[Mesa-dev] [PATCH 4/4] i965: Orphan storage in MapBufferRange if invalidating all valid data.

[Kenneth Graunke]

On Thursday, July 13, 2017 3:04:59 PM PDT Jason Ekstrand wrote:
> Do you have any data on how much this helps?  Regardless, the series is
> 
> Reviewed-by: Jason Ekstrand <jason at jlekstrand.net>

Thanks!  It turns out that, no, I don't have any data on this patch.

I'd originally found it helpful, but I had been testing a broken version
which assumed that GL_MAP_WRITE_BIT implied the mapped region would be
overwritten...but it doesn't, unless you have GL_MAP_INVALIDATE_RANGE_BIT.

With that fixed, I'm not seeing this condition ever trigger in any of the
workloads I looked at.

It still seems like the right thing to do, but maybe I should hold off for
now.  (I should also implement InvalidateBufferSubData...)

Patches 1-3 are still definitely useful.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 833 bytes
Desc: This is a digitally signed message part.
URL: <https://lists.freedesktop.org/archives/mesa-dev/attachments/20170713/8573c991/attachment.sig>