4 TGSI, Tungsten Graphics Shader Infrastructure, is an intermediate language
5 for describing shaders. Since Gallium is inherently shaderful, shaders are
6 an important part of the API. TGSI is the only intermediate representation
12 All TGSI instructions, known as *opcodes*, operate on arbitrary-precision
13 floating-point four-component vectors. An opcode may have up to one
14 destination register, known as *dst*, and between zero and three source
15 registers, called *src0* through *src2*, or simply *src* if there is only
18 Some instructions, like :opcode:`I2F`, permit re-interpretation of vector
19 components as integers. Other instructions permit using registers as
20 two-component vectors with double precision; see :ref:`Double Opcodes`.
22 When an instruction has a scalar result, the result is usually copied into
23 each of the components of *dst*. When this happens, the result is said to be
24 *replicated* to *dst*. :opcode:`RCP` is one such instruction.
29 TGSI supports modifiers on inputs (as well as saturate modifier on instructions).
31 For inputs which have a floating point type, both absolute value and negation
32 modifiers are supported (with absolute value being applied first).
33 TGSI_OPCODE_MOV is considered to have float input type for applying modifiers.
35 For inputs which have signed or unsigned type only the negate modifier is
42 ^^^^^^^^^^^^^^^^^^^^^^^^^
44 These opcodes are guaranteed to be available regardless of the driver being
47 .. opcode:: ARL - Address Register Load
51 dst.x = \lfloor src.x\rfloor
53 dst.y = \lfloor src.y\rfloor
55 dst.z = \lfloor src.z\rfloor
57 dst.w = \lfloor src.w\rfloor
60 .. opcode:: MOV - Move
73 .. opcode:: LIT - Light Coefficients
81 dst.z = (src.x > 0) ? max(src.y, 0)^{clamp(src.w, -128, 128))} : 0
86 .. opcode:: RCP - Reciprocal
88 This instruction replicates its result.
95 .. opcode:: RSQ - Reciprocal Square Root
97 This instruction replicates its result. The results are undefined for src <= 0.
101 dst = \frac{1}{\sqrt{src.x}}
104 .. opcode:: SQRT - Square Root
106 This instruction replicates its result. The results are undefined for src < 0.
113 .. opcode:: EXP - Approximate Exponential Base 2
117 dst.x = 2^{\lfloor src.x\rfloor}
119 dst.y = src.x - \lfloor src.x\rfloor
126 .. opcode:: LOG - Approximate Logarithm Base 2
130 dst.x = \lfloor\log_2{|src.x|}\rfloor
132 dst.y = \frac{|src.x|}{2^{\lfloor\log_2{|src.x|}\rfloor}}
134 dst.z = \log_2{|src.x|}
139 .. opcode:: MUL - Multiply
143 dst.x = src0.x \times src1.x
145 dst.y = src0.y \times src1.y
147 dst.z = src0.z \times src1.z
149 dst.w = src0.w \times src1.w
152 .. opcode:: ADD - Add
156 dst.x = src0.x + src1.x
158 dst.y = src0.y + src1.y
160 dst.z = src0.z + src1.z
162 dst.w = src0.w + src1.w
165 .. opcode:: DP3 - 3-component Dot Product
167 This instruction replicates its result.
171 dst = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z
174 .. opcode:: DP4 - 4-component Dot Product
176 This instruction replicates its result.
180 dst = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z + src0.w \times src1.w
183 .. opcode:: DST - Distance Vector
189 dst.y = src0.y \times src1.y
196 .. opcode:: MIN - Minimum
200 dst.x = min(src0.x, src1.x)
202 dst.y = min(src0.y, src1.y)
204 dst.z = min(src0.z, src1.z)
206 dst.w = min(src0.w, src1.w)
209 .. opcode:: MAX - Maximum
213 dst.x = max(src0.x, src1.x)
215 dst.y = max(src0.y, src1.y)
217 dst.z = max(src0.z, src1.z)
219 dst.w = max(src0.w, src1.w)
222 .. opcode:: SLT - Set On Less Than
226 dst.x = (src0.x < src1.x) ? 1 : 0
228 dst.y = (src0.y < src1.y) ? 1 : 0
230 dst.z = (src0.z < src1.z) ? 1 : 0
232 dst.w = (src0.w < src1.w) ? 1 : 0
235 .. opcode:: SGE - Set On Greater Equal Than
239 dst.x = (src0.x >= src1.x) ? 1 : 0
241 dst.y = (src0.y >= src1.y) ? 1 : 0
243 dst.z = (src0.z >= src1.z) ? 1 : 0
245 dst.w = (src0.w >= src1.w) ? 1 : 0
248 .. opcode:: MAD - Multiply And Add
252 dst.x = src0.x \times src1.x + src2.x
254 dst.y = src0.y \times src1.y + src2.y
256 dst.z = src0.z \times src1.z + src2.z
258 dst.w = src0.w \times src1.w + src2.w
261 .. opcode:: SUB - Subtract
265 dst.x = src0.x - src1.x
267 dst.y = src0.y - src1.y
269 dst.z = src0.z - src1.z
271 dst.w = src0.w - src1.w
274 .. opcode:: LRP - Linear Interpolate
278 dst.x = src0.x \times src1.x + (1 - src0.x) \times src2.x
280 dst.y = src0.y \times src1.y + (1 - src0.y) \times src2.y
282 dst.z = src0.z \times src1.z + (1 - src0.z) \times src2.z
284 dst.w = src0.w \times src1.w + (1 - src0.w) \times src2.w
287 .. opcode:: CND - Condition
291 dst.x = (src2.x > 0.5) ? src0.x : src1.x
293 dst.y = (src2.y > 0.5) ? src0.y : src1.y
295 dst.z = (src2.z > 0.5) ? src0.z : src1.z
297 dst.w = (src2.w > 0.5) ? src0.w : src1.w
300 .. opcode:: DP2A - 2-component Dot Product And Add
304 dst.x = src0.x \times src1.x + src0.y \times src1.y + src2.x
306 dst.y = src0.x \times src1.x + src0.y \times src1.y + src2.x
308 dst.z = src0.x \times src1.x + src0.y \times src1.y + src2.x
310 dst.w = src0.x \times src1.x + src0.y \times src1.y + src2.x
313 .. opcode:: FRC - Fraction
317 dst.x = src.x - \lfloor src.x\rfloor
319 dst.y = src.y - \lfloor src.y\rfloor
321 dst.z = src.z - \lfloor src.z\rfloor
323 dst.w = src.w - \lfloor src.w\rfloor
326 .. opcode:: CLAMP - Clamp
330 dst.x = clamp(src0.x, src1.x, src2.x)
332 dst.y = clamp(src0.y, src1.y, src2.y)
334 dst.z = clamp(src0.z, src1.z, src2.z)
336 dst.w = clamp(src0.w, src1.w, src2.w)
339 .. opcode:: FLR - Floor
341 This is identical to :opcode:`ARL`.
345 dst.x = \lfloor src.x\rfloor
347 dst.y = \lfloor src.y\rfloor
349 dst.z = \lfloor src.z\rfloor
351 dst.w = \lfloor src.w\rfloor
354 .. opcode:: ROUND - Round
367 .. opcode:: EX2 - Exponential Base 2
369 This instruction replicates its result.
376 .. opcode:: LG2 - Logarithm Base 2
378 This instruction replicates its result.
385 .. opcode:: POW - Power
387 This instruction replicates its result.
391 dst = src0.x^{src1.x}
393 .. opcode:: XPD - Cross Product
397 dst.x = src0.y \times src1.z - src1.y \times src0.z
399 dst.y = src0.z \times src1.x - src1.z \times src0.x
401 dst.z = src0.x \times src1.y - src1.x \times src0.y
406 .. opcode:: ABS - Absolute
419 .. opcode:: RCC - Reciprocal Clamped
421 This instruction replicates its result.
423 XXX cleanup on aisle three
427 dst = (1 / src.x) > 0 ? clamp(1 / src.x, 5.42101e-020, 1.884467e+019) : clamp(1 / src.x, -1.884467e+019, -5.42101e-020)
430 .. opcode:: DPH - Homogeneous Dot Product
432 This instruction replicates its result.
436 dst = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z + src1.w
439 .. opcode:: COS - Cosine
441 This instruction replicates its result.
448 .. opcode:: DDX - Derivative Relative To X
452 dst.x = partialx(src.x)
454 dst.y = partialx(src.y)
456 dst.z = partialx(src.z)
458 dst.w = partialx(src.w)
461 .. opcode:: DDY - Derivative Relative To Y
465 dst.x = partialy(src.x)
467 dst.y = partialy(src.y)
469 dst.z = partialy(src.z)
471 dst.w = partialy(src.w)
474 .. opcode:: PK2H - Pack Two 16-bit Floats
479 .. opcode:: PK2US - Pack Two Unsigned 16-bit Scalars
484 .. opcode:: PK4B - Pack Four Signed 8-bit Scalars
489 .. opcode:: PK4UB - Pack Four Unsigned 8-bit Scalars
494 .. opcode:: RFL - Reflection Vector
498 dst.x = 2 \times (src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z) / (src0.x \times src0.x + src0.y \times src0.y + src0.z \times src0.z) \times src0.x - src1.x
500 dst.y = 2 \times (src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z) / (src0.x \times src0.x + src0.y \times src0.y + src0.z \times src0.z) \times src0.y - src1.y
502 dst.z = 2 \times (src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z) / (src0.x \times src0.x + src0.y \times src0.y + src0.z \times src0.z) \times src0.z - src1.z
508 Considered for removal.
511 .. opcode:: SEQ - Set On Equal
515 dst.x = (src0.x == src1.x) ? 1 : 0
517 dst.y = (src0.y == src1.y) ? 1 : 0
519 dst.z = (src0.z == src1.z) ? 1 : 0
521 dst.w = (src0.w == src1.w) ? 1 : 0
524 .. opcode:: SFL - Set On False
526 This instruction replicates its result.
534 Considered for removal.
537 .. opcode:: SGT - Set On Greater Than
541 dst.x = (src0.x > src1.x) ? 1 : 0
543 dst.y = (src0.y > src1.y) ? 1 : 0
545 dst.z = (src0.z > src1.z) ? 1 : 0
547 dst.w = (src0.w > src1.w) ? 1 : 0
550 .. opcode:: SIN - Sine
552 This instruction replicates its result.
559 .. opcode:: SLE - Set On Less Equal Than
563 dst.x = (src0.x <= src1.x) ? 1 : 0
565 dst.y = (src0.y <= src1.y) ? 1 : 0
567 dst.z = (src0.z <= src1.z) ? 1 : 0
569 dst.w = (src0.w <= src1.w) ? 1 : 0
572 .. opcode:: SNE - Set On Not Equal
576 dst.x = (src0.x != src1.x) ? 1 : 0
578 dst.y = (src0.y != src1.y) ? 1 : 0
580 dst.z = (src0.z != src1.z) ? 1 : 0
582 dst.w = (src0.w != src1.w) ? 1 : 0
585 .. opcode:: STR - Set On True
587 This instruction replicates its result.
594 .. opcode:: TEX - Texture Lookup
602 dst = texture_sample(unit, coord, bias)
604 for array textures src0.y contains the slice for 1D,
605 and src0.z contain the slice for 2D.
606 for shadow textures with no arrays, src0.z contains
608 for shadow textures with arrays, src0.z contains
609 the reference value for 1D arrays, and src0.w contains
610 the reference value for 2D arrays.
611 There is no way to pass a bias in the .w value for
612 shadow arrays, and GLSL doesn't allow this.
613 GLSL does allow cube shadows maps to take a bias value,
614 and we have to determine how this will look in TGSI.
616 .. opcode:: TXD - Texture Lookup with Derivatives
628 dst = texture_sample_deriv(unit, coord, bias, ddx, ddy)
631 .. opcode:: TXP - Projective Texture Lookup
635 coord.x = src0.x / src.w
637 coord.y = src0.y / src.w
639 coord.z = src0.z / src.w
645 dst = texture_sample(unit, coord, bias)
648 .. opcode:: UP2H - Unpack Two 16-Bit Floats
654 Considered for removal.
656 .. opcode:: UP2US - Unpack Two Unsigned 16-Bit Scalars
662 Considered for removal.
664 .. opcode:: UP4B - Unpack Four Signed 8-Bit Values
670 Considered for removal.
672 .. opcode:: UP4UB - Unpack Four Unsigned 8-Bit Scalars
678 Considered for removal.
680 .. opcode:: X2D - 2D Coordinate Transformation
684 dst.x = src0.x + src1.x \times src2.x + src1.y \times src2.y
686 dst.y = src0.y + src1.x \times src2.z + src1.y \times src2.w
688 dst.z = src0.x + src1.x \times src2.x + src1.y \times src2.y
690 dst.w = src0.y + src1.x \times src2.z + src1.y \times src2.w
694 Considered for removal.
697 .. opcode:: ARA - Address Register Add
703 Considered for removal.
705 .. opcode:: ARR - Address Register Load With Round
718 .. opcode:: SSG - Set Sign
722 dst.x = (src.x > 0) ? 1 : (src.x < 0) ? -1 : 0
724 dst.y = (src.y > 0) ? 1 : (src.y < 0) ? -1 : 0
726 dst.z = (src.z > 0) ? 1 : (src.z < 0) ? -1 : 0
728 dst.w = (src.w > 0) ? 1 : (src.w < 0) ? -1 : 0
731 .. opcode:: CMP - Compare
735 dst.x = (src0.x < 0) ? src1.x : src2.x
737 dst.y = (src0.y < 0) ? src1.y : src2.y
739 dst.z = (src0.z < 0) ? src1.z : src2.z
741 dst.w = (src0.w < 0) ? src1.w : src2.w
744 .. opcode:: KILL_IF - Conditional Discard
746 Conditional discard. Allowed in fragment shaders only.
750 if (src.x < 0 || src.y < 0 || src.z < 0 || src.w < 0)
755 .. opcode:: KILL - Discard
757 Unconditional discard. Allowed in fragment shaders only.
760 .. opcode:: SCS - Sine Cosine
773 .. opcode:: TXB - Texture Lookup With Bias
787 dst = texture_sample(unit, coord, bias)
790 .. opcode:: NRM - 3-component Vector Normalise
794 dst.x = src.x / (src.x \times src.x + src.y \times src.y + src.z \times src.z)
796 dst.y = src.y / (src.x \times src.x + src.y \times src.y + src.z \times src.z)
798 dst.z = src.z / (src.x \times src.x + src.y \times src.y + src.z \times src.z)
803 .. opcode:: DIV - Divide
807 dst.x = \frac{src0.x}{src1.x}
809 dst.y = \frac{src0.y}{src1.y}
811 dst.z = \frac{src0.z}{src1.z}
813 dst.w = \frac{src0.w}{src1.w}
816 .. opcode:: DP2 - 2-component Dot Product
818 This instruction replicates its result.
822 dst = src0.x \times src1.x + src0.y \times src1.y
825 .. opcode:: TXL - Texture Lookup With explicit LOD
839 dst = texture_sample(unit, coord, lod)
842 .. opcode:: PUSHA - Push Address Register On Stack
851 Considered for cleanup.
855 Considered for removal.
857 .. opcode:: POPA - Pop Address Register From Stack
866 Considered for cleanup.
870 Considered for removal.
873 .. opcode:: BRA - Branch
879 Considered for removal.
882 .. opcode:: CALLNZ - Subroutine Call If Not Zero
888 Considered for cleanup.
892 Considered for removal.
896 ^^^^^^^^^^^^^^^^^^^^^^^^
898 These opcodes are primarily provided for special-use computational shaders.
899 Support for these opcodes indicated by a special pipe capability bit (TBD).
901 XXX doesn't look like most of the opcodes really belong here.
903 .. opcode:: CEIL - Ceiling
907 dst.x = \lceil src.x\rceil
909 dst.y = \lceil src.y\rceil
911 dst.z = \lceil src.z\rceil
913 dst.w = \lceil src.w\rceil
916 .. opcode:: TRUNC - Truncate
929 .. opcode:: MOD - Modulus
933 dst.x = src0.x \bmod src1.x
935 dst.y = src0.y \bmod src1.y
937 dst.z = src0.z \bmod src1.z
939 dst.w = src0.w \bmod src1.w
942 .. opcode:: UARL - Integer Address Register Load
944 Moves the contents of the source register, assumed to be an integer, into the
945 destination register, which is assumed to be an address (ADDR) register.
948 .. opcode:: SAD - Sum Of Absolute Differences
952 dst.x = |src0.x - src1.x| + src2.x
954 dst.y = |src0.y - src1.y| + src2.y
956 dst.z = |src0.z - src1.z| + src2.z
958 dst.w = |src0.w - src1.w| + src2.w
961 .. opcode:: TXF - Texel Fetch (as per NV_gpu_shader4), extract a single texel
962 from a specified texture image. The source sampler may
963 not be a CUBE or SHADOW.
964 src 0 is a four-component signed integer vector used to
965 identify the single texel accessed. 3 components + level.
966 src 1 is a 3 component constant signed integer vector,
967 with each component only have a range of
968 -8..+8 (hw only seems to deal with this range, interface
969 allows for up to unsigned int).
970 TXF(uint_vec coord, int_vec offset).
973 .. opcode:: TXQ - Texture Size Query (as per NV_gpu_program4)
974 retrieve the dimensions of the texture
975 depending on the target. For 1D (width), 2D/RECT/CUBE
976 (width, height), 3D (width, height, depth),
977 1D array (width, layers), 2D array (width, height, layers)
983 dst.x = texture_width(unit, lod)
985 dst.y = texture_height(unit, lod)
987 dst.z = texture_depth(unit, lod)
991 ^^^^^^^^^^^^^^^^^^^^^^^^
992 These opcodes are used for integer operations.
993 Support for these opcodes indicated by PIPE_SHADER_CAP_INTEGERS (all of them?)
996 .. opcode:: I2F - Signed Integer To Float
998 Rounding is unspecified (round to nearest even suggested).
1002 dst.x = (float) src.x
1004 dst.y = (float) src.y
1006 dst.z = (float) src.z
1008 dst.w = (float) src.w
1011 .. opcode:: U2F - Unsigned Integer To Float
1013 Rounding is unspecified (round to nearest even suggested).
1017 dst.x = (float) src.x
1019 dst.y = (float) src.y
1021 dst.z = (float) src.z
1023 dst.w = (float) src.w
1026 .. opcode:: F2I - Float to Signed Integer
1028 Rounding is towards zero (truncate).
1029 Values outside signed range (including NaNs) produce undefined results.
1042 .. opcode:: F2U - Float to Unsigned Integer
1044 Rounding is towards zero (truncate).
1045 Values outside unsigned range (including NaNs) produce undefined results.
1049 dst.x = (unsigned) src.x
1051 dst.y = (unsigned) src.y
1053 dst.z = (unsigned) src.z
1055 dst.w = (unsigned) src.w
1058 .. opcode:: UADD - Integer Add
1060 This instruction works the same for signed and unsigned integers.
1061 The low 32bit of the result is returned.
1065 dst.x = src0.x + src1.x
1067 dst.y = src0.y + src1.y
1069 dst.z = src0.z + src1.z
1071 dst.w = src0.w + src1.w
1074 .. opcode:: UMAD - Integer Multiply And Add
1076 This instruction works the same for signed and unsigned integers.
1077 The multiplication returns the low 32bit (as does the result itself).
1081 dst.x = src0.x \times src1.x + src2.x
1083 dst.y = src0.y \times src1.y + src2.y
1085 dst.z = src0.z \times src1.z + src2.z
1087 dst.w = src0.w \times src1.w + src2.w
1090 .. opcode:: UMUL - Integer Multiply
1092 This instruction works the same for signed and unsigned integers.
1093 The low 32bit of the result is returned.
1097 dst.x = src0.x \times src1.x
1099 dst.y = src0.y \times src1.y
1101 dst.z = src0.z \times src1.z
1103 dst.w = src0.w \times src1.w
1106 .. opcode:: IDIV - Signed Integer Division
1108 TBD: behavior for division by zero.
1112 dst.x = src0.x \ src1.x
1114 dst.y = src0.y \ src1.y
1116 dst.z = src0.z \ src1.z
1118 dst.w = src0.w \ src1.w
1121 .. opcode:: UDIV - Unsigned Integer Division
1123 For division by zero, 0xffffffff is returned.
1127 dst.x = src0.x \ src1.x
1129 dst.y = src0.y \ src1.y
1131 dst.z = src0.z \ src1.z
1133 dst.w = src0.w \ src1.w
1136 .. opcode:: UMOD - Unsigned Integer Remainder
1138 If second arg is zero, 0xffffffff is returned.
1142 dst.x = src0.x \ src1.x
1144 dst.y = src0.y \ src1.y
1146 dst.z = src0.z \ src1.z
1148 dst.w = src0.w \ src1.w
1151 .. opcode:: NOT - Bitwise Not
1164 .. opcode:: AND - Bitwise And
1168 dst.x = src0.x & src1.x
1170 dst.y = src0.y & src1.y
1172 dst.z = src0.z & src1.z
1174 dst.w = src0.w & src1.w
1177 .. opcode:: OR - Bitwise Or
1181 dst.x = src0.x | src1.x
1183 dst.y = src0.y | src1.y
1185 dst.z = src0.z | src1.z
1187 dst.w = src0.w | src1.w
1190 .. opcode:: XOR - Bitwise Xor
1194 dst.x = src0.x \oplus src1.x
1196 dst.y = src0.y \oplus src1.y
1198 dst.z = src0.z \oplus src1.z
1200 dst.w = src0.w \oplus src1.w
1203 .. opcode:: IMAX - Maximum of Signed Integers
1207 dst.x = max(src0.x, src1.x)
1209 dst.y = max(src0.y, src1.y)
1211 dst.z = max(src0.z, src1.z)
1213 dst.w = max(src0.w, src1.w)
1216 .. opcode:: UMAX - Maximum of Unsigned Integers
1220 dst.x = max(src0.x, src1.x)
1222 dst.y = max(src0.y, src1.y)
1224 dst.z = max(src0.z, src1.z)
1226 dst.w = max(src0.w, src1.w)
1229 .. opcode:: IMIN - Minimum of Signed Integers
1233 dst.x = min(src0.x, src1.x)
1235 dst.y = min(src0.y, src1.y)
1237 dst.z = min(src0.z, src1.z)
1239 dst.w = min(src0.w, src1.w)
1242 .. opcode:: UMIN - Minimum of Unsigned Integers
1246 dst.x = min(src0.x, src1.x)
1248 dst.y = min(src0.y, src1.y)
1250 dst.z = min(src0.z, src1.z)
1252 dst.w = min(src0.w, src1.w)
1255 .. opcode:: SHL - Shift Left
1259 dst.x = src0.x << src1.x
1261 dst.y = src0.y << src1.x
1263 dst.z = src0.z << src1.x
1265 dst.w = src0.w << src1.x
1268 .. opcode:: ISHR - Arithmetic Shift Right (of Signed Integer)
1272 dst.x = src0.x >> src1.x
1274 dst.y = src0.y >> src1.x
1276 dst.z = src0.z >> src1.x
1278 dst.w = src0.w >> src1.x
1281 .. opcode:: USHR - Logical Shift Right
1285 dst.x = src0.x >> (unsigned) src1.x
1287 dst.y = src0.y >> (unsigned) src1.x
1289 dst.z = src0.z >> (unsigned) src1.x
1291 dst.w = src0.w >> (unsigned) src1.x
1294 .. opcode:: UCMP - Integer Conditional Move
1298 dst.x = src0.x ? src1.x : src2.x
1300 dst.y = src0.y ? src1.y : src2.y
1302 dst.z = src0.z ? src1.z : src2.z
1304 dst.w = src0.w ? src1.w : src2.w
1308 .. opcode:: ISSG - Integer Set Sign
1312 dst.x = (src0.x < 0) ? -1 : (src0.x > 0) ? 1 : 0
1314 dst.y = (src0.y < 0) ? -1 : (src0.y > 0) ? 1 : 0
1316 dst.z = (src0.z < 0) ? -1 : (src0.z > 0) ? 1 : 0
1318 dst.w = (src0.w < 0) ? -1 : (src0.w > 0) ? 1 : 0
1322 .. opcode:: ISLT - Signed Integer Set On Less Than
1326 dst.x = (src0.x < src1.x) ? ~0 : 0
1328 dst.y = (src0.y < src1.y) ? ~0 : 0
1330 dst.z = (src0.z < src1.z) ? ~0 : 0
1332 dst.w = (src0.w < src1.w) ? ~0 : 0
1335 .. opcode:: USLT - Unsigned Integer Set On Less Than
1339 dst.x = (src0.x < src1.x) ? ~0 : 0
1341 dst.y = (src0.y < src1.y) ? ~0 : 0
1343 dst.z = (src0.z < src1.z) ? ~0 : 0
1345 dst.w = (src0.w < src1.w) ? ~0 : 0
1348 .. opcode:: ISGE - Signed Integer Set On Greater Equal Than
1352 dst.x = (src0.x >= src1.x) ? ~0 : 0
1354 dst.y = (src0.y >= src1.y) ? ~0 : 0
1356 dst.z = (src0.z >= src1.z) ? ~0 : 0
1358 dst.w = (src0.w >= src1.w) ? ~0 : 0
1361 .. opcode:: USGE - Unsigned Integer Set On Greater Equal Than
1365 dst.x = (src0.x >= src1.x) ? ~0 : 0
1367 dst.y = (src0.y >= src1.y) ? ~0 : 0
1369 dst.z = (src0.z >= src1.z) ? ~0 : 0
1371 dst.w = (src0.w >= src1.w) ? ~0 : 0
1374 .. opcode:: USEQ - Integer Set On Equal
1378 dst.x = (src0.x == src1.x) ? ~0 : 0
1380 dst.y = (src0.y == src1.y) ? ~0 : 0
1382 dst.z = (src0.z == src1.z) ? ~0 : 0
1384 dst.w = (src0.w == src1.w) ? ~0 : 0
1387 .. opcode:: USNE - Integer Set On Not Equal
1391 dst.x = (src0.x != src1.x) ? ~0 : 0
1393 dst.y = (src0.y != src1.y) ? ~0 : 0
1395 dst.z = (src0.z != src1.z) ? ~0 : 0
1397 dst.w = (src0.w != src1.w) ? ~0 : 0
1400 .. opcode:: INEG - Integer Negate
1415 .. opcode:: IABS - Integer Absolute Value
1429 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1431 These opcodes are only supported in geometry shaders; they have no meaning
1432 in any other type of shader.
1434 .. opcode:: EMIT - Emit
1436 Generate a new vertex for the current primitive using the values in the
1440 .. opcode:: ENDPRIM - End Primitive
1442 Complete the current primitive (consisting of the emitted vertices),
1443 and start a new one.
1449 These opcodes are part of :term:`GLSL`'s opcode set. Support for these
1450 opcodes is determined by a special capability bit, ``GLSL``.
1451 Some require glsl version 1.30 (UIF/BREAKC/SWITCH/CASE/DEFAULT/ENDSWITCH).
1453 .. opcode:: CAL - Subroutine Call
1459 .. opcode:: RET - Subroutine Call Return
1464 .. opcode:: CONT - Continue
1466 Unconditionally moves the point of execution to the instruction after the
1467 last bgnloop. The instruction must appear within a bgnloop/endloop.
1471 Support for CONT is determined by a special capability bit,
1472 ``TGSI_CONT_SUPPORTED``. See :ref:`Screen` for more information.
1475 .. opcode:: BGNLOOP - Begin a Loop
1477 Start a loop. Must have a matching endloop.
1480 .. opcode:: BGNSUB - Begin Subroutine
1482 Starts definition of a subroutine. Must have a matching endsub.
1485 .. opcode:: ENDLOOP - End a Loop
1487 End a loop started with bgnloop.
1490 .. opcode:: ENDSUB - End Subroutine
1492 Ends definition of a subroutine.
1495 .. opcode:: NOP - No Operation
1500 .. opcode:: BRK - Break
1502 Unconditionally moves the point of execution to the instruction after the
1503 next endloop or endswitch. The instruction must appear within a loop/endloop
1504 or switch/endswitch.
1507 .. opcode:: BREAKC - Break Conditional
1509 Conditionally moves the point of execution to the instruction after the
1510 next endloop or endswitch. The instruction must appear within a loop/endloop
1511 or switch/endswitch.
1512 Condition evaluates to true if src0.x != 0 where src0.x is interpreted
1513 as an integer register.
1517 Considered for removal as it's quite inconsistent wrt other opcodes
1518 (could emulate with UIF/BRK/ENDIF).
1521 .. opcode:: IF - Float If
1523 Start an IF ... ELSE .. ENDIF block. Condition evaluates to true if
1527 where src0.x is interpreted as a floating point register.
1530 .. opcode:: UIF - Bitwise If
1532 Start an UIF ... ELSE .. ENDIF block. Condition evaluates to true if
1536 where src0.x is interpreted as an integer register.
1539 .. opcode:: ELSE - Else
1541 Starts an else block, after an IF or UIF statement.
1544 .. opcode:: ENDIF - End If
1546 Ends an IF or UIF block.
1549 .. opcode:: SWITCH - Switch
1551 Starts a C-style switch expression. The switch consists of one or multiple
1552 CASE statements, and at most one DEFAULT statement. Execution of a statement
1553 ends when a BRK is hit, but just like in C falling through to other cases
1554 without a break is allowed. Similarly, DEFAULT label is allowed anywhere not
1555 just as last statement, and fallthrough is allowed into/from it.
1556 CASE src arguments are evaluated at bit level against the SWITCH src argument.
1561 (some instructions here)
1564 (some instructions here)
1567 (some instructions here)
1572 .. opcode:: CASE - Switch case
1574 This represents a switch case label. The src arg must be an integer immediate.
1577 .. opcode:: DEFAULT - Switch default
1579 This represents the default case in the switch, which is taken if no other
1583 .. opcode:: ENDSWITCH - End of switch
1585 Ends a switch expression.
1588 .. opcode:: NRM4 - 4-component Vector Normalise
1590 This instruction replicates its result.
1594 dst = \frac{src.x}{src.x \times src.x + src.y \times src.y + src.z \times src.z + src.w \times src.w}
1602 The double-precision opcodes reinterpret four-component vectors into
1603 two-component vectors with doubled precision in each component.
1605 Support for these opcodes is XXX undecided. :T
1607 .. opcode:: DADD - Add
1611 dst.xy = src0.xy + src1.xy
1613 dst.zw = src0.zw + src1.zw
1616 .. opcode:: DDIV - Divide
1620 dst.xy = src0.xy / src1.xy
1622 dst.zw = src0.zw / src1.zw
1624 .. opcode:: DSEQ - Set on Equal
1628 dst.xy = src0.xy == src1.xy ? 1.0F : 0.0F
1630 dst.zw = src0.zw == src1.zw ? 1.0F : 0.0F
1632 .. opcode:: DSLT - Set on Less than
1636 dst.xy = src0.xy < src1.xy ? 1.0F : 0.0F
1638 dst.zw = src0.zw < src1.zw ? 1.0F : 0.0F
1640 .. opcode:: DFRAC - Fraction
1644 dst.xy = src.xy - \lfloor src.xy\rfloor
1646 dst.zw = src.zw - \lfloor src.zw\rfloor
1649 .. opcode:: DFRACEXP - Convert Number to Fractional and Integral Components
1651 Like the ``frexp()`` routine in many math libraries, this opcode stores the
1652 exponent of its source to ``dst0``, and the significand to ``dst1``, such that
1653 :math:`dst1 \times 2^{dst0} = src` .
1657 dst0.xy = exp(src.xy)
1659 dst1.xy = frac(src.xy)
1661 dst0.zw = exp(src.zw)
1663 dst1.zw = frac(src.zw)
1665 .. opcode:: DLDEXP - Multiply Number by Integral Power of 2
1667 This opcode is the inverse of :opcode:`DFRACEXP`.
1671 dst.xy = src0.xy \times 2^{src1.xy}
1673 dst.zw = src0.zw \times 2^{src1.zw}
1675 .. opcode:: DMIN - Minimum
1679 dst.xy = min(src0.xy, src1.xy)
1681 dst.zw = min(src0.zw, src1.zw)
1683 .. opcode:: DMAX - Maximum
1687 dst.xy = max(src0.xy, src1.xy)
1689 dst.zw = max(src0.zw, src1.zw)
1691 .. opcode:: DMUL - Multiply
1695 dst.xy = src0.xy \times src1.xy
1697 dst.zw = src0.zw \times src1.zw
1700 .. opcode:: DMAD - Multiply And Add
1704 dst.xy = src0.xy \times src1.xy + src2.xy
1706 dst.zw = src0.zw \times src1.zw + src2.zw
1709 .. opcode:: DRCP - Reciprocal
1713 dst.xy = \frac{1}{src.xy}
1715 dst.zw = \frac{1}{src.zw}
1717 .. opcode:: DSQRT - Square Root
1721 dst.xy = \sqrt{src.xy}
1723 dst.zw = \sqrt{src.zw}
1726 .. _samplingopcodes:
1728 Resource Sampling Opcodes
1729 ^^^^^^^^^^^^^^^^^^^^^^^^^
1731 Those opcodes follow very closely semantics of the respective Direct3D
1732 instructions. If in doubt double check Direct3D documentation.
1733 Note that the swizzle on SVIEW (src1) determines texel swizzling
1736 .. opcode:: SAMPLE - Using provided address, sample data from the
1737 specified texture using the filtering mode identified
1738 by the gven sampler. The source data may come from
1739 any resource type other than buffers.
1740 SAMPLE dst, address, sampler_view, sampler
1742 SAMPLE TEMP[0], TEMP[1], SVIEW[0], SAMP[0]
1744 .. opcode:: SAMPLE_I - Simplified alternative to the SAMPLE instruction.
1745 Using the provided integer address, SAMPLE_I fetches data
1746 from the specified sampler view without any filtering.
1747 The source data may come from any resource type other
1749 SAMPLE_I dst, address, sampler_view
1751 SAMPLE_I TEMP[0], TEMP[1], SVIEW[0]
1752 The 'address' is specified as unsigned integers. If the
1753 'address' is out of range [0...(# texels - 1)] the
1754 result of the fetch is always 0 in all components.
1755 As such the instruction doesn't honor address wrap
1756 modes, in cases where that behavior is desirable
1757 'SAMPLE' instruction should be used.
1758 address.w always provides an unsigned integer mipmap
1759 level. If the value is out of the range then the
1760 instruction always returns 0 in all components.
1761 address.yz are ignored for buffers and 1d textures.
1762 address.z is ignored for 1d texture arrays and 2d
1764 For 1D texture arrays address.y provides the array
1765 index (also as unsigned integer). If the value is
1766 out of the range of available array indices
1767 [0... (array size - 1)] then the opcode always returns
1768 0 in all components.
1769 For 2D texture arrays address.z provides the array
1770 index, otherwise it exhibits the same behavior as in
1771 the case for 1D texture arrays.
1772 The exact semantics of the source address are presented
1774 resource type X Y Z W
1775 ------------- ------------------------
1776 PIPE_BUFFER x ignored
1777 PIPE_TEXTURE_1D x mpl
1778 PIPE_TEXTURE_2D x y mpl
1779 PIPE_TEXTURE_3D x y z mpl
1780 PIPE_TEXTURE_RECT x y mpl
1781 PIPE_TEXTURE_CUBE not allowed as source
1782 PIPE_TEXTURE_1D_ARRAY x idx mpl
1783 PIPE_TEXTURE_2D_ARRAY x y idx mpl
1785 Where 'mpl' is a mipmap level and 'idx' is the
1788 .. opcode:: SAMPLE_I_MS - Just like SAMPLE_I but allows fetch data from
1789 multi-sampled surfaces.
1790 SAMPLE_I_MS dst, address, sampler_view, sample
1792 .. opcode:: SAMPLE_B - Just like the SAMPLE instruction with the
1793 exception that an additional bias is applied to the
1794 level of detail computed as part of the instruction
1796 SAMPLE_B dst, address, sampler_view, sampler, lod_bias
1798 SAMPLE_B TEMP[0], TEMP[1], SVIEW[0], SAMP[0], TEMP[2].x
1800 .. opcode:: SAMPLE_C - Similar to the SAMPLE instruction but it
1801 performs a comparison filter. The operands to SAMPLE_C
1802 are identical to SAMPLE, except that there is an additional
1803 float32 operand, reference value, which must be a register
1804 with single-component, or a scalar literal.
1805 SAMPLE_C makes the hardware use the current samplers
1806 compare_func (in pipe_sampler_state) to compare
1807 reference value against the red component value for the
1808 surce resource at each texel that the currently configured
1809 texture filter covers based on the provided coordinates.
1810 SAMPLE_C dst, address, sampler_view.r, sampler, ref_value
1812 SAMPLE_C TEMP[0], TEMP[1], SVIEW[0].r, SAMP[0], TEMP[2].x
1814 .. opcode:: SAMPLE_C_LZ - Same as SAMPLE_C, but LOD is 0 and derivatives
1815 are ignored. The LZ stands for level-zero.
1816 SAMPLE_C_LZ dst, address, sampler_view.r, sampler, ref_value
1818 SAMPLE_C_LZ TEMP[0], TEMP[1], SVIEW[0].r, SAMP[0], TEMP[2].x
1821 .. opcode:: SAMPLE_D - SAMPLE_D is identical to the SAMPLE opcode except
1822 that the derivatives for the source address in the x
1823 direction and the y direction are provided by extra
1825 SAMPLE_D dst, address, sampler_view, sampler, der_x, der_y
1827 SAMPLE_D TEMP[0], TEMP[1], SVIEW[0], SAMP[0], TEMP[2], TEMP[3]
1829 .. opcode:: SAMPLE_L - SAMPLE_L is identical to the SAMPLE opcode except
1830 that the LOD is provided directly as a scalar value,
1831 representing no anisotropy.
1832 SAMPLE_L dst, address, sampler_view, sampler, explicit_lod
1834 SAMPLE_L TEMP[0], TEMP[1], SVIEW[0], SAMP[0], TEMP[2].x
1836 .. opcode:: GATHER4 - Gathers the four texels to be used in a bi-linear
1837 filtering operation and packs them into a single register.
1838 Only works with 2D, 2D array, cubemaps, and cubemaps arrays.
1839 For 2D textures, only the addressing modes of the sampler and
1840 the top level of any mip pyramid are used. Set W to zero.
1841 It behaves like the SAMPLE instruction, but a filtered
1842 sample is not generated. The four samples that contribute
1843 to filtering are placed into xyzw in counter-clockwise order,
1844 starting with the (u,v) texture coordinate delta at the
1845 following locations (-, +), (+, +), (+, -), (-, -), where
1846 the magnitude of the deltas are half a texel.
1849 .. opcode:: SVIEWINFO - query the dimensions of a given sampler view.
1850 dst receives width, height, depth or array size and
1851 number of mipmap levels as int4. The dst can have a writemask
1852 which will specify what info is the caller interested
1854 SVIEWINFO dst, src_mip_level, sampler_view
1856 SVIEWINFO TEMP[0], TEMP[1].x, SVIEW[0]
1857 src_mip_level is an unsigned integer scalar. If it's
1858 out of range then returns 0 for width, height and
1859 depth/array size but the total number of mipmap is
1860 still returned correctly for the given sampler view.
1861 The returned width, height and depth values are for
1862 the mipmap level selected by the src_mip_level and
1863 are in the number of texels.
1864 For 1d texture array width is in dst.x, array size
1865 is in dst.y and dst.zw are always 0.
1867 .. opcode:: SAMPLE_POS - query the position of a given sample.
1868 dst receives float4 (x, y, 0, 0) indicated where the
1869 sample is located. If the resource is not a multi-sample
1870 resource and not a render target, the result is 0.
1872 .. opcode:: SAMPLE_INFO - dst receives number of samples in x.
1873 If the resource is not a multi-sample resource and
1874 not a render target, the result is 0.
1877 .. _resourceopcodes:
1879 Resource Access Opcodes
1880 ^^^^^^^^^^^^^^^^^^^^^^^
1882 .. opcode:: LOAD - Fetch data from a shader resource
1884 Syntax: ``LOAD dst, resource, address``
1886 Example: ``LOAD TEMP[0], RES[0], TEMP[1]``
1888 Using the provided integer address, LOAD fetches data
1889 from the specified buffer or texture without any
1892 The 'address' is specified as a vector of unsigned
1893 integers. If the 'address' is out of range the result
1896 Only the first mipmap level of a resource can be read
1897 from using this instruction.
1899 For 1D or 2D texture arrays, the array index is
1900 provided as an unsigned integer in address.y or
1901 address.z, respectively. address.yz are ignored for
1902 buffers and 1D textures. address.z is ignored for 1D
1903 texture arrays and 2D textures. address.w is always
1906 .. opcode:: STORE - Write data to a shader resource
1908 Syntax: ``STORE resource, address, src``
1910 Example: ``STORE RES[0], TEMP[0], TEMP[1]``
1912 Using the provided integer address, STORE writes data
1913 to the specified buffer or texture.
1915 The 'address' is specified as a vector of unsigned
1916 integers. If the 'address' is out of range the result
1919 Only the first mipmap level of a resource can be
1920 written to using this instruction.
1922 For 1D or 2D texture arrays, the array index is
1923 provided as an unsigned integer in address.y or
1924 address.z, respectively. address.yz are ignored for
1925 buffers and 1D textures. address.z is ignored for 1D
1926 texture arrays and 2D textures. address.w is always
1930 .. _threadsyncopcodes:
1932 Inter-thread synchronization opcodes
1933 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1935 These opcodes are intended for communication between threads running
1936 within the same compute grid. For now they're only valid in compute
1939 .. opcode:: MFENCE - Memory fence
1941 Syntax: ``MFENCE resource``
1943 Example: ``MFENCE RES[0]``
1945 This opcode forces strong ordering between any memory access
1946 operations that affect the specified resource. This means that
1947 previous loads and stores (and only those) will be performed and
1948 visible to other threads before the program execution continues.
1951 .. opcode:: LFENCE - Load memory fence
1953 Syntax: ``LFENCE resource``
1955 Example: ``LFENCE RES[0]``
1957 Similar to MFENCE, but it only affects the ordering of memory loads.
1960 .. opcode:: SFENCE - Store memory fence
1962 Syntax: ``SFENCE resource``
1964 Example: ``SFENCE RES[0]``
1966 Similar to MFENCE, but it only affects the ordering of memory stores.
1969 .. opcode:: BARRIER - Thread group barrier
1973 This opcode suspends the execution of the current thread until all
1974 the remaining threads in the working group reach the same point of
1975 the program. Results are unspecified if any of the remaining
1976 threads terminates or never reaches an executed BARRIER instruction.
1984 These opcodes provide atomic variants of some common arithmetic and
1985 logical operations. In this context atomicity means that another
1986 concurrent memory access operation that affects the same memory
1987 location is guaranteed to be performed strictly before or after the
1988 entire execution of the atomic operation.
1990 For the moment they're only valid in compute programs.
1992 .. opcode:: ATOMUADD - Atomic integer addition
1994 Syntax: ``ATOMUADD dst, resource, offset, src``
1996 Example: ``ATOMUADD TEMP[0], RES[0], TEMP[1], TEMP[2]``
1998 The following operation is performed atomically on each component:
2002 dst_i = resource[offset]_i
2004 resource[offset]_i = dst_i + src_i
2007 .. opcode:: ATOMXCHG - Atomic exchange
2009 Syntax: ``ATOMXCHG dst, resource, offset, src``
2011 Example: ``ATOMXCHG TEMP[0], RES[0], TEMP[1], TEMP[2]``
2013 The following operation is performed atomically on each component:
2017 dst_i = resource[offset]_i
2019 resource[offset]_i = src_i
2022 .. opcode:: ATOMCAS - Atomic compare-and-exchange
2024 Syntax: ``ATOMCAS dst, resource, offset, cmp, src``
2026 Example: ``ATOMCAS TEMP[0], RES[0], TEMP[1], TEMP[2], TEMP[3]``
2028 The following operation is performed atomically on each component:
2032 dst_i = resource[offset]_i
2034 resource[offset]_i = (dst_i == cmp_i ? src_i : dst_i)
2037 .. opcode:: ATOMAND - Atomic bitwise And
2039 Syntax: ``ATOMAND dst, resource, offset, src``
2041 Example: ``ATOMAND TEMP[0], RES[0], TEMP[1], TEMP[2]``
2043 The following operation is performed atomically on each component:
2047 dst_i = resource[offset]_i
2049 resource[offset]_i = dst_i \& src_i
2052 .. opcode:: ATOMOR - Atomic bitwise Or
2054 Syntax: ``ATOMOR dst, resource, offset, src``
2056 Example: ``ATOMOR TEMP[0], RES[0], TEMP[1], TEMP[2]``
2058 The following operation is performed atomically on each component:
2062 dst_i = resource[offset]_i
2064 resource[offset]_i = dst_i | src_i
2067 .. opcode:: ATOMXOR - Atomic bitwise Xor
2069 Syntax: ``ATOMXOR dst, resource, offset, src``
2071 Example: ``ATOMXOR TEMP[0], RES[0], TEMP[1], TEMP[2]``
2073 The following operation is performed atomically on each component:
2077 dst_i = resource[offset]_i
2079 resource[offset]_i = dst_i \oplus src_i
2082 .. opcode:: ATOMUMIN - Atomic unsigned minimum
2084 Syntax: ``ATOMUMIN dst, resource, offset, src``
2086 Example: ``ATOMUMIN TEMP[0], RES[0], TEMP[1], TEMP[2]``
2088 The following operation is performed atomically on each component:
2092 dst_i = resource[offset]_i
2094 resource[offset]_i = (dst_i < src_i ? dst_i : src_i)
2097 .. opcode:: ATOMUMAX - Atomic unsigned maximum
2099 Syntax: ``ATOMUMAX dst, resource, offset, src``
2101 Example: ``ATOMUMAX TEMP[0], RES[0], TEMP[1], TEMP[2]``
2103 The following operation is performed atomically on each component:
2107 dst_i = resource[offset]_i
2109 resource[offset]_i = (dst_i > src_i ? dst_i : src_i)
2112 .. opcode:: ATOMIMIN - Atomic signed minimum
2114 Syntax: ``ATOMIMIN dst, resource, offset, src``
2116 Example: ``ATOMIMIN TEMP[0], RES[0], TEMP[1], TEMP[2]``
2118 The following operation is performed atomically on each component:
2122 dst_i = resource[offset]_i
2124 resource[offset]_i = (dst_i < src_i ? dst_i : src_i)
2127 .. opcode:: ATOMIMAX - Atomic signed maximum
2129 Syntax: ``ATOMIMAX dst, resource, offset, src``
2131 Example: ``ATOMIMAX TEMP[0], RES[0], TEMP[1], TEMP[2]``
2133 The following operation is performed atomically on each component:
2137 dst_i = resource[offset]_i
2139 resource[offset]_i = (dst_i > src_i ? dst_i : src_i)
2143 Explanation of symbols used
2144 ------------------------------
2151 :math:`|x|` Absolute value of `x`.
2153 :math:`\lceil x \rceil` Ceiling of `x`.
2155 clamp(x,y,z) Clamp x between y and z.
2156 (x < y) ? y : (x > z) ? z : x
2158 :math:`\lfloor x\rfloor` Floor of `x`.
2160 :math:`\log_2{x}` Logarithm of `x`, base 2.
2162 max(x,y) Maximum of x and y.
2165 min(x,y) Minimum of x and y.
2168 partialx(x) Derivative of x relative to fragment's X.
2170 partialy(x) Derivative of x relative to fragment's Y.
2172 pop() Pop from stack.
2174 :math:`x^y` `x` to the power `y`.
2176 push(x) Push x on stack.
2180 trunc(x) Truncate x, i.e. drop the fraction bits.
2187 discard Discard fragment.
2191 target Label of target instruction.
2202 Declares a register that is will be referenced as an operand in Instruction
2205 File field contains register file that is being declared and is one
2208 UsageMask field specifies which of the register components can be accessed
2209 and is one of TGSI_WRITEMASK.
2211 The Local flag specifies that a given value isn't intended for
2212 subroutine parameter passing and, as a result, the implementation
2213 isn't required to give any guarantees of it being preserved across
2214 subroutine boundaries. As it's merely a compiler hint, the
2215 implementation is free to ignore it.
2217 If Dimension flag is set to 1, a Declaration Dimension token follows.
2219 If Semantic flag is set to 1, a Declaration Semantic token follows.
2221 If Interpolate flag is set to 1, a Declaration Interpolate token follows.
2223 If file is TGSI_FILE_RESOURCE, a Declaration Resource token follows.
2225 If Array flag is set to 1, a Declaration Array token follows.
2228 ^^^^^^^^^^^^^^^^^^^^^^^^
2230 Declarations can optional have an ArrayID attribute which can be referred by
2231 indirect addressing operands. An ArrayID of zero is reserved and treaded as
2232 if no ArrayID is specified.
2234 If an indirect addressing operand refers to a specific declaration by using
2235 an ArrayID only the registers in this declaration are guaranteed to be
2236 accessed, accessing any register outside this declaration results in undefined
2237 behavior. Note that for compatibility the effective index is zero-based and
2238 not relative to the specified declaration
2240 If no ArrayID is specified with an indirect addressing operand the whole
2241 register file might be accessed by this operand. This is strongly discouraged
2242 and will prevent packing of scalar/vec2 arrays and effective alias analysis.
2244 Declaration Semantic
2245 ^^^^^^^^^^^^^^^^^^^^^^^^
2247 Vertex and fragment shader input and output registers may be labeled
2248 with semantic information consisting of a name and index.
2250 Follows Declaration token if Semantic bit is set.
2252 Since its purpose is to link a shader with other stages of the pipeline,
2253 it is valid to follow only those Declaration tokens that declare a register
2254 either in INPUT or OUTPUT file.
2256 SemanticName field contains the semantic name of the register being declared.
2257 There is no default value.
2259 SemanticIndex is an optional subscript that can be used to distinguish
2260 different register declarations with the same semantic name. The default value
2263 The meanings of the individual semantic names are explained in the following
2266 TGSI_SEMANTIC_POSITION
2267 """"""""""""""""""""""
2269 For vertex shaders, TGSI_SEMANTIC_POSITION indicates the vertex shader
2270 output register which contains the homogeneous vertex position in the clip
2271 space coordinate system. After clipping, the X, Y and Z components of the
2272 vertex will be divided by the W value to get normalized device coordinates.
2274 For fragment shaders, TGSI_SEMANTIC_POSITION is used to indicate that
2275 fragment shader input contains the fragment's window position. The X
2276 component starts at zero and always increases from left to right.
2277 The Y component starts at zero and always increases but Y=0 may either
2278 indicate the top of the window or the bottom depending on the fragment
2279 coordinate origin convention (see TGSI_PROPERTY_FS_COORD_ORIGIN).
2280 The Z coordinate ranges from 0 to 1 to represent depth from the front
2281 to the back of the Z buffer. The W component contains the reciprocol
2282 of the interpolated vertex position W component.
2284 Fragment shaders may also declare an output register with
2285 TGSI_SEMANTIC_POSITION. Only the Z component is writable. This allows
2286 the fragment shader to change the fragment's Z position.
2293 For vertex shader outputs or fragment shader inputs/outputs, this
2294 label indicates that the resister contains an R,G,B,A color.
2296 Several shader inputs/outputs may contain colors so the semantic index
2297 is used to distinguish them. For example, color[0] may be the diffuse
2298 color while color[1] may be the specular color.
2300 This label is needed so that the flat/smooth shading can be applied
2301 to the right interpolants during rasterization.
2305 TGSI_SEMANTIC_BCOLOR
2306 """"""""""""""""""""
2308 Back-facing colors are only used for back-facing polygons, and are only valid
2309 in vertex shader outputs. After rasterization, all polygons are front-facing
2310 and COLOR and BCOLOR end up occupying the same slots in the fragment shader,
2311 so all BCOLORs effectively become regular COLORs in the fragment shader.
2317 Vertex shader inputs and outputs and fragment shader inputs may be
2318 labeled with TGSI_SEMANTIC_FOG to indicate that the register contains
2319 a fog coordinate in the form (F, 0, 0, 1). Typically, the fragment
2320 shader will use the fog coordinate to compute a fog blend factor which
2321 is used to blend the normal fragment color with a constant fog color.
2323 Only the first component matters when writing from the vertex shader;
2324 the driver will ensure that the coordinate is in this format when used
2325 as a fragment shader input.
2331 Vertex shader input and output registers may be labeled with
2332 TGIS_SEMANTIC_PSIZE to indicate that the register contains a point size
2333 in the form (S, 0, 0, 1). The point size controls the width or diameter
2334 of points for rasterization. This label cannot be used in fragment
2337 When using this semantic, be sure to set the appropriate state in the
2338 :ref:`rasterizer` first.
2341 TGSI_SEMANTIC_TEXCOORD
2342 """"""""""""""""""""""
2344 Only available if PIPE_CAP_TGSI_TEXCOORD is exposed !
2346 Vertex shader outputs and fragment shader inputs may be labeled with
2347 this semantic to make them replaceable by sprite coordinates via the
2348 sprite_coord_enable state in the :ref:`rasterizer`.
2349 The semantic index permitted with this semantic is limited to <= 7.
2351 If the driver does not support TEXCOORD, sprite coordinate replacement
2352 applies to inputs with the GENERIC semantic instead.
2354 The intended use case for this semantic is gl_TexCoord.
2357 TGSI_SEMANTIC_PCOORD
2358 """"""""""""""""""""
2360 Only available if PIPE_CAP_TGSI_TEXCOORD is exposed !
2362 Fragment shader inputs may be labeled with TGSI_SEMANTIC_PCOORD to indicate
2363 that the register contains sprite coordinates in the form (x, y, 0, 1), if
2364 the current primitive is a point and point sprites are enabled. Otherwise,
2365 the contents of the register are undefined.
2367 The intended use case for this semantic is gl_PointCoord.
2370 TGSI_SEMANTIC_GENERIC
2371 """""""""""""""""""""
2373 All vertex/fragment shader inputs/outputs not labeled with any other
2374 semantic label can be considered to be generic attributes. Typical
2375 uses of generic inputs/outputs are texcoords and user-defined values.
2378 TGSI_SEMANTIC_NORMAL
2379 """"""""""""""""""""
2381 Indicates that a vertex shader input is a normal vector. This is
2382 typically only used for legacy graphics APIs.
2388 This label applies to fragment shader inputs only and indicates that
2389 the register contains front/back-face information of the form (F, 0,
2390 0, 1). The first component will be positive when the fragment belongs
2391 to a front-facing polygon, and negative when the fragment belongs to a
2392 back-facing polygon.
2395 TGSI_SEMANTIC_EDGEFLAG
2396 """"""""""""""""""""""
2398 For vertex shaders, this sematic label indicates that an input or
2399 output is a boolean edge flag. The register layout is [F, x, x, x]
2400 where F is 0.0 or 1.0 and x = don't care. Normally, the vertex shader
2401 simply copies the edge flag input to the edgeflag output.
2403 Edge flags are used to control which lines or points are actually
2404 drawn when the polygon mode converts triangles/quads/polygons into
2408 TGSI_SEMANTIC_STENCIL
2409 """""""""""""""""""""
2411 For fragment shaders, this semantic label indicates that an output
2412 is a writable stencil reference value. Only the Y component is writable.
2413 This allows the fragment shader to change the fragments stencilref value.
2416 TGSI_SEMANTIC_VIEWPORT_INDEX
2417 """"""""""""""""""""""""""""
2419 For geometry shaders, this semantic label indicates that an output
2420 contains the index of the viewport (and scissor) to use.
2421 Only the X value is used.
2427 For geometry shaders, this semantic label indicates that an output
2428 contains the layer value to use for the color and depth/stencil surfaces.
2429 Only the X value is used. (Also known as rendertarget array index.)
2432 TGSI_SEMANTIC_CULLDIST
2433 """"""""""""""""""""""
2435 Used as distance to plane for performing application-defined culling
2436 of individual primitives against a plane. When components of vertex
2437 elements are given this label, these values are assumed to be a
2438 float32 signed distance to a plane. Primitives will be completely
2439 discarded if the plane distance for all of the vertices in the
2440 primitive are < 0. If a vertex has a cull distance of NaN, that
2441 vertex counts as "out" (as if its < 0);
2442 The limits on both clip and cull distances are bound
2443 by the PIPE_MAX_CLIP_OR_CULL_DISTANCE_COUNT define which defines
2444 the maximum number of components that can be used to hold the
2445 distances and by the PIPE_MAX_CLIP_OR_CULL_DISTANCE_ELEMENT_COUNT
2446 which specifies the maximum number of registers which can be
2447 annotated with those semantics.
2450 TGSI_SEMANTIC_CLIPDIST
2451 """"""""""""""""""""""
2453 When components of vertex elements are identified this way, these
2454 values are each assumed to be a float32 signed distance to a plane.
2455 Primitive setup only invokes rasterization on pixels for which
2456 the interpolated plane distances are >= 0. Multiple clip planes
2457 can be implemented simultaneously, by annotating multiple
2458 components of one or more vertex elements with the above specified
2459 semantic. The limits on both clip and cull distances are bound
2460 by the PIPE_MAX_CLIP_OR_CULL_DISTANCE_COUNT define which defines
2461 the maximum number of components that can be used to hold the
2462 distances and by the PIPE_MAX_CLIP_OR_CULL_DISTANCE_ELEMENT_COUNT
2463 which specifies the maximum number of registers which can be
2464 annotated with those semantics.
2467 Declaration Interpolate
2468 ^^^^^^^^^^^^^^^^^^^^^^^
2470 This token is only valid for fragment shader INPUT declarations.
2472 The Interpolate field specifes the way input is being interpolated by
2473 the rasteriser and is one of TGSI_INTERPOLATE_*.
2475 The CylindricalWrap bitfield specifies which register components
2476 should be subject to cylindrical wrapping when interpolating by the
2477 rasteriser. If TGSI_CYLINDRICAL_WRAP_X is set to 1, the X component
2478 should be interpolated according to cylindrical wrapping rules.
2481 Declaration Sampler View
2482 ^^^^^^^^^^^^^^^^^^^^^^^^
2484 Follows Declaration token if file is TGSI_FILE_SAMPLER_VIEW.
2486 DCL SVIEW[#], resource, type(s)
2488 Declares a shader input sampler view and assigns it to a SVIEW[#]
2491 resource can be one of BUFFER, 1D, 2D, 3D, 1DArray and 2DArray.
2493 type must be 1 or 4 entries (if specifying on a per-component
2494 level) out of UNORM, SNORM, SINT, UINT and FLOAT.
2497 Declaration Resource
2498 ^^^^^^^^^^^^^^^^^^^^
2500 Follows Declaration token if file is TGSI_FILE_RESOURCE.
2502 DCL RES[#], resource [, WR] [, RAW]
2504 Declares a shader input resource and assigns it to a RES[#]
2507 resource can be one of BUFFER, 1D, 2D, 3D, CUBE, 1DArray and
2510 If the RAW keyword is not specified, the texture data will be
2511 subject to conversion, swizzling and scaling as required to yield
2512 the specified data type from the physical data format of the bound
2515 If the RAW keyword is specified, no channel conversion will be
2516 performed: the values read for each of the channels (X,Y,Z,W) will
2517 correspond to consecutive words in the same order and format
2518 they're found in memory. No element-to-address conversion will be
2519 performed either: the value of the provided X coordinate will be
2520 interpreted in byte units instead of texel units. The result of
2521 accessing a misaligned address is undefined.
2523 Usage of the STORE opcode is only allowed if the WR (writable) flag
2528 ^^^^^^^^^^^^^^^^^^^^^^^^
2531 Properties are general directives that apply to the whole TGSI program.
2536 Specifies the fragment shader TGSI_SEMANTIC_POSITION coordinate origin.
2537 The default value is UPPER_LEFT.
2539 If UPPER_LEFT, the position will be (0,0) at the upper left corner and
2540 increase downward and rightward.
2541 If LOWER_LEFT, the position will be (0,0) at the lower left corner and
2542 increase upward and rightward.
2544 OpenGL defaults to LOWER_LEFT, and is configurable with the
2545 GL_ARB_fragment_coord_conventions extension.
2547 DirectX 9/10 use UPPER_LEFT.
2549 FS_COORD_PIXEL_CENTER
2550 """""""""""""""""""""
2552 Specifies the fragment shader TGSI_SEMANTIC_POSITION pixel center convention.
2553 The default value is HALF_INTEGER.
2555 If HALF_INTEGER, the fractionary part of the position will be 0.5
2556 If INTEGER, the fractionary part of the position will be 0.0
2558 Note that this does not affect the set of fragments generated by
2559 rasterization, which is instead controlled by half_pixel_center in the
2562 OpenGL defaults to HALF_INTEGER, and is configurable with the
2563 GL_ARB_fragment_coord_conventions extension.
2565 DirectX 9 uses INTEGER.
2566 DirectX 10 uses HALF_INTEGER.
2568 FS_COLOR0_WRITES_ALL_CBUFS
2569 """"""""""""""""""""""""""
2570 Specifies that writes to the fragment shader color 0 are replicated to all
2571 bound cbufs. This facilitates OpenGL's fragColor output vs fragData[0] where
2572 fragData is directed to a single color buffer, but fragColor is broadcast.
2575 """"""""""""""""""""""""""
2576 If this property is set on the program bound to the shader stage before the
2577 fragment shader, user clip planes should have no effect (be disabled) even if
2578 that shader does not write to any clip distance outputs and the rasterizer's
2579 clip_plane_enable is non-zero.
2580 This property is only supported by drivers that also support shader clip
2582 This is useful for APIs that don't have UCPs and where clip distances written
2583 by a shader cannot be disabled.
2586 Texture Sampling and Texture Formats
2587 ------------------------------------
2589 This table shows how texture image components are returned as (x,y,z,w) tuples
2590 by TGSI texture instructions, such as :opcode:`TEX`, :opcode:`TXD`, and
2591 :opcode:`TXP`. For reference, OpenGL and Direct3D conventions are shown as
2594 +--------------------+--------------+--------------------+--------------+
2595 | Texture Components | Gallium | OpenGL | Direct3D 9 |
2596 +====================+==============+====================+==============+
2597 | R | (r, 0, 0, 1) | (r, 0, 0, 1) | (r, 1, 1, 1) |
2598 +--------------------+--------------+--------------------+--------------+
2599 | RG | (r, g, 0, 1) | (r, g, 0, 1) | (r, g, 1, 1) |
2600 +--------------------+--------------+--------------------+--------------+
2601 | RGB | (r, g, b, 1) | (r, g, b, 1) | (r, g, b, 1) |
2602 +--------------------+--------------+--------------------+--------------+
2603 | RGBA | (r, g, b, a) | (r, g, b, a) | (r, g, b, a) |
2604 +--------------------+--------------+--------------------+--------------+
2605 | A | (0, 0, 0, a) | (0, 0, 0, a) | (0, 0, 0, a) |
2606 +--------------------+--------------+--------------------+--------------+
2607 | L | (l, l, l, 1) | (l, l, l, 1) | (l, l, l, 1) |
2608 +--------------------+--------------+--------------------+--------------+
2609 | LA | (l, l, l, a) | (l, l, l, a) | (l, l, l, a) |
2610 +--------------------+--------------+--------------------+--------------+
2611 | I | (i, i, i, i) | (i, i, i, i) | N/A |
2612 +--------------------+--------------+--------------------+--------------+
2613 | UV | XXX TBD | (0, 0, 0, 1) | (u, v, 1, 1) |
2614 | | | [#envmap-bumpmap]_ | |
2615 +--------------------+--------------+--------------------+--------------+
2616 | Z | XXX TBD | (z, z, z, 1) | (0, z, 0, 1) |
2617 | | | [#depth-tex-mode]_ | |
2618 +--------------------+--------------+--------------------+--------------+
2619 | S | (s, s, s, s) | unknown | unknown |
2620 +--------------------+--------------+--------------------+--------------+
2622 .. [#envmap-bumpmap] http://www.opengl.org/registry/specs/ATI/envmap_bumpmap.txt
2623 .. [#depth-tex-mode] the default is (z, z, z, 1) but may also be (0, 0, 0, z)
2624 or (z, z, z, z) depending on the value of GL_DEPTH_TEXTURE_MODE.