AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
213,986 Commits 1 Branch 0 Tags
a982e5bb8a93e16e2c88c7250ff029090504e7dd
Commit Graph

213986 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Qiang Yu a982e5bb8a radeonsi: add mesh shader bits for dirty_shaders_mask 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37932>
 2025-10-24 02:07:14 +00:00
Qiang Yu 0ddc1d21f2 radeonsi: dump shader key for mesh shader 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37932>
 2025-10-24 02:07:13 +00:00
Qiang Yu f513d47266 radeonsi: compile mesh shader with ACO only 
RADV only support mesh shader with ACO. So left LLVM
support later.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37932>
 2025-10-24 02:07:13 +00:00
Qiang Yu fc81d7e7d4 radeonsi: si_select_hw_stage support mesh shader 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37932>
 2025-10-24 02:07:13 +00:00
Qiang Yu 351070c46c radeonsi: si_get_output_prim_simplified support mesh shader 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37932>
 2025-10-24 02:07:12 +00:00
Qiang Yu 8ef07d4d8b radeonsi: support mesh shader per vertex output 
mesh shader uses per vertex output store, and
si_nir_assign_param_offsets assert output store to be
scalar.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37932>
 2025-10-24 02:07:12 +00:00
Qiang Yu 845f333111 radeonsi: select key for mesh shader 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37932>
 2025-10-24 02:07:11 +00:00
Qiang Yu e42ada1723 radeonsi: add mesh shader debug options 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37932>
 2025-10-24 02:07:11 +00:00
Qiang Yu 282a0ae20c radeonsi: add mesh shader state create/delete/bind 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37932>
 2025-10-24 02:07:10 +00:00
Qiang Yu 8cae067adc radeonsi: export si_set_user_data_base for mesh shader usage 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37932>
 2025-10-24 02:07:10 +00:00
Qiang Yu 43cf109f47 radeonsi: emit shader pointer for mesh shader 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37932>
 2025-10-24 02:07:09 +00:00
Qiang Yu a44d91d065 radeonsi: call si_shader_change_notify when vs bind 
vs may be null when mesh shader enabled. mesh shader and
vertex shader may share the GS user sgpr, so need to call
si_shader_change_notify to mark shader pointers dirty.

Also remove some init code which will be done anyway when
vs bind first shader in si_shader_change_notify now.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37932>
 2025-10-24 02:07:09 +00:00
Ian Romanick f1bbc3d4e4 nir/algebraic: Don't generate integer min or max that will need to be lowered 
In !35844, there was some discussion about allowing 64-bit bcsel that
would be lowered in the driver. One challenge there would be if a 64-bit
bcsel was transformed into integer min or max by an algebraic
optimization. I believe these were the only algebraic patterns that
could create new integer min or max that would not be immediately
constant folded.

There were no shader-db or fossil-db changes on any Intel platform.

Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38033>
 2025-10-23 22:35:27 +00:00
Caio Oliveira 6fe5d7b0a4 intel/mda: Allow to specify directories with -f 
If you have before/after mda files in separate directories, this make
easier to import them.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37806>
 2025-10-23 22:21:14 +00:00
Jordan Justen 84a67b5ab4 intel/dev: Add NVL-S/U PCI IDs (with FORCE_PROBE required) 
Ref: bspec 74201
Ref: https://gitlab.freedesktop.org/drm/xe/kernel/-/commit/c002b1764e7b0ffd181f32d5103d9d0ac283beeb
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38020>
 2025-10-23 21:47:29 +00:00
Jordan Justen ac1a7e19e8 intel/dev: Add NVL-S/U device info 
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38020>
 2025-10-23 21:47:29 +00:00
Jordan Justen 84bba237ca intel/dev: Add INTEL_PLATFORM_NVL_U platform enum 
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38020>
 2025-10-23 21:47:28 +00:00
Mauro Rossi 7bbbfa6670 util: Fix gnu-empty-initializer error 
Fixes the following building error happening with clang:

../src/util/os_file.c:291:29: error: use of GNU empty initializer extension [-Werror,-Wgnu-empty-initializer]
   struct epoll_event evt = {};
                            ^
1 error generated.

Fixes: 17e28652 ("util: mimic KCMP_FILE via epoll when KCMP is missing")
Cc: "25.3"
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37944>
 2025-10-23 21:11:30 +00:00
Connor Abbott 8d276e0d70 tu: Fix RT count with remapped color attachments 
The index of each RT is the remapped color attachment index, so we have
to use the remapped indices when telling the HW the number of RTs.

This fixes KHR-GLES3.framebuffer_blit.scissor_blit on ANGLE once we
enabled VK_EXT_multisampled_render_to_single_sampled, which switched
ANGLE to using dynamic rendering with
VK_KHR_dynamic_rendering_local_read.

Fixes: d50eef5b06 ("tu: Support color attachment remapping")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37990>
 2025-10-23 20:17:32 +00:00
Zan Dobersek 75da8229f9 tu: don't advertise sample location support for VK_SAMPLE_COUNT_1_BIT 
Hardware doesn't support programmable sample locations with 1x MSAA, so
VK_SAMPLE_COUNT_1_BIT shouldn't be included in the
VkPhysicalDeviceSampleLocationsPropertiesEXT::sampleLocationSampleCounts
bitmask. With this sample count MSAA will also be disabled through relevant
control registers, effectively forcing all samples to the center position.

Fixes failures in VK_SAMPLE_COUNT_1_BIT tests under
dEQP-VK.pipeline.*.*.sample_locations_ext.verify_interpolation.

Signed-off-by: Zan Dobersek <zdobersek@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38026>
 2025-10-23 19:46:23 +00:00
Lionel Landwerlin 2689056c82 anv: destroy sets when destroying pool 
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: mesa-stable
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/14169
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38035>
 2025-10-23 19:25:21 +00:00
Lionel Landwerlin e450297ea9 anv/brw: fix output tcs vertices 
brw_prog_tcs_data::instances can be divided by vertices per threads on
earlier generations.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: a91e0e0d61 ("brw: add support for separate tessellation shader compilation")
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38036>
 2025-10-23 18:54:05 +00:00
Felix DeGrood cbcfaca647 intel/ds: reduce min sampling period of pps-producer to 5us 
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37991>
 2025-10-23 18:22:20 +00:00
Sushma Venkatesh Reddy 69dc01405d intel/perf: Update perf scripts to get additional performance counters 
There are a number of metrics that are of interest for compute workloads
analysis which were missing in the initial PTL OA support (MR: 35298).
Updated oa_ptl.xml file provides these metrics.

Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/13663
Tested-by: Arselan Alvi <arselan.alvi@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37072>
 2025-10-23 16:59:09 +00:00
Sushma Venkatesh Reddy 44c1dcd0ed intel/dev: Add geometry, color and depth pipes count 
Geometry, Color and Depth pipelines count are needed for collecting some
metrics from perfetto.

Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37072>
 2025-10-23 16:59:09 +00:00
Felix DeGrood f448a4668b intel/tools: add cmdbuf/queue annotation parsing 
intel_measure now prints annotations when using '--verbose'.

Filter out internal Renderdoc events when using '--trace'

Reviewed-by: Casey Bowman <casey.g.bowman@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37983>
 2025-10-23 15:31:10 +00:00
Felix DeGrood a21de67fdd intel/tools: make eop default 
Reviewed-by: Casey Bowman <casey.g.bowman@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37983>
 2025-10-23 15:31:10 +00:00
Felix DeGrood 8c10226374 intel/tools: add eop timestamp to intel_measure 
Adds end of pipe to end of pipe timestamp parsing. Does not require
inserting stall between events to get accurate values but events
will sometimes be running in parallel.

Reviewed-by: Casey Bowman <casey.g.bowman@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37983>
 2025-10-23 15:31:09 +00:00
Felix DeGrood 5ba9776bc5 intel/tools: make frame and cb index base-0 in intel_measure 
Better reflects original utrace data.

Reviewed-by: Casey Bowman <casey.g.bowman@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37983>
 2025-10-23 15:31:09 +00:00
Samuel Pitoiset 3440272406 radv/ci: update comments around video failures 
They are expected failures and they will always fail unless we have
new firmwares (which is unlikely to happen).

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38021>
 2025-10-23 16:56:26 +02:00
Samuel Pitoiset f5384df105 radv/ci: stop skipping dEQP-VK.descriptor_indexing.* on Cezanne 
The fix is included in VKCTS now.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38021>
 2025-10-23 16:56:26 +02:00
Xaver Hugl 14fcf145e3 vulkan/wsi: remove support for VK_COLOR_SPACE_EXTENDED_SRGB_NONLINEAR_EXT 
It's not really clear whether or not it should use gamma 2.2 or the piece-wise
transfer function, or how clients would use it for wider gamut in general.
Currently no compositors I know of support ext_srgb, so this shouldn't affect
applications in practice.

Signed-off-by: Xaver Hugl <xaver.hugl@kde.org>
Fixes: 4b663d56 ("vulkan/wsi: implement support for VK_EXT_hdr_metadata on Wayland")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36444>
 2025-10-23 13:02:32 +00:00
Simon Perretta c60232c0c5 pvr: temporarily disable gs_rta_support on all cores 
The gs_rta_support feature is currently bugged and may cause the
driver to assert; disabling it will instead use a fallback method
which is functional.

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/38024>
 2025-10-23 13:18:56 +01:00
Alejandro Piñeiro 75eee7f38b panfrost: cleanup outputs_read/outputs_written at pan_shader_info 
With this commit we do two things:

  * Remove pan_shader_info.fs.outputs_written because it is not used,
    as there is already pan_shader_info.outputs_written

  * For pan_shader_info.fs.outputs_read we direcly copy the nir
    info.outputs_read, without a shift, for consistency and also
    because it is not really required.

Reviewed-by: Lars-Ivar Hesselberg Simonsen <lars-ivar.simonsen@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38022>
 2025-10-23 11:57:37 +00:00
Rhys Perry f3ff2375ec ac/nir: don't consider quads incomplete inside loops 
We move terminates to outside loops, so this doesn't matter anymore.

fossil-db (gfx1201):
Totals from 145 (0.18% of 79839) affected shaders:
Instrs: 174693 -> 174389 (-0.17%); split: -0.18%, +0.01%
CodeSize: 917068 -> 915692 (-0.15%); split: -0.16%, +0.01%
VGPRs: 8340 -> 8184 (-1.87%)
Latency: 2528888 -> 2521006 (-0.31%); split: -0.48%, +0.16%
InvThroughput: 502383 -> 504082 (+0.34%); split: -0.44%, +0.78%
Copies: 15968 -> 15632 (-2.10%); split: -2.14%, +0.04%
PreVGPRs: 5918 -> 5858 (-1.01%)
VALU: 92802 -> 92484 (-0.34%); split: -0.35%, +0.01%
SALU: 29437 -> 29430 (-0.02%)

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37561>
 2025-10-23 11:22:02 +00:00
Rhys Perry 9babec1366 radv,radeonsi: use optimize_txd 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37561>
 2025-10-23 11:22:01 +00:00
Rhys Perry 7d552d71e9 ac/nir: optimize txd(coord, ddx/ddy(coord)) 
This is done in ac_nir_lower_tex so that we can optimize derivative
calculations with a different exec mask than the texture sample by using
the nir_strict_wqm_coord_amd path.

It's also more aware of divergence than nir_lower_tex is.

fossil-db (gfx1201):
Totals from 103 (0.13% of 79839) affected shaders:
MaxWaves: 2610 -> 2620 (+0.38%)
Instrs: 347283 -> 345912 (-0.39%); split: -0.40%, +0.00%
CodeSize: 1892380 -> 1883824 (-0.45%); split: -0.46%, +0.00%
VGPRs: 8028 -> 7824 (-2.54%)
Latency: 3942575 -> 3939623 (-0.07%); split: -0.08%, +0.01%
InvThroughput: 867147 -> 865281 (-0.22%); split: -0.24%, +0.02%
VClause: 6230 -> 6221 (-0.14%); split: -0.19%, +0.05%
SClause: 3910 -> 3914 (+0.10%); split: -0.26%, +0.36%
Copies: 16091 -> 15721 (-2.30%); split: -2.74%, +0.44%
PreSGPRs: 4651 -> 4658 (+0.15%)
PreVGPRs: 6389 -> 6320 (-1.08%); split: -1.17%, +0.09%
VALU: 228715 -> 227490 (-0.54%); split: -0.54%, +0.01%
SALU: 32763 -> 32767 (+0.01%); split: -0.06%, +0.07%
VMEM: 9027 -> 9024 (-0.03%)

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37561>
 2025-10-23 11:22:00 +00:00
Rhys Perry 309ac1f0c0 ac/nir: refactor move_coords_from_divergent_cf a bit 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37561>
 2025-10-23 11:21:59 +00:00
Rhys Perry 92beca9aa5 nir/lower_tex: optimize txd(coord, ddx/ddy(coord)) 
fossil-db (gfx1201):
Totals from 73 (0.09% of 79839) affected shaders:
MaxWaves: 1668 -> 1670 (+0.12%)
Instrs: 352537 -> 347991 (-1.29%); split: -1.29%, +0.00%
CodeSize: 1924140 -> 1887660 (-1.90%); split: -1.90%, +0.00%
VGPRs: 6360 -> 6324 (-0.57%)
Latency: 3891330 -> 3888192 (-0.08%); split: -0.10%, +0.02%
InvThroughput: 789998 -> 783583 (-0.81%); split: -0.84%, +0.03%
VClause: 6409 -> 6408 (-0.02%); split: -0.06%, +0.05%
SClause: 4071 -> 4102 (+0.76%); split: -0.10%, +0.86%
Copies: 16756 -> 16316 (-2.63%); split: -2.94%, +0.32%
PreVGPRs: 5456 -> 5432 (-0.44%); split: -0.57%, +0.13%
VALU: 232982 -> 228117 (-2.09%)
SALU: 32853 -> 32848 (-0.02%); split: -0.05%, +0.03%
VMEM: 9234 -> 9237 (+0.03%)

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37561>
 2025-10-23 11:21:59 +00:00
Rhys Perry 8e7ea4a882 nir/lower_shader_calls: reobtain impl after NIR_PASS 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37573>
 2025-10-23 10:44:38 +00:00
Rhys Perry 241bbb4977 radv: remove NIR_PASS in insert_rt_case 
When NIR_DEBUG=serialize or NIR_DEBUG=clone is used, NIR_PASS recreates
nir_function_impl and nir_variable objects, causing use-after-free since
insert_rt_case() keeps pointers to those in local variables and var_remap.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37573>
 2025-10-23 10:44:38 +00:00
Rhys Perry 55018df38d radv: stop rallocing objects which don't belong to the shader under it 
This doesn't work with NIR_DEBUG=serialize or NIR_DEBUG=clone.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37573>
 2025-10-23 10:44:38 +00:00
Rhys Perry 762a803aa7 radv: remove NIR_PASS in radv_nir_lower_rt_abi 
When NIR_DEBUG=serialize or NIR_DEBUG=clone is used, NIR_PASS recreates
nir_function_impl and nir_variable objects, causing use-after-free since
radv_nir_lower_rt_abi() keeps pointers to those in local variables.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37573>
 2025-10-23 10:44:38 +00:00
Rhys Perry 42bb81137e ac/nir: stop using NIR_PASS in ac_nir_lower_ngg_nogs() 
When NIR_DEBUG=serialize or NIR_DEBUG=clone is used, NIR_PASS recreates
nir_function_impl and nir_variable objects, causing use-after-free since
ac_nir_lower_ngg_nogs() keeps pointers to those in local variables.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/13946
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37573>
 2025-10-23 10:44:38 +00:00
Jose Maria Casanova Crespo ac602a15d1 v3dv: use vk_drm_syncobj_copy_payloads helper 
Enable in v3dv the improvement implemented at
https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36827
("vulkan/wsi: Stop calling unnecessarily calling vkQueueSubmit()")

This shows an average improvement in FPS of 1.56% in vkmark stats.

[vertex] device-local=true:        2032 -> 2071 (+1.94%)
[vertex] device-local=false:       2042 -> 2068 (+1.29%)
[texture] anisotropy=0:            1721 -> 1731 (+0.58%)
[texture] anisotropy=16:           1655 -> 1678 (+1.35%)
[shading] shading=gouraud:         1766 -> 1792 (+1.45%)
[shading] shading=blinn-phong-inf: 1704 -> 1731 (+1.60%)
[shading] shading=phong:           1542 -> 1565 (+1.54%)
[shading] shading=cel:             1529 -> 1563 (+2.27%)
[effect2d] kernel=edge:             914 ->  923 (+0.95%)
[effect2d] kernel=blur:             384 ->  386 (+0.52%)
[desktop] <default>:                789 ->  796 (+0.93%)
[cube] <default>:                  2204 -> 2244 (+1.80%)
[clear] <default>:                 2492 -> 2593 (+4.03%)

The improvement is mainly on vkmark but other gfxrecon traces
exercise this code path but without a significant performance
improvement.

Reviewed-by: Juan A. Suarez <jasuarez@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37996>
 2025-10-23 10:07:05 +00:00
Yiwei Zhang 2e32dd7472 venus: skip feedback cmd record on incompatible queue families 
Feedback requires transfer capability, so we must skip feedback cmd
pool initialization on incompatible queue families. Meanwhile, use
pool_handle for all validity check needed.
- fence and semaphore feedback: skip feedback cmd alloc and record when
  pool_handle is VK_NULL_HANDLE
- event feedback: not affected as we patch in-place upon recording
- query feedback: assert the feedback cmd alloc is on supported queue

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38016>
 2025-10-23 08:57:12 +00:00
Samuel Pitoiset 457d8926e1 amd,radv,radeonsi: add ac_emit_cp_release_mem() 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37956>
 2025-10-23 08:29:27 +00:00
Samuel Pitoiset 22d73fc077 amd,radv,radeonsi: add ac_emit_spm_setup() 
This moves all SPM emit code to common code. This likely also fixes
SPM on GFX11+ for RadeonSI.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37956>
 2025-10-23 08:29:27 +00:00
Samuel Pitoiset 202f8db793 amd,radv,radeonsi: add ac_emit_cp_spi_config_cntl() 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37956>
 2025-10-23 08:29:27 +00:00
Samuel Pitoiset 5cb400a97b amd,radv,radeonsi: add ac_emit_cp_inhibit_clockgating() 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37956>
 2025-10-23 08:29:26 +00:00