On Thu, Feb 09, 2017 at 11:38:31AM -0800, Jason Ekstrand wrote:
> On Thu, Feb 9, 2017 at 10:33 AM, Nanley Chery wrote:
>
> > On Wed, Feb 08, 2017 at 06:27:52PM -0800, Jason Ekstrand wrote:
> > > On Wed, Feb 8, 2017 at 5:34 PM, Nanley Chery
> > wrote:
> > >
> > > > On Thu, Feb 02, 2017 at 01:26:0
On Thu, Feb 9, 2017 at 10:33 AM, Nanley Chery wrote:
> On Wed, Feb 08, 2017 at 06:27:52PM -0800, Jason Ekstrand wrote:
> > On Wed, Feb 8, 2017 at 5:34 PM, Nanley Chery
> wrote:
> >
> > > On Thu, Feb 02, 2017 at 01:26:05PM -0800, Jason Ekstrand wrote:
> > > > In order to get good performance numb
On Wed, Feb 08, 2017 at 09:38:52PM -0800, Jason Ekstrand wrote:
> On Wed, Feb 8, 2017 at 8:11 PM, Jason Ekstrand wrote:
>
> > On Wed, Feb 8, 2017 at 6:27 PM, Jason Ekstrand
> > wrote:
> >
> >> On Wed, Feb 8, 2017 at 5:34 PM, Nanley Chery
> >> wrote:
> >>
> >>> On Thu, Feb 02, 2017 at 01:26:05PM
On Wed, Feb 08, 2017 at 06:27:52PM -0800, Jason Ekstrand wrote:
> On Wed, Feb 8, 2017 at 5:34 PM, Nanley Chery wrote:
>
> > On Thu, Feb 02, 2017 at 01:26:05PM -0800, Jason Ekstrand wrote:
> > > In order to get good performance numbers for this, I had to hack up the
> > > driver to whack wm_prog_d
On Wed, Feb 8, 2017 at 8:11 PM, Jason Ekstrand wrote:
> On Wed, Feb 8, 2017 at 6:27 PM, Jason Ekstrand
> wrote:
>
>> On Wed, Feb 8, 2017 at 5:34 PM, Nanley Chery
>> wrote:
>>
>>> On Thu, Feb 02, 2017 at 01:26:05PM -0800, Jason Ekstrand wrote:
>>> > In order to get good performance numbers for t
On Wed, Feb 8, 2017 at 6:27 PM, Jason Ekstrand wrote:
> On Wed, Feb 8, 2017 at 5:34 PM, Nanley Chery
> wrote:
>
>> On Thu, Feb 02, 2017 at 01:26:05PM -0800, Jason Ekstrand wrote:
>> > In order to get good performance numbers for this, I had to hack up the
>> > driver to whack wm_prog_data::uses_
On Wed, Feb 8, 2017 at 5:34 PM, Nanley Chery wrote:
> On Thu, Feb 02, 2017 at 01:26:05PM -0800, Jason Ekstrand wrote:
> > In order to get good performance numbers for this, I had to hack up the
> > driver to whack wm_prog_data::uses_kill to true to emulate a discard and
> > used the Sascha "shado
On Thu, Feb 02, 2017 at 01:26:05PM -0800, Jason Ekstrand wrote:
> In order to get good performance numbers for this, I had to hack up the
> driver to whack wm_prog_data::uses_kill to true to emulate a discard and
> used the Sascha "shadowmapping" demo. Setting uses_kill to true dropped
> the frame
In order to get good performance numbers for this, I had to hack up the
driver to whack wm_prog_data::uses_kill to true to emulate a discard and
used the Sascha "shadowmapping" demo. Setting uses_kill to true dropped
the framerate on the demo by 25-30%. Enabling the PMA fix brought it
back up to