The emergence of memristors with potential applications in data storage and artificial intelligence has attracted wide attentions. Memristors are assembled in crossbar arrays with data bits encoded by the resistance of individual cells. Despite the proposed high density and excellent scalability, the sneak-path current causing cross interference impedes their practical applications. Therefore, developing novel architectures to mitigate sneak-path current and improve efficiency, reliability, and stability may benefit next-generation storage-class memory (SCM). Moreover, conventional digital computers face the von-Neumann bottleneck and the slowdown of transistors’ scaling, imposing a big challenge to hardware artificial intelligence. Memristive crossbar features colocation of memory and processing units, as well as superior scalability, making it a promising candidate for hardware accelerating machine learning and neuromorphic computing. Herein, first, crossbar architecture is introduced. Then, for storage, the origin of sneak-path current is reviewed and techniques to mitigate this issue from the angle of materials and circuits are discussed. Computing wise, the applications of memristive crossbars in both machine learning and neuromorphic computing are surveyed, focusing on the structure of unit cells, the network topology, and the learning types. Finally, a perspective on future engineering and applications of memristive crossbars is discussed.

https://onlinelibrary.wiley.com/doi/pdf/10.1002/aisy.202100017

Memristive Crossbar Arrays for Storage and Computing Applications

Conventional computing based on von Neumann architecture cannot satisfy the demands of artificial intelligence (AI) applications anymore. Neuromorphic computing, emulating structures and principles based on the human brain, provides an alternative and promising approach for efficient and low consumption information processing. Herein, recent progress in neuromorphic computing enabled by emerging two-dimensional (2D) materials is introduced from devices design and hardware implementation to system integration. Especially, the advances of hopeful artificial synapses and neurons utilizing the resistive-switching-based devices, 2D ferroelectric-based memories and transistors, ultrafast flash, and promising transistors with attractive structures are highlighted. The device features, performance merits, bottlenecks, and possible improvement strategies, along with large-scale brain-inspired network fulfillment, are presented. Challenges and prospects of system application for neuromorphic computing are briefly discussed, shedding light on its great potential for AI.

Neuromorphic computing: Devices, hardware, and system application facilitated by two-dimensional materials

Vanadium dioxide is an unusual material that undergoes a first-order Metal–Insulator Transition (MIT) at 340 K, attracting considerable interest for its intrinsic properties and its potential applications. However, the nature of MIT has not been fully determined. Variants of density functional theory (DFT) have been widely used to study the MIT in pure and doped VO2. A full description of MIT is complicated by several related factors such as V–V dimerization, magnetic properties, and spin correlations. Each of these requires careful attention. In this Perspective, we explain why DFT fails, introduce a spin-pairing model of MIT, and propose a new way to estimate the transition temperature. We then use the method to study the doping and alloying process. Finally, we give an overview of some applications of MIT. This work aims to provide insight into and stimulate more research studies in this promising field.

/pdf/the-metal-insulator-phase-change-in-vanadium-dioxide-and-its-nvsu6gpc1q.pdf

The metal–insulator phase change in vanadium dioxide and its applications

The von Neumann bottleneck and memory wall have posed fundamental limitations in latency and energy consumption of modern computers based on von Neumann architecture. In-memory computing represents a radical shift in the computer architecture that can address such problems by merging computing functions within the memory itself. In this article, we review the emerging nonvolatile memory devices, such as resistance-based and charge-based memory devices, that are explored for in-memory computing applications. We will provide an overview of the materials, mechanisms, and integration of these devices, and discuss the optimizations at the device and array levels that are required to better support in-memory computing. Recent progress in the application of in-memory computing in artificial neural networks, spiking neural networks, digital logic in memory as well as hardware security will also be discussed. Finally, we will discuss the remaining challenges in this field and potential pathways to address them.

In-memory computing with emerging nonvolatile memory devices

In a digital–analog mixed neuromorphic system, various complex peripheral circuits may offset the integration and energy efficiency advantages of the dense crossbar. To simplify the peripheral circuits, a self-activation neural network (SANN) is proposed based on a passive crossbar array formed by the rectified memristive (ReMem) cell. The ReMem cell is a dual-mode resistive switching device with a VO2/TaO x bilayer structure. It shows a hybrid switching behavior including volatile threshold switching and multilevel nonvolatile resistive switching. This unique feature enables not only simultaneously self-selection and distributed activation, but also weight storage. The concept of SANN is theoretically examined, and a neural network is constructed and trained with SANN based on the proposed devices to perform recognition on handwritten digits in the MNIST database. Compared with neuromorphic computing systems using the CMOS-based activation module and additional selective element, the results show comparable recognition accuracy with reduced circuitry complexity. The proposed SANN can be a promising alternative to realize neural network computing systems with simplified peripheral circuits.

Self-Activation Neural Network Based on Self-Selective Memory Device With Rectified Multilevel States

In this letter, we experimentally demonstrated a novel resistive device with a hybrid switching mode that can be alternated between volatile threshold switching and non-volatile resistive switching. The device consists of dual-functional layers VO2 /HfO2 sandwiched by symmetrical TiN electrodes. A >20 unified ratio for selectivity and memory window is obtained. Owing to the stable resistive behavior of HfO2 and insulator-metal transition of VO2, the device shows excellent uniform switching parameters in both switching modes with a high on-state current density (1E4 A/cm2) and fast switching/recovery speed (< 30 ns). This self-selective resistive memory is of great potential in the high-density crossbar array, particularly for the future 3D-Vertical resistive random access memory (RRAM) integration.

Self-Selective Resistive Device With Hybrid Switching Mode for Passive Crossbar Memory Application

Compressed sensing with a tunable random sampling strategy has great potential in reducing the energy/time consumption during the constant acquisition of external information, thereby it is considered one of the most promising sensing strategies in edge-terminal. In this letter, a novel tunable stochastic oscillator (TSO) based on the VO2/TaOx structure was proposed and employed as the core controlling device for compressed sensing. The TSO is jointly governed by the metal-insulator-transition (IMT) based threshold switching of the VO2 layer and the stochastic resistive switching by the TaOx layer. The tunable memristor/resistor in series can modulate the oscillation frequency of the TSO. The orthogonal matching pursuit (OMP) algorithm is implemented to reconstruct the compressed sparse signals, demonstrating a good performance of TSO in compressed sensing.

Tunable Stochastic Oscillator Based on Hybrid VO₂/TaOₓ Device for Compressed Sensing

The growth of vanadium dioxide (VO2) thin films using tetrakis (ethyl-methyl) amino vanadium (TEMAV) and H2O by atomic layer deposition (ALD) has been investigated as a function of the exposure dose and residence time. A novel multiple pulse mode has been employed to mitigate the small deposition rate brought about by the low vapor pressure of TEMAV. Compared to the conventional ALD cycle with a single pulse of precursor, the use of multiple pulsing with very short pulse time allows lower consumption of precursor, but larger exposure dose and longer residence time on the growth surface, resulting in a higher growth rate for a low volatility precursor, while maintaining a good film uniformity across 4-in. wafers. The Raman analysis and the electrical resistivity modulation of the VO2 thin films show that the films synthesized by the multiple pulse mode is comparable to the films synthesized by the conventional single pulse mode.

/pdf/influence-of-precursor-dose-and-residence-time-on-the-growth-2c5z0uebz1.pdf

Influence of precursor dose and residence time on the growth rate and uniformity of vanadium dioxide thin films by atomic layer deposition

Vanadium dioxide (VO2) thin films were deposited by atomic layer deposition (ALD) using a tetrakis(ethylmethylamino) vanadium precursor and an H2O oxidant at a temperature of 150 °C. Optimization of postdeposition annealing results in smooth, continuous VO2 films (thickness, t ∼ 30 nm) with small grains, exhibiting a transition from semiconducting to metal phase, typically known as the metal-insulator transition (MIT), at ∼72 °C with a switching ratio of ∼102. Such films were produced with high repeatability on a wafer scale and have been successfully utilized in resistively coupled oscillators and self-selected resistive devices. Under a smaller process window, thin films (t ∼ 30 nm) with very large grains have also been produced, exhibiting the MIT ratio of ∼103, which is the highest achieved for the ALD VO2 films deposited on SiO2 substrates. Both types of films were characterized again after 120 days to access their stability in air, a property that was rarely investigated.

/pdf/preparation-of-atomic-layer-deposited-vanadium-dioxide-thin-4mo543tcb7.pdf

Guandong Bai

Papers

Self-Selective Resistive Device With Hybrid Switching Mode for Passive Crossbar Memory Application

Self-Activation Neural Network Based on Self-Selective Memory Device With Rectified Multilevel States

Tunable Stochastic Oscillator Based on Hybrid VO₂/TaOₓ Device for Compressed Sensing

Influence of precursor dose and residence time on the growth rate and uniformity of vanadium dioxide thin films by atomic layer deposition

Preparation of atomic layer deposited vanadium dioxide thin films using tetrakis(ethylmethylamino) vanadium as precursor