Thread (42 messages) 42 messages, 7 authors, 2014-06-07

[RFC PATCH 0/5] Frequency resolution in CCF vs. cpufreq

From: Sören Brinkmann <hidden>
Date: 2014-05-15 14:02:21
Also in: linux-pm, lkml

Hi Uwe,

On Thu, 2014-05-15 at 09:47AM +0200, Uwe Kleine-K?nig wrote:
On Wed, May 14, 2014 at 03:30:50PM -0700, Soren Brinkmann wrote:
quoted
Hi,

I have one or two problems with cpufreq and the CCF, which are caused by
rounding/different frequency resolutions.

cpufreq works with kHz, while the CCF uses Hz. On Zynq our default frequency is
666666666 Hz which the CCF, due to rounding, reports as 666666660. And for
Why does this happen? Isn't that a bug? What is the actual freqency?
666666666 Hz or 2000000000/3 Hz?
I don't know for sure. I think it's rounding that takes place in the
CCF. That output clock goes from a x-tal through an PLL and various
muxes and dividers. I guess some inaccuracies in the magnitude of a few
Hz are probably not avoidable in that processing chain.
quoted
cpufreq, which simply divides values it obtains through clk_round_rate() by
1000, 666666.
Since passing 666666 to clk_round_rate() does not result in 666666660
(clk_round_rate() always rounds down!), we chose to put 666667 in the OPP. This
What is OPP?
As Nishanth already said, Operating Performance Points. Sorry for being
lazy and not having spelled that out.

	S?ren
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help