mirror of
https://gitlab.freedesktop.org/mesa/mesa.git
synced 2025-12-24 19:40:10 +01:00
5abac85177
The current scratch mechanism uses an MRF hack where we reserve a few
GRF registers to treat like the MRF and we collect the data into that
MRF region before doing a scratch write. We also use that region for
the header for scratch reads.
This commit changes things and gets rid of the MRF hack. Instead, we
reserve a single register (which RA is free to pick) for the scratch
header and uses split sends for scratch writes to avoid having to do
the copy. This should provide RA with more freedom in the presence of
spilling as well as avoid some unnecessary data moves. In future, the
new GEN9_SCRATCH_HEADER opcode gives us a place where we can do our own
per-thread scratch base address calculations rather than depending on
the scratch base address that gets pushed into g0. Having an opcode for
this lets us do it once at the top of the shader rather than repeating
it at every read/write.
One other noticeable difference is the use of SHADER_OPCODE_SEND. We
can get away with this thanks to the fact that we're now using a set to
track which instructions are generated by spills and don't rely on the
opcodes to find spill/fill instructions. This allows us to avoid adding
more virtual opcodes and let the normal code paths handle things like
scoreboard dependencies between header setup and the SEND. It also
means that post-RA scheduling may be able to space out the header setup
MOV and the SEND for better latency hiding.
Shader-db results on Skylake:
total spills in shared programs: 12137 -> 10604 (-12.63%)
spills in affected programs: 6685 -> 5152 (-22.93%)
helped: 274
HURT: 2
total fills in shared programs: 13065 -> 11515 (-11.86%)
fills in affected programs: 9007 -> 7457 (-17.21%)
helped: 275
HURT: 1
Shader-db results on Ice Lake:
total spills in shared programs: 12482 -> 10953 (-12.25%)
spills in affected programs: 6586 -> 5057 (-23.22%)
helped: 275
HURT: 0
total fills in shared programs: 12819 -> 11234 (-12.36%)
fills in affected programs: 7867 -> 6282 (-20.15%)
helped: 274
HURT: 0
Shader-db results on Tigerlake:
total spills in shared programs: 11689 -> 10233 (-12.46%)
spills in affected programs: 4740 -> 3284 (-30.72%)
helped: 259
HURT: 0
total fills in shared programs: 10840 -> 9443 (-12.89%)
fills in affected programs: 6244 -> 4847 (-22.37%)
helped: 259
HURT: 0
Fossil-db results on Ice Lake:
Spills in all programs: 245249 -> 201633 (-17.8%)
Fills in all programs: 366066 -> 314368 (-14.1%)
More practically, this seems to give about a 0.5-1% perf boost in
Witcher 3 (DXVK) and Shadow of the Tomb Raider (Vulkan native).
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7084>
|
||
|---|---|---|
| .. | ||
| 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.h | ||
| brw_eu_compact.c | ||
| brw_eu_defines.h | ||
| brw_eu_emit.c | ||
| brw_eu_util.c | ||
| brw_eu_validate.c | ||
| brw_fs.cpp | ||
| brw_fs.h | ||
| 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_cse.cpp | ||
| brw_fs_dead_code_eliminate.cpp | ||
| brw_fs_generator.cpp | ||
| 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_gen_enum.h | ||
| brw_inst.h | ||
| brw_interpolation_map.c | ||
| brw_ir.h | ||
| brw_ir_allocator.h | ||
| brw_ir_analysis.h | ||
| brw_ir_fs.h | ||
| brw_ir_performance.cpp | ||
| brw_ir_performance.h | ||
| brw_ir_vec4.h | ||
| brw_nir.c | ||
| brw_nir.h | ||
| brw_nir_analyze_boolean_resolves.c | ||
| brw_nir_analyze_ubo_ranges.c | ||
| brw_nir_attribute_workarounds.c | ||
| brw_nir_clamp_image_1d_2d_array_sizes.c | ||
| brw_nir_lower_alpha_to_coverage.c | ||
| brw_nir_lower_conversions.c | ||
| brw_nir_lower_cs_intrinsics.c | ||
| brw_nir_lower_image_load_store.c | ||
| brw_nir_lower_mem_access_bit_sizes.c | ||
| brw_nir_lower_scoped_barriers.c | ||
| brw_nir_opt_peephole_ffma.c | ||
| brw_nir_tcs_workarounds.c | ||
| brw_nir_trig_workarounds.py | ||
| 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.cpp | ||
| brw_vec4.h | ||
| brw_vec4_builder.h | ||
| brw_vec4_cmod_propagation.cpp | ||
| brw_vec4_copy_propagation.cpp | ||
| brw_vec4_cse.cpp | ||
| brw_vec4_dead_code_eliminate.cpp | ||
| brw_vec4_generator.cpp | ||
| brw_vec4_gs_nir.cpp | ||
| brw_vec4_gs_visitor.cpp | ||
| brw_vec4_gs_visitor.h | ||
| brw_vec4_live_variables.cpp | ||
| brw_vec4_live_variables.h | ||
| brw_vec4_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.h | ||
| brw_vec4_vs_visitor.cpp | ||
| brw_vue_map.c | ||
| brw_wm_iz.cpp | ||
| gen6_gs_visitor.cpp | ||
| gen6_gs_visitor.h | ||
| meson.build | ||
| test_eu_compact.cpp | ||
| test_eu_validate.cpp | ||
| test_fs_cmod_propagation.cpp | ||
| test_fs_copy_propagation.cpp | ||
| test_fs_saturate_propagation.cpp | ||
| test_fs_scoreboard.cpp | ||
| test_vec4_cmod_propagation.cpp | ||
| test_vec4_copy_propagation.cpp | ||
| test_vec4_dead_code_eliminate.cpp | ||
| test_vec4_register_coalesce.cpp | ||
| test_vf_float_conversions.cpp | ||