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