public inbox for linux-pm@vger.kernel.org
 help / color / mirror / Atom feed
From: Simon Arlott <simon@fire.lp0.eu>
To: Peter Teoh <htmldeveloper@gmail.com>
Cc: Kernelnewbies <kernelnewbies@nl.linux.org>,
	linux-pm@lists.linux-foundation.org
Subject: Re: [Question] AMD opteron can support CPUfreq by per core ?
Date: Fri, 31 Oct 2008 17:16:58 +0000	[thread overview]
Message-ID: <490B3D8A.2070601@simon.arlott.org.uk> (raw)
In-Reply-To: <804dabb00810302006x7d59474bg27b716ffadf4515a@mail.gmail.com>

> On Thu, Oct 30, 2008 at 2:06 PM, MinChan Kim <minchan.kim@gmail.com> wrote:
>> Hi,  all,
>>
>> I want to test CPUfreq function in  AMD opteron quad-core series.
>> But I am not sure linux in now can support CPUfreq for ADM opteron by per core ?
>> What I mean is not controling to put together 2 core by one package
>> but control by per core.
>> After all, I want to control all 4 cpu separetely.
>>
>> Is is possible? If it is possible, What kinds of model can support ?

All Quad-Core AMD Opterons support using a separate CPU frequency per core.
All four cores are all independent, but afaik you'll only get a reduction in 
voltage based on the highest speed of all four cores.

You may want to ensure you get a motherboard with DDPM so the CPU and memory 
controller power is independent. http://www.tyan.com/tech/ddpm.aspx

Make sure you use a recent kernel which handles C1E properly.


On 31/10/08 03:06, Peter Teoh wrote:
> check this out:
> 
> http://osdir.com/ml/kernel.cpufreq/2004-07/msg00012.html
> 
> from the reply, since the power management flag is at the per-core
> level (check /proc/cpuinfo), all control can be done at the per-core
> level, hard-ware wise.   (not sure of Linux Kernel itself)
> 
> But at least 4 flags must be present (read above email):   ts, ttp, fid, vid.
> 
> I must also say this is the first time I am aware of these flags too :-).

Don't top post.

I've never heard of these flags - that email is from 2004.

model name	: Quad-Core AMD Opteron(tm) Processor 2354

flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc rep_good pni monitor cx16 lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs

[    5.569030] powernow-k8:    0 : pstate 0 (2200 MHz)
[    5.569136] powernow-k8:    1 : pstate 1 (2000 MHz)
[    5.569233] powernow-k8:    2 : pstate 2 (1700 MHz)
[    5.569330] powernow-k8:    3 : pstate 3 (1400 MHz)
[    5.569434] powernow-k8:    4 : pstate 4 (1100 MHz)
-- 
Simon Arlott

  parent reply	other threads:[~2008-10-31 17:16 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-10-30  6:06 [Question] AMD opteron can support CPUfreq by per core ? MinChan Kim
2008-10-31  3:06 ` Peter Teoh
     [not found] ` <804dabb00810302006x7d59474bg27b716ffadf4515a@mail.gmail.com>
2008-10-31  4:08   ` MinChan Kim
2008-10-31  4:10   ` Peter Teoh
2008-10-31 17:16   ` Simon Arlott [this message]
2008-11-03 14:10   ` Henrik Austad

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=490B3D8A.2070601@simon.arlott.org.uk \
    --to=simon@fire.lp0.eu \
    --cc=htmldeveloper@gmail.com \
    --cc=kernelnewbies@nl.linux.org \
    --cc=linux-pm@lists.linux-foundation.org \
    /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