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 1.9.8  BGNFOR - Begin a For-Loop
 665
 666   dst.x = floor(src.x)
 667   dst.y = floor(src.y)
 668   dst.z = floor(src.z)
 669
 670   if (dst.y <= 0)
 671     pc = [matching ENDFOR] + 1
 672   endif
 673
 674   Note: The destination must be a loop register.
 675         The source must be a constant register.
 676
 677
 678 1.9.9  REP - Repeat
 679
 680   TBD
 681
 682
 683 1.9.10  ELSE - Else
 684
 685   TBD
 686
 687
 688 1.9.11  ENDIF - End If
 689
 690   TBD
 691
 692
 693 1.9.12  ENDFOR - End a For-Loop
 694
 695   dst.x = dst.x + dst.z
 696   dst.y = dst.y - 1.0
 697
 698   if (dst.y > 0)
 699     pc = [matching BGNFOR instruction] + 1
 700   endif
 701
 702   Note: The destination must be a loop register.
 703
 704
 705 1.9.13  ENDREP - End Repeat
 706
 707   TBD
 708
 709
 710 1.10  GL_NV_vertex_program3
 711 ---------------------------
 712
 713
 714 1.10.1  PUSHA - Push Address Register On Stack
 715
 716   push(src.x)
 717   push(src.y)
 718   push(src.z)
 719   push(src.w)
 720
 721
 722 1.10.2  POPA - Pop Address Register From Stack
 723
 724   dst.w = pop()
 725   dst.z = pop()
 726   dst.y = pop()
 727   dst.x = pop()
 728
 729
 730 1.11  GL_NV_gpu_program4
 731 ------------------------
 732
 733
 734 1.11.1  CEIL - Ceiling
 735
 736   dst.x = ceil(src.x)
 737   dst.y = ceil(src.y)
 738   dst.z = ceil(src.z)
 739   dst.w = ceil(src.w)
 740
 741
 742 1.11.2  I2F - Integer To Float
 743
 744   dst.x = (float) src.x
 745   dst.y = (float) src.y
 746   dst.z = (float) src.z
 747   dst.w = (float) src.w
 748
 749
 750 1.11.3  NOT - Bitwise Not
 751
 752   dst.x = ~src.x
 753   dst.y = ~src.y
 754   dst.z = ~src.z
 755   dst.w = ~src.w
 756
 757
 758 1.11.4  TRUNC - Truncate
 759
 760   dst.x = trunc(src.x)
 761   dst.y = trunc(src.y)
 762   dst.z = trunc(src.z)
 763   dst.w = trunc(src.w)
 764
 765
 766 1.11.5  SHL - Shift Left
 767
 768   dst.x = src0.x << src1.x
 769   dst.y = src0.y << src1.x
 770   dst.z = src0.z << src1.x
 771   dst.w = src0.w << src1.x
 772
 773
 774 1.11.6  SHR - Shift Right
 775
 776   dst.x = src0.x >> src1.x
 777   dst.y = src0.y >> src1.x
 778   dst.z = src0.z >> src1.x
 779   dst.w = src0.w >> src1.x
 780
 781
 782 1.11.7  AND - Bitwise And
 783
 784   dst.x = src0.x & src1.x
 785   dst.y = src0.y & src1.y
 786   dst.z = src0.z & src1.z
 787   dst.w = src0.w & src1.w
 788
 789
 790 1.11.8  OR - Bitwise Or
 791
 792   dst.x = src0.x | src1.x
 793   dst.y = src0.y | src1.y
 794   dst.z = src0.z | src1.z
 795   dst.w = src0.w | src1.w
 796
 797
 798 1.11.9  MOD - Modulus
 799
 800   dst.x = src0.x % src1.x
 801   dst.y = src0.y % src1.y
 802   dst.z = src0.z % src1.z
 803   dst.w = src0.w % src1.w
 804
 805
 806 1.11.10  XOR - Bitwise Xor
 807
 808   dst.x = src0.x ^ src1.x
 809   dst.y = src0.y ^ src1.y
 810   dst.z = src0.z ^ src1.z
 811   dst.w = src0.w ^ src1.w
 812
 813
 814 1.11.11  SAD - Sum Of Absolute Differences
 815
 816   dst.x = abs(src0.x - src1.x) + src2.x
 817   dst.y = abs(src0.y - src1.y) + src2.y
 818   dst.z = abs(src0.z - src1.z) + src2.z
 819   dst.w = abs(src0.w - src1.w) + src2.w
 820
 821
 822 1.11.12  TXF - Texel Fetch
 823
 824   TBD
 825
 826
 827 1.11.13  TXQ - Texture Size Query
 828
 829   TBD
 830
 831
 832 1.11.14  CONT - Continue
 833
 834   TBD
 835
 836
 837 1.12  GL_NV_geometry_program4
 838 -----------------------------
 839
 840
 841 1.12.1  EMIT - Emit
 842
 843   TBD
 844
 845
 846 1.12.2  ENDPRIM - End Primitive
 847
 848   TBD
 849
 850
 851 1.13  GLSL
 852 ----------
 853
 854
 855 1.13.1  BGNLOOP - Begin a Loop
 856
 857   TBD
 858
 859
 860 1.13.2  BGNSUB - Begin Subroutine
 861
 862   TBD
 863
 864
 865 1.13.3  ENDLOOP - End a Loop
 866
 867   TBD
 868
 869
 870 1.13.4  ENDSUB - End Subroutine
 871
 872   TBD
 873
 874
 875 1.13.5  INT - Truncate
 876
 877   Alias for TRUNC.
 878
 879
 880 1.13.6  NOISE1 - 1D Noise
 881
 882   TBD
 883
 884
 885 1.13.7  NOISE2 - 2D Noise
 886
 887   TBD
 888
 889
 890 1.13.8  NOISE3 - 3D Noise
 891
 892   TBD
 893
 894
 895 1.13.9  NOISE4 - 4D Noise
 896
 897   TBD
 898
 899
 900 1.13.10  NOP - No Operation
 901
 902   Do nothing.
 903
 904
 905 1.14  ps_1_1
 906 ------------
 907
 908
 909 1.14.1  TEXKILL - Conditional Discard
 910
 911   Alias for KIL.
 912
 913
 914 1.15  ps_1_4
 915 ------------
 916
 917
 918 1.15.1  TEXLD - Texture Lookup
 919
 920   Alias for TEX.
 921
 922
 923 1.16  ps_2_0
 924 ------------
 925
 926
 927 1.16.1  M4X4 - Multiply Matrix
 928
 929   Alias for MULTIPLYMATRIX.
 930
 931
 932 1.16.2  M4X3 - Multiply Matrix
 933
 934   Considered for removal from language.
 935
 936
 937 1.16.3  M3X4 - Multiply Matrix
 938
 939   Considered for removal from language.
 940
 941
 942 1.16.4  M3X3 - Multiply Matrix
 943
 944   Considered for removal from language.
 945
 946
 947 1.16.5  M3X2 - Multiply Matrix
 948
 949   Considered for removal from language.
 950
 951
 952 1.16.6  CRS - Cross Product
 953
 954   Alias for XPD.
 955
 956
 957 1.16.7  NRM4 - 4-component Vector Normalise
 958
 959   dst.x = src.x / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w)
 960   dst.y = src.y / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w)
 961   dst.z = src.z / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w)
 962   dst.w = src.w / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w)
 963
 964
 965 1.16.8  SINCOS - Sine Cosine
 966
 967   Alias for SCS.
 968
 969
 970 1.16.9  TEXLDB - Texture Lookup With Bias
 971
 972   Alias for TXB.
 973
 974
 975 1.16.10  DP2ADD - 2-component Dot Product And Add
 976
 977   Alias for DP2A.
 978
 979
 980 1.17  ps_2_x
 981 ------------
 982
 983
 984 1.17.1  CALL - Subroutine Call
 985
 986   Alias for CAL.
 987
 988
 989 1.17.2  CALLNZ - Subroutine Call If Not Zero
 990
 991   TBD
 992
 993
 994 1.17.3  IFC - If
 995
 996   TBD
 997
 998
 999 1.17.4  BREAK - Break
1000
1001   Alias for BRK.
1002
1003
1004 1.17.5  BREAKC - Break Conditional
1005
1006   TBD
1007
1008
1009 1.17.6  DSX - Derivative Relative To X
1010
1011   Alias for DDX.
1012
1013
1014 1.17.7  DSY - Derivative Relative To Y
1015
1016   Alias for DDY.
1017
1018
1019 1.17.8  TEXLDD - Texture Lookup with Derivatives
1020
1021   Alias for TXD.
1022
1023
1024 1.18  vs_1_1
1025 ------------
1026
1027
1028 1.18.1  EXPP - Approximate Exponential Base 2
1029
1030   Use EXP. See also 1.19.3.
1031
1032
1033 1.18.2  LOGP - Logarithm Base 2
1034
1035   Use LOG. See also 1.19.4.
1036
1037
1038 1.19  vs_2_0
1039 ------------
1040
1041
1042 1.19.1  SGN - Set Sign
1043
1044   Alias for SSG.
1045
1046
1047 1.19.2  MOVA - Move Address Register
1048
1049   Alias for ARR.
1050
1051
1052 1.19.3  EXPP - Approximate Exponential Base 2
1053
1054   Use EX2.
1055
1056
1057 1.19.4  LOGP - Logarithm Base 2
1058
1059   Use LG2.
1060
1061
1062 2  Explanation of symbols used
1063 ==============================
1064
1065
1066 2.1  Functions
1067 --------------
1068
1069
1070   abs(x)            Absolute value of x.
1071                     |x|
1072                     (x < 0.0) ? -x : x
1073
1074   ceil(x)           Ceiling of x.
1075
1076   clamp(x,y,z)      Clamp x between y and z.
1077                     (x < y) ? y : (x > z) ? z : x
1078
1079   cos(x)            Cosine of x.
1080
1081   floor(x)          Floor of x.
1082
1083   lg2(x)            Logarithm base 2 of x.
1084
1085   max(x,y)          Maximum of x and y.
1086                     (x > y) ? x : y
1087
1088   min(x,y)          Minimum of x and y.
1089                     (x < y) ? x : y
1090
1091   partialx(x)       Derivative of x relative to fragment's X.
1092
1093   partialy(x)       Derivative of x relative to fragment's Y.
1094
1095   pop()             Pop from stack.
1096
1097   pow(x,y)          Raise x to power of y.
1098
1099   push(x)           Push x on stack.
1100
1101   round(x)          Round x.
1102
1103   sin(x)            Sine of x.
1104
1105   sqrt(x)           Square root of x.
1106
1107   trunc(x)          Truncate x.
1108
1109
1110 2.2  Keywords
1111 -------------
1112
1113
1114   discard           Discard fragment.
1115
1116   dst               First destination register.
1117
1118   dst0              First destination register.
1119
1120   pc                Program counter.
1121
1122   src               First source register.
1123
1124   src0              First source register.
1125
1126   src1              Second source register.
1127
1128   src2              Third source register.
1129
1130   target            Label of target instruction.
1131
1132
1133 3  Other tokens
1134 ===============
1135
1136
1137 3.1  Declaration Semantic
1138 -------------------------
1139
1140
1141   Follows Declaration token if Semantic bit is set.
1142
1143   Since its purpose is to link a shader with other stages of the pipeline,
1144   it is valid to follow only those Declaration tokens that declare a register
1145   either in INPUT or OUTPUT file.
1146
1147   SemanticName field contains the semantic name of the register being declared.
1148   There is no default value.
1149
1150   SemanticIndex is an optional subscript that can be used to distinguish
1151   different register declarations with the same semantic name. The default value
1152   is 0.
1153
1154   The meanings of the individual semantic names are explained in the following
1155   sections.
1156
1157
1158 3.1.1  FACE
1159
1160   Valid only in a fragment shader INPUT declaration.
1161
1162   FACE.x is negative when the primitive is back facing. FACE.x is positive
1163   when the primitive is front facing.