OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
153,874 Commits 9 Branches 1 Tag
29965f356b9cf464e152acf63dc67b85040dc385
Commit Graph

34 Commits

Author SHA1 Message Date
Marek Olšák
29965f356b ac: replace 5 ac_shader_abi::load_* callbacks with 1 intrinsic_load callback 
This merges them into si_llvm_load_intrinsic and reuses load_tess_varyings.

RADV only implemented 1 callback.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16467>
 2022-05-13 06:45:31 -04:00
Marek Olšák
dc81f0ba46 ac/llvm: remove ac_shader_abi::emit_outputs 
it's called last in ac_nir_translate, so call it in the caller.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16467>
 2022-05-13 06:44:57 -04:00
Timur Kristóf
27c4d8d5fa ac/llvm: Remove now-superfluous intrinsics and ABI callbacks. 
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13155>
 2022-05-10 17:16:03 +00:00
Rhys Perry
f6262804af radv: increase inline push constant limit if we can inline all constants 
fossil-db (Sienna Cichlid):
Totals from 665 (0.49% of 134627) affected shaders:
CodeSize: 4519620 -> 4491724 (-0.62%); split: -0.62%, +0.01%
Instrs: 842745 -> 837313 (-0.64%); split: -0.66%, +0.01%
Latency: 7289925 -> 7279661 (-0.14%); split: -0.30%, +0.16%
InvThroughput: 1240770 -> 1240639 (-0.01%); split: -0.01%, +0.00%
VClause: 15799 -> 15772 (-0.17%)
SClause: 33773 -> 32604 (-3.46%); split: -3.66%, +0.20%
Copies: 67695 -> 64992 (-3.99%); split: -4.49%, +0.50%
PreSGPRs: 38597 -> 38640 (+0.11%); split: -0.14%, +0.25%

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/12145>
 2022-04-12 11:44:30 +00:00
Samuel Pitoiset
4cfb5332d6 radv: lower adjusting gl_FragCoord.z for VRS in NIR 
fossils-db (Sienna Cichlid):
Totals from 4432 (3.29% of 134913) affected shaders:
VGPRs: 231232 -> 231880 (+0.28%)
CodeSize: 24738224 -> 24718008 (-0.08%); split: -0.08%, +0.00%
MaxWaves: 93120 -> 93000 (-0.13%)
Instrs: 4540970 -> 4541062 (+0.00%); split: -0.01%, +0.01%
Latency: 49658353 -> 49641444 (-0.03%); split: -0.05%, +0.01%
InvThroughput: 9604328 -> 9603041 (-0.01%); split: -0.02%, +0.01%
VClause: 66497 -> 66498 (+0.00%)
SClause: 209530 -> 209532 (+0.00%); split: -0.01%, +0.01%
Copies: 276135 -> 276249 (+0.04%); split: -0.14%, +0.18%
PreSGPRs: 189409 -> 189415 (+0.00%)
PreVGPRs: 207368 -> 207458 (+0.04%)

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15450>
 2022-03-28 16:17:37 +02:00
Rhys Perry
15640e58d9 radv,aco: lower texture descriptor loads in NIR 
fossil-db (Sienna Cichlid):
Totals from 39445 (24.30% of 162293) affected shaders:
MaxWaves: 875988 -> 875972 (-0.00%)
Instrs: 35372561 -> 35234909 (-0.39%); split: -0.41%, +0.03%
CodeSize: 190237480 -> 189379240 (-0.45%); split: -0.47%, +0.02%
VGPRs: 1889856 -> 1889928 (+0.00%); split: -0.00%, +0.01%
SpillSGPRs: 10764 -> 10857 (+0.86%); split: -2.04%, +2.91%
SpillVGPRs: 1891 -> 1907 (+0.85%); split: -0.32%, +1.16%
Scratch: 260096 -> 261120 (+0.39%)
Latency: 477701150 -> 477578466 (-0.03%); split: -0.06%, +0.03%
InvThroughput: 87819847 -> 87830346 (+0.01%); split: -0.03%, +0.04%
VClause: 673353 -> 673829 (+0.07%); split: -0.04%, +0.11%
SClause: 1385396 -> 1366478 (-1.37%); split: -1.65%, +0.29%
Copies: 2327965 -> 2229134 (-4.25%); split: -4.58%, +0.34%
Branches: 906707 -> 906434 (-0.03%); split: -0.13%, +0.10%
PreSGPRs: 1874153 -> 1862698 (-0.61%); split: -1.34%, +0.73%
PreVGPRs: 1691382 -> 1691383 (+0.00%); split: -0.00%, +0.00%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12773>
 2022-03-22 16:33:27 +00:00
Rhys Perry
52f850238a radv,aco: lower buffer descriptor loads in NIR 
fossil-db (Sienna Cichlid):
Totals from 75420 (46.47% of 162293) affected shaders:
MaxWaves: 1878200 -> 1879228 (+0.05%); split: +0.06%, -0.00%
Instrs: 54021103 -> 54141370 (+0.22%); split: -0.04%, +0.26%
CodeSize: 287813520 -> 288293352 (+0.17%); split: -0.04%, +0.21%
VGPRs: 3267576 -> 3266296 (-0.04%); split: -0.04%, +0.00%
SpillSGPRs: 10445 -> 10904 (+4.39%); split: -0.31%, +4.70%
SpillVGPRs: 1818 -> 1811 (-0.39%); split: -1.05%, +0.66%
Scratch: 955392 -> 954368 (-0.11%)
Latency: 563477854 -> 562131282 (-0.24%); split: -0.31%, +0.08%
InvThroughput: 111860104 -> 111553968 (-0.27%); split: -0.30%, +0.02%
VClause: 958432 -> 961415 (+0.31%); split: -0.34%, +0.65%
SClause: 1917415 -> 1926952 (+0.50%); split: -0.69%, +1.19%
Copies: 3812945 -> 3916758 (+2.72%); split: -0.27%, +2.99%
Branches: 1611235 -> 1612022 (+0.05%); split: -0.04%, +0.08%
PreSGPRs: 3095505 -> 3126580 (+1.00%); split: -0.06%, +1.07%
PreVGPRs: 2773011 -> 2773013 (+0.00%)

Most regressions seem to be because ACO's convert_pointer_to_64_bit()
can't be CSE'd with radv_nir_apply_pipeline_layout()'s
convert_pointer_to_64_bit(). This should be improved by later commits.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12773>
 2022-03-22 16:33:27 +00:00
Rhys Perry
22050fcf9d radv,aco: lower vulkan_resource_index in NIR 
fossil-db (Sienna Cichlid):
Totals from 31338 (19.31% of 162293) affected shaders:
MaxWaves: 758634 -> 758616 (-0.00%)
Instrs: 26398289 -> 26378282 (-0.08%); split: -0.09%, +0.01%
CodeSize: 141048208 -> 140971060 (-0.05%); split: -0.07%, +0.01%
VGPRs: 1373656 -> 1373736 (+0.01%)
SpillSGPRs: 9944 -> 9924 (-0.20%); split: -0.24%, +0.04%
SpillVGPRs: 1892 -> 1898 (+0.32%); split: -0.95%, +1.27%
Latency: 308570144 -> 308528462 (-0.01%); split: -0.03%, +0.02%
InvThroughput: 57698072 -> 57684901 (-0.02%); split: -0.07%, +0.04%
VClause: 440357 -> 440602 (+0.06%); split: -0.02%, +0.08%
SClause: 974724 -> 973315 (-0.14%); split: -0.18%, +0.04%
Copies: 1944925 -> 1945103 (+0.01%); split: -0.11%, +0.12%
Branches: 799444 -> 799461 (+0.00%); split: -0.00%, +0.00%
PreSGPRs: 1619860 -> 1619233 (-0.04%); split: -0.05%, +0.02%
PreVGPRs: 1252813 -> 1252863 (+0.00%); split: -0.00%, +0.00%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12773>
 2022-03-22 16:33:27 +00:00
Rhys Perry
c4cf92cad7 radv,aco,ac/llvm: fix indirect dispatches on the compute queue on GFX7-10 
Since neither PKT3_LOAD_SH_REG_INDEX nor PKT3_COPY_DATA work with compute
queues on GFX7-10, we have to load the dispatch size from memory in the
shader.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15064>
 2022-03-14 19:54:36 +00:00
Samuel Pitoiset
8a327722d5 ac/nir: add an option to disable anisotropic filtering for single level images 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14171>
 2021-12-16 07:20:50 +00:00
Marek Olšák
69e96cfc0d ac,radv: remove unused inputs array and VS input code 
The previous commit stopped using "inputs".

"load_layer_id" has always been broken and it was probably unused anyway.

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12570>
 2021-09-07 17:51:41 +00:00
Marek Olšák
1e178f7a37 ac: make ac_shader_abi::inputs an array instead of a pointer 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12570>
 2021-09-07 17:51:41 +00:00
Marek Olšák
6df5f268db ac: remove needless parameters from ac_shader_abi::emit_outputs 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12570>
 2021-09-07 17:51:41 +00:00
Marek Olšák
2e95ad1433 ac/llvm: implement a bunch of NIR AMD intrinsics for NGG 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12570>
 2021-09-07 17:51:41 +00:00
Marek Olšák
a33602b1f9 ac/llvm: remove load_tess_coord callback 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12570>
 2021-09-07 17:51:41 +00:00
Timur Kristóf
6e7b1cd251 ac/llvm: Implement new Geometry Shader intrinsics. 
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9201>
 2021-03-17 12:42:23 +00:00
Timur Kristóf
20a2801011 ac/llvm: Implement the new tessellation intrinsics. 
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9201>
 2021-03-17 12:42:23 +00:00
Rhys Perry
2f2a9f253e radv,ac/nir: implement non-uniform get_ssbo_size 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Gitlab: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3711
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7969>
 2021-01-27 13:00:33 +00:00
Samuel Pitoiset
45524afe95 radv/llvm: implement a workaround for gl_FragCoord.z with VRS on GFX10.3 
Without it, FragCoord.z will have the value of one of the fine pixels
instead of the center of the coarse pixel.

It's only enabled for RADV.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7837>
 2020-12-14 16:22:38 +00:00
Marek Olšák
d7ee265a95 ac,radeonsi: fix load_first_vertex 
GL doesn't use it, so this change is not necessary, but it's better
this way.

There is also a small cleanup using si_unpack_param.

Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7721>
 2020-12-01 15:33:03 -05:00
Marek Olšák
6f13034265 ac/llvm: prepare for passing VS->TCS IO via VGPRs 
- bump AC_MAX_ARGS
- add vertex_index_is_invoc_id parameter into load_tess_varyings

Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7623>
 2020-11-23 02:22:21 +00:00
Samuel Pitoiset
6387341cce ac/nir: pass the variable location to store_tcs_outputs 
It's actually simpler for the backend to know the variable location.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7022>
 2020-10-12 09:23:25 +02:00
Samuel Pitoiset
f984654da8 ac/nir,radv: fix invalid IR when loading inline uniform blocks 
Fixes dEQP-VK.binding_model.descriptorset_random.* and
dEQP-VK.binding_model.descriptor_copy.*.

Fixes: 05b6612b4e ("radv: do not lower UBO/SSBO access to offsets")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6977>
 2020-10-05 14:06:16 +02:00
Samuel Pitoiset
9896337d1b ac,radv,radeonsi: remove unused parameters in the shader ABI IO 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6931>
 2020-10-05 13:14:33 +02:00
Pierre-Eric Pelloux-Prayer
82d2d73e03 amd/llvm: switch to 3-spaces style 
Follow-up of !4319 using the same clang-format config.

Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5310>
 2020-09-07 10:00:20 +02:00
Marek Olšák
408fc4e3ac ac/nir: handle all lowered IO intrinsics 
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Connor Abbott <cwabbott0@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6445>
 2020-09-02 22:45:38 -04:00
Pierre-Eric Pelloux-Prayer
32f46a55c8 ac/llvm: add option to clamp division by zero 
Replace div(x) by min(div(x), FLT_MAX)) to avoid getting a NaN result
when x is 0.

A cheaper alternative would be to use legacy mult instructions but they're
not exposed by LLVM.

Cc: mesa-stable
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6259>
 2020-09-02 11:53:16 +02:00
Pierre-Eric Pelloux-Prayer
ae4379d81e ac/nir: export some undef as zero 
NIR already optimizes undef usage.
If undef reaches llvm, it's probably because of a broken shader.

In this situation, rather than letting llvm use the undef values
to do more optimization and probably produce incorrect results,
we replace undef values by 0.

"undef" values that are directly used in exports are kept as undef,
because this allows llvm to optimize them away.

This is only enabled for radeonsi.

Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/2689
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4607>
 2020-05-05 12:26:26 +02:00
Pierre-Eric Pelloux-Prayer
64662dd5ba radeonsi: add workaround for issue 2647 
For unknown reasons pixel shaders in KSP game get executed with
infinite interpolation coefficients and this causes an infinite
loop in the shader.

This commit adds a hacky workaround that kills pixel shaders if
invalid interp coeffs are detected and enables it for KSP.

Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2174
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2647
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4700>
 2020-05-05 09:41:14 +00:00
Samuel Pitoiset
9f005f1f85 radv: enable lowering of GS intrinsics for the LLVM backend 
This replaces emit_vertex with:
   if (vertex_count < max_vertices) {
      emit_vertex_with_counter vertex_count ...
      vertex_count += 1
   }

Which is exactly what NIR->LLVM was doing but at NIR level. This
pass is already called by ACO.

pipeline-db changes on GFX10:
Totals from affected shaders:
SGPRS: 1952 -> 1912 (-2.05 %)
VGPRS: 2112 -> 2044 (-3.22 %)
Code Size: 189368 -> 185620 (-1.98 %) bytes
Max Waves: 494 -> 491 (-0.61 %)

No pipeline-db changes on other generations.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4182>
 2020-04-08 08:24:05 +02:00
Daniel Schürmann
61fb17e8d7 amd: join emit_kill() from radv and radeonsi in ac_nir_to_llvm 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4047>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4047>
 2020-03-09 12:29:32 +00:00
Connor Abbott
3b143369a5 ac/nir, radv, radeonsi: Switch to using ac_shader_args 
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Marek Olšák <marek.olsak@amd.com>
 2019-11-25 14:17:10 +01:00
Connor Abbott
9885af3bdf ac: Add a shared interface between radv, radeonsi, LLVM and ACO 
ac_shader_args will be similar to ac_shader_abi, except for being free
from LLVM-specific concepts and therefore capable of being shared
between LLVM and ACO. This will help us accomplish a few different
things:

- Decouple setting up SGPR and VGPR arguments from translating to LLVM,
so that we can reference these arguments in NIR lowering passes, which
will let us lower e.g. descriptor sets in NIR.

- Stop using radv-specific structures for things like determining the
chip generation in ACO.

In the end, we should replace ac_shader_abi with this structure +
driver-specific lowering passes.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
 2019-11-25 14:12:46 +01:00
Timur Kristóf
3a08110d43 amd: Move all amd/common code that depends on LLVM to amd/llvm. 
This commit is a step towards the goal of being able to build RADV
without LLVM. In the future we would like to offer the option to
use RADV solely with ACO. There is still a need for the common AMD
code located in amd/common but the LLVM specific parts need to be
separated.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Acked-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
 2019-10-08 00:44:08 +00:00