src/gallium/auxiliary/tgsi/tgsi-instruction-set.txt

   1 TGSI Instruction Specification
   2 ==============================
   3 ==============================
   4
   5
   6 1  Instruction Set Operations
   7 =============================
   8
   9
  10 1.1  GL_NV_vertex_program
  11 -------------------------
  12
  13
  14 1.1.1  ARL - Address Register Load
  15
  16   dst.x = floor(src.x)
  17   dst.y = floor(src.y)
  18   dst.z = floor(src.z)
  19   dst.w = floor(src.w)
  20
  21
  22 1.1.2  MOV - Move
  23
  24   dst.x = src.x
  25   dst.y = src.y
  26   dst.z = src.z
  27   dst.w = src.w
  28
  29
  30 1.1.3  LIT - Light Coefficients
  31
  32   dst.x = 1.0
  33   dst.y = max(src.x, 0.0)
  34   dst.z = (src.x > 0.0) ? pow(max(src.y, 0.0), clamp(src.w, -128.0, 128.0)) : 0.0
  35   dst.w = 1.0
  36
  37
  38 1.1.4  RCP - Reciprocal
  39
  40   dst.x = 1.0 / src.x
  41   dst.y = 1.0 / src.x
  42   dst.z = 1.0 / src.x
  43   dst.w = 1.0 / src.x
  44
  45
  46 1.1.5  RSQ - Reciprocal Square Root
  47
  48   dst.x = 1.0 / sqrt(abs(src.x))
  49   dst.y = 1.0 / sqrt(abs(src.x))
  50   dst.z = 1.0 / sqrt(abs(src.x))
  51   dst.w = 1.0 / sqrt(abs(src.x))
  52
  53
  54 1.1.6  EXP - Approximate Exponential Base 2
  55
  56   dst.x = pow(2.0, floor(src.x))
  57   dst.y = src.x - floor(src.x)
  58   dst.z = pow(2.0, src.x)
  59   dst.w = 1.0
  60
  61
  62 1.1.7  LOG - Approximate Logarithm Base 2
  63
  64   dst.x = floor(lg2(abs(src.x)))
  65   dst.y = abs(src.x) / pow(2.0, floor(lg2(abs(src.x))))
  66   dst.z = lg2(abs(src.x))
  67   dst.w = 1.0
  68
  69
  70 1.1.8  MUL - Multiply
  71
  72   dst.x = src0.x * src1.x
  73   dst.y = src0.y * src1.y
  74   dst.z = src0.z * src1.z
  75   dst.w = src0.w * src1.w
  76
  77
  78 1.1.9  ADD - Add
  79
  80   dst.x = src0.x + src1.x
  81   dst.y = src0.y + src1.y
  82   dst.z = src0.z + src1.z
  83   dst.w = src0.w + src1.w
  84
  85
  86 1.1.10  DP3 - 3-component Dot Product
  87
  88   dst.x = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z
  89   dst.y = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z
  90   dst.z = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z
  91   dst.w = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z
  92
  93
  94 1.1.11  DP4 - 4-component Dot Product
  95
  96   dst.x = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src0.w * src1.w
  97   dst.y = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src0.w * src1.w
  98   dst.z = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src0.w * src1.w
  99   dst.w = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src0.w * src1.w
 100
 101
 102 1.1.12  DST - Distance Vector
 103
 104   dst.x = 1.0
 105   dst.y = src0.y * src1.y
 106   dst.z = src0.z
 107   dst.w = src1.w
 108
 109
 110 1.1.13  MIN - Minimum
 111
 112   dst.x = min(src0.x, src1.x)
 113   dst.y = min(src0.y, src1.y)
 114   dst.z = min(src0.z, src1.z)
 115   dst.w = min(src0.w, src1.w)
 116
 117
 118 1.1.14  MAX - Maximum
 119
 120   dst.x = max(src0.x, src1.x)
 121   dst.y = max(src0.y, src1.y)
 122   dst.z = max(src0.z, src1.z)
 123   dst.w = max(src0.w, src1.w)
 124
 125
 126 1.1.15  SLT - Set On Less Than
 127
 128   dst.x = (src0.x < src1.x) ? 1.0 : 0.0
 129   dst.y = (src0.y < src1.y) ? 1.0 : 0.0
 130   dst.z = (src0.z < src1.z) ? 1.0 : 0.0
 131   dst.w = (src0.w < src1.w) ? 1.0 : 0.0
 132
 133
 134 1.1.16  SGE - Set On Greater Equal Than
 135
 136   dst.x = (src0.x >= src1.x) ? 1.0 : 0.0
 137   dst.y = (src0.y >= src1.y) ? 1.0 : 0.0
 138   dst.z = (src0.z >= src1.z) ? 1.0 : 0.0
 139   dst.w = (src0.w >= src1.w) ? 1.0 : 0.0
 140
 141
 142 1.1.17  MAD - Multiply And Add
 143
 144   dst.x = src0.x * src1.x + src2.x
 145   dst.y = src0.y * src1.y + src2.y
 146   dst.z = src0.z * src1.z + src2.z
 147   dst.w = src0.w * src1.w + src2.w
 148
 149
 150 1.2  GL_ATI_fragment_shader
 151 ---------------------------
 152
 153
 154 1.2.1  SUB - Subtract
 155
 156   dst.x = src0.x - src1.x
 157   dst.y = src0.y - src1.y
 158   dst.z = src0.z - src1.z
 159   dst.w = src0.w - src1.w
 160
 161
 162 1.2.2  DOT3 - 3-component Dot Product
 163
 164   Alias for DP3.
 165
 166
 167 1.2.3  DOT4 - 4-component Dot Product
 168
 169   Alias for DP4.
 170
 171
 172 1.2.4  LERP - Linear Interpolate
 173
 174   dst.x = src0.x * (src1.x - src2.x) + src2.x
 175   dst.y = src0.y * (src1.y - src2.y) + src2.y
 176   dst.z = src0.z * (src1.z - src2.z) + src2.z
 177   dst.w = src0.w * (src1.w - src2.w) + src2.w
 178
 179
 180 1.2.5  CND - Condition
 181
 182   dst.x = (src2.x > 0.5) ? src0.x : src1.x
 183   dst.y = (src2.y > 0.5) ? src0.y : src1.y
 184   dst.z = (src2.z > 0.5) ? src0.z : src1.z
 185   dst.w = (src2.w > 0.5) ? src0.w : src1.w
 186
 187
 188 1.2.6  CND0 - Condition Zero
 189
 190        Removed.  Use (CMP src2, src1, src0) instead.
 191
 192 1.2.7  DOT2ADD - 2-component Dot Product And Add
 193
 194   dst.x = src0.x * src1.x + src0.y * src1.y + src2.x
 195   dst.y = src0.x * src1.x + src0.y * src1.y + src2.x
 196   dst.z = src0.x * src1.x + src0.y * src1.y + src2.x
 197   dst.w = src0.x * src1.x + src0.y * src1.y + src2.x
 198
 199
 200 1.3  GL_EXT_vertex_shader
 201 -------------------------
 202
 203
 204 1.3.1  INDEX - Array Lookup
 205
 206   Considered for removal from language.
 207
 208
 209 1.3.2  NEGATE - Negate
 210
 211   Considered for removal from language.
 212
 213
 214 1.3.3  MADD - Multiply And Add
 215
 216   Alias for MAD.
 217
 218
 219 1.3.4  FRAC - Fraction
 220
 221   dst.x = src.x - floor(src.x)
 222   dst.y = src.y - floor(src.y)
 223   dst.z = src.z - floor(src.z)
 224   dst.w = src.w - floor(src.w)
 225
 226
 227 1.3.5  SETGE - Set On Greater Equal
 228
 229   Alias for SGE.
 230
 231
 232 1.3.6  SETLT - Set On Less Than
 233
 234   Alias for SLT.
 235
 236
 237 1.3.7  CLAMP - Clamp
 238
 239   dst.x = clamp(src0.x, src1.x, src2.x)
 240   dst.y = clamp(src0.y, src1.y, src2.y)
 241   dst.z = clamp(src0.z, src1.z, src2.z)
 242   dst.w = clamp(src0.w, src1.w, src2.w)
 243
 244
 245 1.3.8  FLOOR - Floor
 246
 247   dst.x = floor(src.x)
 248   dst.y = floor(src.y)
 249   dst.z = floor(src.z)
 250   dst.w = floor(src.w)
 251
 252
 253 1.3.9  ROUND - Round
 254
 255   dst.x = round(src.x)
 256   dst.y = round(src.y)
 257   dst.z = round(src.z)
 258   dst.w = round(src.w)
 259
 260
 261 1.3.10  EXPBASE2 - Exponential Base 2
 262
 263   dst.x = pow(2.0, src.x)
 264   dst.y = pow(2.0, src.x)
 265   dst.z = pow(2.0, src.x)
 266   dst.w = pow(2.0, src.x)
 267
 268
 269 1.3.11  LOGBASE2 - Logarithm Base 2
 270
 271   dst.x = lg2(src.x)
 272   dst.y = lg2(src.x)
 273   dst.z = lg2(src.x)
 274   dst.w = lg2(src.x)
 275
 276
 277 1.3.12  POWER - Power
 278
 279   dst.x = pow(src0.x, src1.x)
 280   dst.y = pow(src0.x, src1.x)
 281   dst.z = pow(src0.x, src1.x)
 282   dst.w = pow(src0.x, src1.x)
 283
 284
 285 1.3.13  RECIP - Reciprocal
 286
 287   Alias for RCP.
 288
 289
 290 1.3.14  RECIPSQRT - Reciprocal Square Root
 291
 292   Alias for RSQ.
 293
 294
 295 1.3.15  CROSSPRODUCT - Cross Product
 296
 297   dst.x = src0.y * src1.z - src1.y * src0.z
 298   dst.y = src0.z * src1.x - src1.z * src0.x
 299   dst.z = src0.x * src1.y - src1.x * src0.y
 300   dst.w = 1.0
 301
 302
 303 1.3.16  MULTIPLYMATRIX - Multiply Matrix
 304
 305   Considered for removal from language.
 306
 307
 308 1.4  GL_NV_vertex_program1_1
 309 ----------------------------
 310
 311
 312 1.4.1  ABS - Absolute
 313
 314   dst.x = abs(src.x)
 315   dst.y = abs(src.y)
 316   dst.z = abs(src.z)
 317   dst.w = abs(src.w)
 318
 319
 320 1.4.2  RCC - Reciprocal Clamped
 321
 322   dst.x = (1.0 / src.x) > 0.0 ? clamp(1.0 / src.x, 5.42101e-020, 1.884467e+019) : clamp(1.0 / src.x, -1.884467e+019, -5.42101e-020)
 323   dst.y = (1.0 / src.x) > 0.0 ? clamp(1.0 / src.x, 5.42101e-020, 1.884467e+019) : clamp(1.0 / src.x, -1.884467e+019, -5.42101e-020)
 324   dst.z = (1.0 / src.x) > 0.0 ? clamp(1.0 / src.x, 5.42101e-020, 1.884467e+019) : clamp(1.0 / src.x, -1.884467e+019, -5.42101e-020)
 325   dst.w = (1.0 / src.x) > 0.0 ? clamp(1.0 / src.x, 5.42101e-020, 1.884467e+019) : clamp(1.0 / src.x, -1.884467e+019, -5.42101e-020)
 326
 327
 328 1.4.3  DPH - Homogeneous Dot Product
 329
 330   dst.x = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src1.w
 331   dst.y = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src1.w
 332   dst.z = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src1.w
 333   dst.w = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src1.w
 334
 335
 336 1.5  GL_NV_fragment_program
 337 ---------------------------
 338
 339
 340 1.5.1  COS - Cosine
 341
 342   dst.x = cos(src.x)
 343   dst.y = cos(src.x)
 344   dst.z = cos(src.x)
 345   dst.w = cos(src.w)
 346
 347
 348 1.5.2  DDX - Derivative Relative To X
 349
 350   dst.x = partialx(src.x)
 351   dst.y = partialx(src.y)
 352   dst.z = partialx(src.z)
 353   dst.w = partialx(src.w)
 354
 355
 356 1.5.3  DDY - Derivative Relative To Y
 357
 358   dst.x = partialy(src.x)
 359   dst.y = partialy(src.y)
 360   dst.z = partialy(src.z)
 361   dst.w = partialy(src.w)
 362
 363
 364 1.5.4  EX2 - Exponential Base 2
 365
 366   Alias for EXPBASE2.
 367
 368
 369 1.5.5  FLR - Floor
 370
 371   Alias for FLOOR.
 372
 373
 374 1.5.6  FRC - Fraction
 375
 376   Alias for FRAC.
 377
 378
 379 1.5.7  KILP - Predicated Discard
 380
 381   discard
 382
 383
 384 1.5.8  LG2 - Logarithm Base 2
 385
 386   Alias for LOGBASE2.
 387
 388
 389 1.5.9  LRP - Linear Interpolate
 390
 391   Alias for LERP.
 392
 393
 394 1.5.10  PK2H - Pack Two 16-bit Floats
 395
 396   TBD
 397
 398
 399 1.5.11  PK2US - Pack Two Unsigned 16-bit Scalars
 400
 401   TBD
 402
 403
 404 1.5.12  PK4B - Pack Four Signed 8-bit Scalars
 405
 406   TBD
 407
 408
 409 1.5.13  PK4UB - Pack Four Unsigned 8-bit Scalars
 410
 411   TBD
 412
 413
 414 1.5.14  POW - Power
 415
 416   Alias for POWER.
 417
 418
 419 1.5.15  RFL - Reflection Vector
 420
 421   dst.x = 2.0 * (src0.x * src1.x + src0.y * src1.y + src0.z * src1.z) / (src0.x * src0.x + src0.y * src0.y + src0.z * src0.z) * src0.x - src1.x
 422   dst.y = 2.0 * (src0.x * src1.x + src0.y * src1.y + src0.z * src1.z) / (src0.x * src0.x + src0.y * src0.y + src0.z * src0.z) * src0.y - src1.y
 423   dst.z = 2.0 * (src0.x * src1.x + src0.y * src1.y + src0.z * src1.z) / (src0.x * src0.x + src0.y * src0.y + src0.z * src0.z) * src0.z - src1.z
 424   dst.w = 1.0
 425
 426
 427 1.5.16  SEQ - Set On Equal
 428
 429   dst.x = (src0.x == src1.x) ? 1.0 : 0.0
 430   dst.y = (src0.y == src1.y) ? 1.0 : 0.0
 431   dst.z = (src0.z == src1.z) ? 1.0 : 0.0
 432   dst.w = (src0.w == src1.w) ? 1.0 : 0.0
 433
 434
 435 1.5.17  SFL - Set On False
 436
 437   dst.x = 0.0
 438   dst.y = 0.0
 439   dst.z = 0.0
 440   dst.w = 0.0
 441
 442
 443 1.5.18  SGT - Set On Greater Than
 444
 445   dst.x = (src0.x > src1.x) ? 1.0 : 0.0
 446   dst.y = (src0.y > src1.y) ? 1.0 : 0.0
 447   dst.z = (src0.z > src1.z) ? 1.0 : 0.0
 448   dst.w = (src0.w > src1.w) ? 1.0 : 0.0
 449
 450
 451 1.5.19  SIN - Sine
 452
 453   dst.x = sin(src.x)
 454   dst.y = sin(src.x)
 455   dst.z = sin(src.x)
 456   dst.w = sin(src.w)
 457
 458
 459 1.5.20  SLE - Set On Less Equal Than
 460
 461   dst.x = (src0.x <= src1.x) ? 1.0 : 0.0
 462   dst.y = (src0.y <= src1.y) ? 1.0 : 0.0
 463   dst.z = (src0.z <= src1.z) ? 1.0 : 0.0
 464   dst.w = (src0.w <= src1.w) ? 1.0 : 0.0
 465
 466
 467 1.5.21  SNE - Set On Not Equal
 468
 469   dst.x = (src0.x != src1.x) ? 1.0 : 0.0
 470   dst.y = (src0.y != src1.y) ? 1.0 : 0.0
 471   dst.z = (src0.z != src1.z) ? 1.0 : 0.0
 472   dst.w = (src0.w != src1.w) ? 1.0 : 0.0
 473
 474
 475 1.5.22  STR - Set On True
 476
 477   dst.x = 1.0
 478   dst.y = 1.0
 479   dst.z = 1.0
 480   dst.w = 1.0
 481
 482
 483 1.5.23  TEX - Texture Lookup
 484
 485   TBD
 486
 487
 488 1.5.24  TXD - Texture Lookup with Derivatives
 489
 490   TBD
 491
 492
 493 1.5.25  TXP - Projective Texture Lookup
 494
 495   TBD
 496
 497
 498 1.5.26  UP2H - Unpack Two 16-Bit Floats
 499
 500   TBD
 501
 502
 503 1.5.27  UP2US - Unpack Two Unsigned 16-Bit Scalars
 504
 505   TBD
 506
 507
 508 1.5.28  UP4B - Unpack Four Signed 8-Bit Values
 509
 510   TBD
 511
 512
 513 1.5.29  UP4UB - Unpack Four Unsigned 8-Bit Scalars
 514
 515   TBD
 516
 517
 518 1.5.30  X2D - 2D Coordinate Transformation
 519
 520   dst.x = src0.x + src1.x * src2.x + src1.y * src2.y
 521   dst.y = src0.y + src1.x * src2.z + src1.y * src2.w
 522   dst.z = src0.x + src1.x * src2.x + src1.y * src2.y
 523   dst.w = src0.y + src1.x * src2.z + src1.y * src2.w
 524
 525
 526 1.6  GL_NV_vertex_program2
 527 --------------------------
 528
 529
 530 1.6.1  ARA - Address Register Add
 531
 532   TBD
 533
 534
 535 1.6.2  ARR - Address Register Load With Round
 536
 537   dst.x = round(src.x)
 538   dst.y = round(src.y)
 539   dst.z = round(src.z)
 540   dst.w = round(src.w)
 541
 542
 543 1.6.3  BRA - Branch
 544
 545   pc = target
 546
 547
 548 1.6.4  CAL - Subroutine Call
 549
 550   push(pc)
 551   pc = target
 552
 553
 554 1.6.5  RET - Subroutine Call Return
 555
 556   pc = pop()
 557
 558
 559 1.6.6  SSG - Set Sign
 560
 561   dst.x = (src.x > 0.0) ? 1.0 : (src.x < 0.0) ? -1.0 : 0.0
 562   dst.y = (src.y > 0.0) ? 1.0 : (src.y < 0.0) ? -1.0 : 0.0
 563   dst.z = (src.z > 0.0) ? 1.0 : (src.z < 0.0) ? -1.0 : 0.0
 564   dst.w = (src.w > 0.0) ? 1.0 : (src.w < 0.0) ? -1.0 : 0.0
 565
 566
 567 1.7  GL_ARB_vertex_program
 568 --------------------------
 569
 570
 571 1.7.1  SWZ - Extended Swizzle
 572
 573   dst.x = src.x
 574   dst.y = src.y
 575   dst.z = src.z
 576   dst.w = src.w
 577
 578
 579 1.7.2  XPD - Cross Product
 580
 581   Alias for CROSSPRODUCT.
 582
 583
 584 1.8  GL_ARB_fragment_program
 585 ----------------------------
 586
 587
 588 1.8.1  CMP - Compare
 589
 590   dst.x = (src0.x < 0.0) ? src1.x : src2.x
 591   dst.y = (src0.y < 0.0) ? src1.y : src2.y
 592   dst.z = (src0.z < 0.0) ? src1.z : src2.z
 593   dst.w = (src0.w < 0.0) ? src1.w : src2.w
 594
 595
 596 1.8.2  KIL - Conditional Discard
 597
 598   if (src.x < 0.0 || src.y < 0.0 || src.z < 0.0 || src.w < 0.0)
 599     discard
 600   endif
 601
 602
 603 1.8.3  SCS - Sine Cosine
 604
 605   dst.x = cos(src.x)
 606   dst.y = sin(src.x)
 607   dst.z = 0.0
 608   dst.y = 1.0
 609
 610
 611 1.8.4  TXB - Texture Lookup With Bias
 612
 613   TBD
 614
 615
 616 1.9  GL_NV_fragment_program2
 617 ----------------------------
 618
 619
 620 1.9.1  NRM - 3-component Vector Normalise
 621
 622   dst.x = src.x / (src.x * src.x + src.y * src.y + src.z * src.z)
 623   dst.y = src.y / (src.x * src.x + src.y * src.y + src.z * src.z)
 624   dst.z = src.z / (src.x * src.x + src.y * src.y + src.z * src.z)
 625   dst.w = 1.0
 626
 627
 628 1.9.2  DIV - Divide
 629
 630   dst.x = src0.x / src1.x
 631   dst.y = src0.y / src1.y
 632   dst.z = src0.z / src1.z
 633   dst.w = src0.w / src1.w
 634
 635
 636 1.9.3  DP2 - 2-component Dot Product
 637
 638   dst.x = src0.x * src1.x + src0.y * src1.y
 639   dst.y = src0.x * src1.x + src0.y * src1.y
 640   dst.z = src0.x * src1.x + src0.y * src1.y
 641   dst.w = src0.x * src1.x + src0.y * src1.y
 642
 643
 644 1.9.4  DP2A - 2-component Dot Product And Add
 645
 646   Alias for DOT2ADD.
 647
 648
 649 1.9.5  TXL - Texture Lookup With LOD
 650
 651   TBD
 652
 653
 654 1.9.6  BRK - Break
 655
 656   TBD
 657
 658
 659 1.9.7  IF - If
 660
 661   TBD
 662
 663
 664 1.9.10  ELSE - Else
 665
 666   TBD
 667
 668
 669 1.9.11  ENDIF - End If
 670
 671   TBD
 672
 673
 674 1.10  GL_NV_vertex_program3
 675 ---------------------------
 676
 677
 678 1.10.1  PUSHA - Push Address Register On Stack
 679
 680   push(src.x)
 681   push(src.y)
 682   push(src.z)
 683   push(src.w)
 684
 685
 686 1.10.2  POPA - Pop Address Register From Stack
 687
 688   dst.w = pop()
 689   dst.z = pop()
 690   dst.y = pop()
 691   dst.x = pop()
 692
 693
 694 1.11  GL_NV_gpu_program4
 695 ------------------------
 696
 697
 698 1.11.1  CEIL - Ceiling
 699
 700   dst.x = ceil(src.x)
 701   dst.y = ceil(src.y)
 702   dst.z = ceil(src.z)
 703   dst.w = ceil(src.w)
 704
 705
 706 1.11.2  I2F - Integer To Float
 707
 708   dst.x = (float) src.x
 709   dst.y = (float) src.y
 710   dst.z = (float) src.z
 711   dst.w = (float) src.w
 712
 713
 714 1.11.3  NOT - Bitwise Not
 715
 716   dst.x = ~src.x
 717   dst.y = ~src.y
 718   dst.z = ~src.z
 719   dst.w = ~src.w
 720
 721
 722 1.11.4  TRUNC - Truncate
 723
 724   dst.x = trunc(src.x)
 725   dst.y = trunc(src.y)
 726   dst.z = trunc(src.z)
 727   dst.w = trunc(src.w)
 728
 729
 730 1.11.5  SHL - Shift Left
 731
 732   dst.x = src0.x << src1.x
 733   dst.y = src0.y << src1.x
 734   dst.z = src0.z << src1.x
 735   dst.w = src0.w << src1.x
 736
 737
 738 1.11.6  SHR - Shift Right
 739
 740   dst.x = src0.x >> src1.x
 741   dst.y = src0.y >> src1.x
 742   dst.z = src0.z >> src1.x
 743   dst.w = src0.w >> src1.x
 744
 745
 746 1.11.7  AND - Bitwise And
 747
 748   dst.x = src0.x & src1.x
 749   dst.y = src0.y & src1.y
 750   dst.z = src0.z & src1.z
 751   dst.w = src0.w & src1.w
 752
 753
 754 1.11.8  OR - Bitwise Or
 755
 756   dst.x = src0.x | src1.x
 757   dst.y = src0.y | src1.y
 758   dst.z = src0.z | src1.z
 759   dst.w = src0.w | src1.w
 760
 761
 762 1.11.9  MOD - Modulus
 763
 764   dst.x = src0.x % src1.x
 765   dst.y = src0.y % src1.y
 766   dst.z = src0.z % src1.z
 767   dst.w = src0.w % src1.w
 768
 769
 770 1.11.10  XOR - Bitwise Xor
 771
 772   dst.x = src0.x ^ src1.x
 773   dst.y = src0.y ^ src1.y
 774   dst.z = src0.z ^ src1.z
 775   dst.w = src0.w ^ src1.w
 776
 777
 778 1.11.11  SAD - Sum Of Absolute Differences
 779
 780   dst.x = abs(src0.x - src1.x) + src2.x
 781   dst.y = abs(src0.y - src1.y) + src2.y
 782   dst.z = abs(src0.z - src1.z) + src2.z
 783   dst.w = abs(src0.w - src1.w) + src2.w
 784
 785
 786 1.11.12  TXF - Texel Fetch
 787
 788   TBD
 789
 790
 791 1.11.13  TXQ - Texture Size Query
 792
 793   TBD
 794
 795
 796 1.11.14  CONT - Continue
 797
 798   TBD
 799
 800
 801 1.12  GL_NV_geometry_program4
 802 -----------------------------
 803
 804
 805 1.12.1  EMIT - Emit
 806
 807   TBD
 808
 809
 810 1.12.2  ENDPRIM - End Primitive
 811
 812   TBD
 813
 814
 815 1.13  GLSL
 816 ----------
 817
 818
 819 1.13.1  BGNLOOP - Begin a Loop
 820
 821   TBD
 822
 823
 824 1.13.2  BGNSUB - Begin Subroutine
 825
 826   TBD
 827
 828
 829 1.13.3  ENDLOOP - End a Loop
 830
 831   TBD
 832
 833
 834 1.13.4  ENDSUB - End Subroutine
 835
 836   TBD
 837
 838
 839 1.13.5  INT - Truncate
 840
 841   Alias for TRUNC.
 842
 843
 844 1.13.6  NOISE1 - 1D Noise
 845
 846   TBD
 847
 848
 849 1.13.7  NOISE2 - 2D Noise
 850
 851   TBD
 852
 853
 854 1.13.8  NOISE3 - 3D Noise
 855
 856   TBD
 857
 858
 859 1.13.9  NOISE4 - 4D Noise
 860
 861   TBD
 862
 863
 864 1.13.10  NOP - No Operation
 865
 866   Do nothing.
 867
 868
 869 1.14  ps_1_1
 870 ------------
 871
 872
 873 1.14.1  TEXKILL - Conditional Discard
 874
 875   Alias for KIL.
 876
 877
 878 1.15  ps_1_4
 879 ------------
 880
 881
 882 1.15.1  TEXLD - Texture Lookup
 883
 884   Alias for TEX.
 885
 886
 887 1.16  ps_2_0
 888 ------------
 889
 890
 891 1.16.1  M4X4 - Multiply Matrix
 892
 893   Alias for MULTIPLYMATRIX.
 894
 895
 896 1.16.2  M4X3 - Multiply Matrix
 897
 898   Considered for removal from language.
 899
 900
 901 1.16.3  M3X4 - Multiply Matrix
 902
 903   Considered for removal from language.
 904
 905
 906 1.16.4  M3X3 - Multiply Matrix
 907
 908   Considered for removal from language.
 909
 910
 911 1.16.5  M3X2 - Multiply Matrix
 912
 913   Considered for removal from language.
 914
 915
 916 1.16.6  CRS - Cross Product
 917
 918   Alias for XPD.
 919
 920
 921 1.16.7  NRM4 - 4-component Vector Normalise
 922
 923   dst.x = src.x / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w)
 924   dst.y = src.y / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w)
 925   dst.z = src.z / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w)
 926   dst.w = src.w / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w)
 927
 928
 929 1.16.8  SINCOS - Sine Cosine
 930
 931   Alias for SCS.
 932
 933
 934 1.16.9  TEXLDB - Texture Lookup With Bias
 935
 936   Alias for TXB.
 937
 938
 939 1.16.10  DP2ADD - 2-component Dot Product And Add
 940
 941   Alias for DP2A.
 942
 943
 944 1.17  ps_2_x
 945 ------------
 946
 947
 948 1.17.1  CALL - Subroutine Call
 949
 950   Alias for CAL.
 951
 952
 953 1.17.2  CALLNZ - Subroutine Call If Not Zero
 954
 955   TBD
 956
 957
 958 1.17.3  IFC - If
 959
 960   TBD
 961
 962
 963 1.17.4  BREAK - Break
 964
 965   Alias for BRK.
 966
 967
 968 1.17.5  BREAKC - Break Conditional
 969
 970   TBD
 971
 972
 973 1.17.6  DSX - Derivative Relative To X
 974
 975   Alias for DDX.
 976
 977
 978 1.17.7  DSY - Derivative Relative To Y
 979
 980   Alias for DDY.
 981
 982
 983 1.17.8  TEXLDD - Texture Lookup with Derivatives
 984
 985   Alias for TXD.
 986
 987
 988 1.18  vs_1_1
 989 ------------
 990
 991
 992 1.18.1  EXPP - Approximate Exponential Base 2
 993
 994   Use EXP. See also 1.19.3.
 995
 996
 997 1.18.2  LOGP - Logarithm Base 2
 998
 999   Use LOG. See also 1.19.4.
1000
1001
1002 1.19  vs_2_0
1003 ------------
1004
1005
1006 1.19.1  SGN - Set Sign
1007
1008   Alias for SSG.
1009
1010
1011 1.19.2  MOVA - Move Address Register
1012
1013   Alias for ARR.
1014
1015
1016 1.19.3  EXPP - Approximate Exponential Base 2
1017
1018   Use EX2.
1019
1020
1021 1.19.4  LOGP - Logarithm Base 2
1022
1023   Use LG2.
1024
1025
1026 2  Explanation of symbols used
1027 ==============================
1028
1029
1030 2.1  Functions
1031 --------------
1032
1033
1034   abs(x)            Absolute value of x.
1035                     |x|
1036                     (x < 0.0) ? -x : x
1037
1038   ceil(x)           Ceiling of x.
1039
1040   clamp(x,y,z)      Clamp x between y and z.
1041                     (x < y) ? y : (x > z) ? z : x
1042
1043   cos(x)            Cosine of x.
1044
1045   floor(x)          Floor of x.
1046
1047   lg2(x)            Logarithm base 2 of x.
1048
1049   max(x,y)          Maximum of x and y.
1050                     (x > y) ? x : y
1051
1052   min(x,y)          Minimum of x and y.
1053                     (x < y) ? x : y
1054
1055   partialx(x)       Derivative of x relative to fragment's X.
1056
1057   partialy(x)       Derivative of x relative to fragment's Y.
1058
1059   pop()             Pop from stack.
1060
1061   pow(x,y)          Raise x to power of y.
1062
1063   push(x)           Push x on stack.
1064
1065   round(x)          Round x.
1066
1067   sin(x)            Sine of x.
1068
1069   sqrt(x)           Square root of x.
1070
1071   trunc(x)          Truncate x.
1072
1073
1074 2.2  Keywords
1075 -------------
1076
1077
1078   discard           Discard fragment.
1079
1080   dst               First destination register.
1081
1082   dst0              First destination register.
1083
1084   pc                Program counter.
1085
1086   src               First source register.
1087
1088   src0              First source register.
1089
1090   src1              Second source register.
1091
1092   src2              Third source register.
1093
1094   target            Label of target instruction.
1095
1096
1097 3  Other tokens
1098 ===============
1099
1100
1101 3.1  Declaration Semantic
1102 -------------------------
1103
1104
1105   Follows Declaration token if Semantic bit is set.
1106
1107   Since its purpose is to link a shader with other stages of the pipeline,
1108   it is valid to follow only those Declaration tokens that declare a register
1109   either in INPUT or OUTPUT file.
1110
1111   SemanticName field contains the semantic name of the register being declared.
1112   There is no default value.
1113
1114   SemanticIndex is an optional subscript that can be used to distinguish
1115   different register declarations with the same semantic name. The default value
1116   is 0.
1117
1118   The meanings of the individual semantic names are explained in the following
1119   sections.
1120
1121
1122 3.1.1  FACE
1123
1124   Valid only in a fragment shader INPUT declaration.
1125
1126   FACE.x is negative when the primitive is back facing. FACE.x is positive
1127   when the primitive is front facing.