Memristors enable the computation of matrix-vector multiplications (MVM) in memory and, therefore, show great potential in highly increasing the energy efficiency of deep neural network (DNN) inference accelerators. However, computations in memristors suffer from hardware non-idealities and are subject to different sources of noise that may negatively impact system performance. In this work, we theoretically analyze the mean squared error of DNNs that use memristor crossbars to compute MVM. We take into account both the quantization noise, due to the necessity of reducing the DNN model size, and the programming noise, stemming from the variability during the programming of the memristance value. Simulations on pre-trained DNN models showcase the accuracy of the analytical prediction. Furthermore the proposed method is almost two order of magnitude faster than Monte-Carlo simulation, thus making it possible to optimize the implementation parameters to achieve minimal error for a given power constraint.
翻译:存储器能够计算记忆中的矩阵-矢量倍增(MVM),因此,在大幅提高深神经网络(DNN)推力加速器的能效方面显示出巨大的潜力。然而,存储器的计算有硬件非理想性,并受到不同噪音来源的影响,可能对系统性能产生不利影响。在这项工作中,我们从理论上分析了使用 memristor 交叉条纹来计算MVM的 DNN平均正方位错误。我们考虑到由于必须减少 DNN模型的大小而导致的量化噪音,以及由于Memristance 值编程期间的变化而产生的编程噪音。预先训练的 DNNN模型模拟显示了分析预测的准确性。此外,拟议的方法几乎比Monte-Carlo模拟速度快两个数量级,因此有可能优化执行参数,以便在给定的电力制约下达到最小误差。