AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
207,178 Commits 1 Branch 0 Tags
d68a1fc0d43546bc37906439b76ef5d8fbf2e5ee
Commit Graph

207178 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Dave Airlie d68a1fc0d4 radv/video: port hevc slice header encoding from radeonsi 
The radeonsi code has been improved to handle reference lists
better, port the code to radv and vulkan API.

This has been updated to for Vulkan

Reviewed-by: David Rosca <david.rosca@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35628>
 2025-06-20 07:31:04 +00:00
Dave Airlie f7d2939457 radv/video: add some missing hevc header bits 
Reviewed-by: David Rosca <david.rosca@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35628>
 2025-06-20 07:31:04 +00:00
Samuel Pitoiset 5e2fcdfea2 radv/meta: add a helper to determine if clearing is a full rect 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35603>
 2025-06-20 06:36:19 +00:00
Samuel Pitoiset 525e73c045 ac/descriptors: configure {Z,STENCIL}_READ_ONLY for ds surfaces on GFX12+ 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35603>
 2025-06-20 06:36:19 +00:00
Samuel Pitoiset 59dfa8c2f5 radv: switch to nir_intrinsic_load_input_attachment_coord 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35556>
 2025-06-20 06:12:24 +00:00
Rob Clark df55ea8c51 freedreno/a6xx: Don't use 2d blit path for f16 
This seems to canonicalize NaNs when the source format is a 16-bit
floating point format, likely because it implicitly converts to 32b.

Fixes OpenCL-CTS:

  ./test_basic imagearraycopy
  ./test_basic imagearraycopy3d

Signed-off-by: Rob Clark <rob.clark@oss.qualcomm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35589>
 2025-06-20 00:10:47 +00:00
Rob Clark 86a8eda644 freedreno: Add custom f16 blit shader 
To avoid canonicalizing NaNs for f16, we need to avoid promoting the
value to 32b.

Signed-off-by: Rob Clark <rob.clark@oss.qualcomm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35589>
 2025-06-20 00:10:47 +00:00
Rob Clark 2adff20fde util: Add a util_blitter_blit_with_txf() helper 
If a driver is (or is contemplating) providing it's own fs_override then
it needs to know whether the blitter is going to use txf or not.  So
split this logic out into a helper.

Signed-off-by: Rob Clark <rob.clark@oss.qualcomm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35589>
 2025-06-20 00:10:47 +00:00
Rob Clark 9e07f38b91 util+tu: Add util_format_is_float16() 
Extract out a helper to check for f16 formats from turnip so it can be
used elsewhere.

Signed-off-by: Rob Clark <rob.clark@oss.qualcomm.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35589>
 2025-06-20 00:10:47 +00:00
Valentine Burley 0273f1f504 ci/lava: Fix .lava-x86_64-test-android dependencies 
Container jobs might not exist in mesa/mesa pipelines.

Fixes: c035454a3c ("ci/virtio: Add an Android Venus job on Intel Comet Lake")
Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35646>
 2025-06-19 22:08:44 +00:00
Emma Anholt eae86f455c v3d: Stop advertising support for HW clip planes. 
The GL frontend is perfectly good at lowering it like we do.  Cuts out a
bunch of duplicate code.

We still have ucp_enables for the FS due to lowering of CLIPDIST to
discards in the FS.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8953>
 2025-06-19 21:44:55 +00:00
Emma Anholt 211e03d026 gallium: Remove the need for set_clip_state() on !PIPE_CAP_CLIP_PLANES. 
More driver boilerplate we don't need.  We do still have to go through the
transformation in st_atom_clip.c because the clip state can get used in
draw fallbacks.  This revealed that lima had a dirty bit being set that
nobody was reading.

Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8953>
 2025-06-19 21:44:55 +00:00
Eric Anholt a9b622bcca vc4: Drop VS ucp lowering code. 
The GL frontend handles it for us since c1442030ec ("vc4: lower clip
planes in st/mesa").  Now we should just be dropping the VS re-recompiles
we were doing, along with dead code.

Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8953>
 2025-06-19 21:44:55 +00:00
Job Noorman 899a179e8c freedreno/decode: don't count alias regs for GPR stats 
Alias regs don't actually consume GPR space so shouldn't be counted.

Signed-off-by: Job Noorman <jnoorman@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35627>
 2025-06-19 21:23:01 +00:00
Job Noorman d2e1e4442a ir3: enable nir_opt_uniform_subgroup 
fossildb results:

Totals from 320 (0.19% of 164575) affected shaders:
MaxWaves: 2684 -> 2688 (+0.15%)
Instrs: 458284 -> 457275 (-0.22%); split: -0.22%, +0.00%
CodeSize: 896464 -> 896230 (-0.03%); split: -0.09%, +0.06%
NOPs: 109357 -> 109452 (+0.09%); split: -0.08%, +0.17%
MOVs: 25634 -> 24975 (-2.57%)
Full: 5781 -> 5779 (-0.03%)
(ss): 11491 -> 11241 (-2.18%); split: -2.21%, +0.03%
(sy): 5179 -> 5174 (-0.10%); split: -0.12%, +0.02%
(ss)-stall: 57044 -> 56592 (-0.79%); split: -0.95%, +0.16%
(sy)-stall: 114577 -> 114484 (-0.08%); split: -0.11%, +0.03%
Preamble Instrs: 103205 -> 103748 (+0.53%)
Cat0: 124379 -> 124474 (+0.08%); split: -0.07%, +0.15%
Cat1: 30969 -> 30310 (-2.13%)
Cat2: 163648 -> 163260 (-0.24%)
Cat3: 94946 -> 94921 (-0.03%)
Cat4: 13061 -> 13041 (-0.15%)
Cat5: 7421 -> 7414 (-0.09%)
Cat7: 18041 -> 18036 (-0.03%)

Signed-off-by: Job Noorman <jnoorman@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35636>
 2025-06-19 20:56:35 +00:00
Guilherme Gallo c035454a3c ci/virtio: Add an Android Venus job on Intel Comet Lake 
Introduce a Venus job running in Cuttlefish on Intel Comet Lake DUTs.

Signed-off-by: Guilherme Gallo <guilherme.gallo@collabora.com>
Co-authored-by: Antonio Ospite <antonio.ospite@collabora.com>
Co-authored-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35522>
 2025-06-19 20:20:42 +00:00
Valentine Burley 0553a2de25 ci/virtio: Generalize .venus-rules 
Decouple the .venus-rules definition from lavapipe to prepare for adding
hardware driver coverage for Venus.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Co-authored-by: Guilherme Gallo <guilherme.gallo@collabora.com>
Co-authored-by: Eric Engestrom <eric@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35522>
 2025-06-19 20:20:42 +00:00
Valentine Burley 03b480d381 ci/intel: Fix the runner tag for Flip-hatch 
The GitLab runner tags are case sensitive, and Flip-hatch's tag was
incorrectly lowercase. This prevented jobs from being picked up
by the runner.

Also remove an outdated note, as the device now appears to be stable.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35522>
 2025-06-19 20:20:42 +00:00
Valentine Burley b026b5e277 ci/android: Print the detailed deqp versions 
Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35522>
 2025-06-19 20:20:41 +00:00
Valentine Burley bbffb1b967 ci/lava: Remove Android CTS from the core rootfs 
Current LAVA jobs use dEQP instead of Android CTS, so there's no need
to include Android CTS in the rootfs. Removing both Cuttlefish and
Android CTS reduces the rootfs size from ~2GB to ~500MB.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35522>
 2025-06-19 20:20:41 +00:00
Valentine Burley f7befb9d8d ci/lava: Make Cuttlefish a LAVA overlay 
Instead of including Cuttlefish in the core LAVA rootfs, make it an
optional LAVA overlay. This reduces the size of the core rootfs and
keeps Cuttlefish cached when the container is rebuilt, leading to
faster deploys.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35522>
 2025-06-19 20:20:40 +00:00
Guilherme Gallo 6527ac72d4 ci/android: export container for DUTs 
Signed-off-by: Guilherme Gallo <guilherme.gallo@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35522>
 2025-06-19 20:20:39 +00:00
Lionel Landwerlin bfee389f0c anv: only use compressed memory types on Xe2+ 
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 252cac1e5c ("anv: avoid memory type changes with INTEL_DEBUG=noccs")
Tested-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35615>
 2025-06-19 19:55:59 +00:00
Emma Anholt 6808ccf23a mesa: Retire the OptimizeForAOS code. 
It's been unused for years.  Back on the brw driver, it was used for a ~1%
win on a VS-heavy workload, because you could hide instruction latency
using a DP4 sequence instead of MADs for doing the MVP transform.  Given
that r300 and i915 don't seem to want it, and nobody has successfully
ported it for crocus (see
https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14277), just
garbage collect the code at this point.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35617>
 2025-06-19 19:23:53 +00:00
Mel Henning f7aa6ba906 vulkan: Specify library_arch in ICD files 
This should help vk-icd-loader skip libraries of the wrong bit width.

Reviewed-by: Eric Engestrom <eric@igalia.com>
Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35567>
 2025-06-19 17:30:24 +00:00
Mike Blumenkrantz 6b9415cb45 ci: rename "lvp" jobs to lavapipe 
better regex globbing

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35321>
 2025-06-19 17:11:41 +00:00
Mike Blumenkrantz dc066f8577 draw: silence some no-op draw debug prints 
this has been annoying me for years

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35584>
 2025-06-19 16:22:05 +00:00
Faith Ekstrand 366b36aefd vulkan: Drop vk_sampler_init() 
It's ill-defined at best since it doesn't even initialize the
vk_object_base and its only use was NVK and that use is now gone.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35624>
 2025-06-19 15:45:09 +00:00
Faith Ekstrand 5d416a3742 nvk: Use vk_sampler_state for nvk_sampler_get_header() 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35624>
 2025-06-19 15:45:09 +00:00
Faith Ekstrand a33e25185a vulkan/sampler: Add border color swizzle info to vk_sampler_state 
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35624>
 2025-06-19 15:45:09 +00:00
Faith Ekstrand 4cb8bfe285 vulkan: Add a vk_sampler_state struct 
This struct gathers up all the sampler state from VkSamplerCreateInfo
and its pNext chain into a single struct.  The struct is has no pointers
and has uses -Wpadded to ensure no holes.  This means it's hashable and
mem-comparable.  We also make give vk_ycbcr_conversion_state -Wpadded
because vk_sampler_state has a copy of vk_ycbcr_conversion_state
embedded in it.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35624>
 2025-06-19 15:45:08 +00:00
Samuel Pitoiset 5ff6d9cbd8 ci: uprev vkd3d 
This adds new tests with E5B9G9R9 that uncovered a RADV bug.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35634>
 2025-06-19 14:08:52 +00:00
Samuel Pitoiset 50c4d5cccd radv: use one descriptor per plane for combined image+sampler with ycbcr 
This removes a very old hack which will also allow us to enable DCC
for multiplanar formats eventually and to reduce the combined
image+sampler descriptor size from 96 to 48 on RDNA3+.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35457>
 2025-06-19 12:58:32 +00:00
Samuel Pitoiset f46126284f radv: reduce the number of bytes written for combined image+sampler desc 
Only for non multiplanar formats.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35457>
 2025-06-19 12:58:32 +00:00
Samuel Pitoiset 22402dadd3 radv: add a separate path for writing ycbcr combined image+sampler desc 
This will allow us to remove the ycbcr hack and to reduce the number
of bytes written for combined image+sampler from 80 to 64.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35457>
 2025-06-19 12:58:31 +00:00
Samuel Pitoiset 4f37876c7b radv: replace radv_combined_image_descriptor_sampler_offset() by a constant 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35457>
 2025-06-19 12:58:31 +00:00
Ashley Smith 8160d0b80e panfrost: Enable GL_EXT_shader_realtime_clock on panfrost v6+ 
Signed-off-by: Ashley Smith <ashley.smith@collabora.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35496>
 2025-06-19 11:18:53 +00:00
Rhys Perry 2cfd2d3b1d aco/tests: add lower_branches tests 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35202>
 2025-06-19 10:58:39 +00:00
Rhys Perry c45482e652 aco: validate that preds/succs match 
This isn't done in validate_cfg() because that's called less frequently.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35202>
 2025-06-19 10:58:39 +00:00
Rhys Perry 85db025cd7 aco: continue when try_remove_simple_block can't remove a predecessor 
We should update linear_preds so that the predecessors we can remove are
actually removed.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35202>
 2025-06-19 10:58:38 +00:00
Rhys Perry 5344abbc56 aco/lower_branches: keep blocks with multiple logical successors 
It might be the case that both the branch and exec mask write in a
divergent branch block are removed. try_remove_simple_block() might then
try to remove it, but fail because it has multiple logical successors.
Instead, just skip these blocks.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Backport-to: 25.1
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35202>
 2025-06-19 10:58:38 +00:00
Ashley Smith e9c2c32409 panvk: enable VK_KHR_shader_clock 
CTS passing and manual tests show it's working well

Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Signed-off-by: Ashley Smith <ashley.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35488>
 2025-06-19 09:11:51 +00:00
Iago Toral Quiroga 20ec897598 v3dv: switch to using nir_intrinsic_load_input_attachment_coord 
Reviewed-by: Juan A. Suarez <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35569>
 2025-06-19 07:55:23 +00:00
Georg Lehmann 001fe8c236 aco: optimize boolean phi with empty else block 
We can keep the else empty by handling the phi in the "then" block.

Foz-DB Navi21:
Totals from 921 (1.15% of 80065) affected shaders:
Instrs: 4532598 -> 4527309 (-0.12%); split: -0.12%, +0.00%
CodeSize: 24498484 -> 24481780 (-0.07%); split: -0.08%, +0.01%
Latency: 41016915 -> 41020477 (+0.01%); split: -0.10%, +0.11%
InvThroughput: 9998405 -> 9991873 (-0.07%); split: -0.08%, +0.02%
SClause: 128261 -> 128267 (+0.00%)
Copies: 409949 -> 408585 (-0.33%); split: -0.36%, +0.02%
Branches: 169740 -> 169222 (-0.31%); split: -0.58%, +0.27%
PreSGPRs: 64408 -> 64398 (-0.02%)
VALU: 2972521 -> 2972518 (-0.00%)
SALU: 673844 -> 668973 (-0.72%); split: -0.72%, +0.00%

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35165>
 2025-06-19 07:32:43 +00:00
Georg Lehmann 4a2884237a radv: dump NIR for executable info after nir_to_asm 
ACO modifies the NIR, most importantly it updates divergence analysis.

Acked-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32990>
 2025-06-19 07:02:20 +00:00
Georg Lehmann 88753ddd1d aco: allow nir divergence to be printed again 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32990>
 2025-06-19 07:02:20 +00:00
Valentine Burley bc049216cc ci/android: Build test AMD drivers 
Build the radeonsi and RADV drivers for Android.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35578>
 2025-06-19 06:19:06 +00:00
Faith Ekstrand 2782fa2cf3 nvk: Lower input attachments earlier 
Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35551>
 2025-06-19 02:14:05 +00:00
Faith Ekstrand 0e740fa8e6 nvk: Switch to nir_intrinsic_load_input_attachment_coord 
The important change here is that we're no longer using state to
determine whether or not we're multiview.  We just assume that layer_id
is zero when in multiview (this appears to be the case when SET_RT_LAYER
is set to CONTROL_V_SELECTS_LAYER) and that view_index is zero when not
in multiview (this is required by Vulkan) and add the two together.
This fixes a long-standing bug where multiview input attachments didn't
work properly with shader objects.

Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35551>
 2025-06-19 02:14:05 +00:00
Faith Ekstrand e1e32fcf0d nvk: Add a load_root_table() helper 
Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35551>
 2025-06-19 02:14:04 +00:00