A Weighted Sensing Scheme for ReRAM-Based Cross-Point Memory Array

Liu, Chenchen; Li, Hai

doi:10.1109/isvlsi.2014.32

Cited by 28 publications

(12 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sneak path is one of the major concerns in resistive crossbar array design [19,20]. It refers to the intrinsic leakage flowing through unselected cells, which degrades the programming efficiency and the data detection accuracy.…”

Section: T1r Crossbar Arraymentioning

confidence: 99%

A spiking neuromorphic design with resistive crossbar

Liu

Yan

Yang

et al. 2015

Proceedings of the 52nd Annual Design Automation Conference

Self Cite

116

View full text Add to dashboard Cite

Neuromorphic systems recently gained increasing attention for their high computation efficiency. Many designs have been proposed and realized with traditional CMOS technology or emerging devices. In this work, we proposed a spiking neuromorphic design built on resistive crossbar structures and implemented with IBM 130nm technology. Our design adopts a rate coding scheme where pre-and post-neuron signals are represented by digitalized pulses. The weighting function of pre-neuron signals is executed on the resistive crossbar in analog format. The computing result is transferred into digitalized output spikes via an integrate-and-fire circuit (IFC) as the postneuron. We calibrated the computation accuracy of the entire system through circuit simulations. The results demonstrated a good match to our analytic modeling. Furthermore, we implemented both feedforward and Hopfield networks by utilizing the proposed neuromorphic design. The system performance and robustness were studied through massive Monte-Carlo simulations based on the application of digital image recognition. Comparing to the previous crossbar-based computing engine that represents data with voltage amplitude, our design can achieve >50% energy savings, while the average probability of failed recognition increase only 1.46% and 5.99% in the feedforward and Hopfield implementations, respectively.

show abstract

Section: T1r Crossbar Arraymentioning

confidence: 99%

A spiking neuromorphic design with resistive crossbar

Liu

Yan

Yang

et al. 2015

Proceedings of the 52nd Annual Design Automation Conference

Self Cite

116

View full text Add to dashboard Cite

show abstract

“…With the proposed read scheme and low switching power RRAM cell, the stored state of RRAM cell in a 128 × 128 array can be effectively determined even without the selector. This is the largest size among any array presented in literature for 1 R RRAM 1 2 3 6 , even close to among those with 1S1R devices 1 2 3 . Besides, the 1S1R device has low resistance in the range of KΩ at LRS, which consumes ~3 orders of magnitude more power than this 1 R device in MΩ range.…”

Section: Resultsmentioning

confidence: 54%

“…The sneak current is much more severe as the array size increases and it is data pattern dependent. The worst case for usual crosspoint array is when the read cell is at HRS while all other cells are at LRS or vice versa 1 2 3 4 5 6 .…”

mentioning

confidence: 99%

“…To address the sneak path issue, the RRAM devices (1 R) were proposed in series with a diode (1D1R), a transistor (1T1R) and a selector (1S1R) 1 2 3 4 . Other works have been presented which aim on architectural design (device + circuit interaction) to effectively detect the state of RRAM cell in the presence of sneak current 5 6 . In this paper, we present a novel architecture: record large 1 R RRAM array of 128 × 128 is realized with ultra-low read current of 9.7 μA by this scheme, even without selector device.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Novel Read Scheme for Large Size One-Resistor Resistive Random Access Memory Array

Zackriya

Kittur

Chin

2017

Sci Rep

View full text Add to dashboard Cite

The major issue of RRAM is the uneven sneak path that limits the array size. For the first time record large One-Resistor (1R) RRAM array of 128x128 is realized, and the array cells at the worst case still have good Low-/High-Resistive State (LRS/HRS) current difference of 378 nA/16 nA, even without using the selector device. This array has extremely low read current of 9.7 μA due to both low-current RRAM device and circuit interaction, where a novel and simple scheme of a reference point by half selected cell and a differential amplifier (DA) were implemented in the circuit design.

show abstract

“…The selector is a nonlinear device, the resistance of which ranges approximately from 10 3 Ω to 10 13 Ω. When the applied voltage is lower than V th of the integrate capacitor, the selector resistance is more than 10 9 Ω, which is much larger than the memristance range of 10 4 Ω ∼ 10 6 Ω [14]. As a result, the sneak path leakage can be well controlled.…”

Section: Memristor Crossbar Array Structurementioning

confidence: 99%

Spiking-based matrix computation by leveraging memristor crossbar array

Liu

Yan

et al. 2015

2015 IEEE Symposium on Computational Intelligence for Security and Defense Applications (CISDA)

Self Cite

View full text Add to dashboard Cite

As process technology continues scaling down, the memory barrier becomes more severe. Thus, spiking neuromorphic computing that can significantly enhance computing and communication efficiencies has been widely studied. Both conventional CMOS technology and emerging devices have been used in hardware implementation of spiking neuromorphic computing. Particularly, the memristor technology that can naturally emulate plasticity and energy efficiency of biological synapses have gained a lot of attention. However, the use of memristors in high density computation, such as matrix-vector operation, is still missing. In this work, a spiking (pulse-based) computing component that leverages memristor crossbar array is proposed for matrix-vector operation. We adopt the rate coding model and count the produced spike number during a given time period of T as the computation output. We carefully design the crossbar array structure and the integrate-and-fire circuit. The linear relationship between output spike numbers and the sum-ofproduction of input vector and matrix entries is observed in our simulation results. The proposed spiking computing design realizes matrix computation successfully and demonstrates good adaptability in neural network.

show abstract

A Weighted Sensing Scheme for ReRAM-Based Cross-Point Memory Array

Cited by 28 publications

References 25 publications

A spiking neuromorphic design with resistive crossbar

A spiking neuromorphic design with resistive crossbar

A Novel Read Scheme for Large Size One-Resistor Resistive Random Access Memory Array

Spiking-based matrix computation by leveraging memristor crossbar array

Contact Info

Product

Resources

About