MoRS：一种降压型SRAM的近似故障建模框架
MoRS: An Approximate Fault Modelling Framework for Reduced-Voltage SRAMs
摘要：
片上存储器（通常基于静态RAM-SRAM）是用于各种计算设备的关键组件，包括异构设备，例如，GPU、FPGA、ASIC实现高性能。在这些异构结构上运行的深度神经网络（DNN）等现代工作负载高度依赖于片上存储器架构以实现高效加速。因此，提高这种存储器的能量效率直接导致高效的系统。节能的常用方法之一是欠伏，即，电源电压低于标称电平。这样的系统可以安全地欠压，而不会导致故障下降到一定的电压限制。这个安全范围也称为电压保护带。然而，在不降低频率的情况下将电压降低到保护带电平以下会导致基于时序的故障。在本文中，我们提出了MoRS，一个框架，产生的第一个近似欠转故障模型，使用真正的故障提取实验欠转研究SRAM建立模型。我们将MoRS产生的故障注入DNN加速器的片上存储器中，以评估测试系统的弹性。MoRS具有简单的优点，不需要任何高时间开销的实验，同时与完全随机生成的故障注入方法相比足够准确。我们通过将权重映射到SRAM来评估我们在流行的DNN工作负载中的实验，并测量MoRS的输出与真实数据之间的准确性差异。结果表明，实际故障数据与MoRS输出故障模型之间的最大误差为6.21%，而与随机故障注入模型之间的最大误差为23.2%。在与真实数据的平均接近度方面，MoRS的输出比随机故障注入方法高出3.21倍。
英文摘要：
On-chip memory (usually based on Static RAMs-SRAMs) are crucial components for various computing devices including heterogeneous devices, e.g., GPUs, FPGAs, ASICs to achieve high performance. Modern workloads such as Deep Neural Networks (DNNs) running on these heterogeneous fabrics are highly dependent on the on-chip memory architecture for efficient acceleration. Hence, improving the energy-efficiency of such memories directly leads to an efficient system. One of the common methods to save energy is undervolting i.e., supply voltage underscaling below the nominal level. Such systems can be safely undervolted without incurring faults down to a certain voltage limit. This safe range is also called voltage guardband. However, reducing voltage below the guardband level without decreasing frequency causes timing-based faults. In this paper, we propose MoRS, a framework that generates the first approximate undervolting fault model using real faults extracted from experimental undervolting studies on SRAMs to build the model. We inject the faults generated by MoRS into the on-chip memory of the DNN accelerator to evaluate the resilience of the system under the test. MoRS has the advantage of simplicity without any need for high-time overhead experiments while being accurate enough in comparison to a fully randomly-generated fault injection approach. We evaluate our experiment in popular DNN workloads by mapping weights to SRAMs and measure the accuracy difference between the output of the MoRS and the real data. Our results show that the maximum difference between real fault data and the output fault model of MoRS is 6.21%, whereas the maximum difference between real data and random fault injection model is 23.2%. In terms of average proximity to the real data, the output of MoRS outperforms the random fault injection approach by 3.21x.
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。
