Commit graph

308 commits

Author SHA1 Message Date
Rhys Perry
d2d94b62f2 aco: initialize scratch base registers on GFX9-GFX10.3
fossil-db (navi21):
Totals from 1142 (0.70% of 162293) affected shaders:
Instrs: 271636 -> 271974 (+0.12%)
CodeSize: 1532020 -> 1533792 (+0.12%)
Latency: 7484066 -> 7485698 (+0.02%)
InvThroughput: 4048824 -> 4049579 (+0.02%)
SClause: 4171 -> 4212 (+0.98%)
PreSGPRs: 11203 -> 12276 (+9.58%)

fossil-db (vega10):
Totals from 3327 (2.06% of 161355) affected shaders:
Instrs: 257413 -> 257601 (+0.07%)
CodeSize: 1424244 -> 1425372 (+0.08%)
Latency: 8598402 -> 8600466 (+0.02%)
InvThroughput: 7906335 -> 7908234 (+0.02%)
SClause: 4932 -> 4973 (+0.83%)
PreSGPRs: 22010 -> 25405 (+15.42%)

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/17079>
2022-07-08 14:49:03 +00:00
Rhys Perry
cbeb25ce91 aco: make FLAT_instruction::offset signed
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/17079>
2022-07-08 14:49:03 +00:00
Georg Lehmann
efdb323ad2 aco/ir: Pad SOP2 and SOPC to the same size as SOPK.
Being able to directly cast instructions simplifies optimizations.

Signed-off-by: Georg Lehmann <dadschoorse@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15999>
2022-07-06 09:54:54 +00:00
Rhys Perry
84b404d34d aco: don't use 32-bit fp inline constants for fp16 vop3p literals
If we're applying the literal 0x3f800000 to a fp16 vop3p instruction, we
shouldn't use the 1.0 inline constant, because the hardware will use the
16-bit 1.0: 0x00003c00.

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/16296>
2022-07-05 16:39:56 +00:00
Rhys Perry
f937c5be7c aco: add and use constantValue16()
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/16296>
2022-07-05 16:39:56 +00:00
Dave Airlie
a179e1aede aco/radv: drop radv_nir_compiler_options from aco.
Add a new aco input and options structs, then convert from radv
pieces on submit.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16521>
2022-05-17 06:15:25 +00:00
Marek Olšák
39800f0fa3 amd: change chip_class naming to "enum amd_gfx_level gfx_level"
This aligns the naming with PAL.

Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Pierre-Eric Pellou-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16469>
2022-05-13 14:56:22 -04:00
Dave Airlie
c44d5d61ce aco: remove radv vs prolog key from aco internals.
This creates an aco specific key, and converts radv to it.

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16342>
2022-05-11 19:07:11 +00:00
Dave Airlie
04c07a2413 aco/radv: convert to aco shader info at the radv level.
This removes the radv shader info type from aco completely.

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16342>
2022-05-11 19:07:11 +00:00
Dave Airlie
87df607ff5 aco: move to a minimal aco shader info struct.
This should be kept to only things aco uses, and expanded when
radeonsi support is added. Things should be removed if lowered in NIR.

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16342>
2022-05-11 19:07:11 +00:00
Dave Airlie
a2701bfdb8 aco: move info pointer to a copy.
This is just setup to move this to a different struct later.

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16342>
2022-05-11 19:07:11 +00:00
Daniel Schürmann
8d8c59b4cd aco: split num_waves adjustment into separate function
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16039>
2022-04-29 15:39:10 +00:00
Daniel Schürmann
6220046ad1 aco: remove 'max_waves' and use 'num_waves' to adjust for LDS and workgroup size
Totals from 21 (0.02% of 134913) affected shaders: (GFX10.3)
VGPRs: 1024 -> 1176 (+14.84%)
CodeSize: 127824 -> 127664 (-0.13%); split: -0.17%, +0.04%
MaxWaves: 416 -> 378 (-9.13%)
Instrs: 22521 -> 22502 (-0.08%); split: -0.17%, +0.09%
Latency: 146386 -> 143154 (-2.21%); split: -2.21%, +0.00%
InvThroughput: 28379 -> 28944 (+1.99%); split: -0.23%, +2.22%
VClause: 575 -> 579 (+0.70%); split: -0.87%, +1.57%
SClause: 692 -> 645 (-6.79%)
Copies: 780 -> 747 (-4.23%); split: -4.74%, +0.51%

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16039>
2022-04-29 15:39:10 +00:00
Rhys Perry
2135c88d9c aco: fix signedness of DS_instruction::offset0/1
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13778>
2022-04-13 23:08:07 +00:00
Daniel Schürmann
d703a0e808 aco: remove register hints entirely
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15408>
2022-04-13 21:52:43 +00:00
Daniel Schürmann
007cb02db9 aco: use branch definition as scratch register for SSA lowering
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15505>
2022-03-28 07:36:46 +00:00
Daniel Schürmann
2d1e6b756e aco: remove 'high' parameter from can_use_opsel()
No fossil-db changes.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15551>
2022-03-25 22:02:50 +00:00
Rhys Perry
e12bee3cb7 aco: improve support for v_fma_mix
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/14769>
2022-03-17 19:04:17 +00:00
Timur Kristóf
cd0dd5d6b7 aco: Add storage class for Task Shader payload.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15161>
2022-02-25 13:20:08 +01:00
Daniel Schürmann
13c3137960 aco: merge block_kind_uses_[demote|discard_if]
These serve the same purpose. The new name is
block_kind_uses_discard.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14805>
2022-02-08 16:16:07 +00:00
Daniel Schürmann
08b8500dfb aco: remove block_kind_discard
This case doesn't seem to happen in practice.
No need to micro-optimize it.

This patch merges instruction selection for discard/discard_if.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14805>
2022-02-08 16:16:07 +00:00
Rhys Perry
f68797ead7 aco: create v_mac_legacy_f32/v_fmac_legacy_f32
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13436>
2022-01-20 22:54:42 +00:00
Tatsuyuki Ishi
da0412e55b aco: support DPP8
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13971>
2021-12-31 20:56:39 +00:00
Timur Kristóf
6766e6a985 aco: Add Mesh and Task shader stages.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13580>
2021-12-31 13:05:09 +00:00
Samuel Pitoiset
8ec6824335 radv,aco: decouple shader_info/options from radv_shader_args
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/13287>
2021-10-22 07:10:40 +00:00
Rhys Perry
d45958f82e aco: implement VS input loads with prologs
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/11717>
2021-10-13 05:13:10 +00:00
Rhys Perry
f4ea2d7887 aco: implement aco_compile_vs_prolog
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/11717>
2021-10-13 05:13:10 +00:00
Rhys Perry
80841196b2 radv: implement dynamic vertex input state using vertex shader prologs
This doesn't actually use the functionality or implement prolog
compilation yet.

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/11717>
2021-10-13 05:13:10 +00:00
Samuel Pitoiset
d993b59941 aco: constify radv_shader_{info,args}
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/13192>
2021-10-08 14:14:50 +02:00
Tony Wasserka
3c1802accd radv: Disable shader disassembly when no disassembler is available
ACO relies on LLVM to disassemble AMD shaders for ISAs newer than GFX7,
so disassembly needs to be skipped when LLVM is not enabled.

For vkGetPipelineExecutableInternalRepresentationsKHR and vkGetShaderInfoAMD,
the disassembly will not be reported anymore if it can't be generated.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11319>
2021-10-01 10:40:18 +02:00
Rhys Perry
e2b77e6cd4 aco: add and use RegClass::resize helper
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/12172>
2021-09-17 14:36:03 +00:00
Rhys Perry
783609a849 aco: add RegClass::is_linear_vgpr helper
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/12172>
2021-09-17 14:36:03 +00:00
Daniel Schürmann
0988f7b9ba aco: remove explicit dst_preserve flag
Instead, we can rely on the fact that subdword definitions
must preserve the unused bits while dword definitions either
pad or sign-extend.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12640>
2021-09-02 20:39:17 +02:00
Daniel Schürmann
9e3ff06c38 aco: rewrite SDWA selector
This commit introduces a new struct SubdwordSel
in order to ease and clean up the usage of SDWA
selections. This includes removing the distinction
between register-allocated and fixed SDWA selections.
Instead, SDWA selections can now also access the high
bits of subdword variables. Alignment and sizes are
validated accordingly. Size, offset and sign_extend
can be evaluated via helper methods.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12640>
2021-09-02 20:39:17 +02:00
Rhys Perry
33ddbd220f aco: remove DPP when applying constants/literals/sgprs
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12601>
2021-08-31 16:58:20 +00:00
Daniel Schürmann
077776a866 aco/opcodes: remove definition_size[]
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12364>
2021-08-23 10:31:40 +00:00
Daniel Schürmann
e11b23f7cd aco: add instr_is_16bit() helper function
to indicate whether some instruction writes partial registers, only.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12364>
2021-08-23 10:31:40 +00:00
Rhys Perry
1d894a8c85 aco: move a bunch of helpers into aco_ir.h/aco_ir.cpp
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11924>
2021-08-19 18:17:33 +00:00
Rhys Perry
3db3196379 aco: add can_use_DPP() and convert_to_DPP()
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11924>
2021-08-19 18:17:33 +00:00
Tony Wasserka
f438cbc23e aco: Remove deprecated Operand constructors
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11653>
2021-07-13 17:43:26 +00:00
Tony Wasserka
66e51dc474 aco: Remove use of deprecated Operand constructors
This migration was done with libclang-based automatic tooling, which
performed these replacements:
* Operand(uint8_t) -> Operand::c8
* Operand(uint16_t) -> Operand::c16
* Operand(uint32_t, false) -> Operand::c32
* Operand(uint32_t, bool) -> Operand::c32_or_c64
* Operand(uint64_t) -> Operand::c64
* Operand(0) -> Operand::zero(num_bytes)

Casts that were previously used for constructor selection have automatically
been removed (e.g. Operand((uint16_t)1) -> Operand::c16(1)).

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11653>
2021-07-13 17:43:26 +00:00
Tony Wasserka
db436a843c aco: Replace Operand literal constructors with factory member functions
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11653>
2021-07-13 17:43:26 +00:00
Daniel Schürmann
1e2639026f aco: Format.
Manually adjusted some comments for more intuitive line breaks.

Reviewed-by: Tony Wasserka <tony.wasserka@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11258>
2021-07-12 21:27:31 +00:00
Daniel Schürmann
59fdaa1985 aco: reorder and cleanup #includes
Reviewed-by: Tony Wasserka <tony.wasserka@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11271>
2021-07-12 12:09:31 +00:00
Rhys Perry
cf22eabc68 aco: make validate_ir() output usable in tests
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3151>
2021-06-08 08:57:43 +00:00
Rhys Perry
54292e99c7 aco: optimize 32-bit extracts and inserts using SDWA
Still need to use dst_u=preserve field to optimize packs

fossil-db (Sienna Cichlid):
Totals from 15974 (10.66% of 149839) affected shaders:
VGPRs: 1009064 -> 1008968 (-0.01%); split: -0.03%, +0.02%
SpillSGPRs: 7959 -> 7964 (+0.06%)
CodeSize: 101716436 -> 101159568 (-0.55%); split: -0.55%, +0.01%
MaxWaves: 284464 -> 284490 (+0.01%); split: +0.02%, -0.01%
Instrs: 19334216 -> 19224241 (-0.57%); split: -0.57%, +0.00%
Latency: 375465295 -> 375230478 (-0.06%); split: -0.14%, +0.08%
InvThroughput: 79006105 -> 78860705 (-0.18%); split: -0.25%, +0.07%

fossil-db (Polaris):
Totals from 11369 (7.51% of 151365) affected shaders:
SGPRs: 787920 -> 787680 (-0.03%); split: -0.04%, +0.01%
VGPRs: 681056 -> 681040 (-0.00%); split: -0.01%, +0.00%
CodeSize: 68127288 -> 67664120 (-0.68%); split: -0.69%, +0.01%
MaxWaves: 54370 -> 54371 (+0.00%)
Instrs: 13294638 -> 13214109 (-0.61%); split: -0.62%, +0.01%
Latency: 373515759 -> 373214571 (-0.08%); split: -0.11%, +0.03%
InvThroughput: 166529524 -> 166275291 (-0.15%); split: -0.20%, +0.05%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3151>
2021-06-08 08:57:43 +00:00
Timur Kristóf
0e4747d3fb aco: Introduce a new, post-RA optimizer.
This commit adds the skeleton of a new ACO post-RA optimizer,
which is intended to be a simple pass called after RA, and
is meant to do code changes which can only be done
after RA.

It is currently empty, the actual optimizations will be added
in their own commits. It only has a DCE pass, which deletes
some dead code generated by the spiller.

Fossil DB results on Sienna Cichlid:

Totals from 375 (0.25% of 149839) affected shaders:
CodeSize: 2933056 -> 2907192 (-0.88%)
Instrs: 534154 -> 530706 (-0.65%)
Latency: 12088064 -> 12084907 (-0.03%); split: -0.03%, +0.00%
InvThroughput: 4433454 -> 4432421 (-0.02%); split: -0.02%, +0.00%
Copies: 81649 -> 78203 (-4.22%)

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/7779>
2021-05-28 12:14:53 +00:00
Timur Kristóf
8d37aa91d6 aco: Add Operand(Temp, PhysReg) constructor.
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/7779>
2021-05-28 12:14:53 +00:00
Timur Kristóf
04f90db9a0 aco: Use Operand instead of Temp for the exec mask stack.
This will enable us to store non-temporary values,
such as constant operands there.

No Fossil DB changes.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tony Wasserka <tony.wasserka@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10691>
2021-05-18 11:48:22 +00:00
Rhys Perry
dfa38fa0c7 aco: group loads from the same vertex binding into the same clause
In the future, we might have vertex attribute loads from the same binding
but with different descriptors. Since they will be loading from the same
buffer, we should continue grouping them into clauses.

No fossil-db changes.

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/7871>
2021-05-10 12:09:14 +00:00