Title: Realtime signal processing on NVIDIA TX2 using CUDA
Authors : Weiss, Armin
Rosenthal, Matthias
Mazloumian, Amin
Conference details: Nvidia GPU Technology Conference (GTC), San José, Mar 26 - 29, 2018
Issue Date: 26-Mar-2018
License (according to publishing contract) : Not specified
Type of review: No review
Language : English
Subjects : GTC; GPU; Real-time; Tegra X2; CUDA; Persistent Kernel
Subject (DDC) : 005: Computer programming, programs and data
621.3: Electrical engineering and electronics
Abstract: In our presentation, we will focus on low latency real-time signal processing on NVIDIA Jetson TX2. Originally designed for image processing, the Jetson TX2 incorporates a vast amount of embedded GPU processing power. However, it has not been widely used for signal processing so far. There are two main challenges that have to be addressed: Constantly high input and output data rate of arbitrary digital signals, as well as a very short and deterministic latency requirement (processing time and data transfer time). Using the example of multichannel digital audio processing, we will look at details of CUDA kernel programming, which is a precondition for uninterrupted signal processing. Moreover, we explain efficient data I/O transfer to Jetson TX2 GPU memory, synchronization between CPU and GPU as well as update mechanisms for control data.
Departement: School of Engineering
Organisational Unit: Institute of Embedded Systems (InES)
Publication type: Conference Other
URI: https://digitalcollection.zhaw.ch/handle/11475/5349
Appears in Collections:Publikationen School of Engineering

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.