Reliability Improvement in RRAM-based DNN for Edge Computing
Reliability Improvement in RRAM-based DNN for Edge Computing
复制标题
DOI：
10.1109/iscas48785.2022.9937260
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
Md. Oli-Uz-Zaman;Saleh Ahmad Khan;Geng Yuan;Yanzhi Wang;Zhiheng Liao;Jingyan Fu;Caiwen Ding;Jinhui Wang
中科院分区：
文献类型：
--
作者：
Md. Oli-Uz-Zaman;Saleh Ahmad Khan;Geng Yuan;Yanzhi Wang;Zhiheng Liao;Jingyan Fu;Caiwen Ding;Jinhui Wang
近年来，电阻式随机存取存储器（RRAM）在边缘计算应用中受到学术界和工业界的越来越多的关注，因为它提供了低功耗和低延迟来执行复杂的模拟原位矩阵向量乘法-深度神经网络（dnn）的最基本运算。但是故障卡滞（SAF）缺陷使得RRAM在实际应用中不可靠。本文提出了一种差分映射方法（DMM），通过减轻基于rram的dnn的SAF缺陷来提高可靠性。首先，给出并分析了基于CIFAR10数据集的VGG8模型的权值分布；然后DMM用于恢复0.1%至50% SAFs的推断精度。实验结果表明，当SAFs的比例小于7.5%时，DMM可以将dnn恢复到原来的推理精度（90%）。即使SAF在50%的极端条件下，仍然可以高效地将推理精度恢复到80%。更重要的是，DMM是一个高度可靠的稳压器，以避免功率和时间开销产生的saf。
Recently, the Resistive Random Access Memory (RRAM) has been paid more attention for edge computing applications in both academia and industry, because it offers power efficiency and low latency to perform the complex analog in-situ matrix-vector multiplication – the most fundamental operation of Deep Neural Networks (DNNs). But the Stuck at Fault (SAF) defect makes the RRAM unreliable for the practical implementation. A differential mapping method (DMM) is proposed in this paper to improve reliability by mitigate SAF defects from RRAM-based DNNs. Firstly, the weight distribution for the VGG8 model with the CIFAR10 dataset is presented and analyzed. Then the DMM is used for recovering the inference accuracies at 0.1% to 50% SAFs. The experiment results show that the DMM can recover DNNs to their original inference accuracies (90%), when the ratio of SAFs is smaller than 7.5%. And even when the SAF is in the extreme condition 50%, it is still highly efficient to recover the inference accuracy to 80%. What is more, the DMM is a highly reliable regulator to avoid power and timing overhead generated by SAFs.