1/*
2 * Copyright © 2016 Intel Corporation
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, sublicense,
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 next
12 * paragraph) shall be included in all copies or substantial portions of the
13 * 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 NONINFRINGEMENT.  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
24#include "ir.h"
25#include "ir_builder.h"
26#include "ir_optimization.h"
27#include "ir_hierarchical_visitor.h"
28#include "program/prog_instruction.h"
29#include "program/prog_statevars.h"
30#include "util/bitscan.h"
31#include "builtin_functions.h"
32#include "main/shader_types.h"
33
34using namespace ir_builder;
35
36#define imm1(x) new(mem_ctx) ir_constant((float) (x), 1)
37#define imm3(x) new(mem_ctx) ir_constant((float) (x), 3)
38
39static ir_rvalue *
40blend_multiply(ir_variable *src, ir_variable *dst)
41{
42   /* f(Cs,Cd) = Cs*Cd */
43   return mul(src, dst);
44}
45
46static ir_rvalue *
47blend_screen(ir_variable *src, ir_variable *dst)
48{
49   /* f(Cs,Cd) = Cs+Cd-Cs*Cd */
50   return sub(add(src, dst), mul(src, dst));
51}
52
53static ir_rvalue *
54blend_overlay(ir_variable *src, ir_variable *dst)
55{
56   void *mem_ctx = ralloc_parent(src);
57
58   /* f(Cs,Cd) = 2*Cs*Cd, if Cd <= 0.5
59    *            1-2*(1-Cs)*(1-Cd), otherwise
60    */
61   ir_rvalue *rule_1 = mul(imm3(2), mul(src, dst));
62   ir_rvalue *rule_2 =
63      sub(imm3(1), mul(imm3(2), mul(sub(imm3(1), src), sub(imm3(1), dst))));
64   return csel(lequal(dst, imm3(0.5f)), rule_1, rule_2);
65}
66
67static ir_rvalue *
68blend_darken(ir_variable *src, ir_variable *dst)
69{
70   /* f(Cs,Cd) = min(Cs,Cd) */
71   return min2(src, dst);
72}
73
74static ir_rvalue *
75blend_lighten(ir_variable *src, ir_variable *dst)
76{
77   /* f(Cs,Cd) = max(Cs,Cd) */
78   return max2(src, dst);
79}
80
81static ir_rvalue *
82blend_colordodge(ir_variable *src, ir_variable *dst)
83{
84   void *mem_ctx = ralloc_parent(src);
85
86   /* f(Cs,Cd) =
87    *   0, if Cd <= 0
88    *   min(1,Cd/(1-Cs)), if Cd > 0 and Cs < 1
89    *   1, if Cd > 0 and Cs >= 1
90    */
91   return csel(lequal(dst, imm3(0)), imm3(0),
92               csel(gequal(src, imm3(1)), imm3(1),
93                    min2(imm3(1), div(dst, sub(imm3(1), src)))));
94}
95
96static ir_rvalue *
97blend_colorburn(ir_variable *src, ir_variable *dst)
98{
99   void *mem_ctx = ralloc_parent(src);
100
101   /* f(Cs,Cd) =
102    *   1, if Cd >= 1
103    *   1 - min(1,(1-Cd)/Cs), if Cd < 1 and Cs > 0
104    *   0, if Cd < 1 and Cs <= 0
105    */
106   return csel(gequal(dst, imm3(1)), imm3(1),
107               csel(lequal(src, imm3(0)), imm3(0),
108                    sub(imm3(1), min2(imm3(1), div(sub(imm3(1), dst), src)))));
109}
110
111static ir_rvalue *
112blend_hardlight(ir_variable *src, ir_variable *dst)
113{
114   void *mem_ctx = ralloc_parent(src);
115
116   /* f(Cs,Cd) = 2*Cs*Cd, if Cs <= 0.5
117    *            1-2*(1-Cs)*(1-Cd), otherwise
118    */
119   ir_rvalue *rule_1 = mul(imm3(2), mul(src, dst));
120   ir_rvalue *rule_2 =
121      sub(imm3(1), mul(imm3(2), mul(sub(imm3(1), src), sub(imm3(1), dst))));
122   return csel(lequal(src, imm3(0.5f)), rule_1, rule_2);
123}
124
125static ir_rvalue *
126blend_softlight(ir_variable *src, ir_variable *dst)
127{
128   void *mem_ctx = ralloc_parent(src);
129
130   /* f(Cs,Cd) =
131    *   Cd-(1-2*Cs)*Cd*(1-Cd),
132    *     if Cs <= 0.5
133    *   Cd+(2*Cs-1)*Cd*((16*Cd-12)*Cd+3),
134    *     if Cs > 0.5 and Cd <= 0.25
135    *   Cd+(2*Cs-1)*(sqrt(Cd)-Cd),
136    *     if Cs > 0.5 and Cd > 0.25
137    *
138    * We can simplify this to
139    *
140    * f(Cs,Cd) = Cd+(2*Cs-1)*g(Cs,Cd) where
141    * g(Cs,Cd) = Cd*Cd-Cd             if Cs <= 0.5
142    *            Cd*((16*Cd-12)*Cd+3) if Cs > 0.5 and Cd <= 0.25
143    *            sqrt(Cd)-Cd,         otherwise
144    */
145   ir_rvalue *factor_1 = mul(dst, sub(imm3(1), dst));
146   ir_rvalue *factor_2 =
147      mul(dst, add(mul(sub(mul(imm3(16), dst), imm3(12)), dst), imm3(3)));
148   ir_rvalue *factor_3 = sub(sqrt(dst), dst);
149   ir_rvalue *factor = csel(lequal(src, imm3(0.5f)), factor_1,
150                            csel(lequal(dst, imm3(0.25f)),
151                                        factor_2, factor_3));
152   return add(dst, mul(sub(mul(imm3(2), src), imm3(1)), factor));
153}
154
155static ir_rvalue *
156blend_difference(ir_variable *src, ir_variable *dst)
157{
158   return abs(sub(dst, src));
159}
160
161static ir_rvalue *
162blend_exclusion(ir_variable *src, ir_variable *dst)
163{
164   void *mem_ctx = ralloc_parent(src);
165
166   return add(src, sub(dst, mul(imm3(2), mul(src, dst))));
167}
168
169/* Return the minimum of a vec3's components */
170static ir_rvalue *
171minv3(ir_variable *v)
172{
173   return min2(min2(swizzle_x(v), swizzle_y(v)), swizzle_z(v));
174}
175
176/* Return the maximum of a vec3's components */
177static ir_rvalue *
178maxv3(ir_variable *v)
179{
180   return max2(max2(swizzle_x(v), swizzle_y(v)), swizzle_z(v));
181}
182
183static ir_rvalue *
184lumv3(ir_variable *c)
185{
186   ir_constant_data data;
187   data.f[0] = 0.30;
188   data.f[1] = 0.59;
189   data.f[2] = 0.11;
190
191   void *mem_ctx = ralloc_parent(c);
192
193   /* dot(c, vec3(0.30, 0.59, 0.11)) */
194   return dot(c, new(mem_ctx) ir_constant(glsl_type::vec3_type, &data));
195}
196
197static ir_rvalue *
198satv3(ir_variable *c)
199{
200   return sub(maxv3(c), minv3(c));
201}
202
203/* Take the base RGB color <cbase> and override its luminosity with that
204 * of the RGB color <clum>.
205 *
206 * This follows the equations given in the ES 3.2 (June 15th, 2016)
207 * specification.  Revision 16 of GL_KHR_blend_equation_advanced and
208 * revision 9 of GL_NV_blend_equation_advanced specify a different set
209 * of equations.  Older revisions match ES 3.2's text, and dEQP expects
210 * the ES 3.2 rules implemented here.
211 */
212static void
213set_lum(ir_factory *f,
214        ir_variable *color,
215        ir_variable *cbase,
216        ir_variable *clum)
217{
218   void *mem_ctx = f->mem_ctx;
219   f->emit(assign(color, add(cbase, sub(lumv3(clum), lumv3(cbase)))));
220
221   ir_variable *llum = f->make_temp(glsl_type::float_type, "__blend_lum");
222   ir_variable *mincol = f->make_temp(glsl_type::float_type, "__blend_mincol");
223   ir_variable *maxcol = f->make_temp(glsl_type::float_type, "__blend_maxcol");
224
225   f->emit(assign(llum, lumv3(color)));
226   f->emit(assign(mincol, minv3(color)));
227   f->emit(assign(maxcol, maxv3(color)));
228
229   f->emit(if_tree(less(mincol, imm1(0)),
230                   assign(color, add(llum, div(mul(sub(color, llum), llum),
231                                               sub(llum, mincol)))),
232                   if_tree(greater(maxcol, imm1(1)),
233                           assign(color, add(llum, div(mul(sub(color, llum),
234                                                           sub(imm3(1), llum)),
235                                                       sub(maxcol, llum)))))));
236
237}
238
239/* Take the base RGB color <cbase> and override its saturation with
240 * that of the RGB color <csat>.  The override the luminosity of the
241 * result with that of the RGB color <clum>.
242 */
243static void
244set_lum_sat(ir_factory *f,
245            ir_variable *color,
246            ir_variable *cbase,
247            ir_variable *csat,
248            ir_variable *clum)
249{
250   void *mem_ctx = f->mem_ctx;
251
252   ir_rvalue *minbase = minv3(cbase);
253   ir_rvalue *ssat = satv3(csat);
254
255   ir_variable *sbase = f->make_temp(glsl_type::float_type, "__blend_sbase");
256   f->emit(assign(sbase, satv3(cbase)));
257
258   /* Equivalent (modulo rounding errors) to setting the
259    * smallest (R,G,B) component to 0, the largest to <ssat>,
260    * and interpolating the "middle" component based on its
261    * original value relative to the smallest/largest.
262    */
263   f->emit(if_tree(greater(sbase, imm1(0)),
264                   assign(color, div(mul(sub(cbase, minbase), ssat), sbase)),
265                   assign(color, imm3(0))));
266   set_lum(f, color, color, clum);
267}
268
269static ir_rvalue *
270is_mode(ir_variable *mode, enum gl_advanced_blend_mode q)
271{
272   return equal(mode, new(ralloc_parent(mode)) ir_constant(unsigned(q)));
273}
274
275static ir_variable *
276calc_blend_result(ir_factory f,
277                  ir_variable *mode,
278                  ir_variable *fb,
279                  ir_rvalue *blend_src,
280                  GLbitfield blend_qualifiers)
281{
282   void *mem_ctx = f.mem_ctx;
283   ir_variable *result = f.make_temp(glsl_type::vec4_type, "__blend_result");
284
285   /* Save blend_src to a temporary so we can reference it multiple times. */
286   ir_variable *src = f.make_temp(glsl_type::vec4_type, "__blend_src");
287   f.emit(assign(src, blend_src));
288
289   /* If we're not doing advanced blending, just write the original value. */
290   ir_if *if_blending = new(mem_ctx) ir_if(is_mode(mode, BLEND_NONE));
291   f.emit(if_blending);
292   if_blending->then_instructions.push_tail(assign(result, src));
293
294   f.instructions = &if_blending->else_instructions;
295
296   /* (Rs', Gs', Bs') =
297    *   (0, 0, 0),              if As == 0
298    *   (Rs/As, Gs/As, Bs/As),  otherwise
299    */
300   ir_variable *src_rgb = f.make_temp(glsl_type::vec3_type, "__blend_src_rgb");
301   ir_variable *src_alpha = f.make_temp(glsl_type::float_type, "__blend_src_a");
302
303   /* (Rd', Gd', Bd') =
304    *   (0, 0, 0),              if Ad == 0
305    *   (Rd/Ad, Gd/Ad, Bd/Ad),  otherwise
306    */
307   ir_variable *dst_rgb = f.make_temp(glsl_type::vec3_type, "__blend_dst_rgb");
308   ir_variable *dst_alpha = f.make_temp(glsl_type::float_type, "__blend_dst_a");
309
310   f.emit(assign(dst_alpha, swizzle_w(fb)));
311   f.emit(if_tree(equal(dst_alpha, imm1(0)),
312                     assign(dst_rgb, imm3(0)),
313                     assign(dst_rgb, csel(equal(swizzle_xyz(fb),
314                                                swizzle(fb, SWIZZLE_WWWW, 3)),
315                                          imm3(1),
316                                          div(swizzle_xyz(fb), dst_alpha)))));
317
318   f.emit(assign(src_alpha, swizzle_w(src)));
319   f.emit(if_tree(equal(src_alpha, imm1(0)),
320                     assign(src_rgb, imm3(0)),
321                     assign(src_rgb, csel(equal(swizzle_xyz(src),
322                                                swizzle(src, SWIZZLE_WWWW, 3)),
323                                          imm3(1),
324                                          div(swizzle_xyz(src), src_alpha)))));
325
326   ir_variable *factor = f.make_temp(glsl_type::vec3_type, "__blend_factor");
327
328   ir_factory casefactory = f;
329
330   unsigned choices = blend_qualifiers;
331   while (choices) {
332      enum gl_advanced_blend_mode choice = (enum gl_advanced_blend_mode)u_bit_scan(&choices);
333
334      ir_if *iff = new(mem_ctx) ir_if(is_mode(mode, choice));
335      casefactory.emit(iff);
336      casefactory.instructions = &iff->then_instructions;
337
338      ir_rvalue *val = NULL;
339
340      switch (choice) {
341      case BLEND_MULTIPLY:
342         val = blend_multiply(src_rgb, dst_rgb);
343         break;
344      case BLEND_SCREEN:
345         val = blend_screen(src_rgb, dst_rgb);
346         break;
347      case BLEND_OVERLAY:
348         val = blend_overlay(src_rgb, dst_rgb);
349         break;
350      case BLEND_DARKEN:
351         val = blend_darken(src_rgb, dst_rgb);
352         break;
353      case BLEND_LIGHTEN:
354         val = blend_lighten(src_rgb, dst_rgb);
355         break;
356      case BLEND_COLORDODGE:
357         val = blend_colordodge(src_rgb, dst_rgb);
358         break;
359      case BLEND_COLORBURN:
360         val = blend_colorburn(src_rgb, dst_rgb);
361         break;
362      case BLEND_HARDLIGHT:
363         val = blend_hardlight(src_rgb, dst_rgb);
364         break;
365      case BLEND_SOFTLIGHT:
366         val = blend_softlight(src_rgb, dst_rgb);
367         break;
368      case BLEND_DIFFERENCE:
369         val = blend_difference(src_rgb, dst_rgb);
370         break;
371      case BLEND_EXCLUSION:
372         val = blend_exclusion(src_rgb, dst_rgb);
373         break;
374      case BLEND_HSL_HUE:
375         set_lum_sat(&casefactory, factor, src_rgb, dst_rgb, dst_rgb);
376         break;
377      case BLEND_HSL_SATURATION:
378         set_lum_sat(&casefactory, factor, dst_rgb, src_rgb, dst_rgb);
379         break;
380      case BLEND_HSL_COLOR:
381         set_lum(&casefactory, factor, src_rgb, dst_rgb);
382         break;
383      case BLEND_HSL_LUMINOSITY:
384         set_lum(&casefactory, factor, dst_rgb, src_rgb);
385         break;
386      case BLEND_NONE:
387         unreachable("not real cases");
388      }
389
390      if (val)
391         casefactory.emit(assign(factor, val));
392
393      casefactory.instructions = &iff->else_instructions;
394   }
395
396   /* p0(As,Ad) = As*Ad
397    * p1(As,Ad) = As*(1-Ad)
398    * p2(As,Ad) = Ad*(1-As)
399    */
400   ir_variable *p0 = f.make_temp(glsl_type::float_type, "__blend_p0");
401   ir_variable *p1 = f.make_temp(glsl_type::float_type, "__blend_p1");
402   ir_variable *p2 = f.make_temp(glsl_type::float_type, "__blend_p2");
403
404   f.emit(assign(p0, mul(src_alpha, dst_alpha)));
405   f.emit(assign(p1, mul(src_alpha, sub(imm1(1), dst_alpha))));
406   f.emit(assign(p2, mul(dst_alpha, sub(imm1(1), src_alpha))));
407
408   /* R = f(Rs',Rd')*p0(As,Ad) + Y*Rs'*p1(As,Ad) + Z*Rd'*p2(As,Ad)
409    * G = f(Gs',Gd')*p0(As,Ad) + Y*Gs'*p1(As,Ad) + Z*Gd'*p2(As,Ad)
410    * B = f(Bs',Bd')*p0(As,Ad) + Y*Bs'*p1(As,Ad) + Z*Bd'*p2(As,Ad)
411    * A =          X*p0(As,Ad) +     Y*p1(As,Ad) +     Z*p2(As,Ad)
412    *
413    * <X, Y, Z> is always <1, 1, 1>, so we can ignore it.
414    *
415    * In vector form, this is:
416    * RGB = factor * p0 + Cs * p1 + Cd * p2
417    *   A = p0 + p1 + p2
418    */
419   f.emit(assign(result,
420                 add(add(mul(factor, p0), mul(src_rgb, p1)), mul(dst_rgb, p2)),
421                 WRITEMASK_XYZ));
422   f.emit(assign(result, add(add(p0, p1), p2), WRITEMASK_W));
423
424   return result;
425}
426
427/**
428 * Dereference var, or var[0] if it's an array.
429 */
430static ir_dereference *
431deref_output(ir_variable *var)
432{
433   void *mem_ctx = ralloc_parent(var);
434
435   ir_dereference *val = new(mem_ctx) ir_dereference_variable(var);
436   if (val->type->is_array()) {
437      ir_constant *index = new(mem_ctx) ir_constant(0);
438      val = new(mem_ctx) ir_dereference_array(val, index);
439   }
440
441   return val;
442}
443
444static ir_function_signature *
445get_main(gl_linked_shader *sh)
446{
447   ir_function_signature *sig = NULL;
448   /* We can't use _mesa_get_main_function_signature() because we don't
449    * have a symbol table at this point.  Just go find main() by hand.
450    */
451   foreach_in_list(ir_instruction, ir, sh->ir) {
452      ir_function *f = ir->as_function();
453      if (f && strcmp(f->name, "main") == 0) {
454         exec_list void_parameters;
455         sig = f->matching_signature(NULL, &void_parameters, false);
456         break;
457      }
458   }
459   assert(sig != NULL); /* main() must exist */
460   return sig;
461}
462
463bool
464lower_blend_equation_advanced(struct gl_linked_shader *sh, bool coherent)
465{
466   assert(sh->Stage == MESA_SHADER_FRAGMENT);
467
468   if (sh->Program->info.fs.advanced_blend_modes == 0)
469      return false;
470
471   /* Lower early returns in main() so there's a single exit point
472    * where we can insert our lowering code.
473    */
474   do_lower_jumps(sh->ir, false, false, true, false);
475
476   void *mem_ctx = ralloc_parent(sh->ir);
477
478   ir_variable *fb = new(mem_ctx) ir_variable(glsl_type::vec4_type,
479                                              "__blend_fb_fetch",
480                                              ir_var_shader_out);
481   fb->data.location = FRAG_RESULT_DATA0;
482   fb->data.read_only = 1;
483   fb->data.fb_fetch_output = 1;
484   fb->data.memory_coherent = coherent;
485   fb->data.how_declared = ir_var_hidden;
486
487   ir_variable *mode = new(mem_ctx) ir_variable(glsl_type::uint_type,
488                                                "gl_AdvancedBlendModeMESA",
489                                                ir_var_uniform);
490   mode->data.how_declared = ir_var_hidden;
491   mode->allocate_state_slots(1);
492   ir_state_slot *slot0 = &mode->get_state_slots()[0];
493   slot0->swizzle = SWIZZLE_XXXX;
494   slot0->tokens[0] = STATE_ADVANCED_BLENDING_MODE;
495   for (int i = 1; i < STATE_LENGTH; i++)
496      slot0->tokens[i] = 0;
497
498   sh->ir->push_head(fb);
499   sh->ir->push_head(mode);
500
501   /* Gather any output variables referring to render target 0.
502    *
503    * ARB_enhanced_layouts irritatingly allows the shader to specify
504    * multiple output variables for the same render target, each of
505    * which writes a subset of the components, starting at location_frac.
506    * The variables can't overlap, thankfully.
507    */
508   ir_variable *outputs[4] = { NULL, NULL, NULL, NULL };
509   foreach_in_list(ir_instruction, ir, sh->ir) {
510      ir_variable *var = ir->as_variable();
511      if (!var || var->data.mode != ir_var_shader_out)
512         continue;
513
514      if (var->data.location == FRAG_RESULT_DATA0 ||
515          var->data.location == FRAG_RESULT_COLOR) {
516         const int components = var->type->without_array()->vector_elements;
517
518         for (int i = 0; i < components; i++) {
519            outputs[var->data.location_frac + i] = var;
520         }
521      }
522   }
523
524   /* Combine values written to outputs into a single RGBA blend source.
525    * We assign <0, 0, 0, 1> to any components with no corresponding output.
526    */
527   ir_rvalue *blend_source;
528   if (outputs[0] && outputs[0]->type->without_array()->vector_elements == 4) {
529      blend_source = deref_output(outputs[0]);
530   } else {
531      ir_rvalue *blend_comps[4];
532      for (int i = 0; i < 4; i++) {
533         ir_variable *var = outputs[i];
534         if (var) {
535            blend_comps[i] = swizzle(deref_output(outputs[i]),
536                                     i - outputs[i]->data.location_frac, 1);
537         } else {
538            blend_comps[i] = new(mem_ctx) ir_constant(i < 3 ? 0.0f : 1.0f);
539         }
540      }
541
542      blend_source =
543         new(mem_ctx) ir_expression(ir_quadop_vector, glsl_type::vec4_type,
544                                    blend_comps[0], blend_comps[1],
545                                    blend_comps[2], blend_comps[3]);
546   }
547
548   ir_function_signature *main = get_main(sh);
549   ir_factory f(&main->body, mem_ctx);
550
551   ir_variable *result_dest =
552      calc_blend_result(f, mode, fb, blend_source,
553                        sh->Program->info.fs.advanced_blend_modes);
554
555   /* Copy the result back to the original values.  It would be simpler
556    * to demote the program's output variables, and create a new vec4
557    * output for our result, but this pass runs before we create the
558    * ARB_program_interface_query resource list.  So we have to leave
559    * the original outputs in place and use them.
560    */
561   for (int i = 0; i < 4; i++) {
562      if (!outputs[i])
563         continue;
564
565      f.emit(assign(deref_output(outputs[i]), swizzle(result_dest, i, 1),
566                    1 << i));
567   }
568
569   validate_ir_tree(sh->ir);
570   return true;
571}
572