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

[Jesse Barnes]

On Fri, 7 Aug 2009 20:35:36 +0200
Erik Andrén <erik.andren at gmail.com> wrote:

> 2009/8/7 Jesse Barnes <jbarnes at virtuousgeek.org>:
> > 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...
> >
> 
> What are the software requirements to test these patches out?

We've been testing & developing against Eric's drm-intel-next branch as
of a couple of weeks ago...  If you have a KMS setup working, you'd
just need to load the i915 driver with the patch built in.

-- 
Jesse Barnes, Intel Open Source Technology Center