operations and a 14.95% speedup in Spiking Convolutional Neural Network computations when benchmarked against a baseline homogeneous processor equipped with SPM.

Funding

  • National Natural Science Foundation of China
  • National Defense Key Laboratory Project of the State Administration of Science and Industry for National Defense
  • Key Laboratory of Advanced Microprocessor Chips and Systems

Cite

APA

Wei, Y., Wang, X., Xiao, C., Xiao, X., Yang, Z., Gong, R., & Wang, L. (2026). A2SPM: A Memory Access Acceleration for Neuromorphic Processing with the SPM. ACM Transactions on Embedded Computing Systems, 25(4), 1-21. https://doi.org/10.1145/3816142

Vancouver

Wei Y, Wang X, Xiao C, Xiao X, Yang Z, Gong R, et al. A2SPM: A Memory Access Acceleration for Neuromorphic Processing with the SPM. ACM Transactions on Embedded Computing Systems. 2026;25(4):1-21. doi:10.1145/3816142

BibTeX
@article{Wei2026,
  author = {Wei, Yi and Wang, Xiangyu and Xiao, Chao and Xiao, Xun and Yang, Zhijie and Gong, Rui and Wang, Lei},
  title = {A2SPM: A Memory Access Acceleration for Neuromorphic Processing with the SPM},
  journal = {ACM Transactions on Embedded Computing Systems},
  year = {2026},
  volume = {25},
  number = {4},
  pages = {1--21},
  doi = {10.1145/3816142}
}
Start for free →