Abstract
In this article, the design of a novel 3D-NAND-based content addressable memory (CAM) consisting of two flash transistors with ultra-high density and low power consumption is proposed for data-intensive computing. Hewlett simulation program with integrated circuit emphasis (HSPICE) of a 3D-NAND-based CAM array is performed to study the functionality and properties of the presented CAM design, and the results indicate that the energy consumption is 0.196 fJ/bit/search. The cell density of a 16-layer 3D-NAND flash is 157 times higher than CAMs based on conventional static random access memory. Furthermore, to exploit the multibit storage property of 3D-NAND flash, we also propose a multilevel CAM design, which significantly boosts the cell density and expands the functionality. As a proof-of-concept illustration, we take a 4-level CAM to successfully implement the search operation. Furthermore, the impacts of 3D-NAND layers and parasitic effects on the performance of the proposed CAM design are also discussed.
Similar content being viewed by others
References
Thangam M S, Vijayalakshmi M. Data-intensive computation offloading using fog and cloud computing for mobile devices applications. In: Proceedings of International Conference on Smart Systems and Inventive Technology, Tirunelveli, 2018. 547–550
Jonathan A, Ryden M, Oh K, et al. Nebula: distributed edge cloud for data intensive computing. IEEE Trans Parallel Distrib Syst, 2017, 28: 3229–3242
Zhang X Y, Liu C L, Suen C Y. Towards robust pattern recognition: a review. Proc IEEE, 2020, 108: 894–922
Ye Q, Doermann D. Text detection and recognition in imagery: a survey. IEEE Trans Pattern Anal Mach Intell, 2014, 37: 1480–1500
Nielen L, Siemon A, Tappertzhofen S, et al. Study of memristive associative capacitive networks for CAM applications. IEEE J Emerg Sel Top Circ Syst, 2015, 5: 153–161
Zheng L, Shin S, Steve Kang S M. Memristor-based ternary content addressable memory (mTCAM) for data-intensive computing. Semicond Sci Technol, 2014, 29: 104010
Huang P T, Lai S L, Chuang C T, et al. 0.339 fJ/bit/search energy-efficient TCAM macro design in 40 nm LP CMOS. In: Proceedings of Asian Solid-State Circuits Conference, KaoHsiung, 2014. 129–132
Pagiamtzis K, Sheikholeslami A. Content-addressable memory (CAM) circuits and architectures: a tutorial and survey. IEEE J Solid-State Circ, 2006, 41: 712–727
El Baraji M, Javerliac V, Prenat G. Towards an ultra-low power, high density and non-volatile ternary cam. In: Proceedings of Non-Volatile Memory Technology Symposium, Pacific Grove, 2008. 1–7
Imani M, Peroni D, Rahimi A, et al. Resistive CAM acceleration for tunable approximate computing. IEEE Trans Emerg Top Comput, 2019, 7: 271–280
Karam R, Puri R, Ghosh S, et al. Emerging trends in design and applications of memory-based computing and content-addressable memories. Proc IEEE, 2015, 103: 1311–1330
Li J, Montoye R, Ishii M, et al. 1 Mb 0.41 µm2 2T-2R cell nonvolatile TCAM with two-bit encoding and clocked self-referenced sensing. In: Proceedings of Symposium on VLSI Technology, Kyoto, 2013. 104–105
Han R, Shen W, Huang P, et al. A novel ternary content addressable memory design based on resistive random access memory with high intensity and low search energy. Jpn J Appl Phys, 2018, 57: 04FE02
Chen B, Zhang Y, Liu W, et al. Ge-based asymmetric RRAM enable 8F2 content addressable memory. IEEE Electron Device Lett, 2018, 39: 1294–1297
Zheng L, Shin S, Lloyd S, et al. RRAM-based TCAMs for pattern search. In: Proceedings of International Symposium on Circuits and Systems, Montreal, 2016. 1382–1385
Grossi A, Vianello E, Zambelli C, et al. Experimental investigation of 4-kb RRAM arrays programming conditions suitable for TCAM. IEEE Trans VLSI Syst, 2018, 26: 2599–2607
Yin X, Li C, Huang Q, et al. FeCAM: a universal compact digital and analog content addressable memory using ferroelectric. IEEE Trans Electron Dev, 2020, 67: 2785–2792
Tan A J, Chatterjee K, Zhou J, et al. Experimental demonstration of a ferroelectric HfO -based content addressable memory cell. IEEE Electron Device Lett, 2019, 41: 240–243
Ni K, Yin X, Laguna A F, et al. Ferroelectric ternary content-addressable memory for one-shot learning. Nat Electron, 2019, 2: 521–529
Wang C, Zhang D, Zeng L, et al. Design of magnetic non-volatile TCAM with priority-decision in memory technology for high speed, low power, and high reliability. IEEE Trans Circ Syst I, 2020, 67: 464–474
Gupta M K, Hasan M. Robust high speed ternary magnetic content addressable memory. IEEE Trans Electron Dev, 2015, 62: 1163–1169
Xu W, Zhang T, Chen Y. Design of spin-torque transfer magnetoresistive RAM and CAM/TCAM with high sensing and search speed. IEEE Trans VLSI Syst, 2009, 18: 66–74
Miwa T, Yamada H, Hirota Y, et al. A 1 Mb 5-transistor/bit non-volatile CAM based on flash-memory technologies. In: Proceedings of International Solid-State Circuits Conference, San Francisco, 1996. 40–41
Kramer A, Canegallo R, Chinosi M, et al. 55 GCPS CAM using 5b analog flash. In: Proceedings of International Solid-State Circuits Conference, San Francisco, 1997. 44–45
Fedorov V V, Abusultan M, Khatri S P. An area-efficient ternary CAM design using floating gate transistors. In: Proceedings of International Conference on Computer Design, Seoul, 2014. 55–60
Wang F, Feng Y, Zhan X, et al. Implementation of data search in multi-level NAND flash memory by complementary storage scheme. IEEE Electron Dev Lett, 2020, 41: 1189–1192
Suh K D, Suh B H, Lim Y H, et al. A 3.3 V 32 Mb NAND flash memory with incremental step pulse programming scheme. IEEE J Solid-State Circ, 1995, 30: 1149–1156
Kang D, Kim M, Jeon S C, et al. A 512 Gb 3-bit/Cell 3D 6th-Generation V-NAND flash memory with 82 MB/s write throughput and 1.2 Gb/s interface. In: Proceedings of International Solid-State Circuits Conference, San Francisco, 2019. 216–218
Yang H Z, Huang P, Han R Z, et al. A novel high-density and low-power ternary content addressable memory design based on 3D NAND flash. In: Proceedings of Silicon Nanoelectronics Workshop, Honolulu, 2020. 29–30
Lue H T, Du P Y, Chen W C, et al. A 128 Gb (MLC)/192 Gb (TLC) single-gate vertical channel (SGVC) architecture 3D NAND using only 16 layers with robust read disturb, long-retention and excellent scaling capability. In: Proceedings of International Electron Devices Meeting, San Francisco, 2017
Wang P, Xu F, Wang B, et al. Three-dimensional NAND flash for vector-matrix multiplication. IEEE Trans VLSI Syst, 2018, 27: 988–991
Lee S H, Kwon D W, Kim S, et al. Investigation of transient current characteristics with scaling-down poly-Si body thickness and grain size of 3D NAND flash memory. Solid-State Electron, 2019, 152: 41–45
Cho J, Kang D C, Park J, et al. A 512Gb 3b/cell 7th-generation 3D-NAND flash memory with 184 MB/s write throughput and 2.0 Gb/s interface. In: Proceedings of International Solid-State Circuits Conference, San Francisco, 2021. 426–428
Lee S, Kim C, Kim M, et al. A 1 Tb 4b/cell 64-stacked-WL 3D NAND flash memory with 12 MB/s program throughput. In: Proceedings of International Solid-State Circuits Conference, San Francisco, 2018. 340–342
Cai Y, Haratsch E F, Mutlu O, et al. Threshold voltage distribution in MLC NAND flash memory: characterization, analysis, and modeling. In: Proceedings of Design, Automation & Test in Europe Conference & Exhibition, Grenoble, 2013. 1285–1290
Arsovski I, Hebig T, Dobson D, et al. A 32 nm 0.58-fJ/Bit/search 1-GHz ternary content addressable memory compiler using silicon-aware early-predict late-correct sensing with embedded deep-trench capacitor noise mitigation. IEEE J Solid-State Circ, 2013, 48: 932–939
Siau C, Kim K H, Lee S, et al. A 512 Gb 3-bit/cell 3D flash memory on 128-wordline-layer with 132 MB/s write performance featuring circuit-under-array technology. In: Proceedings of International Solid-State Circuits Conference, San Francisco, 2019. 218–220
Tseng P H, Lee F M, Lin Y H, et al. In-memory-searching architecture based on 3D-NAND technology with ultra-high parallelism. In: Proceedings of International Electron Devices Meeting, San Francisco, 2020
Wang K L, Du G, Lun Z Y, et al. Modeling of program Vth distribution for 3-D TLC NAND flash memory. Sci China Inf Sci, 2019, 62: 042401
Pedretti G, Graves C E, Serebryakov S, et al. Tree-based machine learning performed in-memory with memristive analog CAM. Nat Commun, 2021, 12: 1
Kazemi A, Sharifi M M, Laguna A F, et al. In-memory nearest neighbor search with FeFET multi-bit content-addressable memories. In: Proceedings of Design, Automation & Test in Europe Conference & Exhibition, Grenoble, 2021. 1084–1089
Li H T, Chen W C, Levy A, et al. One-shot learning with memory-augmented neural networks using a 64-kbit, 118 GOPS/W RRAM-based non-volatile associative memory. In: Proceedings of Symposium on VLSI Technology, Kyoto, 2021. 1–2
Acknowledgements
This work was supported in part by National Key Research and Development Program of China (Grant Nos. 2019YFB2205100, 2018YFA0701500), National Natural Science Foundation of China (Grant No. 62034006), and 111 Project Program (Grant No. B18001).
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Yang, H., Huang, P., Han, R. et al. An ultra-high-density and energy-efficient content addressable memory design based on 3D-NAND flash. Sci. China Inf. Sci. 66, 142402 (2023). https://doi.org/10.1007/s11432-021-3502-4
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-021-3502-4