Embedded emerging memory technologies for neuromorphic computing: temperature instability and reliability

Chang, Yao‐Feng; Karpov, I. V.; Hopkins, Robin; Janosky, David; Medeiros, Jacob; Sherrill, Benjamin; Zhang, Jiahan; Huang, Yifu; Pramanik, Tanmoy; Chen, Albert; Acosta, Tony; Guler, Abdullah; O'Donnell, James A.; Quintero, Pedro A.; Strutt, Nathan; Golonzka, O.; Connor, Chris; Lee, Jack C.; Hicks, J.

doi:10.1109/irps46558.2021.9405120

Cited by 7 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RRAM macro exhibited a linear growth of conductance through modulation of the voltage sweep. With the sweeping voltage greater than 0.8 V, the conductance continuously changed from 10 µS to 240 µS, indicating a linear relationship between conductivity and applied voltage, thereby enabling uniform steps within a specific range [163]. However, the accuracy of neuromorphic devices and neural networks can be impacted by device instability at high temperatures.…”

Section: Advancements In Mature Embedded Rram Chip Technologymentioning

confidence: 99%

Advances of embedded resistive random access memory in industrial manufacturing and its potential applications

Wang,

Song,

Zhang

et al. 2024

Int. J. Extrem. Manuf.

View full text Add to dashboard Cite

Embedded memory, which heavily relies on the manufacturing process, has been widely adopted in various industrial applications. As the field of embedded memory continues to evolve, innovative strategies are emerging to enhance performance. Among them, resistive random access memory (RRAM) has gained significant attention due to its numerous advantages over traditional memory devices, including high speed (<1ns), high density (4F2/n), high scalability (~nm), and low power consumption (~pJ). This review focuses on the recent progress of embedded RRAM in industrial manufacturing and its potential applications. It provides a brief introduction to the concepts and advantages of RRAM, discusses the key factors that impact its industrial manufacturing, and presents the commercial progress driven by cutting-edge nanotechnology, which has been pursued by many semiconductor giants. Additionally, it highlights the adoption of embedded RRAM in emerging applications within the realm of the Internet of Things (IoT) and future intelligent computing, with a particular emphasis on its role in neuromorphic computing. Finally, the review discusses the current challenges and provides insights into the prospects of embedded RRAM in the era of big data and artificial intelligence (AI).

show abstract

Section: Advancements In Mature Embedded Rram Chip Technologymentioning

confidence: 99%

Advances of embedded resistive random access memory in industrial manufacturing and its potential applications

Wang,

Song,

Zhang

et al. 2024

Int. J. Extrem. Manuf.

View full text Add to dashboard Cite

show abstract

“…A potential issue for RRAM-based IMC is the limited precision of conductance, which is affected by programming variations [12], [13], random telegraph noise (RTN) [14], drift [15], and other types of random fluctuations [16], [17]. Additionally, reliability concerns at array-level such as conductance relaxation over time [18] and temperature instability [19] also challenge the achievement of a stable and high accuracy in RRAM-based IMC. Multilevel-cell (MLC) program/verify techniques have been proposed to overcome the variability effects and improve the precision of conductance in RRAM [20]- [23].…”

Section: Introductionmentioning

confidence: 99%

Accurate Program/Verify Schemes of Resistive Switching Memory (RRAM) for In-Memory Neural Network Circuits

Milo

Glukhov

Pérez

et al. 2021

IEEE Trans. Electron Devices

View full text Add to dashboard Cite

Resistive switching memory (RRAM) is a promising technology for embedded memory and their application in computing. In particular, RRAM arrays can provide a convenient primitive for matrix-vector multiplication (MVM) with strong impact on the acceleration of neural networks for artificial intelligence (AI). At the same time, RRAM is affected by intrinsic conductance variations which might cause a degradation of accuracy in AI inference hardware. This work provides a detailed study of the multilevel-cell (MLC) programming of RRAM for neural network applications. We compare three MLC programming schemes and discuss their variations in terms of the different slope in the programming characteristics. We test the accuracy of a 2layer fully-connected neural network (FC-NN) as a function of the MLC scheme, the number of weight levels, and the weight mapping configuration. We find a trade-off between the FC-NN accuracy, size and current consumption. This work highlights the importance of a holistic approach to AI accelerators encompassing the device properties, the overall circuit performance, and the AI application specifications. Index Terms-Resistive switching memory (RRAM); multilevel cell (MLC) operation; artificial neural network (ANN); in-memory computing (IMC).

show abstract

“…1,2 In addition, the emerging memristive technologies as called ReRAM (resistive random-access memory), have shown that both advanced CMOS node implementation (beyond 14 nm FeFET) and capability for multilevel cell (MLC) application (enabling the flexibility of weighting modulation as synaptic device) by precise electrical control of the filament growth. 3,4 This opens an opportunity for embedded memory and further applications, 5 e.g., neuromorphic computing, which takes inspiration from the high parallelism in the human brain, low power, high speed, and noise-tolerant computing capabilities.…”

mentioning

confidence: 99%

Bifunctional HfOx-based Resistive Memory: Reprogrammable and One-Time Programmable (OTP) Memory

Chen¹,

Chang²,

Lin³

et al. 2022

ECS J. Solid State Sci. Technol.

View full text Add to dashboard Cite

The dual functions in HfOx-based ReRAM and 2V-programmable via-fuse technology featuring in simple metal-insulator-metal BEOL process are presented, which can integrate with the current metal fuse technology. The impact of via-size, ReRAM, and via-fusing programming windows, stacked structures, and integration capability has been extensively studied. The performance and reliability risk assessments show that the ReRAM and via fuse can sustain at 438 K for 500 hours without any degradation. Our results provide pathfinding of high density, integration capability, low programing voltage, multi-functionality between programmable read-only memory (PROM) and ReRAM co-existing in embedded applications.

show abstract

Embedded emerging memory technologies for neuromorphic computing: temperature instability and reliability

Cited by 7 publications

References 16 publications

Advances of embedded resistive random access memory in industrial manufacturing and its potential applications

Advances of embedded resistive random access memory in industrial manufacturing and its potential applications

Accurate Program/Verify Schemes of Resistive Switching Memory (RRAM) for In-Memory Neural Network Circuits

Bifunctional HfOx-based Resistive Memory: Reprogrammable and One-Time Programmable (OTP) Memory

Contact Info

Product

Resources

About