Subject: Re: speedstep and the 133mhz fsb chips
To: None <email@example.com>
From: Michael van Elst <firstname.lastname@example.org>
Date: 12/28/2005 23:27:11
email@example.com (Tom Spindler) writes:
> points out that BSEL[1:0] indicates the FSB multiplier; currently, the
> speedstep code assumes that the frequency will always increase in units
> of 100Mhz. This isn't the case for some of the newer chips - they use
> 133Mhz instead (which explains why my 1.86Ghz chip shows up as 1.4Ghz.)
I guess it is FSB/4. Maybe someone can verify this with a processor
with FSB800 and Enhanced Speedstep?
> lists the voltages for the 90nm-process chips; somewhat vexingly, while
> it gives a fixed voltage for the 'battery optimized mode', this
> changes for the lowest-powered chips - and the 'maximum performance'
> is a big ol' range of voltages (save for the 778, which has a lower
> maximum performance voltage than any of the rest.)
The est driver knows a couple of chips. It is possible to
extend its table with data for the FSB533 processors, at
least for the two datapoints given by Intel. I am currently
doing this for a Pentium M 780 (2.26GHz FSB533) and it
switches nicely between 800MHz and 2.26GHz (est shows
600MHz and 1700GHz).
A real solution however should query that data from the ACPI-BIOS.