[Bug 95472] [i915] Feature request: Add support for fencing for PRIME setups

bugzilla-daemon at freedesktop.org bugzilla-daemon at freedesktop.org
Thu Sep 8 00:23:40 UTC 2016


https://bugs.freedesktop.org/show_bug.cgi?id=95472

--- Comment #64 from Mario Kleiner <mario.kleiner at tuebingen.mpg.de> ---
So Michel was right, and with the attached patch, page-flipped renderoffload
works nicely on Intel Haswell + AMD Tonga under amdgpu-kms, flips properly
waiting on the dmabuf fence for longer running rendering. I also retested Intel
Ivybridge + AMD Cedar under radeon-kms and Intel Ironlake + GeForce 330M under
nouveau-kms to make sure it doesn't cause other problems.

Maybe we can still get this into Linux 4.8-rc6? That would be splendid.

I'll also attach a hacky patch on top of Chris eb-fences branch which seems to
remove the Z-Tearing for windowed copy-swaps - and replaces it be the regular
horizontal tearing we always have with DRI3/Present, even for single gpu,
because we are too slow to get blitting started ahead of scanout.

-- 
You are receiving this mail because:
You are the assignee for the bug.
You are the QA Contact for the bug.
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/intel-gfx-bugs/attachments/20160908/805e2a01/attachment.html>


More information about the intel-gfx-bugs mailing list