RBER Aware Multi-Sensing for Improving Read Performance of 3D MLC NAND Flash Memory

Meng Zhang, Fei Wu, Xubin Chen, Yajuan Du, Weihua Liu, Yahui Zhao, Jiguang Wan, Changsheng XieIEEE Access 2018 · OpenReview

Abstract

3D-multi-level cell (MLC) NAND flash memory adopts 3D stack technology and stores two bits per cell, leading to improved storage capacities, but sacrificing data reliability. Low-density parity-check (LDPC) codes showing strong error correction capability benefit from their soft decision decoding, which is widely exploited to guarantee data reliability. Nevertheless, adopting LDPC codes can introduce a concern about read performance, because their iterative soft-decision decoding requires LogLikelihood Ratio (LLR) information, called soft decision information, by applying multi-sensing voltages. This process of obtaining LLR information leads to high sensing and transferring latencies, lowering down 3D-MLC read performance. In particular, when raw bit error rates (RBER) are much higher due to the long retention periods and program/erase (P/E) cycles, this problem becomes more serious. In this paper, we propose a RBER-aware multi-sensing scheme for reducing sensing and transferring latencies, and thus improving read performance. This proposed scheme exploits the variations of RBER in flash pages with the increase of retention time and P/E cycles to dynamically apply sensing voltages. Simulation results show that this scheme significantly decreases the number of required sensing voltages while maintaining LDPC error correction capability, enhancing 3D-MLC read performance.
BibTeX
@inproceedings{zhang2018rber,
  author = {Meng Zhang and Fei Wu and Xubin Chen and Yajuan Du and Weihua Liu and Yahui Zhao and Jiguang Wan and Changsheng Xie},
  title = {{RBER Aware Multi-Sensing for Improving Read Performance of 3D MLC NAND Flash Memory}},
  booktitle = {IEEE Access},
  year = {2018},
  url = {https://openreview.net/forum?id=S7dMiyAv-H1},
}

Loading related content...

Figure