From 80b76ba692f715bbe63c1def45400a9fc940eb6a Mon Sep 17 00:00:00 2001 From: Rhys Perry Date: Tue, 10 Sep 2024 11:04:46 +0100 Subject: [PATCH] nir: add more intrinsics to nir_intrinsic_can_reorder Including nir_intrinsic_load_global. fossil-db (navi21): Totals from 2725 (3.43% of 79395) affected shaders: MaxWaves: 71972 -> 71964 (-0.01%); split: +0.01%, -0.02% Instrs: 2831052 -> 2819902 (-0.39%); split: -0.45%, +0.06% CodeSize: 15047548 -> 14973072 (-0.49%); split: -0.57%, +0.08% VGPRs: 108864 -> 108856 (-0.01%); split: -0.02%, +0.01% SpillSGPRs: 906 -> 926 (+2.21%) SpillVGPRs: 196 -> 1092 (+457.14%) Scratch: 729088 -> 741376 (+1.69%) Latency: 16621317 -> 16586551 (-0.21%); split: -0.34%, +0.13% InvThroughput: 4169987 -> 4164876 (-0.12%); split: -0.23%, +0.11% VClause: 63247 -> 63471 (+0.35%); split: -0.21%, +0.56% SClause: 56978 -> 55276 (-2.99%); split: -3.50%, +0.51% Copies: 252545 -> 252495 (-0.02%); split: -0.98%, +0.96% Branches: 91378 -> 91388 (+0.01%); split: -0.03%, +0.04% PreSGPRs: 112753 -> 126850 (+12.50%); split: -0.48%, +12.98% PreVGPRs: 90617 -> 90708 (+0.10%) VALU: 1709034 -> 1709368 (+0.02%); split: -0.01%, +0.03% SALU: 463554 -> 462253 (-0.28%); split: -0.57%, +0.29% VMEM: 115952 -> 116272 (+0.28%); split: -0.21%, +0.49% SMEM: 129097 -> 120538 (-6.63%); split: -6.64%, +0.01% Signed-off-by: Rhys Perry Reviewed-by: Georg Lehmann Part-of: --- src/compiler/nir/nir.h | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/src/compiler/nir/nir.h b/src/compiler/nir/nir.h index 96484cc69f7..03d9cc70942 100644 --- a/src/compiler/nir/nir.h +++ b/src/compiler/nir/nir.h @@ -2195,21 +2195,17 @@ void nir_rewrite_image_intrinsic(nir_intrinsic_instr *instr, static inline bool nir_intrinsic_can_reorder(nir_intrinsic_instr *instr) { - if (nir_intrinsic_has_access(instr) && - nir_intrinsic_access(instr) & ACCESS_VOLATILE) - return false; + if (nir_intrinsic_has_access(instr)) { + enum gl_access_qualifier access = nir_intrinsic_access(instr); + if (access & ACCESS_VOLATILE) + return false; + if (access & ACCESS_CAN_REORDER) + return true; + } if (instr->intrinsic == nir_intrinsic_load_deref) { nir_deref_instr *deref = nir_src_as_deref(instr->src[0]); - return nir_deref_mode_is_in_set(deref, nir_var_read_only_modes) || - (nir_intrinsic_access(instr) & ACCESS_CAN_REORDER); - } else if (instr->intrinsic == nir_intrinsic_load_ssbo || - instr->intrinsic == nir_intrinsic_bindless_image_load || - instr->intrinsic == nir_intrinsic_image_deref_load || - instr->intrinsic == nir_intrinsic_image_load || - instr->intrinsic == nir_intrinsic_ald_nv || - instr->intrinsic == nir_intrinsic_load_sysval_nv) { - return nir_intrinsic_access(instr) & ACCESS_CAN_REORDER; + return nir_deref_mode_is_in_set(deref, nir_var_read_only_modes); } else { const nir_intrinsic_info *info = &nir_intrinsic_infos[instr->intrinsic];