This is what other tests do. The next commit will add a third set of
possible results (for Gfx12.5+), and the multiple macro method does not
scale.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23262>
v2: Require that the constant value be representable as either uint16_t
or int16_t. Suggested by Matt.
v3: Remove redundant patterns. Noticed by Matt.
shader-db:
DG2
total instructions in shared programs: 23103767 -> 23103577 (<.01%)
instructions in affected programs: 51822 -> 51632 (-0.37%)
helped: 98 / HURT: 15
total cycles in shared programs: 842347714 -> 842380017 (<.01%)
cycles in affected programs: 1942595 -> 1974898 (1.66%)
helped: 97 / HURT: 32
Nearly all of the affected shaders (around 9,900) are shaders in
Cyberpunk 2077. It's about an even split between vertex and fragment
shaders. The majority of the remaining affected shaders (3,600) are
from Strange Brigade. This was also a nearly even split between
fragment and vertex.
All but two of the lost shaders are SIMD32 fragment shaders in
Cyberpunk 2077. The other two are SIMD32 fragment shaders in Dota2.
fossil-db:
DG2
Instructions in all programs: 196379107 -> 196248608 (-0.1%)
helped: 13467 / HURT: 1210
Cycles in all programs: 13931355281 -> 13929955971 (-0.0%)
helped: 11801 / HURT: 2922
Lost: 90
Reviewed-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23262>
There should not be any isub at this point due to lowerings that happened
ages before getting to late algebraic.
shader-db:
DG2
total instructions in shared programs: 23103769 -> 23103767 (<.01%)
instructions in affected programs: 65 -> 63 (-3.08%)
helped: 1 / HURT: 0
total cycles in shared programs: 842348074 -> 842347714 (<.01%)
cycles in affected programs: 28572 -> 28212 (-1.26%)
helped: 3 / HURT: 0
One compute shader in Assassin's Creed Odyssey was affected.
fossil-db:
DG2
Instructions in all programs: 196400668 -> 196400676 (+0.0%)
helped: 8 / HURT: 5
Cycles in all programs: 13931740724 -> 13931758003 (+0.0%)
helped: 8 / HURT: 7
Reviewed-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23262>
Sources that are already W, UW, or HF can be represented as those types
by definition. Pass them through. Previously an HF source on a MAD would
have been marked as !can_promote. I'm pretty sure this means it would
get moved out to a register, but I did not verify this.
For ADD3, a constant source could be D or UD. In this case, the value
must be tested to determine whether it can be represented as W or
UW. The patterns in opt_algebraic won't generate an ADD3 with constant
source, so this problem cannot occur yet.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23262>
This only impacts ADD3, so at this point it should not have any
affect. As soon as constants are propagated into ADD3 instructions, it
will be a problem.
The worst part is, the ADD3 instrutions that are broken by the old code
aren't even "progress" on this pass.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23262>
this bumps the LVP_SHADER_STAGES to allow task/mesh shaders to be used,
and adds them to various state binding and execution places.
Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23066>
certain state info is no long required if you using mesh/task in the
pipeline.
Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23066>
This is the big execution one, it implement the draw mesh callback.
This executes task shaders and mesh shaders with no overlap.
When task shaders finish, the mesh shader is launched using the payload
data, unless no task shader is run, then the mesh shader is launched.
Once the mesh shader is finished the data is supplied to the draw
pipeline to convert to linear vertex data with no per-prim data,
then passed to draw for clipping and further processing.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23066>
This allows generating task and mesh variants of compute shaders.
It adds:
- vertex and primitive outputs support - aos writing.
- payload support
- mesh iface for the output and count callbacks.
- draw_id
- multiple iteration support to the exec fn to allow launches
in multiple passes to reduce memory usage
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23066>
This is just some infrastructure for creating shaders and contexts.
task/mesh shaders are based on compute shaders and share nearly all
their code with compute.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23066>
mesh shaders can have vertex and primitive outputs, and act a bit
like TCS shaders, add the callback to allow the driver to decide
how to store these.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23066>
mesh shading has a payload to pass between task and mesh shaders,
this acts like shared memory as well, so we use the standard memory
hooks to access it.
This current adds the payload after the 12-byte header which will
contain the x/y/z grid sizes.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23066>
This adds draw mesh shader infrastructure, as mesh shaders have
to be able to feed into the post vs stages like clipping, so
we have to wire informational things up.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23066>
This doesn't matter much in practice, because the integer an float
representations of zero are the same. But it's easier to understand
what's going on if the correct type is used, so let's clean this up.
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23393>
Fixes seg faults in:
dEQP-VK.binding_model.shader_access.primary_cmd_buf
.sampler_immutable.no_access.single_descriptor.*
dEQP-VK.binding_model.shader_access.primary_cmd_buf
.sampler_immutable.no_access.multiple_contiguous_descriptors.*
It does not fix them. Now they just hit asserts in the compiler.
Signed-off-by: Karmjit Mahil <Karmjit.Mahil@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23357>
We need to tell the apps about the hardware limtations, so that they
have a chance to take a fallback path. Fixes GTK misrendering, due to
use of the dummy shaders (now properly fallbacks to software).
Based on a MR by Filip Gawin.
Closes:https://gitlab.freedesktop.org/mesa/mesa/-/issues/7291
Signed-off-by: Pavel Ondračka <pavel.ondracka@gmail.com>
Reviewed-by: Filip Gawin <filip.gawin@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22708>
