On 29-08-18, 09:08, Vincent Guittot wrote: > The unit of dynamic-power-coefficient is described as mW/MHz/uV^2 whereas > its usage in the code assumes that unit is uW/MHz/V^2 > > In drivers/thermal/cpu_cooling.c, the code is : > > power = (u64)capacitance * freq_mhz * voltage_mv * voltage_mv; > do_div(power, 1000000000); > > which can be summarized as : > power (mW) = capacitance * freq_mhz/1000 * (voltage_mv/1000)^2 > or > power (mW) = (capacitance * freq_mhz * (voltage_mv/1000)^2) / 1000 > then > power (mW) = power (uW) / 1000 > so > power (uW) = capacitance * freq_mhz * (voltage_mv/1000)^2 > > Furthermore, if we test basic values like : > voltage_mv = 1000mV = 1V > freq_mhz = 1000Mhz > > The minimum possible power, when dynamic-power-coefficient equals 1, will > be with current unit: > min power = 1 * 1000 * (1000000)^2 = 10^15 mW > which is not realistic > > With the unit used by the code, the min power is > min power = 1 * 1000 * 1^2 = 1000uW = 1mW which is far more realistic > > Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx> > --- > Documentation/devicetree/bindings/arm/cpus.txt | 4 ++-- > 1 file changed, 2 insertions(+), 2 deletions(-) Acked-by: Viresh Kumar <viresh.kumar@xxxxxxxxxx> -- viresh
