OSPADA: One-Shot Programming Aware Data Allocation Policy to Improve 3D NAND Flash Read Performance

Wu, Fei; Lu, Zuo; Zhou, You; He, Xubin; Tan, Zhihu; Xie, Conghua

doi:10.1109/iccd.2018.00018

Cited by 16 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al 4 propose to enhance the device internal parallelism by implementing the block‐level parallelism and partial page accessing in the storage hardware architecture. Wu et al 1 propose a distance‐aware round robin page allocation scheme for improving the utilization of internal parallelism and thus improving the read performance. There are also works proposed to mitigate the detrimental effects of garbage collection activities, 5‐7,11 or mitigate the retention error and degraded system performance incurred by the process variation 3,9,12,13 .…”

Section: Related Workmentioning

confidence: 99%

“…Prior works fail to address the QoS performance incurred by OSP on CT‐based SSDs. Some works propose to improve the system I/O performance by enhanced internal parallelism, 1,4 which does not consider the QoS performance. There are also works proposed to improve the QoS performance by revised garbage collection, 5‐7 or mitigate the impaired storage lifetime incurred by process variation 8‐10 .…”

Section: Introductionmentioning

confidence: 99%

“…With the rapid development of high‐density NAND flash technology, three‐dimensional (3D) solid‐state‐drivers (SSDs) have been employed as the prevalent storage solution in the market. There are two mainstream 3D SSD technologies, floating‐gate (FG) technology and charge‐trap (CT) technology 1 . CT‐based technology has been deemed as a predominant candidate since it eliminates the cell‐to‐cell interference 1 .…”

Section: Introductionmentioning

confidence: 99%

“…There are two mainstream 3D SSD technologies, floating‐gate (FG) technology and charge‐trap (CT) technology 1 . CT‐based technology has been deemed as a predominant candidate since it eliminates the cell‐to‐cell interference 1 . Thus, multiple pages in a word line could be programmed simultaneously, which is called one‐shot‐programming (OSP), for example, three pages for tripple‐level cell (TLC)‐based SSDs.…”

Section: Introductionmentioning

confidence: 99%

“…1 CT-based technology has been deemed as a predominant candidate since it eliminates the cell-to-cell interference. 1 Thus, multiple pages in a word line could be programmed simultaneously, which is called one-shot-programming (OSP), for example, three pages for tripple-level cell (TLC)-based SSDs. This technique can maximize the system input/output (I/O) throughput, thus improving the user experience significantly.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Machine learning assisted OSP approach for improved QoS performance on 3D charge‐trap based SSDs

Zhu

et al. 2020

Int J Intell Syst

View full text Add to dashboard Cite

Three-dimensional (3D) charge-trap based solid-statedrivers (SSDs) have become an emerging storage solution in recent years. One-shot-programming in 3D charge-trap based SSDs could deliver a maximized system input/output (I/O) throughput at the cost of degraded Quality-of-Service (QoS) performance. This paper proposes reinforcement-learning based one-shotprogramming (RLOSP), a reinforcement learning based approach to improve the QoS performance for 3D charge-trap based SSDs. By learning the I/O patterns of the workload environments as well as the device internal status, the proposed approach could properly choose requests in the device queue, and allocate physical addresses for these requests during one-shotprogramming. In this manner, the storage device could deliver an improved QoS performance. Experimental results reveal that the proposed approach could reduce the worst-case latency at the 99.9th percentile by 37.5%-59.2%, with an optimal system I/O throughput.

show abstract