mirror of
https://gitlab.freedesktop.org/mesa/mesa.git
synced 2025-12-21 20:10:14 +01:00
fabe3ead57
Funny story... a single shader was hurt for instructions, spills, fills. That same shader was also the most helped for cycles. #GPUsAreWeird No changes on any other Intel platform. v2: Refactor selection of atomic opcode to a separate function. Suggested by Jason. Haswell, Broadwell, and Skylake had similar results. (Skylake shown) total instructions in shared programs: 14304116 -> 14304261 (<.01%) instructions in affected programs: 12776 -> 12921 (1.13%) helped: 19 HURT: 1 helped stats (abs) min: 1 max: 16 x̄: 2.32 x̃: 1 helped stats (rel) min: 0.05% max: 7.27% x̄: 0.92% x̃: 0.55% HURT stats (abs) min: 189 max: 189 x̄: 189.00 x̃: 189 HURT stats (rel) min: 4.87% max: 4.87% x̄: 4.87% x̃: 4.87% 95% mean confidence interval for instructions value: -12.83 27.33 95% mean confidence interval for instructions %-change: -1.57% 0.31% Inconclusive result (value mean confidence interval includes 0). total cycles in shared programs: 527552861 -> 527531226 (<.01%) cycles in affected programs: 1459195 -> 1437560 (-1.48%) helped: 16 HURT: 2 helped stats (abs) min: 2 max: 21328 x̄: 1353.69 x̃: 6 helped stats (rel) min: 0.01% max: 5.29% x̄: 0.36% x̃: 0.03% HURT stats (abs) min: 12 max: 12 x̄: 12.00 x̃: 12 HURT stats (rel) min: 0.03% max: 0.03% x̄: 0.03% x̃: 0.03% 95% mean confidence interval for cycles value: -3699.81 1295.92 95% mean confidence interval for cycles %-change: -0.94% 0.30% Inconclusive result (value mean confidence interval includes 0). total spills in shared programs: 8025 -> 8033 (0.10%) spills in affected programs: 208 -> 216 (3.85%) helped: 1 HURT: 1 total fills in shared programs: 10989 -> 11040 (0.46%) fills in affected programs: 444 -> 495 (11.49%) helped: 1 HURT: 1 Ivy Bridge total instructions in shared programs: 11709181 -> 11709153 (<.01%) instructions in affected programs: 3505 -> 3477 (-0.80%) helped: 3 HURT: 0 helped stats (abs) min: 1 max: 23 x̄: 9.33 x̃: 4 helped stats (rel) min: 0.11% max: 1.16% x̄: 0.63% x̃: 0.61% total cycles in shared programs: 254741126 -> 254738801 (<.01%) cycles in affected programs: 919067 -> 916742 (-0.25%) helped: 3 HURT: 0 helped stats (abs) min: 21 max: 2144 x̄: 775.00 x̃: 160 helped stats (rel) min: 0.03% max: 0.90% x̄: 0.32% x̃: 0.03% total spills in shared programs: 4536 -> 4533 (-0.07%) spills in affected programs: 40 -> 37 (-7.50%) helped: 1 HURT: 0 total fills in shared programs: 4819 -> 4813 (-0.12%) fills in affected programs: 94 -> 88 (-6.38%) helped: 1 HURT: 0 Signed-off-by: Ian Romanick <ian.d.romanick@intel.com> Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com> [v1] Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> |
||
|---|---|---|
| .. | ||
| .gitignore | ||
| 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_disasm.c | ||
| brw_disasm_info.c | ||
| brw_disasm_info.h | ||
| brw_eu.c | ||
| 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_conversions.cpp | ||
| brw_fs_lower_pack.cpp | ||
| brw_fs_nir.cpp | ||
| brw_fs_reg_allocate.cpp | ||
| brw_fs_register_coalesce.cpp | ||
| brw_fs_saturate_propagation.cpp | ||
| brw_fs_sel_peephole.cpp | ||
| brw_fs_surface_builder.cpp | ||
| brw_fs_surface_builder.h | ||
| brw_fs_validate.cpp | ||
| brw_fs_visitor.cpp | ||
| brw_inst.h | ||
| brw_interpolation_map.c | ||
| brw_ir_allocator.h | ||
| brw_ir_fs.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_lower_cs_intrinsics.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_vec4_cmod_propagation.cpp | ||
| test_vec4_copy_propagation.cpp | ||
| test_vec4_register_coalesce.cpp | ||
| test_vf_float_conversions.cpp | ||