summaryrefslogtreecommitdiffstats
path: root/src/glsl/nir/nir.h
blob: 815c22c5e8b88c9d4af291aa60e0eed4fe2a570d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
/*
 * Copyright © 2014 Connor Abbott
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice (including the next
 * paragraph) shall be included in all copies or substantial portions of the
 * Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 *
 * Authors:
 *    Connor Abbott (cwabbott0@gmail.com)
 *
 */

#pragma once

#include "util/hash_table.h"
#include "../list.h"
#include "GL/gl.h" /* GLenum */
#include "util/list.h"
#include "util/ralloc.h"
#include "util/set.h"
#include "util/bitset.h"
#include "nir_types.h"
#include "shader_enums.h"
#include <stdio.h>

#include "nir_opcodes.h"

#ifdef __cplusplus
extern "C" {
#endif

struct gl_program;
struct gl_shader_program;

#define NIR_FALSE 0u
#define NIR_TRUE (~0u)

/** Defines a cast function
 *
 * This macro defines a cast function from in_type to out_type where
 * out_type is some structure type that contains a field of type out_type.
 *
 * Note that you have to be a bit careful as the generated cast function
 * destroys constness.
 */
#define NIR_DEFINE_CAST(name, in_type, out_type, field)  \
static inline out_type *                                 \
name(const in_type *parent)                              \
{                                                        \
   return exec_node_data(out_type, parent, field);       \
}

struct nir_function_overload;
struct nir_function;
struct nir_shader;
struct nir_instr;


/**
 * Description of built-in state associated with a uniform
 *
 * \sa nir_variable::state_slots
 */
typedef struct {
   int tokens[5];
   int swizzle;
} nir_state_slot;

typedef enum {
   nir_var_all = -1,
   nir_var_shader_in,
   nir_var_shader_out,
   nir_var_global,
   nir_var_local,
   nir_var_uniform,
   nir_var_shader_storage,
   nir_var_system_value
} nir_variable_mode;

/**
 * Data stored in an nir_constant
 */
union nir_constant_data {
   unsigned u[16];
   int i[16];
   float f[16];
   bool b[16];
};

typedef struct nir_constant {
   /**
    * Value of the constant.
    *
    * The field used to back the values supplied by the constant is determined
    * by the type associated with the \c nir_variable.  Constants may be
    * scalars, vectors, or matrices.
    */
   union nir_constant_data value;

   /* we could get this from the var->type but makes clone *much* easier to
    * not have to care about the type.
    */
   unsigned num_elements;

   /* Array elements / Structure Fields */
   struct nir_constant **elements;
} nir_constant;

/**
 * \brief Layout qualifiers for gl_FragDepth.
 *
 * The AMD/ARB_conservative_depth extensions allow gl_FragDepth to be redeclared
 * with a layout qualifier.
 */
typedef enum {
    nir_depth_layout_none, /**< No depth layout is specified. */
    nir_depth_layout_any,
    nir_depth_layout_greater,
    nir_depth_layout_less,
    nir_depth_layout_unchanged
} nir_depth_layout;

/**
 * Either a uniform, global variable, shader input, or shader output. Based on
 * ir_variable - it should be easy to translate between the two.
 */

typedef struct {
   struct exec_node node;

   /**
    * Declared type of the variable
    */
   const struct glsl_type *type;

   /**
    * Declared name of the variable
    */
   char *name;

   struct nir_variable_data {

      /**
       * Is the variable read-only?
       *
       * This is set for variables declared as \c const, shader inputs,
       * and uniforms.
       */
      unsigned read_only:1;
      unsigned centroid:1;
      unsigned sample:1;
      unsigned patch:1;
      unsigned invariant:1;

      /**
       * Storage class of the variable.
       *
       * \sa nir_variable_mode
       */
      nir_variable_mode mode:4;

      /**
       * Interpolation mode for shader inputs / outputs
       *
       * \sa glsl_interp_qualifier
       */
      unsigned interpolation:2;

      /**
       * \name ARB_fragment_coord_conventions
       * @{
       */
      unsigned origin_upper_left:1;
      unsigned pixel_center_integer:1;
      /*@}*/

      /**
       * Was the location explicitly set in the shader?
       *
       * If the location is explicitly set in the shader, it \b cannot be changed
       * by the linker or by the API (e.g., calls to \c glBindAttribLocation have
       * no effect).
       */
      unsigned explicit_location:1;
      unsigned explicit_index:1;

      /**
       * Was an initial binding explicitly set in the shader?
       *
       * If so, constant_initializer contains an integer nir_constant
       * representing the initial binding point.
       */
      unsigned explicit_binding:1;

      /**
       * Does this variable have an initializer?
       *
       * This is used by the linker to cross-validiate initializers of global
       * variables.
       */
      unsigned has_initializer:1;

      /**
       * Is this variable a generic output or input that has not yet been matched
       * up to a variable in another stage of the pipeline?
       *
       * This is used by the linker as scratch storage while assigning locations
       * to generic inputs and outputs.
       */
      unsigned is_unmatched_generic_inout:1;

      /**
       * If non-zero, then this variable may be packed along with other variables
       * into a single varying slot, so this offset should be applied when
       * accessing components.  For example, an offset of 1 means that the x
       * component of this variable is actually stored in component y of the
       * location specified by \c location.
       */
      unsigned location_frac:2;

      /**
       * Non-zero if this variable was created by lowering a named interface
       * block which was not an array.
       *
       * Note that this variable and \c from_named_ifc_block_array will never
       * both be non-zero.
       */
      unsigned from_named_ifc_block_nonarray:1;

      /**
       * Non-zero if this variable was created by lowering a named interface
       * block which was an array.
       *
       * Note that this variable and \c from_named_ifc_block_nonarray will never
       * both be non-zero.
       */
      unsigned from_named_ifc_block_array:1;

      /**
       * \brief Layout qualifier for gl_FragDepth.
       *
       * This is not equal to \c ir_depth_layout_none if and only if this
       * variable is \c gl_FragDepth and a layout qualifier is specified.
       */
      nir_depth_layout depth_layout;

      /**
       * Storage location of the base of this variable
       *
       * The precise meaning of this field depends on the nature of the variable.
       *
       *   - Vertex shader input: one of the values from \c gl_vert_attrib.
       *   - Vertex shader output: one of the values from \c gl_varying_slot.
       *   - Geometry shader input: one of the values from \c gl_varying_slot.
       *   - Geometry shader output: one of the values from \c gl_varying_slot.
       *   - Fragment shader input: one of the values from \c gl_varying_slot.
       *   - Fragment shader output: one of the values from \c gl_frag_result.
       *   - Uniforms: Per-stage uniform slot number for default uniform block.
       *   - Uniforms: Index within the uniform block definition for UBO members.
       *   - Non-UBO Uniforms: uniform slot number.
       *   - Other: This field is not currently used.
       *
       * If the variable is a uniform, shader input, or shader output, and the
       * slot has not been assigned, the value will be -1.
       */
      int location;

      /**
       * The actual location of the variable in the IR. Only valid for inputs
       * and outputs.
       */
      unsigned int driver_location;

      /**
       * output index for dual source blending.
       */
      int index;

      /**
       * Descriptor set binding for sampler or UBO.
       */
      int descriptor_set;

      /**
       * Initial binding point for a sampler or UBO.
       *
       * For array types, this represents the binding point for the first element.
       */
      int binding;

      /**
       * Location an atomic counter is stored at.
       */
      struct {
         unsigned offset;
      } atomic;

      /**
       * ARB_shader_image_load_store qualifiers.
       */
      struct {
         bool read_only; /**< "readonly" qualifier. */
         bool write_only; /**< "writeonly" qualifier. */
         bool coherent;
         bool _volatile;
         bool restrict_flag;

         /** Image internal format if specified explicitly, otherwise GL_NONE. */
         GLenum format;
      } image;

      /**
       * Highest element accessed with a constant expression array index
       *
       * Not used for non-array variables.
       */
      unsigned max_array_access;

   } data;

   /**
    * Built-in state that backs this uniform
    *
    * Once set at variable creation, \c state_slots must remain invariant.
    * This is because, ideally, this array would be shared by all clones of
    * this variable in the IR tree.  In other words, we'd really like for it
    * to be a fly-weight.
    *
    * If the variable is not a uniform, \c num_state_slots will be zero and
    * \c state_slots will be \c NULL.
    */
   /*@{*/
   unsigned num_state_slots;    /**< Number of state slots used */
   nir_state_slot *state_slots;  /**< State descriptors. */
   /*@}*/

   /**
    * Constant expression assigned in the initializer of the variable
    */
   nir_constant *constant_initializer;

   /**
    * For variables that are in an interface block or are an instance of an
    * interface block, this is the \c GLSL_TYPE_INTERFACE type for that block.
    *
    * \sa ir_variable::location
    */
   const struct glsl_type *interface_type;
} nir_variable;

#define nir_foreach_variable(var, var_list) \
   foreach_list_typed(nir_variable, var, node, var_list)

/**
 * Returns the bits in the inputs_read, outputs_written, or
 * system_values_read bitfield corresponding to this variable.
 */
static inline uint64_t
nir_variable_get_io_mask(nir_variable *var, gl_shader_stage stage)
{
   assert(var->data.mode == nir_var_shader_in ||
          var->data.mode == nir_var_shader_out ||
          var->data.mode == nir_var_system_value);
   assert(var->data.location >= 0);

   const struct glsl_type *var_type = var->type;
   if (stage == MESA_SHADER_GEOMETRY && var->data.mode == nir_var_shader_in) {
      /* Most geometry shader inputs are per-vertex arrays */
      if (var->data.location >= VARYING_SLOT_VAR0)
         assert(glsl_type_is_array(var_type));

      if (glsl_type_is_array(var_type))
         var_type = glsl_get_array_element(var_type);
   }

   unsigned slots = glsl_count_attribute_slots(var_type);
   return ((1ull << slots) - 1) << var->data.location;
}

typedef struct {
   struct exec_node node;

   unsigned num_components; /** < number of vector components */
   unsigned num_array_elems; /** < size of array (0 for no array) */

   /** generic register index. */
   unsigned index;

   /** only for debug purposes, can be NULL */
   const char *name;

   /** whether this register is local (per-function) or global (per-shader) */
   bool is_global;

   /**
    * If this flag is set to true, then accessing channels >= num_components
    * is well-defined, and simply spills over to the next array element. This
    * is useful for backends that can do per-component accessing, in
    * particular scalar backends. By setting this flag and making
    * num_components equal to 1, structures can be packed tightly into
    * registers and then registers can be accessed per-component to get to
    * each structure member, even if it crosses vec4 boundaries.
    */
   bool is_packed;

   /** set of nir_src's where this register is used (read from) */
   struct list_head uses;

   /** set of nir_dest's where this register is defined (written to) */
   struct list_head defs;

   /** set of nir_if's where this register is used as a condition */
   struct list_head if_uses;
} nir_register;

typedef enum {
   nir_instr_type_alu,
   nir_instr_type_call,
   nir_instr_type_tex,
   nir_instr_type_intrinsic,
   nir_instr_type_load_const,
   nir_instr_type_jump,
   nir_instr_type_ssa_undef,
   nir_instr_type_phi,
   nir_instr_type_parallel_copy,
} nir_instr_type;

typedef struct nir_instr {
   struct exec_node node;
   nir_instr_type type;
   struct nir_block *block;

   /** generic instruction index. */
   unsigned index;

   /* A temporary for optimization and analysis passes to use for storing
    * flags.  For instance, DCE uses this to store the "dead/live" info.
    */
   uint8_t pass_flags;
} nir_instr;

static inline nir_instr *
nir_instr_next(nir_instr *instr)
{
   struct exec_node *next = exec_node_get_next(&instr->node);
   if (exec_node_is_tail_sentinel(next))
      return NULL;
   else
      return exec_node_data(nir_instr, next, node);
}

static inline nir_instr *
nir_instr_prev(nir_instr *instr)
{
   struct exec_node *prev = exec_node_get_prev(&instr->node);
   if (exec_node_is_head_sentinel(prev))
      return NULL;
   else
      return exec_node_data(nir_instr, prev, node);
}

static inline bool
nir_instr_is_first(nir_instr *instr)
{
   return exec_node_is_head_sentinel(exec_node_get_prev(&instr->node));
}

static inline bool
nir_instr_is_last(nir_instr *instr)
{
   return exec_node_is_tail_sentinel(exec_node_get_next(&instr->node));
}

typedef struct {
   /** for debugging only, can be NULL */
   const char* name;

   /** generic SSA definition index. */
   unsigned index;

   /** Index into the live_in and live_out bitfields */
   unsigned live_index;

   nir_instr *parent_instr;

   /** set of nir_instr's where this register is used (read from) */
   struct list_head uses;

   /** set of nir_if's where this register is used as a condition */
   struct list_head if_uses;

   uint8_t num_components;
} nir_ssa_def;

struct nir_src;

typedef struct {
   nir_register *reg;
   struct nir_src *indirect; /** < NULL for no indirect offset */
   unsigned base_offset;

   /* TODO use-def chain goes here */
} nir_reg_src;

typedef struct {
   nir_instr *parent_instr;
   struct list_head def_link;

   nir_register *reg;
   struct nir_src *indirect; /** < NULL for no indirect offset */
   unsigned base_offset;

   /* TODO def-use chain goes here */
} nir_reg_dest;

struct nir_if;

typedef struct nir_src {
   union {
      nir_instr *parent_instr;
      struct nir_if *parent_if;
   };

   struct list_head use_link;

   union {
      nir_reg_src reg;
      nir_ssa_def *ssa;
   };

   bool is_ssa;
} nir_src;

#ifdef __cplusplus
#  define NIR_SRC_INIT nir_src()
#else
#  define NIR_SRC_INIT (nir_src) { { NULL } }
#endif

#define nir_foreach_use(reg_or_ssa_def, src) \
   list_for_each_entry(nir_src, src, &(reg_or_ssa_def)->uses, use_link)

#define nir_foreach_use_safe(reg_or_ssa_def, src) \
   list_for_each_entry_safe(nir_src, src, &(reg_or_ssa_def)->uses, use_link)

#define nir_foreach_if_use(reg_or_ssa_def, src) \
   list_for_each_entry(nir_src, src, &(reg_or_ssa_def)->if_uses, use_link)

#define nir_foreach_if_use_safe(reg_or_ssa_def, src) \
   list_for_each_entry_safe(nir_src, src, &(reg_or_ssa_def)->if_uses, use_link)

typedef struct {
   union {
      nir_reg_dest reg;
      nir_ssa_def ssa;
   };

   bool is_ssa;
} nir_dest;

#ifdef __cplusplus
#  define NIR_DEST_INIT nir_dest()
#else
#  define NIR_DEST_INIT (nir_dest) { { { NULL } } }
#endif

#define nir_foreach_def(reg, dest) \
   list_for_each_entry(nir_dest, dest, &(reg)->defs, reg.def_link)

#define nir_foreach_def_safe(reg, dest) \
   list_for_each_entry_safe(nir_dest, dest, &(reg)->defs, reg.def_link)

static inline nir_src
nir_src_for_ssa(nir_ssa_def *def)
{
   nir_src src = NIR_SRC_INIT;

   src.is_ssa = true;
   src.ssa = def;

   return src;
}

static inline nir_src
nir_src_for_reg(nir_register *reg)
{
   nir_src src = NIR_SRC_INIT;

   src.is_ssa = false;
   src.reg.reg = reg;
   src.reg.indirect = NULL;
   src.reg.base_offset = 0;

   return src;
}

static inline nir_dest
nir_dest_for_reg(nir_register *reg)
{
   nir_dest dest = NIR_DEST_INIT;

   dest.reg.reg = reg;

   return dest;
}

void nir_src_copy(nir_src *dest, const nir_src *src, void *instr_or_if);
void nir_dest_copy(nir_dest *dest, const nir_dest *src, nir_instr *instr);

typedef struct {
   nir_src src;

   /**
    * \name input modifiers
    */
   /*@{*/
   /**
    * For inputs interpreted as floating point, flips the sign bit. For
    * inputs interpreted as integers, performs the two's complement negation.
    */
   bool negate;

   /**
    * Clears the sign bit for floating point values, and computes the integer
    * absolute value for integers. Note that the negate modifier acts after
    * the absolute value modifier, therefore if both are set then all inputs
    * will become negative.
    */
   bool abs;
   /*@}*/

   /**
    * For each input component, says which component of the register it is
    * chosen from. Note that which elements of the swizzle are used and which
    * are ignored are based on the write mask for most opcodes - for example,
    * a statement like "foo.xzw = bar.zyx" would have a writemask of 1101b and
    * a swizzle of {2, x, 1, 0} where x means "don't care."
    */
   uint8_t swizzle[4];
} nir_alu_src;

typedef struct {
   nir_dest dest;

   /**
    * \name saturate output modifier
    *
    * Only valid for opcodes that output floating-point numbers. Clamps the
    * output to between 0.0 and 1.0 inclusive.
    */

   bool saturate;

   unsigned write_mask : 4; /* ignored if dest.is_ssa is true */
} nir_alu_dest;

typedef enum {
   nir_type_invalid = 0, /* Not a valid type */
   nir_type_float,
   nir_type_int,
   nir_type_uint,
   nir_type_bool
} nir_alu_type;

typedef enum {
   NIR_OP_IS_COMMUTATIVE = (1 << 0),
   NIR_OP_IS_ASSOCIATIVE = (1 << 1),
} nir_op_algebraic_property;

typedef struct {
   const char *name;

   unsigned num_inputs;

   /**
    * The number of components in the output
    *
    * If non-zero, this is the size of the output and input sizes are
    * explicitly given; swizzle and writemask are still in effect, but if
    * the output component is masked out, then the input component may
    * still be in use.
    *
    * If zero, the opcode acts in the standard, per-component manner; the
    * operation is performed on each component (except the ones that are
    * masked out) with the input being taken from the input swizzle for
    * that component.
    *
    * The size of some of the inputs may be given (i.e. non-zero) even
    * though output_size is zero; in that case, the inputs with a zero
    * size act per-component, while the inputs with non-zero size don't.
    */
   unsigned output_size;

   /**
    * The type of vector that the instruction outputs. Note that the
    * staurate modifier is only allowed on outputs with the float type.
    */

   nir_alu_type output_type;

   /**
    * The number of components in each input
    */
   unsigned input_sizes[4];

   /**
    * The type of vector that each input takes. Note that negate and
    * absolute value are only allowed on inputs with int or float type and
    * behave differently on the two.
    */
   nir_alu_type input_types[4];

   nir_op_algebraic_property algebraic_properties;
} nir_op_info;

extern const nir_op_info nir_op_infos[nir_num_opcodes];

typedef struct nir_alu_instr {
   nir_instr instr;
   nir_op op;
   nir_alu_dest dest;
   nir_alu_src src[];
} nir_alu_instr;

void nir_alu_src_copy(nir_alu_src *dest, const nir_alu_src *src,
                      nir_alu_instr *instr);
void nir_alu_dest_copy(nir_alu_dest *dest, const nir_alu_dest *src,
                       nir_alu_instr *instr);

/* is this source channel used? */
static inline bool
nir_alu_instr_channel_used(nir_alu_instr *instr, unsigned src, unsigned channel)
{
   if (nir_op_infos[instr->op].input_sizes[src] > 0)
      return channel < nir_op_infos[instr->op].input_sizes[src];

   return (instr->dest.write_mask >> channel) & 1;
}

/*
 * For instructions whose destinations are SSA, get the number of channels
 * used for a source
 */
static inline unsigned
nir_ssa_alu_instr_src_components(const nir_alu_instr *instr, unsigned src)
{
   assert(instr->dest.dest.is_ssa);

   if (nir_op_infos[instr->op].input_sizes[src] > 0)
      return nir_op_infos[instr->op].input_sizes[src];

   return instr->dest.dest.ssa.num_components;
}

typedef enum {
   nir_deref_type_var,
   nir_deref_type_array,
   nir_deref_type_struct
} nir_deref_type;

typedef struct nir_deref {
   nir_deref_type deref_type;
   struct nir_deref *child;
   const struct glsl_type *type;
} nir_deref;

typedef struct {
   nir_deref deref;

   nir_variable *var;
} nir_deref_var;

/* This enum describes how the array is referenced.  If the deref is
 * direct then the base_offset is used.  If the deref is indirect then then
 * offset is given by base_offset + indirect.  If the deref is a wildcard
 * then the deref refers to all of the elements of the array at the same
 * time.  Wildcard dereferences are only ever allowed in copy_var
 * intrinsics and the source and destination derefs must have matching
 * wildcards.
 */
typedef enum {
   nir_deref_array_type_direct,
   nir_deref_array_type_indirect,
   nir_deref_array_type_wildcard,
} nir_deref_array_type;

typedef struct {
   nir_deref deref;

   nir_deref_array_type deref_array_type;
   unsigned base_offset;
   nir_src indirect;
} nir_deref_array;

typedef struct {
   nir_deref deref;

   unsigned index;
} nir_deref_struct;

NIR_DEFINE_CAST(nir_deref_as_var, nir_deref, nir_deref_var, deref)
NIR_DEFINE_CAST(nir_deref_as_array, nir_deref, nir_deref_array, deref)
NIR_DEFINE_CAST(nir_deref_as_struct, nir_deref, nir_deref_struct, deref)

/* Returns the last deref in the chain. */
static inline nir_deref *
nir_deref_tail(nir_deref *deref)
{
   while (deref->child)
      deref = deref->child;
   return deref;
}

typedef struct {
   nir_instr instr;

   unsigned num_params;
   nir_deref_var **params;
   nir_deref_var *return_deref;

   struct nir_function_overload *callee;
} nir_call_instr;

#define INTRINSIC(name, num_srcs, src_components, has_dest, dest_components, \
                  num_variables, num_indices, flags) \
   nir_intrinsic_##name,

#define LAST_INTRINSIC(name) nir_last_intrinsic = nir_intrinsic_##name,

typedef enum {
#include "nir_intrinsics.h"
   nir_num_intrinsics = nir_last_intrinsic + 1
} nir_intrinsic_op;

#undef INTRINSIC
#undef LAST_INTRINSIC

/** Represents an intrinsic
 *
 * An intrinsic is an instruction type for handling things that are
 * more-or-less regular operations but don't just consume and produce SSA
 * values like ALU operations do.  Intrinsics are not for things that have
 * special semantic meaning such as phi nodes and parallel copies.
 * Examples of intrinsics include variable load/store operations, system
 * value loads, and the like.  Even though texturing more-or-less falls
 * under this category, texturing is its own instruction type because
 * trying to represent texturing with intrinsics would lead to a
 * combinatorial explosion of intrinsic opcodes.
 *
 * By having a single instruction type for handling a lot of different
 * cases, optimization passes can look for intrinsics and, for the most
 * part, completely ignore them.  Each intrinsic type also has a few
 * possible flags that govern whether or not they can be reordered or
 * eliminated.  That way passes like dead code elimination can still work
 * on intrisics without understanding the meaning of each.
 *
 * Each intrinsic has some number of constant indices, some number of
 * variables, and some number of sources.  What these sources, variables,
 * and indices mean depends on the intrinsic and is documented with the
 * intrinsic declaration in nir_intrinsics.h.  Intrinsics and texture
 * instructions are the only types of instruction that can operate on
 * variables.
 */
typedef struct {
   nir_instr instr;

   nir_intrinsic_op intrinsic;

   nir_dest dest;

   /** number of components if this is a vectorized intrinsic
    *
    * Similarly to ALU operations, some intrinsics are vectorized.
    * An intrinsic is vectorized if nir_intrinsic_infos.dest_components == 0.
    * For vectorized intrinsics, the num_components field specifies the
    * number of destination components and the number of source components
    * for all sources with nir_intrinsic_infos.src_components[i] == 0.
    */
   uint8_t num_components;

   int const_index[3];

   nir_deref_var *variables[2];

   nir_src src[];
} nir_intrinsic_instr;

/**
 * \name NIR intrinsics semantic flags
 *
 * information about what the compiler can do with the intrinsics.
 *
 * \sa nir_intrinsic_info::flags
 */
typedef enum {
   /**
    * whether the intrinsic can be safely eliminated if none of its output
    * value is not being used.
    */
   NIR_INTRINSIC_CAN_ELIMINATE = (1 << 0),

   /**
    * Whether the intrinsic can be reordered with respect to any other
    * intrinsic, i.e. whether the only reordering dependencies of the
    * intrinsic are due to the register reads/writes.
    */
   NIR_INTRINSIC_CAN_REORDER = (1 << 1),
} nir_intrinsic_semantic_flag;

#define NIR_INTRINSIC_MAX_INPUTS 4

typedef struct {
   const char *name;

   unsigned num_srcs; /** < number of register/SSA inputs */

   /** number of components of each input register
    *
    * If this value is 0, the number of components is given by the
    * num_components field of nir_intrinsic_instr.
    */
   unsigned src_components[NIR_INTRINSIC_MAX_INPUTS];

   bool has_dest;

   /** number of components of the output register
    *
    * If this value is 0, the number of components is given by the
    * num_components field of nir_intrinsic_instr.
    */
   unsigned dest_components;

   /** the number of inputs/outputs that are variables */
   unsigned num_variables;

   /** the number of constant indices used by the intrinsic */
   unsigned num_indices;

   /** semantic flags for calls to this intrinsic */
   nir_intrinsic_semantic_flag flags;
} nir_intrinsic_info;

extern const nir_intrinsic_info nir_intrinsic_infos[nir_num_intrinsics];

/**
 * \group texture information
 *
 * This gives semantic information about textures which is useful to the
 * frontend, the backend, and lowering passes, but not the optimizer.
 */

typedef enum {
   nir_tex_src_coord,
   nir_tex_src_projector,
   nir_tex_src_comparitor, /* shadow comparitor */
   nir_tex_src_offset,
   nir_tex_src_bias,
   nir_tex_src_lod,
   nir_tex_src_ms_index, /* MSAA sample index */
   nir_tex_src_ddx,
   nir_tex_src_ddy,
   nir_tex_src_texture_offset, /* < dynamically uniform indirect offset */
   nir_tex_src_sampler_offset, /* < dynamically uniform indirect offset */
   nir_num_tex_src_types
} nir_tex_src_type;

typedef struct {
   nir_src src;
   nir_tex_src_type src_type;
} nir_tex_src;

typedef enum {
   nir_texop_tex,                /**< Regular texture look-up */
   nir_texop_txb,                /**< Texture look-up with LOD bias */
   nir_texop_txl,                /**< Texture look-up with explicit LOD */
   nir_texop_txd,                /**< Texture look-up with partial derivatvies */
   nir_texop_txf,                /**< Texel fetch with explicit LOD */
   nir_texop_txf_ms,                /**< Multisample texture fetch */
   nir_texop_txs,                /**< Texture size */
   nir_texop_lod,                /**< Texture lod query */
   nir_texop_tg4,                /**< Texture gather */
   nir_texop_query_levels,       /**< Texture levels query */
   nir_texop_texture_samples,    /**< Texture samples query */
   nir_texop_samples_identical,  /**< Query whether all samples are definitely
                                  * identical.
                                  */
} nir_texop;

typedef struct {
   nir_instr instr;

   enum glsl_sampler_dim sampler_dim;
   nir_alu_type dest_type;

   nir_texop op;
   nir_dest dest;
   nir_tex_src *src;
   unsigned num_srcs, coord_components;
   bool is_array, is_shadow;

   /**
    * If is_shadow is true, whether this is the old-style shadow that outputs 4
    * components or the new-style shadow that outputs 1 component.
    */
   bool is_new_style_shadow;

   /* constant offset - must be 0 if the offset source is used */
   int const_offset[4];

   /* gather component selector */
   unsigned component : 2;

   /** The texture index
    *
    * If this texture instruction has a nir_tex_src_texture_offset source,
    * then the texture index is given by texture_index + texture_offset.
    */
   unsigned texture_index;

   /** The size of the texture array or 0 if it's not an array */
   unsigned texture_array_size;

   /** The texture deref
    *
    * If both this and `sampler` are both NULL, use texture_index instead.
    * If `texture` is NULL, but `sampler` is non-NULL, then the texture is
    * implied from the sampler.
    */
   nir_deref_var *texture;

   /** The sampler index
    *
    * If this texture instruction has a nir_tex_src_sampler_offset source,
    * then the sampler index is given by sampler_index + sampler_offset.
    */
   unsigned sampler_index;

   /** The sampler deref
    *
    * If this is null, use sampler_index instead.
    */
   nir_deref_var *sampler;
} nir_tex_instr;

static inline unsigned
nir_tex_instr_dest_size(nir_tex_instr *instr)
{
   switch (instr->op) {
   case nir_texop_txs: {
      unsigned ret;
      switch (instr->sampler_dim) {
         case GLSL_SAMPLER_DIM_1D:
         case GLSL_SAMPLER_DIM_BUF:
            ret = 1;
            break;
         case GLSL_SAMPLER_DIM_2D:
         case GLSL_SAMPLER_DIM_CUBE:
         case GLSL_SAMPLER_DIM_MS:
         case GLSL_SAMPLER_DIM_RECT:
         case GLSL_SAMPLER_DIM_EXTERNAL:
            ret = 2;
            break;
         case GLSL_SAMPLER_DIM_3D:
            ret = 3;
            break;
         default:
            unreachable("not reached");
      }
      if (instr->is_array)
         ret++;
      return ret;
   }

   case nir_texop_lod:
      return 2;

   case nir_texop_texture_samples:
   case nir_texop_query_levels:
   case nir_texop_samples_identical:
      return 1;

   default:
      if (instr->is_shadow && instr->is_new_style_shadow)
         return 1;

      return 4;
   }
}

/* Returns true if this texture operation queries something about the texture
 * rather than actually sampling it.
 */
static inline bool
nir_tex_instr_is_query(nir_tex_instr *instr)
{
   switch (instr->op) {
   case nir_texop_txs:
   case nir_texop_lod:
   case nir_texop_texture_samples:
   case nir_texop_query_levels:
      return true;
   case nir_texop_tex:
   case nir_texop_txb:
   case nir_texop_txl:
   case nir_texop_txd:
   case nir_texop_txf:
   case nir_texop_txf_ms:
   case nir_texop_tg4:
      return false;
   default:
      unreachable("Invalid texture opcode");
   }
}

static inline unsigned
nir_tex_instr_src_size(nir_tex_instr *instr, unsigned src)
{
   if (instr->src[src].src_type == nir_tex_src_coord)
      return instr->coord_components;


   if (instr->src[src].src_type == nir_tex_src_offset ||
       instr->src[src].src_type == nir_tex_src_ddx ||
       instr->src[src].src_type == nir_tex_src_ddy) {
      if (instr->is_array)
         return instr->coord_components - 1;
      else
         return instr->coord_components;
   }

   return 1;
}

static inline int
nir_tex_instr_src_index(nir_tex_instr *instr, nir_tex_src_type type)
{
   for (unsigned i = 0; i < instr->num_srcs; i++)
      if (instr->src[i].src_type == type)
         return (int) i;

   return -1;
}

typedef struct {
   union {
      float f[4];
      int32_t i[4];
      uint32_t u[4];
   };
} nir_const_value;

typedef struct {
   nir_instr instr;

   nir_const_value value;

   nir_ssa_def def;
} nir_load_const_instr;

typedef enum {
   nir_jump_return,
   nir_jump_break,
   nir_jump_continue,
} nir_jump_type;

typedef struct {
   nir_instr instr;
   nir_jump_type type;
} nir_jump_instr;

/* creates a new SSA variable in an undefined state */

typedef struct {
   nir_instr instr;
   nir_ssa_def def;
} nir_ssa_undef_instr;

typedef struct {
   struct exec_node node;

   /* The predecessor block corresponding to this source */
   struct nir_block *pred;

   nir_src src;
} nir_phi_src;

#define nir_foreach_phi_src(phi, entry) \
   foreach_list_typed(nir_phi_src, entry, node, &(phi)->srcs)
#define nir_foreach_phi_src_safe(phi, entry) \
   foreach_list_typed_safe(nir_phi_src, entry, node, &(phi)->srcs)

typedef struct {
   nir_instr instr;

   struct exec_list srcs; /** < list of nir_phi_src */

   nir_dest dest;
} nir_phi_instr;

typedef struct {
   struct exec_node node;
   nir_src src;
   nir_dest dest;
} nir_parallel_copy_entry;

#define nir_foreach_parallel_copy_entry(pcopy, entry) \
   foreach_list_typed(nir_parallel_copy_entry, entry, node, &(pcopy)->entries)

typedef struct {
   nir_instr instr;

   /* A list of nir_parallel_copy_entry's.  The sources of all of the
    * entries are copied to the corresponding destinations "in parallel".
    * In other words, if we have two entries: a -> b and b -> a, the values
    * get swapped.
    */
   struct exec_list entries;
} nir_parallel_copy_instr;

NIR_DEFINE_CAST(nir_instr_as_alu, nir_instr, nir_alu_instr, instr)
NIR_DEFINE_CAST(nir_instr_as_call, nir_instr, nir_call_instr, instr)
NIR_DEFINE_CAST(nir_instr_as_jump, nir_instr, nir_jump_instr, instr)
NIR_DEFINE_CAST(nir_instr_as_tex, nir_instr, nir_tex_instr, instr)
NIR_DEFINE_CAST(nir_instr_as_intrinsic, nir_instr, nir_intrinsic_instr, instr)
NIR_DEFINE_CAST(nir_instr_as_load_const, nir_instr, nir_load_const_instr, instr)
NIR_DEFINE_CAST(nir_instr_as_ssa_undef, nir_instr, nir_ssa_undef_instr, instr)
NIR_DEFINE_CAST(nir_instr_as_phi, nir_instr, nir_phi_instr, instr)
NIR_DEFINE_CAST(nir_instr_as_parallel_copy, nir_instr,
                nir_parallel_copy_instr, instr)

/*
 * Control flow
 *
 * Control flow consists of a tree of control flow nodes, which include
 * if-statements and loops. The leaves of the tree are basic blocks, lists of
 * instructions that always run start-to-finish. Each basic block also keeps
 * track of its successors (blocks which may run immediately after the current
 * block) and predecessors (blocks which could have run immediately before the
 * current block). Each function also has a start block and an end block which
 * all return statements point to (which is always empty). Together, all the
 * blocks with their predecessors and successors make up the control flow
 * graph (CFG) of the function. There are helpers that modify the tree of
 * control flow nodes while modifying the CFG appropriately; these should be
 * used instead of modifying the tree directly.
 */

typedef enum {
   nir_cf_node_block,
   nir_cf_node_if,
   nir_cf_node_loop,
   nir_cf_node_function
} nir_cf_node_type;

typedef struct nir_cf_node {
   struct exec_node node;
   nir_cf_node_type type;
   struct nir_cf_node *parent;
} nir_cf_node;

typedef struct nir_block {
   nir_cf_node cf_node;

   struct exec_list instr_list; /** < list of nir_instr */

   /** generic block index; generated by nir_index_blocks */
   unsigned index;

   /*
    * Each block can only have up to 2 successors, so we put them in a simple
    * array - no need for anything more complicated.
    */
   struct nir_block *successors[2];

   /* Set of nir_block predecessors in the CFG */
   struct set *predecessors;

   /*
    * this node's immediate dominator in the dominance tree - set to NULL for
    * the start block.
    */
   struct nir_block *imm_dom;

   /* This node's children in the dominance tree */
   unsigned num_dom_children;
   struct nir_block **dom_children;

   /* Set of nir_block's on the dominance frontier of this block */
   struct set *dom_frontier;

   /*
    * These two indices have the property that dom_{pre,post}_index for each
    * child of this block in the dominance tree will always be between
    * dom_pre_index and dom_post_index for this block, which makes testing if
    * a given block is dominated by another block an O(1) operation.
    */
   unsigned dom_pre_index, dom_post_index;

   /* live in and out for this block; used for liveness analysis */
   BITSET_WORD *live_in;
   BITSET_WORD *live_out;
} nir_block;

static inline nir_instr *
nir_block_first_instr(nir_block *block)
{
   struct exec_node *head = exec_list_get_head(&block->instr_list);
   return exec_node_data(nir_instr, head, node);
}

static inline nir_instr *
nir_block_last_instr(nir_block *block)
{
   struct exec_node *tail = exec_list_get_tail(&block->instr_list);
   return exec_node_data(nir_instr, tail, node);
}

#define nir_foreach_instr(block, instr) \
   foreach_list_typed(nir_instr, instr, node, &(block)->instr_list)
#define nir_foreach_instr_reverse(block, instr) \
   foreach_list_typed_reverse(nir_instr, instr, node, &(block)->instr_list)
#define nir_foreach_instr_safe(block, instr) \
   foreach_list_typed_safe(nir_instr, instr, node, &(block)->instr_list)
#define nir_foreach_instr_reverse_safe(block, instr) \
   foreach_list_typed_reverse_safe(nir_instr, instr, node, &(block)->instr_list)

typedef struct nir_if {
   nir_cf_node cf_node;
   nir_src condition;

   struct exec_list then_list; /** < list of nir_cf_node */
   struct exec_list else_list; /** < list of nir_cf_node */
} nir_if;

static inline nir_cf_node *
nir_if_first_then_node(nir_if *if_stmt)
{
   struct exec_node *head = exec_list_get_head(&if_stmt->then_list);
   return exec_node_data(nir_cf_node, head, node);
}

static inline nir_cf_node *
nir_if_last_then_node(nir_if *if_stmt)
{
   struct exec_node *tail = exec_list_get_tail(&if_stmt->then_list);
   return exec_node_data(nir_cf_node, tail, node);
}

static inline nir_cf_node *
nir_if_first_else_node(nir_if *if_stmt)
{
   struct exec_node *head = exec_list_get_head(&if_stmt->else_list);
   return exec_node_data(nir_cf_node, head, node);
}

static inline nir_cf_node *
nir_if_last_else_node(nir_if *if_stmt)
{
   struct exec_node *tail = exec_list_get_tail(&if_stmt->else_list);
   return exec_node_data(nir_cf_node, tail, node);
}

typedef struct {
   nir_cf_node cf_node;

   struct exec_list body; /** < list of nir_cf_node */
} nir_loop;

static inline nir_cf_node *
nir_loop_first_cf_node(nir_loop *loop)
{
   return exec_node_data(nir_cf_node, exec_list_get_head(&loop->body), node);
}

static inline nir_cf_node *
nir_loop_last_cf_node(nir_loop *loop)
{
   return exec_node_data(nir_cf_node, exec_list_get_tail(&loop->body), node);
}

/**
 * Various bits of metadata that can may be created or required by
 * optimization and analysis passes
 */
typedef enum {
   nir_metadata_none = 0x0,
   nir_metadata_block_index = 0x1,
   nir_metadata_dominance = 0x2,
   nir_metadata_live_ssa_defs = 0x4,
   nir_metadata_not_properly_reset = 0x8,
} nir_metadata;

typedef struct {
   nir_cf_node cf_node;

   /** pointer to the overload of which this is an implementation */
   struct nir_function_overload *overload;

   struct exec_list body; /** < list of nir_cf_node */

   nir_block *end_block;

   /** list for all local variables in the function */
   struct exec_list locals;

   /** array of variables used as parameters */
   unsigned num_params;
   nir_variable **params;

   /** variable used to hold the result of the function */
   nir_variable *return_var;

   /** list of local registers in the function */
   struct exec_list registers;

   /** next available local register index */
   unsigned reg_alloc;

   /** next available SSA value index */
   unsigned ssa_alloc;

   /* total number of basic blocks, only valid when block_index_dirty = false */
   unsigned num_blocks;

   nir_metadata valid_metadata;
} nir_function_impl;

static inline nir_block *
nir_start_block(nir_function_impl *impl)
{
   return (nir_block *) exec_list_get_head(&impl->body);
}

static inline nir_cf_node *
nir_cf_node_next(nir_cf_node *node)
{
   struct exec_node *next = exec_node_get_next(&node->node);
   if (exec_node_is_tail_sentinel(next))
      return NULL;
   else
      return exec_node_data(nir_cf_node, next, node);
}

static inline nir_cf_node *
nir_cf_node_prev(nir_cf_node *node)
{
   struct exec_node *prev = exec_node_get_prev(&node->node);
   if (exec_node_is_head_sentinel(prev))
      return NULL;
   else
      return exec_node_data(nir_cf_node, prev, node);
}

static inline bool
nir_cf_node_is_first(const nir_cf_node *node)
{
   return exec_node_is_head_sentinel(node->node.prev);
}

static inline bool
nir_cf_node_is_last(const nir_cf_node *node)
{
   return exec_node_is_tail_sentinel(node->node.next);
}

NIR_DEFINE_CAST(nir_cf_node_as_block, nir_cf_node, nir_block, cf_node)
NIR_DEFINE_CAST(nir_cf_node_as_if, nir_cf_node, nir_if, cf_node)
NIR_DEFINE_CAST(nir_cf_node_as_loop, nir_cf_node, nir_loop, cf_node)
NIR_DEFINE_CAST(nir_cf_node_as_function, nir_cf_node, nir_function_impl, cf_node)

typedef enum {
   nir_parameter_in,
   nir_parameter_out,
   nir_parameter_inout,
} nir_parameter_type;

typedef struct {
   nir_parameter_type param_type;
   const struct glsl_type *type;
} nir_parameter;

typedef struct nir_function_overload {
   struct exec_node node;

   unsigned num_params;
   nir_parameter *params;
   const struct glsl_type *return_type;

   nir_function_impl *impl; /** < NULL if the overload is only declared yet */

   /** pointer to the function of which this is an overload */
   struct nir_function *function;
} nir_function_overload;

typedef struct nir_function {
   struct exec_node node;

   struct exec_list overload_list; /** < list of nir_function_overload */
   const char *name;
   struct nir_shader *shader;
} nir_function;

#define nir_function_first_overload(func) \
   exec_node_data(nir_function_overload, \
                  exec_list_get_head(&(func)->overload_list), node)

typedef struct nir_shader_compiler_options {
   bool lower_ffma;
   bool lower_fdiv;
   bool lower_flrp;
   bool lower_fpow;
   bool lower_fsat;
   bool lower_fsqrt;
   /** lowers fneg and ineg to fsub and isub. */
   bool lower_negate;
   /** lowers fsub and isub to fadd+fneg and iadd+ineg. */
   bool lower_sub;

   /* lower {slt,sge,seq,sne} to {flt,fge,feq,fne} + b2f: */
   bool lower_scmp;

   /* Does the native fdot instruction replicate its result for four
    * components?  If so, then opt_algebraic_late will turn all fdotN
    * instructions into fdot_replicatedN instructions.
    */
   bool fdot_replicates;

   /** lowers ffract to fsub+ffloor: */
   bool lower_ffract;

   /**
    * Does the driver support real 32-bit integers?  (Otherwise, integers
    * are simulated by floats.)
    */
   bool native_integers;
} nir_shader_compiler_options;

typedef struct nir_shader_info {
   const char *name;

   /* Descriptive name provided by the client; may be NULL */
   const char *label;

   /* Number of textures used by this shader */
   unsigned num_textures;
   /* Number of uniform buffers used by this shader */
   unsigned num_ubos;
   /* Number of atomic buffers used by this shader */
   unsigned num_abos;
   /* Number of shader storage buffers used by this shader */
   unsigned num_ssbos;
   /* Number of images used by this shader */
   unsigned num_images;

   /* Which inputs are actually read */
   uint64_t inputs_read;
   /* Which outputs are actually written */
   uint64_t outputs_written;
   /* Which system values are actually read */
   uint64_t system_values_read;

   /* Which patch inputs are actually read */
   uint32_t patch_inputs_read;
   /* Which patch outputs are actually written */
   uint32_t patch_outputs_written;

   /* Whether or not this shader ever uses textureGather() */
   bool uses_texture_gather;

   /* Whether or not this shader uses the gl_ClipDistance output */
   bool uses_clip_distance_out;

   /* Whether or not separate shader objects were used */
   bool separate_shader;

   /** Was this shader linked with any transform feedback varyings? */
   bool has_transform_feedback_varyings;

   union {
      struct {
         /** The number of vertices recieves per input primitive */
         unsigned vertices_in;

         /** The output primitive type (GL enum value) */
         unsigned output_primitive;

         /** The maximum number of vertices the geometry shader might write. */
         unsigned vertices_out;

         /** 1 .. MAX_GEOMETRY_SHADER_INVOCATIONS */
         unsigned invocations;

         /** Whether or not this shader uses EndPrimitive */
         bool uses_end_primitive;

         /** Whether or not this shader uses non-zero streams */
         bool uses_streams;
      } gs;

      struct {
         bool uses_discard;

         /**
          * Whether early fragment tests are enabled as defined by
          * ARB_shader_image_load_store.
          */
         bool early_fragment_tests;

         /** gl_FragDepth layout for ARB_conservative_depth. */
         enum gl_frag_depth_layout depth_layout;
      } fs;

      struct {
         unsigned local_size[3];
      } cs;

      struct {
         /** The number of vertices in the TCS output patch. */
         unsigned vertices_out;
      } tcs;
   };
} nir_shader_info;

typedef struct nir_shader {
   /** list of uniforms (nir_variable) */
   struct exec_list uniforms;

   /** list of inputs (nir_variable) */
   struct exec_list inputs;

   /** list of outputs (nir_variable) */
   struct exec_list outputs;

   /** Set of driver-specific options for the shader.
    *
    * The memory for the options is expected to be kept in a single static
    * copy by the driver.
    */
   const struct nir_shader_compiler_options *options;

   /** Various bits of compile-time information about a given shader */
   struct nir_shader_info info;

   /** list of global variables in the shader (nir_variable) */
   struct exec_list globals;

   /** list of system value variables in the shader (nir_variable) */
   struct exec_list system_values;

   struct exec_list functions; /** < list of nir_function */

   /** list of global register in the shader */
   struct exec_list registers;

   /** next available global register index */
   unsigned reg_alloc;

   /**
    * the highest index a load_input_*, load_uniform_*, etc. intrinsic can
    * access plus one
    */
   unsigned num_inputs, num_uniforms, num_outputs;

   /** The shader stage, such as MESA_SHADER_VERTEX. */
   gl_shader_stage stage;
} nir_shader;

#define nir_foreach_overload(shader, overload)                        \
   foreach_list_typed(nir_function, func, node, &(shader)->functions) \
      foreach_list_typed(nir_function_overload, overload, node, \
                         &(func)->overload_list)

nir_shader *nir_shader_create(void *mem_ctx,
                              gl_shader_stage stage,
                              const nir_shader_compiler_options *options);

/** creates a register, including assigning it an index and adding it to the list */
nir_register *nir_global_reg_create(nir_shader *shader);

nir_register *nir_local_reg_create(nir_function_impl *impl);

void nir_reg_remove(nir_register *reg);

/** Adds a variable to the appropreate list in nir_shader */
void nir_shader_add_variable(nir_shader *shader, nir_variable *var);

static inline void
nir_function_impl_add_variable(nir_function_impl *impl, nir_variable *var)
{
   assert(var->data.mode == nir_var_local);
   exec_list_push_tail(&impl->locals, &var->node);
}

/** creates a variable, sets a few defaults, and adds it to the list */
nir_variable *nir_variable_create(nir_shader *shader,
                                  nir_variable_mode mode,
                                  const struct glsl_type *type,
                                  const char *name);
/** creates a local variable and adds it to the list */
nir_variable *nir_local_variable_create(nir_function_impl *impl,
                                        const struct glsl_type *type,
                                        const char *name);

/** creates a function and adds it to the shader's list of functions */
nir_function *nir_function_create(nir_shader *shader, const char *name);

/** creates a null function returning null */
nir_function_overload *nir_function_overload_create(nir_function *func);

nir_function_impl *nir_function_impl_create(nir_function_overload *func);
/** creates a function_impl that isn't tied to any particular overload */
nir_function_impl *nir_function_impl_create_bare(nir_shader *shader);

nir_block *nir_block_create(nir_shader *shader);
nir_if *nir_if_create(nir_shader *shader);
nir_loop *nir_loop_create(nir_shader *shader);

nir_function_impl *nir_cf_node_get_function(nir_cf_node *node);

/** requests that the given pieces of metadata be generated */
void nir_metadata_require(nir_function_impl *impl, nir_metadata required);
/** dirties all but the preserved metadata */
void nir_metadata_preserve(nir_function_impl *impl, nir_metadata preserved);

/** creates an instruction with default swizzle/writemask/etc. with NULL registers */
nir_alu_instr *nir_alu_instr_create(nir_shader *shader, nir_op op);

nir_jump_instr *nir_jump_instr_create(nir_shader *shader, nir_jump_type type);

nir_load_const_instr *nir_load_const_instr_create(nir_shader *shader,
                                                  unsigned num_components);

nir_intrinsic_instr *nir_intrinsic_instr_create(nir_shader *shader,
                                                nir_intrinsic_op op);

nir_call_instr *nir_call_instr_create(nir_shader *shader,
                                      nir_function_overload *callee);

nir_tex_instr *nir_tex_instr_create(nir_shader *shader, unsigned num_srcs);

nir_phi_instr *nir_phi_instr_create(nir_shader *shader);

nir_parallel_copy_instr *nir_parallel_copy_instr_create(nir_shader *shader);

nir_ssa_undef_instr *nir_ssa_undef_instr_create(nir_shader *shader,
                                                unsigned num_components);

nir_deref_var *nir_deref_var_create(void *mem_ctx, nir_variable *var);
nir_deref_array *nir_deref_array_create(void *mem_ctx);
nir_deref_struct *nir_deref_struct_create(void *mem_ctx, unsigned field_index);

nir_deref *nir_copy_deref(void *mem_ctx, nir_deref *deref);

nir_load_const_instr *
nir_deref_get_const_initializer_load(nir_shader *shader, nir_deref_var *deref);

/**
 * NIR Cursors and Instruction Insertion API
 * @{
 *
 * A tiny struct representing a point to insert/extract instructions or
 * control flow nodes.  Helps reduce the combinatorial explosion of possible
 * points to insert/extract.
 *
 * \sa nir_control_flow.h
 */
typedef enum {
   nir_cursor_before_block,
   nir_cursor_after_block,
   nir_cursor_before_instr,
   nir_cursor_after_instr,
} nir_cursor_option;

typedef struct {
   nir_cursor_option option;
   union {
      nir_block *block;
      nir_instr *instr;
   };
} nir_cursor;

static inline nir_block *
nir_cursor_current_block(nir_cursor cursor)
{
   if (cursor.option == nir_cursor_before_instr ||
       cursor.option == nir_cursor_after_instr) {
      return cursor.instr->block;
   } else {
      return cursor.block;
   }
}

bool nir_cursors_equal(nir_cursor a, nir_cursor b);

static inline nir_cursor
nir_before_block(nir_block *block)
{
   nir_cursor cursor;
   cursor.option = nir_cursor_before_block;
   cursor.block = block;
   return cursor;
}

static inline nir_cursor
nir_after_block(nir_block *block)
{
   nir_cursor cursor;
   cursor.option = nir_cursor_after_block;
   cursor.block = block;
   return cursor;
}

static inline nir_cursor
nir_before_instr(nir_instr *instr)
{
   nir_cursor cursor;
   cursor.option = nir_cursor_before_instr;
   cursor.instr = instr;
   return cursor;
}

static inline nir_cursor
nir_after_instr(nir_instr *instr)
{
   nir_cursor cursor;
   cursor.option = nir_cursor_after_instr;
   cursor.instr = instr;
   return cursor;
}

static inline nir_cursor
nir_after_block_before_jump(nir_block *block)
{
   nir_instr *last_instr = nir_block_last_instr(block);
   if (last_instr && last_instr->type == nir_instr_type_jump) {
      return nir_before_instr(last_instr);
   } else {
      return nir_after_block(block);
   }
}

static inline nir_cursor
nir_before_cf_node(nir_cf_node *node)
{
   if (node->type == nir_cf_node_block)
      return nir_before_block(nir_cf_node_as_block(node));

   return nir_after_block(nir_cf_node_as_block(nir_cf_node_prev(node)));
}

static inline nir_cursor
nir_after_cf_node(nir_cf_node *node)
{
   if (node->type == nir_cf_node_block)
      return nir_after_block(nir_cf_node_as_block(node));

   return nir_before_block(nir_cf_node_as_block(nir_cf_node_next(node)));
}

static inline nir_cursor
nir_before_cf_list(struct exec_list *cf_list)
{
   nir_cf_node *first_node = exec_node_data(nir_cf_node,
                                            exec_list_get_head(cf_list), node);
   return nir_before_cf_node(first_node);
}

static inline nir_cursor
nir_after_cf_list(struct exec_list *cf_list)
{
   nir_cf_node *last_node = exec_node_data(nir_cf_node,
                                           exec_list_get_tail(cf_list), node);
   return nir_after_cf_node(last_node);
}

/**
 * Insert a NIR instruction at the given cursor.
 *
 * Note: This does not update the cursor.
 */
void nir_instr_insert(nir_cursor cursor, nir_instr *instr);

static inline void
nir_instr_insert_before(nir_instr *instr, nir_instr *before)
{
   nir_instr_insert(nir_before_instr(instr), before);
}

static inline void
nir_instr_insert_after(nir_instr *instr, nir_instr *after)
{
   nir_instr_insert(nir_after_instr(instr), after);
}

static inline void
nir_instr_insert_before_block(nir_block *block, nir_instr *before)
{
   nir_instr_insert(nir_before_block(block), before);
}

static inline void
nir_instr_insert_after_block(nir_block *block, nir_instr *after)
{
   nir_instr_insert(nir_after_block(block), after);
}

static inline void
nir_instr_insert_before_cf(nir_cf_node *node, nir_instr *before)
{
   nir_instr_insert(nir_before_cf_node(node), before);
}

static inline void
nir_instr_insert_after_cf(nir_cf_node *node, nir_instr *after)
{
   nir_instr_insert(nir_after_cf_node(node), after);
}

static inline void
nir_instr_insert_before_cf_list(struct exec_list *list, nir_instr *before)
{
   nir_instr_insert(nir_before_cf_list(list), before);
}

static inline void
nir_instr_insert_after_cf_list(struct exec_list *list, nir_instr *after)
{
   nir_instr_insert(nir_after_cf_list(list), after);
}

void nir_instr_remove(nir_instr *instr);

/** @} */

typedef bool (*nir_foreach_ssa_def_cb)(nir_ssa_def *def, void *state);
typedef bool (*nir_foreach_dest_cb)(nir_dest *dest, void *state);
typedef bool (*nir_foreach_src_cb)(nir_src *src, void *state);
bool nir_foreach_ssa_def(nir_instr *instr, nir_foreach_ssa_def_cb cb,
                         void *state);
bool nir_foreach_dest(nir_instr *instr, nir_foreach_dest_cb cb, void *state);
bool nir_foreach_src(nir_instr *instr, nir_foreach_src_cb cb, void *state);

nir_const_value *nir_src_as_const_value(nir_src src);
bool nir_src_is_dynamically_uniform(nir_src src);
bool nir_srcs_equal(nir_src src1, nir_src src2);
void nir_instr_rewrite_src(nir_instr *instr, nir_src *src, nir_src new_src);
void nir_instr_move_src(nir_instr *dest_instr, nir_src *dest, nir_src *src);
void nir_if_rewrite_condition(nir_if *if_stmt, nir_src new_src);
void nir_instr_rewrite_dest(nir_instr *instr, nir_dest *dest,
                            nir_dest new_dest);

void nir_ssa_dest_init(nir_instr *instr, nir_dest *dest,
                       unsigned num_components, const char *name);
void nir_ssa_def_init(nir_instr *instr, nir_ssa_def *def,
                      unsigned num_components, const char *name);
void nir_ssa_def_rewrite_uses(nir_ssa_def *def, nir_src new_src);
void nir_ssa_def_rewrite_uses_after(nir_ssa_def *def, nir_src new_src,
                                    nir_instr *after_me);

/* visits basic blocks in source-code order */
typedef bool (*nir_foreach_block_cb)(nir_block *block, void *state);
bool nir_foreach_block(nir_function_impl *impl, nir_foreach_block_cb cb,
                       void *state);
bool nir_foreach_block_reverse(nir_function_impl *impl, nir_foreach_block_cb cb,
                               void *state);
bool nir_foreach_block_in_cf_node(nir_cf_node *node, nir_foreach_block_cb cb,
                                  void *state);

/* If the following CF node is an if, this function returns that if.
 * Otherwise, it returns NULL.
 */
nir_if *nir_block_get_following_if(nir_block *block);

nir_loop *nir_block_get_following_loop(nir_block *block);

void nir_index_local_regs(nir_function_impl *impl);
void nir_index_global_regs(nir_shader *shader);
void nir_index_ssa_defs(nir_function_impl *impl);
unsigned nir_index_instrs(nir_function_impl *impl);

void nir_index_blocks(nir_function_impl *impl);

void nir_print_shader(nir_shader *shader, FILE *fp);
void nir_print_instr(const nir_instr *instr, FILE *fp);

nir_shader *nir_shader_clone(void *mem_ctx, const nir_shader *s);
nir_function_impl *nir_function_impl_clone(const nir_function_impl *impl);

#ifdef DEBUG
void nir_validate_shader(nir_shader *shader);
void nir_metadata_set_validation_flag(nir_shader *shader);
void nir_metadata_check_validation_flag(nir_shader *shader);
#else
static inline void nir_validate_shader(nir_shader *shader) { (void) shader; }
static inline void nir_metadata_set_validation_flag(nir_shader *shader) { (void) shader; }
static inline void nir_metadata_check_validation_flag(nir_shader *shader) { (void) shader; }
#endif /* DEBUG */

void nir_calc_dominance_impl(nir_function_impl *impl);
void nir_calc_dominance(nir_shader *shader);

nir_block *nir_dominance_lca(nir_block *b1, nir_block *b2);
bool nir_block_dominates(nir_block *parent, nir_block *child);

void nir_dump_dom_tree_impl(nir_function_impl *impl, FILE *fp);
void nir_dump_dom_tree(nir_shader *shader, FILE *fp);

void nir_dump_dom_frontier_impl(nir_function_impl *impl, FILE *fp);
void nir_dump_dom_frontier(nir_shader *shader, FILE *fp);

void nir_dump_cfg_impl(nir_function_impl *impl, FILE *fp);
void nir_dump_cfg(nir_shader *shader, FILE *fp);

int nir_gs_count_vertices(const nir_shader *shader);

bool nir_split_var_copies(nir_shader *shader);

bool nir_lower_returns_impl(nir_function_impl *impl);
bool nir_lower_returns(nir_shader *shader);

bool nir_inline_functions_impl(nir_function_impl *impl);
bool nir_inline_functions(nir_shader *shader);

void nir_lower_var_copy_instr(nir_intrinsic_instr *copy, void *mem_ctx);
void nir_lower_var_copies(nir_shader *shader);

bool nir_lower_global_vars_to_local(nir_shader *shader);

bool nir_lower_locals_to_regs(nir_shader *shader);

void nir_lower_outputs_to_temporaries(nir_shader *shader);

void nir_lower_outputs_to_temporaries(nir_shader *shader);

void nir_shader_gather_info(nir_shader *shader, nir_function_impl *entrypoint);

void nir_assign_var_locations(struct exec_list *var_list,
                              unsigned *size,
                              int (*type_size)(const struct glsl_type *));

void nir_lower_io(nir_shader *shader,
                  nir_variable_mode mode,
                  int (*type_size)(const struct glsl_type *));
nir_src *nir_get_io_offset_src(nir_intrinsic_instr *instr);
nir_src *nir_get_io_vertex_index_src(nir_intrinsic_instr *instr);

void nir_lower_vars_to_ssa(nir_shader *shader);

bool nir_remove_dead_variables(nir_shader *shader);

void nir_move_vec_src_uses_to_dest(nir_shader *shader);
bool nir_lower_vec_to_movs(nir_shader *shader);
void nir_lower_alu_to_scalar(nir_shader *shader);
void nir_lower_load_const_to_scalar(nir_shader *shader);

void nir_lower_phis_to_scalar(nir_shader *shader);

void nir_lower_samplers(nir_shader *shader,
                        const struct gl_shader_program *shader_program);

bool nir_lower_system_values(nir_shader *shader);

typedef struct nir_lower_tex_options {
   /**
    * bitmask of (1 << GLSL_SAMPLER_DIM_x) to control for which
    * sampler types a texture projector is lowered.
    */
   unsigned lower_txp;

   /**
    * If true, lower rect textures to 2D, using txs to fetch the
    * texture dimensions and dividing the texture coords by the
    * texture dims to normalize.
    */
   bool lower_rect;

   /**
    * To emulate certain texture wrap modes, this can be used
    * to saturate the specified tex coord to [0.0, 1.0].  The
    * bits are according to sampler #, ie. if, for example:
    *
    *   (conf->saturate_s & (1 << n))
    *
    * is true, then the s coord for sampler n is saturated.
    *
    * Note that clamping must happen *after* projector lowering
    * so any projected texture sample instruction with a clamped
    * coordinate gets automatically lowered, regardless of the
    * 'lower_txp' setting.
    */
   unsigned saturate_s;
   unsigned saturate_t;
   unsigned saturate_r;

   /* Bitmask of samplers that need swizzling.
    *
    * If (swizzle_result & (1 << sampler_index)), then the swizzle in
    * swizzles[sampler_index] is applied to the result of the texturing
    * operation.
    */
   unsigned swizzle_result;

   /* A swizzle for each sampler.  Values 0-3 represent x, y, z, or w swizzles
    * while 4 and 5 represent 0 and 1 respectively.
    */
   uint8_t swizzles[32][4];
} nir_lower_tex_options;

bool nir_lower_tex(nir_shader *shader,
                   const nir_lower_tex_options *options);

void nir_lower_idiv(nir_shader *shader);

void nir_lower_clip_vs(nir_shader *shader, unsigned ucp_enables);
void nir_lower_clip_fs(nir_shader *shader, unsigned ucp_enables);

void nir_lower_two_sided_color(nir_shader *shader);

void nir_lower_atomics(nir_shader *shader,
                       const struct gl_shader_program *shader_program);
void nir_lower_to_source_mods(nir_shader *shader);

bool nir_lower_gs_intrinsics(nir_shader *shader);

bool nir_normalize_cubemap_coords(nir_shader *shader);

void nir_live_ssa_defs_impl(nir_function_impl *impl);
bool nir_ssa_defs_interfere(nir_ssa_def *a, nir_ssa_def *b);

void nir_convert_to_ssa_impl(nir_function_impl *impl);
void nir_convert_to_ssa(nir_shader *shader);

/* If phi_webs_only is true, only convert SSA values involved in phi nodes to
 * registers.  If false, convert all values (even those not involved in a phi
 * node) to registers.
 */
void nir_convert_from_ssa(nir_shader *shader, bool phi_webs_only);

bool nir_opt_algebraic(nir_shader *shader);
bool nir_opt_algebraic_late(nir_shader *shader);
bool nir_opt_constant_folding(nir_shader *shader);

bool nir_opt_global_to_local(nir_shader *shader);

bool nir_copy_prop(nir_shader *shader);

bool nir_opt_cse(nir_shader *shader);

bool nir_opt_dce(nir_shader *shader);

bool nir_opt_dead_cf(nir_shader *shader);

void nir_opt_gcm(nir_shader *shader);

bool nir_opt_peephole_select(nir_shader *shader);

bool nir_opt_remove_phis(nir_shader *shader);

bool nir_opt_undef(nir_shader *shader);

void nir_sweep(nir_shader *shader);

nir_intrinsic_op nir_intrinsic_from_system_value(gl_system_value val);
gl_system_value nir_system_value_from_intrinsic(nir_intrinsic_op intrin);

#ifdef __cplusplus
} /* extern "C" */
#endif