Exploring Image Selection for Self-Testing in Neural Network Accelerators
Exploring Image Selection for Self-Testing in Neural Network Accelerators
复制标题
DOI：
10.1109/isvlsi54635.2022.00076
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Fanruo Meng;Chengmo Yang
中科院分区：
文献类型：
--
作者：
Fanruo Meng;Chengmo Yang
硬件加速器对于在资源受限的边缘设备上适应计算和内存密集型神经网络（NN）应用至关重要。虽然硬件加速器促进了快速和节能的卷积运算，但它们的准确性受到片上和片外存储器中各种类型故障的威胁，其中存储着数百万个NN权重。为了实现快速和及时的故障检测，可以采用在加速器中周期性地运行一小组测试图像的自测试过程。本文主要研究和比较基于多数值分数的测试图像选择策略。各种图像选择标准进行了研究，包括输出概率分布，梯度灵敏度，神经元覆盖。实验研究表明，基于输出概率分布选择的图像在较宽的故障率范围内具有较高的故障检测精度，并且计算复杂度较低。这一小组测试图像允许实时监控DNN加速器的健康状况以及随后的恢复和自我修复过程。
Hardware accelerators are essential to the accommodation of computation and memory-intensive neural network (NN) applications on resource-constrained edge devices. While hardware accelerators facilitate fast and energy-efficient convolution operations, their accuracy is threatened by various types of faults in their on-chip and off-chip memories, where millions of NN weights are held. To achieve fast and in-time fault detection, a self-test process that periodically runs a small set of test images in the accelerator can be adopted. This paper focuses on developing and comparing multiple numerical score based test image selection strategies. Various image selection criteria are studied, including output probability distribution, gradient sensitivity, and neuron coverage. Experimental studies show that images selected based on the output probability distribution offers high fault detection accuracy over a wide range of fault rates as well as low computation complexity. The small set of test images allows for real-time monitoring of the healthiness of DNN accelerators as well as the subsequent recovery and self-healing process.