summaryrefslogtreecommitdiff
path: root/src/mesa/shader/slang/library/slang_common_builtin.gc
blob: 9764fc25b0916705e1837f2ea8a44376e51aef04 (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
/*
 * Mesa 3-D graphics library
 * Version:  7.3
 *
 * Copyright (C) 2006  Brian Paul   All Rights Reserved.
 * Copyright (C) 2008  VMware, Inc.  All Rights Reserved.
 *
 * 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 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
 * BRIAN PAUL 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.
 */

//
// From Shader Spec, ver. 1.10, rev. 59
//

// Note: the values assigned to these constants here aren't actually used.
// They're set by the compiler according to the GL context limits.
// See slang_simplify.c
const int gl_MaxLights = 8;
const int gl_MaxClipPlanes = 6;
const int gl_MaxTextureUnits = 8;
const int gl_MaxTextureCoords = 8;
const int gl_MaxVertexAttribs = 16;
const int gl_MaxVertexUniformComponents = 512;
const int gl_MaxVaryingFloats = 32;
const int gl_MaxVertexTextureImageUnits = 0;
const int gl_MaxCombinedTextureImageUnits = 2;
const int gl_MaxTextureImageUnits = 2;
const int gl_MaxFragmentUniformComponents = 64;
const int gl_MaxDrawBuffers = 1;

uniform mat4 gl_ModelViewMatrix;
uniform mat4 gl_ProjectionMatrix;
uniform mat4 gl_ModelViewProjectionMatrix;
uniform mat4 gl_TextureMatrix[gl_MaxTextureCoords];

uniform mat3 gl_NormalMatrix;

uniform mat4 gl_ModelViewMatrixInverse;
uniform mat4 gl_ProjectionMatrixInverse;
uniform mat4 gl_ModelViewProjectionMatrixInverse;
uniform mat4 gl_TextureMatrixInverse[gl_MaxTextureCoords];

uniform mat4 gl_ModelViewMatrixTranspose;
uniform mat4 gl_ProjectionMatrixTranspose;
uniform mat4 gl_ModelViewProjectionMatrixTranspose;
uniform mat4 gl_TextureMatrixTranspose[gl_MaxTextureCoords];

uniform mat4 gl_ModelViewMatrixInverseTranspose;
uniform mat4 gl_ProjectionMatrixInverseTranspose;
uniform mat4 gl_ModelViewProjectionMatrixInverseTranspose;
uniform mat4 gl_TextureMatrixInverseTranspose[gl_MaxTextureCoords];

uniform float gl_NormalScale;

struct gl_DepthRangeParameters {
    float near;
    float far;
    float diff;
};

uniform gl_DepthRangeParameters gl_DepthRange;

uniform vec4 gl_ClipPlane[gl_MaxClipPlanes];

struct gl_PointParameters {
    float size;
    float sizeMin;
    float sizeMax;
    float fadeThresholdSize;
    float distanceConstantAttenuation;
    float distanceLinearAttenuation;
    float distanceQuadraticAttenuation;
};

uniform gl_PointParameters gl_Point;

struct gl_MaterialParameters {
    vec4 emission;
    vec4 ambient;
    vec4 diffuse;
    vec4 specular;
    float shininess;
};

uniform gl_MaterialParameters gl_FrontMaterial;
uniform gl_MaterialParameters gl_BackMaterial;

/* NOTE: the order of these fields is significant!
 * See the definition of the lighting state vars such as STATE_SPOT_DIRECTION.
 */
struct gl_LightSourceParameters {
    vec4 ambient;
    vec4 diffuse;
    vec4 specular;
    vec4 position;
    vec4 halfVector;
    vec3 spotDirection;
    float spotCosCutoff;

    float constantAttenuation;
    float linearAttenuation;
    float quadraticAttenuation;
    float spotExponent;

    float spotCutoff;
};

uniform gl_LightSourceParameters gl_LightSource[gl_MaxLights];

struct gl_LightModelParameters {
    vec4 ambient;
};

uniform gl_LightModelParameters gl_LightModel;

struct gl_LightModelProducts {
    vec4 sceneColor;
};

uniform gl_LightModelProducts gl_FrontLightModelProduct;
uniform gl_LightModelProducts gl_BackLightModelProduct;

struct gl_LightProducts {
    vec4 ambient;
    vec4 diffuse;
    vec4 specular;
};

uniform gl_LightProducts gl_FrontLightProduct[gl_MaxLights];
uniform gl_LightProducts gl_BackLightProduct[gl_MaxLights];

uniform vec4 gl_TextureEnvColor[gl_MaxTextureImageUnits];
uniform vec4 gl_EyePlaneS[gl_MaxTextureCoords];
uniform vec4 gl_EyePlaneT[gl_MaxTextureCoords];
uniform vec4 gl_EyePlaneR[gl_MaxTextureCoords];
uniform vec4 gl_EyePlaneQ[gl_MaxTextureCoords];
uniform vec4 gl_ObjectPlaneS[gl_MaxTextureCoords];
uniform vec4 gl_ObjectPlaneT[gl_MaxTextureCoords];
uniform vec4 gl_ObjectPlaneR[gl_MaxTextureCoords];
uniform vec4 gl_ObjectPlaneQ[gl_MaxTextureCoords];

struct gl_FogParameters {
    vec4 color;
    float density;
    float start;
    float end;
    float scale;
};

uniform gl_FogParameters gl_Fog;





//
// 8.1 Angle and Trigonometry Functions
//

//// radians

float radians(const float deg)
{
   const float c = 3.1415926 / 180.0;
   __asm vec4_multiply __retVal, deg, c;
}

vec2 radians(const vec2 deg)
{
   const float c = 3.1415926 / 180.0;
   __asm vec4_multiply __retVal.xy, deg.xy, c.xx;
}

vec3 radians(const vec3 deg)
{
   const float c = 3.1415926 / 180.0;
   __asm vec4_multiply __retVal.xyz, deg.xyz, c.xxx;
}

vec4 radians(const vec4 deg)
{
   const float c = 3.1415926 / 180.0;
   __asm vec4_multiply __retVal, deg, c.xxxx;
}


//// degrees

float degrees(const float rad)
{
   const float c = 180.0 / 3.1415926;
   __asm vec4_multiply __retVal, rad, c;
}

vec2 degrees(const vec2 rad)
{
   const float c = 180.0 / 3.1415926;
   __asm vec4_multiply __retVal.xy, rad.xy, c.xx;
}

vec3 degrees(const vec3 rad)
{
   const float c = 180.0 / 3.1415926;
   __asm vec4_multiply __retVal.xyz, rad.xyz, c.xxx;
}

vec4 degrees(const vec4 rad)
{
   const float c = 180.0 / 3.1415926;
   __asm vec4_multiply __retVal, rad, c.xxxx;
}


//// sin

float sin(const float radians)
{
   __asm float_sine __retVal, radians;
}

vec2 sin(const vec2 radians)
{
   __asm float_sine __retVal.x, radians.x;
   __asm float_sine __retVal.y, radians.y;
}

vec3 sin(const vec3 radians)
{
   __asm float_sine __retVal.x, radians.x;
   __asm float_sine __retVal.y, radians.y;
   __asm float_sine __retVal.z, radians.z;
}

vec4 sin(const vec4 radians)
{
   __asm float_sine __retVal.x, radians.x;
   __asm float_sine __retVal.y, radians.y;
   __asm float_sine __retVal.z, radians.z;
   __asm float_sine __retVal.w, radians.w;
}


//// cos

float cos(const float radians)
{
   __asm float_cosine __retVal, radians;
}

vec2 cos(const vec2 radians)
{
   __asm float_cosine __retVal.x, radians.x;
   __asm float_cosine __retVal.y, radians.y;
}

vec3 cos(const vec3 radians)
{
   __asm float_cosine __retVal.x, radians.x;
   __asm float_cosine __retVal.y, radians.y;
   __asm float_cosine __retVal.z, radians.z;
}

vec4 cos(const vec4 radians)
{
   __asm float_cosine __retVal.x, radians.x;
   __asm float_cosine __retVal.y, radians.y;
   __asm float_cosine __retVal.z, radians.z;
   __asm float_cosine __retVal.w, radians.w;
}



//// tan

float tan(const float angle)
{
   const float s = sin(angle);
   const float c = cos(angle);
   return s / c;
}

vec2 tan(const vec2 angle)
{
   const vec2 s = sin(angle);
   const vec2 c = cos(angle);
   return s / c;
}

vec3 tan(const vec3 angle)
{
   const vec3 s = sin(angle);
   const vec3 c = cos(angle);
   return s / c;
}

vec4 tan(const vec4 angle)
{
   const vec4 s = sin(angle);
   const vec4 c = cos(angle);
   return s / c;
}



float asin(const float x)
{
   const float a0 = 1.5707288;  // PI/2?
   const float a1 = -0.2121144;
   const float a2 = 0.0742610;
   //const float a3 = -0.0187293;
   const float halfPi = 3.1415926 * 0.5;
   const float y = abs(x);
   // three terms seem to be enough:
   __retVal = (halfPi - sqrt(1.0 - y) * (a0 + y * (a1 + a2 * y))) * sign(x);
   // otherwise, try four:
   //__retVal = (halfPi - sqrt(1.0 - y) * (a0 + y * (a1 + y * (a2 + y * a3)))) * sign(x);
}

vec2 asin(const vec2 v)
{
   __retVal.x = asin(v.x);
   __retVal.y = asin(v.y);
}

vec3 asin(const vec3 v)
{
   __retVal.x = asin(v.x);
   __retVal.y = asin(v.y);
   __retVal.z = asin(v.z);
}

vec4 asin(const vec4 v)
{
   __retVal.x = asin(v.x);
   __retVal.y = asin(v.y);
   __retVal.z = asin(v.z);
   __retVal.w = asin(v.w);
}

float acos(const float x)
{
   const float halfPi = 3.1415926 * 0.5;
   __retVal = halfPi - asin(x);
}

vec2 acos(const vec2 v)
{
   __retVal.x = acos(v.x);
   __retVal.y = acos(v.y);
}

vec3 acos(const vec3 v)
{
   __retVal.x = acos(v.x);
   __retVal.y = acos(v.y);
   __retVal.z = acos(v.z);
}

vec4 acos(const vec4 v)
{
   __retVal.x = acos(v.x);
   __retVal.y = acos(v.y);
   __retVal.z = acos(v.z);
   __retVal.w = acos(v.w);
}

float atan(const float x)
{
   __retVal = asin(x * inversesqrt(x * x + 1.0));
}

vec2 atan(const vec2 y_over_x)
{
   __retVal.x = atan(y_over_x.x);
   __retVal.y = atan(y_over_x.y);
}

vec3 atan(const vec3 y_over_x)
{
   __retVal.x = atan(y_over_x.x);
   __retVal.y = atan(y_over_x.y);
   __retVal.z = atan(y_over_x.z);
}

vec4 atan(const vec4 y_over_x)
{
   __retVal.x = atan(y_over_x.x);
   __retVal.y = atan(y_over_x.y);
   __retVal.z = atan(y_over_x.z);
   __retVal.w = atan(y_over_x.w);
}

float atan(const float y, const float x)
{
   float r;
   if (abs(x) > 1.0e-4) {
      r = atan(y / x);
      if (x < 0.0) {
         r = r + sign(y) * 3.141593;
      }
   }
   else {
      r = sign(y) * 1.5707965;  // pi/2
   }
   return r;
}

vec2 atan(const vec2 u, const vec2 v)
{
   __retVal.x = atan(u.x, v.x);
   __retVal.y = atan(u.y, v.y);
}

vec3 atan(const vec3 u, const vec3 v)
{
   __retVal.x = atan(u.x, v.x);
   __retVal.y = atan(u.y, v.y);
   __retVal.z = atan(u.z, v.z);
}

vec4 atan(const vec4 u, const vec4 v)
{
   __retVal.x = atan(u.x, v.x);
   __retVal.y = atan(u.y, v.y);
   __retVal.z = atan(u.z, v.z);
   __retVal.w = atan(u.w, v.w);
}


//
// 8.2 Exponential Functions
//

//// pow

float pow(const float a, const float b)
{
   __asm float_power __retVal, a, b;
}

vec2 pow(const vec2 a, const vec2 b)
{
   __asm float_power __retVal.x, a.x, b.x;
   __asm float_power __retVal.y, a.y, b.y;
}

vec3 pow(const vec3 a, const vec3 b)
{
   __asm float_power __retVal.x, a.x, b.x;
   __asm float_power __retVal.y, a.y, b.y;
   __asm float_power __retVal.z, a.z, b.z;
}

vec4 pow(const vec4 a, const vec4 b)
{
   __asm float_power __retVal.x, a.x, b.x;
   __asm float_power __retVal.y, a.y, b.y;
   __asm float_power __retVal.z, a.z, b.z;
   __asm float_power __retVal.w, a.w, b.w;
}


//// exp

float exp(const float a)
{
   // NOTE: log2(e) = 1.44269502
   float t = a * 1.44269502;
   __asm float_exp2 __retVal, t;
}

vec2 exp(const vec2 a)
{
   vec2 t = a * 1.44269502;
   __asm float_exp2 __retVal.x, t.x;
   __asm float_exp2 __retVal.y, t.y;
}

vec3 exp(const vec3 a)
{
   vec3 t = a * 1.44269502;
   __asm float_exp2 __retVal.x, t.x;
   __asm float_exp2 __retVal.y, t.y;
   __asm float_exp2 __retVal.z, t.z;
}

vec4 exp(const vec4 a)
{
   vec4 t = a * 1.44269502;
   __asm float_exp2 __retVal.x, t.x;
   __asm float_exp2 __retVal.y, t.y;
   __asm float_exp2 __retVal.z, t.z;
   __asm float_exp2 __retVal.w, t.w;
}



//// log2

float log2(const float x)
{
   __asm float_log2 __retVal, x;
}

vec2 log2(const vec2 v)
{
   __asm float_log2 __retVal.x, v.x;
   __asm float_log2 __retVal.y, v.y;
}

vec3 log2(const vec3 v)
{
   __asm float_log2 __retVal.x, v.x;
   __asm float_log2 __retVal.y, v.y;
   __asm float_log2 __retVal.z, v.z;
}

vec4 log2(const vec4 v)
{
   __asm float_log2 __retVal.x, v.x;
   __asm float_log2 __retVal.y, v.y;
   __asm float_log2 __retVal.z, v.z;
   __asm float_log2 __retVal.w, v.w;
}


//// log  (natural log)

float log(const float x)
{
   // note:  logBaseB(x) = logBaseN(x) / logBaseN(B)
   // compute log(x) = log2(x) / log2(e)
   // c = 1.0 / log2(e) = 0.693147181
   const float c = 0.693147181;
   return log2(x) * c;
}

vec2 log(const vec2 v)
{
   const float c = 0.693147181;
   return log2(v) * c;
}

vec3 log(const vec3 v)
{
   const float c = 0.693147181;
   return log2(v) * c;
}

vec4 log(const vec4 v)
{
   const float c = 0.693147181;
   return log2(v) * c;
}


//// exp2

float exp2(const float a)
{
   __asm float_exp2 __retVal, a;
}

vec2 exp2(const vec2 a)
{
   __asm float_exp2 __retVal.x, a.x;
   __asm float_exp2 __retVal.y, a.y;
}

vec3 exp2(const vec3 a)
{
   __asm float_exp2 __retVal.x, a.x;
   __asm float_exp2 __retVal.y, a.y;
   __asm float_exp2 __retVal.z, a.z;
}

vec4 exp2(const vec4 a)
{
   __asm float_exp2 __retVal.x, a.x;
   __asm float_exp2 __retVal.y, a.y;
   __asm float_exp2 __retVal.z, a.z;
   __asm float_exp2 __retVal.w, a.w;
}


//// sqrt

float sqrt(const float x)
{
   float r;
   __asm float_rsq r, x;
   __asm float_rcp __retVal, r;
}

vec2 sqrt(const vec2 v)
{
   float r;
   __asm float_rsq r, v.x;
   __asm float_rcp __retVal.x, r;
   __asm float_rsq r, v.y;
   __asm float_rcp __retVal.y, r;
}

vec3 sqrt(const vec3 v)
{
   float r;
   __asm float_rsq r, v.x;
   __asm float_rcp __retVal.x, r;
   __asm float_rsq r, v.y;
   __asm float_rcp __retVal.y, r;
   __asm float_rsq r, v.z;
   __asm float_rcp __retVal.z, r;
}

vec4 sqrt(const vec4 v)
{
   float r;
   __asm float_rsq r, v.x;
   __asm float_rcp __retVal.x, r;
   __asm float_rsq r, v.y;
   __asm float_rcp __retVal.y, r;
   __asm float_rsq r, v.z;
   __asm float_rcp __retVal.z, r;
   __asm float_rsq r, v.w;
   __asm float_rcp __retVal.w, r;
}


//// inversesqrt

float inversesqrt(const float x)
{
   __asm float_rsq __retVal.x, x;
}

vec2 inversesqrt(const vec2 v)
{
   __asm float_rsq __retVal.x, v.x;
   __asm float_rsq __retVal.y, v.y;
}

vec3 inversesqrt(const vec3 v)
{
   __asm float_rsq __retVal.x, v.x;
   __asm float_rsq __retVal.y, v.y;
   __asm float_rsq __retVal.z, v.z;
}

vec4 inversesqrt(const vec4 v)
{
   __asm float_rsq __retVal.x, v.x;
   __asm float_rsq __retVal.y, v.y;
   __asm float_rsq __retVal.z, v.z;
   __asm float_rsq __retVal.w, v.w;
}


//// normalize

float normalize(const float x)
{
   __retVal = 1.0;
}

vec2 normalize(const vec2 v)
{
   const float s = inversesqrt(dot(v, v));
   __asm vec4_multiply __retVal.xy, v, s;
}

vec3 normalize(const vec3 v)
{
//   const float s = inversesqrt(dot(v, v));
//   __retVal = v * s;
// XXX note, we _could_ use __retVal.w instead of tmp and and save a
// register, but that's actually a compilation error because v is a vec3
// and the .w suffix is illegal.  Oh well.
   float tmp;
   __asm vec3_dot tmp, v, v;
   __asm float_rsq tmp, tmp;
   __asm vec4_multiply __retVal.xyz, v, tmp;
}

vec4 normalize(const vec4 v)
{
   float tmp;
   __asm vec4_dot tmp, v, v;
   __asm float_rsq tmp, tmp;
   __asm vec4_multiply __retVal.xyz, v, tmp;
}



//
// 8.3 Common Functions
//


//// abs

float abs(const float a)
{
   __asm vec4_abs __retVal, a;
}

vec2 abs(const vec2 a)
{
   __asm vec4_abs __retVal.xy, a;
}

vec3 abs(const vec3 a)
{
   __asm vec4_abs __retVal.xyz, a;
}

vec4 abs(const vec4 a)
{
   __asm vec4_abs __retVal, a;
}


//// sign

float sign(const float x)
{
   float p, n;
   __asm vec4_sgt p, x, 0.0;            // p = (x > 0)
   __asm vec4_sgt n, 0.0, x;            // n = (x < 0)
   __asm vec4_subtract __retVal, p, n;  // sign = p - n
}

vec2 sign(const vec2 v)
{
   vec2 p, n;
   __asm vec4_sgt p.xy, v, 0.0;
   __asm vec4_sgt n.xy, 0.0, v;
   __asm vec4_subtract __retVal.xy, p, n;
}

vec3 sign(const vec3 v)
{
   vec3 p, n;
   __asm vec4_sgt p.xyz, v, 0.0;
   __asm vec4_sgt n.xyz, 0.0, v;
   __asm vec4_subtract __retVal.xyz, p, n;
}

vec4 sign(const vec4 v)
{
   vec4 p, n;
   __asm vec4_sgt p, v, 0.0;
   __asm vec4_sgt n, 0.0, v;
   __asm vec4_subtract __retVal, p, n;
}


//// floor

float floor(const float a)
{
   __asm vec4_floor __retVal, a;
}

vec2 floor(const vec2 a)
{
   __asm vec4_floor __retVal.xy, a;
}

vec3 floor(const vec3 a)
{
   __asm vec4_floor __retVal.xyz, a;
}

vec4 floor(const vec4 a)
{
   __asm vec4_floor __retVal, a;
}


//// ceil

float ceil(const float a)
{
   // XXX this could be improved
   float b = -a;
   __asm vec4_floor b, b;
   __retVal = -b;
}

vec2 ceil(const vec2 a)
{
   vec2 b = -a;
   __asm vec4_floor b, b;
   __retVal.xy = -b;
}

vec3 ceil(const vec3 a)
{
   vec3 b = -a;
   __asm vec4_floor b, b;
   __retVal.xyz = -b;
}

vec4 ceil(const vec4 a)
{
   vec4 b = -a;
   __asm vec4_floor b, b;
   __retVal = -b;
}


//// fract

float fract(const float a)
{
   __asm vec4_frac __retVal, a;
}

vec2 fract(const vec2 a)
{
   __asm vec4_frac __retVal.xy, a;
}

vec3 fract(const vec3 a)
{
   __asm vec4_frac __retVal.xyz, a;
}

vec4 fract(const vec4 a)
{
   __asm vec4_frac __retVal, a;
}


//// mod  (very untested!)

float mod(const float a, const float b)
{
    float oneOverB;
    __asm float_rcp oneOverB, b;
    __retVal = a - b * floor(a * oneOverB);
}

vec2 mod(const vec2 a, const float b)
{
    float oneOverB;
    __asm float_rcp oneOverB, b;
    __retVal.xy = a - b * floor(a * oneOverB);
}

vec3 mod(const vec3 a, const float b)
{
    float oneOverB;
    __asm float_rcp oneOverB, b;
    __retVal.xyz = a - b * floor(a * oneOverB);
}

vec4 mod(const vec4 a, const float b)
{
    float oneOverB;
    __asm float_rcp oneOverB, b;
    __retVal = a - b * floor(a * oneOverB);
}

vec2 mod(const vec2 a, const vec2 b)
{
    vec2 oneOverB;
    __asm float_rcp oneOverB.x, b.x;
    __asm float_rcp oneOverB.y, b.y;
    __retVal = a - b * floor(a * oneOverB);
}

vec3 mod(const vec3 a, const vec3 b)
{
    vec3 oneOverB;
    __asm float_rcp oneOverB.x, b.x;
    __asm float_rcp oneOverB.y, b.y;
    __asm float_rcp oneOverB.z, b.z;
    __retVal = a - b * floor(a * oneOverB);
}

vec4 mod(const vec4 a, const vec4 b)
{
    vec4 oneOverB;
    __asm float_rcp oneOverB.x, b.x;
    __asm float_rcp oneOverB.y, b.y;
    __asm float_rcp oneOverB.z, b.z;
    __asm float_rcp oneOverB.w, b.w;
    __retVal = a - b * floor(a * oneOverB);
}


//// min

float min(const float a, const float b)
{
   __asm vec4_min __retVal, a, b;
}

vec2 min(const vec2 a, const vec2 b)
{
   __asm vec4_min __retVal.xy, a.xy, b.xy;
}

vec3 min(const vec3 a, const vec3 b)
{
   __asm vec4_min __retVal.xyz, a.xyz, b.xyz;
}

vec4 min(const vec4 a, const vec4 b)
{
   __asm vec4_min __retVal, a, b;
}

vec2 min(const vec2 a, const float b)
{
   __asm vec4_min __retVal, a.xy, b;
}

vec3 min(const vec3 a, const float b)
{
   __asm vec4_min __retVal, a.xyz, b;
}

vec4 min(const vec4 a, const float b)
{
   __asm vec4_min __retVal, a, b;
}


//// max

float max(const float a, const float b)
{
   __asm vec4_max __retVal, a, b;
}

vec2 max(const vec2 a, const vec2 b)
{
   __asm vec4_max __retVal.xy, a.xy, b.xy;
}

vec3 max(const vec3 a, const vec3 b)
{
   __asm vec4_max __retVal.xyz, a.xyz, b.xyz;
}

vec4 max(const vec4 a, const vec4 b)
{
   __asm vec4_max __retVal, a, b;
}

vec2 max(const vec2 a, const float b)
{
   __asm vec4_max __retVal, a.xy, b;
}

vec3 max(const vec3 a, const float b)
{
   __asm vec4_max __retVal, a.xyz, b;
}

vec4 max(const vec4 a, const float b)
{
   __asm vec4_max __retVal, a, b;
}


//// clamp

float clamp(const float val, const float minVal, const float maxVal)
{
   __asm vec4_clamp __retVal, val, minVal, maxVal;
}

vec2 clamp(const vec2 val, const float minVal, const float maxVal)
{
   __asm vec4_clamp __retVal, val, minVal, maxVal;
}

vec3 clamp(const vec3 val, const float minVal, const float maxVal)
{
   __asm vec4_clamp __retVal, val, minVal, maxVal;
}

vec4 clamp(const vec4 val, const float minVal, const float maxVal)
{
   __asm vec4_clamp __retVal, val, minVal, maxVal;
}

vec2 clamp(const vec2 val, const vec2 minVal, const vec2 maxVal)
{
   __asm vec4_clamp __retVal, val, minVal, maxVal;
}

vec3 clamp(const vec3 val, const vec3 minVal, const vec3 maxVal)
{
   __asm vec4_clamp __retVal, val, minVal, maxVal;
}

vec4 clamp(const vec4 val, const vec4 minVal, const vec4 maxVal)
{
   __asm vec4_clamp __retVal, val, minVal, maxVal;
}


//// mix

float mix(const float x, const float y, const float a)
{
   __asm vec4_lrp __retVal, a, y, x;
}

vec2 mix(const vec2 x, const vec2 y, const float a)
{
   __asm vec4_lrp __retVal, a, y, x;
}

vec3 mix(const vec3 x, const vec3 y, const float a)
{
   __asm vec4_lrp __retVal, a, y, x;
}

vec4 mix(const vec4 x, const vec4 y, const float a)
{
   __asm vec4_lrp __retVal, a, y, x;
}

vec2 mix(const vec2 x, const vec2 y, const vec2 a)
{
   __asm vec4_lrp __retVal, a, y, x;
}

vec3 mix(const vec3 x, const vec3 y, const vec3 a)
{
   __asm vec4_lrp __retVal, a, y, x;
}

vec4 mix(const vec4 x, const vec4 y, const vec4 a)
{
   __asm vec4_lrp __retVal, a, y, x;
}


//// step

float step(const float edge, const float x)
{
   __asm vec4_sge __retVal, x, edge;
}

vec2 step(const vec2 edge, const vec2 x)
{
   __asm vec4_sge __retVal.xy, x, edge;
}

vec3 step(const vec3 edge, const vec3 x)
{
   __asm vec4_sge __retVal.xyz, x, edge;
}

vec4 step(const vec4 edge, const vec4 x)
{
   __asm vec4_sge __retVal, x, edge;
}

vec2 step(const float edge, const vec2 v)
{
   __asm vec4_sge __retVal.xy, v, edge;
}

vec3 step(const float edge, const vec3 v)
{
   __asm vec4_sge __retVal.xyz, v, edge;
}

vec4 step(const float edge, const vec4 v)
{
   __asm vec4_sge __retVal, v, edge;
}


//// smoothstep

float smoothstep(const float edge0, const float edge1, const float x)
{
    float t = clamp((x - edge0) / (edge1 - edge0), 0.0, 1.0);
    return t * t * (3.0 - 2.0 * t);
}

vec2 smoothstep(const vec2 edge0, const vec2 edge1, const vec2 v)
{
   vec2 t = clamp((v - edge0) / (edge1 - edge0), 0.0, 1.0);
   return t * t * (3.0 - 2.0 * t);
}

vec3 smoothstep(const vec3 edge0, const vec3 edge1, const vec3 v)
{
   vec3 t = clamp((v - edge0) / (edge1 - edge0), 0.0, 1.0);
   return t * t * (3.0 - 2.0 * t);
}

vec4 smoothstep(const vec4 edge0, const vec4 edge1, const vec4 v)
{
   vec4 t = clamp((v - edge0) / (edge1 - edge0), 0.0, 1.0);
   return t * t * (3.0 - 2.0 * t);
}

vec2 smoothstep(const float edge0, const float edge1, const vec2 v)
{
   vec2 t = clamp((v - edge0) / (edge1 - edge0), 0.0, 1.0);
   return t * t * (3.0 - 2.0 * t);
}

vec3 smoothstep(const float edge0, const float edge1, const vec3 v)
{
   vec3 t = clamp((v - edge0) / (edge1 - edge0), 0.0, 1.0);
   return t * t * (3.0 - 2.0 * t);
}

vec4 smoothstep(const float edge0, const float edge1, const vec4 v)
{
   vec4 t = clamp((v - edge0) / (edge1 - edge0), 0.0, 1.0);
   return t * t * (3.0 - 2.0 * t);
}



//
// 8.4 Geometric Functions
//


//// length

float length(const float x)
{
   return abs(x);
}

float length(const vec2 v)
{
   float r;
   const float p = dot(v, v);      // p = v.x * v.x + v.y * v.y
   __asm float_rsq r, p;           // r = 1 / sqrt(p)
   __asm float_rcp __retVal.x, r;  // retVal = 1 / r
}

float length(const vec3 v)
{
   float r;
   const float p = dot(v, v);      // p = v.x * v.x + v.y * v.y + v.z * v.z
   __asm float_rsq r, p;           // r = 1 / sqrt(p)
   __asm float_rcp __retVal, r;    // retVal = 1 / r
}

float length(const vec4 v)
{
   float r;
   const float p = dot(v, v);      // p = v.x * v.x + v.y * v.y + ...
   __asm float_rsq r, p;           // r = 1 / sqrt(p)
   __asm float_rcp __retVal, r;    // retVal = 1 / r
}


//// distance

float distance(const float x, const float y)
{
   const float d = x - y;
   __retVal = length(d);
}

float distance(const vec2 v, const vec2 u)
{
   const vec2 d2 = v - u;
   __retVal = length(d2);
}

float distance(const vec3 v, const vec3 u)
{
   const vec3 d3 = v - u;
   __retVal = length(d3);
}

float distance(const vec4 v, const vec4 u)
{
   const vec4 d4 = v - u;
   __retVal = length(d4);
}


//// cross

vec3 cross(const vec3 v, const vec3 u)
{
   __asm vec3_cross __retVal.xyz, v, u;
}


//// faceforward

float faceforward(const float N, const float I, const float Nref)
{
    // this could probably be done better
    const float d = dot(Nref, I);
    float s;
    __asm vec4_sgt s, 0.0, d;  // s = (0.0 > d) ? 1 : 0
    return mix(-N, N, s);
}

vec2 faceforward(const vec2 N, const vec2 I, const vec2 Nref)
{
    // this could probably be done better
    const float d = dot(Nref, I);
    float s;
    __asm vec4_sgt s, 0.0, d;  // s = (0.0 > d) ? 1 : 0
    return mix(-N, N, s);
}

vec3 faceforward(const vec3 N, const vec3 I, const vec3 Nref)
{
    // this could probably be done better
    const float d = dot(Nref, I);
    float s;
    __asm vec4_sgt s, 0.0, d;  // s = (0.0 > d) ? 1 : 0
    return mix(-N, N, s);
}

vec4 faceforward(const vec4 N, const vec4 I, const vec4 Nref)
{
    // this could probably be done better
    const float d = dot(Nref, I);
    float s;
    __asm vec4_sgt s, 0.0, d;  // s = (0.0 > d) ? 1 : 0
    return mix(-N, N, s);
}


//// reflect

float reflect(const float I, const float N)
{
   return I - 2.0 * dot(N, I) * N;
}

vec2 reflect(const vec2 I, const vec2 N)
{
   return I - 2.0 * dot(N, I) * N;
}

vec3 reflect(const vec3 I, const vec3 N)
{
   return I - 2.0 * dot(N, I) * N;
}

vec4 reflect(const vec4 I, const vec4 N)
{
   return I - 2.0 * dot(N, I) * N;
}

//// refract

float refract(const float I, const float N, const float eta)
{
   float n_dot_i = dot(N, I);
   float k = 1.0 - eta * eta * (1.0 - n_dot_i * n_dot_i);
   float retval;
   if (k < 0.0)
      retval = 0.0;
   else
      retval = eta * I - (eta * n_dot_i + sqrt(k)) * N;
   return retval;
}

vec2 refract(const vec2 I, const vec2 N, const float eta)
{
   float n_dot_i = dot(N, I);
   float k = 1.0 - eta * eta * (1.0 - n_dot_i * n_dot_i);
   vec2 retval;
   if (k < 0.0)
      retval = vec2(0.0);
   else
      retval = eta * I - (eta * n_dot_i + sqrt(k)) * N;
   return retval;
}

vec3 refract(const vec3 I, const vec3 N, const float eta)
{
   float n_dot_i = dot(N, I);
   float k = 1.0 - eta * eta * (1.0 - n_dot_i * n_dot_i);
   vec3 retval;
   if (k < 0.0)
      retval = vec3(0.0);
   else
      retval = eta * I - (eta * n_dot_i + sqrt(k)) * N;
   return retval;
}

vec4 refract(const vec4 I, const vec4 N, const float eta)
{
   float n_dot_i = dot(N, I);
   float k = 1.0 - eta * eta * (1.0 - n_dot_i * n_dot_i);
   vec4 retval;
   if (k < 0.0)
      retval = vec4(0.0);
   else
      retval = eta * I - (eta * n_dot_i + sqrt(k)) * N;
   return retval;
}




//
// 8.5 Matrix Functions
//

mat2 matrixCompMult (mat2 m, mat2 n) {
    return mat2 (m[0] * n[0], m[1] * n[1]);
}

mat3 matrixCompMult (mat3 m, mat3 n) {
    return mat3 (m[0] * n[0], m[1] * n[1], m[2] * n[2]);
}

mat4 matrixCompMult (mat4 m, mat4 n) {
    return mat4 (m[0] * n[0], m[1] * n[1], m[2] * n[2], m[3] * n[3]);
}




//
// 8.6 Vector Relational Functions
//

//// lessThan

bvec2 lessThan(const vec2 u, const vec2 v)
{
   __asm vec4_slt __retVal.xy, u, v;
}

bvec3 lessThan(const vec3 u, const vec3 v)
{
   __asm vec4_slt __retVal.xyz, u, v;
}

bvec4 lessThan(const vec4 u, const vec4 v)
{
   __asm vec4_slt __retVal, u, v;
}

bvec2 lessThan(const ivec2 u, const ivec2 v)
{
   __asm vec4_slt __retVal.xy, u, v;
}

bvec3 lessThan(const ivec3 u, const ivec3 v)
{
   __asm vec4_slt __retVal.xyz, u, v;
}

bvec4 lessThan(const ivec4 u, const ivec4 v)
{
   __asm vec4_slt __retVal, u, v;
}


//// lessThanEqual

bvec2 lessThanEqual(const vec2 u, const vec2 v)
{
   __asm vec4_sle __retVal.xy, u, v;
}

bvec3 lessThanEqual(const vec3 u, const vec3 v)
{
   __asm vec4_sle __retVal.xyz, u, v;
}

bvec4 lessThanEqual(const vec4 u, const vec4 v)
{
   __asm vec4_sle __retVal, u, v;
}

bvec2 lessThanEqual(const ivec2 u, const ivec2 v)
{
   __asm vec4_sle __retVal.xy, u, v;
}

bvec3 lessThanEqual(const ivec3 u, const ivec3 v)
{
   __asm vec4_sle __retVal.xyz, u, v;
}

bvec4 lessThanEqual(const ivec4 u, const ivec4 v)
{
   __asm vec4_sle __retVal, u, v;
}


//// greaterThan

bvec2 greaterThan(const vec2 u, const vec2 v)
{
   __asm vec4_sgt __retVal.xy, u, v;
}

bvec3 greaterThan(const vec3 u, const vec3 v)
{
   __asm vec4_sgt __retVal.xyz, u, v;
}

bvec4 greaterThan(const vec4 u, const vec4 v)
{
   __asm vec4_sgt __retVal, u, v;
}

bvec2 greaterThan(const ivec2 u, const ivec2 v)
{
   __asm vec4_sgt __retVal.xy, u.xy, v.xy;
}

bvec3 greaterThan(const ivec3 u, const ivec3 v)
{
   __asm vec4_sgt __retVal.xyz, u, v;
}

bvec4 greaterThan(const ivec4 u, const ivec4 v)
{
   __asm vec4_sgt __retVal, u, v;
}


//// greaterThanEqual

bvec2 greaterThanEqual(const vec2 u, const vec2 v)
{
   __asm vec4_sge __retVal.xy, u, v;
}

bvec3 greaterThanEqual(const vec3 u, const vec3 v)
{
   __asm vec4_sge __retVal.xyz, u, v;
}

bvec4 greaterThanEqual(const vec4 u, const vec4 v)
{
   __asm vec4_sge __retVal, u, v;
}

bvec2 greaterThanEqual(const ivec2 u, const ivec2 v)
{
   __asm vec4_sge __retVal.xy, u, v;
}

bvec3 greaterThanEqual(const ivec3 u, const ivec3 v)
{
   __asm vec4_sge __retVal.xyz, u, v;
}

bvec4 greaterThanEqual(const ivec4 u, const ivec4 v)
{
   __asm vec4_sge __retVal, u, v;
}


//// equal

bvec2 equal(const vec2 u, const vec2 v)
{
   __asm vec4_seq __retVal.xy, u, v;
}

bvec3 equal(const vec3 u, const vec3 v)
{
   __asm vec4_seq __retVal.xyz, u, v;
}

bvec4 equal(const vec4 u, const vec4 v)
{
   __asm vec4_seq __retVal, u, v;
}

bvec2 equal(const ivec2 u, const ivec2 v)
{
   __asm vec4_seq __retVal.xy, u, v;
}

bvec3 equal(const ivec3 u, const ivec3 v)
{
   __asm vec4_seq __retVal.xyz, u, v;
}

bvec4 equal(const ivec4 u, const ivec4 v)
{
   __asm vec4_seq __retVal, u, v;
}

bvec2 equal(const bvec2 u, const bvec2 v)
{
   __asm vec4_seq __retVal.xy, u, v;
}

bvec3 equal(const bvec3 u, const bvec3 v)
{
   __asm vec4_seq __retVal.xyz, u, v;
}

bvec4 equal(const bvec4 u, const bvec4 v)
{
   __asm vec4_seq __retVal, u, v;
}




//// notEqual

bvec2 notEqual(const vec2 u, const vec2 v)
{
   __asm vec4_sne __retVal.xy, u, v;
}

bvec3 notEqual(const vec3 u, const vec3 v)
{
   __asm vec4_sne __retVal.xyz, u, v;
}

bvec4 notEqual(const vec4 u, const vec4 v)
{
   __asm vec4_sne __retVal, u, v;
}

bvec2 notEqual(const ivec2 u, const ivec2 v)
{
   __asm vec4_sne __retVal.xy, u, v;
}

bvec3 notEqual(const ivec3 u, const ivec3 v)
{
   __asm vec4_sne __retVal.xyz, u, v;
}

bvec4 notEqual(const ivec4 u, const ivec4 v)
{
   __asm vec4_sne __retVal, u, v;
}

bvec2 notEqual(const bvec2 u, const bvec2 v)
{
   __asm vec4_sne __retVal.xy, u, v;
}

bvec3 notEqual(const bvec3 u, const bvec3 v)
{
   __asm vec4_sne __retVal.xyz, u, v;
}

bvec4 notEqual(const bvec4 u, const bvec4 v)
{
   __asm vec4_sne __retVal, u, v;
}



//// any

bool any(const bvec2 v)
{
   float sum;
   __asm vec4_add sum.x, v.x, v.y;
   __asm vec4_sne __retVal.x, sum.x, 0.0;
}

bool any(const bvec3 v)
{
   float sum;
   __asm vec4_add sum.x, v.x, v.y;
   __asm vec4_add sum.x, sum.x, v.z;
   __asm vec4_sne __retVal.x, sum.x, 0.0;
}

bool any(const bvec4 v)
{
   float sum;
   __asm vec4_add sum.x, v.x, v.y;
   __asm vec4_add sum.x, sum.x, v.z;
   __asm vec4_add sum.x, sum.x, v.w;
   __asm vec4_sne __retVal.x, sum.x, 0.0;
}


//// all

bool all (const bvec2 v)
{
   float prod;
   __asm vec4_multiply prod, v.x, v.y;
   __asm vec4_sne __retVal, prod, 0.0;
}

bool all (const bvec3 v)
{
   float prod;
   __asm vec4_multiply prod, v.x, v.y;
   __asm vec4_multiply prod, prod, v.z;
   __asm vec4_sne __retVal, prod, 0.0;
}

bool all (const bvec4 v)
{
   float prod;
   __asm vec4_multiply prod, v.x, v.y;
   __asm vec4_multiply prod, prod, v.z;
   __asm vec4_multiply prod, prod, v.w;
   __asm vec4_sne __retVal, prod, 0.0;
}



//// not

bvec2 not (const bvec2 v)
{
   __asm vec4_seq __retVal.xy, v, 0.0;
}

bvec3 not (const bvec3 v)
{
   __asm vec4_seq __retVal.xyz, v, 0.0;
}

bvec4 not (const bvec4 v)
{
   __asm vec4_seq __retVal, v, 0.0;
}



//// Texture Lookup Functions  (for both fragment and vertex shaders)

vec4 texture1D(const sampler1D sampler, const float coord)
{
   __asm vec4_tex_1d __retVal, sampler, coord;
}

vec4 texture1DProj(const sampler1D sampler, const vec2 coord)
{
   // need to swizzle .y into .w
   __asm vec4_tex_1d_proj __retVal, sampler, coord.xyyy;
}

vec4 texture1DProj(const sampler1D sampler, const vec4 coord)
{
   __asm vec4_tex_1d_proj __retVal, sampler, coord;
}


vec4 texture2D(const sampler2D sampler, const vec2 coord)
{
   __asm vec4_tex_2d __retVal, sampler, coord;
}

vec4 texture2DProj(const sampler2D sampler, const vec3 coord)
{
   // need to swizzle 'z' into 'w'.
   __asm vec4_tex_2d_proj __retVal, sampler, coord.xyzz;
}

vec4 texture2DProj(const sampler2D sampler, const vec4 coord)
{
   __asm vec4_tex_2d_proj __retVal, sampler, coord;
}


vec4 texture3D(const sampler3D sampler, const vec3 coord)
{
   __asm vec4_tex_3d __retVal, sampler, coord;
}

vec4 texture3DProj(const sampler3D sampler, const vec4 coord)
{
   __asm vec4_tex_3d_proj __retVal, sampler, coord;
}


vec4 textureCube(const samplerCube sampler, const vec3 coord)
{
   __asm vec4_tex_cube __retVal, sampler, coord;
}



vec4 shadow1D(const sampler1DShadow sampler, const vec3 coord)
{
   __asm vec4_tex_1d_shadow __retVal, sampler, coord;
}

vec4 shadow1DProj(const sampler1DShadow sampler, const vec4 coord)
{
   // .s and .p will be divided by .q
   __asm vec4_tex_1d_proj_shadow __retVal, sampler, coord;
}

vec4 shadow2D(const sampler2DShadow sampler, const vec3 coord)
{
   __asm vec4_tex_2d_shadow __retVal, sampler, coord;
}

vec4 shadow2DProj(const sampler2DShadow sampler, const vec4 coord)
{
   // .s, .t and .p will be divided by .q
   __asm vec4_tex_2d_proj_shadow __retVal, sampler, coord;
}


//// GL_ARB_texture_rectangle:
vec4 texture2DRect(const sampler2DRect sampler, const vec2 coord)
{
   __asm vec4_tex_rect __retVal, sampler, coord;
}

vec4 texture2DRectProj(const sampler2DRect sampler, const vec3 coord)
{
   // need to swizzle .y into .w
   __asm vec4_tex_rect_proj __retVal, sampler, coord.xyzz;
}

vec4 texture2DRectProj(const sampler2DRect sampler, const vec4 coord)
{
   __asm vec4_tex_rect_proj __retVal, sampler, ccoord;
}

vec4 shadow2DRect(const sampler2DRectShadow sampler, const vec3 coord)
{
   __asm vec4_tex_rect_shadow __retVal, sampler, coord;
}

vec4 shadow2DRectProj(const sampler2DRectShadow sampler, const vec4 coord)
{
   __asm vec4_tex_rect_proj_shadow __retVal, sampler, coord;
}



//
// 8.9 Noise Functions
//
// AUTHOR: Stefan Gustavson (stegu@itn.liu.se), Nov 26, 2005
//

float noise1(const float x)
{
   __asm float_noise1 __retVal, x;
}


float noise1(const vec2 x)
{
    __asm float_noise2 __retVal, x;
}

float noise1(const vec3 x)
{
    __asm float_noise3 __retVal, x;
}

float noise1(const vec4 x)
{
    __asm float_noise4 __retVal, x;
}

vec2 noise2(const float x)
{
   __retVal.x = noise1(x);
   __retVal.y = noise1(x + 19.34);
}

vec2 noise2(const vec2 x)
{
   __retVal.x = noise1(x);
   __retVal.y = noise1(x + vec2(19.34, 7.66));
}

vec2 noise2(const vec3 x)
{
   __retVal.x = noise1(x);
   __retVal.y = noise1(x + vec3(19.34, 7.66, 3.23));
}

vec2 noise2(const vec4 x)
{
   __retVal.x = noise1(x);
   __retVal.y = noise1(x + vec4(19.34, 7.66, 3.23, 2.77));
}

vec3 noise3(const float x)
{
   __retVal.x = noise1(x);
   __retVal.y = noise1(x + 19.34);
   __retVal.z = noise1(x + 5.47);
}

vec3 noise3(const vec2 x)
{
   __retVal.x = noise1(x);
   __retVal.y = noise1(x + vec2(19.34, 7.66));
   __retVal.z = noise1(x + vec2(5.47, 17.85));
}

vec3 noise3(const vec3 x)
{
   __retVal.x = noise1(x);
   __retVal.y = noise1(x + vec3(19.34, 7.66, 3.23));
   __retVal.z = noise1(x + vec3(5.47, 17.85, 11.04));
}

vec3 noise3(const vec4 x)
{
   __retVal.x = noise1(x);
   __retVal.y = noise1(x + vec4(19.34, 7.66, 3.23, 2.77));
   __retVal.z = noise1(x + vec4(5.47, 17.85, 11.04, 13.19));
}

vec4 noise4(const float x)
{
   __retVal.x = noise1(x);
   __retVal.y = noise1(x + 19.34);
   __retVal.z = noise1(x + 5.47);
   __retVal.w = noise1(x + 23.54);
}

vec4 noise4(const vec2 x)
{
   __retVal.x = noise1(x);
   __retVal.y = noise1(x + vec2 (19.34, 7.66));
   __retVal.z = noise1(x + vec2 (5.47, 17.85));
   __retVal.w = noise1(x + vec2 (23.54, 29.11));
}

vec4 noise4(const vec3 x)
{
   __retVal.x = noise1(x);
   __retVal.y = noise1(x + vec3(19.34, 7.66, 3.23));
   __retVal.z = noise1(x + vec3(5.47, 17.85, 11.04));
   __retVal.w = noise1(x + vec3(23.54, 29.11, 31.91));
}

vec4 noise4(const vec4 x)
{
   __retVal.x = noise1(x);
   __retVal.y = noise1(x + vec4(19.34, 7.66, 3.23, 2.77));
   __retVal.z = noise1(x + vec4(5.47, 17.85, 11.04, 13.19));
   __retVal.w = noise1(x + vec4(23.54, 29.11, 31.91, 37.48));
}