On Wed, Jan 11, 2017 at 10:16:06AM +0200, Martin Peres wrote:
> On 10/01/17 23:23, Chris Wilson wrote:
> >Not much has changed in the couple of years since last posting, just a
> >lot of rebasing.
> >
> >Still the major open question is how much locking do individual contexts
> >require amongst a shared set - can we rely of the upper layer providing
> >sufficient serialisation around access to brw_context?
> >
> >The 40% improvement for silly relocation microbenchmarks is still there.
> >-Chris
>
> Thanks for doing this!
>
> On top of what commit did you base this work? I wanted to quickly
> let some machines run on it (piglit, deqp, rendering and performance
> testing) but it does not apply on mesa HEAD anymore.
There's a pair of Werror and pthread-stub patches in between to allow me
to catch build errors and prevent the then breakage of recursive
mutexes. (I'm used to git just ignoring little details like that! ;)
It was meant to be applicable to
commit 860d91ec5b1381b261e6776466154f375dfe125b
Author: Lionel Landwerlin <lionel.g.landwer...@intel.com>
Date: Tue Jan 10 12:46:25 2017 +0000
anv: set input_slots_valid on brw_wm_prog_key
Sorry about that.
> https://cgit.freedesktop.org/~ickle/mesa/log/?h=brw-batch seems also
> a bit out of date.
Resynced.
-Chris
--
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
