人工神经网络中基于重要性驱动的混合8 T-6 T SRAM能量高效突触存储
Significance Driven Hybrid 8T-6T SRAM for Energy-Efficient Synaptic Storage in Artificial Neural Networks
摘要:
多层人工神经网络(ANN)在分类和识别应用中具有广泛的用途。这种网络的规模和复杂性以及通用计算平台的不足已经导致对开发高效硬件实现的极大兴趣。在这项工作中,我们专注于设计能量高效的片上存储的突触权重。为了最小化这种大规模网络的典型数字CMOS实现的功耗,数字神经元可以通过降低时钟频率在缩放电压下可靠地操作。相反,使用常规6 T SRAM设计的片上突触存储器在降低的电压下易受位单元故障的影响。然而,神经网络对小突触权重扰动的固有错误弹性使我们能够缩放6 TSRAM的工作电压。我们对广泛使用的数字识别数据集的分析表明,电压可以从标称工作电压(950 mV)缩放200 mV,几乎没有精度损失(小于0.5%)(22 nm预测技术)。超出该范围的缩放会由于突触权重的MSB中的故障的增加的概率而导致实质性的性能降级。因此,我们提出了一种有效性驱动的混合8 T-6 T SRAM,其中敏感MSB存储在8 T位单元中,由于解耦的读取和写入路径,这些位单元在缩放电压下是鲁棒的。为了进一步减小面积损失,我们提出了一种由多个8 T-6 T SRAM组组成的突触敏感性驱动的混合存储器架构。我们的电路到系统级仿真框架表明,所提出的突触敏感性驱动的架构提供了一个30.91%的存储器访问功率减少了10.41%的面积开销,在分类精度小于1%的损失。
英文摘要:
Multilayered artificial neural networks (ANN) have found widespread utility in classification and recognition applications. The scale and complexity of such networks together with the inadequacies of general purpose computing platforms have led to a significant interest in the development of efficient hardware implementations. In this work, we focus on designing energy efficient on-chip storage for the synaptic weights. In order to minimize the power consumption of typical digital CMOS implementations of such large-scale networks, the digital neurons could be operated reliably at scaled voltages by reducing the clock frequency. On the contrary, the on-chip synaptic storage designed using a conventional 6T SRAM is susceptible to bitcell failures at reduced voltages. However, the intrinsic error resiliency of NNs to small synaptic weight perturbations enables us to scale the operating voltage of the 6TSRAM. Our analysis on a widely used digit recognition dataset indicates that the voltage can be scaled by 200mV from the nominal operating voltage (950mV) for practically no loss (less than 0.5%) in accuracy (22nm predictive technology). Scaling beyond that causes substantial performance degradation owing to increased probability of failures in the MSBs of the synaptic weights. We, therefore propose a significance driven hybrid 8T-6T SRAM, wherein the sensitive MSBs are stored in 8T bitcells that are robust at scaled voltages due to decoupled read and write paths. In an effort to further minimize the area penalty, we present a synaptic-sensitivity driven hybrid memory architecture consisting of multiple 8T-6T SRAM banks. Our circuit to system-level simulation framework shows that the proposed synaptic-sensitivity driven architecture provides a 30.91% reduction in the memory access power with a 10.41% area overhead, for less than 1% loss in the classification accuracy.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。