mesa/src/intel/compiler/meson.build

171 lines
5.1 KiB
Meson
Raw Normal View History

# Copyright © 2017 Intel Corporation
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
libintel_compiler_files = files(
'brw_cfg.cpp',
'brw_cfg.h',
'brw_clip.h',
'brw_clip_line.c',
'brw_clip_point.c',
'brw_clip_tri.c',
'brw_clip_unfilled.c',
'brw_clip_util.c',
'brw_compile_clip.c',
'brw_compile_sf.c',
'brw_compiler.c',
'brw_compiler.h',
'brw_dead_control_flow.cpp',
'brw_dead_control_flow.h',
'brw_debug_recompile.c',
'brw_disasm.c',
'brw_disasm_info.c',
'brw_disasm_info.h',
'brw_eu.cpp',
'brw_eu_compact.c',
'brw_eu_defines.h',
'brw_eu_emit.c',
'brw_eu.h',
'brw_eu_util.c',
'brw_eu_validate.c',
intel/fs: Implement GRF bank conflict mitigation pass. Unnecessary GRF bank conflicts increase the issue time of ternary instructions (the overwhelmingly most common of which is MAD) by roughly 50%, leading to reduced ALU throughput. This pass attempts to minimize the number of bank conflicts by rearranging the layout of the GRF space post-register allocation. It's in general not possible to eliminate all of them without introducing extra copies, which are typically more expensive than the bank conflict itself. In a shader-db run on SKL this helps roughly 46k shaders: total conflicts in shared programs: 1008981 -> 600461 (-40.49%) conflicts in affected programs: 816222 -> 407702 (-50.05%) helped: 46234 HURT: 72 The running time of shader-db itself on SKL seems to be increased by roughly 2.52%±1.13% with n=20 due to the additional work done by the compiler back-end. On earlier generations the pass is somewhat less effective in relative terms because the hardware incurs a bank conflict anytime the last two sources of the instruction are duplicate (e.g. while trying to square a value using MAD), which is impossible to avoid without introducing copies. E.g. for a shader-db run on SNB: total conflicts in shared programs: 944636 -> 623185 (-34.03%) conflicts in affected programs: 853258 -> 531807 (-37.67%) helped: 31052 HURT: 19 And on BDW: total conflicts in shared programs: 1418393 -> 987539 (-30.38%) conflicts in affected programs: 1179787 -> 748933 (-36.52%) helped: 47592 HURT: 70 On SKL GT4e this improves performance of GpuTest Volplosion by 3.64% ±0.33% with n=16. NOTE: This patch intentionally disregards some i965 coding conventions for the sake of reviewability. This is addressed by the next squash patch which introduces an amount of (for the most part boring) boilerplate that might distract reviewers from the non-trivial algorithmic details of the pass. The following patch is squashed in: SQUASH: intel/fs/bank_conflicts: Roll back to the nineties. Acked-by: Matt Turner <mattst88@gmail.com>
2017-06-15 15:23:57 -07:00
'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_pack.cpp',
'brw_fs_lower_regioning.cpp',
'brw_fs_nir.cpp',
'brw_fs_reg_allocate.cpp',
'brw_fs_register_coalesce.cpp',
'brw_fs_saturate_propagation.cpp',
'brw_fs_scoreboard.cpp',
'brw_fs_sel_peephole.cpp',
'brw_fs_validate.cpp',
'brw_fs_visitor.cpp',
'brw_inst.h',
'brw_interpolation_map.c',
'brw_ir.h',
'brw_ir_allocator.h',
'brw_ir_analysis.h',
'brw_ir_fs.h',
'brw_ir_vec4.h',
'brw_nir.h',
'brw_nir.c',
'brw_nir_analyze_boolean_resolves.c',
'brw_nir_analyze_ubo_ranges.c',
'brw_nir_attribute_workarounds.c',
'brw_nir_lower_conversions.c',
'brw_nir_lower_cs_intrinsics.c',
'brw_nir_lower_alpha_to_coverage.c',
'brw_nir_lower_image_load_store.c',
'brw_nir_lower_mem_access_bit_sizes.c',
'brw_nir_opt_peephole_ffma.c',
'brw_nir_tcs_workarounds.c',
'brw_nir_clamp_image_1d_2d_array_sizes.c',
'brw_packed_float.c',
'brw_predicated_break.cpp',
'brw_reg.h',
'brw_reg_type.c',
'brw_reg_type.h',
'brw_schedule_instructions.cpp',
'brw_shader.cpp',
'brw_shader.h',
'brw_vec4_builder.h',
'brw_vec4_cmod_propagation.cpp',
'brw_vec4_copy_propagation.cpp',
'brw_vec4.cpp',
'brw_vec4_cse.cpp',
'brw_vec4_dead_code_eliminate.cpp',
'brw_vec4_generator.cpp',
'brw_vec4_gs_visitor.cpp',
'brw_vec4_gs_visitor.h',
'brw_vec4.h',
'brw_vec4_live_variables.cpp',
'brw_vec4_live_variables.h',
'brw_vec4_nir.cpp',
'brw_vec4_gs_nir.cpp',
'brw_vec4_reg_allocate.cpp',
'brw_vec4_surface_builder.cpp',
'brw_vec4_surface_builder.h',
'brw_vec4_tcs.cpp',
'brw_vec4_tcs.h',
'brw_vec4_tes.cpp',
'brw_vec4_tes.h',
'brw_vec4_visitor.cpp',
'brw_vec4_vs_visitor.cpp',
'brw_vec4_vs.h',
'brw_vue_map.c',
'brw_wm_iz.cpp',
'gen6_gs_visitor.cpp',
'gen6_gs_visitor.h',
)
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', join_paths(meson.source_root(), 'src/compiler/nir/'),
],
depend_files : nir_algebraic_py,
capture : true,
)
libintel_compiler = static_library(
'intel_compiler',
[libintel_compiler_files, brw_nir_trig, ir_expression_operation_h],
include_directories : [inc_include, inc_src, inc_mapi, inc_mesa, inc_gallium, inc_intel],
c_args : [c_vis_args, no_override_init_args],
cpp_args : [cpp_vis_args],
dependencies : idep_nir_headers,
build_by_default : false,
)
if with_tests
# The last two tests are not C++ or gtest, pre comment in autotools make
foreach t : ['fs_cmod_propagation', 'fs_copy_propagation',
'fs_saturate_propagation', 'vf_float_conversions',
'vec4_register_coalesce', 'vec4_copy_propagation',
'vec4_cmod_propagation', 'vec4_dead_code_eliminate',
'eu_compact', 'eu_validate', 'fs_scoreboard']
test(
t,
executable(
[t, ir_expression_operation_h],
'test_@0@.cpp'.format(t),
include_directories : [inc_include, inc_src, inc_mapi, inc_mesa, inc_gallium, inc_intel],
link_with : [
libintel_compiler, libintel_common, libintel_dev, libisl,
],
dependencies : [idep_gtest, idep_nir, idep_mesautil],
),
suite : ['intel'],
)
endforeach
endif