I'm using the NNAPI delegate of Tensorflow Lite to run our net. I am trying to determine which accelerator (NPU, GPU, DSP) is used during runtime. In the Burnout Benchmark there are three graphs that show the usage of CPU, GPU and NPU. I know how to read the CPU usage, but I can't find a way to read the GPU, NPU or even the DSP usage programmatically.
I was wondering, how to show the usages of all accelerators. Could you help me out with this?
I did some research, but what I found were other apps that monitor the GPU usage. I want to read the usage of the GPU and NPU programmatcally in my app.
Thank you in advance!
