fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-26 05:58:11 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
214874 commits 66 branches 936 tags 1 GiB
Commit graph

71949 commits

Author SHA1 Message Date
Gert Wollny
1f58a36abb r600/sfn: Add method to force-override the dest of an AluInstr 
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37321>
 2025-11-17 14:46:57 +00:00
Gert Wollny
6f8841b338 r600/sfn: Make value factory a member of the block scheduler 
No need to pass it around all the time.

Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37321>
 2025-11-17 14:46:56 +00:00
Gert Wollny
8e0a0ca098 r600/sfn: Add slot access operator to AluGroup 
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37321>
 2025-11-17 14:46:56 +00:00
Gert Wollny
12d913fe4f r600/sfn: change register ID of dummy dest register 
Handle it correctly in the assembler, live range evaluation
and RA.

Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37321>
 2025-11-17 14:46:56 +00:00
Gert Wollny
fc5728950b r600/sfn: don't use dummy register with non-write 64 bit slots 
For trans ops and two source ops we can just clear the write flag

Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37321>
 2025-11-17 14:46:56 +00:00
Gert Wollny
603af345be r600/sfn: fix querying number of sources for LDS ops in readport validation 
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37321>
 2025-11-17 14:46:55 +00:00
Gert Wollny
0cd0efbbf9 r600/sfn: Don't assign dest registers in non-write interpolation slots 
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37321>
 2025-11-17 14:46:55 +00:00
Gert Wollny
ebe395608a r600/sfn: Silence warning about unused parameter 
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37321>
 2025-11-17 14:46:55 +00:00
Gert Wollny
43df08dd42 r600/sfn: remove some unused static variables 
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37321>
 2025-11-17 14:46:54 +00:00
Gert Wollny
a22c03f0a3 r600: Handle dummy dest in assembler and disass 
The dummy dest will not be allocated, so we must not
count it.

In the disassambler write PV and PS if the ALU dest GPR is
only used via PS/PV.

Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37321>
 2025-11-17 14:46:54 +00:00
Valentine Burley
eb0c95a5d5 lavapipe/ci: Run vkd3d job in parallel 
This appears to be stable now, and running on multiple threads fixes the
the timeout problems we were hitting in lavapipe-vkd3d.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38476>
 2025-11-17 14:00:10 +00:00
Samuel Pitoiset
f5ecc5ffd5 ac,radv,radeonsi: add ac_emit_sdma_copy_tiled_sub_window() 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38448>
 2025-11-17 11:29:24 +00:00
Samuel Pitoiset
5f8fa6ae03 ac,radv,radeonsi: add ac_emit_sdma_copy_linear_sub_window() 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38448>
 2025-11-17 11:29:23 +00:00
Samuel Pitoiset
6413651bcf ac,radv,radeonsi: add ac_emit_sdma_copy_linear() 
RadeonSI wasn't considering the undocumented HW limitation apparently.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38430>
 2025-11-17 08:28:37 +01:00
Timur Kristóf
cad4e7d2e7 radv, radeonsi: Move GFX6-7 CB clamp issue to ac_gpu_info 
To improve consistency between the two drivers.
This excludes Hawaii from the workaround on RADV.

Also add the same to ac_null_device_create().

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38304>
 2025-11-15 14:24:59 +01:00
Timur Kristóf
35b376b942 radeonsi: Respect if rbplus is allowed when choosing color formats 
For consistency with RADV.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38304>
 2025-11-15 14:24:52 +01:00
Timur Kristóf
4f793d2515 radeonsi: Inline si_choose_spi_color_formats 
Will be necessary for the subsequent commit.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38304>
 2025-11-15 14:24:46 +01:00
Marek Olšák
f9341082a2 nir,glsl,zink: remove the option nir_io_separate_clip_cull_distance_arrays
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
This calls nir_separate_merged_clip_cull_io in zink, which is better
than having to handle separate clip & cull arrays in all passes.

Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38452>
 2025-11-15 03:30:10 +00:00
Marek Olšák
e372365cf4 nir: rename nir_copy_prop -> nir_opt_copy_prop 
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38411>
 2025-11-15 02:16:38 +00:00
Lucas Fryzek
b75b0ce7b2 lp: Implement gallium depth_bounds_test capability
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
Support for this capability in llvmpipe expose
support for GL_EXT_depth_bounds_test, as well as supporting
the `depthBounds` device feature in lavapipe.

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36487>
 2025-11-14 09:43:22 +00:00
Daniel Schürmann
7ee1932309 treewide: Never preserve nir_metadata_dominance without nir_metadata_block_index 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38367>
 2025-11-14 09:09:14 +00:00
Adrián Larumbe
a24f490488 panfrost: match a GL object's maximum label length to KMD uAPI limit 
At present, this is the value mandated by the KMD's uAPI, or 4096 bytes.

Signed-off-by: Adrián Larumbe <adrian.larumbe@collabora.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38027>
 2025-11-13 19:16:15 +00:00
Adrián Larumbe
a68c584d70 mesa: gallium: make GL object maximum label length a pipescreen cap 
Commit a4ffd2395f ("mesa: Implement label sharing from GL objects with
UM drivers") enabled GL clients to tag objects at a UM driver level. In
the case of Panfrost, and for both KMDs, maximum label size is set to
4096, but the Mesa limit is much lower.

Since glObjectLabel() allocates object labels dynamically, there's no
need to have this value chiseled in stone, so allow Gallium driver
implementers to set their own limit through a pipe screen capability.

Keep the same default maximum label length as before.

Signed-off-by: Adrián Larumbe <adrian.larumbe@collabora.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38027>
 2025-11-13 19:16:15 +00:00
Pohsiang (John) Hsu
e9757d25e0 mediafoundation: propagate input timestamp / duration to output 
Reviewed-by: Sil Vilerino <sivileri@microsoft.com>

Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/14261
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38427>
 2025-11-13 16:31:06 +00:00
Benjamin Cheng
b4ae11ee42 ac,radeonsi/vcn,radv/video: Drop signature param 
The signature is not very useful, and is unnecessary CPU overhead.

Reviewed-by: David Rosca <david.rosca@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38372>
 2025-11-13 14:35:58 +00:00
Gert Wollny
79e4323cf0 r600/sfn: Don't start a new ALU-CF if LDS pipeline loads are pending 
Fixes: e57643cf (r600/sfn: Add handling for R600 indirect access alias handling)

Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38398>
 2025-11-13 11:17:51 +00:00
Qiang Yu
ece827d53b radeonsi: enable EXT_mesh_shader 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:27 +00:00
Qiang Yu
3d01529316 radeonsi: si_calculate_max_simd_waves support task and mesh shader 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:25 +00:00
Qiang Yu
4495978932 radeonsi: handle maybe per primitive input for fragment shader 
Some fragment shader may be per-primitive when mesh pipeline,
per-vertex when vertex pipeline. We sort these inputs always
after other per-vertex inputs in nir_recompute_io_bases, so
fragment shader code is same, just need to set different reg.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:24 +00:00
Qiang Yu
1733dddee9 radeonsi: add mesh shader functions 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:23 +00:00
Qiang Yu
4c220f9745 radeonsi: add si_emit_rasterizer_prim_state_for_mesh 
To be used by mesh pipeline.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:22 +00:00
Qiang Yu
4ee6553767 radeonsi: add si_update_shaders_for_mesh 
To be used by mesh pipeline.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:20 +00:00
Qiang Yu
8410970e8b radeonsi: add si_update_shaders_shared_by_vertex_and_mesh_pipe 
Move shared part of si_update_shaders to this function,
no implementation change.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:19 +00:00
Qiang Yu
87715a1c8c radeonsi: compute culldist_mask and clipdist_mask for mesh shader 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:18 +00:00
Qiang Yu
355e499b52 radeonsi: si_emit_buffered_compute_sh_regs support gang cs 
To be used by task shader gang cs.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:17 +00:00
Qiang Yu
b713f453c6 radeonsi: lower mesh shader local id and workgroup id 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:15 +00:00
Qiang Yu
2e025d66c3 radeonsi: add task shader queries support 
Need to emit query start/stop/sample packets in compute
queue.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:15 +00:00
Qiang Yu
9a31151436 radeonsi: increase task wait count when emit barrier 
It will be waited by task queue too.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:15 +00:00
Qiang Yu
c0f6e97d6c radeonsi: implement nir_intrinsic_load_ring_mesh_scratch_amd 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:13 +00:00
Qiang Yu
5048216b43 radeonsi: init mesh shader ngg info 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:13 +00:00
Qiang Yu
432f66a7b6 radeonsi: add si_create_compute_state_for_nir 
To be shared by task shader state creation.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:11 +00:00
Qiang Yu
263cce11bd radeonsi: move shared_size to si_shader_variant_info 
For mesh shader which know this after ac_nir_lower_ngg_mesh.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:08 +00:00
Qiang Yu
e3ab6249f2 radeonsi: export si_init_compute_preamble_state for task shader 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:03 +00:00
Qiang Yu
0ee4747678 radeonsi: log cs support mesh shader 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:02 +00:00
Qiang Yu
f1138c18ac radeonsi: implement task ring nir intrinsic lower 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:02 +00:00
Qiang Yu
e819554b2a radeonsi: add task/mesh shader context states 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:30:00 +00:00
Qiang Yu
cffc40051d winsys/amdgpu: support gang submit for kernel queue 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:29:58 +00:00
Qiang Yu
963ad4bb4e radeonsi: add si_emit_task_shader_pointers 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:29:58 +00:00
Qiang Yu
66cd3f1b52 radeonsi: add si_upload_shader_descriptos 
To be shared with gfx, mesh and compute pipeline.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:29:55 +00:00
Qiang Yu
12f33b596c radeonsi: export si_setup_compute_scratch_buffer for task shader 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38044>
 2025-11-13 01:29:54 +00:00