All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andy Green <andy.green@linaro.org>
To: Viresh Kumar <viresh.kumar@linaro.org>
Cc: "Comaschi, F." <fcomaschi@tue.nl>,
	cpufreq@vger.kernel.org,
	Lists linaro-kernel <linaro-kernel@lists.linaro.org>,
	Linux PM List <linux-pm@lists.linux-foundation.org>,
	Chander Kashyap <chander.kashyap@linaro.org>,
	Chanwoo Choi <cw00.choi@samsung.com>,
	Lukasz Majewski <l.majewski@samsung.com>
Subject: Re: Arndale power management
Date: Tue, 16 Jul 2013 09:48:53 +0100	[thread overview]
Message-ID: <CAAfg0W4uD=ke6zWnC0bAauAJ=xg5L76oOcnUM8VRypxC7==S3A@mail.gmail.com> (raw)
In-Reply-To: <CAKohpok=WAJs9FBQxEuo=nh4=b184hHyzpLAwEjVYMUZVnB+2g@mail.gmail.com>

Hi -

On 16 July 2013 07:43, Viresh Kumar <viresh.kumar@linaro.org> wrote:
> Adding few more lists so that others can also help..
>
> On 15 July 2013 20:00, Comaschi, F. <fcomaschi@tue.nl> wrote:

>> 2) Recently I have read Andy Green’s presentation “How to measure SoC power”. However, by measuring power on the PMIC input side through the ARM Energy Probe, probably I won't be able to see the effect of DVFS. Do you have any suggestions on how to measure the effect of DVFS, even through hardware measurements?
>
> You need probes on the voltage regulator which is feed the cores...
> But again, that is very much hardware specific. And I haven't worked
> on Exynos at all :)

Arndale has a lot of shunts on the board already, I counted 14 last
time I looked.

You will be able to see the power benefit of DVFS extremely clearly at
the input side of the regulator, but you won't see the voltage you
have set reported.

Since the AEP creates trouble on low voltage / high current rails with
its fullscale 165mV drop (you may only have 900mV on Vcore) measuring
current needs to be done on regulator input side.  Since you're
interested in power, you need to measure voltage also at the regulator
input to allow it to be calculated.

However nothing stops you sticking a second AEP channel on the output
side of the regulator just for monitoring its voltage.  You just need
to stick both wires of the pair on the output side for it to report
the voltage separately.  Because you're not using a shunt there, you
don't introduce any voltage drop.

Then you'll see power (+ regulator efficiency loss) one one channel
and actual DVFS voltage (and 0 for current) on the other.

-Andy

  parent reply	other threads:[~2013-07-16  8:48 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <611CFE9D6FBBDC4B97935A5287A11345014441@XSERVER21B.campus.tue.nl>
2013-07-16  6:43 ` Arndale power management Viresh Kumar
2013-07-16  7:23   ` Lukasz Majewski
2013-07-17 11:33     ` Mark Brown
2013-07-16  8:48   ` Andy Green [this message]
2013-07-25  1:58   ` Mike Turquette
     [not found]     ` <611CFE9D6FBBDC4B97935A5287A1134501BB6D@XSERVER21B.campus.tue.nl>
     [not found]       ` <CAPtuhTg3YdTGy58UT9gVmp9EZNBwxaqv69A8nv_Gackyc5qc5Q@mail.gmail.com>
2013-07-26  6:06         ` Comaschi, F.

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='CAAfg0W4uD=ke6zWnC0bAauAJ=xg5L76oOcnUM8VRypxC7==S3A@mail.gmail.com' \
    --to=andy.green@linaro.org \
    --cc=chander.kashyap@linaro.org \
    --cc=cpufreq@vger.kernel.org \
    --cc=cw00.choi@samsung.com \
    --cc=fcomaschi@tue.nl \
    --cc=l.majewski@samsung.com \
    --cc=linaro-kernel@lists.linaro.org \
    --cc=linux-pm@lists.linux-foundation.org \
    --cc=viresh.kumar@linaro.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.