Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 17 Aug 2018 18:47:40 +0300
From:      Greg V <greg@unrelenting.technology>
To:        Emmanuel Vadot <manu@bidouilliste.com>
Cc:        freebsd-arm <freebsd-arm@freebsd.org>
Subject:   Re: Rockchip RK3399 (ROCKPro64) boots to multiuser
Message-ID:  <1534520860.4036.0@hraggstad.unrelenting.technology>
In-Reply-To: <1534366621.3897.2@hraggstad.unrelenting.technology>
References:  <1533577708.4175.0@hraggstad.unrelenting.technology> <CAGtf9xP8qsindy8zu9e%2B1TkRySqp-Sis22LZQ7f=W%2BMkK6rZOg@mail.gmail.com> <1534253037.1656.0@hraggstad.unrelenting.technology> <CAGtf9xM5oZowxFgrTn3CfbM=g5Jd9g3ZgzZJP=m1Tn8ii2kVuA@mail.gmail.com> <20180815105602.b106e1f55a3f839880b1b60e@bidouilliste.com> <CAGtf9xPKe6s16Y=Qo=s6mHogzvLM%2B5=NQCCNUDvTGLQL=6CezA@mail.gmail.com> <1534362095.3897.1@hraggstad.unrelenting.technology> <20180815224449.98b920836c2c7f8610449835@bidouilliste.com> <1534366621.3897.2@hraggstad.unrelenting.technology>

next in thread | previous in thread | raw e-mail | index | archive | help


On Wed, Aug 15, 2018 at 11:57 PM, Greg V <greg@unrelenting.technology>=20
wrote:
>=20
>=20
> On Wed, Aug 15, 2018 at 11:44 PM, Emmanuel Vadot=20
> <manu@bidouilliste.com> wrote:
>> On Wed, 15 Aug 2018 22:41:34 +0300
>> Greg V <greg@unrelenting.technology> wrote:
>>>  Alright everyone, good news ? I managed to reclock the CPU!!!
>>>=20
>>>  The patch is now at https://reviews.freebsd.org/D16732
>>=20
>>  Thanks a lot !!
>>  I'll have a deeper look when I'm back from BSDCam.
>>=20
>>>  (and I think the style is more correct now. Though it's really=20
>>> =7F=7Ffscking
>>>  silly that the style doesn't like making "table-like" structures=20
>>> =7F=7Flook
>>>  like tables, i.e. with one-line "rows".)
>>>=20
>>>  Plus the hack you need to reclock the CPU right now at
>>>  https://gist.github.com/myfreeweb/88cb9340652f56498f4be770c77b9d61
>>>=20
>>>  (the hack allows cpufreq_dt to deal with clock only, no voltage ?
>>>  since we don't have all the drivers for voltage.)
>>=20
>>  Are you able to switch to any frequency with that ?
>>  I would expect the cpu to hang if the voltage is too low or too=20
>> high.
>> (I encounter that on RK3328)
>=20
> Yeah =E2=80=94 I maxed the clocks for both big and LITTLE cores and got=20
> pretty great performance.
>=20
> e.g. unixbench dhrystone index with cpuset to a big core: 804 =E2=80=94=20
> which is more than the 737 I got on Scaleway's ThunderX VPS!
> ThunderX is still way better on unixbench's other tests though.
> Not that unixbench is a great test=E2=80=A6
>=20
> Compiling neovim also took *way* less time than on RPi/ROCK64.
>=20
> So, I think the big cores' voltage regulator (silergy,syr827) might=20
> just default to the highest voltage.
> The chip gets rather warm when just idling in FreeBSD=E2=80=A6

Update: tried porting the fanpwr driver from OpenBSD:

https://gist.github.com/myfreeweb/584de9b746a328e10c904395afe8a48f

Reports 1.0V on boot. For some reason, cpufreq doesn't see the=20
regulator though =E2=80=94 any idea why could that be??
(cpufreq_dt shouldn't require the controller and regulator to be=20
separate nodes, right? There are other drivers like sy8106a where it's=20
all one node=E2=80=A6)

Also, overclocked to 2.184GHz, still works great (benchmark score went=20
up again.)

I guess either the syr827 is not actually running 1.0 V, or the=20
provided table is waaaay overvolted, or I won the silicon lottery and=20
my chip is just that good.
Maybe I should write an efuse driver to look at the leakage=20
measurements=E2=80=A6
=




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1534520860.4036.0>