A Self-Test Framework for Detecting Fault-induced Accuracy Drop in Neural Network Accelerators
A Self-Test Framework for Detecting Fault-induced Accuracy Drop in Neural Network Accelerators
复制标题
DOI：
10.1145/3394885.3431519
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Fanruo Meng;Fateme S. Hosseini;Chengmo Yang
中科院分区：
文献类型：
--
作者：
Fanruo Meng;Fateme S. Hosseini;Chengmo Yang
使用SRAM或新兴存储设备构建的硬件加速器对于在资源受限的设备上适应不断增加的深度神经网络（DNN）工作负载至关重要。然而，在部署之后，这些加速器的性能受到其片上和片外存储器中的故障的威胁，其中存储有数百万个DNN权重。根据底层内存技术的不同，可能会存在不同类型的错误，从而降低推理准确性。为了应对这一挑战，本文提出了一个在线自测框架，该框架使用从测试数据集中选择的一小组测试图像来监控加速器的准确性。在检测到明显的准确度下降水平时，该框架使用额外的测试图像来识别相应的故障类型，并通过分析测试图像的排名变化来预测故障的准确性。实验结果表明，该方法能够快速检测DNN加速器的故障状态，并提供准确的故障类型和故障严重性信息，为后续的恢复和自愈过程提供支持。
Hardware accelerators built with SRAM or emerging memory devices are essential to the accommodation of the ever-increasing Deep Neural Network (DNN) workloads on resource-constrained devices. After deployment, however, the performance of these accelerators is threatened by the faults in their on-chip and off-chip memories where millions of DNN weights are held. Different types of faults may exist depending on the underlying memory technology, degrading inference accuracy. To tackle this challenge, this paper proposes an online self-test framework that monitors the accuracy of the accelerator with a small set of test images selected from the test dataset. Upon detecting a noticeable level of accuracy drop, the framework uses additional test images to identify the corresponding fault type and predict the severeness of faults by analyzing the change in the ranking of the test images. Experimental results show that our method can quickly detect the fault status of a DNN accelerator and provide accurate fault type and fault severeness information, allowing for subsequent recovery and self-healing process.