AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
189,044 Commits 1 Branch 0 Tags
f703dfd1bb8c22b6791dd95c7de270e176452b4b
Commit Graph

175138 Commits

Author SHA1 Message Date
Marek Olšák f703dfd1bb radeonsi: add gfx12 
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:06 -04:00
Marek Olšák c8ad0f0715 ac/surface/tests: add gfx12 tests 
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:06 -04:00
Marek Olšák d22564d29c ac/surface: add gfx12 
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:06 -04:00
Marek Olšák 686e5a03f5 ac/llvm: add a workaround for nir_intrinsic_load_constant for LLVM on gfx12 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:06 -04:00
Marek Olšák 546465e1ba ac/llvm: implement nir_intrinsic_ordered_xfb_counter_add_gfx12_amd 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:06 -04:00
Marek Olšák 5d94ec9ec4 ac/llvm: handle nir_atomic_op_ordered_add_gfx12_amd 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:06 -04:00
Marek Olšák 2a7302f601 ac/nir: add gfx12 streamout NIR code 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:06 -04:00
Marek Olšák 542c7ee75f ac/nir: add ac_nir_sleep and handle the intrinsics 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:06 -04:00
Marek Olšák af9f04ad59 ac/llvm: update inline assembly for buffer_load_format_xyzw with TFE for gfx12 
Only the scope and the temporal hint are new.

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:06 -04:00
Marek Olšák 9d33e66ad6 ac/llvm: add CS SGPR changes for gfx12 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:06 -04:00
Marek Olšák 0356209543 ac/llvm: add new cache flags for gfx12 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:06 -04:00
Marek Olšák a6c46509cc ac/llvm: use new s_wait instructions and split the existing ones for gfx12 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:05 -04:00
Marek Olšák 12bca6123a ac/nir,llvm: add GS VGPR changes for gfx12 
See the big comment.

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:05 -04:00
Marek Olšák 4e1abe5d8c ac/nir: update ac_nir_lower_resinfo for gfx12 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:05 -04:00
Marek Olšák 2adc66e586 amd: add initial common code for gfx12 
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:05 -04:00
Marek Olšák 58a5de5c34 amd: add gfx12 register definitions into the register header generator 
The generator renamed some definitions to resolve conflicts.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:05 -04:00
Marek Olšák 724b6d667c amd: add gfx12 register definitions 
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:05 -04:00
Marek Olšák ff47395757 amd: import gfx12 addrlib 
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29007>
 2024-05-11 22:14:05 -04:00
Robert Mader 8a02ca1b2e egl/x11: Allow all RGB visuals to match 32-bit RGBA EGLConfigs 
Drop the limitation to 24 or 30 bit configs. It was an abritrary
compromise to usually give apps what they wanted, but now we are about
to get a clean solution for alpha-blending on X11.

Based on a patch by Freya Gentz <zegentzy@protonmail.com>, see
https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2376

Signed-off-by: Robert Mader <robert.mader@posteo.de>
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9989>
 2024-05-11 19:43:47 +00:00
Robert Mader 9bdab38424 egl: Implement EGL_MESA_x11_native_visual_id 
EGL 1.5 specification requires to not match on EGL_NATIVE_VISUAL_ID.

EGL_MESA_x11_native_visual_id extension allows us to remove this
restriction for X11, where we need to match EGL_NATIVE_VISUAL_ID to find
visuals which allow blending.

The reasoning is that on X11, compositors use the visual as "magic bit"
to decide whether to alpha-blend surface contents.
Unlike on most (all?) other windowing systems, requesting an alpha channel
for the config alone does not already imply blending on the compositor
level.

Thus, in order to allow clients to explicitly request configs with
"magic bit" and, similar to GLX, to order configs in a way so clients
not requesting alpha-blending do not get it by accident, do match
visual ids.

Note that one consequence of this is that more configs get
reported to clients.

Based on a patch by Freya Gentz <zegentzy@protonmail.com>, see
https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2376

Signed-off-by: Robert Mader <robert.mader@posteo.de>
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9989>
 2024-05-11 19:43:47 +00:00
David Heidelberg 3736c9997c egl/x11: Move RGBA visuals in the second config selection group 
This ensures that alpha-blended windows are at the bottom of the visuals
list, so they don't get picked up accidentally.

Based on: "egl-X11: Put RGBA visuals in the second config selection group"

Suggested-by: Freya Gentz <zegentzy@protonmail.com>  # original concept
Co-authored-by: Robert Mader <robert.mader@posteo.de>
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9989>
 2024-05-11 19:43:47 +00:00
Robert Mader 0d90415625 egl: Implement EGL_EXT_config_select_group 
It allows us to influence the order of EGL configs for arbitrary
reasons, which will be used in the following commit.

Based on a patch by Freya Gentz <zegentzy@protonmail.com>, see
https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2376

Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Reviewed-by: Adam Jackson <ajax@redhat.com>
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
Signed-off-by: Robert Mader <robert.mader@posteo.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9989>
 2024-05-11 19:43:47 +00:00
Dr. David Alan Gilbert 8b6b327d1b treewide: Cleanup unused structs 
vk/wsi: Remove unused struct 'wsi_headless_format'

'wsi_headless_format' appears unused, and seems
to have been since initial commit.

radv: Remove unused struct 'blit_region'

'blit_region' appears unused, I think since initial commit.

r600: Remove unused structs

'eg_interp' and 'r600_shader_src' are unused.
I think they are just leftovers from the cleanup
in 20e6c31ba6.

i915: Remove unused struct 'i915_tracked_hw_state'

'i915_tracked_hw_state' appears unused. I think it's just
a leftover from 179cb58795.

llvmpipe: Remove unused struct 'linear_interp'

'linear_interp' doesn't ever seem to have been used.

radeonsi: Remove unused struct 'texture_orig_info'

'texture_orig_info' seems unused, I think since 46b2b3bda8.

svga: Remove unused struct 'svga_3d_invalidate_gb_image'

'svga_3d_invalidate_gb_image' appears unused since 1942c06f9c.
Remove it.

nir: Remove unused struct 'split_struct_state'

'split_struct_state' looks unused since the original commit.

Signed-off-by: Dr. David Alan Gilbert <dave@treblig.org>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29105>
 2024-05-11 17:30:59 +00:00
Faith Ekstrand 4842bbb200 nouveau/headers: Add a bool for whether or not to dump offsets 
It's occasionally useful to shut them off.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29147>
 2024-05-11 04:34:15 +00:00
Faith Ekstrand 99b0117243 nvk: Don't rely on push_dirty for which push sets exist 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29147>
 2024-05-11 04:34:15 +00:00
Faith Ekstrand 53737b9d5b nvk: Get rid of sets_dirty 
We're not using it for anything

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29147>
 2024-05-11 04:34:15 +00:00
Faith Ekstrand c834644c4e nvk/meta: Restore set_sizes[0] 
Fixes: af3e7ba105 ("nvk: Stash descriptor set sizes")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29147>
 2024-05-11 04:34:15 +00:00
Faith Ekstrand a160c2a14e nvk: Re-emit sample locations when rasterization samples changes 
We need them for the case where explicit sample locations are not
enabled.  While we're at it, fix the case where rasterization_samples=0.
This can happen when rasterizer discard is enabled.  This fixes MSAA
resolves with NVK+Zink.  In particular, it fixes MSAA for the Unigine
Heaven and Valley benchmark.

This also fixes all of the spec@arb_texture_float@multisample-formats
piglit tests.

Fixes: 41d094c2cc ("nvk: Support dynamic state for enabling sample locations")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/10786
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29147>
 2024-05-11 04:34:15 +00:00
Mike Blumenkrantz bc15c95c7a frontends/dri: always init opencl_func_mutex in InitScreen hooks 
this otherwise leads to a mismatch where some types of screen may have
the mutex initialized while others don't, in which case dri_release_screen()
will attempt to destroy an uninitialized mutex

cc: mesa-stable

Reviewed-by: Adam Jackson <ajax@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29021>
 2024-05-11 02:40:54 +00:00
Mike Blumenkrantz a1225e81c9 frontends/dri: only release pipe when screen init fails 
the caller (driCreateNewScreen3) will always call dri_destroy_screen()
when these functions return failure, so releasing the screen
is always wrong

cc: mesa-stable

Reviewed-by: Adam Jackson <ajax@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29021>
 2024-05-11 02:40:54 +00:00
Caio Oliveira b8dbd64267 intel/brw: Fix commas when dumping instructions 
Some commas were being skipped, according to history as an attempt
to elide BAD_FILEs, but we still print them, so be consistent.  Also
for instructions without any sources, the trailing comma was always
being printed.  Fix that too.

Example of instruction output before the change

    halt_target(8) (null):UD,
    send(8) (mlen: 1) (EOT) (null):UD, 0u, 0u, g126:UD(null):UD NoMask

and after it

    halt_target(8) (null):UD
    send(8) (mlen: 1) (EOT) (null):UD, 0u, 0u, g126:UD, (null):UD NoMask

Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29114>
 2024-05-11 02:17:57 +00:00
Caio Oliveira c9fe20fdf1 intel/brw: Use vNN instead of vgrfNN when printing instructions 
Reduce the noise in the shader dump output.

Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29114>
 2024-05-11 02:17:56 +00:00
Caio Oliveira 3a081106b0 intel/brw: Hide register pressure information in dumps 
It was the default to show register pressure for each instruction,
but it gets in the way of cleaner diffs before/after an optimization pass.
Add INTEL_DEBUG=reg-pressure option to show it again.

Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29114>
 2024-05-11 02:17:56 +00:00
Caio Oliveira 866b1245e9 intel/brw: Don't print IP as part of the dump 
The sequential IP cause noise when diffing before/after a pass that
either add or remove instructions.

Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29114>
 2024-05-11 02:17:56 +00:00
Lionel Landwerlin fd47f90d37 brw: drop dependency on libintel_common 
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/11136
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29128>
 2024-05-11 01:52:01 +00:00
Lionel Landwerlin 36c043e2eb intel: move debug identifier out of libintel_dev 
The debug identifier is put into the captured buffers for error
capture. This helps us figure out what version of the driver people
are running when encountering a GPU hang. This identifier has the
git-sha1 + driver name.

libintel_dev is also a dependency of the compiler so any change to the
git-sha1 also triggers recompile which we want to avoid.

This changes moves the debug identifier to src/intel/common which
drivers already depend on, so the compiler is not affected anymore.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/11136
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29128>
 2024-05-11 01:52:01 +00:00
Mike Blumenkrantz 4882f49e6b zink: don't submit main cmdbuf if has_work is not set 
this should avoid submitting empty cmdbufs

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00
Mike Blumenkrantz 0a24b8f9a3 zink: stop flagging has_work on batch tracking 
this used to be a lazy workaround, but now it can actually mean something

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00
Mike Blumenkrantz 74f572b28f zink: flag has_work in a few more places 
it's unlikely that any of these would be hit without first triggering
a has_work elsewhere, but this makes it more obvious

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00
Mike Blumenkrantz 8f687f2a46 zink: rely on zink_get_cmdbuf() to set has_work flags 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00
Mike Blumenkrantz b9ec12d439 zink: check all has_work flags for flushes 
not sure this actually changes anything right now

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00
Mike Blumenkrantz 06abe4399d zink: reset all the has_work flags in the same place 
no functional changes

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00
Mike Blumenkrantz e4c516bece zink: zink_batch_state::has_barriers -> has_reordered_work 
and add a note

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00
Mike Blumenkrantz ac07fefdda zink: delete zink_batch 
this makes the code a bit more ergonomic

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00
Mike Blumenkrantz 40f595b30c zink: remove all zink_batch usage from zink_context.c 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00
Mike Blumenkrantz 91969dfa5a zink: remove all zink_batch usage from zink_render_pass.c 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00
Mike Blumenkrantz 05ba13ed18 zink: remove all zink_batch usage from zink_draw.cpp 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00
Mike Blumenkrantz bdb4860c10 zink: remove all zink_batch usage from zink_resource.h 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00
Mike Blumenkrantz 0d8d90d577 zink: remove all uses of zink_batch from zink_batch.c 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00
Mike Blumenkrantz 4adfb03f5b zink: remove zink_batch usage from zink_clear.c 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29108>
 2024-05-11 01:29:44 +00:00