search for: 23.053

Hi again, It works :-) Reclocking, however, is another kettle of fish. Trying #echo 0f > /sys/kernel/debug/dri/0/pstate hangs X. Trying the same with no X running reveals: Dec 7 10:08:42 dell-smo kernel: [ 728.831020] nouveau 0000:08:00.0: clk: unable to find matching pll values a number of time as then soft lockup. Very much akin to

Hi, With drm-next from http://kernel.ubuntu.com/~kernel-ppa/mainline/drm-next/2016-12-08/ I don't get the error messages, but I still get a soft cpu lockup. What info would you need from me to get it working? Best regards, Sune Mølgaard On 2016-12-08 08:10, Karol Herbst wrote: > hi, > > give the drm-next kernel tree a try. Sadly the reclocking improvements didn't land with

Aha! That seems to do it. If I interpret correctly, it doesn't set it quite to full power, though, but it's certainly an improvement: 07: core 405 MHz memory 810 MHz 0a: core 270-1124 MHz memory 1600 MHz 0f: core 270-1124 MHz memory 2002 MHz AC DC * AC: core 1012 MHz memory 2002 MHz A short run of glmark2 shows aver 100% improvement to ~550 FPS. Interestingly, it's still nowhere

Hello, The idea was to use the modesetting DDX instead of Nouveau’s one for Maxwell+ as EXA was [broken][1]. But you can give a try at Ilia’s [patches][2], which fix the Nouveau DDX for GM10x and GM20x (I don’t think it has been tested on a GM108 yet). Best regards, Pierre Moreau [1]: https://cgit.freedesktop.org/nouveau/xf86-video-nouveau/commit/?id=3e2e0faa2ee1cce9c1bb5c7ad80d0592460f3edc

hi, give the drm-next kernel tree a try. Sadly the reclocking improvements didn't land with 4.9, so 4.10 is required. Greetings. On 7 December 2016 10:26:44 a.m. GMT+01:00, "Sune Mølgaard" <smo at translucent.dk> wrote: >Hi again, > >It works :-) > >Reclocking, however, is another kettle of fish. > >Trying #echo 0f > /sys/kernel/debug/dri/0/pstate

also you can't change the clocks when there is nothing running on the GPU. I have some patches pending for this in another series, but maybe I may be able toe extract those fixes. Changing the clocks while something is running shouldn't cause any troubles. Alternatively if you don't care about power consumption, you can boot with nouveau.runpm=0 so that the gpu is always on.

you can boot with nouveau.config=NvBoost=2 to enable higher clocks, but that won't fill in the difference compared to Intel. For this there are some changes needed on the mesa side regarding scheduling. Also keep in mind, that PCIe is an important bottleneck here, because the GPU can't push frames fast enough through the bus, that's why any "high FPS" benchmark will be in

Hi, It would seem like it (attachments are from 4.9-rc1, btw), but it doesn't look like there is any support in the Xorg driver. How can I help with that? Best regards, Sune Mølgaard Translucent ApS On 2016-04-22 09:33, Pierre Moreau wrote: > Hello, > > A patch was merged yesterday to recognise GM108 (see >

I recently upgraded "libvirt" on Gentoo to 1.2.2-r1 (latest available). I have not used LXC containers for a few weeks, so I don't recall what version of libvirt I was using when my container last booted successfully. Unfortunately, Gentoo's portage tree does not offer any previous versions of libvirt that I could downgrade to. TL;DR: My container is configured to use