Pentium D 915 support

Pentium D 915 support

[Erik Slagter]

[-- Attachment #1.1: Type: text/plain, Size: 3526 bytes --]

Hi,

I just bought a new motherboard and cpu and carefully checked whether
both support EIST.

The motherboard is a ASUStek P5WDG2-WS, the cpu a Pentium D 915. This
seems to be the only (besides the 945) from the 9xx series that has
proper EIST support (new stepping), according to the intel
processorfinder.

I already learned that I need to use speedstep-centrino (odd...) but the
module doesn't load (not found message).

I guess this cpu is too new to have cpufreq support (I am running with
kernel 2.6.18-rc2, btw), so I had a peek in the source file, and found a
table with apparently cpuid values. The values of my D915 were not there
(as expected). So I added it and changed two other places, and it looks
(very superfluously) that this should be enough to make it work, at
least to make the module recognise the cpu.

I don't dare to test it though, I don't know if I can break stuff this
way (like really, permanently...).

Can you please have a look and give your comments?

cat /proc/cpuinfo:

> cpuinfo
> processor       : 0
> vendor_id       : GenuineIntel
> cpu family      : 15
> model           : 6
> model name      :               Intel(R) Pentium(R) D CPU 2.80GHz
> stepping        : 4
> cpu MHz         : 2800.000
> cache size      : 2048 KB
> physical id     : 0
> siblings        : 2
> core id         : 0
> cpu cores       : 2
> fpu             : yes
> fpu_exception   : yes
> cpuid level     : 6
> wp              : yes
> flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl est cid cx16 xtpr lahf_lm
> bogomips        : 5623.94
> clflush size    : 64
> cache_alignment : 128
> address sizes   : 36 bits physical, 48 bits virtual
> power management:
> 
> processor       : 1
> vendor_id       : GenuineIntel
> cpu family      : 15
> model           : 6
> model name      :               Intel(R) Pentium(R) D CPU 2.80GHz
> stepping        : 4
> cpu MHz         : 2800.000
> cache size      : 2048 KB
> physical id     : 0
> siblings        : 2
> core id         : 1
> cpu cores       : 2
> fpu             : yes
> fpu_exception   : yes
> cpuid level     : 6
> wp              : yes
> flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl est cid cx16 xtpr lahf_lm
> bogomips        : 5620.20
> clflush size    : 64
> cache_alignment : 128
> address sizes   : 36 bits physical, 48 bits virtual
> power management:

This is what I did to speedstep-centrino.c:

--- speedstep-centrino.c        2006-07-30 15:02:25.000000000 +0200
+++ speedstep-centrino.c-ems    2006-07-30 15:01:04.000000000 +0200
@@ -50,6 +50,7 @@
        CPU_DOTHAN_B0,
        CPU_MP4HT_D0,
        CPU_MP4HT_E0,
+       CPU_PD900,
 };

 static const struct cpu_id cpu_ids[] = {
@@ -59,6 +60,7 @@
        [CPU_DOTHAN_B0] = { 6, 13, 6 },
        [CPU_MP4HT_D0]  = {15,  3, 4 },
        [CPU_MP4HT_E0]  = {15,  4, 1 },
+       [CPU_PD900]             = {15,  6, 4 },
 };
 #define N_IDS  ARRAY_SIZE(cpu_ids)

@@ -226,6 +228,7 @@
        { &cpu_ids[CPU_DOTHAN_B0], NULL, 0, NULL },
        { &cpu_ids[CPU_MP4HT_D0], NULL, 0, NULL },
        { &cpu_ids[CPU_MP4HT_E0], NULL, 0, NULL },
+       { &cpu_ids[CPU_PD900], NULL, 0, NULL },

        { NULL, }
 };

Thank you for your time.

[-- Attachment #1.2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 2771 bytes --]

[-- Attachment #2: Type: text/plain, Size: 147 bytes --]

_______________________________________________
Cpufreq mailing list
Cpufreq@lists.linux.org.uk
http://lists.linux.org.uk/mailman/listinfo/cpufreq

Re: Pentium D 915 support

[Alexey Starikovskiy]

Do you have acpi support disabled in your kernel? Cpufreq driver should get information from it for new processors.
Regards,
Alex

Erik Slagter wrote:
> Hi,
> 
> I just bought a new motherboard and cpu and carefully checked whether
> both support EIST.
> 
> The motherboard is a ASUStek P5WDG2-WS, the cpu a Pentium D 915. This
> seems to be the only (besides the 945) from the 9xx series that has
> proper EIST support (new stepping), according to the intel
> processorfinder.
> 
> I already learned that I need to use speedstep-centrino (odd...) but the
> module doesn't load (not found message).
> 
> I guess this cpu is too new to have cpufreq support (I am running with
> kernel 2.6.18-rc2, btw), so I had a peek in the source file, and found a
> table with apparently cpuid values. The values of my D915 were not there
> (as expected). So I added it and changed two other places, and it looks
> (very superfluously) that this should be enough to make it work, at
> least to make the module recognise the cpu.
> 
> I don't dare to test it though, I don't know if I can break stuff this
> way (like really, permanently...).
> 
> Can you please have a look and give your comments?
> 
> cat /proc/cpuinfo:
> 
>> cpuinfo
>> processor       : 0
>> vendor_id       : GenuineIntel
>> cpu family      : 15
>> model           : 6
>> model name      :               Intel(R) Pentium(R) D CPU 2.80GHz
>> stepping        : 4
>> cpu MHz         : 2800.000
>> cache size      : 2048 KB
>> physical id     : 0
>> siblings        : 2
>> core id         : 0
>> cpu cores       : 2
>> fpu             : yes
>> fpu_exception   : yes
>> cpuid level     : 6
>> wp              : yes
>> flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl est cid cx16 xtpr lahf_lm
>> bogomips        : 5623.94
>> clflush size    : 64
>> cache_alignment : 128
>> address sizes   : 36 bits physical, 48 bits virtual
>> power management:
>>
>> processor       : 1
>> vendor_id       : GenuineIntel
>> cpu family      : 15
>> model           : 6
>> model name      :               Intel(R) Pentium(R) D CPU 2.80GHz
>> stepping        : 4
>> cpu MHz         : 2800.000
>> cache size      : 2048 KB
>> physical id     : 0
>> siblings        : 2
>> core id         : 1
>> cpu cores       : 2
>> fpu             : yes
>> fpu_exception   : yes
>> cpuid level     : 6
>> wp              : yes
>> flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl est cid cx16 xtpr lahf_lm
>> bogomips        : 5620.20
>> clflush size    : 64
>> cache_alignment : 128
>> address sizes   : 36 bits physical, 48 bits virtual
>> power management:
> 
> This is what I did to speedstep-centrino.c:
> 
> --- speedstep-centrino.c        2006-07-30 15:02:25.000000000 +0200
> +++ speedstep-centrino.c-ems    2006-07-30 15:01:04.000000000 +0200
> @@ -50,6 +50,7 @@
>         CPU_DOTHAN_B0,
>         CPU_MP4HT_D0,
>         CPU_MP4HT_E0,
> +       CPU_PD900,
>  };
> 
>  static const struct cpu_id cpu_ids[] = {
> @@ -59,6 +60,7 @@
>         [CPU_DOTHAN_B0] = { 6, 13, 6 },
>         [CPU_MP4HT_D0]  = {15,  3, 4 },
>         [CPU_MP4HT_E0]  = {15,  4, 1 },
> +       [CPU_PD900]             = {15,  6, 4 },
>  };
>  #define N_IDS  ARRAY_SIZE(cpu_ids)
> 
> @@ -226,6 +228,7 @@
>         { &cpu_ids[CPU_DOTHAN_B0], NULL, 0, NULL },
>         { &cpu_ids[CPU_MP4HT_D0], NULL, 0, NULL },
>         { &cpu_ids[CPU_MP4HT_E0], NULL, 0, NULL },
> +       { &cpu_ids[CPU_PD900], NULL, 0, NULL },
> 
>         { NULL, }
>  };
> 
> Thank you for your time.
> 
> 
> ------------------------------------------------------------------------
> 
> _______________________________________________
> Cpufreq mailing list
> Cpufreq@lists.linux.org.uk
> http://lists.linux.org.uk/mailman/listinfo/cpufreq

Re: Pentium D 915 support

[Erik Slagter]

[-- Attachment #1.1: Type: text/plain, Size: 4523 bytes --]

On zo, 2006-07-30 at 19:33 +0400, Alexey Starikovskiy wrote:

Erik Slagter wrote:

> > The motherboard is a ASUStek P5WDG2-WS, the cpu a Pentium D 915. This
> > seems to be the only (besides the 945) from the 9xx series that has
> > proper EIST support (new stepping), according to the intel
> > processorfinder.
> > 
> > I already learned that I need to use speedstep-centrino (odd...) but the
> > module doesn't load (not found message).
> > 
> > I guess this cpu is too new to have cpufreq support (I am running with
> > kernel 2.6.18-rc2, btw), so I had a peek in the source file, and found a
> > table with apparently cpuid values. The values of my D915 were not there
> > (as expected). So I added it and changed two other places, and it looks
> > (very superfluously) that this should be enough to make it work, at
> > least to make the module recognise the cpu.
> > 
> > I don't dare to test it though, I don't know if I can break stuff this
> > way (like really, permanently...).

> Do you have acpi support disabled in your kernel? Cpufreq driver
> should get information from it for new processors.

I have acpi enabled. More precisely: 

> CONFIG_ACPI=y
> # CONFIG_ACPI_AC is not set
> # CONFIG_ACPI_BATTERY is not set
> # CONFIG_ACPI_BUTTON is not set
> # CONFIG_ACPI_VIDEO is not set
> # CONFIG_ACPI_HOTKEY is not set
> # CONFIG_ACPI_FAN is not set
> # CONFIG_ACPI_DOCK is not set
> CONFIG_ACPI_PROCESSOR=y
> CONFIG_ACPI_THERMAL=y
> # CONFIG_ACPI_ASUS is not set
> # CONFIG_ACPI_IBM is not set
> # CONFIG_ACPI_TOSHIBA is not set
> # CONFIG_ACPI_CUSTOM_DSDT is not set
> CONFIG_ACPI_BLACKLIST_YEAR=0
> # CONFIG_ACPI_DEBUG is not set
> CONFIG_ACPI_EC=y
> CONFIG_ACPI_POWER=y
> CONFIG_ACPI_SYSTEM=y
> CONFIG_X86_PM_TIMER=y
> CONFIG_ACPI_CONTAINER=y
> # CONFIG_ACPI_SBS is not set

Cpufreq:

> CONFIG_CPU_FREQ=y
> CONFIG_CPU_FREQ_TABLE=y
> CONFIG_CPU_FREQ_DEBUG=y
> CONFIG_CPU_FREQ_STAT=y
> # CONFIG_CPU_FREQ_STAT_DETAILS is not set
> CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
> # CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
> CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
> CONFIG_CPU_FREQ_GOV_POWERSAVE=y
> CONFIG_CPU_FREQ_GOV_USERSPACE=y
> CONFIG_CPU_FREQ_GOV_ONDEMAND=y
> CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y

> CONFIG_X86_POWERNOW_K8=m
> CONFIG_X86_POWERNOW_K8_ACPI=y
> CONFIG_X86_SPEEDSTEP_CENTRINO=m
> CONFIG_X86_SPEEDSTEP_CENTRINO_ACPI=y
> CONFIG_X86_ACPI_CPUFREQ=m

I tried all driver modules in turn. The acpi-cpufreq modules loads but
gives weird output (see later on). Powernow-k8 doesn't load which was to
be expected. But speedstep-centrino doesn't load either:

artemis root:... $ modprobe speedstep-centrino
FATAL: Error inserting speedstep_centrino (...speedstep-centrino.ko): No such device

dmesg doesn't say anything.

modprobe acpi-cpufreq does work but output of cpufreq-info shows:

> cpufrequtils 0.4: cpufreq-info (C) Dominik Brodowski 2004
> Report errors and bugs to linux@brodo.de, please.
> analyzing CPU 0:
>   driver: acpi-cpufreq
>   CPUs which need to switch frequency at the same time: 0
>   hardware limits: 2.40 GHz - 2.80 GHz
>   available frequency steps: 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.40 GHz  available cpufreq governors: conservative, ondemand, powersave, userspace, performance
>   current policy: frequency should be within 2.40 GHz and 2.80 GHz.
>                   The governor "performance" may decide which speed to use
>                   within this range.
>   current CPU frequency is 2.80 GHz.
> analyzing CPU 1:
>   driver: acpi-cpufreq
>   CPUs which need to switch frequency at the same time: 1
>   hardware limits: 2.40 GHz - 2.80 GHz
>   available frequency steps: 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.40 GHz  available cpufreq governors: conservative, ondemand, powersave, userspace, performance
>   current policy: frequency should be within 2.40 GHz and 2.80 GHz.
>                   The governor "performance" may decide which speed to use
>                   within this range.
>   current CPU frequency is 2.80 GHz.

Please note the amount of repeated same frequency.

Also, it strikes me that /proc/acpi/../power only shows C1, is this normal?

Last but not least: the loading or unloading of the module doesn't have
any effect on the actual power consumption, even with powersave governor
and both cores at 2.4 Ghz (both at 140 W).

[-- Attachment #1.2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 2771 bytes --]

[-- Attachment #2: Type: text/plain, Size: 147 bytes --]

_______________________________________________
Cpufreq mailing list
Cpufreq@lists.linux.org.uk
http://lists.linux.org.uk/mailman/listinfo/cpufreq

Re: Pentium D 915 support

[Thomas Renninger]

On Sun, 2006-07-30 at 17:58 +0200, Erik Slagter wrote:
> On zo, 2006-07-30 at 19:33 +0400, Alexey Starikovskiy wrote:
> modprobe acpi-cpufreq does work but output of cpufreq-info shows:
> 
> > cpufrequtils 0.4: cpufreq-info (C) Dominik Brodowski 2004
> > Report errors and bugs to linux@brodo.de, please.
> > analyzing CPU 0:
> >   driver: acpi-cpufreq
> >   CPUs which need to switch frequency at the same time: 0
> >   hardware limits: 2.40 GHz - 2.80 GHz
> >   available frequency steps: 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.40 GHz  available cpufreq governors: conservative, ondemand, powersave, userspace, performance
> >   current policy: frequency should be within 2.40 GHz and 2.80 GHz.
> >                   The governor "performance" may decide which speed to use
> >                   within this range.
> >   current CPU frequency is 2.80 GHz.
> > analyzing CPU 1:
> >   driver: acpi-cpufreq
> >   CPUs which need to switch frequency at the same time: 1
> >   hardware limits: 2.40 GHz - 2.80 GHz
> >   available frequency steps: 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.40 GHz  available cpufreq governors: conservative, ondemand, powersave, userspace, performance
> >   current policy: frequency should be within 2.40 GHz and 2.80 GHz.
> >                   The governor "performance" may decide which speed to use
> >                   within this range.
> >   current CPU frequency is 2.80 GHz.
> 
> Please note the amount of repeated same frequency.
> 
I already saw something similar.
This is BIOS information, they probably want to take care that no
performance is lost and define 9 high and one low step.

> Also, it strikes me that /proc/acpi/../power only shows C1, is this normal?
> 
On a Pentium D, I'd say yes.

> Last but not least: the loading or unloading of the module doesn't have
> any effect on the actual power consumption, even with powersave governor
> and both cores at 2.4 Ghz (both at 140 W).
Strange. 2.4 GHz is still a lot?

Have you already searched for a new BIOS, if not better do that first.

     Thomas

Re: Pentium D 915 support

[Erik Slagter]

[-- Attachment #1.1: Type: text/plain, Size: 764 bytes --]

On do, 2006-08-03 at 13:44 +0200, Thomas Renninger wrote:
> > Please note the amount of repeated same frequency.
> I already saw something similar.
> This is BIOS information, they probably want to take care that no
> performance is lost and define 9 high and one low step.

What do you mean?

> > Last but not least: the loading or unloading of the module doesn't have
> > any effect on the actual power consumption, even with powersave governor
> > and both cores at 2.4 Ghz (both at 140 W).
> Strange. 2.4 GHz is still a lot?
> 
> Have you already searched for a new BIOS, if not better do that first.

The only difference between my BIOS version and the one available for
download is the support for "new cpu's" according to the ASUS website.

[-- Attachment #1.2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 2771 bytes --]

[-- Attachment #2: Type: text/plain, Size: 147 bytes --]

_______________________________________________
Cpufreq mailing list
Cpufreq@lists.linux.org.uk
http://lists.linux.org.uk/mailman/listinfo/cpufreq

Re: Pentium D 915 support

[Thomas Renninger]

On Thu, 2006-08-03 at 13:48 +0200, Erik Slagter wrote:
> On do, 2006-08-03 at 13:44 +0200, Thomas Renninger wrote:
> > > Please note the amount of repeated same frequency.
> > I already saw something similar.
> > This is BIOS information, they probably want to take care that no
> > performance is lost and define 9 high and one low step.
> 
> What do you mean?
available frequency steps: 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80
GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.40 GHz

They define 9 2.8 GHz frequency steps and one 2.4 GHz.
That means if OS is going down with speed step by step it will take a
while until you reach 2.4 GHz.
This could be intended (avoid possible performance losses), but also
just be a BIOS bug.

> 
> > > Last but not least: the loading or unloading of the module doesn't have
> > > any effect on the actual power consumption, even with powersave governor
> > > and both cores at 2.4 Ghz (both at 140 W).
> > Strange. 2.4 GHz is still a lot?
> > 
> > Have you already searched for a new BIOS, if not better do that first.
> 
> The only difference between my BIOS version and the one available for
> download is the support for "new cpu's" according to the ASUS website.
No idea whether it helps, but I would give it a try.

Maybe you find some specs on the Intel site what speed steps should be
supported and how many power/temperature gain you can get. 2.4 GHz
doesn't sound like you save a lot of energy...

   Thomas

Re: Pentium D 915 support

[Erik Slagter]

[-- Attachment #1.1: Type: text/plain, Size: 366 bytes --]

On do, 2006-08-03 at 16:56 +0200, Thomas Renninger wrote:
> Maybe you find some specs on the Intel site what speed steps should be
> supported and how many power/temperature gain you can get. 2.4 GHz
> doesn't sound like you save a lot of energy...

According to Alexey (@ intel.com) the processor simply only supports
two frequencies. I guess he can know...

[-- Attachment #1.2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 2771 bytes --]

[-- Attachment #2: Type: text/plain, Size: 147 bytes --]

_______________________________________________
Cpufreq mailing list
Cpufreq@lists.linux.org.uk
http://lists.linux.org.uk/mailman/listinfo/cpufreq

Re: Pentium D 915 support

[Alexey Starikovskiy]

Thomas, please stop misinforming...
Thomas Renninger wrote:
> On Thu, 2006-08-03 at 13:48 +0200, Erik Slagter wrote:
>> On do, 2006-08-03 at 13:44 +0200, Thomas Renninger wrote:
>>>> Please note the amount of repeated same frequency.
>>> I already saw something similar.
>>> This is BIOS information, they probably want to take care that no
>>> performance is lost and define 9 high and one low step.
>> What do you mean?
> available frequency steps: 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80
> GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.40 GHz
> 
> They define 9 2.8 GHz frequency steps and one 2.4 GHz.
> That means if OS is going down with speed step by step it will take a
> while until you reach 2.4 GHz.
Algorithm does not care about same P-steps. It will get to 2.4 in one step.
> This could be intended (avoid possible performance losses), but also
> just be a BIOS bug.
This is not BIOS bug, it is just a way to avoid dynamic memory allocation in BIOS.
And it has nothing to do with performance losses due to note above.

>>>> Last but not least: the loading or unloading of the module doesn't have
>>>> any effect on the actual power consumption, even with powersave governor
>>>> and both cores at 2.4 Ghz (both at 140 W).
>>> Strange. 2.4 GHz is still a lot?
>>>
>>> Have you already searched for a new BIOS, if not better do that first.
>> The only difference between my BIOS version and the one available for
>> download is the support for "new cpu's" according to the ASUS website.
> No idea whether it helps, but I would give it a try.

> 
> Maybe you find some specs on the Intel site what speed steps should be
> supported and how many power/temperature gain you can get. 2.4 GHz
> doesn't sound like you save a lot of energy...
Lowest frequency for P4 is 2.8 Ghz (14xFSB), PD is 2.4 (12xFSB), Core is 6x, but FSB is much higher.

Regards,
	Alex.

Re: Pentium D 915 support

[Erik Slagter]

[-- Attachment #1.1: Type: text/plain, Size: 421 bytes --]

On do, 2006-08-03 at 19:29 +0400, Alexey Starikovskiy wrote:
> > This could be intended (avoid possible performance losses), but also
> > just be a BIOS bug.
> This is not BIOS bug, it is just a way to avoid dynamic memory allocation in BIOS.
> And it has nothing to do with performance losses due to note above.

BTW Is there intention to correct the output of
cat /proc/acpi/processor/CPU?/performance as well?

[-- Attachment #1.2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 2771 bytes --]

[-- Attachment #2: Type: text/plain, Size: 147 bytes --]

_______________________________________________
Cpufreq mailing list
Cpufreq@lists.linux.org.uk
http://lists.linux.org.uk/mailman/listinfo/cpufreq

Re: Pentium D 915 support

[Alexey Starikovskiy]

Erik Slagter wrote:
> On do, 2006-08-03 at 19:29 +0400, Alexey Starikovskiy wrote:
>>> This could be intended (avoid possible performance losses), but also
>>> just be a BIOS bug.
>> This is not BIOS bug, it is just a way to avoid dynamic memory allocation in BIOS.
>> And it has nothing to do with performance losses due to note above.
> 
> BTW Is there intention to correct the output of
> cat /proc/acpi/processor/CPU?/performance as well?
Intention was to keep it as reference of BIOS output, so no, there is no intention to correct it, unless you give a
reason to do that.

Re: Pentium D 915 support

[Thomas Renninger]

> Thomas Renninger wrote:
> > available frequency steps: 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80
> > GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.80 GHz, 2.40 GHz
> > 
> Algorithm does not care about same P-steps. It will get to 2.4 in one step.
> This is not BIOS bug, it is just a way to avoid dynamic memory allocation in BIOS.
> And it has nothing to do with performance losses due to note above.

That makes sense, thanks for pointing that out,

    Thomas

RE: Pentium D 915 support

[Brown, Len]

>> BTW Is there intention to correct the output of
>> cat /proc/acpi/processor/CPU?/performance as well?

The way to correct this is to delete this file as soon as we can.

-Len

RE: Pentium D 915 support

[Erik Slagter]

[-- Attachment #1.1: Type: text/plain, Size: 284 bytes --]

On do, 2006-08-03 at 11:57 -0400, Brown, Len wrote:
> >> BTW Is there intention to correct the output of
> >> cat /proc/acpi/processor/CPU?/performance as well?
> 
> The way to correct this is to delete this file as soon as we can.

I already noticed the "deprecated" part ;-)

[-- Attachment #1.2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 2771 bytes --]

[-- Attachment #2: Type: text/plain, Size: 147 bytes --]

_______________________________________________
Cpufreq mailing list
Cpufreq@lists.linux.org.uk
http://lists.linux.org.uk/mailman/listinfo/cpufreq