cpufreq Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Alexey Starikovskiy <alexey_y_starikovskiy@linux.intel.com>
To: trenn@suse.de
Cc: cpufreq@lists.linux.org.uk
Subject: Re: Pentium D 915 support
Date: Thu, 03 Aug 2006 19:29:42 +0400	[thread overview]
Message-ID: <44D21666.5030304@linux.intel.com> (raw)
In-Reply-To: <1154617009.4302.515.camel@queen.suse.de>

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.

  parent reply	other threads:[~2006-08-03 15:29 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-07-30 13:12 Pentium D 915 support Erik Slagter
2006-07-30 15:33 ` Alexey Starikovskiy
2006-07-30 15:58   ` Erik Slagter
2006-08-03 11:44     ` Thomas Renninger
2006-08-03 11:48       ` Erik Slagter
2006-08-03 14:56         ` Thomas Renninger
2006-08-03 14:55           ` Erik Slagter
2006-08-03 15:29           ` Alexey Starikovskiy [this message]
2006-08-03 15:33             ` Erik Slagter
2006-08-03 15:51               ` Alexey Starikovskiy
2006-08-03 16:37             ` Thomas Renninger
  -- strict thread matches above, loose matches on Subject: below --
2006-08-03 15:57 Brown, Len
2006-08-03 16:29 ` Erik Slagter

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=44D21666.5030304@linux.intel.com \
    --to=alexey_y_starikovskiy@linux.intel.com \
    --cc=cpufreq@lists.linux.org.uk \
    --cc=trenn@suse.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox