AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
190,096 Commits 1 Branch 0 Tags
75b1fa9263c21f06c4231bc11fc66adae89f4af9
Commit Graph

190096 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Georg Lehmann 75b1fa9263 nir/opt_algebraic: alternative 8bit pack_[us]norm_4x8 lowering 
Foz-DB Navi21:
Totals from 42 (0.05% of 79395) affected shaders:
Instrs: 2709529 -> 2705848 (-0.14%)
CodeSize: 14720732 -> 14711384 (-0.06%); split: -0.06%, +0.00%
VGPRs: 4096 -> 4104 (+0.20%)
Latency: 17907612 -> 17904468 (-0.02%); split: -0.02%, +0.00%
InvThroughput: 4723551 -> 4722649 (-0.02%); split: -0.02%, +0.00%
Copies: 223516 -> 219819 (-1.65%)
Branches: 109578 -> 109594 (+0.01%); split: -0.00%, +0.02%
VALU: 1730848 -> 1727151 (-0.21%)

Tested-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Jason Ekstrand <jason.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28882>
 2024-06-04 17:00:29 +00:00
Georg Lehmann f66883a875 nir: lower pack_uvec4_to_uint to pack_32_4x8 if supported 
Foz-DB Navi31:
Totals from 42 (0.05% of 79395) affected shaders:
Instrs: 3326544 -> 3324640 (-0.06%)
CodeSize: 16908376 -> 16896212 (-0.07%); split: -0.07%, +0.00%
VGPRs: 4284 -> 4296 (+0.28%)
Latency: 17862544 -> 17855438 (-0.04%); split: -0.05%, +0.01%
InvThroughput: 3535291 -> 3533993 (-0.04%); split: -0.04%, +0.00%
VClause: 95270 -> 95275 (+0.01%); split: -0.01%, +0.01%
SClause: 65402 -> 65397 (-0.01%)
Copies: 229723 -> 234124 (+1.92%)
Branches: 109481 -> 109518 (+0.03%); split: -0.00%, +0.04%
PreVGPRs: 3879 -> 3909 (+0.77%)
VALU: 1789208 -> 1787370 (-0.10%); split: -0.10%, +0.00%
SALU: 409136 -> 409129 (-0.00%); split: -0.00%, +0.00%

Tested-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Jason Ekstrand <jason.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28882>
 2024-06-04 17:00:29 +00:00
Georg Lehmann a3f77e09a1 ac: set has_pack_32_4x8 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28882>
 2024-06-04 17:00:29 +00:00
Faith Ekstrand 1604ab0ef7 dozen: Advertise VK_EXT_shader_replicated_composites 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Faith Ekstrand 4db99332f3 lavapipe: Advertise VK_EXT_shader_replicated_composites 
Acked-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Faith Ekstrand f8290aea48 turnip: Advertise VK_EXT_shader_replicated_composites 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Faith Ekstrand bf9038b3b8 radv: Advertise VK_EXT_shader_replicated_composites 
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Faith Ekstrand 705dc133c2 hasvk: Advertise VK_EXT_shader_replicated_composites 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Faith Ekstrand a7db1e80d0 anv: Advertise VK_EXT_shader_replicated_composites 
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Faith Ekstrand d805ffd1a4 nvk: Advertise VK_EXT_shader_replicated_composites 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Faith Ekstrand c452143024 spirv: Implement SPV_EXT_replicated_composites 
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Faith Ekstrand fff42bcc66 spirv: Assert that non-vector composites have the right length 
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Faith Ekstrand 8fa46b31a8 spirv: Handle constant cooperative matrices in OpCompositeExtract 
Fixes: b98f87612b ("spirv: Implement SPV_KHR_cooperative_matrix")
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Faith Ekstrand 7e6cd395c7 nir: Handle cmat types in lower_variable_initializers 
Fixes: b98f87612b ("spirv: Implement SPV_KHR_cooperative_matrix")
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Faith Ekstrand c2ab522360 spirv: Update the JSON and headers 
Acked-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Acked-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Faith Ekstrand 5e01f9848b vulkan: Update XML and headers to 1.3.286 
Acked-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Acked-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Kevin Chuang 4c7f51d3b4 anv: implement mesh shader queries 
Mesh shader queries include mesh-primitives-generated count and
task/mesh shader pipeline statistics.

Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29523>
 2024-06-04 16:24:48 +00:00
Kevin Chuang b69f7f625b anv: Update pipeline statistics mask for task/mesh shader invocations 
Since VkQueryPipelineStatisticFlagBits is extended by two bits for
task/mesh shader invocations, ANV_PIPELINE_STATISTICS_MASK should be
defined conditionally based on GFX_VER.

This commit modifies the mask and updates the vk_pipeline_stat_to_reg
array accordingly.

Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29523>
 2024-06-04 16:24:48 +00:00
Kevin Chuang d07321e3d8 intel/genxml: add task/mesh shader statistics registers 
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29523>
 2024-06-04 16:24:48 +00:00
Lionel Landwerlin d9567b5ee4 anv: fix Gfx9 fast clears on srgb formats 
Only MCS surfaces are affected because SRGB format are not listed as
supporting CCS compression.

Fixes CTS test :
  dEQP-VK.api.image_clearing.core.clear_color_attachment.single_layer.*_srgb_*sample_count_*
  dEQP-VK.api.image_clearing.dedicated_allocation.clear_color_attachment.single_layer.*srgb*

This is similar to what we did in Iris in f8961ea0 ("iris: Disable
sRGB fast-clears for non-0/1 values").

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/10003
Fixes: 4cfb4f7d12 ("anv: support fast color clears on vkCmdClearAttachments")
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29518>
 2024-06-04 16:12:32 +00:00
Georg Lehmann 18a0ff137f nir: sink/move inverse_ballot like moves 
It's just a copy for the backends that don't lower it.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29502>
 2024-06-04 15:40:57 +00:00
Georg Lehmann 818ff03865 aco: optimize branching sequence with p_create_vector exec producer 
This happens with inverse_ballot and wave64.

Foz-DB Navi21:
Totals from 3 (0.00% of 79395) affected shaders:
Instrs: 2689 -> 2683 (-0.22%)
CodeSize: 14988 -> 14972 (-0.11%)
Latency: 20207 -> 20204 (-0.01%)
Copies: 144 -> 141 (-2.08%)
Branches: 76 -> 73 (-3.95%)
SALU: 241 -> 238 (-1.24%)

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29502>
 2024-06-04 15:40:57 +00:00
Georg Lehmann 690f880d18 nir/opt_uniform_atomics: handle inverse_ballot when detecting single lane ifs 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29502>
 2024-06-04 15:40:57 +00:00
bbhtt 4f5503fa2d nvk: Clean up unused header from libdrm_nouveau 
This was added in 6e0089307e without a
dependency on libdrm_nouveau. If libdrm is not compiled with nouveau
enabled, the build errors here.

This is currently unused and since
821f4c8d99 removed dependency on
libdrm_nouveau, this should be gone too.

Fixes: 821f4c8d99 ("nouveau: import libdrm_nouveau")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29517>
 2024-06-04 15:24:40 +00:00
Rob Clark 46322630f1 gallium/tc: Allow replacement if replacing valid_range 
If a buffer upload replaces the entire valid_buffer_range, we can
promote the update to DISCARD_WHOLE_RESOURCE.  This helps badly behaved
apps which constantly upload to the same offset (but are overwriting
the entire valid range each time).

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29507>
 2024-06-04 14:49:56 +00:00
Rob Clark 27dd3807a8 freedreno: Use buffer replacement limit 
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29507>
 2024-06-04 14:49:56 +00:00
Rob Clark 4c469b7cf0 gallium/tc: Add optional buffer replacement limit 
Allow drivers to limit the amount of replacement buffers created, to
avoid runaway memory scenarios.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29507>
 2024-06-04 14:49:56 +00:00
Iago Toral Quiroga 0311ac50ad v3dv: implement vkGetDeviceImageSubresourceLayoutKHR 
Added with VK_KHR_maintenance5.

Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29472>
 2024-06-03 07:59:21 +00:00
Iago Toral Quiroga b882cf2ae3 v3dv: add a get_image_subresource_layout helper 
We want to use this helper to implement VkDeviceImageSubresourceInfoKHR.

Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29472>
 2024-06-03 07:59:21 +00:00
Iago Toral Quiroga bf4a8a5c5a v3dv: refactor create_image 
So we can have a single internal helper we can use to create
any type of image.

Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29472>
 2024-06-03 07:59:21 +00:00
Iago Toral Quiroga cccdaab4ef v3dv: implement vkGetImageSubresourceLayout2KHR 
Added with VK_KHR_maintenance5.

Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29472>
 2024-06-03 07:59:21 +00:00
Sergi Blanch Torne dfabed2fc9 Uprev Piglit to cf8daaf5ba90fc9b8a0e144355026e2a14c79944 
https://gitlab.freedesktop.org/mesa/piglit/-/compare/e180f96239edba441f22f58dfc852cafb902844a...cf8daaf5ba90fc9b8a0e144355026e2a14c79944

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29364>
 2024-06-03 06:58:28 +00:00
Sergi Blanch Torne 065ad0f271 ci: disable Collabora's farm due to maintenance 
Planned downtime in the farm:
* Start: 2024-06-03 07:00 UTC
* End: 2024-06-03 13:00 UTC

Signed-off-by: Sergi Blanch Torne <sergi.blanch.torne@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29486>
 2024-06-03 06:06:44 +00:00
Timothy Arceri 8112d44b94 lima: remove the standalone compiler 
This is mostly a revert of cc78a42577 but we leave the meson tools
option as there is now a disassem tool.

This standalone compiler is unmaintained. The replacement is using
drm_shim which goes through the maintained/tested path.

Reviewed-by: Erico Nunes <nunes.erico@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29494>
 2024-06-03 00:25:44 +00:00
David Heidelberg a79a2486c7 ci: propagate RUSTICL_ENABLE and DEBUG variables to the DUTs 
Signed-off-by: David Heidelberg <david@ixit.cz>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29513>
 2024-06-02 07:13:33 +00:00
David Heidelberg 0b54ccff57 ci/lava: the containers take sometimes more than 60m 
It's sad, but killing the rebuild because of 60m when it finishes in 70m
it's such a waste. The Marge-bot pipeline will timeout anyway, so no
change here.

Signed-off-by: David Heidelberg <david@ixit.cz>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29513>
 2024-06-02 07:13:33 +00:00
David Heidelberg 46dd8b8d89 ci/radv: Document recent flake 
Probably same as dfe5e56671 and 1f0f76dbdc .

Signed-off-by: David Heidelberg <david@ixit.cz>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29514>
 2024-06-02 06:56:57 +00:00
Karol Herbst bc149e0303 iris: fix PIPE_RESOURCE_PARAM_STRIDE for buffers 
Iris calls iris_resource_get_param with PIPE_RESOURCE_PARAM_STRIDE
internally now when exporting memory objects. OpenCL's gl_sharing allows
to export buffers as well, which do not have strides.

This fixes the assert being hit there for buffers.

Fixes: 831703157e ("iris: Use resource_get_param in resource_get_handle")
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29501>
 2024-06-01 23:35:46 +00:00
David Heidelberg 2620a7064c ci: move (c)bindgen to own shell script 
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29394>
 2024-06-01 20:16:32 +00:00
David Heidelberg a93932daf0 ci/meson: reuse meson installation 
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29394>
 2024-06-01 20:16:32 +00:00
David Heidelberg 24d9c066e2 ci/lava: add support for RustiCL 
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29394>
 2024-06-01 20:16:32 +00:00
David Heidelberg 70515de489 ci/arm64: rustify the build 
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29394>
 2024-06-01 20:16:32 +00:00
David Heidelberg a77d953e20 mailmap: update my email 
Signed-off-by: David Heidelberg <david@ixit.cz>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29511>
 2024-06-01 18:25:28 +00:00
Kevin Chuang 3349963645 anv: Properly handle cases for different query types in copy_query_results_with_shader 
Like it describes in the comment section of VK_QUERY_TYPE_OCCLUSION,
only occlusion and timestamps queries needs ANV_COPY_QUERY_FLAG_PARTIAL.
VK_QUERY_TYPE_PRIMITIVES_GENERATED_EXT is captured by MI commands.

Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29493>
 2024-06-01 13:05:48 +00:00
Timothy Arceri 71d455b96f glsl: remove unused detect_recursion_linked() 
This is now unused as the recursion is now detected via a nir pass.

Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29495>
 2024-05-31 23:53:07 +00:00
Lionel Landwerlin 724bb7fa15 brw: better model READ_ARF_REG opcode 
This opcode gets translated to 2 ALU instructions with dependency ALU
stall. This change reproduces the FS_OPCODE_PACK_HALF_2x16_SPLIT
values which is another opcode that generates 2 instructions.

Signed-off-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/29446>
 2024-05-31 20:22:27 +00:00
Lionel Landwerlin ac03cefb28 brw: limit dependencies on SR register 
Signed-off-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/29446>
 2024-05-31 20:22:27 +00:00
Lionel Landwerlin d8b78924c5 brw: use a single virtual opcode to read ARF registers 
In 2c65d90bc8 I forgot to add the new SHADER_OPCODE_READ_MASK_REG
opcode to the list of barrier instruction in the scheduler. Let's just
use a single opcode for all ARF registers that need special
scoreboarding and put the register as source (nicer for the debug
output).

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 2c65d90bc8 ("intel/brw: ensure find_live_channel don't access arch register without sync")
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29446>
 2024-05-31 20:22:27 +00:00
Francisco Jerez 588c725f27 intel/xe2+: Enable native 64-bit integer arithmetic. 
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29148>
 2024-05-31 09:14:01 -07:00
Ian Romanick 7b7e5cf5d4 nir/algebraic: intel/fs: Optimize some patterns before lowering 64-bit integers 
v2: Add some comments explaining some of the nuance of the shift
optimizations. Fix a bug in the shift count calculation of the upper
32-bits. Move the @64 from the variable to the opcode. All suggested
by Jordan.

No shader-db changes on any Intel platform.

fossil-db:

Meteor Lake and DG2 had similar results. (Meteor Lake shown)
Totals:
Instrs: 154507026 -> 154506576 (-0.00%)
Cycle count: 17436298868 -> 17436295016 (-0.00%)
Max live registers: 32635309 -> 32635297 (-0.00%)

Totals from 42 (0.01% of 632575) affected shaders:
Instrs: 5616 -> 5166 (-8.01%)
Cycle count: 133680 -> 129828 (-2.88%)
Max live registers: 1158 -> 1146 (-1.04%)

No fossil-db changes on any other Intel platform.

Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29148>
 2024-05-31 09:13:23 -07:00