EA-HWP: An Efficient CNN/SNN Accelerator With Hybrid Weight Precision
- 26 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 73 (4) , 468-472
Abstract
Due to the low power consumption and event-driven characteristics, spiking neural networks (SNNs) have garnered significant interest in recent years. In comparison, convolutional neural networks (CNNs) achieve state-of-the-art results in image classification tasks by virtue of their local perception and hierarchical learning characteristics. The fusion computing of SNN and CNN represents a promising direction that can fully leverage the low-power advantages of SNN and the high-precision advantages of CNN. In this breif, a 28-nm efficient heterogeneous CNN/SNN accelerator, named EA-HWP is proposed. EA-HWP employs a heterogeneous distributed design for the efficient on-chip implementation of CNN computation, CNN-SNN conversion, and SNN computation. Meanwhile, based on the characteristics of weight distribution, dense-and-sparse computing architecture is proposed for hybrid weight precision computation. Fabricated in 28-nm CMOS process, EA-HWP can run at a maximum of 1152MHz for CNN and 792MHz for SNN. When the supply voltage is 0.625V, EA-HWP can achieve energy efficiency of 0.14pJ/OP for CNN and 0.26pJ/SOP for SNN, respectively.Keywords
Funding Information
- National Key Research and Development Program of China (2024YFB4405501)
This publication has 21 references indexed in Scilit:
- A A 22nm 0.43pJ/SOP Sparsity-Aware In-Memory Neuromorphic Computing System with Hybrid Spiking and Artificial Neural Network and Configurable Topology2023
- Knowledge Distillation: A SurveyInternational Journal of Computer Vision, 2021
- 0.5V 4.8 pJ/SOP 0.93\mu \mathrm{W}$ Leakage/core Neuromorphic Processor with Asynchronous NoC and Reconfigurable LIF Neuron2020
- Tight Compression: Compressing CNN Model Tightly Through Unstructured Pruning and Simulated Annealing Based Permutation2020
- Blood Pressure Estimation From PPG Signals Using Convolutional Neural Networks And Siamese Network2020
- UNPU: A 50.6TOPS/W unified deep neural network accelerator with 1b-to-16b fully-variable weight bit-precision2018
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Networks of spiking neurons: The third generation of neural network modelsNeural Networks, 1997
- Neuromorphic electronic systemsProceedings of the IEEE, 1990