Machine Learning-Based Error Recovery System for NAND Flash Memory with Process Variation

2021 ◽  
Author(s):  
Seonmin Lee ◽  
Jeongju Jee ◽  
Hyuncheol Park
Keyword(s):  
Machine Learning ◽  
Flash Memory ◽  
Process Variation ◽  
Error Recovery ◽  
Nand Flash ◽  
Nand Flash Memory ◽  
Recovery System

scholarly journals Compression-Assisted Adaptive ECC and RAID Scattering for NAND Flash Storage Devices

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2952 ◽  
Author(s):  
Seung-Ho Lim ◽  
Ki-Woong Park
Keyword(s):  
Flash Memory ◽  
Error Recovery ◽  
Recovery Phase ◽  
Error Correction Codes ◽  
Nand Flash ◽  
Nand Flash Memory ◽  
Flash Storage ◽  
Storage Devices ◽  
Complementary Method ◽  
Compressed Data

NAND flash memory-based storage devices are vulnerable to errors induced by NAND flash memory cells. Error-correction codes (ECCs) are integrated into the flash memory controller to correct errors in flash memory. However, since ECCs show inherent limits in checking the excessive increase in errors, a complementary method should be considered for the reliability of flash storage devices. In this paper, we propose a scheme based on lossless data compression that enhances the error recovery ability of flash storage devices, which applies to improve recovery capability both of inside and outside the page. Within a page, ECC encoding is realized on compressed data by the adaptive ECC module, which results in a reduced code rate. From the perspective of outside the page, the compressed data are not placed at the beginning of the page, but rather is placed at a specific location within the page, which makes it possible to skip certain pages during the recovery phase. As a result, the proposed scheme improves the uncorrectable bit error rate (UBER) of the legacy system.

Process Variation Aware Read Performance Improvement for LDPC-Based nand Flash Memory

2020 ◽  
Vol 69 (1) ◽  
pp. 310-321 ◽  
Author(s):  
Qiao Li ◽  
Liang Shi ◽  
Yejia Di ◽  
Congming Gao ◽  
Cheng Ji ◽  
...  
Keyword(s):  
Performance Improvement ◽  
Flash Memory ◽  
Process Variation ◽  
Nand Flash ◽  
Nand Flash Memory

scholarly journals Machine Learning-Based Optimization Technique for High-Capacity V-NAND Flash Memory

2021 ◽  
Author(s):  
Jisuk Kim ◽  
Earl Kim ◽  
Daehyeon Lee ◽  
Taeheon Lee ◽  
Daesik Ham ◽  
...  
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Flash Memory ◽  
State Of The Art ◽  
Optimization Technique ◽  
High Capacity ◽  
Turnaround Time ◽  
Nand Flash ◽  
Nand Flash Memory ◽  
The Individual

Abstract In the NAND flash manufacturing process, thousands of internal electronic fuses (eFuse) should be tuned in order to optimize performance and validity. In this paper, we propose a machine learning-based optimization technique that can automatically tune the individual eFuse value based on a deep learning and genetic algorithm. Using state-of-the-art triple-level cell (TLC) V-NAND flash wafers, we trained our model and validated its effectiveness. The experimental results show that our technique can automatically optimize NAND flash memory, thus reducing total turnaround time (TAT) by 70 % compared with the manual-based process.

A Dynamic Huffman Coding Method for Reliable TLC NAND Flash Memory

2021 ◽  
Vol 26 (5) ◽  
pp. 1-25
Author(s):  
Chin-Hsien Wu ◽  
Hao-Wei Zhang ◽  
Chia-Wei Liu ◽  
Ta-Ching Yu ◽  
Chi-Yen Yang
Keyword(s):  
Machine Learning ◽  
Flash Memory ◽  
Huffman Coding ◽  
Nand Flash ◽  
Nand Flash Memory ◽  
Compression Performance ◽  
Learning From Data ◽  
Physical Problems ◽  
Coding Method ◽  
Multi Level

With the progress of the manufacturing process, NAND flash memory has evolved from the single-level cell and multi-level cell into the triple-level cell (TLC). NAND flash memory has physical problems such as the characteristic of erase-before-write and the limitation of program/erase cycles. Moreover, TLC NAND flash memory has low reliability and short lifetime. Thus, we propose a dynamic Huffman coding method that can apply to the write operations of NAND flash memory. The proposed method exploits observations from a Huffman tree and machine learning from data patterns to dynamically select a suitable Huffman coding. According to the experimental results, the proposed method can improve the reliability of TLC NAND flash memory and also consider the compression performance for those applications that require the Huffman coding.

Sign in / Sign up

Export Citation Format

Share Document