A high-speed MIM resistive memory cell with an inherent vanadium selector

Lin, Chih-Yang; Tseng, Yi-Ting; Chen, Po-Hsun; Chang, Ting‐Chang; Eshraghian, Jason K.; Wang, Qiwen; Lin, Qi; Tan, Yung‐Fang; Tai, Mao‐Chou; Hung, Wei‐Chun; Huang, Hui‐Chun; Lü, Wei; Sze, Simon M.

doi:10.1016/j.apmt.2020.100848

Cited by 13 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…14–18 Vanadium oxides are of particular interest due to these materials provide outstanding advantages in many optoelectronic devices, such as smart windows, 19–21 sensors, 22–24 and resistive memories. 25–29 They have received considerable attention since they are studied as a metal–insulator transition (MIT) material. 30–34 The MIT can be induced by increasing the temperature/pressure, which causes changes to the structural, electronic, electrical, and optical properties of the materials.…”

Section: Introductionmentioning

confidence: 99%

Insights into first-principles characterization of the monoclinic VO₂(B) polymorph via DFT + U calculation: electronic, magnetic and optical properties

et al. 2022

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Insights into first-principles characterization of the monoclinic VO₂(B) polymorph via DFT + U calculation: electronic, magnetic and optical properties

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Memristors are now ubiquitous in neuromorphic computing literature due to their long retention [2]- [4], excellent scalability [5], [6], fast read and write speeds [7], [8], compatibility with CMOS technology [9]- [12], and precise weight updates [13], [14]. The development of dense integrated structures with 3-D stacked crossbar arrays enables an increase in the throughput for a given chip area, but thus far, target applications of 3-D RRAM have mostly been limited to digital memory [16]- [23].…”

Section: Introductionmentioning

confidence: 99%

A 3-D Reconfigurable RRAM Crossbar Inference Engine

Eshraghian

Cho

Kang

2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

Self Cite

View full text Add to dashboard Cite

Deep neural network inference accelerators are rapidly growing in importance as we turn to massively parallelized processing beyond GPUs and ASICs. The dominant operation in feedforward inference is the multiply-and-accumlate process, where each column in a crossbar generates the current response of a single neuron. As a result, memristor crossbar arrays parallelize inference and image processing tasks very efficiently. In this brief, we present a 3-D active memristor crossbar array 'CrossStack', which adopts stacked pairs of Al/TiO 2/TiO2 -x/Al devices with common middle electrodes. By designing CMOS-memristor hybrid cells used in the layout of the array, CrossStack can operate in one of two user-configurable modes as a reconfigurable inference engine: 1) expansion mode and 2) deep-net mode. In expansion mode, the resolution of the network is doubled by increasing the number of inputs for a given chip area, reducing IR drop by 22%. In deep-net mode, inference speed per-10-bit convolution is improved by 29% by simultaneously using one TiO 2/TiO2 -x layer for read processes, and the other for write processes. We experimentally verify both modes on our 10 × 10 × 2 array.Index Terms-deep learning, in-memory computing, memristors, neural network, RRAM.

show abstract

Controlling Threshold and Resistive Switch Functionalities in Ag‐Incorporated Organometallic Halide Perovskites for Memristive Crossbar Array

Kim

Baek

et al. 2022

Adv Funct Materials

View full text Add to dashboard Cite

Halide perovskites (HPs) can be the effective functional materials for the sneak-path current issue in the memristive crossbar array. Herein, an efficient strategy is proposed to integrate the HPs-based bidirectional threshold and bipolar resistive switches (TS and RS). The resistance change characteristics from volatile threshold to nonvolatile resistive switching are modulated by controlling Ag doping concentration in the MAPbI 3 . HPs provide the diffusive condition and the quantity of Ag regulates the radius of its network. A low amount of Ag contributes to weak network with a short lifetime. However, when the amount of Ag increases, the conductive filament becomes more robust, showing a long lifetime. A MAPbI 3 :Ag TS with a low Ag content is developed, showing a steep switching slope (1 mV per decade), fast switching speed (< 80 ns), and low off-current (10 nA). And, a MAPbI 3 :Ag RS with a high Ag content is developed, showing multilevel storage capability and long retention time (1400 s). Finally, these TS and RS coupled into the 1S-1R integrated component, resulting the development of the maximum crossbar array size to 1.4 × 10 12 . This study offers an efficient methodology for tailoring the resistance change characteristics and a promising strategy for practical HPs-based memristive crossbar application.

show abstract

A high-speed MIM resistive memory cell with an inherent vanadium selector

Cited by 13 publications

References 41 publications

Insights into first-principles characterization of the monoclinic VO₂(B) polymorph via DFT + U calculation: electronic, magnetic and optical properties

Insights into first-principles characterization of the monoclinic VO₂(B) polymorph via DFT + U calculation: electronic, magnetic and optical properties

A 3-D Reconfigurable RRAM Crossbar Inference Engine

Controlling Threshold and Resistive Switch Functionalities in Ag‐Incorporated Organometallic Halide Perovskites for Memristive Crossbar Array

Contact Info

Product

Resources

About

A high-speed MIM resistive memory cell with an inherent vanadium selector

Cited by 13 publications

References 41 publications

Insights into first-principles characterization of the monoclinic VO2(B) polymorph via DFT + U calculation: electronic, magnetic and optical properties

Insights into first-principles characterization of the monoclinic VO2(B) polymorph via DFT + U calculation: electronic, magnetic and optical properties

A 3-D Reconfigurable RRAM Crossbar Inference Engine

Controlling Threshold and Resistive Switch Functionalities in Ag‐Incorporated Organometallic Halide Perovskites for Memristive Crossbar Array

Contact Info

Product

Resources

About

Insights into first-principles characterization of the monoclinic VO₂(B) polymorph via DFT + U calculation: electronic, magnetic and optical properties

Insights into first-principles characterization of the monoclinic VO₂(B) polymorph via DFT + U calculation: electronic, magnetic and optical properties