Any chance to run acpi_cpufreq on ATOM N270 (HP Mini)?
in [Suse]
|
Prev: Why does
Next: openSUSE 11.3-RC1 - powernow-K8 on AMD ?
From: Mateusz Viste on 19 Jun 2010 02:10 Hi, Is there any way I could run acpi-cpufreq on an ATOM N270 CPU? When I try to modprobe it, the module doesn't load: hpmini:~ # modprobe acpi-cpufreq FATAL: Error inserting acpi_cpufreq (/lib/modules/2.6.31.12-0.2-desktop/kernel/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.ko): No such device ....and I am pretty sure that N270 does have support for Speedstep. Well, at least according to Intel, it does: http://ark.intel.com/Product.aspx?id=36331 My kernel is in version 2.6.31.12-0 (OpenSUSE v11.2), and the PC is actually a HP Mini netbook. On the other hand, p4clockmod is loading without any problem, but p4cockmod is definitely not what I am looking for. :) So... is there any happy HP Mini owner out there that managed to use SpeedStep with OpenSUSE? Best regards, Mateusz Viste
From: UpGrade on 19 Jun 2010 03:21 On Sat, 19 Jun 2010 08:10:46 +0200, Mateusz Viste <mateusz(a)no-spam.please> wrote: >Hi, > >Is there any way I could run acpi-cpufreq on an ATOM N270 CPU? >When I try to modprobe it, the module doesn't load: > >hpmini:~ # modprobe acpi-cpufreq >FATAL: Error inserting acpi_cpufreq >(/lib/modules/2.6.31.12-0.2-desktop/kernel/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.ko): >No such device > >...and I am pretty sure that N270 does have support for Speedstep. Well, >at least according to Intel, it does: >http://ark.intel.com/Product.aspx?id=36331 > >My kernel is in version 2.6.31.12-0 (OpenSUSE v11.2), and the PC is >actually a HP Mini netbook. > >On the other hand, p4clockmod is loading without any problem, but >p4cockmod is definitely not what I am looking for. :) > >So... is there any happy HP Mini owner out there that managed to use >SpeedStep with OpenSUSE? > >Best regards, >Mateusz Viste If this is overclocking, I think you have too much time on your hands. At the standard rate, they play BluRay and other high rate streams and decode ops just fine. Also, why would Intel lie? D'oh! Why screw with it? Overclock a real motherboard and processor. Attempting to do it with this will likely only get you a heat related FOOL failure. You should have bought the Acer.
From: Malcolm on 19 Jun 2010 10:16 On Sat, 19 Jun 2010 08:10:46 +0200 Mateusz Viste <mateusz(a)no-spam.please> wrote: > Hi, > > Is there any way I could run acpi-cpufreq on an ATOM N270 CPU? > When I try to modprobe it, the module doesn't load: > > hpmini:~ # modprobe acpi-cpufreq > FATAL: Error inserting acpi_cpufreq > (/lib/modules/2.6.31.12-0.2-desktop/kernel/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.ko): > No such device > > ...and I am pretty sure that N270 does have support for Speedstep. > Well, at least according to Intel, it does: > http://ark.intel.com/Product.aspx?id=36331 > > My kernel is in version 2.6.31.12-0 (OpenSUSE v11.2), and the PC is > actually a HP Mini netbook. > > On the other hand, p4clockmod is loading without any problem, but > p4cockmod is definitely not what I am looking for. :) > > So... is there any happy HP Mini owner out there that managed to use > SpeedStep with OpenSUSE? > > Best regards, > Mateusz Viste Hi It worked fine on my ASUS netbook N280 with 11.2, on 11.3 testing in RC1 it didn't load for some reason and have to do it manually. https://bugzilla.novell.com/show_bug.cgi?id=615644 -- Cheers Malcolm ��� (Linux Counter #276890) SUSE Linux Enterprise Desktop 11 (x86_64) Kernel 2.6.32.12-0.7-default up 2 days 10:00, 3 users, load average: 0.02, 0.04, 0.00 GPU GeForce 8600 GTS Silent - Driver Version: 195.36.31
From: VioletaPachydermata on 19 Jun 2010 12:26 On Sat, 19 Jun 2010 09:16:08 -0500, Malcolm <malcolm_nospamlewis(a)bellsouth.net> wrote: >Hi >It worked fine on my ASUS netbook N280 with 11.2, on 11.3 testing in >RC1 it didn't load for some reason and have to do it manually. So, what you guys are doing is creating no more than a quicker battery burner so that your typically idle laptop cpu can sit and do nothing even faster. Unless you are decoding video, I don't see a reason. If you would even consider using a laptop for something like weather modeling or PCB auto-routing, you are doing nothing but wasting batteries, as such things should take place on desktop workstations. So I still find it hard to understand why you need your browser or email client to pop up one second quicker than it did before. When you are mobile, you are not gaining anything useful, particularly when charge life is considered. Don't try to spout life length numbers, because you cannot make a comparison unless the two machines perform a full cpu intensive task the whole time on both.
From: Mateusz Viste on 19 Jun 2010 14:25
On Saturday 19 June 2010 09:21, UpGrade wrote: > If this is overclocking, No, it is not. > I think you have too much time on your hands. You clearly didn't understood (or misunderstood) my initial post. > Attempting to do it with this will likely only get you a heat related > FOOL failure. Actually, what I am trying to achieve is to *lower* the temperature (and battery lifetime), by lowering the CPU freq and voltage when the system is idle. That's what cpufreq is about. Best regards, Mateusz Viste |