AFarePart: 用于DNN边缘加速器的精度感知故障容错分区器
AFarePart: Accuracy-aware Fault-resilient Partitioner for DNN Edge Accelerators
AI总结:
本文提出了一种精度感知的DNN分区框架,通过NSGA-II多目标优化提升故障容错性,实验显示在性能开销小的情况下,故障容忍度提升达27.7%。
摘要:
深度神经网络(DNNs)正越来越多地部署在分布式和资源受限的平台上,如系统级芯片(SoC)加速器和边缘-云系统。DNNs通常被划分并执行于异构处理单元上以优化延迟和能耗。然而,这些划分模型在硬件故障和通信错误下的可靠性仍然是一个关键但尚未深入研究的话题,尤其是在安全关键应用中。在本文中,我们提出了一种精度感知、故障容错的DNN分区框架,目标是使用NSGA-II进行多目标优化,其中在故障条件下精度下降被作为核心指标引入,与能耗和延迟并列。我们的框架在优化过程中执行运行时故障注入,并利用反馈回路优先考虑容错分区。我们在硬件加速器上评估了我们的方法,包括AlexNet、SqueezeNet和ResNet18等基准CNNs,并展示了在性能开销最小的情况下,故障容忍度可提高27.7%。我们的结果强调了将容错性纳入DNN分区中的重要性,从而为在易出错环境中实现稳健的AI推理铺平了道路。
英文摘要:
Deep Neural Networks (DNNs) are increasingly deployed across distributed and resource-constrained platforms, such as System-on-Chip (SoC) accelerators and edge-cloud systems. DNNs are often partitioned and executed across heterogeneous processing units to optimize latency and energy. However, the reliability of these partitioned models under hardware faults and communication errors remains a critical yet underexplored topic, especially in safety-critical applications. In this paper, we propose an accuracy-aware, fault-resilient DNN partitioning framework targeting multi-objective optimization using NSGA-II, where accuracy degradation under fault conditions is introduced as a core metric alongside energy and latency. Our framework performs runtime fault injection during optimization and utilizes a feedback loop to prioritize fault-tolerant partitioning. We evaluate our approach on benchmark CNNs including AlexNet, SqueezeNet and ResNet18 on hardware accelerators, and demonstrate up to 27.7% improvement in fault tolerance with minimal increase in performance overhead. Our results highlight the importance of incorporating resilience into DNN partitioning, and thereby paving the way for robust AI inference in error-prone environments.
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。