This topic describes the Arm NN Timeline in Streamline.
Arm NN is an open source Machine Learning (ML) inference engine for Android and Linux which accelerates ML on Arm CPUs and GPUs.
If you are using Streamline with Arm NN and timeline profiling is enabled there is an Arm NN Timeline view for running process that uses Arm NN. Each row in the view is a neural network, which you can expand to see the layers of the neural network. Connections between layers indicate that the output of one layer is the input for another layer. Expanding a layer shows the workloads in that layer. Workload names are in the form workload:<Backend>(<GUID>), where <Backend> is the hardware or mechanism responsible for the workload, and <GUID> is a Globally Unique Identifier (GUID) provided by Arm NN. The jobs on each row indicate how long each inference of the network, each layer, or each workload ran for.