Comprehensive Benchmarking of Binary Neural Networks on NVM Crossbar Architectures
Not on the map. Why?
Abstract (arXiv)
Non-volatile memory (NVM) crossbars have been identified as a promising technology, for accelerating important machine learning operations, with matrix-vector multiplication being a key example. Binary neural networks (BNNs) are especially well-suited for use with NVM crossbars due to their use of a low-bitwidth representation for both activations and weights. However, the aggressive quantization of BNNs can result in suboptimal accuracy, and the analog effects of NVM crossbars can further degrade the accuracy during inference. This paper presents a comprehensive study that benchmarks BNNs trained and validated on ImageNet and deployed on NeuroSim, a simulator for NVM-crossbar-based PIM architecture. Our study analyzes the impact of various parameters, such as input precision and ADC resolution, on both the accuracy of the inference and the hardware performance metrics. We have found that an ADC resolution of 8-bit with an input precision of 4-bit achieves near-optimal accuracy compared to the original BNNs. In addition, we have identified bottleneck components in the PIM architecture that affect area, latency, and energy consumption, and we demonstrate the impact that different BNN layers have on hardware performance.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 16 of its 46 references that are in the map. First posted on arXiv 11 Aug 2023.
Builds on
16 of 46 references.
References · 16
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2020Binary Neural Networks: A Surveycited by 190
- 2020ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functionscited by 184
- 2017Towards Accurate Binary Convolutional Neural Networkcited by 149
- 2017A Survey of Neuromorphic Computing and Neural Networks in Hardwarecited by 85
- 2019PUMA: A Programmable Ultra-efficient Memristor-based Accelerator for Machine Learning Inferencecited by 61
- 2021PokeBNN: A Binary Pursuit of Lightweight Accuracycited by 49
- 2020A Modern Primer on Processing in Memorycited by 32
- 2020FracBNN: Accurate and FPGA-Efficient Binary Neural Networks with Fractional Activationscited by 32
- 2018RxNN: A Framework for Evaluating Deep Neural Networks on Resistive Crossbarscited by 19
- 2019PANTHER: A Programmable Architecture for Neural Network Training Harnessing Energy-efficient ReRAMcited by 17
4 more
- 2022Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticketcited by 14
- 2023Binarized Neural Machine Translationcited by 13
- 2020TxSim:Modeling Training of Deep Neural Networks on Resistive Crossbar Systemscited by 9
- 2021BCNN: Binary Complex Neural Networkcited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.
- 2025Attack on a PUF-based Secure Binary Neural Networkcited by 0
- 2025Attack on a PUF-based Secure Binary Neural Network28 Oct 2025
Similar, not cited
Close in wording, no citation either way
- 2024BinSparX: Sparsified Binary Neural Networks for Reduced Hardware Non-Idealities in Xbar Arrays
- 2023Examining the Role and Limits of Batchnorm Optimization to Mitigate Diverse Hardware-noise in In-memory Computing
- 2025Optimizing Binary and Ternary Neural Network Inference on RRAM Crossbars using CIM-Explorer
- 2026Multibit neural inference in a N-ary crossbar architecture
- 2023Quantization of Deep Neural Networks to facilitate self-correction of weights on Phase Change Memory-based analog hardware
- 2024ZOBNN: Zero-Overhead Dependable Design of Binary Neural Networks with Deliberately Quantized Parameters
- 2024BF-IMNA: A Bit Fluid In-Memory Neural Architecture for Neural Network Acceleration
- 2023Optimizing data-flow in Binary Neural Networks