2019 IEEE International Conference on Big Data (Big Data) 2019
DOI: 10.1109/bigdata47090.2019.9006406
|View full text |Cite
|
Sign up to set email alerts
|

An Empirical Study of Quad-Level Cell (QLC) NAND Flash SSDs for Big Data Applications

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

1
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 19 publications
(6 citation statements)
references
References 7 publications
1
5
0
Order By: Relevance
“…We estimate the endurance limit by dividing the SSD's TBW (terabytes written: the total amount of writes the SSD manufacturer guarantees) by the logical capacity. This estimation is consistent with recent works [21,22].…”
Section: Introductionsupporting
confidence: 94%
See 1 more Smart Citation
“…We estimate the endurance limit by dividing the SSD's TBW (terabytes written: the total amount of writes the SSD manufacturer guarantees) by the logical capacity. This estimation is consistent with recent works [21,22].…”
Section: Introductionsupporting
confidence: 94%
“…We implement a capacity-variant SSD on the extended FTLSim [9] from § 2 and use the SSD configuration in Table 2 for our evaluation. However, we set the endurance limit to 500 erases, a typical level for QLC [21,22], and once a block reaches this, it will be mapped out and no longer used in the SSD, effectively reducing the SSD's physical capacity. For the fixed capacity SSD, the SSD is considered to reach its end of life once the physical capacity becomes smaller than its logical capacity: the SSD is considered to have failed once this happens.…”
Section: Case Study On Capacity Variancementioning
confidence: 99%
“…These advancements in control mechanisms have paved the way for the successful commercialization of triple-level cell (TLC) and quadruple-level cell (QLC) technologies within the domain of 3D NAND. This achievement has further enhanced the appeal and versatility of this memory technology [9][10][11][12]. However, it is essential to acknowledge that the transition to multilevel cells presents a unique set of challenges, particularly concerning threshold voltage (V TH ) distribution.…”
Section: Introductionmentioning
confidence: 99%
“…The dramatic shift from the compute-centric paradigm to the data-centric paradigm in this era of big data has led to a surge in the flow of asynchronous data [1]- [2]. Ultra-dense storage technologies are urgently required to cope up with this data explosion [3].…”
Section: Introductionmentioning
confidence: 99%
“…were proposed [10]- [11]. 3D NAND flash memory has emerged as the most promising candidate for handling big data [2].…”
Section: Introductionmentioning
confidence: 99%