Conference paper

Performance Constraints of Machine Learning on Embedded Devices

Ł. Grzymkowski, T. Stefanski (Gdansk Univ. of Techn., Poland)

Machine learning is no longer confined to cloud and high-end server systems and has been successfully deployed on devices that are part of Internet of Things. This paper presents the analysis of performance of convolutional neural networks deployed on an ARM microcontroller. Inference time is measured for different core frequencies, with and without DSP instructions and disabled access to cache. Networks use both real-valued and complex-valued tensors and are tested using different inference engines. We conclude that the system must be tuned in a holistic way to achieve optimal efficiency.

Download one page abstract

Receipt of papers:

March 13th, 2020

Notification of acceptance:

May 18th, 2020

Registration opening:

May 20th, 2020

Final paper versions:

June 5th, 2020