Thank you for both the suggestion and for your insight.
On 2016-12-08 15:32, Karol Herbst wrote:
> 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
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
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
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
With drm-next from
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?
On 2016-12-08 08:10, Karol Herbst wrote:
give the drm-next kernel tree a try. Sadly the reclocking improvements didn't
land with 4.9, so 4.10 is required.
On 7 December 2016 10:26:44 a.m. GMT+01:00, "Sune Mølgaard"
>It works :-)
>Reclocking, however, is another kettle of
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 :08:00.0:
clk: unable to find matching pll values
The idea was to use the modesetting DDX instead of Nouveau’s one for Maxwell+
as EXA was [broken]. But you can give a try at Ilia’s [patches], which
fix the Nouveau DDX for GM10x and GM20x (I don’t think it has been tested on a
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?
On 2016-04-22 09:33, Pierre Moreau wrote:
> A patch was merged yesterday to
A patch was merged yesterday to recognise GM108 (see
I guess it will make it into 4.7.
On 12:14 PM - Apr 18 2016, Sune Mølgaard wrote:
> Is there anything I can do in this regard?
Is there anything I can do in this regard?
On 2016-03-31 23:12, Pierre Moreau wrote:
> Oh, hum, GM108 is NV118 and not NV108 which is Gk208… My bad!
> SMF from the bug report seemed to have some working setup, and since he didn't
> pinged back, I guess it's working nicely. But some more
Oh, hum, GM108 is NV118 and not NV108 which is Gk208… My bad!
SMF from the bug report seemed to have some working setup, and since he didn't
pinged back, I guess it's working nicely. But some more checking might still be
On 04:59 PM - Mar 31 2016, Ilia Mirkin wrote:
> Actually GM108 is
Actually GM108 is not one of the recognized chips. Someone needs to go
through and check that its goldens didn't change. Nobody's done that.
On Thu, Mar 31, 2016 at 4:57 PM, Pierre Moreau wrote:
Acceleration support for GM107 was merged in kernel 4.1, and modesetting
support was added to 3.15. Which kernel version did you try? The GM108 chipset
seems to be recognised since at least 2015/08/20.
On 02:55 PM - Mar 29 2016, Sune Mølgaard wrote:
Mail list logo