I feel that it would be a waste if the Pixel’s hardware capabilities related to AI aren’t being utilised in a privacy-conscious way. Are there features/avenues in GrapheneOS to make use of this?
GrapheneOS itself doesn’t use it, but all apps can access the Neural Core functionality and other parts of the Tensor SoC, according to this text: https://grapheneos.org/usage#google-camera
I believe that would be up to each individual app? It seems that in addition to ARM cores and a Mali GPU (targeted without issues by OpenGL ES for example) the Google Tensor chips also have an “Edge TPU” and it seems to be usable via the NN API (https://developer.android.com/ndk/guides/neuralnetworks) and a quick search through the GrapheneOS Github also yields this: https://github.com/GrapheneOS/device_google_gs201/tree/13/edgetpu, in particular:
[Bringup] Enable darwinn EdgeTPU implementation of NNAPI on PRO.
The NNAPI is now fully functional and passes all the tests. This CL enables the Darwinn NNAPI service by default on the master branch.
