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   dst.x = (src2.x >= 0.0) ? src0.x : src1.x
 191   dst.y = (src2.y >= 0.0) ? src0.y : src1.y
 192   dst.z = (src2.z >= 0.0) ? src0.z : src1.z
 193   dst.w = (src2.w >= 0.0) ? src0.w : src1.w
 194
 195
 196 1.2.7  DOT2ADD - 2-component Dot Product And Add
 197
 198   dst.x = src0.x * src1.x + src0.y * src1.y + src2.x
 199   dst.y = src0.x * src1.x + src0.y * src1.y + src2.x
 200   dst.z = src0.x * src1.x + src0.y * src1.y + src2.x
 201   dst.w = src0.x * src1.x + src0.y * src1.y + src2.x
 202
 203
 204 1.3  GL_EXT_vertex_shader
 205 -------------------------
 206
 207
 208 1.3.1  INDEX - Array Lookup
 209
 210   Considered for removal from language.
 211
 212
 213 1.3.2  NEGATE - Negate
 214
 215   Considered for removal from language.
 216
 217
 218 1.3.3  MADD - Multiply And Add
 219
 220   Alias for MAD.
 221
 222
 223 1.3.4  FRAC - Fraction
 224
 225   dst.x = src.x - floor(src.x)
 226   dst.y = src.y - floor(src.y)
 227   dst.z = src.z - floor(src.z)
 228   dst.w = src.w - floor(src.w)
 229
 230
 231 1.3.5  SETGE - Set On Greater Equal
 232
 233   Alias for SGE.
 234
 235
 236 1.3.6  SETLT - Set On Less Than
 237
 238   Alias for SLT.
 239
 240
 241 1.3.7  CLAMP - Clamp
 242
 243   dst.x = clamp(src0.x, src1.x, src2.x)
 244   dst.y = clamp(src0.y, src1.y, src2.y)
 245   dst.z = clamp(src0.z, src1.z, src2.z)
 246   dst.w = clamp(src0.w, src1.w, src2.w)
 247
 248
 249 1.3.8  FLOOR - Floor
 250
 251   dst.x = floor(src.x)
 252   dst.y = floor(src.y)
 253   dst.z = floor(src.z)
 254   dst.w = floor(src.w)
 255
 256
 257 1.3.9  ROUND - Round
 258
 259   dst.x = round(src.x)
 260   dst.y = round(src.y)
 261   dst.z = round(src.z)
 262   dst.w = round(src.w)
 263
 264
 265 1.3.10  EXPBASE2 - Exponential Base 2
 266
 267   dst.x = pow(2.0, src.x)
 268   dst.y = pow(2.0, src.x)
 269   dst.z = pow(2.0, src.x)
 270   dst.w = pow(2.0, src.x)
 271
 272
 273 1.3.11  LOGBASE2 - Logarithm Base 2
 274
 275   dst.x = lg2(src.x)
 276   dst.y = lg2(src.x)
 277   dst.z = lg2(src.x)
 278   dst.w = lg2(src.x)
 279
 280
 281 1.3.12  POWER - Power
 282
 283   dst.x = pow(src0.x, src1.x)
 284   dst.y = pow(src0.x, src1.x)
 285   dst.z = pow(src0.x, src1.x)
 286   dst.w = pow(src0.x, src1.x)
 287
 288
 289 1.3.13  RECIP - Reciprocal
 290
 291   Alias for RCP.
 292
 293
 294 1.3.14  RECIPSQRT - Reciprocal Square Root
 295
 296   Alias for RSQ.
 297
 298
 299 1.3.15  CROSSPRODUCT - Cross Product
 300
 301   dst.x = src0.y * src1.z - src1.y * src0.z
 302   dst.y = src0.z * src1.x - src1.z * src0.x
 303   dst.z = src0.x * src1.y - src1.x * src0.y
 304   dst.w = 1.0
 305
 306
 307 1.3.16  MULTIPLYMATRIX - Multiply Matrix
 308
 309   Considered for removal from language.
 310
 311
 312 1.4  GL_NV_vertex_program1_1
 313 ----------------------------
 314
 315
 316 1.4.1  ABS - Absolute
 317
 318   dst.x = abs(src.x)
 319   dst.y = abs(src.y)
 320   dst.z = abs(src.z)
 321   dst.w = abs(src.w)
 322
 323
 324 1.4.2  RCC - Reciprocal Clamped
 325
 326   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)
 327   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)
 328   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)
 329   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)
 330
 331
 332 1.4.3  DPH - Homogeneous Dot Product
 333
 334   dst.x = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src1.w
 335   dst.y = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src1.w
 336   dst.z = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src1.w
 337   dst.w = src0.x * src1.x + src0.y * src1.y + src0.z * src1.z + src1.w
 338
 339
 340 1.5  GL_NV_fragment_program
 341 ---------------------------
 342
 343
 344 1.5.1  COS - Cosine
 345
 346   dst.x = cos(src.x)
 347   dst.y = cos(src.x)
 348   dst.z = cos(src.x)
 349   dst.w = cos(src.w)
 350
 351
 352 1.5.2  DDX - Derivative Relative To X
 353
 354   dst.x = partialx(src.x)
 355   dst.y = partialx(src.y)
 356   dst.z = partialx(src.z)
 357   dst.w = partialx(src.w)
 358
 359
 360 1.5.3  DDY - Derivative Relative To Y
 361
 362   dst.x = partialy(src.x)
 363   dst.y = partialy(src.y)
 364   dst.z = partialy(src.z)
 365   dst.w = partialy(src.w)
 366
 367
 368 1.5.4  EX2 - Exponential Base 2
 369
 370   Alias for EXPBASE2.
 371
 372
 373 1.5.5  FLR - Floor
 374
 375   Alias for FLOOR.
 376
 377
 378 1.5.6  FRC - Fraction
 379
 380   Alias for FRAC.
 381
 382
 383 1.5.7  KILP - Predicated Discard
 384
 385   discard
 386
 387
 388 1.5.8  LG2 - Logarithm Base 2
 389
 390   Alias for LOGBASE2.
 391
 392
 393 1.5.9  LRP - Linear Interpolate
 394
 395   Alias for LERP.
 396
 397
 398 1.5.10  PK2H - Pack Two 16-bit Floats
 399
 400   TBD
 401
 402
 403 1.5.11  PK2US - Pack Two Unsigned 16-bit Scalars
 404
 405   TBD
 406
 407
 408 1.5.12  PK4B - Pack Four Signed 8-bit Scalars
 409
 410   TBD
 411
 412
 413 1.5.13  PK4UB - Pack Four Unsigned 8-bit Scalars
 414
 415   TBD
 416
 417
 418 1.5.14  POW - Power
 419
 420   Alias for POWER.
 421
 422
 423 1.5.15  RFL - Reflection Vector
 424
 425   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
 426   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
 427   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
 428   dst.w = 1.0
 429
 430
 431 1.5.16  SEQ - Set On Equal
 432
 433   dst.x = (src0.x == src1.x) ? 1.0 : 0.0
 434   dst.y = (src0.y == src1.y) ? 1.0 : 0.0
 435   dst.z = (src0.z == src1.z) ? 1.0 : 0.0
 436   dst.w = (src0.w == src1.w) ? 1.0 : 0.0
 437
 438
 439 1.5.17  SFL - Set On False
 440
 441   dst.x = 0.0
 442   dst.y = 0.0
 443   dst.z = 0.0
 444   dst.w = 0.0
 445
 446
 447 1.5.18  SGT - Set On Greater Than
 448
 449   dst.x = (src0.x > src1.x) ? 1.0 : 0.0
 450   dst.y = (src0.y > src1.y) ? 1.0 : 0.0
 451   dst.z = (src0.z > src1.z) ? 1.0 : 0.0
 452   dst.w = (src0.w > src1.w) ? 1.0 : 0.0
 453
 454
 455 1.5.19  SIN - Sine
 456
 457   dst.x = sin(src.x)
 458   dst.y = sin(src.x)
 459   dst.z = sin(src.x)
 460   dst.w = sin(src.w)
 461
 462
 463 1.5.20  SLE - Set On Less Equal Than
 464
 465   dst.x = (src0.x <= src1.x) ? 1.0 : 0.0
 466   dst.y = (src0.y <= src1.y) ? 1.0 : 0.0
 467   dst.z = (src0.z <= src1.z) ? 1.0 : 0.0
 468   dst.w = (src0.w <= src1.w) ? 1.0 : 0.0
 469
 470
 471 1.5.21  SNE - Set On Not Equal
 472
 473   dst.x = (src0.x != src1.x) ? 1.0 : 0.0
 474   dst.y = (src0.y != src1.y) ? 1.0 : 0.0
 475   dst.z = (src0.z != src1.z) ? 1.0 : 0.0
 476   dst.w = (src0.w != src1.w) ? 1.0 : 0.0
 477
 478
 479 1.5.22  STR - Set On True
 480
 481   dst.x = 1.0
 482   dst.y = 1.0
 483   dst.z = 1.0
 484   dst.w = 1.0
 485
 486
 487 1.5.23  TEX - Texture Lookup
 488
 489   TBD
 490
 491
 492 1.5.24  TXD - Texture Lookup with Derivatives
 493
 494   TBD
 495
 496
 497 1.5.25  TXP - Projective Texture Lookup
 498
 499   TBD
 500
 501
 502 1.5.26  UP2H - Unpack Two 16-Bit Floats
 503
 504   TBD
 505
 506
 507 1.5.27  UP2US - Unpack Two Unsigned 16-Bit Scalars
 508
 509   TBD
 510
 511
 512 1.5.28  UP4B - Unpack Four Signed 8-Bit Values
 513
 514   TBD
 515
 516
 517 1.5.29  UP4UB - Unpack Four Unsigned 8-Bit Scalars
 518
 519   TBD
 520
 521
 522 1.5.30  X2D - 2D Coordinate Transformation
 523
 524   dst.x = src0.x + src1.x * src2.x + src1.y * src2.y
 525   dst.y = src0.y + src1.x * src2.z + src1.y * src2.w
 526   dst.z = src0.x + src1.x * src2.x + src1.y * src2.y
 527   dst.w = src0.y + src1.x * src2.z + src1.y * src2.w
 528
 529
 530 1.6  GL_NV_vertex_program2
 531 --------------------------
 532
 533
 534 1.6.1  ARA - Address Register Add
 535
 536   TBD
 537
 538
 539 1.6.2  ARR - Address Register Load With Round
 540
 541   dst.x = round(src.x)
 542   dst.y = round(src.y)
 543   dst.z = round(src.z)
 544   dst.w = round(src.w)
 545
 546
 547 1.6.3  BRA - Branch
 548
 549   pc = target
 550
 551
 552 1.6.4  CAL - Subroutine Call
 553
 554   push(pc)
 555   pc = target
 556
 557
 558 1.6.5  RET - Subroutine Call Return
 559
 560   pc = pop()
 561
 562
 563 1.6.6  SSG - Set Sign
 564
 565   dst.x = (src.x > 0.0) ? 1.0 : (src.x < 0.0) ? -1.0 : 0.0
 566   dst.y = (src.y > 0.0) ? 1.0 : (src.y < 0.0) ? -1.0 : 0.0
 567   dst.z = (src.z > 0.0) ? 1.0 : (src.z < 0.0) ? -1.0 : 0.0
 568   dst.w = (src.w > 0.0) ? 1.0 : (src.w < 0.0) ? -1.0 : 0.0
 569
 570
 571 1.7  GL_ARB_vertex_program
 572 --------------------------
 573
 574
 575 1.7.1  SWZ - Extended Swizzle
 576
 577   dst.x = src.x
 578   dst.y = src.y
 579   dst.z = src.z
 580   dst.w = src.w
 581
 582
 583 1.7.2  XPD - Cross Product
 584
 585   Alias for CROSSPRODUCT.
 586
 587
 588 1.8  GL_ARB_fragment_program
 589 ----------------------------
 590
 591
 592 1.8.1  CMP - Compare
 593
 594   dst.x = (src0.x < 0.0) ? src1.x : src2.x
 595   dst.y = (src0.y < 0.0) ? src1.y : src2.y
 596   dst.z = (src0.z < 0.0) ? src1.z : src2.z
 597   dst.w = (src0.w < 0.0) ? src1.w : src2.w
 598
 599
 600 1.8.2  KIL - Conditional Discard
 601
 602   if (src.x < 0.0 || src.y < 0.0 || src.z < 0.0 || src.w < 0.0)
 603     discard
 604   endif
 605
 606
 607 1.8.3  SCS - Sine Cosine
 608
 609   dst.x = cos(src.x)
 610   dst.y = sin(src.x)
 611   dst.z = 0.0
 612   dst.y = 1.0
 613
 614
 615 1.8.4  TXB - Texture Lookup With Bias
 616
 617   TBD
 618
 619
 620 1.9  GL_NV_fragment_program2
 621 ----------------------------
 622
 623
 624 1.9.1  NRM - 3-component Vector Normalise
 625
 626   dst.x = src.x / (src.x * src.x + src.y * src.y + src.z * src.z)
 627   dst.y = src.y / (src.x * src.x + src.y * src.y + src.z * src.z)
 628   dst.z = src.z / (src.x * src.x + src.y * src.y + src.z * src.z)
 629   dst.w = 1.0
 630
 631
 632 1.9.2  DIV - Divide
 633
 634   dst.x = src0.x / src1.x
 635   dst.y = src0.y / src1.y
 636   dst.z = src0.z / src1.z
 637   dst.w = src0.w / src1.w
 638
 639
 640 1.9.3  DP2 - 2-component Dot Product
 641
 642   dst.x = src0.x * src1.x + src0.y * src1.y
 643   dst.y = src0.x * src1.x + src0.y * src1.y
 644   dst.z = src0.x * src1.x + src0.y * src1.y
 645   dst.w = src0.x * src1.x + src0.y * src1.y
 646
 647
 648 1.9.4  DP2A - 2-component Dot Product And Add
 649
 650   Alias for DOT2ADD.
 651
 652
 653 1.9.5  TXL - Texture Lookup With LOD
 654
 655   TBD
 656
 657
 658 1.9.6  BRK - Break
 659
 660   TBD
 661
 662
 663 1.9.7  IF - If
 664
 665   TBD
 666
 667
 668 1.9.8  LOOP - Loop
 669
 670   TBD
 671
 672
 673 1.9.9  REP - Repeat
 674
 675   TBD
 676
 677
 678 1.9.10  ELSE - Else
 679
 680   TBD
 681
 682
 683 1.9.11  ENDIF - End If
 684
 685   TBD
 686
 687
 688 1.9.12  ENDLOOP - End Loop
 689
 690   TBD
 691
 692
 693 1.9.13  ENDREP - End Repeat
 694
 695   TBD
 696
 697
 698 1.10  GL_NV_vertex_program3
 699 ---------------------------
 700
 701
 702 1.10.1  PUSHA - Push Address Register On Stack
 703
 704   push(src.x)
 705   push(src.y)
 706   push(src.z)
 707   push(src.w)
 708
 709
 710 1.10.2  POPA - Pop Address Register From Stack
 711
 712   dst.w = pop()
 713   dst.z = pop()
 714   dst.y = pop()
 715   dst.x = pop()
 716
 717
 718 1.11  GL_NV_gpu_program4
 719 ------------------------
 720
 721
 722 1.11.1  CEIL - Ceiling
 723
 724   dst.x = ceil(src.x)
 725   dst.y = ceil(src.y)
 726   dst.z = ceil(src.z)
 727   dst.w = ceil(src.w)
 728
 729
 730 1.11.2  I2F - Integer To Float
 731
 732   dst.x = (float) src.x
 733   dst.y = (float) src.y
 734   dst.z = (float) src.z
 735   dst.w = (float) src.w
 736
 737
 738 1.11.3  NOT - Bitwise Not
 739
 740   dst.x = ~src.x
 741   dst.y = ~src.y
 742   dst.z = ~src.z
 743   dst.w = ~src.w
 744
 745
 746 1.11.4  TRUNC - Truncate
 747
 748   dst.x = trunc(src.x)
 749   dst.y = trunc(src.y)
 750   dst.z = trunc(src.z)
 751   dst.w = trunc(src.w)
 752
 753
 754 1.11.5  SHL - Shift Left
 755
 756   dst.x = src0.x << src1.x
 757   dst.y = src0.y << src1.x
 758   dst.z = src0.z << src1.x
 759   dst.w = src0.w << src1.x
 760
 761
 762 1.11.6  SHR - Shift Right
 763
 764   dst.x = src0.x >> src1.x
 765   dst.y = src0.y >> src1.x
 766   dst.z = src0.z >> src1.x
 767   dst.w = src0.w >> src1.x
 768
 769
 770 1.11.7  AND - Bitwise And
 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 1.11.8  OR - Bitwise Or
 779
 780   dst.x = src0.x | src1.x
 781   dst.y = src0.y | src1.y
 782   dst.z = src0.z | src1.z
 783   dst.w = src0.w | src1.w
 784
 785
 786 1.11.9  MOD - Modulus
 787
 788   dst.x = src0.x % src1.x
 789   dst.y = src0.y % src1.y
 790   dst.z = src0.z % src1.z
 791   dst.w = src0.w % src1.w
 792
 793
 794 1.11.10  XOR - Bitwise Xor
 795
 796   dst.x = src0.x ^ src1.x
 797   dst.y = src0.y ^ src1.y
 798   dst.z = src0.z ^ src1.z
 799   dst.w = src0.w ^ src1.w
 800
 801
 802 1.11.11  SAD - Sum Of Absolute Differences
 803
 804   dst.x = abs(src0.x - src1.x) + src2.x
 805   dst.y = abs(src0.y - src1.y) + src2.y
 806   dst.z = abs(src0.z - src1.z) + src2.z
 807   dst.w = abs(src0.w - src1.w) + src2.w
 808
 809
 810 1.11.12  TXF - Texel Fetch
 811
 812   TBD
 813
 814
 815 1.11.13  TXQ - Texture Size Query
 816
 817   TBD
 818
 819
 820 1.11.14  CONT - Continue
 821
 822   TBD
 823
 824
 825 1.12  GL_NV_geometry_program4
 826 -----------------------------
 827
 828
 829 1.12.1  EMIT - Emit
 830
 831   TBD
 832
 833
 834 1.12.2  ENDPRIM - End Primitive
 835
 836   TBD
 837
 838
 839 1.13  GLSL
 840 ----------
 841
 842
 843 1.13.1  BGNLOOP2 - Begin Loop
 844
 845   TBD
 846
 847
 848 1.13.2  BGNSUB - Begin Subroutine
 849
 850   TBD
 851
 852
 853 1.13.3  ENDLOOP2 - End Loop
 854
 855   TBD
 856
 857
 858 1.13.4  ENDSUB - End Subroutine
 859
 860   TBD
 861
 862
 863 1.13.5  INT - Truncate
 864
 865   Alias for TRUNC.
 866
 867
 868 1.13.6  NOISE1 - 1D Noise
 869
 870   TBD
 871
 872
 873 1.13.7  NOISE2 - 2D Noise
 874
 875   TBD
 876
 877
 878 1.13.8  NOISE3 - 3D Noise
 879
 880   TBD
 881
 882
 883 1.13.9  NOISE4 - 4D Noise
 884
 885   TBD
 886
 887
 888 1.13.10  NOP - No Operation
 889
 890   Do nothing.
 891
 892
 893 1.14  ps_1_1
 894 ------------
 895
 896
 897 1.14.1  TEXKILL - Conditional Discard
 898
 899   Alias for KIL.
 900
 901
 902 1.15  ps_1_4
 903 ------------
 904
 905
 906 1.15.1  TEXLD - Texture Lookup
 907
 908   Alias for TEX.
 909
 910
 911 1.16  ps_2_0
 912 ------------
 913
 914
 915 1.16.1  M4X4 - Multiply Matrix
 916
 917   Alias for MULTIPLYMATRIX.
 918
 919
 920 1.16.2  M4X3 - Multiply Matrix
 921
 922   Considered for removal from language.
 923
 924
 925 1.16.3  M3X4 - Multiply Matrix
 926
 927   Considered for removal from language.
 928
 929
 930 1.16.4  M3X3 - Multiply Matrix
 931
 932   Considered for removal from language.
 933
 934
 935 1.16.5  M3X2 - Multiply Matrix
 936
 937   Considered for removal from language.
 938
 939
 940 1.16.6  CRS - Cross Product
 941
 942   Alias for XPD.
 943
 944
 945 1.16.7  NRM4 - 4-component Vector Normalise
 946
 947   dst.x = src.x / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w)
 948   dst.y = src.y / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w)
 949   dst.z = src.z / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w)
 950   dst.w = src.w / (src.x * src.x + src.y * src.y + src.z * src.z + src.w * src.w)
 951
 952
 953 1.16.8  SINCOS - Sine Cosine
 954
 955   Alias for SCS.
 956
 957
 958 1.16.9  TEXLDB - Texture Lookup With Bias
 959
 960   Alias for TXB.
 961
 962
 963 1.16.10  DP2ADD - 2-component Dot Product And Add
 964
 965   Alias for DP2A.
 966
 967
 968 1.17  ps_2_x
 969 ------------
 970
 971
 972 1.17.1  CALL - Subroutine Call
 973
 974   Alias for CAL.
 975
 976
 977 1.17.2  CALLNZ - Subroutine Call If Not Zero
 978
 979   TBD
 980
 981
 982 1.17.3  IFC - If
 983
 984   TBD
 985
 986
 987 1.17.4  BREAK - Break
 988
 989   Alias for BRK.
 990
 991
 992 1.17.5  BREAKC - Break Conditional
 993
 994   TBD
 995
 996
 997 1.17.6  DSX - Derivative Relative To X
 998
 999   Alias for DDX.
1000
1001
1002 1.17.7  DSY - Derivative Relative To Y
1003
1004   Alias for DDY.
1005
1006
1007 1.17.8  TEXLDD - Texture Lookup with Derivatives
1008
1009   Alias for TXD.
1010
1011
1012 1.18  vs_1_1
1013 ------------
1014
1015
1016 1.18.1  EXPP - Approximate Exponential Base 2
1017
1018   Alias for EXP.
1019
1020
1021 1.18.2  LOGP - Logarithm Base 2
1022
1023   Alias for LG2.
1024
1025
1026 1.19  vs_2_0
1027 ------------
1028
1029
1030 1.19.1  SGN - Set Sign
1031
1032   Alias for SSG.
1033
1034
1035 1.19.2  MOVA - Move Address Register
1036
1037   Alias for ARR.
1038
1039
1040 2  Explanation of symbols used
1041 ==============================
1042
1043
1044 2.1  Functions
1045 --------------
1046
1047
1048   abs(x)            Absolute value of x.
1049                     |x|
1050                     (x < 0.0) ? -x : x
1051
1052   ceil(x)           Ceiling of x.
1053
1054   clamp(x,y,z)      Clamp x between y and z.
1055                     (x < y) ? y : (x > z) ? z : x
1056
1057   cos(x)            Cosine of x.
1058
1059   floor(x)          Floor of x.
1060
1061   lg2(x)            Logarithm base 2 of x.
1062
1063   max(x,y)          Maximum of x and y.
1064                     (x > y) ? x : y
1065
1066   min(x,y)          Minimum of x and y.
1067                     (x < y) ? x : y
1068
1069   partialx(x)       Derivative of x relative to fragment's X.
1070
1071   partialy(x)       Derivative of x relative to fragment's Y.
1072
1073   pop()             Pop from stack.
1074
1075   pow(x,y)          Raise x to power of y.
1076
1077   push(x)           Push x on stack.
1078
1079   round(x)          Round x.
1080
1081   sin(x)            Sine of x.
1082
1083   sqrt(x)           Square root of x.
1084
1085   trunc(x)          Truncate x.
1086
1087
1088 2.2  Keywords
1089 -------------
1090
1091
1092   discard           Discard fragment.
1093
1094   dst               First destination register.
1095
1096   dst0              First destination register.
1097
1098   pc                Program counter.
1099
1100   src               First source register.
1101
1102   src0              First source register.
1103
1104   src1              Second source register.
1105
1106   src2              Third source register.
1107
1108   target            Label of target instruction.
1109