fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-17 16:08:06 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
217231 commits 66 branches 935 tags 932 MiB
Commit graph

19685 commits

Author SHA1 Message Date
Rhys Perry
103160ff2f aco/ra: prefer clobbered registers in get_reg_specified() 
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/38679>
 2026-01-19 09:17:53 +00:00
Rhys Perry
2b20d568e0 aco/ra: prefer clobbered registers in callees 
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/38679>
 2026-01-19 09:17:53 +00:00
Rhys Perry
21b1118a08 aco/ra: refactor get_reg_impl and get_regs_for_copies using tuples 
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/38679>
 2026-01-19 09:17:52 +00:00
Rhys Perry
61919b93fa aco/ra: always abort loop in get_regs_for_copies() if candidate is worse 
fossil-db (navi31):
Totals from 2 (0.00% of 79825) affected shaders:
Instrs: 58162 -> 58178 (+0.03%)
CodeSize: 299132 -> 299212 (+0.03%)
Latency: 72864 -> 72861 (-0.00%)
VClause: 977 -> 984 (+0.72%)
Copies: 7433 -> 7428 (-0.07%)
Branches: 1602 -> 1603 (+0.06%)
VALU: 37100 -> 37095 (-0.01%)

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/38679>
 2026-01-19 09:17:51 +00:00
Rhys Perry
137f71895d aco/ra: always prefer earlier regs in get_reg_impl() if costs are the same 
Before, this would have updated best_win if it encounters an assignment
with the same num_moves and num_vars but is aligned, even if the previous
best assignment was also aligned.

fossil-db (navi31):
Totals from 7693 (9.64% of 79825) affected shaders:
Instrs: 9767559 -> 9766370 (-0.01%); split: -0.11%, +0.09%
CodeSize: 51008244 -> 51002396 (-0.01%); split: -0.09%, +0.08%
VGPRs: 497224 -> 497212 (-0.00%); split: -0.00%, +0.00%
Latency: 80435654 -> 80373798 (-0.08%); split: -0.20%, +0.12%
InvThroughput: 12426170 -> 12414490 (-0.09%); split: -0.15%, +0.06%
VClause: 217725 -> 217438 (-0.13%); split: -0.59%, +0.46%
SClause: 230555 -> 230551 (-0.00%); split: -0.00%, +0.00%
Copies: 758396 -> 757988 (-0.05%); split: -0.81%, +0.75%
Branches: 200669 -> 200662 (-0.00%); split: -0.01%, +0.01%
VALU: 6040415 -> 6039979 (-0.01%); split: -0.10%, +0.09%
SALU: 960327 -> 960671 (+0.04%); split: -0.03%, +0.07%
VOPD: 426 -> 458 (+7.51%)

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/38679>
 2026-01-19 09:17:50 +00:00
Rhys Perry
0a744ba735 aco: increase max_reg_demand to help avoid preserved VGPRs 
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/38679>
 2026-01-19 09:17:50 +00:00
Rhys Perry
bf56f1efd3 aco: move update(fixed_reg_demand) into update_vgpr_sgpr_demand 
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/38679>
 2026-01-19 09:17:50 +00:00
Rhys Perry
a932bc40d3 aco/ra: don't use update_vgpr_sgpr_demand in increase_register_file 
In a future commit, update_vgpr_sgpr_demand() should only be given the
register demand calculated from the number of live temporaries, not the
maximum register used.

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/38679>
 2026-01-19 09:17:49 +00:00
Rhys Perry
6e618ac327 aco: don't try to preserve SCC in callees 
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/38679>
 2026-01-19 09:17:48 +00:00
Rhys Perry
88ee78c6b7 aco: track number of post-RA spilled vgprs/sgprs 
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/38679>
 2026-01-19 09:17:47 +00:00
Rhys Perry
f5f2f9110c radv/rt: lower non-return load_param to variable loads 
nir_intrinsic_load_param can't be CSE'd, which can prevent phi cleanup
and potentially unneeded scratch access.

fossil-db (navi31):
Totals from 4 (0.01% of 79825) affected shaders:
Instrs: 2504 -> 2384 (-4.79%)
CodeSize: 13584 -> 12784 (-5.89%)
Latency: 96124 -> 96056 (-0.07%)
InvThroughput: 12016 -> 12008 (-0.07%)
Copies: 664 -> 504 (-24.10%)
Branches: 92 -> 88 (-4.35%)
VALU: 1232 -> 1112 (-9.74%)
VOPD: 308 -> 228 (-25.97%)

fossil-db (navi31, monolithic pipelines disabled):
Totals from 52 (0.06% of 80095) affected shaders:
Instrs: 126296 -> 124734 (-1.24%)
CodeSize: 718272 -> 707864 (-1.45%)
Latency: 2866019 -> 2865125 (-0.03%)
InvThroughput: 502663 -> 502537 (-0.03%)
Copies: 19616 -> 17536 (-10.60%)
Branches: 4344 -> 4292 (-1.20%)
VALU: 65432 -> 63872 (-2.38%)
VOPD: 14543 -> 13503 (-7.15%)

fossil-db (navi31, monolithic pipelines disabled, any-hit function calls):
Totals from 52 (0.06% of 80304) affected shaders:
Instrs: 38232 -> 34956 (-8.57%)
CodeSize: 184616 -> 171400 (-7.16%)
Latency: 944112 -> 941483 (-0.28%)
InvThroughput: 122152 -> 121817 (-0.27%)
Copies: 13065 -> 10302 (-21.15%)
Branches: 1471 -> 1419 (-3.54%)
PreSGPRs: 2673 -> 2598 (-2.81%)
VALU: 22576 -> 19368 (-14.21%)
SALU: 6549 -> 6474 (-1.15%)

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39344>
 2026-01-19 08:55:39 +00:00
Rhys Perry
37b956a203 radv/rt: cleanup phis after lowering parameter variables to SSA 
No fossil-db changes.

fossil-db (navi31, monolithic pipelines disabled):
Totals from 21 (0.03% of 80095) affected shaders:
MaxWaves: 312 -> 320 (+2.56%)
Instrs: 9989 -> 9666 (-3.23%)
CodeSize: 56020 -> 53696 (-4.15%)
VGPRs: 1488 -> 1440 (-3.23%)
Latency: 157965 -> 146639 (-7.17%)
InvThroughput: 25192 -> 22390 (-11.12%)
VClause: 186 -> 148 (-20.43%)
PreVGPRs: 1196 -> 1147 (-4.10%)
VALU: 5053 -> 5040 (-0.26%)
VMEM: 506 -> 240 (-52.57%)
VOPD: 992 -> 1005 (+1.31%)

fossil-db (navi31, monolithic pipelines disabled, any-hit function calls):
Totals from 41 (0.05% of 80304) affected shaders:
Instrs: 20615 -> 20436 (-0.87%); split: -0.97%, +0.10%
CodeSize: 98780 -> 98080 (-0.71%); split: -0.79%, +0.09%
Latency: 341542 -> 341796 (+0.07%); split: -0.05%, +0.13%
InvThroughput: 46353 -> 46386 (+0.07%); split: -0.05%, +0.12%
Copies: 6958 -> 6818 (-2.01%); split: -2.41%, +0.40%
Branches: 676 -> 657 (-2.81%)
VALU: 12232 -> 12092 (-1.14%); split: -1.37%, +0.23%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39344>
 2026-01-19 08:55:39 +00:00
Samuel Pitoiset
91a5a0f2b9 radv/meta: fix layered depth stencil resolves with compute
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
Fixes a bunch of new VKCTS coverage like
dEQP-VK.pipeline.monolithic.multisample.m10_resolve.resolve_cmd.d32_sfloat.depth.average.full_multilayer.no_flags

Cc: mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39349>
 2026-01-19 07:22:26 +00:00
Konstantin Seurer
091b43b970 radv: Use HPLOC for TLAS builds
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
The BVH quality is comparable to PLOC but the build is much faster.

Reviewed-by: Natalie Vock <natalie.vock@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39116>
 2026-01-18 19:21:08 +01:00
Mauro Rossi
197cb437cd radv/rt: Fix gnu-empty-initializer error in radv_pipeline_rt.c
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
Fixes the following building error happening with clang:

FAILED: src/amd/vulkan/libvulkan_radeon.so.p/radv_pipeline_rt.c.o
...
../src/amd/vulkan/radv_pipeline_rt.c:934:38: error: use of GNU empty initializer extension [-Werror,-Wgnu-empty-initializer]
   struct nir_function raygen_stub = {};
                                     ^
1 error generated.

Fixes: 0a1911b2 ("radv,aco: Use function call structure for RT programs")
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39370>
 2026-01-17 17:13:05 +01:00
Samuel Pitoiset
43eff522e9 ac/debug: add a function that dumps texture descriptors 
In a human readable way. Useful for debugging.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39285>
 2026-01-16 11:35:34 +00:00
Samuel Pitoiset
5555297121 radv/meta: always use mip level 0 for source image resolves 
MSAA+mipmaps isn't a thing.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39285>
 2026-01-16 11:35:34 +00:00
Samuel Pitoiset
cb57338d6f radv/meta: batch resolving all color image layers with compute 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39285>
 2026-01-16 11:35:34 +00:00
Samuel Pitoiset
1199f91a2f radv/meta: use 2D array for color resolves with compute 
Cc: mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39285>
 2026-01-16 11:35:34 +00:00
Valentine Burley
939eab79bb radeonsi/ci: Merge VA-API jobs 
Combine the `radeonsi-raven-va` and `radeonsi-raven-vaapi-fluster` jobs
into one deqp-runner suite.
OOM kills no longer appear to be an issue.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39015>
 2026-01-16 10:29:41 +00:00
Valentine Burley
7af687bd33 radeonsi/ci: Remove redundant radeonsi-vaapi-fluster-rules 
The only difference was that these rules incorrectly added a second
-fluster suffix to the expectation files after a refactoring.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39015>
 2026-01-16 10:29:41 +00:00
Valentine Burley
47d85dc568 radeonsi/ci: Convert libva-utils job to deqp-runner suite 
Drop the custom gtest-runner.sh script and add a deqp-runner suite for
the `radeonsi-raven-va` job.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39015>
 2026-01-16 10:29:41 +00:00
Rhys Perry
d2a9122cfa aco/tests: add function call regalloc tests
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
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/38811>
 2026-01-16 10:05:43 +00:00
Rhys Perry
aa09335485 aco/ra: emit p_split_vector after p_parallelcopy 
This fixes situations where the variable being split is a parallelcopy
definition.

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/38811>
 2026-01-16 10:05:43 +00:00
Rhys Perry
7caa0ab897 aco/ra: fix split_blocking_vectors with some subdword vectors 
For example, v6b at byte=2 should be split into v2b,v1 instead of v1,v2b.

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/38811>
 2026-01-16 10:05:43 +00:00
Rhys Perry
667771950d aco/ra: update register file when recreating blocking vectors 
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/38811>
 2026-01-16 10:05:43 +00:00
Rhys Perry
5cf991ecfb aco/ra: use original name for blocking vectors rename 
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/38811>
 2026-01-16 10:05:43 +00:00
Rhys Perry
829e3a6a7d aco/ra: fix operands when recreating blocking vectors 
It is likely that these have been moved.

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/38811>
 2026-01-16 10:05:43 +00:00
Rhys Perry
6e6e40ab5c aco/ra: discard tmp_file after get_regs_for_copies fails 
get_regs_for_copies() might change tmp_file, so we need to create a new
one.

Recursively handle_call() with an modified register_file instead of
repeating get_regs_for_copies().

This also updates register_file for the caller.

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/38811>
 2026-01-16 10:05:43 +00:00
Rhys Perry
159154a741 aco/ra: remove dead code in split_blocking_vectors 
collect_vars_from_bitset() from the caller should have already cleared
these.

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/38811>
 2026-01-16 10:05:43 +00:00
Rhys Perry
89d06f7db5 aco: add RA validation for p_call 
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/38811>
 2026-01-16 10:05:43 +00:00
Rhys Perry
d0801c9eb7 aco: always run RA validation during 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/38811>
 2026-01-16 10:05:43 +00:00
Rhys Perry
bf30a57440 aco/ra: omit renaming when necessary when moving copy definitions 
This should resolve the FIXME.

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/38811>
 2026-01-16 10:05:41 +00:00
Rhys Perry
8dcfce3587 aco/ra: refactor update_renames slightly 
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/38811>
 2026-01-16 10:05:39 +00:00
Samuel Pitoiset
cb7e1859d7 radv/sqtt: fail if GPU clocks can't be sampled 
All timing would be wrong otherwise, this should be considered a real
error.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39311>
 2026-01-16 08:30:32 +00:00
Samuel Pitoiset
feed5fbc71 radv/sqtt: delay VMID reservation at capture time 
If two devices/instances are created, the VMID reservation will just
fail. It seems fine as long as it's reserved before SPM is used.

Fixes: a7a4abc8d8 ("radv: Move VMID reservation to vkCreateDevice")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39311>
 2026-01-16 08:30:32 +00:00
Emma Anholt
ed8676dc28 nir: Rename the unit_test_*_amd intrinics to be un-vendored. 
We'll reuse these from the nir_opt_algebraic_pattern_test.

Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39076>
 2026-01-15 19:09:37 +00:00
Emma Anholt
b375da7f2a nir: Let nir_eval_const_opcode() return a poison mask in case of UB. 
This is unused by any callers currently, but will be useful for nir
algebraic pattern testing, and as a way to turn our comments in
nir_opcodes.py into actual C code.  For now, always returns false.

Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39076>
 2026-01-15 19:09:32 +00:00
Samuel Pitoiset
ae34627e54 ac/cmdbuf: disable ENABLE_PING_PONG_BIN_ORDER on GFX11.5
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
Might be a hardware bug.

Cc: mesa-stable
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/14240
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39315>
 2026-01-15 17:55:26 +00:00
Benjamin Cheng
371656de90 radv/video_enc: Remove CTS WA 
This has been fixed in CTS since ebe05a88f36e3be8e232bfce97812353c396674a.

Reviewed-by: David Rosca <david.rosca@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39242>
 2026-01-15 11:45:33 +00:00
Marek Olšák
fa88c65bb8 radv,radeonsi: don't set LINE_STIPPLE_TEX_ENA on gfx12 
Fixes: 3c5c96fedb - radv: double pixel throughput in certain cases of PS without interpolated inputs
Fixes: 5acabdd1f8 - radeonsi: double pixel throughput in certain cases of PS without inputs
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/14646

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39316>
 2026-01-15 09:12:13 +00:00
Samuel Pitoiset
c559042a2a radv/dgc: adjust task+mesh SQTT markers 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39178>
 2026-01-15 09:43:00 +01:00
Samuel Pitoiset
82d00a4963 radv: fix missing SQTT markers for task+mesh draws 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39178>
 2026-01-15 09:43:00 +01:00
Samuel Pitoiset
aee006efcd radv/sqtt: emit userdata in the gang CS when needed 
For task shaders.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39178>
 2026-01-15 09:43:00 +01:00
Samuel Pitoiset
4da2e971e6 radv/sqtt: rework radv_emit_sqtt_userdata() to support gang CS 
For task shaders.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39178>
 2026-01-15 09:42:59 +01:00
Samuel Pitoiset
1917750baf ci: uprev VKCTS main to 4d3bedc74e2258c483cf968753207cff84d9e4fc 
RADV is the only driver using VKCTS main.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39229>
 2026-01-15 06:43:34 +00:00
Natalie Vock
6f076cdfda radv: Use wave32 for RT on gfx11+ 
ACO got a lot better at forming VOPD instructions, and testing
feedback seems to point in a slightly positive direction for this.

gfx12 will also start requiring wave32 for dynamic VGPR allocation at
some point.

Measurements on navi31:

Cyberpunk 2077:
Difference at 95.0% confidence
        1.12333 +/- 0.42876
        1.88216% +/- 0.718391%
        (Student's t, pooled s = 0.189165)

Black Myth Wukong benchmark:
Difference at 95.0% confidence
        4 +/- 1.30862
        13.9535% +/- 4.56495%
        (Student's t, pooled s = 0.57735)

Portal with RTX:
66.2ms->61.5ms (~7.64% improvement)

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39275>
 2026-01-14 23:39:24 +00:00
Aitor Camacho
fcf53988c4 nir/opt_varyings: Support implementations that cannot compact 16-bits
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
Add nir_io_compact_to_higher_16 flag so that the pass knows if it can
compact 16-bit varyings into the higher 16 bits of a 32-bit varying.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Aitor Camacho <aitor@lunarg.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38994>
 2026-01-14 20:44:41 +00:00
Natalie Vock
cc81c7de23 nir,aco: Clean up useless lowering of sbt_base_amd 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29580>
 2026-01-14 14:19:07 +00:00
Natalie Vock
27c0326391 radv: Re-enable RT pipelines 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29580>
 2026-01-14 14:19:07 +00:00