mesa/src/intel/compiler/meson.build
Ian Romanick 119801e647 intel/brw: Move fsat instructions closer to the source
Intel GPUs have a saturate destination modifier, and
brw_fs_opt_saturate_propagation tries to replace explicit saturate
operations with this destination modifier. That pass is limited in
several ways. If the source of the explicit saturate is in a different
block or if the source of the explicit saturate is live after the
explicit saturate, brw_fs_opt_saturate_propagation will be unable to
make progress.

This optimization exists to help brw_fs_opt_saturate_propagation make
more progress. It tries to move NIR fsat instructions to the same block
that contains the definition of its source. It does this only in cases
where it will not create additional live values. It also attempts to do
this only in cases where the explicit saturate will ultimiately be
converted to a destination modifier.

v2: Fix metadata_preserve when theres no progress and use
nir_metadata_control_flow when there is progress. All suggested by
Alyssa.

v3: Fix a typo in the file header comment. Noticed by Ken.  Don't
require nir_metadata_instr_index. Use nir_def_rewrite_uses_after instead
of open-coding something slightly more specific. Both suggested by Ken.

shader-db:

All Intel platforms had similar results. (Meteor Lake shown)
total instructions in shared programs: 19733645 -> 19733028 (<.01%)
instructions in affected programs: 193300 -> 192683 (-0.32%)
helped: 246
HURT: 1
helped stats (abs) min: 2 max: 48 x̄: 2.51 x̃: 2
helped stats (rel) min: 0.18% max: 0.39% x̄: 0.33% x̃: 0.34%
HURT stats (abs)   min: 1 max: 1 x̄: 1.00 x̃: 1
HURT stats (rel)   min: 0.31% max: 0.31% x̄: 0.31% x̃: 0.31%
95% mean confidence interval for instructions value: -2.87 -2.13
95% mean confidence interval for instructions %-change: -0.34% -0.32%
Instructions are helped.

total cycles in shared programs: 916180971 -> 916264656 (<.01%)
cycles in affected programs: 30197180 -> 30280865 (0.28%)
helped: 194
HURT: 142
helped stats (abs) min: 1 max: 21251 x̄: 872.75 x̃: 19
helped stats (rel) min: <.01% max: 23.17% x̄: 2.59% x̃: 0.23%
HURT stats (abs)   min: 1 max: 28058 x̄: 1781.68 x̃: 399
HURT stats (rel)   min: <.01% max: 37.21% x̄: 4.85% x̃: 1.63%
95% mean confidence interval for cycles value: -196.84 694.97
95% mean confidence interval for cycles %-change: -0.17% 1.27%
Inconclusive result (value mean confidence interval includes 0).

fossil-db:

Meteor Lake, DG2, and Tiger Lake had similar results. (Meteor Lake shown)
Totals:
Instrs: 151512021 -> 151511351 (-0.00%); split: -0.00%, +0.00%
Cycle count: 17209013596 -> 17209840995 (+0.00%); split: -0.02%, +0.02%
Max live registers: 32013312 -> 32013549 (+0.00%)
Max dispatch width: 5512304 -> 5512136 (-0.00%)

Totals from 774 (0.12% of 630172) affected shaders:
Instrs: 1559285 -> 1558615 (-0.04%); split: -0.05%, +0.01%
Cycle count: 1312656268 -> 1313483667 (+0.06%); split: -0.24%, +0.30%
Max live registers: 82195 -> 82432 (+0.29%)
Max dispatch width: 6664 -> 6496 (-2.52%)

Ice Lake
Totals:
Instrs: 151416791 -> 151416137 (-0.00%); split: -0.00%, +0.00%
Cycle count: 15162468885 -> 15163298824 (+0.01%); split: -0.00%, +0.01%
Max live registers: 32471367 -> 32471603 (+0.00%)
Max dispatch width: 5623752 -> 5623712 (-0.00%)

Totals from 733 (0.12% of 635598) affected shaders:
Instrs: 877965 -> 877311 (-0.07%); split: -0.09%, +0.01%
Cycle count: 190763628 -> 191593567 (+0.44%); split: -0.21%, +0.64%
Max live registers: 72067 -> 72303 (+0.33%)
Max dispatch width: 6216 -> 6176 (-0.64%)

Skylake
Totals:
Instrs: 140794845 -> 140794075 (-0.00%); split: -0.00%, +0.00%
Cycle count: 14665159301 -> 14665320514 (+0.00%); split: -0.00%, +0.01%
Max live registers: 31783341 -> 31783662 (+0.00%); split: -0.00%, +0.00%

Totals from 659 (0.11% of 625670) affected shaders:
Instrs: 829061 -> 828291 (-0.09%); split: -0.09%, +0.00%
Cycle count: 185478478 -> 185639691 (+0.09%); split: -0.33%, +0.41%
Max live registers: 67491 -> 67812 (+0.48%); split: -0.01%, +0.48%

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29774>
2024-08-09 14:26:10 -07:00

317 lines
8.3 KiB
Meson

# Copyright © 2017 Intel Corporation
# SPDX-License-Identifier: MIT
intel_nir_files = files(
'intel_nir.h',
'intel_nir.c',
'intel_nir_blockify_uniform_loads.c',
'intel_nir_clamp_image_1d_2d_array_sizes.c',
'intel_nir_clamp_per_vertex_loads.c',
'intel_nir_lower_conversions.c',
'intel_nir_lower_non_uniform_barycentric_at_sample.c',
'intel_nir_lower_non_uniform_resource_intel.c',
'intel_nir_lower_printf.c',
'intel_nir_lower_shading_rate_output.c',
'intel_nir_lower_sparse.c',
'intel_nir_lower_texture.c',
'intel_nir_opt_peephole_ffma.c',
'intel_nir_opt_peephole_imul32x16.c',
'intel_nir_tcs_workarounds.c',
)
libintel_compiler_brw_files = files(
'brw_cfg.cpp',
'brw_cfg.h',
'brw_compile_bs.cpp',
'brw_compile_cs.cpp',
'brw_compile_fs.cpp',
'brw_compile_gs.cpp',
'brw_compile_mesh.cpp',
'brw_compile_tcs.cpp',
'brw_compile_tes.cpp',
'brw_compile_vs.cpp',
'brw_compiler.c',
'brw_compiler.h',
'brw_debug_recompile.c',
'brw_def_analysis.cpp',
'brw_disasm.c',
'brw_disasm_info.cpp',
'brw_disasm_info.h',
'brw_eu.c',
'brw_eu_compact.c',
'brw_eu_defines.h',
'brw_eu_emit.c',
'brw_eu.h',
'brw_eu_validate.c',
'brw_fs_bank_conflicts.cpp',
'brw_fs_builder.h',
'brw_fs_cmod_propagation.cpp',
'brw_fs_combine_constants.cpp',
'brw_fs_copy_propagation.cpp',
'brw_fs.cpp',
'brw_fs_cse.cpp',
'brw_fs_dead_code_eliminate.cpp',
'brw_fs_generator.cpp',
'brw_fs.h',
'brw_fs_live_variables.cpp',
'brw_fs_live_variables.h',
'brw_fs_lower.cpp',
'brw_fs_lower_dpas.cpp',
'brw_fs_lower_integer_multiplication.cpp',
'brw_fs_lower_pack.cpp',
'brw_fs_lower_regioning.cpp',
'brw_fs_lower_simd_width.cpp',
'brw_fs_nir.cpp',
'brw_fs_opt.cpp',
'brw_fs_opt_algebraic.cpp',
'brw_fs_opt_virtual_grfs.cpp',
'brw_fs_reg_allocate.cpp',
'brw_fs_register_coalesce.cpp',
'brw_fs_saturate_propagation.cpp',
'brw_fs_scoreboard.cpp',
'brw_fs_thread_payload.cpp',
'brw_fs_validate.cpp',
'brw_fs_visitor.cpp',
'brw_fs_workaround.cpp',
'brw_inst.h',
'brw_ir.h',
'brw_ir_allocator.h',
'brw_ir_analysis.h',
'brw_ir_fs.h',
'brw_ir_performance.h',
'brw_ir_performance.cpp',
'brw_isa_info.h',
'brw_lower_logical_sends.cpp',
'brw_nir.h',
'brw_nir.c',
'brw_nir_analyze_ubo_ranges.c',
'brw_nir_lower_cooperative_matrix.c',
'brw_nir_lower_cs_intrinsics.c',
'brw_nir_lower_alpha_to_coverage.c',
'brw_nir_lower_intersection_shader.c',
'brw_nir_lower_ray_queries.c',
'brw_nir_lower_rt_intrinsics.c',
'brw_nir_lower_shader_calls.c',
'brw_nir_lower_storage_image.c',
'brw_nir_opt_fsat.c',
'brw_nir_rt.h',
'brw_nir_rt.c',
'brw_nir_rt_builder.h',
'brw_packed_float.c',
'brw_print.cpp',
'brw_prim.h',
'brw_private.h',
'brw_reg.h',
'brw_reg_type.c',
'brw_reg_type.h',
'brw_rt.h',
'brw_schedule_instructions.cpp',
'brw_shader.cpp',
'brw_simd_selection.cpp',
'brw_vue_map.c',
)
brw_device_sha1_gen_src = custom_target('brw_device_sha1_gen.c',
input : ['brw_device_sha1_gen_c.py', '../dev/intel_device_info.py'],
output : ['brw_device_sha1_gen.c'],
command : [prog_python, '@INPUT0@', '--outdir', meson.current_build_dir()])
brw_nir_lower_fsign = custom_target(
'brw_nir_lower_fsign.c',
input : 'brw_nir_lower_fsign.py',
output : 'brw_nir_lower_fsign.c',
command : [
prog_python, '@INPUT@', '-p', dir_compiler_nir,
],
depend_files : nir_algebraic_depends,
capture : true,
)
brw_nir_trig = custom_target(
'brw_nir_trig_workarounds.c',
input : 'brw_nir_trig_workarounds.py',
output : 'brw_nir_trig_workarounds.c',
command : [
prog_python, '@INPUT@', '-p', dir_compiler_nir,
],
depend_files : nir_algebraic_depends,
capture : true,
)
libintel_compiler_brw = static_library(
'intel_compiler',
[libintel_compiler_brw_files, intel_nir_files, brw_nir_lower_fsign, brw_nir_trig, ir_expression_operation_h, [brw_device_sha1_gen_src]],
include_directories : [inc_include, inc_src, inc_intel],
c_args : [no_override_init_args],
gnu_symbol_visibility : 'hidden',
dependencies : [idep_nir_headers, idep_mesautil, idep_intel_dev],
build_by_default : false,
)
idep_intel_compiler_brw = declare_dependency(
link_with : [libintel_compiler_brw],
dependencies : [
idep_nir,
idep_mesautil,
],
)
# For now this tool is only going to be used by Anv
if get_option('intel-clc') == 'system'
prog_intel_clc = find_program('intel_clc', native : true)
dep_prog_intel_clc = []
elif with_intel_clc
prog_intel_clc = executable(
'intel_clc',
[
'intel_clc.c',
'brw_kernel.c',
# Use just the nir_options part of ELK instead of fully linking.
'elk/elk_nir_options.h',
'elk/elk_nir_options.c',
],
link_with : [libisl],
include_directories : [inc_include, inc_src, inc_intel],
c_args : [pre_args, no_override_init_args],
link_args : [ld_args_build_id],
dependencies : [idep_nir, idep_vtn, idep_mesaclc, idep_mesautil, idep_intel_dev,
idep_intel_compiler_brw],
# If we can run host binaries directly, just build intel_clc for the host.
# Most commonly this happens when doing a cross compile from an x86_64 build
# machine to an x86 host
native : not meson.can_run_host_binaries(),
install : get_option('install-intel-clc'),
)
dep_prog_intel_clc = [prog_intel_clc]
endif
if with_tests
test(
'intel_compiler_brw_tests',
executable(
'intel_compiler_brw_tests',
files(
'test_eu_compact.cpp',
'test_eu_validate.cpp',
'test_fs_cmod_propagation.cpp',
'test_fs_combine_constants.cpp',
'test_fs_copy_propagation.cpp',
'test_fs_cse.cpp',
'test_fs_saturate_propagation.cpp',
'test_fs_scoreboard.cpp',
'test_simd_selection.cpp',
'test_vf_float_conversions.cpp',
),
ir_expression_operation_h,
include_directories : [inc_include, inc_src, inc_intel],
link_with : libisl,
dependencies : [idep_gtest, idep_nir, idep_mesautil, idep_intel_dev,
idep_intel_compiler_brw],
),
suite : ['intel'],
protocol : 'gtest',
)
endif
if with_intel_tools
bison_command = []
if yacc_is_bison
bison_command = [
prog_bison, '@INPUT@', '--defines=@OUTPUT1@',
'--output=@OUTPUT0@'
]
else
bison_command = [
prog_bison, '-H', '@OUTPUT1@',
'-o', '@OUTPUT0@', '@INPUT@'
]
endif
brw_gram_tab = custom_target(
'brw_gram.tab.[ch]',
input : 'brw_gram.y',
output : ['brw_gram.tab.c', 'brw_gram.tab.h'],
command : bison_command
)
brw_lex_yy_c = custom_target(
'brw_lex.yy.c',
input : 'brw_lex.l',
output : 'brw_lex.yy.c',
command : [prog_flex, '-o', '@OUTPUT@', '@INPUT@']
)
brw_asm_deps = [
dep_thread,
idep_intel_compiler_brw,
idep_intel_dev,
idep_mesautil,
]
brw_asm = static_library(
'brw_asm',
['brw_asm.c', brw_gram_tab[0], brw_gram_tab[1], brw_lex_yy_c],
dependencies : brw_asm_deps,
include_directories : [inc_include, inc_src, inc_intel],
c_args : [no_override_init_args],
gnu_symbol_visibility : 'hidden',
build_by_default : false,
)
idep_brw_asm = declare_dependency(
link_with : brw_asm,
dependencies : brw_asm_deps,
)
brw_asm_tool = executable(
'brw_asm',
['brw_asm_tool.c'],
dependencies : idep_brw_asm,
include_directories : [inc_include, inc_src, inc_intel],
c_args : [no_override_init_args],
gnu_symbol_visibility : 'hidden',
install : true
)
asm_testcases = [
['skl', 'gfx9'],
['icl', 'gfx11'],
['tgl', 'gfx12'],
['dg2', 'gfx12.5'],
]
test_runner = find_program('tests/run-test.py')
foreach testcase : asm_testcases
_gen_name = testcase[0]
_gen_num = testcase[1]
_gen_folder = join_paths(meson.current_source_dir(), 'tests',
_gen_num.replace('gfx', 'gen'))
test(
'brw_asm_' + _gen_num, test_runner,
args : [
'--brw_asm', brw_asm_tool,
'--gen_name', _gen_name,
'--gen_folder', _gen_folder,
],
suite : 'intel',
)
endforeach
brw_disasm_tool = executable(
'brw_disasm',
files('brw_disasm_tool.c'),
dependencies : [idep_mesautil, dep_thread, idep_intel_dev,
idep_intel_compiler_brw],
include_directories : [inc_include, inc_src, inc_intel],
c_args : [no_override_init_args],
gnu_symbol_visibility : 'hidden',
install : true
)
endif
subdir('elk')