We have been stopping as soon as we find a conflict but that doesn't
mean we can't merge it in an earlier slot, so keep going. Going by
shader-db, this sometimes allows us to merge the final thrsw a bit
earlier and avoid emitting NOP instructions at the program end to
make up for its delay slots. I have not observed cases where this
helps with regular thrsw though, but it doesn't hurt to try with
those too.
total instructions in shared programs: 11526876 -> 11526354 (<.01%)
instructions in affected programs: 10760 -> 10238 (-4.85%)
helped: 236
HURT: 0
Instructions are helped.
total max-temps in shared programs: 2231705 -> 2231677 (<.01%)
max-temps in affected programs: 276 -> 248 (-10.14%)
helped: 27
HURT: 0
Max-temps are helped.
total inst-and-stalls in shared programs: 11545177 -> 11544655 (<.01%)
inst-and-stalls in affected programs: 10777 -> 10255 (-4.84%)
helped: 236
HURT: 0
Inst-and-stalls are helped.
total nops in shared programs: 321624 -> 321152 (-0.15%)
nops in affected programs: 751 -> 279 (-62.85%)
helped: 236
HURT: 0
Nops are helped.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22679>
This change updates the sqtt layer to add mesh shader specific RGP
instrumentation logic. This should allow RGP to correctly identify GPU
work derived from vkCmdDrawMeshTasksEXT, vkCmdDrawMeshTasksIndirectEXT,
and vkCmdDrawMeshTasksIndirectCountEXT API calls.
This change also updates the mesa-to-RGP shader stage translation logic
to handle the mesh & task stages.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21917>
If extendedDynamicState3ConservativeRasterizationMode is enabled,
VK_EXT_conservative_rasterization is mandatory.
Fixes recent updates in dEQP-VK.info.device_mandatory_features.
Cc: mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22681>
Without this, we get some trailing spaces in some cases, and some
double space in some other cases. Let's clean that up a bit.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22550>
The encoder queue doesn't like padding at all, don't pad in the sysmem
paths for encoder queue.
The encoder queue will be using on gfx11 for decoding.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21980>
this should match the functionality of GPL, but it should also (theoretically)
have significantly less CPU overhead, so I've enabled this to be the new
default when available
currently I'm not changing any of the requirements for shader object enablement,
so this is probably only be usable on desktops
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22725>
this matches up the rest of the codebase using zink_shader_object
zink_gfx_program::objects is left in place for shader binding so that
the entire array can always be bound in one call
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22725>
drivers that use nir_assign_io_var_locations() with EXT_shader_object all
have the same bug with a shader interface that looks like this:
shader output block:
* PSIZ
* VAR0
* VAR8
shader input block:
* VAR0
* VAR8
in this case, output driver locations will be assigned like:
* PSIZ=0
* VAR0=1
* VAR8=2
and input driver locations will be:
* VAR0=0
* VAR8=1
which breaks the shaders even though this is a totally legitimate thing
to do
thus, a second set of shaders have to be created without PSIZ to work around
the bug since I've already spent 18+ hours trying to fix it and have only succeeded
in breaking every driver that uses it
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22725>
This change makes usage bits verification closer to the Vulkan spec.
i.e. VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT does not always require all formats
to support all the requested usage bits.
Also, VK_IMAGE_CREATE_EXTENDED_USAGE_BIT, when combined with
VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT can relax the requirements for the
usage supported by the original image format.
v2: Removed strict verification of the format_list_info formats usage
per chadversary's suggestion. Other minor style/comments tweaks.
v3: Added checking of all compatible formats when
VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT and VK_IMAGE_CREATE_EXTENDED_USAGE_BIT
are specified, but no list of possible formats was given.
v4: Add VK_IMAGE_CREATE_BLOCK_TEXEL_VIEW_COMPATIBLE_BIT handling.
Cc: 22.2 <mesa-stable>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/6031
Signed-off-by: Sviatoslav Peleshko <sviatoslav.peleshko@globallogic.com>
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17182>
It's not invalid to have this value in the list, but the only case it
is actually valid as format in the creation of an image or image view
is with Android Hardware Buffers which have their format specified
externally.
So we can just ignore all entries with VK_FORMAT_UNDEFINED.
Cc: 22.2 <mesa-stable>
Signed-off-by: Sviatoslav Peleshko <sviatoslav.peleshko@globallogic.com>
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17182>
To get Sphinx and Bootstrap to work well together, we need to massage
the output from Sphinx a bit. This adds an extension to do such changes,
based on work from here:
https://github.com/pydata/pydata-sphinx-theme
...However, because we don't ship as an external theme, we can't just do
things as a part of __init__.py, so instead we register an extension
that does the heavy lifting for us.
Reviewed-by: Eric Engestrom <eric@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8399>
It's easier to keep this sorted if we have each element on a separate
line. Let's do that for long-term ease of maintainability.
Reviewed-by: Eric Engestrom <eric@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8399>
Indeed, the hardcoded framebuffer cleanup doesn't handle "resolve".
For instance, this issue is triggered with "piglit/bin/glx-copy-sub-buffer -samples=2 -auto"
while setting GALLIUM_REFCNT_LOG=refcnt.log.
Fixes: f5bde99cbd ("gallium: plumb resolve attachments through from frontends -> pipe_framebuffer_state")
Signed-off-by: Patrick Lerda <patrick9876@free.fr>
Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22554>
We had a lot of implicit locks going on even though there was strictly no
need in doing so. This makes the compilation APIs more atomic while also
providing a cleaner interface.
Not in the mood of splitting it up without deadlocking in the middle. So
it's one big commit sadly.
Signed-off-by: Karol Herbst <git@karolherbst.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22434>
