Signed-off-by: Karol Herbst
---
drm/nouveau/nvkm/subdev/clk/base.c | 17 -
1 file changed, 16 insertions(+), 1 deletion(-)
diff --git a/drm/nouveau/nvkm/subdev/clk/base.c
b/drm/nouveau/nvkm/subdev/clk/base.c
index 889cce2..4928668 100644
---
there is a field in the voltage table which tells us if the VIDs are taken from
the entries or calculated through the header
v2: don't break older versions
Signed-off-by: Karol Herbst
Reviewed-by: Martin Peres
---
before clocking to a cstate, we have to check if the voltage is within the
allowed range
Signed-off-by: Karol Herbst
---
drm/nouveau/include/nvkm/subdev/volt.h | 1 +
drm/nouveau/nvkm/subdev/volt/base.c| 2 +-
2 files changed, 2 insertions(+), 1 deletion(-)
diff
min_id indicates a volt map entry which acts as a floor value, this will be
used to set the lower voltage limit through pstates
Signed-off-by: Karol Herbst
---
drm/nouveau/include/nvkm/subdev/volt.h | 2 +-
drm/nouveau/nvkm/subdev/clk/base.c | 6 --
Hi,
On 14-03-16 21:50, Samuel Pitoiset wrote:
Btw, do you need someone with commit access to push your previous
series (the tgsi thing)? I can do this for you.
Thanks for the offer. IIRC Ilia wanted some minor fixes there, so I'll do
a v2 tomorrow. Talking about commit rights, I guess it
On 16/03/16 20:17, Karol Herbst wrote:
there is a field in the voltage table which tells us if the VIDs are taken from
the entries or calculated through the header
v2: don't break older versions of the table
Signed-off-by: Karol Herbst
---
we should never allow to select a cstate which current voltage (depending on
the temperature) is higher than
1. the max volt entries in the voltage map table
2. what tha gpu actually can volt to
this resolves most of the remaining volting errors on fermi and newer
Signed-off-by: Karol Herbst
the voltage entries actually may map to a different voltage depending on the
current temperature.
Signed-off-by: Karol Herbst
---
bin/nv_cmp_volt.c | 2 +-
drm/nouveau/include/nvkm/subdev/volt.h | 2 +-
drm/nouveau/nvkm/subdev/volt/base.c| 14
Reviewed-by: Marek Olšák
Marek
On Thu, Mar 17, 2016 at 10:13 AM, Hans de Goede wrote:
> These magic file-index defines where only ever used in the nouveau code
> and that no longer uses them.
>
> Signed-off-by: Hans de Goede
> ---
this tool can be run alongside the nvidia driver to print information about
the current p/cstate, which voltage was set by nvidia and what nouveau would
set in the same situation.
Signed-off-by: Karol Herbst
---
bin/nv_cmp_volt.c | 130
This series fixes most of the issues regarding volting on GPUs with any form
of GPU Boost inside their vbios, which is mainly Kepler and newer, but we find
some boosting related tables in Fermi vbios' already
In the end reclocking should work on most Kepler cards without any issues
Karol Herbst
these entries specify a maximum voltage nvidia never exceeds, we shouldn't do
that, too.
Signed-off-by: Karol Herbst
---
drm/nouveau/include/nvkm/subdev/bios/vmap.h | 2 ++
drm/nouveau/include/nvkm/subdev/volt.h | 2 ++
drm/nouveau/nvkm/subdev/bios/vmap.c
this table contains three important clocks:
base clock: this is the non boosted max clock
tdp clock: the clock at wich the vbios guarentees the TDP won't ever be
exceeded at max load (seems to be always the same as the base
clock, but behaves differently)
boost clock:
https://bugs.freedesktop.org/show_bug.cgi?id=94627
Ilia Mirkin changed:
What|Removed |Added
Status|NEW |RESOLVED
https://bugs.freedesktop.org/show_bug.cgi?id=94627
--- Comment #4 from Karol Herbst ---
I bisected it, here is my git bisect log:
git bisect start
# bad: [5dbb57a99482e2e04302ec8ef8cb4130e4ddb882] nouveua_compiler stuff
git bisect bad
handeLOAD / handleSTORE / handleATOM can only handle TGSI_FILE_BUFFER
and TGSI_FILE_MEMORY. Make things fail explictly when another
register-file is used in these functions.
Signed-off-by: Hans de Goede
---
Changes in v2:
-Split out of "nouveau: codegen: Disable more old
https://bugs.freedesktop.org/show_bug.cgi?id=94627
--- Comment #3 from Ilia Mirkin ---
I'm able to reproduce with Mesa 11.1.2, but not with the current mesa master.
Would be nice to figure out what fixed it, but I don't really have the patience
to do a reverse bisect (trace
On 16.03.2016 04:23, Hans de Goede wrote:
tgsi_default_instruction_memory / tgsi_build_instruction_memory were
returning uninitialized memory for tgsi_instruction_memory.Texture and
tgsi_instruction_memory.Format. Note 0 means not set, and thus is a
correct default initializer for these.
Fixes:
https://bugs.freedesktop.org/show_bug.cgi?id=94627
Ilia Mirkin changed:
What|Removed |Added
Component|Other |Drivers/DRI/nouveau
Some of the lowering steps we currently do for FILE_MEMORY_GLOBAL only
apply to buffers, making it impossible to use FILE_MEMORY_GLOBAL for
OpenCL global buffers.
This commits changes the buffer code to use FILE_MEMORY_BUFFER at the
ir_from_tgsi and lowering steps, freeing use of
We shouldn't set voltages below the min or above the max voltage the gpu is
able to set, so save the range
Signed-off-by: Karol Herbst
---
drm/nouveau/include/nvkm/subdev/volt.h | 3 +++
drm/nouveau/nvkm/subdev/volt/base.c| 14 +-
2 files changed, 16
From: Karol Herbst
now the cstatei parameter can be used of the nvkm_cstate_prog function to
select a specific cstate
-1 is a magic value, which will always select the highest currently possible
cstate
Signed-off-by: Karol Herbst
---
Some Fermi+ gpus have no usefull header in the voltage table, which means
nouveau has to read the voltages out of the entries directly.
The mask may be bigger than 0x1f, but this value is already >2V, so it will
be fine for now.
This patch fixes volting issues on those cards enabling them to
Hi,
On 16-03-16 15:55, Ilia Mirkin wrote:
This approach leads to the emitters needing to know about both global and
buffer, even though at that point, they are identical. I was thinking that
in the lowering logic, buffer would just get rewritten as global (with the
offset added), thus not
0: base clock from the vbios is max clock
1: boost only to boost clock from the vbios (default)
2: boost to max clock available
Signed-off-by: Karol Herbst
---
drm/nouveau/include/nvkm/subdev/clk.h | 9 -
drm/nouveau/nvkm/subdev/clk/base.c| 26
On 03/16/2016 11:49 AM, Hans de Goede wrote:
Hi,
On 16-03-16 11:45, Samuel Pitoiset wrote:
On 03/16/2016 10:23 AM, Hans de Goede wrote:
Commit c3083c7082 ("nv50/ir: add support for BUFFER accesses")
disabled /
commented out some of the old resource handling code, but not all of it.
this selects which formula is used to calculate the voltage
Signed-off-by: Karol Herbst
---
drm/nouveau/include/nvkm/subdev/bios/vmap.h | 2 +-
drm/nouveau/nvkm/subdev/bios/vmap.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git
On a very few GPUs with the voltage table version 0x50 we have to read out
the VIDs out of the entries of the table, where all the other gpus are either
PWM based or get a base and a step voltage out of the table header.
Currently nouveau tried to autodetect this and actually doesn't parse the
These magic file-index defines where only ever used in the nouveau code
and that no longer uses them.
Signed-off-by: Hans de Goede
---
Changes in v2:
-Split out of "nouveau: codegen: Disable more old resource handling code"
---
src/gallium/include/pipe/p_shader_tokens.h | 9
Commit c3083c7082 ("nv50/ir: add support for BUFFER accesses") disabled /
commented out some of the old resource handling code, but not all of it.
Effectively all of it is dead already, if we ever enter the old code
paths in handeLOAD / handleSTORE / handleATOM we will get an exception
due to
On 03/17/2016 05:07 PM, Hans de Goede wrote:
Hi,
On 14-03-16 21:50, Samuel Pitoiset wrote:
Btw, do you need someone with commit access to push your previous
series (the tgsi thing)? I can do this for you.
Thanks for the offer. IIRC Ilia wanted some minor fixes there, so
I'll do
a v2
From: Karol Herbst
Signed-off-by: Karol Herbst
---
drm/nouveau/include/nvkm/subdev/clk.h | 1 +
drm/nouveau/nvkm/subdev/clk/base.c| 1 +
2 files changed, 2 insertions(+)
diff --git a/drm/nouveau/include/nvkm/subdev/clk.h
Hi!
I have a very strange problem with a recently purchased ViewSonic 4k
display connected via display port to a Thinkpad 410 with nvidia gt218m
(nvs 3100m).
Every time the mouse pointer touches the left edge of the screen, the
display becomes a block of solid color and freezes.
Series is:
Reviewed-by: Samuel Pitoiset
On 03/17/2016 10:13 AM, Hans de Goede wrote:
Commit c3083c7082 ("nv50/ir: add support for BUFFER accesses") disabled /
commented out some of the old resource handling code, but not all of it.
Effectively all of it is dead
34 matches
Mail list logo