BCIM: Efficient Implementation of Binary Neural Network Based on Computation in Memory
- 4 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computing
- Vol. 13 (2) , 395-408
Abstract
Applications of Binary Neural Networks (BNNs) are promising for embedded systems with hard constraints on energy and computing power. Contrary to conventional neural networks using floating-point datatypes, BNNs use binarized weights and activations to reduce memory and computation requirements. Memristors, emerging non-volatile memory devices, show great potential as a target implementation platform for BNNs by integrating storage and compute units. However, the efficiency of this hardware highly depends on how the network is mapped and executed on these devices. In this paper, we propose an efficient implementation of XNOR-based BNN to maximize parallelization. In this implementation, costly analog-to-digital converters are replaced with sense amplifiers with custom reference(s) to generate activation values. Besides, a novel mapping is introduced to minimize the overhead of data communication between convolution layers mapped to different memristor crossbars. This comes with extensive analytical and simulation-based analysis to evaluate the implication of different design choices considering the accuracy of the network. The results show that our approach achieves up to $5\times$ energy-saving and $100\times$ improvement in latency compared to baselines.Keywords
All Related Versions
Funding Information
- EU's Horizon Europe Research and Innovation programme (101070374)
This publication has 41 references indexed in Scilit:
- A comprehensive review of Binary Neural NetworkArtificial Intelligence Review, 2023
- Highly parallelized memristive binary neural networkNeural Networks, 2021
- Maximizing Parallel Activation of Word-Lines in MRAM-Based Binary Neural Network AcceleratorsIEEE Access, 2021
- Nanoionic memristive phenomena in metal oxides: the valence change mechanismAdvances in Physics, 2021
- In-memory hyperdimensional computingNature Electronics, 2020
- Convolutional neural network: a review of models, methodologies and applications to object detectionProgress in Artificial Intelligence, 2019
- Memristor crossbar array for binarized neural networksAIP Advances, 2019
- Memristor‐Based Analog Computation and Neural Network Classification with a Dot Product EngineAdvanced Materials, 2018
- FP-BNN: Binarized neural network on FPGANeurocomputing, 2018
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks2016