fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2025-12-25 00:00:11 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
213475 commits 64 branches 914 tags 1 GiB
Commit graph

213475 commits

This branch
This branch
All branches
Author SHA1 Message Date
Simon Perretta
8dcfbcde52 pvr: support VK_KHR_map_memory2 
Signed-off-by: Simon Perretta <simon.perretta@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37726>
 2025-10-14 17:21:58 +00:00
Simon Perretta
d0608fd3d6 pvr: advertise VK_KHR_device_group_creation 
Handled by common code.

Signed-off-by: Simon Perretta <simon.perretta@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37726>
 2025-10-14 17:21:57 +00:00
Simon Perretta
bf5e88a754 pvr: advertise VK_EXT_shader_replicated_composites 
Handled by common code.

Signed-off-by: Simon Perretta <simon.perretta@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37726>
 2025-10-14 17:21:57 +00:00
Simon Perretta
0a92ee50a1 pvr: advertise VK_KHR_shader_relaxed_extended_instruction 
Handled by common code.

Signed-off-by: Simon Perretta <simon.perretta@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37726>
 2025-10-14 17:21:56 +00:00
Simon Perretta
466abd1d0e pvr: advertise VK_KHR_shader_non_semantic_info 
Handled by common code.

Signed-off-by: Simon Perretta <simon.perretta@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37726>
 2025-10-14 17:21:56 +00:00
Simon Perretta
4d34c07b7a pvr: advertise VK_KHR_sampler_mirror_clamp_to_edge 
Signed-off-by: Simon Perretta <simon.perretta@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37726>
 2025-10-14 17:21:55 +00:00
Daniel Schürmann
d0b87a0d5f ac/nir_flag_smem_for_loads: call divergence analysis internally
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
Also don't flag more SMEM instructions (in ACO) after the last
call to ac_nir_lower_mem_access_bit_sizes().

Totals from 75 (0.09% of 79839) affected shaders: (Navi48)

Instrs: 191246 -> 189960 (-0.67%)
CodeSize: 996840 -> 985976 (-1.09%)
Latency: 3066184 -> 2945500 (-3.94%)
InvThroughput: 355373 -> 353106 (-0.64%); split: -0.66%, +0.02%
SClause: 4848 -> 4699 (-3.07%)
Copies: 13827 -> 13925 (+0.71%); split: -0.07%, +0.78%
Branches: 5176 -> 5003 (-3.34%)
PreSGPRs: 6222 -> 6272 (+0.80%)
VALU: 108934 -> 108993 (+0.05%); split: -0.00%, +0.06%
SALU: 31679 -> 31210 (-1.48%); split: -1.51%, +0.03%
SMEM: 7158 -> 6739 (-5.85%)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37843>
 2025-10-14 16:33:12 +00:00
Daniel Schürmann
c8830a1a79 radv: delay ac_nir_lower_mem_access_bit_sizes 
Totals from 937 (1.17% of 79839) affected shaders: (Navi48)

MaxWaves: 25196 -> 25272 (+0.30%); split: +0.33%, -0.03%
Instrs: 619389 -> 617586 (-0.29%); split: -0.38%, +0.09%
CodeSize: 3161156 -> 3147008 (-0.45%); split: -0.49%, +0.04%
VGPRs: 54456 -> 54300 (-0.29%); split: -0.31%, +0.02%
Latency: 1548791 -> 1550501 (+0.11%); split: -0.16%, +0.27%
InvThroughput: 233599 -> 233561 (-0.02%); split: -0.10%, +0.08%
Copies: 42820 -> 42799 (-0.05%); split: -0.63%, +0.58%
PreVGPRs: 43480 -> 43479 (-0.00%)
VALU: 348357 -> 348358 (+0.00%); split: -0.08%, +0.08%
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37843>
 2025-10-14 16:33:12 +00:00
Daniel Schürmann
9b1a635bb3 amd/common: merge radv_nir_opt_access_speculate() into ac_nir_flag_smem_for_loads() 
One shader is negatively affected, but we save 2 entire iterations over every shader.
This effect is also mitigated with the next commits.

Totals from 1 (0.00% of 79839) affected shaders: (Navi48)

Instrs: 947 -> 958 (+1.16%)
CodeSize: 4728 -> 4732 (+0.08%)
Latency: 20678 -> 20723 (+0.22%)
InvThroughput: 2697 -> 2698 (+0.04%)
SClause: 26 -> 27 (+3.85%)
Copies: 139 -> 145 (+4.32%)
Branches: 46 -> 47 (+2.17%)
VALU: 460 -> 463 (+0.65%)
SALU: 201 -> 204 (+1.49%)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37843>
 2025-10-14 16:33:12 +00:00
Daniel Schürmann
8ff44f17ef amd/lower_mem_access_bit_sizes: also use SMEM for subdword loads 
We can simply extract from the loaded dwords as per
nir_lower_mem_access_bit_sizes() lowering.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37843>
 2025-10-14 16:33:11 +00:00
Daniel Schürmann
fbf0399517 amd/lower_mem_access_bit_sizes: lower all SMEM instructions to supported sizes 
This creates more SMEM instruction, mostly because vec3 64bit are being split
instead of overfetched.

Totals from 442 (0.55% of 79839) affected shaders: (Navi48)

Instrs: 288998 -> 289469 (+0.16%); split: -0.04%, +0.21%
CodeSize: 1538212 -> 1541460 (+0.21%); split: -0.03%, +0.24%
Latency: 3010072 -> 3009373 (-0.02%); split: -0.04%, +0.01%
InvThroughput: 885572 -> 885564 (-0.00%); split: -0.00%, +0.00%
VClause: 6900 -> 6885 (-0.22%); split: -0.28%, +0.06%
SClause: 4457 -> 4469 (+0.27%); split: -0.18%, +0.45%
VALU: 162473 -> 162469 (-0.00%)
SALU: 42871 -> 42855 (-0.04%); split: -0.05%, +0.01%
SMEM: 6893 -> 7239 (+5.02%)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37843>
 2025-10-14 16:33:11 +00:00
Daniel Schürmann
9553e56c67 radv: use load_global instead of load_global_amd for load_sample_positions_amd 
For consistency.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37843>
 2025-10-14 16:33:10 +00:00
Daniel Schürmann
fad10b91a6 nir/divergence: don't assume that load_sample_positions_amd is always uniform 
Sample positions aren't uniform when the sample id is divergent.
This was a regression when we started lowering fragment shader
barycentrics in NIR.

Fixes: 7f444fc72c ("nir: add nir_intrinsic_load_sample_positions_amd")
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37843>
 2025-10-14 16:33:10 +00:00
Romaric Jodin
ed0c18ae4a meson: add depend_files for gl_enums.py 
gl_enums.py depends on (at least):
- license.py
- gl_XML.py
- some XML files

Adding glapi_xml_py_deps to make sure that ninja-to-soong can produce
valid blueprint for Android

Ref #14072

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37865>
 2025-10-14 16:03:30 +00:00
Samuel Pitoiset
c5fa0c2a2a radv: allow to inline all push constants even with dynamic descriptors 
Dynamic descriptors are uploaded/emitted separately now.

fossils-db (GFX1201):
Totals from 3299 (4.14% of 79646) affected shaders:
Instrs: 1811407 -> 1811391 (-0.00%); split: -0.19%, +0.19%
CodeSize: 9339360 -> 9339824 (+0.00%); split: -0.15%, +0.16%
Latency: 7419818 -> 7417817 (-0.03%); split: -0.06%, +0.04%
InvThroughput: 1647859 -> 1647821 (-0.00%); split: -0.00%, +0.00%
VClause: 30536 -> 30534 (-0.01%)
SClause: 31009 -> 30642 (-1.18%); split: -1.55%, +0.37%
Copies: 111591 -> 112131 (+0.48%); split: -0.72%, +1.20%
PreSGPRs: 127639 -> 127628 (-0.01%)
SALU: 290492 -> 291034 (+0.19%); split: -0.28%, +0.46%

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37768>
 2025-10-14 15:34:43 +00:00
Samuel Pitoiset
a47952d495 radv: upload and emit dynamic descriptors separately from push constants 
Dynamic descriptors are rarely used and this will allow to do more
optimizations for push constants, like gathering the size from shaders
themselves instead of using the pipeline layout.

fossils-db (GFX1201):
Totals from 21740 (27.30% of 79646) affected shaders:
Instrs: 11186407 -> 11192061 (+0.05%); split: -0.05%, +0.10%
CodeSize: 59842068 -> 59864412 (+0.04%); split: -0.04%, +0.08%
Latency: 56333136 -> 56325208 (-0.01%); split: -0.03%, +0.02%
InvThroughput: 8576452 -> 8576516 (+0.00%); split: -0.00%, +0.00%
SClause: 279186 -> 279713 (+0.19%); split: -0.06%, +0.25%
Copies: 577854 -> 581735 (+0.67%); split: -0.28%, +0.95%
PreSGPRs: 867163 -> 866409 (-0.09%)
SALU: 1391187 -> 1395055 (+0.28%); split: -0.12%, +0.39%

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37768>
 2025-10-14 15:34:43 +00:00
Samuel Pitoiset
bc32286e5b radv: declare a new user SGPR for dynamic descriptors 
To move them out of push constants.

fossils-db (GFX1201):
Totals from 20700 (25.99% of 79646) affected shaders:
Instrs: 14375624 -> 14370051 (-0.04%); split: -0.07%, +0.03%
CodeSize: 76746128 -> 76723772 (-0.03%); split: -0.05%, +0.02%
Latency: 74103586 -> 74113651 (+0.01%); split: -0.01%, +0.02%
InvThroughput: 11908817 -> 11908798 (-0.00%); split: -0.00%, +0.00%
VClause: 249605 -> 249607 (+0.00%); split: -0.00%, +0.00%
SClause: 337914 -> 337772 (-0.04%); split: -0.08%, +0.04%
Copies: 843585 -> 839233 (-0.52%); split: -0.62%, +0.10%
PreSGPRs: 836283 -> 837260 (+0.12%)
SALU: 1790713 -> 1786374 (-0.24%); split: -0.29%, +0.05%

Co-authored-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37768>
 2025-10-14 15:34:43 +00:00
Valentine Burley
6541b911bd freedreno/ci: Remove baremetal job templates 
The last devices from the former Google farm have been migrated.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37478>
 2025-10-14 14:47:50 +00:00
Valentine Burley
bbdaebae12 freedreno/ci: Move a306 and a530 jobs to LAVA 
The a306 and a530 devices were moved from the Google farm to the Collabora LAVA farm.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37478>
 2025-10-14 14:47:50 +00:00
Valentine Burley
f3fac5752c freedreno/ci: Update expectations for a306 and a530 
Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37478>
 2025-10-14 14:47:49 +00:00
Valentine Burley
90b3d18c46 freedreno/ci: Update kernel to pull in updated dtb 
The only change since the previous kernel is the updated dtb for
dragonboard-820c, which allows the GPU firmware to be found.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37478>
 2025-10-14 14:47:49 +00:00
Valentine Burley
57541eaa9b ci/lava: Make fastboot commands customizable 
Instead of hardcoding the A/B slot selection, allow an optional
environment variable (LAVA_FASTBOOT_CMD) for devices that need it.
This is used for sm8350-hdk to select slot A, but can be omitted
for devices that don’t support A/B slots.

Update the lava-trigger container to pull in
1b521e7b38.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37478>
 2025-10-14 14:47:49 +00:00
Utku Iseri
08da41f2f1 panvk: override can_present_on_device
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
Non-PCI devices are responsible for checking device matches
themselves by overriding can_present_on_device on wsi_device
to take the non-blitting WSI path.

We can allow on-device presentation for both the display
controller, and any panthor node. The simplest way of
achieving that is allowing this for all devices with bus
type platform, as there's nothing else that has this
property.

Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Reviewed-by: Lars-Ivar Hesselberg Simonsen <lars-ivar.simonsen@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37543>
 2025-10-14 14:07:29 +00:00
Job Noorman
0b82b803d9 nir,ir3: rename umul_low to umul_16x16 
This is more in line with similar opcodes like umul_32x16.

Also change its const expr: the masking based on bit size was
unnecessary as it is only defined for 32 bits. Use simple casts instead.

Signed-off-by: Job Noorman <jnoorman@igalia.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37863>
 2025-10-14 12:54:54 +00:00
Timur Kristóf
772b9ce411 radv: Remove qf from radv_spm/sqtt/perfcounter where applicable
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37775>
 2025-10-14 12:33:20 +00:00
Timur Kristóf
8501c8cd43 radv: Remove unneeded forward declaration of qf from dgc header 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37775>
 2025-10-14 12:33:19 +00:00
Timur Kristóf
4462def21b radv: Remove qf argument from radv_cs_write_data (and _head) 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37775>
 2025-10-14 12:33:18 +00:00
Timur Kristóf
2bd1beac4c radv: Remove qf argument from radv_cs_emit_cache_flush 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37775>
 2025-10-14 12:33:18 +00:00
Timur Kristóf
5f901928e8 radv: Remove qf argument from radv_cp_wait_mem 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37775>
 2025-10-14 12:33:16 +00:00
Timur Kristóf
bc1f438f2a radv: Remove qf argument from radv_cs_emit_write_event_eop 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37775>
 2025-10-14 12:33:15 +00:00
Timur Kristóf
a0104c5bf6 radv: Add amd_ip_type to radv_cmd_stream 
Specify an amd_ip_type when initializing radv_cmd_stream
so that we know which packets are valid for the HW IP type
of a given command stream.

This field should be used instead of radv_cmd_buffer::qf when
emitting packets to a command stream.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37775>
 2025-10-14 12:33:13 +00:00
Timur Kristóf
a57419f96b radv: Clarify image and image/buffer copy helper functions 
Refactor the functions to make it clear what they do:
copy_memory_to_image -> gfx_or_compute_copy_memory_to_image
copy_image_to_memory -> compute_copy_image_to_memory
copy_image -> gfx_or_compute_copy_image

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37775>
 2025-10-14 12:33:12 +00:00
Timur Kristóf
db4a9aaf29 radv: Call transfer copy functions from API functions, not helpers 
Improves code readability.
No functional changes.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37775>
 2025-10-14 12:33:12 +00:00
Timur Kristóf
21232ffd12 radv: Pass correct queue family in radv_emit_cache_flush 
Probably a leftover from a past refactor.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37775>
 2025-10-14 12:33:12 +00:00
Timur Kristóf
50f0912f54 radv: Pass correct queue family to radv_cs_emit_write_event_eop 
Probably a leftover from a previous code refactor.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37775>
 2025-10-14 12:33:12 +00:00
Erik Faye-Lund
c2f6c74c1c gallium/aux: unconditionally write buffer 
There's no reason to compare the pointer before writing it here any
more. All that does, is make us trigger an unnessecary Valgrind error
with a branch based on an undefined value if the passed pointer wasn't
properly initialized here.

Fixes: b3133e250e ("gallium: add pipe_context::resource_release to eliminate buffer refcounting")
Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37842>
 2025-10-14 12:05:27 +00:00
Erik Faye-Lund
fe82d97883 aux/pp: release correct sampler-views 
arr[0] and arr[1] aren't really the two allocated sampler views any more
at this point. To make it possible to reason about these pointers,
assign the created objects to speparate pointers, so we can free them
from those instead of having to track which array indices they're stored
in.

Fixes: 73da0dcddc ("gallium: eliminate frontend refcounting from samplerviews")
Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37839>
 2025-10-14 11:42:46 +00:00
Samuel Pitoiset
a566a933ca radv: always return optimalDeviceAccess=TRUE for block-compressed formats
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
Required by the spec.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37817>
 2025-10-14 10:14:45 +00:00
Samuel Pitoiset
a157faee42 radv: only return identicalMemoryLayout for linear images 
This isn't true for tiled images because the swizzling can change.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37817>
 2025-10-14 10:14:45 +00:00
Yiwei Zhang
6c2de971c1 panvk: improve error propagation in panvk_pool_upload_aligned 
Instead of crashing with segfault within upload_shader_desc_info, allow
the caller to handle the alloc failure (they already do).

Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37861>
 2025-10-14 09:55:48 +00:00
Yiwei Zhang
49cdf9f0d5 panvk: drop panvk_pool_upload helper 
Currently there's no user of it, and practically no one would use
implicit alignment.

Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37861>
 2025-10-14 09:55:48 +00:00
Yiwei Zhang
22ed6c3582 panvk: improve big_bo_pool bo utilization 
Better not cap at slab_size, otherwise the bo cache is purely wasting
memory as it could only be used for up to slab_size upon re-use. This
change unlocks the pool alloc limit to the actual bo size.

Dropped the redundant pair of parentheses to stay in one line.

Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37861>
 2025-10-14 09:55:47 +00:00
Yiwei Zhang
dcd2a99415 panvk: allow panvk_pool_alloc_mem to use full slab_size 
We waste the last chunk if the last alloc happen to match the size.

Cc: mesa-stable
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37861>
 2025-10-14 09:55:47 +00:00
David Rosca
c941e57d74 ac/gfx10_format_table: Use new names for 422 subsampled formats 
Fixes: f20ee2806e ("util/format: Add subsampling info to our YUV-as-RGB format names")
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37838>
 2025-10-14 09:33:28 +00:00
Benjamin Cheng
c8093e6cb1 radv: Output requested encode query results only 
Video encode feedback queries have a configurable set of feedback bits,
specified in VkQueryPoolVideoEncodeFeedbackCreateInfoKHR::encodeFeedbackFlags.
Only the bits specified should be output when retrieving results.

Fixes: 1d74661dfd ("radv: add encoder queue support pieces and encoder queries.")
Reviewed-by: David Rosca <david.rosca@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37774>
 2025-10-14 09:11:25 +00:00
Benjamin Cheng
c17dfcd745 vulkan/query_pool: Store video encode feedback 
Drivers need to track which feedback bits were set at creation time to
output the correct things in vkGetQueryPoolResults().

Cc: mesa-stable
Reviewed-by: David Rosca <david.rosca@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37774>
 2025-10-14 09:11:25 +00:00
Georg Lehmann
f1cbac7a8e aco/optimizer: unify constant labels 
Foz-DB Navi21:
Totals from 14 (0.02% of 79789) affected shaders:
Instrs: 44868 -> 44867 (-0.00%)
CodeSize: 279132 -> 279124 (-0.00%)
Copies: 11692 -> 11691 (-0.01%)
VALU: 30353 -> 30352 (-0.00%)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35272>
 2025-10-14 08:33:43 +00:00
Georg Lehmann
2d410cf18e aco/optimizer: apply f2f16 conversion with the new helpers 
Foz-DB Navi21:
Totals from 183 (0.23% of 79789) affected shaders:
Instrs: 158014 -> 157170 (-0.53%); split: -0.54%, +0.01%
CodeSize: 836444 -> 830148 (-0.75%); split: -0.76%, +0.01%
Latency: 593790 -> 592580 (-0.20%); split: -0.39%, +0.19%
InvThroughput: 150243 -> 148783 (-0.97%); split: -0.98%, +0.00%
VClause: 1301 -> 1312 (+0.85%); split: -0.31%, +1.15%
SClause: 2608 -> 2606 (-0.08%)
PreVGPRs: 8706 -> 8674 (-0.37%)
VALU: 102042 -> 101067 (-0.96%); split: -0.97%, +0.01%

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35272>
 2025-10-14 08:33:43 +00:00
Georg Lehmann
2572528d31 aco/optimizer: remove can_apply_extract 
Foz-DB NAvi21:
Totals from 10 (0.01% of 79789) affected shaders:
Latency: 426254 -> 426256 (+0.00%); split: -0.00%, +0.00%
InvThroughput: 81782 -> 81784 (+0.00%)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35272>
 2025-10-14 08:33:42 +00:00
Georg Lehmann
d90976bbad aco/optimizer: delete apply_extract 
Foz-DB Navi21:
Totals from 35 (0.04% of 79789) affected shaders:
Instrs: 166213 -> 166149 (-0.04%); split: -0.05%, +0.01%
CodeSize: 946604 -> 945856 (-0.08%); split: -0.08%, +0.01%
Latency: 2770103 -> 2769799 (-0.01%); split: -0.01%, +0.00%
InvThroughput: 1312839 -> 1312685 (-0.01%)
Copies: 31100 -> 31033 (-0.22%); split: -0.26%, +0.05%
VALU: 114493 -> 114393 (-0.09%); split: -0.09%, +0.00%
SALU: 27249 -> 27285 (+0.13%)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35272>
 2025-10-14 08:33:42 +00:00