EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Triple‐Level Content‐Addressable Vertical NAND Flash Memory

Sung-Ho Park iD, Jiseong Im, Yeongheon Yang, Ryun-Han Koo, Jonghyun Ko, Mingyun Oh iD, Dongbeen Shin iD, Gyuweon Jung iD, Jong-Ho Lee iD

Advanced Science · 2026-11 · 13 (61)

DOI: 10.1002/advs.77390 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 24.08.2026. Verfasst von Sung-Ho Park und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering and Inter-University Semiconductor Research Center, Seoul National University, Seoul, Republic of K…. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Seoul National University, National Research Foundation of Korea, SK hynix Inc..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Content‐addressable memory (CAM) enables massively parallel search by directly comparing input data with stored entries, offering a powerful paradigm for accelerating data‐intensive tasks. Here, we present a triple‐level content‐addressable vertical NAND flash memory (V‐NAND TLCAM) that exploits the eight threshold‐voltage states of commercial triple‐level‐cell (TLC) V‐NAND flash devices to achieve compact, high‐throughput, and energy‐efficient in‐memory search. A parity‐split (PS) scheme, in which odd and even word‐lines are accessed separately, enhances the sensing margin and mitigates worst‐case errors while preserving storage density and supporting don't‐care matching. Measurements on >100‐layer TLC V‐NAND flash memory confirm stable operation with up to a 24× improvement in read‐operation throughput and a 54.4× reduction in the estimated read energy compared with conventional readout. Furthermore, few‐shot learning simulations on the Omniglot dataset demonstrate that the proposed TLCAM maintains over 90% accuracy in 5‐shot learning, approaching GPU‐based cosine similarity baselines. These results highlight V‐NAND TLCAM as a scalable and energy‐efficient hardware platform for bridging device‐level innovations with practical machine learning applications.

Schlagwörter

Stichwörter der Autor:innen

V‐NAND flash memorycontent‐addressable memoryfew‐shot learning

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering and Inter-University Semiconductor Research Center, Seoul National University, Seoul, Republic of Korea.
  • Research and Development Division, SK Hynix Inc., Icheon, Republic of Korea.

ORCID-Profile: Sung-Ho Park, Mingyun Oh, Dongbeen Shin, Gyuweon Jung, Jong-Ho Lee

Förderung

  • Seoul National University
  • National Research Foundation of Korea
  • SK hynix Inc.

Zitieren

APA

Park, S. H., Im, J., Yang, Y., Koo, R. H., Ko, J., Oh, M., Shin, D., Jung, G., & Lee, J. H. (2026). Triple‐Level Content‐Addressable Vertical NAND Flash Memory. Advanced Science, 13(61). https://doi.org/10.1002/advs.77390

Vancouver

Park SH, Im J, Yang Y, Koo RH, Ko J, Oh M, et al. Triple‐Level Content‐Addressable Vertical NAND Flash Memory. Advanced Science. 2026;13(61). doi:10.1002/advs.77390

BibTeX
@article{Park2026,
  author = {Park, Sung-Ho and Im, Jiseong and Yang, Yeongheon and Koo, Ryun-Han and Ko, Jonghyun and Oh, Mingyun and Shin, Dongbeen and Jung, Gyuweon and Lee, Jong-Ho},
  title = {Triple‐Level Content‐Addressable Vertical NAND Flash Memory},
  journal = {Advanced Science},
  year = {2026},
  volume = {13},
  number = {61},
  doi = {10.1002/advs.77390}
}
Kostenlos starten →