Quoting Ville Syrjälä (2018-07-20 15:19:20)
> On Fri, Jul 20, 2018 at 03:03:09PM +0100, Chris Wilson wrote:
> > Quoting Ville Syrjälä (2018-07-20 14:50:25)
> > > On Fri, Jul 20, 2018 at 02:38:32PM +0100, Chris Wilson wrote:
> > > > Quoting Ville Syrjälä (2018-07-20 14:32:40)
> > > > > Another quest
Quoting Tvrtko Ursulin (2018-07-20 15:58:51)
> True, it only catches the imbalance in one direction quickly. If suspend
> idea works go with that, but what's so bad about some log messages?
> Assuming leak towards the overflow direction on each flip it could be
> reached in ~18 hours which is re
On 20/07/2018 14:59, Chris Wilson wrote:
Quoting Tvrtko Ursulin (2018-07-20 14:29:52)
On 20/07/2018 14:02, Chris Wilson wrote:
Quoting Tvrtko Ursulin (2018-07-20 13:49:09)
On 12/07/2018 18:38, Chris Wilson wrote:
+ if (rps->interactive)
+ new_power = HIGH_POWER;
+ rps_s
On Fri, Jul 20, 2018 at 03:03:09PM +0100, Chris Wilson wrote:
> Quoting Ville Syrjälä (2018-07-20 14:50:25)
> > On Fri, Jul 20, 2018 at 02:38:32PM +0100, Chris Wilson wrote:
> > > Quoting Ville Syrjälä (2018-07-20 14:32:40)
> > > > Another question is what happens where there are parallel flips
> >
Quoting Ville Syrjälä (2018-07-20 14:50:25)
> On Fri, Jul 20, 2018 at 02:38:32PM +0100, Chris Wilson wrote:
> > Quoting Ville Syrjälä (2018-07-20 14:32:40)
> > > Another question is what happens where there are parallel flips
> > > happening? One could undo the boost from the other AFAICS. But mayb
Quoting Tvrtko Ursulin (2018-07-20 14:29:52)
>
> On 20/07/2018 14:02, Chris Wilson wrote:
> > Quoting Tvrtko Ursulin (2018-07-20 13:49:09)
> >>
> >> On 12/07/2018 18:38, Chris Wilson wrote:
> >>> + if (rps->interactive)
> >>> + new_power = HIGH_POWER;
> >>> + rps_set_power(dev_
On Fri, Jul 20, 2018 at 02:38:32PM +0100, Chris Wilson wrote:
> Quoting Ville Syrjälä (2018-07-20 14:32:40)
> > On Fri, Jul 20, 2018 at 02:14:11PM +0100, Chris Wilson wrote:
> > > Quoting Ville Syrjälä (2018-07-20 14:07:31)
> > > > On Fri, Jul 20, 2018 at 02:02:34PM +0100, Chris Wilson wrote:
> > >
Quoting Ville Syrjälä (2018-07-20 14:32:40)
> On Fri, Jul 20, 2018 at 02:14:11PM +0100, Chris Wilson wrote:
> > Quoting Ville Syrjälä (2018-07-20 14:07:31)
> > > On Fri, Jul 20, 2018 at 02:02:34PM +0100, Chris Wilson wrote:
> > > Doing this kind of global thing from the plane hooks seems a bit
> >
On Fri, Jul 20, 2018 at 02:14:11PM +0100, Chris Wilson wrote:
> Quoting Ville Syrjälä (2018-07-20 14:07:31)
> > On Fri, Jul 20, 2018 at 02:02:34PM +0100, Chris Wilson wrote:
> > Doing this kind of global thing from the plane hooks seems a bit
> > strange. How about just doing this directly from com
On 20/07/2018 14:02, Chris Wilson wrote:
Quoting Tvrtko Ursulin (2018-07-20 13:49:09)
On 12/07/2018 18:38, Chris Wilson wrote:
diff --git a/drivers/gpu/drm/i915/intel_display.c
b/drivers/gpu/drm/i915/intel_display.c
index 7998e70a3174..5809366ff9f0 100644
--- a/drivers/gpu/drm/i915/intel_dis
Quoting Ville Syrjälä (2018-07-20 14:07:31)
> On Fri, Jul 20, 2018 at 02:02:34PM +0100, Chris Wilson wrote:
> Doing this kind of global thing from the plane hooks seems a bit
> strange. How about just doing this directly from commit_tail()
> etc.?
We want it upfront in prepare (so that it's set be
On Fri, Jul 20, 2018 at 02:02:34PM +0100, Chris Wilson wrote:
> Quoting Tvrtko Ursulin (2018-07-20 13:49:09)
> >
> > On 12/07/2018 18:38, Chris Wilson wrote:
> > > diff --git a/drivers/gpu/drm/i915/intel_display.c
> > > b/drivers/gpu/drm/i915/intel_display.c
> > > index 7998e70a3174..5809366ff9f0
Quoting Tvrtko Ursulin (2018-07-20 13:49:09)
>
> On 12/07/2018 18:38, Chris Wilson wrote:
> > diff --git a/drivers/gpu/drm/i915/intel_display.c
> > b/drivers/gpu/drm/i915/intel_display.c
> > index 7998e70a3174..5809366ff9f0 100644
> > --- a/drivers/gpu/drm/i915/intel_display.c
> > +++ b/drivers/g
On 12/07/2018 18:38, Chris Wilson wrote:
RPS provides a feedback loop where we use the load during the previous
evaluation interval to decide whether to up or down clock the GPU
frequency. Our responsiveness is split into 3 regimes, a high and low
plateau with the intent to keep the gpu clocked
RPS provides a feedback loop where we use the load during the previous
evaluation interval to decide whether to up or down clock the GPU
frequency. Our responsiveness is split into 3 regimes, a high and low
plateau with the intent to keep the gpu clocked high to cover occasional
stalls under high l
15 matches
Mail list logo
