AMDGPU In Linux 4.9 To Bring Virtual Display Support, Improved GPU Reset

[phoronix]

Phoronix: AMDGPU In Linux 4.9 To Bring Virtual Display Support, Improved GPU Reset

The first pull request has been submitted of new Radeon and AMDGPU DRM driver updates to be queued in DRM-Next for landing with the Linux 4.9 kernel...

http://www.phoronix.com/scan.php?page=news_item&px=AMDGPU-Linux-4.9-First

[davidbepo]

and no DAL also

[boxie]

I wonder if bridgman is able to give us a front page post update on the DAL situation?

[ElectricPrism]

ELI5 please?

Does this mean that you can have a virtual display with a remote interface to connect say via Android / iPad and use that as the display? If I could use a Tablet as a screen with a stylus at a fair latency it might perform comperable to my Wacom Cintiq 21ux - I also like the idea of having a strong central computer between several people doing different things at once on different Tablet user sessions - that would be awesome.

[droste]

No, this means you can fake having a display without having an actual display, nothing more.

You *can* access what should be displayed on the fake display and send it somewhere else to achieve what you want to do, but this is not in this pull request (nor should it be in the kernel).

[Namenlos]

and no DAL also

It would be kind of strange to pull such a huge codebase into an LTS kernel I think. If they are aiming for staging maybe, I am not sure in what way staging matters in terms of LTS support.

[darkbasic]

and no DAL also

Better no DAL than shitty pull requests. The first one was scary at least, and it takes time to rewrite large portions of code. We will wait for a proper code.

[illwieckz]

That Virtual Display support looks like something needed by the XConnect project, right ?

[R00KIE]

In my opinion, it would be better to move some of the code to GPU's "firmware" so that the Linux kernel (Windows, Mac kernel) does not need to deal with too many low-level details.

The amount of complexity in current GPUs is enough for them to contain a small operating system. It would be really cool to connect to the GPU OS via a wireless TCP/IP connection.

I'd rather see minimal GPU (or anything else) firmware that takes care of only the absolute minimum functionality, such as preventing self destruction and basic sanity checks, and let drivers or something else along the stack deal with the rest.

I believe we've seen enough bugs and security problems hardcoded in firmware that will never get updated or fixed, so we should know better and not ask for trouble further down the line.

[darkbasic]

In my opinion, it would be better to move some of the code to GPU's "firmware" so that the Linux kernel (Windows, Mac kernel) does not need to deal with too many low-level details.

The amount of complexity in current GPUs is enough for them to contain a small operating system. It would be really cool to connect to the GPU OS via a wireless TCP/IP connection.

No, please. *PLEASE* no. Unless firmware's source code gets released of course.

I'd rather see minimal GPU (or anything else) firmware that takes care of only the absolute minimum functionality, such as preventing self destruction and basic sanity checks, and let drivers or something else along the stack deal with the rest.

I believe we've seen enough bugs and security problems hardcoded in firmware that will never get updated or fixed, so we should know better and not ask for trouble further down the line.

+1
The more closed source *SHIT* removed, the better.