[Mesa-dev] [PATCH 7/7] i965/gen7+: Implement fast color clears for MSAA buffers.

Anuj Phogat anuj.phogat at gmail.com
Thu Dec 5 10:23:58 PST 2013


On Thu, Dec 5, 2013 at 4:36 AM, Paul Berry <stereotype441 at gmail.com> wrote:
> On 4 December 2013 15:07, Chad Versace <chad.versace at linux.intel.com> wrote:
>>
>>
>> bugget, verticeally, and vestically! oh my!
>
>
> Wow, I wish I could say I did all those typos on purpose.  Those are
> hilarious!
>
> They're all fixed now.
>
>>
>>
>> Patches 1-6 are
>> Reviewed-by: Chad Versace <chad.versace at linux.intel.com>
>>
>> But this patch 7... If the user specifies an ill-aligned clear rectangle,
>> does this code clear a slightly larger, well-aligned rectangle? In other
>> words,
>> will this clear pixels outside the user-specified clear rectangle? Local
>> inspection of the code suggests so to me. But my global understanding of
>> these codepaths is vague.
>
>
> Ken is right in his response about this--partial fast clears never happen
> because of the !partial_clear check, so the extra pixels that get cleared
> are always outside the bounds of the buffer (and hence irrelevant).  Thanks
> to tiling, there's no worry about overflowing into memory owned by other
> regions--the extra pixels that get cleared always belong to tiles that
> contain in-bounds pixels.  In theory I believe we could do partial clears if
> we first verified that they were aligned, but (a) the bspec doesn't
> recommend it, and (b) I doubt there would be much benefit, since
> sufficiently aligned clears that don't clear the entire buffer are probably
> quite rare.
>
> I'll follow up with a patch that improves the comments to clarify this.
>
Reviewed-by: Anuj Phogat <anuj.phogat at gmail.com>

> _______________________________________________
> mesa-dev mailing list
> mesa-dev at lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/mesa-dev
>


More information about the mesa-dev mailing list