From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dominik Brodowski Subject: Re: my dothan didn't work with cpufreq... Date: Thu, 22 Jul 2004 08:04:37 +0200 Sender: cpufreq-bounces@www.linux.org.uk Message-ID: <20040722060437.GA8888@dominikbrodowski.de> References: <40F2FA8B.10307@lifl.fr> <20040713094937.GB8124@dominikbrodowski.de> <1090461320.13505.3.camel@localhost> Mime-Version: 1.0 Return-path: Content-Disposition: inline In-Reply-To: <1090461320.13505.3.camel@localhost> List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: cpufreq-bounces+glkc-cpufreq=gmane.org@www.linux.org.uk Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Jeremy Fitzhardinge Cc: cpufreq@www.linux.org.uk On Wed, Jul 21, 2004 at 06:55:20PM -0700, Jeremy Fitzhardinge wrote: > I've been meaning to look into this to see if there's some way to add a > table method. It's moderately tricky because there's two steppings of > Dothan, and the specs are not obvious to me (they seem to list 4 > voltages per frequency point, which is confusing). AFAICS in some specs, there are identical-looking (CPUID, string) Dothans with different voltage requirements, at least for the B1 stepping. Also, as the usage of the ACPI P-State library in speedstep-centrino seems to work flawlessly on Dothans [at least I haven't heard otherwise], I'm tempted to remove the "(EXPERIMENTAL)" mark on it and possibly make it even the default. What do you think? > I guess it would also be good to get dumps from the ACPI tables. What's > the best way to do that? acpi_pdump with pdc=1 as parameter. This test module can be grabbed here: http://www.brodo.de/patches/2004-04-06/cpufreq-acpi_pdump.c Dominik