Demonstration of a Multi-Level μA-Range Bulk Switching ReRAM and its Application for Keyword Spotting
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
Despite the great promises of resistive random-access memory (ReRAM) for fast, low-power in memory computing, the models deployed on ReRAM crossbars suffer from accuracy loss, due to poor yield, inaccurate switching and high noise. In this paper, we report a forming-free bulk ReRAM (b-ReRAM) cell that can be programmed up to 128 levels between 400nA $(4\mu \mathrm{S})$ and $4\mu A (40\mu S)$. The device operates by continuous modulation of bulk oxygen vacancies, therefore exhibiting favorable characteristics including forming-free operation, analog switching, low noise and low operating currents [1], [2]. The multilayer ReRAM stack is deposited using a specially built 300mm deposition system that features a clustered sequence of Physical Vapor Deposition (PVD) and Atomic Layer Deposition (ALD), leading to high wafer-level yield and uniformity. High programming accuracy can be achieved over 25k b-ReRAM devices across 15 dies. A fully integrated system on chip (SoC) with BEOL-integrated b-ReRAM arrays is built with 65nm CMOS technology, and keyword spotting (KWS) is demonstrated with accuracy equivalent to the software quantized model and high energy efficiency at 98.5 TOPS/W. Moreover, we evaluate the performance of the bitcell for large neural network (NN) applications in a custom hardware-aware simulation platform and show that software comparable accuracy can be achieved. This work for the first-time reports that high yield and high programming accuracy can be achieved with b-ReRAM at the wafer-level scale and demonstrates that superior analog behavior enables the mapping of NN models onto the ReRAM-based SoC prototype with no accuracy loss and high energy efficiency.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Few studies went beyond that and built/characterized crossbar arrays of memristive devices48,68–70, but that are still very far from real full-hardware implementations of all the mathematical operations required by the ANN.”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [48]
In the citing paper
“the possibility to program multiple non-volatile states (up to ~10047,48, and even ~100049)”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [48]
In the citing paper
“The most advanced studies in this field have reported fully integrated memristor-based compute-in-memory systems48,53–55,58,59,61,71–73, but a systematic description of essential details on the device structure or circuit architecture are generally lacking in these reports.”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [48]
Citations
Cites
2021 IEEE International Electron Devices Meeting (IEDM)
(2021) · doi:10.1109/iedm19574.2021 · Cited by 197
Research works printed but not linked: 8
- Li, 2020, Adv. Mater.
- Wang, IEEE International Electron Devices Meeting (IEDM)
- Lee, 2011, Nat. Mater.
- Yang, 2012, Nat. Commun.
- Kim, 2015, Adv. Funct. Mater.
- Jeong, 2017, IEEE Trans. on Nanotechnol.
- Cai, 2022, Adv. Intell. Syst.
- Wang, IEEE international electron devices meeting (IEDM)
Cited by
Hardware implementation of memristor-based artificial neural networks
Aguirre, F., Sebastian, A., Le Gallo, M., Song, W., Wang, T., Yang, J. J., Lu, W., Chang, M.-F., Ielmini, D., Yang, Y., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-45670-9 · Cited by 564
“Few studies went beyond that and built/characterized crossbar arrays of memristive devices 48,68 – 70 , but that are still very far from real full-hardware implementations of all the mathematical operations required by the ANN.”
InfluentialSelf-citationPark, J., Kumar, A., Zhou, Y., Oh, S., Kim, J. H., Shi, Y., Jain, S., Hota, G., Qiu, E., Nagle, A. L., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-46682-1 · Cited by 171
“The bulk switching shows the opposite polarity to the fi lamentary switching consistent with other previous reports 23,42 .”
Self-citationTrue random number generation using the spin crossover in LaCoO3
Woo, K. S., Zhang, A., Arabelo, A. K., Brown, T. D., Park, M., Talin, A. A., Fuller, E. J., Bisht, R. S., Qian, X., Arróyave, R., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-49149-5 · Cited by 60
“Using such memristor crossbars to accelerate optimization with a Hop fi eld network has been discussed in detail 32 , and the chip and supporting hardware are detailed elsewhere 37,38 .”
Self-citationAn 8-bit 20.7 TOPS/W Multilevel Cell ReRAM Macro With ADC-Assisted Bit-Serial Processing
Correll, J. M., Jie, L., Song, S., Lee, S., Zhu, J., Tang, W., Wormald, L. D., Erhardt, J., Breil, N., Quon, R. A., et al. (2025) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2025.3540114 · Cited by 18
“However, the design has only one low-precision ADC and does not use pitch-matching, and therefore is not optimized for future many-bits-per-cell ReRAM programming [14], [15] or overall resource amortization.”
Self-citationSafe, secure and trustworthy compute-in-memory accelerators
Wang, Z., Wu, Y., Park, Y., & Lu, W. D. (2024) · Nature Electronics · doi:10.1038/s41928-024-01312-y · Cited by 20
“…attacks can have severe consequences in applications such Perspective https://doi.org/10.1038/s41928-024-01312-y efforts have been devoted to material and device engineering to achieve fast switching 33,34 , multilevel storage 35,36 , low-power operation 37,38 and high-density integration 12,39 .”
InfluentialSelf-citation
Metadata
- Authors
- Wu, Y., Cai, F., Thomas, L., Liu, T., Nourbakhsh, A., Hebding, J., Smith, E., Quon, R., Smith, R., Kumar, A., Pang, A., Holt, J., Someshwar, R., Nardi, F., Anthis, J., Yen, S.-H., Chevallier, C., Uppala, A., Chen, X., Breil, N., Sherwood, T., Wong, K., Cho, W., Thompson, D., Hsu, J., Ayyagari, B., Krishnan, S., Lu, W. D., & Chudzik, M.
- Affiliations
- Applied Materials (United States) (US)
- University of Michigan (US)
- Venue
- 2022 International Electron Devices Meeting (IEDM)
- Publisher
- IEEE
- Published
- 2022-12-03
- Pages
- 18.4.1-18.4.4
- ISSN
- 0163-1918 (ISSN-L)
- OpenAlex
- W4317792971
- Cited by
- 8
- References
- 1
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 4
- FWCI
- 2.83
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Technical digest - International Electron Devices Meeting/Technical digest (publishedVersion)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Ferroelectric and Negative Capacitance Devices
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Low-power high-performance VLSI design
- Keywords
- resistive random access memory, multi-level cell, forming-free operation, oxygen vacancies, analog switching, keyword spotting, BEOL integration, energy efficiency
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Demonstration of a Multi-Level μA-Range Bulk Switching ReRAM and its Application for Keyword Spotting. https://app.cochat.ai/papers/10.1109/iedm45625.2022.10019450
- The paper
- Wu, Y., Cai, F., Thomas, L., Liu, T., Nourbakhsh, A., Hebding, J., Smith, E., Quon, R., Smith, R., Kumar, A., Pang, A., Holt, J., Someshwar, R., Nardi, F., Anthis, J., Yen, S.-H., Chevallier, C., Uppala, A., Chen, X., . . . Chudzik, M. (2022). Demonstration of a Multi-Level μA-Range Bulk Switching ReRAM and its Application for Keyword Spotting. 2022 International Electron Devices Meeting (IEDM). https://doi.org/10.1109/iedm45625.2022.10019450
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.