big.LITTLE status for rk3399/rockpro64?

Emmanuel Vadot manu at bidouilliste.com
Tue Jul 14 07:49:50 UTC 2020


On Mon, 13 Jul 2020 18:46:14 -0700
Vincent Milum Jr <freebsd-arm at darkain.com> wrote:

> Some more observations.
> 
> I've full power cycled the Pinebook Pro a few times now rather than just
> software rebooted, and the keyboard/trackpad issue has not come back yet.
> 
> All 6 cores seem to be working, but not optimally. The big cores are not
> boosting to their max frequency. Regardless, 6 cores is still 50% more than
> 4 cores, so more compute power!
> 
> This is observed while compiling the FreeBSD kernel directly on the
> Pinebook Pro.
> 
> dev.cpu.5.freq_levels: 1800/-1 1608/-1 1416/-1 1200/-1 1008/-1 816/-1
> 600/-1 408/-1
> dev.cpu.5.freq: 1416
> dev.cpu.4.freq_levels: 1800/-1 1608/-1 1416/-1 1200/-1 1008/-1 816/-1
> 600/-1 408/-1
> dev.cpu.4.freq: 1416
> dev.cpu.3.freq_levels: 1416/-1 1200/-1 1008/-1 816/-1 600/-1 408/-1
> dev.cpu.3.freq: 1416
> dev.cpu.2.freq_levels: 1416/-1 1200/-1 1008/-1 816/-1 600/-1 408/-1
> dev.cpu.2.freq: 1416
> dev.cpu.1.freq_levels: 1416/-1 1200/-1 1008/-1 816/-1 600/-1 408/-1
> dev.cpu.1.freq: 1416
> dev.cpu.0.freq_levels: 1416/-1 1200/-1 1008/-1 816/-1 600/-1 408/-1
> dev.cpu.0.freq: 1416
> hw.temperature.CPU: 56.1C
> hw.temperature.GPU: 51.1C

 This is a problem in our cpufreq framework, all freqs must be the
same. We need to support clusters in it so we could have different
clusters at different speed..

> 
> 
> On Mon, Jul 13, 2020 at 1:24 PM Vincent Milum Jr <freebsd-arm at darkain.com>
> wrote:
> 
> > I've enabled all 6 cores now.
> >
> > Unsure if it is related, but there were initialization issues with the
> > keyboard and trackpad after reboot. On first reboot, the keyboard entirely
> > locked up while typing the user name. On second reboot, keyboard
> > functioned, but there was no trackpad once I got into the X session. After
> > some time, it eventually started working on its own, no idea why.
> >
> > Hardware aside, compute so far seems to work as expected. I tried opening
> > large YouTube videos, and watched it stress all 6 cores without issue.
> >
> > On Mon, Jul 13, 2020 at 11:06 AM Danilo Egêa Gondolfo <danilo at freebsd.org>
> > wrote:
> >
> >> On Mon, Jul 13, 2020 at 6:27 PM Vincent Milum Jr <freebsd-arm at darkain.com>
> >> wrote:
> >>
> >>> I'm curious about this, too. I recently got the Pinebook Pro up and
> >>> running, and would like to start testing all 6 CPU cores for doing
> >>> compilation tasks.
> >>>
> >>> On Mon, Jul 13, 2020 at 10:19 AM Josh Howard <bsd at zeppelin.net> wrote:
> >>>
> >>> > It looks like it's been a couple of months since there's been any news
> >>> > around it. Anything in particular still needed as far as testing or
> >>> > debugging that goes? I have a Rockpro64 and a RockPi4e (though I don't
> >>> have
> >>> > that booting yet.) that I could potentially test on.
> >>> >
> >>> > Thanks
> >>> >
> >>> >
> >>> > _______________________________________________
> >>> > freebsd-arm at freebsd.org mailing list
> >>> > https://lists.freebsd.org/mailman/listinfo/freebsd-arm
> >>> > To unsubscribe, send any mail to "freebsd-arm-unsubscribe at freebsd.org"
> >>> >
> >>> _______________________________________________
> >>> freebsd-arm at freebsd.org mailing list
> >>> https://lists.freebsd.org/mailman/listinfo/freebsd-arm
> >>> To unsubscribe, send any mail to "freebsd-arm-unsubscribe at freebsd.org"
> >>>
> >>
> >> The number of CPUs was limited here
> >> https://svnweb.freebsd.org/base?view=revision&revision=360321
> >>
> >> If you remove the hw.ncpu from your loader.conf you'll be able to use
> >> all the 6 cores.
> >>
> >> Although the commit message mentions a "known issue" with the big.LITTLE
> >> architecture, I was able to use all the 6 cores to rebuild the entire
> >> system and I didn't face any issue.
> >>
> >> Maybe manu@ could give us some context about that.
> >>
> >
> _______________________________________________
> freebsd-arm at freebsd.org mailing list
> https://lists.freebsd.org/mailman/listinfo/freebsd-arm
> To unsubscribe, send any mail to "freebsd-arm-unsubscribe at freebsd.org"


-- 
Emmanuel Vadot <manu at bidouilliste.com>


More information about the freebsd-arm mailing list