This paper discusses the introduction of an integrated Posit Processing Unit (PPU) as an alternative to Floating-point Processing Unit (FPU) for Deep Neural Networks (DNNs) in automotive applications. Autonomous Driving tasks are increasingly depending on DNNs. For example, the detection of obstacles by means of object classification needs to be performed in real-time without involving remote computing. To speed up the inference phase of DNNs the CPUs on-board the vehicle should be equipped with co-processors, such as GPUs, which embed specific optimization for DNN tasks. In this work, we review an alternative arithmetic that could be used within the co-processor. We argue that a new representation for floating point numbers called Posit is particularly advantageous, allowing for a better trade-off between computation accuracy and implementation complexity. We conclude that implementing a PPU within the co-processor is a promising way to speed up the DNN inference phase.
Exploiting Posit Arithmetic for Deep Neural Networks in Autonomous Driving Applications
01.01.2018
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
neural net , Autonomous vehicle , intelligent transportation system , Software , Posit arithmetic , Sensor , road vehicle , Hardware , floating point number , DNN inference phase , Open area test site , Task analysi , mobile robot , autonomous Driving , Deep Neural Network , Autonomous Driving task , Planning , Floating-point Processing Unit , Posit Processing Unit , automotive application
DDC: | 629 |
HEADLIGHT RANGE ESTIMATION FOR AUTONOMOUS DRIVING USING DEEP NEURAL NETWORKS
British Library Conference Proceedings | 2019
|PATCHING DEPLOYED DEEP NEURAL NETWORKS FOR AUTONOMOUS MACHINE APPLICATIONS
Europäisches Patentamt | 2022
|An Autonomous Driving Approach Based on Trajectory Learning Using Deep Neural Networks
Springer Verlag | 2021
|EXPLOITING HIERARCHY FOR SCALABLE DECISION MAKING IN AUTONOMOUS DRIVING
British Library Conference Proceedings | 2018
|