From mboxrd@z Thu Jan 1 00:00:00 1970 From: Simon Braunschmidt Subject: Re: [QUESTION] 3 frequency steps for p3 on windows Date: Tue, 17 May 2005 17:11:44 +0200 Message-ID: <200505171711.45444.brasimon@web.de> References: <200505122253.18630.brasimon@web.de> Mime-Version: 1.0 Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: <200505122253.18630.brasimon@web.de> Content-Disposition: inline List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: cpufreq-bounces@lists.linux.org.uk Errors-To: cpufreq-bounces+glkc-cpufreq=gmane.org@lists.linux.org.uk Content-Type: text/plain; charset="iso-8859-1" To: cpufreq@lists.linux.org.uk Am Donnerstag, 12. Mai 2005 22:53 schrieb Simon Braunschmidt: > Hi, > > I have a compaq armada m300 with a speedstep-enabled 600mhz pentium. > It is running ubuntu so its essentialy a 2.6.10 kernel. > Scaling the frequency dynamically works very good so far, i can choose > between ~500mhz and ~600mhz. > > However, when i boot into windows xp sp2, after installing some enabler > programm from the compaq website, the freqency of the cpu is scaled > dynamically with the THREE steps ~413mhz, ~500mhz and ~600mhz, the exact > values for 500 and 600 being the same as in linux. > > So in windows i get an extra frequency option for 413mhz not available in > linux. > > Is there any chance of supporting this in linux? Since i only ever heard = of > 2 frequency steps for the early p3's, i think this will be a > compaq-specific behaviour. Is compaq giving out documentation? > > please cc me > > Greetings > Simon Braunschmidt > After some (random) experimentation (changing from ac to battery while in s= 3=20 state, maybe something more, didnt take notes, seems all unrelated), the=20 frequency steping in linux was ~415mhz and ~500mhz. The values=20 in /sys=AD=AD/.../cpufreq stayed the same, and the max. frequency was now ~= 500mhz=20 (the 600mhz diddnt seem to work anymore). This behaviour was gone after a reboot and i hadnt been able to reproduce i= t,=20 strange. So in principle it is possible under linux to use the "compaq 3 steps=20 behaviour", but the inner workings need to be understood. Any pointers wher= e=20 i could start? Greetings Simon Braunschmidt > > simon@heimdal:/sys/devices/system/cpu/cpu0/cpufreq$ uname -a > Linux heimdal 2.6.10-5-686 #1 Tue Apr 5 12:27:02 UTC 2005 i686 GNU/Linux > > simon@heimdal:/sys/devices/system/cpu/cpu0/cpufreq$ cat /proc/cpuinfo > processor : 0 > vendor_id : GenuineIntel > cpu family : 6 > model : 8 > model name : Pentium III (Coppermine) > stepping : 3 > cpu MHz : 498.115 > cache size : 256 KB > fdiv_bug : no > hlt_bug : no > f00f_bug : no > coma_bug : no > fpu : yes > fpu_exception : yes > cpuid level : 2 > wp : yes > flags : fpu vme de pse tsc msr pae mce cx8 sep mtrr pge mca cmov > pat pse36 mmx fxsr sse > bogomips : 986.45 > > simon@heimdal:/sys/devices/system/cpu/cpu0/cpufreq$ sudo cat * > Password: > 0 > 500000 > 600000 > 500000 > 600000 500000 > userspace ondemand powersave performance > 500000 > speedstep-smi > userspace > 600000 > 500000 > 500000 > simon@heimdal:/sys/devices/system/cpu/cpu0/cpufreq$