Date: Tue, 28 Jul 2020 23:27:26 +0000 From: myfreeweb <greg@unrelenting.technology> To: freebsd-arm@freebsd.org, Vincent Milum Jr <freebsd-arm@darkain.com> Subject: Re: Fwd: big.LITTLE status for rk3399/rockpro64? Message-ID: <8E583BD2-001F-4C9E-80D2-1D33F903C921@unrelenting.technology> In-Reply-To: <CAOWUMWFicnTLnHL_F7k-X_455-VLfdDHk=Ka5oBKv=NiWcu=oA@mail.gmail.com> References: <878sfnz61y.wl-bsd@zeppelin.net> <CAOWUMWGY%2B=w%2B9jJ8yhb9Lew6MjGorVquvATgok1_fyRMUBS6vg@mail.gmail.com> <CAFU7VyNzbFbOP5rMuVEZiMpHs_pdaD3X0Cp0GJRZTyd2pXTHPQ@mail.gmail.com> <20200714094519.f61b85e267d24c02f6a1c09f@bidouilliste.com> <87y2n6tcqr.wl-bsd@zeppelin.net> <20200728123143.GB96119@cicely18.cicely.de> <CAOWUMWEMPR9M8wTLsyrA4S_fkhAKL9Z_mjydZC4tARp3jD-kDg@mail.gmail.com> <CAOWUMWFicnTLnHL_F7k-X_455-VLfdDHk=Ka5oBKv=NiWcu=oA@mail.gmail.com>
index | next in thread | previous in thread | raw e-mail
On July 28, 2020 3:43:19 PM UTC, Vincent Milum Jr <freebsd-arm@darkain.com> wrote: >The issue is most certainly from the big.LITTLE setup. Talking with others >via Twitter, we've determined the issue is the CAM system doesn't play >nicely in this setup. Anything that touches CAM on a big.LITTLE setup has a >chance (but not guarantee) of breaking the system. Interesting.. >The downside is that the two big cores >are not fully clocking up to their max speed, because FreeBSD doesn't have >support yet to clock cores or groups of cores independently. Back when I was actively experimenting with RK3399, I could use the sysctl to set maximum frequency allowed by dtb for the big cores (2200). It would *display* weirdly since heterogeneous systems are not properly supported, I think the readout of the sysctl was the max of the little cores, but all cores *were* at max clock, since the performance was there.home | help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?8E583BD2-001F-4C9E-80D2-1D33F903C921>