[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <43d99930-377c-7906-8dc9-4374d8d43b6e@baylibre.com>
Date: Mon, 1 Jul 2019 11:07:52 +0200
From: Neil Armstrong <narmstrong@...libre.com>
To: Kevin Hilman <khilman@...libre.com>, jbrunet@...libre.com
Cc: linux-arm-kernel@...ts.infradead.org,
linux-amlogic@...ts.infradead.org, linux-kernel@...r.kernel.org,
linux-clk@...r.kernel.org, martin.blumenstingl@...glemail.com,
linux-gpio@...r.kernel.org
Subject: Re: [RFC/RFT v2 12/14] arm64: dts: meson-g12a: enable DVFS on G12A
boards
On 28/06/2019 20:08, Kevin Hilman wrote:
> Neil Armstrong <narmstrong@...libre.com> writes:
>
>> Enable DVFS for the U200, SEI520 and X96-Max Amlogic G12A based board
>> by setting the clock, OPP and supply for each CPU cores.
>>
>> The CPU cluster power supply can achieve 0.73V to 1.01V using a PWM
>> output clocked at 800KHz with an inverse duty-cycle.
>>
>> DVFS has been tested by running the arm64 cpuburn at [1] and cycling
>> between all the possible cpufreq translations and checking the final
>> frequency using the clock-measurer, script at [2].
>>
>> [1] https://github.com/ssvb/cpuburn-arm/blob/master/cpuburn-a53.S
>> [2] https://gist.github.com/superna9999/d4de964dbc0f84b7d527e1df2ddea25f
>>
>> Signed-off-by: Neil Armstrong <narmstrong@...libre.com>
>
> [...]
>
>> @@ -297,6 +316,34 @@
>> status = "okay";
>> };
>>
>> +&cpu0 {
>> + cpu-supply = <&vddcpu>;
>> + operating-points-v2 = <&cpu_opp_table>;
>> + clocks = <&clkc CLKID_CPU_CLK>;
>> + clock-latency = <50000>;
>> +};
>> +
>> +&cpu1 {
>> + cpu-supply = <&vddcpu>;
>> + operating-points-v2 = <&cpu_opp_table>;
>> + clocks = <&clkc CLKID_CPU_CLK>;
>> + clock-latency = <50000>;
>> +};
>> +
>> +&cpu2 {
>> + cpu-supply = <&vddcpu>;
>> + operating-points-v2 = <&cpu_opp_table>;
>> + clocks = <&clkc CLKID_CPU_CLK>;
>> + clock-latency = <50000>;
>> +};
>> +
>> +&cpu3 {
>> + cpu-supply = <&vddcpu>;
>> + operating-points-v2 = <&cpu_opp_table>;
>> + clocks = <&clkc CLKID_CPU_CLK>;
>> + clock-latency = <50000>;
>> +};
>
> Just curious where this max clock transtion (clock-latency) value came
> from. Were you able to measure that somehow?
It was taken from vendor tree. Haven't got chance to measure it, I assume
it's a safe value for now.
>
> Kevin
>
Powered by blists - more mailing lists