a263474d3b
nir/algebraic: Move some generated-code algebraic opt args into a struct.
...
I'm going to be adding some more tables to reduce relocations in the
generated code, so move the current tables to a struct for arg-passing
sanity.
Reviewed-by: Adam Jackson <ajax@redhat.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13987 >
2021-12-07 07:08:59 +00:00
b88202b0e4
nir/constant_folding: Optimize txb with bias of constant zero to tex
...
v2: Fail gracefully when bias_idx < 0. See comment in the code for the
rationale. See also issue #5722 .
All Haswell and newer Intel GPUs had similar results. (Ice Lake shown)
total instructions in shared programs: 19757733 -> 19753431 (-0.02%)
instructions in affected programs: 277248 -> 272946 (-1.55%)
helped: 1644
HURT: 1
helped stats (abs) min: 1 max: 16 x̄: 2.62 x̃: 2
helped stats (rel) min: 0.05% max: 11.11% x̄: 2.11% x̃: 1.61%
HURT stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
HURT stats (rel) min: 0.35% max: 0.35% x̄: 0.35% x̃: 0.35%
95% mean confidence interval for instructions value: -2.72 -2.51
95% mean confidence interval for instructions %-change: -2.19% -2.03%
Instructions are helped.
total cycles in shared programs: 938517439 -> 938384079 (-0.01%)
cycles in affected programs: 19548849 -> 19415489 (-0.68%)
helped: 1358
HURT: 269
helped stats (abs) min: 1 max: 2328 x̄: 133.01 x̃: 16
helped stats (rel) min: <.01% max: 41.12% x̄: 1.40% x̃: 0.48%
HURT stats (abs) min: 1 max: 1302 x̄: 175.70 x̃: 30
HURT stats (rel) min: <.01% max: 69.03% x̄: 6.24% x̃: 1.04%
95% mean confidence interval for cycles value: -99.14 -64.79
95% mean confidence interval for cycles %-change: -0.47% 0.19%
Inconclusive result (%-change mean confidence interval includes 0).
LOST: 21
GAINED: 32
All Ivy Bridge and older Intel GPUs had similar results. (Ivy Bridge shown)
total instructions in shared programs: 15302017 -> 15301485 (<.01%)
instructions in affected programs: 22565 -> 22033 (-2.36%)
helped: 168
HURT: 0
helped stats (abs) min: 1 max: 7 x̄: 3.17 x̃: 3
helped stats (rel) min: 0.04% max: 4.39% x̄: 3.05% x̃: 3.27%
95% mean confidence interval for instructions value: -3.45 -2.89
95% mean confidence interval for instructions %-change: -3.19% -2.91%
Instructions are helped.
total cycles in shared programs: 550119761 -> 549989147 (-0.02%)
cycles in affected programs: 12834251 -> 12703637 (-1.02%)
helped: 164
HURT: 0
helped stats (abs) min: 20 max: 4547 x̄: 796.43 x̃: 294
helped stats (rel) min: 0.23% max: 53.84% x̄: 2.05% x̃: 0.37%
95% mean confidence interval for cycles value: -942.62 -650.24
95% mean confidence interval for cycles %-change: -3.17% -0.94%
Cycles are helped.
fossil-db results:
Tiger Lake, Ice Lake, and Skylake had similar results. (Ice Lake shown)
Instructions in all programs: 142073649 -> 141307526 (-0.5%)
SENDs in all programs: 6876848 -> 6876778 (-0.0%)
Loops in all programs: 38283 -> 38283 (+0.0%)
Cycles in all programs: 8410049681 -> 8402902960 (-0.1%)
Spills in all programs: 190623 -> 190599 (-0.0%)
Fills in all programs: 297780 -> 297756 (-0.0%)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net > [v1]
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14025 >
2021-12-06 19:50:42 +00:00
0cbcc15afe
nir: add a ray query optimization pass
...
Just remove queries that are never used or proceeded with. The latter
case leading to undefined values.
v2: Don't use nir_shader_instructions_pass() to find variables (Caio)
Simplify replacement (Caio)
v3: Don't track all the queries intrinsic effects (Caio)
Rename things to represent only read queries (Caio)
Use set instead of hash_table (Caio)
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13718 >
2021-12-04 20:46:35 +00:00
5a9cdab170
nir: track variables representing ray queries
...
v2: Fix missing ray_query variable check (Caio)
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13718 >
2021-12-04 20:46:35 +00:00
0d6f050b46
nir: add intrinsics for ray queries
...
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13718 >
2021-12-04 20:46:35 +00:00
0800ec2c77
nir: add a new access flag to allow access in helper invocations
...
v2: Add nir_print support
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13718 >
2021-12-04 20:46:35 +00:00
54489b3c09
nir/print: printout ACCESS_STREAM_CACHE_POLICY
...
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13718 >
2021-12-04 20:46:35 +00:00
f98984ad13
nir/lower_io: include the variable access in the lowered intrinsic
...
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Cc: mesa-stable
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13718 >
2021-12-04 20:46:35 +00:00
b717872e08
intel/compiler: Get mesh_global_addr from the Inline Parameter for Task/Mesh
...
Signed-off-by: Marcin Ślusarz <marcin.slusarz@intel.com >
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13661 >
2021-12-04 00:41:46 +00:00
f28adc711f
nir: Print task and mesh shader I/O variable names.
...
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com >
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14007 >
2021-12-03 21:34:45 +00:00
7e66da89f8
nir: Fix sorting per-primitive outputs.
...
Fixes: 59860d4873timur.kristof@gmail.com >
Reviewed-by: Marek Olšák <marek.olsak@amd.com >
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14006 >
2021-12-03 17:06:47 +00:00
a2d8c5b26d
nir/algebraic: optimize a*#b & -4
...
fossil-db (Sienna Cichlid):
Totals from 611 (0.47% of 128647) affected shaders:
CodeSize: 3096680 -> 3090976 (-0.18%)
Instrs: 570494 -> 569249 (-0.22%)
Latency: 5765865 -> 5759619 (-0.11%)
InvThroughput: 969840 -> 967608 (-0.23%)
VClause: 9690 -> 9688 (-0.02%)
Copies: 42884 -> 42894 (+0.02%); split: -0.01%, +0.03%
PreVGPRs: 28290 -> 28288 (-0.01%)
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13752 >
2021-12-03 13:41:07 +00:00
2368c36427
nir/opt_offsets: remove need to loop try_extract_const_addition
...
fossil-db (Sienna Cichlid):
Totals from 1 (0.00% of 134572) affected shaders:
no stat changes
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com >
Reviewed-by: Emma Anholt <emma@anholt.net >
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14009 >
2021-12-03 11:51:49 +00:00
5c0fe11072
nir/opt_offsets: fix try_extract_const_addition recursion
...
This initially looks like a miscompilation bug, but I don't think it's
actually possible for it to create incorrect code.
fossil-db (Sienna Cichlid):
Totals from 32 (0.02% of 134572) affected shaders:
VGPRs: 1336 -> 1320 (-1.20%)
CodeSize: 90552 -> 89468 (-1.20%)
Instrs: 17007 -> 16852 (-0.91%); split: -0.92%, +0.01%
Latency: 429040 -> 428136 (-0.21%); split: -0.21%, +0.00%
InvThroughput: 84966 -> 84572 (-0.46%); split: -0.47%, +0.00%
Copies: 1458 -> 1468 (+0.69%); split: -0.07%, +0.75%
Branches: 382 -> 384 (+0.52%)
PreSGPRs: 970 -> 968 (-0.21%)
PreVGPRs: 1029 -> 1011 (-1.75%)
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com >
Reviewed-by: Emma Anholt <emma@anholt.net >
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14009 >
2021-12-03 11:51:49 +00:00
f77ccdfb4a
nir: add NIR_DEBUG envvar
...
Move all the NIR related debug environmental variables in a single
NIR_DEBUG one.
Use NIR_DEBUG=help to print all the available options.
v2:
- Use a macro to simplify (Marcin, Jason)
- Remove wrong changes (Marcin)
v3 (Marcin):
- Remove rendundant NIR mentioning in option descriptions.
- Unwrap option descriptions.
- Ensure the constant is unsigned.
- Use extern array to remove switch.
v4:
- Add missing kernel shader (Jason).
- Add unlikely() (Marcin).
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com >
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net >
Reviewed-by: Marcin Ślusarz <marcin.slusarz@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13840 >
2021-12-03 11:15:29 +00:00
06fe04b4d7
nir: Make nir_build_alu() variants per 1-4 arg count.
...
This saves a bunch of generated code to pack up the extra NULLs to get to
4 args, and saves executing the conditions in nir_build_alu() to then skip
those NULLs.
Saves another 27kb on disk.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13916 >
2021-12-01 22:12:19 +00:00
e770ec1182
nir: Uninline a bunch of nir.h functions.
...
I aimed for "things that look like big switch statements, or cases where
the compiler is unlikely to be able to constant-propagate an argument into
something useful."
Saves another 80kb on disk. No perf difference on iris shader-db, n=23.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13916 >
2021-12-01 22:12:19 +00:00
8e568d3f00
nir/opt_deref: don't try to cast empty structures
...
Found while running valgrind :
==3583454== Invalid read of size 4
==3583454== at 0xF48336: glsl_get_struct_field_offset (nir_types.cpp:84)
==3583454== by 0xC7CD0D: opt_replace_struct_wrapper_cast (nir_deref.c:1068)
==3583454== by 0xC7CDD9: opt_deref_cast (nir_deref.c:1087)
==3583454== by 0xC7DD8E: nir_opt_deref_impl (nir_deref.c:1369)
==3583454== by 0xC7DF4E: nir_opt_deref (nir_deref.c:1428)
==3583454== by 0xA63F3C: brw_kernel_from_spirv (brw_kernel.c:325)
==3583454== by 0xA3BC2C: main (intel_clc.c:481)
==3583454== Address 0xe4f7e88 is 24 bytes after a block of size 48 in arena "client"
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Cc: mesa-stable
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13952 >
2021-12-01 08:24:39 +00:00
391569e911
nir: Fix read depth for predecessors
...
In some non-trivial cases (the amber script file in the merge
request description) phi instruction has more than 32 elements
in predecessors tree and that isn't recursion, just large tree.
In that case, phis not fully converted into a register or mov,
but successfully removed.
The fix removes the counter and adds container of visited blocks.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3690
Cc: mesa-stable
Signed-off-by: Mykhailo Skorokhodov <mykhailo.skorokhodov@globallogic.com >
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13710 >
2021-11-30 00:12:48 +00:00
32a8b391e3
nir/tests: add DCE test for loops following a jump
...
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com >
Acked-by: Jason Ekstrand <jason@jlekstrand.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10284 >
2021-11-29 22:22:24 +00:00
cc5dd15417
nir/cf: fix insertion of loops/ifs after jumps
...
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com >
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10284 >
2021-11-29 22:22:24 +00:00
2fe13aa2ad
nir/dce: fix DCE of loops with a halt or return instruction in the pre-header
...
If there is a halt or return instruction right before a loop with a single
continue, we would have taken the fast path intended for loops without
continues.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com >
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com >
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net >
Tested-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Fixes: 71a985d80bhttps://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10284 >
2021-11-29 22:22:24 +00:00
b7f423006a
nir/lower_clip: support clipdist array + no vars
...
This runs after the "to io" lowering on freedreno. Support this case.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu >
Reviewed-by: Emma Anholt <emma@anholt.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13917 >
2021-11-28 04:44:56 +00:00
7efb1c4b29
nir/lower_clip: increment num_inputs/outputs by appropriate amount
...
The inputs/outputs are meant to be in vec4 units.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu >
Reviewed-by: Emma Anholt <emma@anholt.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13917 >
2021-11-28 04:44:56 +00:00
3bf47700e2
nir/lower_clip: location offset goes into offset, not base
...
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu >
Reviewed-by: Emma Anholt <emma@anholt.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13917 >
2021-11-28 04:44:56 +00:00
a8930e6302
nir/lower_clip: replace bogus comment about gl_ClipDistance reading in GL
...
gl_ClipDistance most definitely can be read in fragment shaders since
GLSL 1.30. This is also accessible in ES with EXT_clip_cull_distance.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu >
Reviewed-by: Emma Anholt <emma@anholt.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13917 >
2021-11-28 04:44:56 +00:00
e54264c84f
nir: add shader_info::source_sha1, its initialization and printing
...
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13869 >
2021-11-26 11:58:27 +00:00
34510ce3cc
nir/lower_subgroups: fix left shift of -1
...
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com >
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com >
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/5365
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12901 >
2021-11-24 16:45:05 +00:00
811a7a2d31
nir/lower_tex: don't calculate texture_mask for texture_index>=32
...
With Vulkan, texture_index can be 32 or larger, which creates a shift
exponent larger than 31 (undefined behaviour). Since we don't use
texture_mask with Vulkan, just initialize it to 0.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com >
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com >
Gitlab: https://gitlab.freedesktop.org/mesa/mesa/-/issues/5365
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12901 >
2021-11-24 16:45:04 +00:00
b425100781
spirv: run nir_copy_prop before nir_rematerialize_derefs_in_use_blocks_impl
...
spirv_to_nir sometimes wraps derefs in vec2 or mov instructions as part of
its texture handling. These get in the way of
nir_rematerialize_derefs_in_use_blocks_impl. Running copy propagation
should get rid of the extra move instructions and get us back to intact
deref chains for everything except variable pointer use-cases.
fossil-db (Sienna Cichlid):
Totals from 6 (0.00% of 134572) affected shaders:
CodeSize: 92656 -> 93088 (+0.47%)
Instrs: 17060 -> 17138 (+0.46%)
Latency: 224408 -> 227539 (+1.40%)
InvThroughput: 37402 -> 37924 (+1.40%)
VClause: 408 -> 402 (-1.47%)
Copies: 1065 -> 1107 (+3.94%)
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com >
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net >
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/5668
Fixes: 14a12b771dhttps://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13924 >
2021-11-24 15:43:51 +00:00
99388f0c27
freedreno/ir3: handle global atomics
...
Only for a6xx since we don't know the instructions for global
atomics on previous gens. Per Qualcomm's docs in OpenCL atomics
are only supported since a5xx together with Generic memory space.
Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8717 >
2021-11-23 18:26:37 +00:00
7603187aec
nir: Un-inline more of nir_builder.h.
...
Cuts another 470KB of libnir.a in my release build.
Reviewed-by: Matt Turner <mattst88@gmail.com >
Acked-by: Jason Ekstrand <jason@jlekstrand.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13889 >
2021-11-22 20:40:47 +00:00
d9bfcf5f5b
nir: Un-inline nir_builder_alu_instr_finish_and_insert()
...
This function is big and I don't think it will won't get meaningfully
constant-propagated during inlining without LTO. Move it to a .c file so
we just have one copy, saving 2.8MB from libnir.a on an amd64 release
build.
text data bss total filename
before:
18953406 7768312 687260 27408978 build-release/driver-symlinks/iris_dri.so
9734366 5542453 481692 15758511 build-release/lib/libvulkan_intel.so
28687772 13310765 1168952 43167489 (TOTALS)
after:
15478350 7767864 687260 23933474 build-release/driver-symlinks/iris_dri.so
6810366 5541685 481692 12833743 build-release/lib/libvulkan_intel.so
22288716 13309549 1168952 36767217 (TOTALS)
No statistically significant performance difference on iris shader-db, n=8.
Reviewed-by: Matt Turner <mattst88@gmail.com >
Acked-by: Jason Ekstrand <jason@jlekstrand.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13889 >
2021-11-22 20:40:47 +00:00
3b5b4b5d45
nir: apply interpolated input intrinsics setting when lowering clipdist
...
For drivers that use this in fragment shaders, load_input is going to
produce incorrect results (flat-shaded values).
Fixes clipping tests on a4xx.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu >
Reviewed-by: Connor Abbott <cwabbott0@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13900 >
2021-11-22 20:11:19 +00:00
df934873e1
nir: always keep the clip distance array size updated
...
Drivers expect to know the number of clip distances irrespective of
whether compact arrays are used or not.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu >
Reviewed-by: Connor Abbott <cwabbott0@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13900 >
2021-11-22 20:11:19 +00:00
508f917d8c
util/dag: Make edge data a uintptr_t
...
Nobody was actually using it as a pointer, and I'm going to introduce a
shared function which relies on it not being a pointer so let's fix this
once and for all.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13722 >
2021-11-17 13:41:47 +00:00
011ea32585
nir: fix constant expression of ibitfield_extract
...
This fixes dEQP-VK.graphicsfuzz.cov-condition-bitfield-extract-integer.
For example, nir_ibitfield_extract(3, 1, 2) should return 1.
Cc: 21.3 mesa-stable
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/13791 >
2021-11-16 17:32:21 +00:00
59860d4873
nir: Group per-primitive outputs at the end for driver location assign.
...
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com >
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com >
Acked-by: Caio Oliveira <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13466 >
2021-11-16 07:46:55 +00:00
f23f7ef316
nir: Don't compact per-vertex and per-primitive outputs together.
...
Prevent nir_compact_varyings from putting per-vertex and per-primitive
output components in the same slot.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com >
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13466 >
2021-11-16 07:46:55 +00:00
e1e461d11c
nir: Lower cull and clip distance arrays for mesh shaders.
...
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com >
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13466 >
2021-11-16 07:46:55 +00:00
6a502a0a2c
nir: Add new option to lower invocation ID from invocation index.
...
Add this as an option to nir_lower_compute_system_values_options
instead of just relying on the shader's options.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com >
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13466 >
2021-11-16 07:46:55 +00:00
7562e34463
nir, spirv: Don't mark NV_mesh_shader primitive indices as per-primitive.
...
They are not per-primitive in NV_mesh_shader, but a flat array.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com >
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13466 >
2021-11-16 07:46:55 +00:00
d79d9a7a06
nir: Fix nir_lower_io with per primitive outputs.
...
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com >
Acked-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13466 >
2021-11-16 07:46:55 +00:00
9cf4124be0
nir: Print Mesh Shader specific info.
...
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com >
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13466 >
2021-11-16 07:46:55 +00:00
5aa39253cb
nir: Rename nir_get_io_vertex_index_src and include per-primitive I/O.
...
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com >
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13466 >
2021-11-16 07:46:55 +00:00
185826a400
nir: remove double-validation of src component counts
...
The nir_tex_instr_src_size helper already sorts this out correctly, no
need to do it twice, and validate_src takes care of it.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu >
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13781 >
2021-11-16 01:23:41 +00:00
1e4c6e059e
nir/fold_16bit_sampler_conversions: skip sparse residency tex instructions
...
The residency return value mismatches between NIR and Radeon.
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/13592 >
2021-11-15 18:28:20 +00:00
719b48f85d
nir/lower_system_values: replace local_invocation_id components with zero
...
fossil-db (Sienna Cichlid):
Totals from 360 (0.28% of 128647) affected shaders:
VGPRs: 7912 -> 7272 (-8.09%); split: -8.59%, +0.51%
CodeSize: 542456 -> 544688 (+0.41%); split: -0.32%, +0.73%
MaxWaves: 10866 -> 10952 (+0.79%)
Instrs: 95973 -> 96010 (+0.04%); split: -0.34%, +0.38%
Latency: 4366023 -> 4344664 (-0.49%); split: -0.90%, +0.41%
InvThroughput: 19656659 -> 18297185 (-6.92%); split: -6.92%, +0.00%
VClause: 3242 -> 3116 (-3.89%); split: -4.04%, +0.15%
SClause: 3422 -> 3504 (+2.40%); split: -0.20%, +2.60%
Copies: 8854 -> 9376 (+5.90%); split: -0.89%, +6.79%
Branches: 2329 -> 2326 (-0.13%); split: -0.39%, +0.26%
PreSGPRs: 7620 -> 7841 (+2.90%); split: -0.43%, +3.33%
PreVGPRs: 5765 -> 5504 (-4.53%)
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com >
Reviewed-by: Daniel-schuermann <daniel@schuermann.dev >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13757 >
2021-11-12 18:59:51 +00:00
e257344a82
nir/lower_pntc_ytransform: Support PointCoordIsSysval
...
Pattern match the point coord sysval and support lowering it as well.
This is required to handle flipped framebuffers on Bifrost. However,
what this pass normalizes to is the opposite of the hardware mode we
used on Bifrost before, so we need to swap modes at the same time to
prevent regressions.
Fixes Piglit glsl-fs-pointcoord and glsl-fs-pointcoord_gles2
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com >
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net >
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13073 >
2021-11-12 12:34:14 +00:00
33b4eb149e
nir: add new SSA instruction scheduler grouping loads into indirection groups
...
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com >
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13604 >
2021-11-08 21:20:11 +00:00
Emma Anholt