From: Marek Olšák Date: Tue, 12 Jul 2016 16:52:55 +0000 (+0200) Subject: radeonsi: set dereferenceable attribute on descriptor arrays X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=348b9a5b1c0e8a0e05ff940c1f4a10e67cdee073;p=mesa.git radeonsi: set dereferenceable attribute on descriptor arrays This allows moving the loads arbitrarily in the Sinking pass. 26002 shaders in 14643 tests Totals: SGPRS: 2080160 -> 2080160 (0.00 %) VGPRS: 798875 -> 797826 (-0.13 %) Spilled SGPRs: 108485 -> 79165 (-27.03 %) Spilled VGPRs: 327 -> 327 (0.00 %) Scratch VGPRs: 1656 -> 1652 (-0.24 %) dwords per thread Code Size: 36127192 -> 35559780 (-1.57 %) bytes LDS: 767 -> 767 (0.00 %) blocks Max Waves: 212464 -> 212672 (0.10 %) Wait states: 0 -> 0 (0.00 %) PERCENTAGES / App Shaders SGPRs VGPRs SpillSGPR SpillVGPR Scratch CodeSize MaxWaves Waits (unknown) 4 . . . . . . . . 0ad 6 . . . . . . . . alien_isolation 2938 . 0.04 % -8.53 % . . -0.71 % -0.06 % . anholt 10 . . . . . . . . batman_arkham_origins 589 . -0.58 % -79.54 % . . -6.72 % 0.57 % . bioshock-infinite 1769 . -0.65 % -89.32 % . . -4.73 % 0.48 % . borderlands2 3968 . -0.31 % -51.21 % . . -4.09 % 0.22 % . brutal-legend 338 . -0.03 % -2.95 % . . -0.06 % . . civilization_beyond.. 116 . . -14.17 % . . -0.88 % . . counter_strike_glob.. 1142 . . . . . . . . dirt-showdown 541 . -0.56 % -40.14 % . -3.45 % -1.82 % 0.35 % . dolphin 22 . . . . . 0.16 % . . dota2 1747 . . . . . 0.01 % . . europa_universalis_4 76 . -0.23 % -42.11 % . . -0.96 % . . f1-2015 774 . -0.09 % -28.89 % . . -2.60 % 0.09 % . furmark-0.7.0 4 . . . . . . . . gimark-0.7.0 10 . . . . . . . . glamor 16 . . . . . . . . humus-celshading 4 . . . . . . . . humus-domino 6 . . . . . . . . humus-dynamicbranching 24 . 0.71 % . . . 0.29 % -0.45 % . humus-hdr 10 . . . . . . . . humus-portals 2 . . . . . . . . humus-volumetricfog.. 6 . . . . . . . . left_4_dead_2 1762 . . . . . . . . metro_2033_redux 2670 . -0.10 % -7.15 % . . -0.03 % . . nexuiz 80 . . . . . . . . pixmark-julia-fp32 2 . . . . . . . . pixmark-julia-fp64 2 . . . . . . . . pixmark-piano-0.7.0 2 . . . . . . . . pixmark-volplosion-.. 2 . . . . . . . . plot3d-0.7.0 8 . . . . . . . . portal 474 . . . . . . . . sauerbraten 7 . . . . . . . . serious_sam_3_bfe 392 . . -13.20 % . . -1.81 % . . supertuxkart 4 . . . . . . . . talos_principle 324 . -0.21 % -18.39 % . . -2.73 % 0.14 % . team_fortress_2 808 . . . . . . . . tesseract 430 . 0.08 % -68.57 % . . -0.45 % . . tessmark-0.7.0 6 . . . . . . . . thea 172 . . . . . 0.03 % . . ue4_effects_cave 299 . -0.04 % -10.15 % . . -0.25 % 0.04 % . ue4_elemental 586 . -0.02 % -13.93 % . . -0.13 % 0.02 % . ue4_lightroom_inter.. 74 . -0.17 % -70.00 % . . -1.27 % . . ue4_realistic_rende.. 92 . . -32.58 % . . -0.35 % . . unigine_heaven 322 . 0.12 % -54.17 % . . -1.42 % -0.12 % . unigine_sanctuary 264 . . . . . . . . unigine_tropics 210 . . . . . . . . unigine_valley 278 . -0.15 % -40.74 % . . -2.00 % 0.09 % . unity 72 . . . . . 0.03 % . . warsow 176 . . . . . . . . warzone2100 4 . . . . . 0.13 % . . witcher2 1040 . -0.03 % -86.28 % . . -0.28 % 0.01 % . xcom_enemy_within 1236 . -0.24 % -63.54 % . . -0.93 % 0.18 % . yofrankie 82 . -0.61 % -100.00 % . . -0.83 % 0.41 % . ----------------------------------------------------------------------------------------------------------- Total 26002 . -0.13 % -27.03 % . -0.24 % -1.57 % 0.10 % . Reviewed-by: Nicolai Hähnle --- diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c index f60c363d619..22fcd931450 100644 --- a/src/gallium/drivers/radeonsi/si_shader.c +++ b/src/gallium/drivers/radeonsi/si_shader.c @@ -33,6 +33,7 @@ #include "gallivm/lp_bld_arit.h" #include "gallivm/lp_bld_bitarit.h" #include "gallivm/lp_bld_flow.h" +#include "gallivm/lp_bld_misc.h" #include "radeon/r600_cs.h" #include "radeon/radeon_llvm.h" #include "radeon/radeon_elf_util.h" @@ -5311,11 +5312,17 @@ static void si_create_function(struct si_shader_context *ctx, for (i = 0; i <= last_sgpr; ++i) { LLVMValueRef P = LLVMGetParam(ctx->radeon_bld.main_fn, i); - /* We tell llvm that array inputs are passed by value to allow Sinking pass - * to move load. Inputs are constant so this is fine. */ - if (i <= last_array_pointer) + /* The combination of: + * - ByVal + * - dereferenceable + * - tbaa + * allows the optimization passes to move loads and reduces + * SGPR spilling significantly. + */ + if (i <= last_array_pointer) { LLVMAddAttribute(P, LLVMByValAttribute); - else + lp_add_attr_dereferenceable(P, UINT64_MAX); + } else LLVMAddAttribute(P, LLVMInRegAttribute); }