[ltp] Re: Comparison: rovclock and PowerPlay

[Alex Deucher]

On 8/29/06, David Abrahams <dave@boost-consulting.com> wrote:
> "Matthias Redlich" <matthias.redlich@gmx.de> writes:
>
> > Hello,
> >
> > I use a ThinkPad R52 with an ATI Radeon Mobility x300. I have always
> > used fglrx with ATI Powerplay to save power. I am using my laptop for
> > office tasks and programming only so I do not need extraordninary
> > graphics.
>
> I am in the same situation with different equipment.  I need lots of
> resolution, so IBM decided I must be a gamer and stuffed too much
> power into the GPU ;-)
>
> Unfortunately, it gets really hot.  It's routinely at 70 degrees
> centigrade when idling in the lowest power state.  In higher power
> states, it gets really, really hot at idle unless the fan runs hard
> (god help you if a 3d screensaver kicks in). And worse for me, ATI
> decided not to enable any low-power states when in dual-head mode (but
> read on...)
>
>   Aside: I have to say, I don't understand the output of the following
>   on my machine
>
>     $ sudo aticonfig --set-powerstate=1
>     $ aticonfig --lsp
>         core/mem      [flags]
>     -----------------
>       1: 128/135 MHz  [low voltage]
>     *    209/135 MHz  [low voltage]
>       2: 324/135 MHz
>       3: 398/324 MHz  [default state]
>
>   It seems to indicate that I'm in an odd, unnumbered state we could
>   call "1.5" that uses a higher core frequency than I'd get in state
>   1.  If anyone knows what this means I'd love to hear it.
>
> > Now I wonder whether rovclock or Powerplay is better for power saving
> > and lower temperature (fan always-on problem). Has anybody got a
> > comparison? What about temperature? Do you have other good hints to
> > reduce the power consumption of your ATI card?
>
> Well, I just tried rovclock and it hosed my display.  Haven't tried it
> since.

the new Avivo based radeons have a completely new display engine, and
the register layout has changed significantly.  It's doubtful rovclock
will work at all on avivo based radeons since the clock registers have
probably changed locations.

>
> Well, I've been playing around with ACPI and hotkeys and just
> discovered some really interesting things.  Before I could use the
> video hotkey I had to enable all the hotkeys with
>
>   sudo echo 0xffff > /proc/acpi/ibm/hotkey
>
> (stuck it in my /etc/rc.local actually).  Without customizing the
> event response, /etc/acpi/events/ibm-videobtn was just a do-nothing
> stub, but the button actually did lots: it would cycle through all
> combinations of screens I had connected.  Brilliant!

ibm_acpi takes over the buttons, when it does they produce button
events which you can use to call scripts, etc.  when ibm_acpi doesn't
claim the buttons, then the bios controls them and they call into the
radeon bios to toggle displays and such.  the bios and the X driver
don't know about each other so they are messing with register state
without the other's knowledge.

Alex