public inbox for linux-omap@vger.kernel.org
 help / color / mirror / Atom feed
From: Vishwanath Sripathy <vishwanath.bs@ti.com>
To: Kevin Hilman <khilman@ti.com>
Cc: linux-omap@vger.kernel.org, patches@linaro.org
Subject: RE: [PATCH 3/3] OMAP36xx PM: Updated C state latencies for OMAP3630
Date: Wed, 2 Mar 2011 22:47:04 +0530	[thread overview]
Message-ID: <3621cbf4ab2de0ad80b3b87910b060a8@mail.gmail.com> (raw)
In-Reply-To: <871v2qikgf.fsf@ti.com>

> -----Original Message-----
> From: Kevin Hilman [mailto:khilman@ti.com]
> Sent: Wednesday, March 02, 2011 3:15 AM
> To: Vishwanath BS
> Cc: linux-omap@vger.kernel.org; patches@linaro.org
> Subject: Re: [PATCH 3/3] OMAP36xx PM: Updated C state latencies for
> OMAP3630
>
> Vishwanath BS <vishwanath.bs@ti.com> writes:
>
> > This patch has changes to update the C state latencies for OMAP3630
> and
> > disables the useless C-States, keeping only the optimized ones with
> their
> > corresponding measured latencies.
>
> I think "useless" vs. "optimized" here are not the right words, and
> doesn't summarize the problem being solved.
>
> If I understood Nicole and Vincent's summary it was that there is no
> significant power savings between some of the states, so they are not
> necessary.
Yes, also some of the C states were consuming more power than deeper C
state.

>
> Also, I believe Nicole & Vincent's research applies to both 34xx and
> 36xx.
I need to check. AFAIK, the experiments were done on OMAP3630 boards.
>
> > Only 4 C-states are kept instead of 7
> > C-States:
> > * C1 . MPU WFI clock gated + Core autogating
> > * C3 . MPU CSWR + Core inactive
> > * C5 . MPU CSWR + Core CSWR
> > * C7 . MPU OFF + Core OFF
> >
> > Thanks to Nicole Chaloub<n-chalhoub@ti.com> and Vincent Bour <v-
> bour@ti.com>
> > for their investigation.
> >
> > Tested on ZOOM3 board using latest pm branch.
> >
> > Signed-off-by: Vishwanath BS <vishwanath.bs@ti.com>
> > ---
> >  arch/arm/mach-omap2/board-3630sdp.c |   19
> +++++++++++++++++++
> >  arch/arm/mach-omap2/board-zoom.c    |   19
> +++++++++++++++++++
>
> Why are these added as board-specific changes?
>
> If these are to be the default 3630 CPUidle states, add a default 36xx
> cpuidle_params_table along side the 34xx one and have CPUidle pick the
> right one at runtime.
Yes, I can do that.

Vishwa
>
> Kevin
>
> >  2 files changed, 38 insertions(+), 0 deletions(-)
> >
> > diff --git a/arch/arm/mach-omap2/board-3630sdp.c b/arch/arm/mach-
> omap2/board-3630sdp.c
> > index 6264564..8d05fc9
> > --- a/arch/arm/mach-omap2/board-3630sdp.c
> > +++ b/arch/arm/mach-omap2/board-3630sdp.c
> > @@ -25,6 +25,24 @@
> >  #include "board-flash.h"
> >  #include "mux.h"
> >  #include "sdram-hynix-h8mbx00u0mer-0em.h"
> > +#include "pm.h"
> > +
> > +static struct cpuidle_params omap36xx_cpuidle_params_table[] = {
> > +	/* C1 */
> > +	{1, 74, 78, 152},
> > +	/* C2 */
> > +	{0, 165, 90, 255},
> > +	/* C3 */
> > +	{1, 163, 180, 345},
> > +	/* C4 */
> > +	{0, 2852, 605, 3457},
> > +	/* C5 */
> > +	{1, 800, 366, 2120},
> > +	/* C6 */
> > +	{0, 4080, 801, 4881},
> > +	/* C7 */
> > +	{1, 4300, 8794, 159000},
> > +};
> >
> >  #if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE)
> >
> > @@ -212,6 +230,7 @@ static void __init omap_sdp_init(void)
> >  	board_flash_init(sdp_flash_partitions, chip_sel_sdp);
> >  	enable_board_wakeup_source();
> >  	usb_ehci_init(&ehci_pdata);
> > +	omap3_pm_init_cpuidle(omap36xx_cpuidle_params_table);
> >  }
> >
> >  MACHINE_START(OMAP_3630SDP, "OMAP 3630SDP board")
> > diff --git a/arch/arm/mach-omap2/board-zoom.c b/arch/arm/mach-
> omap2/board-zoom.c
> > index e26754c..6bd364a
> > --- a/arch/arm/mach-omap2/board-zoom.c
> > +++ b/arch/arm/mach-omap2/board-zoom.c
> > @@ -30,6 +30,24 @@
> >  #include "mux.h"
> >  #include "sdram-micron-mt46h32m32lf-6.h"
> >  #include "sdram-hynix-h8mbx00u0mer-0em.h"
> > +#include "pm.h"
> > +
> > +static struct cpuidle_params omap36xx_cpuidle_params_table[] = {
> > +	/* C1 */
> > +	{1, 74, 78, 152},
> > +	/* C2 */
> > +	{0, 165, 90, 255},
> > +	/* C3 */
> > +	{1, 163, 180, 345},
> > +	/* C4 */
> > +	{0, 2852, 605, 3457},
> > +	/* C5 */
> > +	{1, 800, 366, 2120},
> > +	/* C6 */
> > +	{0, 4080, 801, 4881},
> > +	/* C7 */
> > +	{1, 4300, 8794, 159000},
> > +};
> >
> >  #define ZOOM3_EHCI_RESET_GPIO		64
> >
> > @@ -126,6 +144,7 @@ static void __init omap_zoom_init(void)
> >  		usb_ehci_init(&ehci_pdata);
> >  	}
> >
> > +	omap3_pm_init_cpuidle(omap36xx_cpuidle_params_table);
> >  	board_nand_init(zoom_nand_partitions,
> >  			ARRAY_SIZE(zoom_nand_partitions),
> ZOOM_NAND_CS);
> >  	zoom_debugboard_init();

      reply	other threads:[~2011-03-02 17:17 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-02-16  9:01 [PATCH 0/3] OMAP3 PM: CPUIdle fixes Vishwanath BS
2011-02-16  9:01 ` [PATCH 1/3] OMAP3 PM: Deny clock gating only for safe state Vishwanath BS
2011-03-01 21:01   ` Kevin Hilman
2011-03-02 17:14     ` Vishwanath Sripathy
2011-03-02 21:11       ` Kevin Hilman
2011-02-16  9:01 ` [PATCH 2/3] OMAP3 PM: Update only enabled C states Vishwanath BS
2011-02-16  9:01 ` [PATCH 3/3] OMAP36xx PM: Updated C state latencies for OMAP3630 Vishwanath BS
2011-03-01 21:45   ` Kevin Hilman
2011-03-02 17:17     ` Vishwanath Sripathy [this message]

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=3621cbf4ab2de0ad80b3b87910b060a8@mail.gmail.com \
    --to=vishwanath.bs@ti.com \
    --cc=khilman@ti.com \
    --cc=linux-omap@vger.kernel.org \
    --cc=patches@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox