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
1257 The shift count is masked with 0x1f before the shift is applied.
1261 dst.x = src0.x << (0x1f & src1.x)
1263 dst.y = src0.y << (0x1f & src1.y)
1265 dst.z = src0.z << (0x1f & src1.z)
1267 dst.w = src0.w << (0x1f & src1.w)
1270 .. opcode:: ISHR - Arithmetic Shift Right (of Signed Integer)
1272 The shift count is masked with 0x1f before the shift is applied.
1276 dst.x = src0.x >> (0x1f & src1.x)
1278 dst.y = src0.y >> (0x1f & src1.y)
1280 dst.z = src0.z >> (0x1f & src1.z)
1282 dst.w = src0.w >> (0x1f & src1.w)
1285 .. opcode:: USHR - Logical Shift Right
1287 The shift count is masked with 0x1f before the shift is applied.
1291 dst.x = src0.x >> (unsigned) (0x1f & src1.x)
1293 dst.y = src0.y >> (unsigned) (0x1f & src1.y)
1295 dst.z = src0.z >> (unsigned) (0x1f & src1.z)
1297 dst.w = src0.w >> (unsigned) (0x1f & src1.w)
1300 .. opcode:: UCMP - Integer Conditional Move
1304 dst.x = src0.x ? src1.x : src2.x
1306 dst.y = src0.y ? src1.y : src2.y
1308 dst.z = src0.z ? src1.z : src2.z
1310 dst.w = src0.w ? src1.w : src2.w
1314 .. opcode:: ISSG - Integer Set Sign
1318 dst.x = (src0.x < 0) ? -1 : (src0.x > 0) ? 1 : 0
1320 dst.y = (src0.y < 0) ? -1 : (src0.y > 0) ? 1 : 0
1322 dst.z = (src0.z < 0) ? -1 : (src0.z > 0) ? 1 : 0
1324 dst.w = (src0.w < 0) ? -1 : (src0.w > 0) ? 1 : 0
1328 .. opcode:: ISLT - Signed Integer Set On Less Than
1332 dst.x = (src0.x < src1.x) ? ~0 : 0
1334 dst.y = (src0.y < src1.y) ? ~0 : 0
1336 dst.z = (src0.z < src1.z) ? ~0 : 0
1338 dst.w = (src0.w < src1.w) ? ~0 : 0
1341 .. opcode:: USLT - Unsigned Integer Set On Less Than
1345 dst.x = (src0.x < src1.x) ? ~0 : 0
1347 dst.y = (src0.y < src1.y) ? ~0 : 0
1349 dst.z = (src0.z < src1.z) ? ~0 : 0
1351 dst.w = (src0.w < src1.w) ? ~0 : 0
1354 .. opcode:: ISGE - Signed Integer Set On Greater Equal Than
1358 dst.x = (src0.x >= src1.x) ? ~0 : 0
1360 dst.y = (src0.y >= src1.y) ? ~0 : 0
1362 dst.z = (src0.z >= src1.z) ? ~0 : 0
1364 dst.w = (src0.w >= src1.w) ? ~0 : 0
1367 .. opcode:: USGE - Unsigned Integer Set On Greater Equal Than
1371 dst.x = (src0.x >= src1.x) ? ~0 : 0
1373 dst.y = (src0.y >= src1.y) ? ~0 : 0
1375 dst.z = (src0.z >= src1.z) ? ~0 : 0
1377 dst.w = (src0.w >= src1.w) ? ~0 : 0
1380 .. opcode:: USEQ - Integer Set On Equal
1384 dst.x = (src0.x == src1.x) ? ~0 : 0
1386 dst.y = (src0.y == src1.y) ? ~0 : 0
1388 dst.z = (src0.z == src1.z) ? ~0 : 0
1390 dst.w = (src0.w == src1.w) ? ~0 : 0
1393 .. opcode:: USNE - Integer Set On Not Equal
1397 dst.x = (src0.x != src1.x) ? ~0 : 0
1399 dst.y = (src0.y != src1.y) ? ~0 : 0
1401 dst.z = (src0.z != src1.z) ? ~0 : 0
1403 dst.w = (src0.w != src1.w) ? ~0 : 0
1406 .. opcode:: INEG - Integer Negate
1421 .. opcode:: IABS - Integer Absolute Value
1435 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1437 These opcodes are only supported in geometry shaders; they have no meaning
1438 in any other type of shader.
1440 .. opcode:: EMIT - Emit
1442 Generate a new vertex for the current primitive using the values in the
1446 .. opcode:: ENDPRIM - End Primitive
1448 Complete the current primitive (consisting of the emitted vertices),
1449 and start a new one.
1455 These opcodes are part of :term:`GLSL`'s opcode set. Support for these
1456 opcodes is determined by a special capability bit, ``GLSL``.
1457 Some require glsl version 1.30 (UIF/BREAKC/SWITCH/CASE/DEFAULT/ENDSWITCH).
1459 .. opcode:: CAL - Subroutine Call
1465 .. opcode:: RET - Subroutine Call Return
1470 .. opcode:: CONT - Continue
1472 Unconditionally moves the point of execution to the instruction after the
1473 last bgnloop. The instruction must appear within a bgnloop/endloop.
1477 Support for CONT is determined by a special capability bit,
1478 ``TGSI_CONT_SUPPORTED``. See :ref:`Screen` for more information.
1481 .. opcode:: BGNLOOP - Begin a Loop
1483 Start a loop. Must have a matching endloop.
1486 .. opcode:: BGNSUB - Begin Subroutine
1488 Starts definition of a subroutine. Must have a matching endsub.
1491 .. opcode:: ENDLOOP - End a Loop
1493 End a loop started with bgnloop.
1496 .. opcode:: ENDSUB - End Subroutine
1498 Ends definition of a subroutine.
1501 .. opcode:: NOP - No Operation
1506 .. opcode:: BRK - Break
1508 Unconditionally moves the point of execution to the instruction after the
1509 next endloop or endswitch. The instruction must appear within a loop/endloop
1510 or switch/endswitch.
1513 .. opcode:: BREAKC - Break Conditional
1515 Conditionally moves the point of execution to the instruction after the
1516 next endloop or endswitch. The instruction must appear within a loop/endloop
1517 or switch/endswitch.
1518 Condition evaluates to true if src0.x != 0 where src0.x is interpreted
1519 as an integer register.
1523 Considered for removal as it's quite inconsistent wrt other opcodes
1524 (could emulate with UIF/BRK/ENDIF).
1527 .. opcode:: IF - Float If
1529 Start an IF ... ELSE .. ENDIF block. Condition evaluates to true if
1533 where src0.x is interpreted as a floating point register.
1536 .. opcode:: UIF - Bitwise If
1538 Start an UIF ... ELSE .. ENDIF block. Condition evaluates to true if
1542 where src0.x is interpreted as an integer register.
1545 .. opcode:: ELSE - Else
1547 Starts an else block, after an IF or UIF statement.
1550 .. opcode:: ENDIF - End If
1552 Ends an IF or UIF block.
1555 .. opcode:: SWITCH - Switch
1557 Starts a C-style switch expression. The switch consists of one or multiple
1558 CASE statements, and at most one DEFAULT statement. Execution of a statement
1559 ends when a BRK is hit, but just like in C falling through to other cases
1560 without a break is allowed. Similarly, DEFAULT label is allowed anywhere not
1561 just as last statement, and fallthrough is allowed into/from it.
1562 CASE src arguments are evaluated at bit level against the SWITCH src argument.
1567 (some instructions here)
1570 (some instructions here)
1573 (some instructions here)
1578 .. opcode:: CASE - Switch case
1580 This represents a switch case label. The src arg must be an integer immediate.
1583 .. opcode:: DEFAULT - Switch default
1585 This represents the default case in the switch, which is taken if no other
1589 .. opcode:: ENDSWITCH - End of switch
1591 Ends a switch expression.
1594 .. opcode:: NRM4 - 4-component Vector Normalise
1596 This instruction replicates its result.
1600 dst = \frac{src.x}{src.x \times src.x + src.y \times src.y + src.z \times src.z + src.w \times src.w}
1608 The double-precision opcodes reinterpret four-component vectors into
1609 two-component vectors with doubled precision in each component.
1611 Support for these opcodes is XXX undecided. :T
1613 .. opcode:: DADD - Add
1617 dst.xy = src0.xy + src1.xy
1619 dst.zw = src0.zw + src1.zw
1622 .. opcode:: DDIV - Divide
1626 dst.xy = src0.xy / src1.xy
1628 dst.zw = src0.zw / src1.zw
1630 .. opcode:: DSEQ - Set on Equal
1634 dst.xy = src0.xy == src1.xy ? 1.0F : 0.0F
1636 dst.zw = src0.zw == src1.zw ? 1.0F : 0.0F
1638 .. opcode:: DSLT - Set on Less than
1642 dst.xy = src0.xy < src1.xy ? 1.0F : 0.0F
1644 dst.zw = src0.zw < src1.zw ? 1.0F : 0.0F
1646 .. opcode:: DFRAC - Fraction
1650 dst.xy = src.xy - \lfloor src.xy\rfloor
1652 dst.zw = src.zw - \lfloor src.zw\rfloor
1655 .. opcode:: DFRACEXP - Convert Number to Fractional and Integral Components
1657 Like the ``frexp()`` routine in many math libraries, this opcode stores the
1658 exponent of its source to ``dst0``, and the significand to ``dst1``, such that
1659 :math:`dst1 \times 2^{dst0} = src` .
1663 dst0.xy = exp(src.xy)
1665 dst1.xy = frac(src.xy)
1667 dst0.zw = exp(src.zw)
1669 dst1.zw = frac(src.zw)
1671 .. opcode:: DLDEXP - Multiply Number by Integral Power of 2
1673 This opcode is the inverse of :opcode:`DFRACEXP`.
1677 dst.xy = src0.xy \times 2^{src1.xy}
1679 dst.zw = src0.zw \times 2^{src1.zw}
1681 .. opcode:: DMIN - Minimum
1685 dst.xy = min(src0.xy, src1.xy)
1687 dst.zw = min(src0.zw, src1.zw)
1689 .. opcode:: DMAX - Maximum
1693 dst.xy = max(src0.xy, src1.xy)
1695 dst.zw = max(src0.zw, src1.zw)
1697 .. opcode:: DMUL - Multiply
1701 dst.xy = src0.xy \times src1.xy
1703 dst.zw = src0.zw \times src1.zw
1706 .. opcode:: DMAD - Multiply And Add
1710 dst.xy = src0.xy \times src1.xy + src2.xy
1712 dst.zw = src0.zw \times src1.zw + src2.zw
1715 .. opcode:: DRCP - Reciprocal
1719 dst.xy = \frac{1}{src.xy}
1721 dst.zw = \frac{1}{src.zw}
1723 .. opcode:: DSQRT - Square Root
1727 dst.xy = \sqrt{src.xy}
1729 dst.zw = \sqrt{src.zw}
1732 .. _samplingopcodes:
1734 Resource Sampling Opcodes
1735 ^^^^^^^^^^^^^^^^^^^^^^^^^
1737 Those opcodes follow very closely semantics of the respective Direct3D
1738 instructions. If in doubt double check Direct3D documentation.
1739 Note that the swizzle on SVIEW (src1) determines texel swizzling
1742 .. opcode:: SAMPLE - Using provided address, sample data from the
1743 specified texture using the filtering mode identified
1744 by the gven sampler. The source data may come from
1745 any resource type other than buffers.
1746 SAMPLE dst, address, sampler_view, sampler
1748 SAMPLE TEMP[0], TEMP[1], SVIEW[0], SAMP[0]
1750 .. opcode:: SAMPLE_I - Simplified alternative to the SAMPLE instruction.
1751 Using the provided integer address, SAMPLE_I fetches data
1752 from the specified sampler view without any filtering.
1753 The source data may come from any resource type other
1755 SAMPLE_I dst, address, sampler_view
1757 SAMPLE_I TEMP[0], TEMP[1], SVIEW[0]
1758 The 'address' is specified as unsigned integers. If the
1759 'address' is out of range [0...(# texels - 1)] the
1760 result of the fetch is always 0 in all components.
1761 As such the instruction doesn't honor address wrap
1762 modes, in cases where that behavior is desirable
1763 'SAMPLE' instruction should be used.
1764 address.w always provides an unsigned integer mipmap
1765 level. If the value is out of the range then the
1766 instruction always returns 0 in all components.
1767 address.yz are ignored for buffers and 1d textures.
1768 address.z is ignored for 1d texture arrays and 2d
1770 For 1D texture arrays address.y provides the array
1771 index (also as unsigned integer). If the value is
1772 out of the range of available array indices
1773 [0... (array size - 1)] then the opcode always returns
1774 0 in all components.
1775 For 2D texture arrays address.z provides the array
1776 index, otherwise it exhibits the same behavior as in
1777 the case for 1D texture arrays.
1778 The exact semantics of the source address are presented
1780 resource type X Y Z W
1781 ------------- ------------------------
1782 PIPE_BUFFER x ignored
1783 PIPE_TEXTURE_1D x mpl
1784 PIPE_TEXTURE_2D x y mpl
1785 PIPE_TEXTURE_3D x y z mpl
1786 PIPE_TEXTURE_RECT x y mpl
1787 PIPE_TEXTURE_CUBE not allowed as source
1788 PIPE_TEXTURE_1D_ARRAY x idx mpl
1789 PIPE_TEXTURE_2D_ARRAY x y idx mpl
1791 Where 'mpl' is a mipmap level and 'idx' is the
1794 .. opcode:: SAMPLE_I_MS - Just like SAMPLE_I but allows fetch data from
1795 multi-sampled surfaces.
1796 SAMPLE_I_MS dst, address, sampler_view, sample
1798 .. opcode:: SAMPLE_B - Just like the SAMPLE instruction with the
1799 exception that an additional bias is applied to the
1800 level of detail computed as part of the instruction
1802 SAMPLE_B dst, address, sampler_view, sampler, lod_bias
1804 SAMPLE_B TEMP[0], TEMP[1], SVIEW[0], SAMP[0], TEMP[2].x
1806 .. opcode:: SAMPLE_C - Similar to the SAMPLE instruction but it
1807 performs a comparison filter. The operands to SAMPLE_C
1808 are identical to SAMPLE, except that there is an additional
1809 float32 operand, reference value, which must be a register
1810 with single-component, or a scalar literal.
1811 SAMPLE_C makes the hardware use the current samplers
1812 compare_func (in pipe_sampler_state) to compare
1813 reference value against the red component value for the
1814 surce resource at each texel that the currently configured
1815 texture filter covers based on the provided coordinates.
1816 SAMPLE_C dst, address, sampler_view.r, sampler, ref_value
1818 SAMPLE_C TEMP[0], TEMP[1], SVIEW[0].r, SAMP[0], TEMP[2].x
1820 .. opcode:: SAMPLE_C_LZ - Same as SAMPLE_C, but LOD is 0 and derivatives
1821 are ignored. The LZ stands for level-zero.
1822 SAMPLE_C_LZ dst, address, sampler_view.r, sampler, ref_value
1824 SAMPLE_C_LZ TEMP[0], TEMP[1], SVIEW[0].r, SAMP[0], TEMP[2].x
1827 .. opcode:: SAMPLE_D - SAMPLE_D is identical to the SAMPLE opcode except
1828 that the derivatives for the source address in the x
1829 direction and the y direction are provided by extra
1831 SAMPLE_D dst, address, sampler_view, sampler, der_x, der_y
1833 SAMPLE_D TEMP[0], TEMP[1], SVIEW[0], SAMP[0], TEMP[2], TEMP[3]
1835 .. opcode:: SAMPLE_L - SAMPLE_L is identical to the SAMPLE opcode except
1836 that the LOD is provided directly as a scalar value,
1837 representing no anisotropy.
1838 SAMPLE_L dst, address, sampler_view, sampler, explicit_lod
1840 SAMPLE_L TEMP[0], TEMP[1], SVIEW[0], SAMP[0], TEMP[2].x
1842 .. opcode:: GATHER4 - Gathers the four texels to be used in a bi-linear
1843 filtering operation and packs them into a single register.
1844 Only works with 2D, 2D array, cubemaps, and cubemaps arrays.
1845 For 2D textures, only the addressing modes of the sampler and
1846 the top level of any mip pyramid are used. Set W to zero.
1847 It behaves like the SAMPLE instruction, but a filtered
1848 sample is not generated. The four samples that contribute
1849 to filtering are placed into xyzw in counter-clockwise order,
1850 starting with the (u,v) texture coordinate delta at the
1851 following locations (-, +), (+, +), (+, -), (-, -), where
1852 the magnitude of the deltas are half a texel.
1855 .. opcode:: SVIEWINFO - query the dimensions of a given sampler view.
1856 dst receives width, height, depth or array size and
1857 number of mipmap levels as int4. The dst can have a writemask
1858 which will specify what info is the caller interested
1860 SVIEWINFO dst, src_mip_level, sampler_view
1862 SVIEWINFO TEMP[0], TEMP[1].x, SVIEW[0]
1863 src_mip_level is an unsigned integer scalar. If it's
1864 out of range then returns 0 for width, height and
1865 depth/array size but the total number of mipmap is
1866 still returned correctly for the given sampler view.
1867 The returned width, height and depth values are for
1868 the mipmap level selected by the src_mip_level and
1869 are in the number of texels.
1870 For 1d texture array width is in dst.x, array size
1871 is in dst.y and dst.z is 0. The number of mipmaps
1873 In contrast to d3d10 resinfo, there's no way in the
1874 tgsi instruction encoding to specify the return type
1875 (float/rcpfloat/uint), hence always using uint. Also,
1876 unlike the SAMPLE instructions, the swizzle on src1
1877 resinfo allowing swizzling dst values is ignored (due
1878 to the interaction with rcpfloat modifier which requires
1879 some swizzle handling in the state tracker anyway).
1881 .. opcode:: SAMPLE_POS - query the position of a given sample.
1882 dst receives float4 (x, y, 0, 0) indicated where the
1883 sample is located. If the resource is not a multi-sample
1884 resource and not a render target, the result is 0.
1886 .. opcode:: SAMPLE_INFO - dst receives number of samples in x.
1887 If the resource is not a multi-sample resource and
1888 not a render target, the result is 0.
1891 .. _resourceopcodes:
1893 Resource Access Opcodes
1894 ^^^^^^^^^^^^^^^^^^^^^^^
1896 .. opcode:: LOAD - Fetch data from a shader resource
1898 Syntax: ``LOAD dst, resource, address``
1900 Example: ``LOAD TEMP[0], RES[0], TEMP[1]``
1902 Using the provided integer address, LOAD fetches data
1903 from the specified buffer or texture without any
1906 The 'address' is specified as a vector of unsigned
1907 integers. If the 'address' is out of range the result
1910 Only the first mipmap level of a resource can be read
1911 from using this instruction.
1913 For 1D or 2D texture arrays, the array index is
1914 provided as an unsigned integer in address.y or
1915 address.z, respectively. address.yz are ignored for
1916 buffers and 1D textures. address.z is ignored for 1D
1917 texture arrays and 2D textures. address.w is always
1920 .. opcode:: STORE - Write data to a shader resource
1922 Syntax: ``STORE resource, address, src``
1924 Example: ``STORE RES[0], TEMP[0], TEMP[1]``
1926 Using the provided integer address, STORE writes data
1927 to the specified buffer or texture.
1929 The 'address' is specified as a vector of unsigned
1930 integers. If the 'address' is out of range the result
1933 Only the first mipmap level of a resource can be
1934 written to using this instruction.
1936 For 1D or 2D texture arrays, the array index is
1937 provided as an unsigned integer in address.y or
1938 address.z, respectively. address.yz are ignored for
1939 buffers and 1D textures. address.z is ignored for 1D
1940 texture arrays and 2D textures. address.w is always
1944 .. _threadsyncopcodes:
1946 Inter-thread synchronization opcodes
1947 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1949 These opcodes are intended for communication between threads running
1950 within the same compute grid. For now they're only valid in compute
1953 .. opcode:: MFENCE - Memory fence
1955 Syntax: ``MFENCE resource``
1957 Example: ``MFENCE RES[0]``
1959 This opcode forces strong ordering between any memory access
1960 operations that affect the specified resource. This means that
1961 previous loads and stores (and only those) will be performed and
1962 visible to other threads before the program execution continues.
1965 .. opcode:: LFENCE - Load memory fence
1967 Syntax: ``LFENCE resource``
1969 Example: ``LFENCE RES[0]``
1971 Similar to MFENCE, but it only affects the ordering of memory loads.
1974 .. opcode:: SFENCE - Store memory fence
1976 Syntax: ``SFENCE resource``
1978 Example: ``SFENCE RES[0]``
1980 Similar to MFENCE, but it only affects the ordering of memory stores.
1983 .. opcode:: BARRIER - Thread group barrier
1987 This opcode suspends the execution of the current thread until all
1988 the remaining threads in the working group reach the same point of
1989 the program. Results are unspecified if any of the remaining
1990 threads terminates or never reaches an executed BARRIER instruction.
1998 These opcodes provide atomic variants of some common arithmetic and
1999 logical operations. In this context atomicity means that another
2000 concurrent memory access operation that affects the same memory
2001 location is guaranteed to be performed strictly before or after the
2002 entire execution of the atomic operation.
2004 For the moment they're only valid in compute programs.
2006 .. opcode:: ATOMUADD - Atomic integer addition
2008 Syntax: ``ATOMUADD dst, resource, offset, src``
2010 Example: ``ATOMUADD TEMP[0], RES[0], TEMP[1], TEMP[2]``
2012 The following operation is performed atomically on each component:
2016 dst_i = resource[offset]_i
2018 resource[offset]_i = dst_i + src_i
2021 .. opcode:: ATOMXCHG - Atomic exchange
2023 Syntax: ``ATOMXCHG dst, resource, offset, src``
2025 Example: ``ATOMXCHG TEMP[0], RES[0], TEMP[1], TEMP[2]``
2027 The following operation is performed atomically on each component:
2031 dst_i = resource[offset]_i
2033 resource[offset]_i = src_i
2036 .. opcode:: ATOMCAS - Atomic compare-and-exchange
2038 Syntax: ``ATOMCAS dst, resource, offset, cmp, src``
2040 Example: ``ATOMCAS TEMP[0], RES[0], TEMP[1], TEMP[2], TEMP[3]``
2042 The following operation is performed atomically on each component:
2046 dst_i = resource[offset]_i
2048 resource[offset]_i = (dst_i == cmp_i ? src_i : dst_i)
2051 .. opcode:: ATOMAND - Atomic bitwise And
2053 Syntax: ``ATOMAND dst, resource, offset, src``
2055 Example: ``ATOMAND TEMP[0], RES[0], TEMP[1], TEMP[2]``
2057 The following operation is performed atomically on each component:
2061 dst_i = resource[offset]_i
2063 resource[offset]_i = dst_i \& src_i
2066 .. opcode:: ATOMOR - Atomic bitwise Or
2068 Syntax: ``ATOMOR dst, resource, offset, src``
2070 Example: ``ATOMOR TEMP[0], RES[0], TEMP[1], TEMP[2]``
2072 The following operation is performed atomically on each component:
2076 dst_i = resource[offset]_i
2078 resource[offset]_i = dst_i | src_i
2081 .. opcode:: ATOMXOR - Atomic bitwise Xor
2083 Syntax: ``ATOMXOR dst, resource, offset, src``
2085 Example: ``ATOMXOR TEMP[0], RES[0], TEMP[1], TEMP[2]``
2087 The following operation is performed atomically on each component:
2091 dst_i = resource[offset]_i
2093 resource[offset]_i = dst_i \oplus src_i
2096 .. opcode:: ATOMUMIN - Atomic unsigned minimum
2098 Syntax: ``ATOMUMIN dst, resource, offset, src``
2100 Example: ``ATOMUMIN TEMP[0], RES[0], TEMP[1], TEMP[2]``
2102 The following operation is performed atomically on each component:
2106 dst_i = resource[offset]_i
2108 resource[offset]_i = (dst_i < src_i ? dst_i : src_i)
2111 .. opcode:: ATOMUMAX - Atomic unsigned maximum
2113 Syntax: ``ATOMUMAX dst, resource, offset, src``
2115 Example: ``ATOMUMAX TEMP[0], RES[0], TEMP[1], TEMP[2]``
2117 The following operation is performed atomically on each component:
2121 dst_i = resource[offset]_i
2123 resource[offset]_i = (dst_i > src_i ? dst_i : src_i)
2126 .. opcode:: ATOMIMIN - Atomic signed minimum
2128 Syntax: ``ATOMIMIN dst, resource, offset, src``
2130 Example: ``ATOMIMIN TEMP[0], RES[0], TEMP[1], TEMP[2]``
2132 The following operation is performed atomically on each component:
2136 dst_i = resource[offset]_i
2138 resource[offset]_i = (dst_i < src_i ? dst_i : src_i)
2141 .. opcode:: ATOMIMAX - Atomic signed maximum
2143 Syntax: ``ATOMIMAX dst, resource, offset, src``
2145 Example: ``ATOMIMAX TEMP[0], RES[0], TEMP[1], TEMP[2]``
2147 The following operation is performed atomically on each component:
2151 dst_i = resource[offset]_i
2153 resource[offset]_i = (dst_i > src_i ? dst_i : src_i)
2157 Explanation of symbols used
2158 ------------------------------
2165 :math:`|x|` Absolute value of `x`.
2167 :math:`\lceil x \rceil` Ceiling of `x`.
2169 clamp(x,y,z) Clamp x between y and z.
2170 (x < y) ? y : (x > z) ? z : x
2172 :math:`\lfloor x\rfloor` Floor of `x`.
2174 :math:`\log_2{x}` Logarithm of `x`, base 2.
2176 max(x,y) Maximum of x and y.
2179 min(x,y) Minimum of x and y.
2182 partialx(x) Derivative of x relative to fragment's X.
2184 partialy(x) Derivative of x relative to fragment's Y.
2186 pop() Pop from stack.
2188 :math:`x^y` `x` to the power `y`.
2190 push(x) Push x on stack.
2194 trunc(x) Truncate x, i.e. drop the fraction bits.
2201 discard Discard fragment.
2205 target Label of target instruction.
2216 Declares a register that is will be referenced as an operand in Instruction
2219 File field contains register file that is being declared and is one
2222 UsageMask field specifies which of the register components can be accessed
2223 and is one of TGSI_WRITEMASK.
2225 The Local flag specifies that a given value isn't intended for
2226 subroutine parameter passing and, as a result, the implementation
2227 isn't required to give any guarantees of it being preserved across
2228 subroutine boundaries. As it's merely a compiler hint, the
2229 implementation is free to ignore it.
2231 If Dimension flag is set to 1, a Declaration Dimension token follows.
2233 If Semantic flag is set to 1, a Declaration Semantic token follows.
2235 If Interpolate flag is set to 1, a Declaration Interpolate token follows.
2237 If file is TGSI_FILE_RESOURCE, a Declaration Resource token follows.
2239 If Array flag is set to 1, a Declaration Array token follows.
2242 ^^^^^^^^^^^^^^^^^^^^^^^^
2244 Declarations can optional have an ArrayID attribute which can be referred by
2245 indirect addressing operands. An ArrayID of zero is reserved and treaded as
2246 if no ArrayID is specified.
2248 If an indirect addressing operand refers to a specific declaration by using
2249 an ArrayID only the registers in this declaration are guaranteed to be
2250 accessed, accessing any register outside this declaration results in undefined
2251 behavior. Note that for compatibility the effective index is zero-based and
2252 not relative to the specified declaration
2254 If no ArrayID is specified with an indirect addressing operand the whole
2255 register file might be accessed by this operand. This is strongly discouraged
2256 and will prevent packing of scalar/vec2 arrays and effective alias analysis.
2258 Declaration Semantic
2259 ^^^^^^^^^^^^^^^^^^^^^^^^
2261 Vertex and fragment shader input and output registers may be labeled
2262 with semantic information consisting of a name and index.
2264 Follows Declaration token if Semantic bit is set.
2266 Since its purpose is to link a shader with other stages of the pipeline,
2267 it is valid to follow only those Declaration tokens that declare a register
2268 either in INPUT or OUTPUT file.
2270 SemanticName field contains the semantic name of the register being declared.
2271 There is no default value.
2273 SemanticIndex is an optional subscript that can be used to distinguish
2274 different register declarations with the same semantic name. The default value
2277 The meanings of the individual semantic names are explained in the following
2280 TGSI_SEMANTIC_POSITION
2281 """"""""""""""""""""""
2283 For vertex shaders, TGSI_SEMANTIC_POSITION indicates the vertex shader
2284 output register which contains the homogeneous vertex position in the clip
2285 space coordinate system. After clipping, the X, Y and Z components of the
2286 vertex will be divided by the W value to get normalized device coordinates.
2288 For fragment shaders, TGSI_SEMANTIC_POSITION is used to indicate that
2289 fragment shader input contains the fragment's window position. The X
2290 component starts at zero and always increases from left to right.
2291 The Y component starts at zero and always increases but Y=0 may either
2292 indicate the top of the window or the bottom depending on the fragment
2293 coordinate origin convention (see TGSI_PROPERTY_FS_COORD_ORIGIN).
2294 The Z coordinate ranges from 0 to 1 to represent depth from the front
2295 to the back of the Z buffer. The W component contains the reciprocol
2296 of the interpolated vertex position W component.
2298 Fragment shaders may also declare an output register with
2299 TGSI_SEMANTIC_POSITION. Only the Z component is writable. This allows
2300 the fragment shader to change the fragment's Z position.
2307 For vertex shader outputs or fragment shader inputs/outputs, this
2308 label indicates that the resister contains an R,G,B,A color.
2310 Several shader inputs/outputs may contain colors so the semantic index
2311 is used to distinguish them. For example, color[0] may be the diffuse
2312 color while color[1] may be the specular color.
2314 This label is needed so that the flat/smooth shading can be applied
2315 to the right interpolants during rasterization.
2319 TGSI_SEMANTIC_BCOLOR
2320 """"""""""""""""""""
2322 Back-facing colors are only used for back-facing polygons, and are only valid
2323 in vertex shader outputs. After rasterization, all polygons are front-facing
2324 and COLOR and BCOLOR end up occupying the same slots in the fragment shader,
2325 so all BCOLORs effectively become regular COLORs in the fragment shader.
2331 Vertex shader inputs and outputs and fragment shader inputs may be
2332 labeled with TGSI_SEMANTIC_FOG to indicate that the register contains
2333 a fog coordinate in the form (F, 0, 0, 1). Typically, the fragment
2334 shader will use the fog coordinate to compute a fog blend factor which
2335 is used to blend the normal fragment color with a constant fog color.
2337 Only the first component matters when writing from the vertex shader;
2338 the driver will ensure that the coordinate is in this format when used
2339 as a fragment shader input.
2345 Vertex shader input and output registers may be labeled with
2346 TGIS_SEMANTIC_PSIZE to indicate that the register contains a point size
2347 in the form (S, 0, 0, 1). The point size controls the width or diameter
2348 of points for rasterization. This label cannot be used in fragment
2351 When using this semantic, be sure to set the appropriate state in the
2352 :ref:`rasterizer` first.
2355 TGSI_SEMANTIC_TEXCOORD
2356 """"""""""""""""""""""
2358 Only available if PIPE_CAP_TGSI_TEXCOORD is exposed !
2360 Vertex shader outputs and fragment shader inputs may be labeled with
2361 this semantic to make them replaceable by sprite coordinates via the
2362 sprite_coord_enable state in the :ref:`rasterizer`.
2363 The semantic index permitted with this semantic is limited to <= 7.
2365 If the driver does not support TEXCOORD, sprite coordinate replacement
2366 applies to inputs with the GENERIC semantic instead.
2368 The intended use case for this semantic is gl_TexCoord.
2371 TGSI_SEMANTIC_PCOORD
2372 """"""""""""""""""""
2374 Only available if PIPE_CAP_TGSI_TEXCOORD is exposed !
2376 Fragment shader inputs may be labeled with TGSI_SEMANTIC_PCOORD to indicate
2377 that the register contains sprite coordinates in the form (x, y, 0, 1), if
2378 the current primitive is a point and point sprites are enabled. Otherwise,
2379 the contents of the register are undefined.
2381 The intended use case for this semantic is gl_PointCoord.
2384 TGSI_SEMANTIC_GENERIC
2385 """""""""""""""""""""
2387 All vertex/fragment shader inputs/outputs not labeled with any other
2388 semantic label can be considered to be generic attributes. Typical
2389 uses of generic inputs/outputs are texcoords and user-defined values.
2392 TGSI_SEMANTIC_NORMAL
2393 """"""""""""""""""""
2395 Indicates that a vertex shader input is a normal vector. This is
2396 typically only used for legacy graphics APIs.
2402 This label applies to fragment shader inputs only and indicates that
2403 the register contains front/back-face information of the form (F, 0,
2404 0, 1). The first component will be positive when the fragment belongs
2405 to a front-facing polygon, and negative when the fragment belongs to a
2406 back-facing polygon.
2409 TGSI_SEMANTIC_EDGEFLAG
2410 """"""""""""""""""""""
2412 For vertex shaders, this sematic label indicates that an input or
2413 output is a boolean edge flag. The register layout is [F, x, x, x]
2414 where F is 0.0 or 1.0 and x = don't care. Normally, the vertex shader
2415 simply copies the edge flag input to the edgeflag output.
2417 Edge flags are used to control which lines or points are actually
2418 drawn when the polygon mode converts triangles/quads/polygons into
2422 TGSI_SEMANTIC_STENCIL
2423 """""""""""""""""""""
2425 For fragment shaders, this semantic label indicates that an output
2426 is a writable stencil reference value. Only the Y component is writable.
2427 This allows the fragment shader to change the fragments stencilref value.
2430 TGSI_SEMANTIC_VIEWPORT_INDEX
2431 """"""""""""""""""""""""""""
2433 For geometry shaders, this semantic label indicates that an output
2434 contains the index of the viewport (and scissor) to use.
2435 Only the X value is used.
2441 For geometry shaders, this semantic label indicates that an output
2442 contains the layer value to use for the color and depth/stencil surfaces.
2443 Only the X value is used. (Also known as rendertarget array index.)
2446 TGSI_SEMANTIC_CULLDIST
2447 """"""""""""""""""""""
2449 Used as distance to plane for performing application-defined culling
2450 of individual primitives against a plane. When components of vertex
2451 elements are given this label, these values are assumed to be a
2452 float32 signed distance to a plane. Primitives will be completely
2453 discarded if the plane distance for all of the vertices in the
2454 primitive are < 0. If a vertex has a cull distance of NaN, that
2455 vertex counts as "out" (as if its < 0);
2456 The limits on both clip and cull distances are bound
2457 by the PIPE_MAX_CLIP_OR_CULL_DISTANCE_COUNT define which defines
2458 the maximum number of components that can be used to hold the
2459 distances and by the PIPE_MAX_CLIP_OR_CULL_DISTANCE_ELEMENT_COUNT
2460 which specifies the maximum number of registers which can be
2461 annotated with those semantics.
2464 TGSI_SEMANTIC_CLIPDIST
2465 """"""""""""""""""""""
2467 When components of vertex elements are identified this way, these
2468 values are each assumed to be a float32 signed distance to a plane.
2469 Primitive setup only invokes rasterization on pixels for which
2470 the interpolated plane distances are >= 0. Multiple clip planes
2471 can be implemented simultaneously, by annotating multiple
2472 components of one or more vertex elements with the above specified
2473 semantic. The limits on both clip and cull distances are bound
2474 by the PIPE_MAX_CLIP_OR_CULL_DISTANCE_COUNT define which defines
2475 the maximum number of components that can be used to hold the
2476 distances and by the PIPE_MAX_CLIP_OR_CULL_DISTANCE_ELEMENT_COUNT
2477 which specifies the maximum number of registers which can be
2478 annotated with those semantics.
2481 Declaration Interpolate
2482 ^^^^^^^^^^^^^^^^^^^^^^^
2484 This token is only valid for fragment shader INPUT declarations.
2486 The Interpolate field specifes the way input is being interpolated by
2487 the rasteriser and is one of TGSI_INTERPOLATE_*.
2489 The CylindricalWrap bitfield specifies which register components
2490 should be subject to cylindrical wrapping when interpolating by the
2491 rasteriser. If TGSI_CYLINDRICAL_WRAP_X is set to 1, the X component
2492 should be interpolated according to cylindrical wrapping rules.
2495 Declaration Sampler View
2496 ^^^^^^^^^^^^^^^^^^^^^^^^
2498 Follows Declaration token if file is TGSI_FILE_SAMPLER_VIEW.
2500 DCL SVIEW[#], resource, type(s)
2502 Declares a shader input sampler view and assigns it to a SVIEW[#]
2505 resource can be one of BUFFER, 1D, 2D, 3D, 1DArray and 2DArray.
2507 type must be 1 or 4 entries (if specifying on a per-component
2508 level) out of UNORM, SNORM, SINT, UINT and FLOAT.
2511 Declaration Resource
2512 ^^^^^^^^^^^^^^^^^^^^
2514 Follows Declaration token if file is TGSI_FILE_RESOURCE.
2516 DCL RES[#], resource [, WR] [, RAW]
2518 Declares a shader input resource and assigns it to a RES[#]
2521 resource can be one of BUFFER, 1D, 2D, 3D, CUBE, 1DArray and
2524 If the RAW keyword is not specified, the texture data will be
2525 subject to conversion, swizzling and scaling as required to yield
2526 the specified data type from the physical data format of the bound
2529 If the RAW keyword is specified, no channel conversion will be
2530 performed: the values read for each of the channels (X,Y,Z,W) will
2531 correspond to consecutive words in the same order and format
2532 they're found in memory. No element-to-address conversion will be
2533 performed either: the value of the provided X coordinate will be
2534 interpreted in byte units instead of texel units. The result of
2535 accessing a misaligned address is undefined.
2537 Usage of the STORE opcode is only allowed if the WR (writable) flag
2542 ^^^^^^^^^^^^^^^^^^^^^^^^
2545 Properties are general directives that apply to the whole TGSI program.
2550 Specifies the fragment shader TGSI_SEMANTIC_POSITION coordinate origin.
2551 The default value is UPPER_LEFT.
2553 If UPPER_LEFT, the position will be (0,0) at the upper left corner and
2554 increase downward and rightward.
2555 If LOWER_LEFT, the position will be (0,0) at the lower left corner and
2556 increase upward and rightward.
2558 OpenGL defaults to LOWER_LEFT, and is configurable with the
2559 GL_ARB_fragment_coord_conventions extension.
2561 DirectX 9/10 use UPPER_LEFT.
2563 FS_COORD_PIXEL_CENTER
2564 """""""""""""""""""""
2566 Specifies the fragment shader TGSI_SEMANTIC_POSITION pixel center convention.
2567 The default value is HALF_INTEGER.
2569 If HALF_INTEGER, the fractionary part of the position will be 0.5
2570 If INTEGER, the fractionary part of the position will be 0.0
2572 Note that this does not affect the set of fragments generated by
2573 rasterization, which is instead controlled by half_pixel_center in the
2576 OpenGL defaults to HALF_INTEGER, and is configurable with the
2577 GL_ARB_fragment_coord_conventions extension.
2579 DirectX 9 uses INTEGER.
2580 DirectX 10 uses HALF_INTEGER.
2582 FS_COLOR0_WRITES_ALL_CBUFS
2583 """"""""""""""""""""""""""
2584 Specifies that writes to the fragment shader color 0 are replicated to all
2585 bound cbufs. This facilitates OpenGL's fragColor output vs fragData[0] where
2586 fragData is directed to a single color buffer, but fragColor is broadcast.
2589 """"""""""""""""""""""""""
2590 If this property is set on the program bound to the shader stage before the
2591 fragment shader, user clip planes should have no effect (be disabled) even if
2592 that shader does not write to any clip distance outputs and the rasterizer's
2593 clip_plane_enable is non-zero.
2594 This property is only supported by drivers that also support shader clip
2596 This is useful for APIs that don't have UCPs and where clip distances written
2597 by a shader cannot be disabled.
2600 Texture Sampling and Texture Formats
2601 ------------------------------------
2603 This table shows how texture image components are returned as (x,y,z,w) tuples
2604 by TGSI texture instructions, such as :opcode:`TEX`, :opcode:`TXD`, and
2605 :opcode:`TXP`. For reference, OpenGL and Direct3D conventions are shown as
2608 +--------------------+--------------+--------------------+--------------+
2609 | Texture Components | Gallium | OpenGL | Direct3D 9 |
2610 +====================+==============+====================+==============+
2611 | R | (r, 0, 0, 1) | (r, 0, 0, 1) | (r, 1, 1, 1) |
2612 +--------------------+--------------+--------------------+--------------+
2613 | RG | (r, g, 0, 1) | (r, g, 0, 1) | (r, g, 1, 1) |
2614 +--------------------+--------------+--------------------+--------------+
2615 | RGB | (r, g, b, 1) | (r, g, b, 1) | (r, g, b, 1) |
2616 +--------------------+--------------+--------------------+--------------+
2617 | RGBA | (r, g, b, a) | (r, g, b, a) | (r, g, b, a) |
2618 +--------------------+--------------+--------------------+--------------+
2619 | A | (0, 0, 0, a) | (0, 0, 0, a) | (0, 0, 0, a) |
2620 +--------------------+--------------+--------------------+--------------+
2621 | L | (l, l, l, 1) | (l, l, l, 1) | (l, l, l, 1) |
2622 +--------------------+--------------+--------------------+--------------+
2623 | LA | (l, l, l, a) | (l, l, l, a) | (l, l, l, a) |
2624 +--------------------+--------------+--------------------+--------------+
2625 | I | (i, i, i, i) | (i, i, i, i) | N/A |
2626 +--------------------+--------------+--------------------+--------------+
2627 | UV | XXX TBD | (0, 0, 0, 1) | (u, v, 1, 1) |
2628 | | | [#envmap-bumpmap]_ | |
2629 +--------------------+--------------+--------------------+--------------+
2630 | Z | XXX TBD | (z, z, z, 1) | (0, z, 0, 1) |
2631 | | | [#depth-tex-mode]_ | |
2632 +--------------------+--------------+--------------------+--------------+
2633 | S | (s, s, s, s) | unknown | unknown |
2634 +--------------------+--------------+--------------------+--------------+
2636 .. [#envmap-bumpmap] http://www.opengl.org/registry/specs/ATI/envmap_bumpmap.txt
2637 .. [#depth-tex-mode] the default is (z, z, z, 1) but may also be (0, 0, 0, z)
2638 or (z, z, z, z) depending on the value of GL_DEPTH_TEXTURE_MODE.