KIT | KIT-Bibliothek | Impressum | Datenschutz

CNNParted: An open source framework for efficient Convolutional Neural Network inference partitioning in embedded systems

Kreß, Fabian ORCID iD icon 1; Sidorenko, Vladimir 1; Schmidt, Patrick 1; Hoefer, Julian ORCID iD icon 1; Hotfilter, Tim ORCID iD icon 1; Walter, Iris ORCID iD icon 1; Harbaum, Tanja ORCID iD icon 1; Becker, Jürgen 1
1 Institut für Technik der Informationsverarbeitung (ITIV), Karlsruher Institut für Technologie (KIT)


Applications such as autonomous driving or assistive robotics heavily rely on the usage of Deep Neural Networks. In particular, Convolutional Neural Networks (CNNs) provide precise and reliable results in image processing tasks like camera-based object detection or semantic segmentation. However, to achieve even better results, CNNs are becoming more and more complex. Deploying these networks in distributed embedded systems thereby imposes new challenges, due to additional constraints regarding performance and energy consumption in the near-sensor compute platforms, i.e. the sensor nodes. Processing all data in the central node, however, is disadvantageous since raw data of camera consumes large bandwidth and running CNN inference of multiple tasks requires certain performance. Moreover, sending raw data over the interconnect is not advisable for privacy reasons. Hence, offloading CNN workload to the sensor nodes in the system can lead to reduced traffic on the link and a higher level of data security. However, due to the limited hardware-resources on the sensor nodes, partitioning CNNs has to be done carefully to meet overall latency requirements and energy constraints. ... mehr

Preprint §
DOI: 10.5445/IR/1000158061
Veröffentlicht am 13.10.2023
DOI: 10.1016/j.comnet.2023.109759
Zitationen: 2
Web of Science
Zitationen: 2
Zitationen: 2
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Technik der Informationsverarbeitung (ITIV)
Publikationstyp Zeitschriftenaufsatz
Publikationsmonat/-jahr 06.2023
Sprache Englisch
Identifikator ISSN: 1389-1286, 0376-5075, 1872-7069, 1878-3120
KITopen-ID: 1000158061
Erschienen in Computer Networks
Verlag Elsevier
Band 229
Seiten Article no: 109759
Schlagwörter Convolutional Neural Networks; Embedded systems; Hardware accelerator; Simulation framework; Hardware/software co-design
Nachgewiesen in Web of Science
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page