3D NAND闪存P/E次数的快速测评与寿命预测

HTML

PDF (PC)

3D NAND闪存P/E次数的快速测评与寿命预测

Rapid Measurement and Lifetime Prediction of 3D NAND Flash P/E Cycles

3D NAND闪存P/E次数的快速测评与寿命预测

Rapid Measurement and Lifetime Prediction of 3D NAND Flash P/E Cycles

摘要/Abstract

参考文献

Metrics

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

Metrics

本文评价

推荐阅读 0

doi:10.12052/gdutxb.240023

广东工业大学学报 ›› 2024, Vol. 41 ›› Issue (06): 52-59.doi: 10.12052/gdutxb.240023

• 集成电路科学与工程 • 上一篇

罗铮, 韩国军

广东工业大学信息工程学院, 广东广州 510006

收稿日期:2024-02-06 发布日期:2024-12-31
通信作者: 韩国军(1974-),男,教授,主要研究方向为信息论与差错控制编译码技术、存储器件与系统、智能通信与车联网等,E-mail:gjhan@gdut.edu.cn
作者简介:罗铮(1999-),男,硕士研究生,主要研究方向为3D NAND闪存错误特性,E-mail:1145806026@qq.com
基金资助:
NSFC-广东省联合基金项目(U2001203)

Luo Zheng, Han Guo-jun

School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China

Received:2024-02-06 Published:2024-12-31

摘要： 基于3D三层单元NAND闪存的固态硬盘由于存储密度高、每比特成本低，正逐渐成为大规模存储系统中占主导地位的存储介质。随着技术的发展，3D NAND闪存芯片的存储密度越来越高，可靠性也越来越差。可靠性的降低和厂商制定寿命标称值过于保守导致闪存芯片在未达到实际寿命前被过早地淘汰，造成不必要的浪费。通过机器学习预测模型对闪存芯片进行寿命预测可以优化存储策略，有效延长寿命并减少损失。然而因生产工艺差异，导致闪存芯片之间的错误特性有一定的不同，会影响对闪存芯片寿命预测的准确度。本文经过实验发现数据保留错误的误比特率可用来表征擦/写次数，并提出通过将相邻字线写入特定内容的方法激励字线间干扰，可有效减少耗时并提高寿命预测准确率，经验证可缩短耗时约90.9%，预测准确率可提高33.3个百分点。

关键词: 3D闪存, 寿命预测, 数据保留错误, 字线间干扰, 支持向量机

Abstract: Solid State Disks based on 3D triple cell NAND flash has becoming a dominant storage medium in mass storage systems due to their high storage density and low cost per bit. With the rapid development of technologies, 3D NAND flash chips are becoming less reliable with high storage densities. Reduced reliability and overly conservative manufacturers' formulation of lifetime nominal values result in flash chips being prematurely phased out before reaching their actual lifespan with unnecessary waste. Lifetime prediction of flash chips through machine learning-based prediction models can optimize storage strategies to effectively extend lifetime and reduce losses. However, due to the differences in production processes, the error characteristics of flash memory chips are somewhat different from each other, which affects the accuracy of the life prediction of flash memory chips. In this paper, we experimentally find that the bit error rate of data retention errors can be used to characterize the number of program/erase cycles times, and propose to stimulate the interference between word-lines by writing specific contents to adjacent word-lines, which can effectively reduce the elapsed time and improve the accuracy of the life time prediction. Experimental results show that the elapsed time can be shorten by about 90.9%, and the prediction accuracy can be improved by 33.3 percentage points.

Key words: 3D NAND, life time predict, data retention error, word-line interference, SVM(Support Vector Machine)

中图分类号:

TP333

罗铮, 韩国军. 3D NAND闪存P/E次数的快速测评与寿命预测[J]. 广东工业大学学报, 2024, 41(06): 52-59.doi: 10.12052/gdutxb.240023

Luo Zheng, Han Guo-jun. Rapid Measurement and Lifetime Prediction of 3D NAND Flash P/E Cycles[J]. Journal of Guangdong University of Technology, 2024, 41(06): 52-59.doi: 10.12052/gdutxb.240023

[1] YOON C W. The fundamentals of NAND flash memory: technology for tomorrow’s fourth industrial revolution [J]. IEEE Solid-State Circuits Magazine, 2022, 14(2): 56-65.
[2] MURUGAN M, DU D H. Rejuvenator: a static wear leveling algorithm for NAND flash memory with minimized overhead[C]//2011 IEEE 27th Symposium on Mass Storage Systems and Technologies (MSST) . Denver, USA: IEEE, 2011: 1-12.
[3] CAI Y, GHOSE S, HARATSCH E F, et al. Error characterization, mitigation, and recovery in flash-memory-based solid-state drives [J]. Proceedings of the IEEE, 2017, 105(9): 1666-1704.
[4] FITZGERALD B, HOGAN D, RYAN C, et al. Endurance prediction and error reduction in NAND flash using machine learning[C]//2017 17th Non-Volatile Memory Technology Symposium (NVMTS) . Aachen, Germany: IEEE, 2017: 1-8.
[5] MA R, WU F, ZHANG M, et al. RBER-aware lifetime prediction scheme for 3D-TLC NAND flash memory [J]. IEEE Access, 2019, 7: 44696-44708.
[6] ZHANG H, WANG J, CHEN Z, et al. An SVM-based NAND flash endurance prediction method [J]. Micromachines, 2021, 12(7): 746.
[7] KIM S, LEE K, WOO C, et al. Analysis of failure mechanisms during the long-term retention operation in 3-D NAND flash memories [J]. IEEE Transactions on Electron Devices, 2020, 67(12): 5472-5478.
[8] YOO H, CHOI E, OH J, et al. Modeling and optimization of the chip level program disturbance of 3D NAND Flash memory[C]//2013 5th IEEE International Memory Workshop. Monterey, USA: IEEE, 2013: 147-150.
[9] PARK M, KIM K, PARK J H, et al. Direct field effect of neighboring cell transistor on cell-to-cell interference of NAND flash cell arrays [J]. IEEE Electron Device Letters, 2008, 30(2): 174-177.
[10] CAI Y, LUO Y, GHOSE S, et al. Read disturb errors in MLC NAND flash memory: characterization, mitigation, and recovery[C]//2015 45th Annual IEEE/IFIP International Conference on Dependable Systems and Networks. Rio de Janeiro, Brazil: IEEE, 2015: 438-449.
[11] LUO Y, GHOSE S, CAI Y, et al. Improving 3D NAND flash memory lifetime by tolerating early retention loss and process variation [J]. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2018, 2(3): 1-48.
[12] PARK S K, MOON J. Characterization of inter-cell interference in 3D NAND flash memory [J]. IEEE Transactions on Circuits and Systems I: Regular Papers, 2021, 68(3): 1183-1192.
[13] WEI D, FENG H, QIAO L, et al. Experimental verification and analysis of the acceleration factor model for 3-D NAND flash memory [J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2021, 41(10): 3543-3547.
[14] WEI D, FENG H, LIU M, et al. Edge word-Line reliability problem in 3-D NAND flash memory: observations, analysis, and solutions [J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2023, 31(6): 861-873.
[15] JEDEC, JC-64.8. SSD requirements and endurance test method: JESD218B[S]. USA: JEDEC Solid State Technology Association, 2010.

Viewed

Full text

From	Others	local

Times	19	59
Rate	24%	76%

Abstract

164

Just accepted	Online first	Issue

0	0	164

	From	local

	Times	164
	Rate	100%

Cited

Web of Science	Crossref	ScienceDirect	Search for Citations in Google Scholar >>


This page requires you have already subscribed to WoS.

Shared

Discussed

Just accepted

Online first

Just accepted

Online first

[1]	刘锦能, 肖燕珊, 刘波. 基于最小二乘孪生支持向量机的不确定数据学习算法[J]. 广东工业大学学报, 2024, 41(01): 79-85.
[2]	张宇, 刘波. 基于自步学习策略的归纳式迁移学习模型研究[J]. 广东工业大学学报, 2023, 40(04): 31-36.
[3]	陈友鹏, 陈璟华. 基于鲸鱼优化参数的最小二乘支持向量机短期负荷预测方法[J]. 广东工业大学学报, 2020, 37(03): 75-81.
[4]	王丹荣, 莫艳. 基于支持向量机的离散线性微分方程求解方法[J]. 广东工业大学学报, 2020, 37(02): 87-93.
[5]	陈培文, 傅秀芬. 采用SVM方法的文本情感极性分类研究[J]. 广东工业大学学报, 2014, 31(3): 95-101.
[6]	胡俊, 滕少华, 张巍, 刘冬宁. 支持向量机与哈夫曼树实现多分类的研究[J]. 广东工业大学学报, 2014, 31(2): 36-42.
[7]	夏琴晔, 杨宜民. 基于biSCAN和SVM的机器人目标识别新算法研究[J]. 广东工业大学学报, 2013, 30(4): 65-69.
[8]	朱燕飞；谭洪舟；章云； . 基于LS-SVM的非线性系统盲辨识[J]. 广东工业大学学报, 2007, 24(2): 76-79.