Characterization of memristor based on non-linear ion drift model

Thomas, Sam; Prakash, Surya; Priya, K. Bhanu

doi:10.1109/icecds.2017.8389839

Cited by 4 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To characterize the non-volatile memristive device, we employed the SPICE software based on a non-linear drift model as previously studied in [38,39]. The typical currentvoltage characteristic (IVC) of the non-volatile memristor is depicted in figure 1(c).…”

Section: Device Modelmentioning

confidence: 99%

Superconducting in-memory computing architecture coupling with memristor synapses for binarized neural networks

Xu,

Liu,

et al. 2024

Supercond. Sci. Technol.

View full text Add to dashboard Cite

In-memory computing electronic components offer a promising non-von Neumann strategy to develop energy-efficient and high-speed hardware systems for artificial intelligence (AI). However, the implementation of conventional electronic hardware demands a huge computational and power budget, thereby limiting their wider application. In this work, we propose a novel superconducting in-memory computing architecture by coupling the memristor device. Leveraging the phase transition of the superconductor induced by external applied Joule power, we can modulate the state of the bottom superconductor based on memristor resistive states and applied voltages, enabling the execution of in-memory computing operations. We then successfully implement vector-matrix multiplication of input and output signals within the designed array, facilitating its integration into AI systems. Constructing a binarized neural network with superconductor-memristor arrays achieves a high level of accuracy, approximately 97%, in handwritten number classification. Through an evaluation of power consumption in our proposed architecture, we find a remarkable ~48400× advantage in power efficiency compared to typical memristor systems. This marks the inaugural demonstration of a superconducting in-memory computing architecture through memristor coupling, offering a promising hardware platform for various AI systems with superior energy efficiency and computing capacity.

show abstract

Section: Device Modelmentioning

confidence: 99%

Superconducting in-memory computing architecture coupling with memristor synapses for binarized neural networks

Xu,

Liu,

et al. 2024

Supercond. Sci. Technol.

View full text Add to dashboard Cite

show abstract

Noise analysis of CMOS-memristive and CMOS-resistive current mirrors

Kupreyev

2018

2018 International Conference on Computing and Network Communications (CoCoNet)

View full text Add to dashboard Cite

Modified nonlinear ion drift model for TiO2 memristor: a temperature dependent study

Panda,

Dash,

Jothiramalingam

et al. 2024

J. Ovonic. Res.

View full text Add to dashboard Cite

The creation and optimisation of memristor models with different topologies and physical mechanisms have received increasing attention in recent years. Memristors, known for their unique resistive switching mechanism, have garnered significant interest as promising components for next-generation computing. However, to effectively design and test memristor-based circuits, it is crucial to have a mathematical representation of the experimentally determined current-voltage characteristics of memristors. This paper proposes a model and conducts an analysis that offers insights into memristor technology, beginning with its characteristics and extending to simulations involving various parameters. The proposed model and its dependency on temperature are implemented using MATLAB. The model captures changes in current characteristics concerning the fundamental voltage without using any window functions. Thus, it accurately represents the variation in memristance with temperature, contributing to a more precise and observed modelling approach.

show abstract

Characterization of memristor based on non-linear ion drift model

Cited by 4 publications

References 8 publications

Superconducting in-memory computing architecture coupling with memristor synapses for binarized neural networks

Superconducting in-memory computing architecture coupling with memristor synapses for binarized neural networks

Noise analysis of CMOS-memristive and CMOS-resistive current mirrors

Modified nonlinear ion drift model for TiO2 memristor: a temperature dependent study

Contact Info

Product

Resources

About