Keep Clear of the Edges : An Empirical Study of Artificial Intelligence Workload Performance and Resource Footprint on Edge Devices
Keep Clear of the Edges : An Empirical Study of Artificial Intelligence Workload Performance and Resource Footprint on Edge Devices
复制标题
DOI：
10.1109/ipccc55026.2022.9894338
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Kun Suo;Tu N. Nguyen;Yong Shi;Jing He;Chih-Cheng Hung
中科院分区：
文献类型：
--
作者：
Kun Suo;Tu N. Nguyen;Yong Shi;Jing He;Chih-Cheng Hung
最近，随着万物互联和5G网络的到来，自动驾驶汽车、智能工业、4K/8 K、虚拟现实（VR）、增强现实（AR）等各种边缘场景产生的数据量，已经大爆炸了。所有这些趋势都显著地为设施带来了实时性、硬件依赖性、低功耗和安全性要求，并迅速普及了边缘计算。与此同时，人工智能（AI）工作负载也极大地改变了从云服务到移动的应用的计算模式。与人工智能在云或移动的平台上的广泛部署和充分研究不同，人工智能工作负载性能及其对边缘的资源影响尚未得到很好的理解。缺乏对它们在边缘环境中的优势、局限性、性能和资源消耗的深入分析和比较。在本文中，我们对边缘平台上的代表性AI工作负载进行了全面研究。我们首先对现代边缘硬件和流行的AI工作负载进行总结。然后，我们定量评估三个类别（即，分类、图像到图像和分割），我们发现硬件和神经网络模型之间的交互会对边缘的AI工作负载产生不可忽视的影响和开销。我们的实验表明，性能变化和资源占用的差异限制了某些类型的工作负载及其算法在边缘平台上的可用性，用户需要根据边缘环境的需求和特征选择合适的工作负载，模型和算法。
Recently, with the advent of the Internet of everything and 5G network, the amount of data generated by various edge scenarios such as autonomous vehicles, smart industry, 4K/8K, virtual reality (VR), augmented reality (AR), etc., has greatly exploded. All these trends significantly brought real-time, hardware dependence, low power consumption, and security requirements to the facilities, and rapidly popularized edge computing. Meanwhile, artificial intelligence (AI) workloads also changed the computing paradigm from cloud services to mobile applications dramatically. Different from wide deployment and sufficient study of AI in the cloud or mobile platforms, AI workload performance and their resource impact on edges have not been well understood yet. There lacks an in-depth analysis and comparison of their advantages, limitations, performance, and resource consumptions in an edge environment. In this paper, we perform a comprehensive study of representative AI workloads on edge platforms. We first conduct a summary of modern edge hardware and popular AI workloads. Then we quantitatively evaluate three categories (i.e., classification, image-to-image, and segmentation) of the most popular and widely used AI applications in realistic edge environments based on Raspberry Pi, Nvidia TX2, etc. We find that interaction between hardware and neural network models incurs non-negligible impact and overhead on AI workloads at edges. Our experiments show that performance variation and difference in resource footprint limit availability of certain types of workloads and their algorithms for edge platforms, and users need to select appropriate workload, model, and algorithm based on requirements and characteristics of edge environments.