From: Marek Olšák Date: Sat, 4 Jul 2020 02:09:44 +0000 (-0400) Subject: radeonsi: call nir_split_array_vars/shrink_vec_array_vars/opt_find_array_copies X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=283ad85944b5d9082f0ede7ab41fb353db53fee8;p=mesa.git radeonsi: call nir_split_array_vars/shrink_vec_array_vars/opt_find_array_copies Loosely based on RADV and https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5668 54793 shaders in 33659 tests Totals: SGPRS: 2739498 -> 2739474 (-0.00 %) VGPRS: 1534120 -> 1534256 (0.01 %) Spilled SGPRs: 2579 -> 2579 (0.00 %) Spilled VGPRs: 29 -> 29 (0.00 %) Private memory VGPRs: 2176 -> 256 (-88.24 %) Scratch size: 2220 -> 288 (-87.03 %) dwords per thread Code Size: 55572924 -> 55584592 (0.02 %) bytes LDS: 92 -> 92 (0.00 %) blocks Max Waves: 966044 -> 966021 (-0.00 %) Wait states: 0 -> 0 (0.00 %) Totals from affected shaders: SGPRS: 7272 -> 7248 (-0.33 %) VGPRS: 4848 -> 4984 (2.81 %) Spilled SGPRs: 0 -> 0 (0.00 %) Spilled VGPRs: 0 -> 0 (0.00 %) Private memory VGPRs: 2176 -> 256 (-88.24 %) Scratch size: 2188 -> 256 (-88.30 %) dwords per thread Code Size: 336332 -> 348000 (3.47 %) bytes LDS: 18 -> 18 (0.00 %) blocks Max Waves: 2659 -> 2636 (-0.86 %) Wait states: 0 -> 0 (0.00 %) | PERCENTAGE DELTAS | Shaders | SGPRs | VGPRs |SpillSGPR |SpillVGPR | PrivVGPR | Scratch | CodeSize | MaxWaves | Waits | |------------------------|----------|----------|----------|----------|----------|----------|----------|----------|----------|----------| | 0ad | 6| . | . | . | . | . | . | . | . | . | | alien_isolation | 2936| . | . | . | . | . | . | . | . | . | | anholt | 10| . | . | . | . | . | . | . | . | . | | antichamber | 180| . | . | . | . | . | . | . | . | . | | batman_arkham_origins | 589| . | . | . | . | . | . | . | . | . | | bioshock-infinite | 1769| . | . | . | . | . | . | . | . | . | | borderlands2 | 3968| . | . | . | . | . | . | . | . | . | | borderlands_presequel | 1326| . | . | . | . | . | . | . | . | . | | brutal-legend | 338| . | . | . | . | . | . | . | . | . | | chromeos | 86| . | . | . | . | . | . | . | . | . | | chromium | 2| . | . | . | . | . | . | . | . | . | | civilization_beyond.. | 116| . | . | . | . | . | . | . | . | . | | company_of_heroes2 | 240| . | . | . | . | . | . | . | . | . | | counter_strike_glob.. | 1142| . | . | . | . | . | . | . | . | . | | deadcore | 76| . | . | . | . | . | . | . | . | . | | deus_ex_mankind_div.. | 1410| . | . | . | . | . | . | . | . | . | | dirt-showdown | 533| . | . | . | . | . | . | . | . | . | | dirt_rally | 364| . | . | . | . | . | . | . | . | . | | divinity | 1052| . | . | . | . | . | . | . | . | . | | dolphin | 22| . | . | . | . | . | . | . | . | . | | dota2 | 1747| . | . | . | . | . | . | . | . | . | | europa_universalis_4 | 76| . | . | . | . | . | . | . | . | . | | f1-2015 | 775| 0.02 %| 0.12 %| . | . | -100.00 %| -100.00 %| 0.19 %| -0.04 %| . | | furmark-0.7.0 | 4| . | . | . | . | . | . | . | . | . | | gimark-0.7.0 | 10| . | . | . | . | . | . | . | . | . | | glamor | 16| . | . | . | . | . | . | . | . | . | | glmark | 96| . | . | . | . | . | . | . | . | . | | grid_autosport | 1767| -0.03 %| 0.17 %| . | . | -85.52 %| -84.44 %| 0.40 %| -0.03 %| . | | hitman | 1413| . | . | . | . | . | . | . | . | . | | humus-celshading | 4| . | . | . | . | . | . | . | . | . | | humus-domino | 6| . | . | . | . | . | . | . | . | . | | humus-dynamicbranching | 24| . | . | . | . | . | . | . | . | . | | humus-hdr | 10| . | . | . | . | . | . | . | . | . | | humus-portals | 2| . | . | . | . | . | . | . | . | . | | humus-volumetricfog.. | 6| . | . | . | . | . | . | . | . | . | | left_4_dead_2 | 1762| . | . | . | . | . | . | . | . | . | | legend_of_grimrock | 100| . | . | . | . | . | . | . | . | . | | life_is_strange | 1296| . | . | . | . | . | . | . | . | . | | mad_max | 358| . | . | . | . | . | . | . | . | . | | many-spheres | 6| . | . | . | . | . | . | . | . | . | | metro_2033_redux | 2670| . | 0.02 %| . | . | . | . | . | -0.02 %| . | | nexuiz | 80| . | . | . | . | . | . | . | . | . | | payday2 | 1362| . | . | . | . | . | . | . | . | . | | pixmark-julia-fp32 | 2| . | . | . | . | . | . | . | . | . | | pixmark-julia-fp64 | 2| . | . | . | . | . | . | . | . | . | | pixmark-piano-0.7.0 | 2| . | . | . | . | . | . | . | . | . | | pixmark-volplosion-.. | 2| . | . | . | . | . | . | . | . | . | | plot3d-0.7.0 | 8| . | . | . | . | . | . | . | . | . | | portal | 474| . | . | . | . | . | . | . | . | . | | reflections_subway | 98| . | . | . | . | . | . | 0.02 %| . | . | | rocket_league | 494| . | . | . | . | . | . | . | . | . | | saints_row_iv | 1704| . | . | . | . | . | . | . | . | . | | saints_row_the_third | 671| . | . | . | . | . | . | . | . | . | | sauerbraten | 7| . | . | . | . | . | . | . | . | . | | scifi_hallway | 98| . | . | . | . | . | . | . | . | . | | serious_sam_3_bfe | 392| . | . | . | . | . | . | . | . | . | | shadow_of_mordor | 1410| . | . | . | . | . | . | . | . | . | | shadow_warrior | 3956| . | . | . | . | . | . | . | . | . | | skia | 6094| . | . | . | . | . | . | . | . | . | | sun_temple | 109| . | . | . | . | . | . | 0.01 %| . | . | | supertuxkart | 4| . | . | . | . | . | . | . | . | . | | talos_principle | 324| . | . | . | . | . | . | . | . | . | | team_fortress_2 | 808| . | . | . | . | . | . | . | . | . | | tesseract | 430| . | . | . | . | . | . | . | . | . | | tessmark-0.7.0 | 6| . | . | . | . | . | . | . | . | . | | thea | 172| . | . | . | . | . | . | . | . | . | | tomb_raider | 1448| -0.02 %| . | . | . | . | . | . | . | . | | total_war_warhammer | 242| . | . | . | . | . | . | . | . | . | | ubershaders | 54| . | . | . | . | . | . | . | . | . | | ue4_effects_cave | 290| . | . | . | . | . | . | 0.02 %| . | . | | ue4_elemental | 561| . | . | . | . | . | . | 0.02 %| . | . | | ue4_lightroom_inter.. | 64| . | . | . | . | . | . | . | . | . | | ue4_realistic_rende.. | 86| . | . | . | . | . | . | . | . | . | | unigine_heaven | 322| . | . | . | . | . | . | . | . | . | | unigine_sanctuary | 264| . | . | . | . | . | . | . | . | . | | unigine_tropics | 210| . | . | . | . | . | . | . | . | . | | unigine_valley | 278| . | . | . | . | . | . | . | . | . | | unity | 72| . | . | . | . | . | . | . | . | . | | victor_vran | 1262| . | . | . | . | . | . | . | . | . | | warsow | 176| . | . | . | . | . | . | . | . | . | | warzone2100 | 4| . | . | . | . | . | . | . | . | . | | wasteland2 | 76| . | . | . | . | . | . | . | . | . | | wavelet-volume | 4| . | . | . | . | . | . | . | . | . | | witcher2 | 1040| . | . | . | . | . | . | . | . | . | | xcom_enemy_within | 1236| . | . | . | . | . | . | . | . | . | | yofrankie | 82| . | . | . | . | . | . | . | . | . | |------------------------|----------|----------|----------|----------|----------|----------|----------|----------|----------|----------| | All affected | 157| -0.33 %| 2.81 %| . | . | -88.24 %| -88.30 %| 3.47 %| -0.86 %| . | |------------------------|----------|----------|----------|----------|----------|----------|----------|----------|----------|----------| | Total | 54793| . | . | . | . | -88.24 %| -87.03 %| 0.02 %| . | . | Acked-by: Pierre-Eric Pelloux-Prayer Part-of: --- diff --git a/src/gallium/drivers/radeonsi/si_shader_nir.c b/src/gallium/drivers/radeonsi/si_shader_nir.c index ad9ebd65341..19c9332408a 100644 --- a/src/gallium/drivers/radeonsi/si_shader_nir.c +++ b/src/gallium/drivers/radeonsi/si_shader_nir.c @@ -739,7 +739,7 @@ void si_nir_scan_shader(const struct nir_shader *nir, struct si_shader_info *inf } } -static void si_nir_opts(struct nir_shader *nir) +static void si_nir_opts(struct nir_shader *nir, bool first) { bool progress; @@ -752,7 +752,24 @@ static void si_nir_opts(struct nir_shader *nir) bool lower_alu_to_scalar = false; bool lower_phis_to_scalar = false; - NIR_PASS(progress, nir, nir_opt_copy_prop_vars); + if (first) { + bool opt_find_array_copies = false; + + NIR_PASS(progress, nir, nir_split_array_vars, nir_var_function_temp); + NIR_PASS(lower_alu_to_scalar, nir, nir_shrink_vec_array_vars, nir_var_function_temp); + NIR_PASS(opt_find_array_copies, nir, nir_opt_find_array_copies); + NIR_PASS(progress, nir, nir_opt_copy_prop_vars); + + /* Call nir_lower_var_copies() to remove any copies introduced + * by nir_opt_find_array_copies(). + */ + if (opt_find_array_copies) + NIR_PASS(progress, nir, nir_lower_var_copies); + progress |= opt_find_array_copies; + } else { + NIR_PASS(progress, nir, nir_opt_copy_prop_vars); + } + NIR_PASS(progress, nir, nir_opt_dead_write_vars); NIR_PASS(lower_alu_to_scalar, nir, nir_opt_trivial_continues); @@ -920,7 +937,7 @@ static void si_lower_nir(struct si_screen *sscreen, struct nir_shader *nir) NIR_PASS_V(nir, nir_lower_var_copies); NIR_PASS_V(nir, nir_lower_pack); NIR_PASS_V(nir, nir_opt_access); - si_nir_opts(nir); + si_nir_opts(nir, true); /* Lower large variables that are always constant with load_constant * intrinsics, which get turned into PC-relative loads from a data @@ -935,7 +952,7 @@ static void si_lower_nir(struct si_screen *sscreen, struct nir_shader *nir) changed |= ac_lower_indirect_derefs(nir, sscreen->info.chip_class); if (changed) - si_nir_opts(nir); + si_nir_opts(nir, false); NIR_PASS_V(nir, nir_lower_bool_to_int32); NIR_PASS_V(nir, nir_remove_dead_variables, nir_var_function_temp, NULL);