1/* 2 * Copyright (c) 2019 Zodiac Inflight Innovations 3 * 4 * Permission is hereby granted, free of charge, to any person obtaining a 5 * copy of this software and associated documentation files (the "Software"), 6 * to deal in the Software without restriction, including without limitation 7 * the rights to use, copy, modify, merge, publish, distribute, sub license, 8 * and/or sell copies of the Software, and to permit persons to whom the 9 * Software is furnished to do so, subject to the following conditions: 10 * 11 * The above copyright notice and this permission notice (including the 12 * next paragraph) shall be included in all copies or substantial portions 13 * of the Software. 14 * 15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL 18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 21 * DEALINGS IN THE SOFTWARE. 22 * 23 * Authors: 24 * Jonathan Marek <jonathan@marek.ca> 25 */ 26 27#include "etnaviv_nir.h" 28 29/* io related lowering 30 * run after lower_int_to_float because it adds i2f/f2i ops 31 */ 32void 33etna_lower_io(nir_shader *shader, struct etna_shader_variant *v) 34{ 35 nir_foreach_function(function, shader) { 36 nir_builder b; 37 nir_builder_init(&b, function->impl); 38 39 nir_foreach_block(block, function->impl) { 40 nir_foreach_instr_safe(instr, block) { 41 if (instr->type == nir_instr_type_intrinsic) { 42 nir_intrinsic_instr *intr = nir_instr_as_intrinsic(instr); 43 44 switch (intr->intrinsic) { 45 case nir_intrinsic_load_front_face: { 46 /* HW front_face is 0.0/1.0, not 0/~0u for bool 47 * lower with a comparison with 0 48 */ 49 intr->dest.ssa.bit_size = 32; 50 51 b.cursor = nir_after_instr(instr); 52 53 nir_ssa_def *ssa = nir_ine(&b, &intr->dest.ssa, nir_imm_int(&b, 0)); 54 if (v->key.front_ccw) 55 nir_instr_as_alu(ssa->parent_instr)->op = nir_op_ieq; 56 57 nir_ssa_def_rewrite_uses_after(&intr->dest.ssa, 58 ssa, 59 ssa->parent_instr); 60 } break; 61 case nir_intrinsic_store_deref: { 62 nir_deref_instr *deref = nir_src_as_deref(intr->src[0]); 63 if (shader->info.stage != MESA_SHADER_FRAGMENT || !v->key.frag_rb_swap) 64 break; 65 66 assert(deref->deref_type == nir_deref_type_var); 67 68 if (deref->var->data.location != FRAG_RESULT_COLOR && 69 deref->var->data.location != FRAG_RESULT_DATA0) 70 break; 71 72 b.cursor = nir_before_instr(instr); 73 74 nir_ssa_def *ssa = nir_mov(&b, intr->src[1].ssa); 75 nir_alu_instr *alu = nir_instr_as_alu(ssa->parent_instr); 76 alu->src[0].swizzle[0] = 2; 77 alu->src[0].swizzle[2] = 0; 78 nir_instr_rewrite_src(instr, &intr->src[1], nir_src_for_ssa(ssa)); 79 } break; 80 case nir_intrinsic_load_vertex_id: 81 case nir_intrinsic_load_instance_id: 82 /* detect use of vertex_id/instance_id */ 83 v->vs_id_in_reg = v->infile.num_reg; 84 break; 85 default: 86 break; 87 } 88 } 89 90 if (instr->type != nir_instr_type_tex) 91 continue; 92 93 nir_tex_instr *tex = nir_instr_as_tex(instr); 94 nir_src *coord = NULL; 95 nir_src *src1 = NULL; 96 unsigned src1_idx; 97 98 assert(tex->sampler_index == tex->texture_index); 99 100 for (unsigned i = 0; i < tex->num_srcs; i++) { 101 switch (tex->src[i].src_type) { 102 case nir_tex_src_coord: 103 coord = &tex->src[i].src; 104 break; 105 case nir_tex_src_bias: 106 case nir_tex_src_lod: 107 assert(!src1); 108 src1 = &tex->src[i].src; 109 src1_idx = i; 110 break; 111 case nir_tex_src_ddx: 112 case nir_tex_src_ddy: 113 case nir_tex_src_comparator: 114 break; 115 default: 116 assert(0); 117 break; 118 } 119 } 120 121 /* pre HALTI5 needs texture sources in a single source */ 122 123 if (!src1 || v->shader->specs->halti >= 5) 124 continue; 125 126 assert(coord && src1 && tex->coord_components < 4); 127 128 nir_alu_instr *vec = nir_alu_instr_create(shader, nir_op_vec4); 129 for (unsigned i = 0; i < tex->coord_components; i++) { 130 vec->src[i].src = nir_src_for_ssa(coord->ssa); 131 vec->src[i].swizzle[0] = i; 132 } 133 for (unsigned i = tex->coord_components; i < 4; i++) 134 vec->src[i].src = nir_src_for_ssa(src1->ssa); 135 136 vec->dest.write_mask = 0xf; 137 nir_ssa_dest_init(&vec->instr, &vec->dest.dest, 4, 32, NULL); 138 139 nir_tex_instr_remove_src(tex, src1_idx); 140 nir_instr_rewrite_src(&tex->instr, coord, nir_src_for_ssa(&vec->dest.dest.ssa)); 141 tex->coord_components = 4; 142 143 nir_instr_insert_before(&tex->instr, &vec->instr); 144 } 145 } 146 } 147} 148 149static void 150etna_lower_alu_impl(nir_function_impl *impl, bool has_new_transcendentals) 151{ 152 nir_shader *shader = impl->function->shader; 153 154 nir_builder b; 155 nir_builder_init(&b, impl); 156 157 /* in a seperate loop so we can apply the multiple-uniform logic to the new fmul */ 158 nir_foreach_block(block, impl) { 159 nir_foreach_instr_safe(instr, block) { 160 if (instr->type != nir_instr_type_alu) 161 continue; 162 163 nir_alu_instr *alu = nir_instr_as_alu(instr); 164 /* multiply sin/cos src by constant 165 * TODO: do this earlier (but it breaks const_prop opt) 166 */ 167 if (alu->op == nir_op_fsin || alu->op == nir_op_fcos) { 168 b.cursor = nir_before_instr(instr); 169 170 nir_ssa_def *imm = has_new_transcendentals ? 171 nir_imm_float(&b, 1.0 / M_PI) : 172 nir_imm_float(&b, 2.0 / M_PI); 173 174 nir_instr_rewrite_src(instr, &alu->src[0].src, 175 nir_src_for_ssa(nir_fmul(&b, alu->src[0].src.ssa, imm))); 176 } 177 178 /* change transcendental ops to vec2 and insert vec1 mul for the result 179 * TODO: do this earlier (but it breaks with optimizations) 180 */ 181 if (has_new_transcendentals && ( 182 alu->op == nir_op_fdiv || alu->op == nir_op_flog2 || 183 alu->op == nir_op_fsin || alu->op == nir_op_fcos)) { 184 nir_ssa_def *ssa = &alu->dest.dest.ssa; 185 186 assert(ssa->num_components == 1); 187 188 nir_alu_instr *mul = nir_alu_instr_create(shader, nir_op_fmul); 189 mul->src[0].src = mul->src[1].src = nir_src_for_ssa(ssa); 190 mul->src[1].swizzle[0] = 1; 191 192 mul->dest.write_mask = 1; 193 nir_ssa_dest_init(&mul->instr, &mul->dest.dest, 1, 32, NULL); 194 195 ssa->num_components = 2; 196 197 mul->dest.saturate = alu->dest.saturate; 198 alu->dest.saturate = 0; 199 200 nir_instr_insert_after(instr, &mul->instr); 201 202 nir_ssa_def_rewrite_uses_after(ssa, &mul->dest.dest.ssa, 203 &mul->instr); 204 } 205 } 206 } 207} 208 209void 210etna_lower_alu(nir_shader *shader, bool has_new_transcendentals) 211{ 212 nir_foreach_function(function, shader) { 213 if (function->impl) 214 etna_lower_alu_impl(function->impl, has_new_transcendentals); 215 } 216} 217