Towards Executing Computer Vision Functionality on Programmable Network Devices

Glebke, René; Krude, Johannes; Kunze, Ike; Rüth, Jan; Senger, Felix; Wehrle, Klaus

doi:10.1145/3359993.3366646

Cited by 33 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While commonly, specific hardware is required to provide speed-up factors for learning, not inference, recent research has also evaluated the possibility to employ commodity hardware for these scenarios [37,38]. Specifically, in [39], the authors were able to achieve a throughput of 19 decisions per second for autonomous line following on a smart network interface. While the task at hand is different, the overall concept of offloading potrtions or all of the computer vision tasks into the network is similar.…”

Section: Discussionmentioning

confidence: 99%

You Only Look Once, But Compute Twice: Service Function Chaining for Low-Latency Object Detection in Softwarized Networks

2021

View full text Add to dashboard Cite

With increasing numbers of computer vision and object detection application scenarios, those requiring ultra-low service latency times have become increasingly prominent; e.g., those for autonomous and connected vehicles or smart city applications. The incorporation of machine learning through the applications of trained models in these scenarios can pose a computational challenge. The softwarization of networks provides opportunities to incorporate computing into the network, increasing flexibility by distributing workloads through offloading from client and edge nodes over in-network nodes to servers. In this article, we present an example for splitting the inference component of the YOLOv2 trained machine learning model between client, network, and service side processing to reduce the overall service latency. Assuming a client has 20% of the server computational resources, we observe a more than 12-fold reduction of service latency when incorporating our service split compared to on-client processing and and an increase in speed of more than 25% compared to performing everything on the server. Our approach is not only applicable to object detection, but can also be applied in a broad variety of machine learning-based applications and services.

show abstract

Section: Discussionmentioning

confidence: 99%

You Only Look Once, But Compute Twice: Service Function Chaining for Low-Latency Object Detection in Softwarized Networks

2021

View full text Add to dashboard Cite

show abstract

“…In-network processing again offers a solution as control programs can be deployed in the network and thus significantly reduce the inherent latencies. These programs currently range from simple LQR controllers [132] to basic line detection mechanisms [56] and can thus cover a variety of simple control tasks. Additionally, complementary safety measures, such as emergency stops, can also be realized in networking hardware, as is demonstrated by Cesen et al [31].…”

Section: Interconnected and Industry-capable Infrastructurementioning

confidence: 99%

A Computer Science Perspective on Digital Transformation in Production

Brauner

Dalibor

Jarke

et al. 2022

ACM Trans. Internet Things

Self Cite

View full text Add to dashboard Cite

The Industrial Internet-of-Things (IIoT) promises significant improvements for the manufacturing industry by facilitating the integration of manufacturing systems by Digital Twins. However, ecological and economic demands also require a cross-domain linkage of multiple scientific perspectives from material sciences, engineering, operations, business, and ergonomics, as optimization opportunities can be derived from any of these perspectives. To extend the IIoT to a true Internet of Production , two concepts are required: first, a complex, interrelated network of Digital Shadows which combine domain-specific models with data-driven AI methods; and second, the integration of a large number of research labs, engineering, and production sites as a World Wide Lab which offers controlled exchange of selected, innovation-relevant data even across company boundaries. In this article, we define the underlying Computer Science challenges implied by these novel concepts in four layers: Smart human interfaces provide access to information that has been generated by model-integrated AI . Given the large variety of manufacturing data, new data modeling techniques should enable efficient management of Digital Shadows, which is supported by an interconnected infrastructure . Based on a detailed analysis of these challenges, we derive a systematized research roadmap to make the vision of the Internet of Production a reality.

show abstract

“…In addition to the aforementioned categories, data plane programming is being used for stream processing [167,168], parallel processing [169], string searching [170], erasure coding [171], in-network lock managers [172], database queries acceleration [173], in-network compression [174], and computer vision offloading [175].…”

Section: Summary and Lessons Learnedmentioning

confidence: 99%

An Exhaustive Survey on P4 Programmable Data Plane Switches: Taxonomy, Applications, Challenges, and Future Trends

2021

View full text Add to dashboard Cite

Traditionally, the data plane has been designed with fixed functions to forward packets using a small set of protocols. This closed-design paradigm has limited the capability of the switches to proprietary implementations which are hard-coded by vendors, inducing a lengthy, costly, and inflexible process. Recently, data plane programmability has attracted significant attention from both the research community and the industry, permitting operators and programmers in general to run customized packet processing functions. This open-design paradigm is paving the way for an unprecedented wave of innovation and experimentation by reducing the time of designing, testing, and adopting new protocols; enabling a customized, top-down approach to develop network applications; providing granular visibility of packet events defined by the programmer; reducing complexity and enhancing resource utilization of the programmable switches; and drastically improving the performance of applications that are offloaded to the data plane. Despite the impressive advantages of programmable data plane switches and their importance in modern networks, the literature has been missing a comprehensive survey. To this end, this paper provides a background encompassing an overview of the evolution of networks from legacy to programmable, describing the essentials of programmable switches, and summarizing their advantages over Softwaredefined Networking (SDN) and legacy devices. The paper then presents a unique, comprehensive taxonomy of applications developed with P4 language; surveying, classifying, and analyzing more than 200 articles; discussing challenges and considerations; and presenting future perspectives and open research issues.

show abstract

Towards Executing Computer Vision Functionality on Programmable Network Devices

Cited by 33 publications

References 26 publications

You Only Look Once, But Compute Twice: Service Function Chaining for Low-Latency Object Detection in Softwarized Networks

You Only Look Once, But Compute Twice: Service Function Chaining for Low-Latency Object Detection in Softwarized Networks

A Computer Science Perspective on Digital Transformation in Production

An Exhaustive Survey on P4 Programmable Data Plane Switches: Taxonomy, Applications, Challenges, and Future Trends

Contact Info

Product

Resources

About