An Early-Life NAND Flash Endurance Prediction System
NAND flash memory – ubiquitous in today’s world of smart phones, SSDs (solid state drives), and cloud storage – has a number of well-known reliability problems. NAND data contains bit errors, which require the use of error correcting codes (ECCs). The raw bit error r...
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
IEEE
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/80274b70c9ca43afbe723930c694608e |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:80274b70c9ca43afbe723930c694608e |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:80274b70c9ca43afbe723930c694608e2021-11-18T00:09:51ZAn Early-Life NAND Flash Endurance Prediction System2169-353610.1109/ACCESS.2021.3124604https://doaj.org/article/80274b70c9ca43afbe723930c694608e2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9597529/https://doaj.org/toc/2169-3536NAND flash memory – ubiquitous in today’s world of smart phones, SSDs (solid state drives), and cloud storage – has a number of well-known reliability problems. NAND data contains bit errors, which require the use of error correcting codes (ECCs). The raw bit error rate (RBER) increases with program-erase (P-E) cycling, and the number of P-E cycles the device can withstand before the RBER exceeds the ECC capability is called its <italic>endurance</italic>. ECC operates on data stored in a sector of NAND, and there is a large variation in the endurance of sectors within a device and across devices, resulting in excessively conservative endurance specifications. This research shows, for the first time, that a sector’s true endurance can be predicted with remarkable accuracy, using a combination of the sector’s location within the device, and measurements taken at the very beginning of life. Real-world data is gathered on millions of NAND sectors using a custom-built test platform. Optimised machine learning classification models are built from the raw data to predict if a sector will pass or fail to a fixed ECC threshold, after a target P-E cycling level has been reached. A novel technique is demonstrated that uses different ECC thresholds for model training and testing, which allows the models to be tuned so that they never misclassify samples that would fail. This eliminates ECC failures and data loss, allowing simpler, less expensive ECC schemes to be used for modern NAND devices. It also enables significant endurance extensions to be achieved.Barry FitzgeraldConor RyanJoe SullivanIEEEarticleNAND flashsolid state drivesenduranceretentionmachine learninggradient boostingElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 148635-148649 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
NAND flash solid state drives endurance retention machine learning gradient boosting Electrical engineering. Electronics. Nuclear engineering TK1-9971 |
| spellingShingle |
NAND flash solid state drives endurance retention machine learning gradient boosting Electrical engineering. Electronics. Nuclear engineering TK1-9971 Barry Fitzgerald Conor Ryan Joe Sullivan An Early-Life NAND Flash Endurance Prediction System |
| description |
NAND flash memory – ubiquitous in today’s world of smart phones, SSDs (solid state drives), and cloud storage – has a number of well-known reliability problems. NAND data contains bit errors, which require the use of error correcting codes (ECCs). The raw bit error rate (RBER) increases with program-erase (P-E) cycling, and the number of P-E cycles the device can withstand before the RBER exceeds the ECC capability is called its <italic>endurance</italic>. ECC operates on data stored in a sector of NAND, and there is a large variation in the endurance of sectors within a device and across devices, resulting in excessively conservative endurance specifications. This research shows, for the first time, that a sector’s true endurance can be predicted with remarkable accuracy, using a combination of the sector’s location within the device, and measurements taken at the very beginning of life. Real-world data is gathered on millions of NAND sectors using a custom-built test platform. Optimised machine learning classification models are built from the raw data to predict if a sector will pass or fail to a fixed ECC threshold, after a target P-E cycling level has been reached. A novel technique is demonstrated that uses different ECC thresholds for model training and testing, which allows the models to be tuned so that they never misclassify samples that would fail. This eliminates ECC failures and data loss, allowing simpler, less expensive ECC schemes to be used for modern NAND devices. It also enables significant endurance extensions to be achieved. |
| format |
article |
| author |
Barry Fitzgerald Conor Ryan Joe Sullivan |
| author_facet |
Barry Fitzgerald Conor Ryan Joe Sullivan |
| author_sort |
Barry Fitzgerald |
| title |
An Early-Life NAND Flash Endurance Prediction System |
| title_short |
An Early-Life NAND Flash Endurance Prediction System |
| title_full |
An Early-Life NAND Flash Endurance Prediction System |
| title_fullStr |
An Early-Life NAND Flash Endurance Prediction System |
| title_full_unstemmed |
An Early-Life NAND Flash Endurance Prediction System |
| title_sort |
early-life nand flash endurance prediction system |
| publisher |
IEEE |
| publishDate |
2021 |
| url |
https://doaj.org/article/80274b70c9ca43afbe723930c694608e |
| work_keys_str_mv |
AT barryfitzgerald anearlylifenandflashendurancepredictionsystem AT conorryan anearlylifenandflashendurancepredictionsystem AT joesullivan anearlylifenandflashendurancepredictionsystem AT barryfitzgerald earlylifenandflashendurancepredictionsystem AT conorryan earlylifenandflashendurancepredictionsystem AT joesullivan earlylifenandflashendurancepredictionsystem |
| _version_ |
1718425233067606016 |