Layer-by-layer Adaptively Optimized ECC of NAND flash-based SSD Storing Convolutional Neural Network Weight for Scene Recognition
Layer-by-layer Adaptively Optimized ECC of NAND flash-based SSD Storing Convolutional Neural Network Weight for Scene Recognition
复制标题
基于 NAND 闪存的 SSD 的逐层自适应优化 ECC 存储用于场景识别的卷积神经网络权重
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
K. Takeuchi
中科院分区：
文献类型：
--
作者：
Keita Mizushina;Toshiki Nakamura;Yoshiaki Deguchi;K. Takeuchi
提出了逐层自适应优化纠错码（ECC），以提高基于三层单元（TLC）NAND闪存的SSD的可靠性，用于使用物联网边缘设备的卷积神经网络（CNN）进行场景识别。逐层自适应优化ECC由逐层迭代优化低密度奇偶校验（LBL-LDPC）和逐层码长调整非对称编码（LBL-AC）组成。传统的LDPC ECC和非对称编码（AC）等技术提高了系统的可靠性。然而，它们需要ECC解码时间和标志/奇偶校验单元的大开销。提出的LBL-LDPC和LBL-AC分别减少了14%的ECC解码时间和26%的数据开销，而不会降低识别精度。数据保留时间延长了230%。
Layer-by-layer Adaptively Optimized Error Correcting Code (ECC) is proposed to improve the reliability of triple-level cell (TLC) NAND flash-based SSD for the scene recognition using convolutional neural network (CNN) of IoT edge devices. Layer-by-layer Adaptively Optimized ECC is composed of Layer-by-layer Iteration-Optimized Low Density Parity-Check (LBL-LDPC) and Layer-by-layer Code-length Adjusted Asymmetric Coding (LBL-AC). The conventional techniques like LDPC ECC and Asymmetric Coding (AC) improve the reliability. However, they require large overheads of the ECC decoding time and the flag/parity cell. Proposed LBL-LDPC and LBL-AC decrease the ECC decoding time by 14% and the data overhead by 26%, respectively, without recognition accuracy degradation. In addition, the data-retention time extends by 230%.