[Bug 89597] Implement SSBOs in GLSL front-end and i965

[bugzilla-daemon at freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=89597

--- Comment #42 from Jason Ekstrand <jason at jlekstrand.net> ---
(In reply to Francisco Jerez from comment #38)
> (In reply to Iago Toral from comment #37)
> > If that is not a good idea, then I guess the alternative would be to do it
> > the other way around: fix the dispatch mask in the read/write messages to be
> > like the pixel mask we use in atomic operations, but I don't know if that is
> > possible.
> 
> AFAIK scattered DWORD read and write messages don't to take a
> sample mask independent from the execution mask.  It seems to me
> that they aren't particularly well-suited for this extension.
> Is there any reason you aren't using untyped surface reads and
> writes instead?  That would allow you to provide an explicit
> sample mask, share some code with ARB_shader_image_load_store by
> using the same instructions (I'll land my patches adding support
> for untyped surface writes shortly), and access up to 128 bits of
> data per channel and message, likely giving better performance in
> the long run.

I'll take the blame for that.  I'm not nearly as familiar with the image
read/write instructions as you are (having worked on load_store) and I wasn't
thinking about pixel masks at the time.  I previously used the scattered
read/write instructions for doing spilling on registers with indirects which is
why I suggested them.  It certainly sounds like the untyped image read/write
instructions are better suited for the task.

-- 
You are receiving this mail because:
You are the QA Contact for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.freedesktop.org/archives/intel-3d-bugs/attachments/20150504/88c6cf3a/attachment-0001.html>