Announcement
Collapse
No announcement yet.
User Profile
Collapse
-
Even if they did decide to truly embrace FOSS and provide something comparable to amdgpu, it would take them years to catch up to AMD....
- Likes 2
Leave a comment:
-
These changes are only relevant for the case where a display is hooked up to the Nvidia GPU.
Even so, it's intended for the case where the...
- Likes 1
Leave a comment:
-
MrCooper replied to XWayland 24.1 RC Released With Explicit Sync, Improved Rootful & GLAMOR Optimizationsin WaylandYou're arguing with a strawman.
Nobody (with a clue) is saying that X the protocol is being abandoned. It was always clear that good support...
Leave a comment:
-
Mutter's explicit sync support landed for 46.1, which might be in the final Ubuntu release....
- Likes 2
Leave a comment:
-
MrCooper replied to X.Org Server Change Allows GLAMOR To Fallback To Software Rendering For Obsolete GPUsin X.Org & DRMJust in time for Xwayland 24.1
glamor can't accelerate anything with a GPU which doesn't have pixel shaders. So this will allow...
Leave a comment:
-
If the Wayland compositor uses the new APIs to actually enlarge its connection buffer, yes.​
That's a different issue, probably...
- Likes 3
Leave a comment:
-
So? Backporting fixes isn't "diverging".
Yes it does, since the non-Xwayland-specific code in the Xwayland binary...
- Likes 1
Leave a comment:
-
It has nothing to do with RCU, the analogy makes no sense.
Because the kernel allows submitting GPU work using buffers which have...
- Likes 1
Leave a comment:
-
It was Nvidia's choice to do this, instead of handling implicit sync in their driver as required by the existing Wayland protocol and X Present extension....
- Likes 7
Leave a comment:
-
Not really. This MR itself carries very little risk as long as the client doesn't actually use the new PresentPixmapSynced request. And at this point...
- Likes 11
Leave a comment:
-
Per my blog post, it's because the compositor makes its own GPU work depend on unfinished client GPU work. This means the compositor GPU work cannot finish...
Leave a comment:
-
I wrote that blog post, so I'm quite familiar with it.
My blog post explains how a Wayland compositor can avoid the stall.
...
Leave a comment:
-
Indeed, there's no inherent reason why there would be any significant difference for this kind of benchmarks. The GPU drivers and apps themselves should...
- Likes 2
Leave a comment:
-
That's just absurd. There's normally only one buffer per application frame for which implicit synchronization needs to be handled at the display protocol...
- Likes 1
Leave a comment:
-
I don't see any significant contributions from any other GPU vendor in the discussions on the wayland-protocols MR and related ones.
There...
- Likes 3
Leave a comment:
-
It really is mostly at this point.
Apples and oranges. Not the same kind of explicit sync.
That's...
- Likes 4
Leave a comment:
No activity results to display
Show More
Leave a comment: