this post was submitted on 29 Jul 2023
20 points (91.7% liked)

Android

27951 readers
357 users here now

DROID DOES

Welcome to the droidymcdroidface-iest, Lemmyest (Lemmiest), test, bestest, phoniest, pluckiest, snarkiest, and spiciest Android community on Lemmy (Do not respond)! Here you can participate in amazing discussions and events relating to all things Android.

The rules for posting and commenting, besides the rules defined here for lemmy.world, are as follows:

Rules


1. All posts must be relevant to Android devices/operating system.


2. Posts cannot be illegal or NSFW material.


3. No spam, self promotion, or upvote farming. Sources engaging in these behavior will be added to the Blacklist.


4. Non-whitelisted bots will be banned.


5. Engage respectfully: Harassment, flamebaiting, bad faith engagement, or agenda posting will result in your posts being removed. Excessive violations will result in temporary or permanent ban, depending on severity.


6. Memes are not allowed to be posts, but are allowed in the comments.


7. Posts from clickbait sources are heavily discouraged. Please de-clickbait titles if it needs to be submitted.


8. Submission statements of any length composed of your own thoughts inside the post text field are mandatory for any microblog posts, and are optional but recommended for article/image/video posts.


Community Resources:


We are Android girls*,

In our Lemmy.world.

The back is plastic,

It's fantastic.

*Well, not just girls: people of all gender identities are welcomed here.


Our Partner Communities:

!android@lemmy.ml


founded 1 year ago
MODERATORS
 

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?

top 2 comments
sorted by: hot top controversial new old
[โ€“] zephyrvs@lemmy.ml 8 points 1 year ago

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

[โ€“] AlmightySnoo@lemmy.world 5 points 1 year ago

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.