[Intel-gfx] [PATCH] add LVDS downclocking support

[Jesse Barnes]

On Mon, 23 Mar 2009 00:30:11 +0000
Steven J Newbury <steve at snewbury.org.uk> wrote:

> On Sun, 2009-03-22 at 20:18 +0100, Erik Andrén wrote:
> > -----BEGIN PGP SIGNED MESSAGE-----
> > Hash: SHA1
> > 
> > 
> > 
> > Jesse Barnes wrote:
> > > This is a refreshed patch from Matthew Garrett to enable LVDS
> > > downclocking. 965+ hardware can do this automatically, but other
> > > 9xx chips need some help. So this patch adds some damage code to
> > > track idle time.  If we're idle for more than 500ms we downclock
> > > the display based on the value calculated at mode set time.
> > > 
> > > Comments & testing appreciated.  I've only tested on my GM45 so
> > > far, and I think to fully realize the benefits we'll need to
> > > enable self refresh, but it should help on many platforms as-is.
> > > 
> > 
> > Hi,
> > I've tested this on my 965GM laptop applied on top of Ubuntu Jauntys
> > 2.6.3 version of the intel driver. When measuring with my Energy
> > Monitor 3000 [1] I did not record any power savings at all. In fact,
> > I saw an increase of a couple of deciwatts. (Could be a measuring
> > error though).
> > Otherwise the system seemed stable and functioned as expected.
> > 
> > What is the expected power decrease when using this patch?
> > 
> > Best regards,
> > Erik Andrén
> > 
> > 
> > [1]
> > http://www.alamaison.com.au/p/361923/voltcraft-plus-energy-monitor-3000.html
> I'm not surprised you didn't see any change measuring power usage at
> the outlet.  Laptop power supplies are rarely switched mode, and
> typically provide their full rating while in use.  They aren't
> typically designed with energy efficiency in mind.
> 
> If you want to measure the energy efficiency of a laptop, your best
> bet is powertop when running from battery.

Have you guys had a chance to test the latest patchset from Matthew and
myself?  Seems to save quite a bit of power on my GM45 and 915GM test
machines...

-- 
Jesse Barnes, Intel Open Source Technology Center