[Mesa-dev] [Bug 111004] memcpy accessing GPU memory mappings using SSE instructions breaks in KVM

bugzilla-daemon at freedesktop.org bugzilla-daemon at freedesktop.org
Thu Jun 27 08:47:11 UTC 2019


--- Comment #10 from Christian K├Ânig <christian.koenig at amd.com> ---
Sorry but this is not a bug at all.

As Michel already noted core Vulkan as well as some OpenGL/OpenCL extensions
mandate that the platform support all well aligned memory accesses to GPU local
memory (VRAM).

If your platform (KVM in this case) can't do this for some reason you simply
can't use that platform with this software.

In other words even if you replace memcpy/memset in Mesa with custom non SSE
versions it is perfectly valid for an application to use SSE to access VRAM.
And you can't change a binary application (which is actually just conforming to
a standard).

The only possible workaround I can see in the driver is to not use VRAM at all
for CPU mappings. That's actually rather easily doable, but would potentially
cripple performance quite a bit.

I can point you to the necessary bits of code if you are interested in that.

You are receiving this mail because:
You are the assignee for the bug.
You are the QA Contact for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/mesa-dev/attachments/20190627/1ab6b4d0/attachment.html>

More information about the mesa-dev mailing list