Artículo
Performance assessment of deep learning frameworks through metrics of CPU hardware exploitation on an embedded platform
Autor/es | Velasco Montero, Delia
Fernández Berni, Jorge Carmona Galán, Ricardo Rodríguez Vázquez, Ángel Benito |
Departamento | Universidad de Sevilla. Departamento de Electrónica y Electromagnetismo |
Fecha de publicación | 2020 |
Fecha de depósito | 2023-11-06 |
Publicado en |
|
Resumen | In this paper, we analyze heterogeneous performance exhibited by some popular deep learning software frameworks for visual inference on a resource-constrained hardware platform. Benchmarking of Caffe, OpenCV, TensorFlow, ... In this paper, we analyze heterogeneous performance exhibited by some popular deep learning software frameworks for visual inference on a resource-constrained hardware platform. Benchmarking of Caffe, OpenCV, TensorFlow, and Caffe2 is performed on the same set of convolutional neural networks in terms of instantaneous throughput, power consumption, memory footprint, and CPU utilization. To understand the resulting dissimilar behavior, we thoroughly examine how the resources in the processor are differently exploited by these frameworks. We demonstrate that a strong correlation exists between hardware events occurring in the processor and inference performance. The proposedhardware-aware analysis aims to findlimitations andbottlenecks emerging from the jointinteraction offrameworks andnetworks on a particular CPU-based platform. This provides insight into introducing suitable modifications in bothtypes of components to enhance their global performance. It also facilitates the selection of frameworks and networks among a large diversity of these components available these days for visual understanding. © 2020 J.J. Strossmayer University of Osijek , Faculty of Electrical Engineering, Computer Science and Information Technology. All rights reserved. |
Agencias financiadoras | Ministerio de Ciencia, Innovación y Universidades (MICINN). España European Commission (EC). Fondo Europeo de Desarrollo Regional (FEDER) European Union (EU) H2020 MSCA Gobierno de España US Office of Naval Research |
Identificador del proyecto | RTI2018-097088-B-C31
765866 FPU17/02804 N00014-19-1-2156 |
Cita | Velasco Montero, D., Fernández Berni, J., Carmona Galán, R. y Rodríguez Vázquez, Á.B. (2020). Performance assessment of deep learning frameworks through metrics of CPU hardware exploitation on an embedded platform. International Journal of Electrical and Computer Engineering Systems, 11 (1), 1-11. https://doi.org/10.32985/ijeces.11.1.1. |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
performance assessment.pdf | 1.416Mb | [PDF] | Ver/ | Artículo |