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:`doubleopcodes`.
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 and precise modifier
32 For arithmetic instruction having a precise modifier certain optimizations
33 which may alter the result are disallowed. Example: *add(mul(a,b),c)* can't be
34 optimized to TGSI_OPCODE_MAD, because some hardware only supports the fused
37 For inputs which have a floating point type, both absolute value and
38 negation modifiers are supported (with absolute value being applied
39 first). The only source of TGSI_OPCODE_MOV and the second and third
40 sources of TGSI_OPCODE_UCMP are considered to have float type for
43 For inputs which have signed or unsigned type only the negate modifier is
50 ^^^^^^^^^^^^^^^^^^^^^^^^^
52 These opcodes are guaranteed to be available regardless of the driver being
55 .. opcode:: ARL - Address Register Load
59 dst.x = (int) \lfloor src.x\rfloor
61 dst.y = (int) \lfloor src.y\rfloor
63 dst.z = (int) \lfloor src.z\rfloor
65 dst.w = (int) \lfloor src.w\rfloor
68 .. opcode:: MOV - Move
81 .. opcode:: LIT - Light Coefficients
86 dst.y &= max(src.x, 0) \\
87 dst.z &= (src.x > 0) ? max(src.y, 0)^{clamp(src.w, -128, 128))} : 0 \\
91 .. opcode:: RCP - Reciprocal
93 This instruction replicates its result.
100 .. opcode:: RSQ - Reciprocal Square Root
102 This instruction replicates its result. The results are undefined for src <= 0.
106 dst = \frac{1}{\sqrt{src.x}}
109 .. opcode:: SQRT - Square Root
111 This instruction replicates its result. The results are undefined for src < 0.
118 .. opcode:: EXP - Approximate Exponential Base 2
122 dst.x &= 2^{\lfloor src.x\rfloor} \\
123 dst.y &= src.x - \lfloor src.x\rfloor \\
124 dst.z &= 2^{src.x} \\
128 .. opcode:: LOG - Approximate Logarithm Base 2
132 dst.x &= \lfloor\log_2{|src.x|}\rfloor \\
133 dst.y &= \frac{|src.x|}{2^{\lfloor\log_2{|src.x|}\rfloor}} \\
134 dst.z &= \log_2{|src.x|} \\
138 .. opcode:: MUL - Multiply
142 dst.x = src0.x \times src1.x
144 dst.y = src0.y \times src1.y
146 dst.z = src0.z \times src1.z
148 dst.w = src0.w \times src1.w
151 .. opcode:: ADD - Add
155 dst.x = src0.x + src1.x
157 dst.y = src0.y + src1.y
159 dst.z = src0.z + src1.z
161 dst.w = src0.w + src1.w
164 .. opcode:: DP3 - 3-component Dot Product
166 This instruction replicates its result.
170 dst = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z
173 .. opcode:: DP4 - 4-component Dot Product
175 This instruction replicates its result.
179 dst = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z + src0.w \times src1.w
182 .. opcode:: DST - Distance Vector
187 dst.y &= src0.y \times src1.y\\
192 .. opcode:: MIN - Minimum
196 dst.x = min(src0.x, src1.x)
198 dst.y = min(src0.y, src1.y)
200 dst.z = min(src0.z, src1.z)
202 dst.w = min(src0.w, src1.w)
205 .. opcode:: MAX - Maximum
209 dst.x = max(src0.x, src1.x)
211 dst.y = max(src0.y, src1.y)
213 dst.z = max(src0.z, src1.z)
215 dst.w = max(src0.w, src1.w)
218 .. opcode:: SLT - Set On Less Than
222 dst.x = (src0.x < src1.x) ? 1.0F : 0.0F
224 dst.y = (src0.y < src1.y) ? 1.0F : 0.0F
226 dst.z = (src0.z < src1.z) ? 1.0F : 0.0F
228 dst.w = (src0.w < src1.w) ? 1.0F : 0.0F
231 .. opcode:: SGE - Set On Greater Equal Than
235 dst.x = (src0.x >= src1.x) ? 1.0F : 0.0F
237 dst.y = (src0.y >= src1.y) ? 1.0F : 0.0F
239 dst.z = (src0.z >= src1.z) ? 1.0F : 0.0F
241 dst.w = (src0.w >= src1.w) ? 1.0F : 0.0F
244 .. opcode:: MAD - Multiply And Add
246 Perform a * b + c. The implementation is free to decide whether there is an
247 intermediate rounding step or not.
251 dst.x = src0.x \times src1.x + src2.x
253 dst.y = src0.y \times src1.y + src2.y
255 dst.z = src0.z \times src1.z + src2.z
257 dst.w = src0.w \times src1.w + src2.w
260 .. opcode:: LRP - Linear Interpolate
264 dst.x = src0.x \times src1.x + (1 - src0.x) \times src2.x
266 dst.y = src0.y \times src1.y + (1 - src0.y) \times src2.y
268 dst.z = src0.z \times src1.z + (1 - src0.z) \times src2.z
270 dst.w = src0.w \times src1.w + (1 - src0.w) \times src2.w
273 .. opcode:: FMA - Fused Multiply-Add
275 Perform a * b + c with no intermediate rounding step.
279 dst.x = src0.x \times src1.x + src2.x
281 dst.y = src0.y \times src1.y + src2.y
283 dst.z = src0.z \times src1.z + src2.z
285 dst.w = src0.w \times src1.w + src2.w
288 .. opcode:: FRC - Fraction
292 dst.x = src.x - \lfloor src.x\rfloor
294 dst.y = src.y - \lfloor src.y\rfloor
296 dst.z = src.z - \lfloor src.z\rfloor
298 dst.w = src.w - \lfloor src.w\rfloor
301 .. opcode:: FLR - Floor
305 dst.x = \lfloor src.x\rfloor
307 dst.y = \lfloor src.y\rfloor
309 dst.z = \lfloor src.z\rfloor
311 dst.w = \lfloor src.w\rfloor
314 .. opcode:: ROUND - Round
327 .. opcode:: EX2 - Exponential Base 2
329 This instruction replicates its result.
336 .. opcode:: LG2 - Logarithm Base 2
338 This instruction replicates its result.
345 .. opcode:: POW - Power
347 This instruction replicates its result.
351 dst = src0.x^{src1.x}
354 .. opcode:: LDEXP - Multiply Number by Integral Power of 2
360 dst.x = src0.x * 2^{src1.x}
361 dst.y = src0.y * 2^{src1.y}
362 dst.z = src0.z * 2^{src1.z}
363 dst.w = src0.w * 2^{src1.w}
366 .. opcode:: COS - Cosine
368 This instruction replicates its result.
375 .. opcode:: DDX, DDX_FINE - Derivative Relative To X
377 The fine variant is only used when ``PIPE_CAP_TGSI_FS_FINE_DERIVATIVE`` is
378 advertised. When it is, the fine version guarantees one derivative per row
379 while DDX is allowed to be the same for the entire 2x2 quad.
383 dst.x = partialx(src.x)
385 dst.y = partialx(src.y)
387 dst.z = partialx(src.z)
389 dst.w = partialx(src.w)
392 .. opcode:: DDY, DDY_FINE - Derivative Relative To Y
394 The fine variant is only used when ``PIPE_CAP_TGSI_FS_FINE_DERIVATIVE`` is
395 advertised. When it is, the fine version guarantees one derivative per column
396 while DDY is allowed to be the same for the entire 2x2 quad.
400 dst.x = partialy(src.x)
402 dst.y = partialy(src.y)
404 dst.z = partialy(src.z)
406 dst.w = partialy(src.w)
409 .. opcode:: PK2H - Pack Two 16-bit Floats
411 This instruction replicates its result.
415 dst = f32\_to\_f16(src.x) | f32\_to\_f16(src.y) << 16
418 .. opcode:: PK2US - Pack Two Unsigned 16-bit Scalars
420 This instruction replicates its result.
424 dst = f32\_to\_unorm16(src.x) | f32\_to\_unorm16(src.y) << 16
427 .. opcode:: PK4B - Pack Four Signed 8-bit Scalars
429 This instruction replicates its result.
433 dst = f32\_to\_snorm8(src.x) |
434 (f32\_to\_snorm8(src.y) << 8) |
435 (f32\_to\_snorm8(src.z) << 16) |
436 (f32\_to\_snorm8(src.w) << 24)
439 .. opcode:: PK4UB - Pack Four Unsigned 8-bit Scalars
441 This instruction replicates its result.
445 dst = f32\_to\_unorm8(src.x) |
446 (f32\_to\_unorm8(src.y) << 8) |
447 (f32\_to\_unorm8(src.z) << 16) |
448 (f32\_to\_unorm8(src.w) << 24)
451 .. opcode:: SEQ - Set On Equal
455 dst.x = (src0.x == src1.x) ? 1.0F : 0.0F
457 dst.y = (src0.y == src1.y) ? 1.0F : 0.0F
459 dst.z = (src0.z == src1.z) ? 1.0F : 0.0F
461 dst.w = (src0.w == src1.w) ? 1.0F : 0.0F
464 .. opcode:: SGT - Set On Greater Than
468 dst.x = (src0.x > src1.x) ? 1.0F : 0.0F
470 dst.y = (src0.y > src1.y) ? 1.0F : 0.0F
472 dst.z = (src0.z > src1.z) ? 1.0F : 0.0F
474 dst.w = (src0.w > src1.w) ? 1.0F : 0.0F
477 .. opcode:: SIN - Sine
479 This instruction replicates its result.
486 .. opcode:: SLE - Set On Less Equal Than
490 dst.x = (src0.x <= src1.x) ? 1.0F : 0.0F
492 dst.y = (src0.y <= src1.y) ? 1.0F : 0.0F
494 dst.z = (src0.z <= src1.z) ? 1.0F : 0.0F
496 dst.w = (src0.w <= src1.w) ? 1.0F : 0.0F
499 .. opcode:: SNE - Set On Not Equal
503 dst.x = (src0.x != src1.x) ? 1.0F : 0.0F
505 dst.y = (src0.y != src1.y) ? 1.0F : 0.0F
507 dst.z = (src0.z != src1.z) ? 1.0F : 0.0F
509 dst.w = (src0.w != src1.w) ? 1.0F : 0.0F
512 .. opcode:: TEX - Texture Lookup
514 for array textures src0.y contains the slice for 1D,
515 and src0.z contain the slice for 2D.
517 for shadow textures with no arrays (and not cube map),
518 src0.z contains the reference value.
520 for shadow textures with arrays, src0.z contains
521 the reference value for 1D arrays, and src0.w contains
522 the reference value for 2D arrays and cube maps.
524 for cube map array shadow textures, the reference value
525 cannot be passed in src0.w, and TEX2 must be used instead.
531 shadow_ref = src0.z or src0.w (optional)
535 dst = texture\_sample(unit, coord, shadow_ref)
538 .. opcode:: TEX2 - Texture Lookup (for shadow cube map arrays only)
540 this is the same as TEX, but uses another reg to encode the
551 dst = texture\_sample(unit, coord, shadow_ref)
556 .. opcode:: TXD - Texture Lookup with Derivatives
568 dst = texture\_sample\_deriv(unit, coord, ddx, ddy)
571 .. opcode:: TXP - Projective Texture Lookup
575 coord.x = src0.x / src0.w
577 coord.y = src0.y / src0.w
579 coord.z = src0.z / src0.w
585 dst = texture\_sample(unit, coord)
588 .. opcode:: UP2H - Unpack Two 16-Bit Floats
592 dst.x = f16\_to\_f32(src0.x \& 0xffff)
594 dst.y = f16\_to\_f32(src0.x >> 16)
596 dst.z = f16\_to\_f32(src0.x \& 0xffff)
598 dst.w = f16\_to\_f32(src0.x >> 16)
602 Considered for removal.
604 .. opcode:: UP2US - Unpack Two Unsigned 16-Bit Scalars
610 Considered for removal.
612 .. opcode:: UP4B - Unpack Four Signed 8-Bit Values
618 Considered for removal.
620 .. opcode:: UP4UB - Unpack Four Unsigned 8-Bit Scalars
626 Considered for removal.
629 .. opcode:: ARR - Address Register Load With Round
633 dst.x = (int) round(src.x)
635 dst.y = (int) round(src.y)
637 dst.z = (int) round(src.z)
639 dst.w = (int) round(src.w)
642 .. opcode:: SSG - Set Sign
646 dst.x = (src.x > 0) ? 1 : (src.x < 0) ? -1 : 0
648 dst.y = (src.y > 0) ? 1 : (src.y < 0) ? -1 : 0
650 dst.z = (src.z > 0) ? 1 : (src.z < 0) ? -1 : 0
652 dst.w = (src.w > 0) ? 1 : (src.w < 0) ? -1 : 0
655 .. opcode:: CMP - Compare
659 dst.x = (src0.x < 0) ? src1.x : src2.x
661 dst.y = (src0.y < 0) ? src1.y : src2.y
663 dst.z = (src0.z < 0) ? src1.z : src2.z
665 dst.w = (src0.w < 0) ? src1.w : src2.w
668 .. opcode:: KILL_IF - Conditional Discard
670 Conditional discard. Allowed in fragment shaders only.
674 if (src.x < 0 || src.y < 0 || src.z < 0 || src.w < 0)
679 .. opcode:: KILL - Discard
681 Unconditional discard. Allowed in fragment shaders only.
684 .. opcode:: DEMOTE - Demote Invocation to a Helper
686 This demotes the current invocation to a helper, but continues
687 execution (while KILL may or may not terminate the
688 invocation). After this runs, all the usual helper invocation rules
689 apply about discarding buffer and render target writes. This is
690 useful for having accurate derivatives in the other invocations
691 which have not been demoted.
693 Allowed in fragment shaders only.
696 .. opcode:: READ_HELPER - Reads Invocation Helper Status
698 This is identical to ``TGSI_SEMANTIC_HELPER_INVOCATION``, except
699 this will read the current value, which might change as a result of
700 a ``DEMOTE`` instruction.
702 Allowed in fragment shaders only.
705 .. opcode:: TXB - Texture Lookup With Bias
707 for cube map array textures and shadow cube maps, the bias value
708 cannot be passed in src0.w, and TXB2 must be used instead.
710 if the target is a shadow texture, the reference value is always
711 in src.z (this prevents shadow 3d and shadow 2d arrays from
712 using this instruction, but this is not needed).
728 dst = texture\_sample(unit, coord, bias)
731 .. opcode:: TXB2 - Texture Lookup With Bias (some cube maps only)
733 this is the same as TXB, but uses another reg to encode the
734 lod bias value for cube map arrays and shadow cube maps.
735 Presumably shadow 2d arrays and shadow 3d targets could use
736 this encoding too, but this is not legal.
738 shadow cube map arrays are neither possible nor required.
748 dst = texture\_sample(unit, coord, bias)
751 .. opcode:: DIV - Divide
755 dst.x = \frac{src0.x}{src1.x}
757 dst.y = \frac{src0.y}{src1.y}
759 dst.z = \frac{src0.z}{src1.z}
761 dst.w = \frac{src0.w}{src1.w}
764 .. opcode:: DP2 - 2-component Dot Product
766 This instruction replicates its result.
770 dst = src0.x \times src1.x + src0.y \times src1.y
773 .. opcode:: TEX_LZ - Texture Lookup With LOD = 0
775 This is the same as TXL with LOD = 0. Like every texture opcode, it obeys
776 pipe_sampler_view::u.tex.first_level and pipe_sampler_state::min_lod.
777 There is no way to override those two in shaders.
793 dst = texture\_sample(unit, coord, lod)
796 .. opcode:: TXL - Texture Lookup With explicit LOD
798 for cube map array textures, the explicit lod value
799 cannot be passed in src0.w, and TXL2 must be used instead.
801 if the target is a shadow texture, the reference value is always
802 in src.z (this prevents shadow 3d / 2d array / cube targets from
803 using this instruction, but this is not needed).
819 dst = texture\_sample(unit, coord, lod)
822 .. opcode:: TXL2 - Texture Lookup With explicit LOD (for cube map arrays only)
824 this is the same as TXL, but uses another reg to encode the
826 Presumably shadow 3d / 2d array / cube targets could use
827 this encoding too, but this is not legal.
829 shadow cube map arrays are neither possible nor required.
839 dst = texture\_sample(unit, coord, lod)
843 ^^^^^^^^^^^^^^^^^^^^^^^^
845 These opcodes are primarily provided for special-use computational shaders.
846 Support for these opcodes indicated by a special pipe capability bit (TBD).
848 XXX doesn't look like most of the opcodes really belong here.
850 .. opcode:: CEIL - Ceiling
854 dst.x = \lceil src.x\rceil
856 dst.y = \lceil src.y\rceil
858 dst.z = \lceil src.z\rceil
860 dst.w = \lceil src.w\rceil
863 .. opcode:: TRUNC - Truncate
876 .. opcode:: MOD - Modulus
880 dst.x = src0.x \bmod src1.x
882 dst.y = src0.y \bmod src1.y
884 dst.z = src0.z \bmod src1.z
886 dst.w = src0.w \bmod src1.w
889 .. opcode:: UARL - Integer Address Register Load
891 Moves the contents of the source register, assumed to be an integer, into the
892 destination register, which is assumed to be an address (ADDR) register.
895 .. opcode:: TXF - Texel Fetch
897 As per NV_gpu_shader4, extract a single texel from a specified texture
898 image or PIPE_BUFFER resource. The source sampler may not be a CUBE or
900 four-component signed integer vector used to identify the single texel
901 accessed. 3 components + level. If the texture is multisampled, then
902 the fourth component indicates the sample, not the mipmap level.
903 Just like texture instructions, an optional
904 offset vector is provided, which is subject to various driver restrictions
905 (regarding range, source of offsets). This instruction ignores the sampler
908 TXF(uint_vec coord, int_vec offset).
911 .. opcode:: TXQ - Texture Size Query
913 As per NV_gpu_program4, retrieve the dimensions of the texture depending on
914 the target. For 1D (width), 2D/RECT/CUBE (width, height), 3D (width, height,
915 depth), 1D array (width, layers), 2D array (width, height, layers).
916 Also return the number of accessible levels (last_level - first_level + 1)
919 For components which don't return a resource dimension, their value
926 dst.x = texture\_width(unit, lod)
928 dst.y = texture\_height(unit, lod)
930 dst.z = texture\_depth(unit, lod)
932 dst.w = texture\_levels(unit)
935 .. opcode:: TXQS - Texture Samples Query
937 This retrieves the number of samples in the texture, and stores it
938 into the x component as an unsigned integer. The other components are
939 undefined. If the texture is not multisampled, this function returns
940 (1, undef, undef, undef).
944 dst.x = texture\_samples(unit)
947 .. opcode:: TG4 - Texture Gather
949 As per ARB_texture_gather, gathers the four texels to be used in a bi-linear
950 filtering operation and packs them into a single register. Only works with
951 2D, 2D array, cubemaps, and cubemaps arrays. For 2D textures, only the
952 addressing modes of the sampler and the top level of any mip pyramid are
953 used. Set W to zero. It behaves like the TEX instruction, but a filtered
954 sample is not generated. The four samples that contribute to filtering are
955 placed into xyzw in clockwise order, starting with the (u,v) texture
956 coordinate delta at the following locations (-, +), (+, +), (+, -), (-, -),
957 where the magnitude of the deltas are half a texel.
959 PIPE_CAP_TEXTURE_SM5 enhances this instruction to support shadow per-sample
960 depth compares, single component selection, and a non-constant offset. It
961 doesn't allow support for the GL independent offset to get i0,j0. This would
962 require another CAP is hw can do it natively. For now we lower that before
971 dst = texture\_gather4 (unit, coord, component)
973 (with SM5 - cube array shadow)
981 dst = texture\_gather (uint, coord, compare)
983 .. opcode:: LODQ - level of detail query
985 Compute the LOD information that the texture pipe would use to access the
986 texture. The Y component contains the computed LOD lambda_prime. The X
987 component contains the LOD that will be accessed, based on min/max lod's
994 dst.xy = lodq(uint, coord);
996 .. opcode:: CLOCK - retrieve the current shader time
998 Invoking this instruction multiple times in the same shader should
999 cause monotonically increasing values to be returned. The values
1000 are implicitly 64-bit, so if fewer than 64 bits of precision are
1001 available, to provide expected wraparound semantics, the value
1002 should be shifted up so that the most significant bit of the time
1003 is the most significant bit of the 64-bit value.
1011 ^^^^^^^^^^^^^^^^^^^^^^^^
1012 These opcodes are used for integer operations.
1013 Support for these opcodes indicated by PIPE_SHADER_CAP_INTEGERS (all of them?)
1016 .. opcode:: I2F - Signed Integer To Float
1018 Rounding is unspecified (round to nearest even suggested).
1022 dst.x = (float) src.x
1024 dst.y = (float) src.y
1026 dst.z = (float) src.z
1028 dst.w = (float) src.w
1031 .. opcode:: U2F - Unsigned Integer To Float
1033 Rounding is unspecified (round to nearest even suggested).
1037 dst.x = (float) src.x
1039 dst.y = (float) src.y
1041 dst.z = (float) src.z
1043 dst.w = (float) src.w
1046 .. opcode:: F2I - Float to Signed Integer
1048 Rounding is towards zero (truncate).
1049 Values outside signed range (including NaNs) produce undefined results.
1062 .. opcode:: F2U - Float to Unsigned Integer
1064 Rounding is towards zero (truncate).
1065 Values outside unsigned range (including NaNs) produce undefined results.
1069 dst.x = (unsigned) src.x
1071 dst.y = (unsigned) src.y
1073 dst.z = (unsigned) src.z
1075 dst.w = (unsigned) src.w
1078 .. opcode:: UADD - Integer Add
1080 This instruction works the same for signed and unsigned integers.
1081 The low 32bit of the result is returned.
1085 dst.x = src0.x + src1.x
1087 dst.y = src0.y + src1.y
1089 dst.z = src0.z + src1.z
1091 dst.w = src0.w + src1.w
1094 .. opcode:: UMAD - Integer Multiply And Add
1096 This instruction works the same for signed and unsigned integers.
1097 The multiplication returns the low 32bit (as does the result itself).
1101 dst.x = src0.x \times src1.x + src2.x
1103 dst.y = src0.y \times src1.y + src2.y
1105 dst.z = src0.z \times src1.z + src2.z
1107 dst.w = src0.w \times src1.w + src2.w
1110 .. opcode:: UMUL - Integer Multiply
1112 This instruction works the same for signed and unsigned integers.
1113 The low 32bit of the result is returned.
1117 dst.x = src0.x \times src1.x
1119 dst.y = src0.y \times src1.y
1121 dst.z = src0.z \times src1.z
1123 dst.w = src0.w \times src1.w
1126 .. opcode:: IMUL_HI - Signed Integer Multiply High Bits
1128 The high 32bits of the multiplication of 2 signed integers are returned.
1132 dst.x = (src0.x \times src1.x) >> 32
1134 dst.y = (src0.y \times src1.y) >> 32
1136 dst.z = (src0.z \times src1.z) >> 32
1138 dst.w = (src0.w \times src1.w) >> 32
1141 .. opcode:: UMUL_HI - Unsigned Integer Multiply High Bits
1143 The high 32bits of the multiplication of 2 unsigned integers are returned.
1147 dst.x = (src0.x \times src1.x) >> 32
1149 dst.y = (src0.y \times src1.y) >> 32
1151 dst.z = (src0.z \times src1.z) >> 32
1153 dst.w = (src0.w \times src1.w) >> 32
1156 .. opcode:: IDIV - Signed Integer Division
1158 TBD: behavior for division by zero.
1162 dst.x = \frac{src0.x}{src1.x}
1164 dst.y = \frac{src0.y}{src1.y}
1166 dst.z = \frac{src0.z}{src1.z}
1168 dst.w = \frac{src0.w}{src1.w}
1171 .. opcode:: UDIV - Unsigned Integer Division
1173 For division by zero, 0xffffffff is returned.
1177 dst.x = \frac{src0.x}{src1.x}
1179 dst.y = \frac{src0.y}{src1.y}
1181 dst.z = \frac{src0.z}{src1.z}
1183 dst.w = \frac{src0.w}{src1.w}
1186 .. opcode:: UMOD - Unsigned Integer Remainder
1188 If second arg is zero, 0xffffffff is returned.
1192 dst.x = src0.x \bmod src1.x
1194 dst.y = src0.y \bmod src1.y
1196 dst.z = src0.z \bmod src1.z
1198 dst.w = src0.w \bmod src1.w
1201 .. opcode:: NOT - Bitwise Not
1214 .. opcode:: AND - Bitwise And
1218 dst.x = src0.x \& src1.x
1220 dst.y = src0.y \& src1.y
1222 dst.z = src0.z \& src1.z
1224 dst.w = src0.w \& src1.w
1227 .. opcode:: OR - Bitwise Or
1231 dst.x = src0.x | src1.x
1233 dst.y = src0.y | src1.y
1235 dst.z = src0.z | src1.z
1237 dst.w = src0.w | src1.w
1240 .. opcode:: XOR - Bitwise Xor
1244 dst.x = src0.x \oplus src1.x
1246 dst.y = src0.y \oplus src1.y
1248 dst.z = src0.z \oplus src1.z
1250 dst.w = src0.w \oplus src1.w
1253 .. opcode:: IMAX - Maximum of Signed Integers
1257 dst.x = max(src0.x, src1.x)
1259 dst.y = max(src0.y, src1.y)
1261 dst.z = max(src0.z, src1.z)
1263 dst.w = max(src0.w, src1.w)
1266 .. opcode:: UMAX - Maximum of Unsigned Integers
1270 dst.x = max(src0.x, src1.x)
1272 dst.y = max(src0.y, src1.y)
1274 dst.z = max(src0.z, src1.z)
1276 dst.w = max(src0.w, src1.w)
1279 .. opcode:: IMIN - Minimum of Signed Integers
1283 dst.x = min(src0.x, src1.x)
1285 dst.y = min(src0.y, src1.y)
1287 dst.z = min(src0.z, src1.z)
1289 dst.w = min(src0.w, src1.w)
1292 .. opcode:: UMIN - Minimum of Unsigned Integers
1296 dst.x = min(src0.x, src1.x)
1298 dst.y = min(src0.y, src1.y)
1300 dst.z = min(src0.z, src1.z)
1302 dst.w = min(src0.w, src1.w)
1305 .. opcode:: SHL - Shift Left
1307 The shift count is masked with 0x1f before the shift is applied.
1311 dst.x = src0.x << (0x1f \& src1.x)
1313 dst.y = src0.y << (0x1f \& src1.y)
1315 dst.z = src0.z << (0x1f \& src1.z)
1317 dst.w = src0.w << (0x1f \& src1.w)
1320 .. opcode:: ISHR - Arithmetic Shift Right (of Signed Integer)
1322 The shift count is masked with 0x1f before the shift is applied.
1326 dst.x = src0.x >> (0x1f \& src1.x)
1328 dst.y = src0.y >> (0x1f \& src1.y)
1330 dst.z = src0.z >> (0x1f \& src1.z)
1332 dst.w = src0.w >> (0x1f \& src1.w)
1335 .. opcode:: USHR - Logical Shift Right
1337 The shift count is masked with 0x1f before the shift is applied.
1341 dst.x = src0.x >> (unsigned) (0x1f \& src1.x)
1343 dst.y = src0.y >> (unsigned) (0x1f \& src1.y)
1345 dst.z = src0.z >> (unsigned) (0x1f \& src1.z)
1347 dst.w = src0.w >> (unsigned) (0x1f \& src1.w)
1350 .. opcode:: UCMP - Integer Conditional Move
1354 dst.x = src0.x ? src1.x : src2.x
1356 dst.y = src0.y ? src1.y : src2.y
1358 dst.z = src0.z ? src1.z : src2.z
1360 dst.w = src0.w ? src1.w : src2.w
1364 .. opcode:: ISSG - Integer Set Sign
1368 dst.x = (src0.x < 0) ? -1 : (src0.x > 0) ? 1 : 0
1370 dst.y = (src0.y < 0) ? -1 : (src0.y > 0) ? 1 : 0
1372 dst.z = (src0.z < 0) ? -1 : (src0.z > 0) ? 1 : 0
1374 dst.w = (src0.w < 0) ? -1 : (src0.w > 0) ? 1 : 0
1378 .. opcode:: FSLT - Float Set On Less Than (ordered)
1380 Same comparison as SLT but returns integer instead of 1.0/0.0 float
1384 dst.x = (src0.x < src1.x) ? \sim 0 : 0
1386 dst.y = (src0.y < src1.y) ? \sim 0 : 0
1388 dst.z = (src0.z < src1.z) ? \sim 0 : 0
1390 dst.w = (src0.w < src1.w) ? \sim 0 : 0
1393 .. opcode:: ISLT - Signed Integer Set On Less Than
1397 dst.x = (src0.x < src1.x) ? \sim 0 : 0
1399 dst.y = (src0.y < src1.y) ? \sim 0 : 0
1401 dst.z = (src0.z < src1.z) ? \sim 0 : 0
1403 dst.w = (src0.w < src1.w) ? \sim 0 : 0
1406 .. opcode:: USLT - Unsigned Integer Set On Less Than
1410 dst.x = (src0.x < src1.x) ? \sim 0 : 0
1412 dst.y = (src0.y < src1.y) ? \sim 0 : 0
1414 dst.z = (src0.z < src1.z) ? \sim 0 : 0
1416 dst.w = (src0.w < src1.w) ? \sim 0 : 0
1419 .. opcode:: FSGE - Float Set On Greater Equal Than (ordered)
1421 Same comparison as SGE but returns integer instead of 1.0/0.0 float
1425 dst.x = (src0.x >= src1.x) ? \sim 0 : 0
1427 dst.y = (src0.y >= src1.y) ? \sim 0 : 0
1429 dst.z = (src0.z >= src1.z) ? \sim 0 : 0
1431 dst.w = (src0.w >= src1.w) ? \sim 0 : 0
1434 .. opcode:: ISGE - Signed Integer Set On Greater Equal Than
1438 dst.x = (src0.x >= src1.x) ? \sim 0 : 0
1440 dst.y = (src0.y >= src1.y) ? \sim 0 : 0
1442 dst.z = (src0.z >= src1.z) ? \sim 0 : 0
1444 dst.w = (src0.w >= src1.w) ? \sim 0 : 0
1447 .. opcode:: USGE - Unsigned Integer Set On Greater Equal Than
1451 dst.x = (src0.x >= src1.x) ? \sim 0 : 0
1453 dst.y = (src0.y >= src1.y) ? \sim 0 : 0
1455 dst.z = (src0.z >= src1.z) ? \sim 0 : 0
1457 dst.w = (src0.w >= src1.w) ? \sim 0 : 0
1460 .. opcode:: FSEQ - Float Set On Equal (ordered)
1462 Same comparison as SEQ but returns integer instead of 1.0/0.0 float
1466 dst.x = (src0.x == src1.x) ? \sim 0 : 0
1468 dst.y = (src0.y == src1.y) ? \sim 0 : 0
1470 dst.z = (src0.z == src1.z) ? \sim 0 : 0
1472 dst.w = (src0.w == src1.w) ? \sim 0 : 0
1475 .. opcode:: USEQ - Integer Set On Equal
1479 dst.x = (src0.x == src1.x) ? \sim 0 : 0
1481 dst.y = (src0.y == src1.y) ? \sim 0 : 0
1483 dst.z = (src0.z == src1.z) ? \sim 0 : 0
1485 dst.w = (src0.w == src1.w) ? \sim 0 : 0
1488 .. opcode:: FSNE - Float Set On Not Equal (unordered)
1490 Same comparison as SNE but returns integer instead of 1.0/0.0 float
1494 dst.x = (src0.x != src1.x) ? \sim 0 : 0
1496 dst.y = (src0.y != src1.y) ? \sim 0 : 0
1498 dst.z = (src0.z != src1.z) ? \sim 0 : 0
1500 dst.w = (src0.w != src1.w) ? \sim 0 : 0
1503 .. opcode:: USNE - Integer Set On Not Equal
1507 dst.x = (src0.x != src1.x) ? \sim 0 : 0
1509 dst.y = (src0.y != src1.y) ? \sim 0 : 0
1511 dst.z = (src0.z != src1.z) ? \sim 0 : 0
1513 dst.w = (src0.w != src1.w) ? \sim 0 : 0
1516 .. opcode:: INEG - Integer Negate
1531 .. opcode:: IABS - Integer Absolute Value
1545 These opcodes are used for bit-level manipulation of integers.
1547 .. opcode:: IBFE - Signed Bitfield Extract
1549 Like GLSL bitfieldExtract. Extracts a set of bits from the input, and
1550 sign-extends them if the high bit of the extracted window is set.
1554 def ibfe(value, offset, bits):
1555 if offset < 0 or bits < 0 or offset + bits > 32:
1557 if bits == 0: return 0
1558 # Note: >> sign-extends
1559 return (value << (32 - offset - bits)) >> (32 - bits)
1561 .. opcode:: UBFE - Unsigned Bitfield Extract
1563 Like GLSL bitfieldExtract. Extracts a set of bits from the input, without
1568 def ubfe(value, offset, bits):
1569 if offset < 0 or bits < 0 or offset + bits > 32:
1571 if bits == 0: return 0
1572 # Note: >> does not sign-extend
1573 return (value << (32 - offset - bits)) >> (32 - bits)
1575 .. opcode:: BFI - Bitfield Insert
1577 Like GLSL bitfieldInsert. Replaces a bit region of 'base' with the low bits
1582 def bfi(base, insert, offset, bits):
1583 if offset < 0 or bits < 0 or offset + bits > 32:
1585 # << defined such that mask == ~0 when bits == 32, offset == 0
1586 mask = ((1 << bits) - 1) << offset
1587 return ((insert << offset) & mask) | (base & ~mask)
1589 .. opcode:: BREV - Bitfield Reverse
1591 See SM5 instruction BFREV. Reverses the bits of the argument.
1593 .. opcode:: POPC - Population Count
1595 See SM5 instruction COUNTBITS. Counts the number of set bits in the argument.
1597 .. opcode:: LSB - Index of lowest set bit
1599 See SM5 instruction FIRSTBIT_LO. Computes the 0-based index of the first set
1600 bit of the argument. Returns -1 if none are set.
1602 .. opcode:: IMSB - Index of highest non-sign bit
1604 See SM5 instruction FIRSTBIT_SHI. Computes the 0-based index of the highest
1605 non-sign bit of the argument (i.e. highest 0 bit for negative numbers,
1606 highest 1 bit for positive numbers). Returns -1 if all bits are the same
1607 (i.e. for inputs 0 and -1).
1609 .. opcode:: UMSB - Index of highest set bit
1611 See SM5 instruction FIRSTBIT_HI. Computes the 0-based index of the highest
1612 set bit of the argument. Returns -1 if none are set.
1615 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1617 These opcodes are only supported in geometry shaders; they have no meaning
1618 in any other type of shader.
1620 .. opcode:: EMIT - Emit
1622 Generate a new vertex for the current primitive into the specified vertex
1623 stream using the values in the output registers.
1626 .. opcode:: ENDPRIM - End Primitive
1628 Complete the current primitive in the specified vertex stream (consisting of
1629 the emitted vertices), and start a new one.
1635 These opcodes are part of :term:`GLSL`'s opcode set. Support for these
1636 opcodes is determined by a special capability bit, ``GLSL``.
1637 Some require glsl version 1.30 (UIF/SWITCH/CASE/DEFAULT/ENDSWITCH).
1639 .. opcode:: CAL - Subroutine Call
1645 .. opcode:: RET - Subroutine Call Return
1650 .. opcode:: CONT - Continue
1652 Unconditionally moves the point of execution to the instruction after the
1653 last bgnloop. The instruction must appear within a bgnloop/endloop.
1657 Support for CONT is determined by a special capability bit,
1658 ``TGSI_CONT_SUPPORTED``. See :ref:`Screen` for more information.
1661 .. opcode:: BGNLOOP - Begin a Loop
1663 Start a loop. Must have a matching endloop.
1666 .. opcode:: BGNSUB - Begin Subroutine
1668 Starts definition of a subroutine. Must have a matching endsub.
1671 .. opcode:: ENDLOOP - End a Loop
1673 End a loop started with bgnloop.
1676 .. opcode:: ENDSUB - End Subroutine
1678 Ends definition of a subroutine.
1681 .. opcode:: NOP - No Operation
1686 .. opcode:: BRK - Break
1688 Unconditionally moves the point of execution to the instruction after the
1689 next endloop or endswitch. The instruction must appear within a loop/endloop
1690 or switch/endswitch.
1693 .. opcode:: IF - Float If
1695 Start an IF ... ELSE .. ENDIF block. Condition evaluates to true if
1699 where src0.x is interpreted as a floating point register.
1702 .. opcode:: UIF - Bitwise If
1704 Start an UIF ... ELSE .. ENDIF block. Condition evaluates to true if
1708 where src0.x is interpreted as an integer register.
1711 .. opcode:: ELSE - Else
1713 Starts an else block, after an IF or UIF statement.
1716 .. opcode:: ENDIF - End If
1718 Ends an IF or UIF block.
1721 .. opcode:: SWITCH - Switch
1723 Starts a C-style switch expression. The switch consists of one or multiple
1724 CASE statements, and at most one DEFAULT statement. Execution of a statement
1725 ends when a BRK is hit, but just like in C falling through to other cases
1726 without a break is allowed. Similarly, DEFAULT label is allowed anywhere not
1727 just as last statement, and fallthrough is allowed into/from it.
1728 CASE src arguments are evaluated at bit level against the SWITCH src argument.
1734 (some instructions here)
1737 (some instructions here)
1740 (some instructions here)
1745 .. opcode:: CASE - Switch case
1747 This represents a switch case label. The src arg must be an integer immediate.
1750 .. opcode:: DEFAULT - Switch default
1752 This represents the default case in the switch, which is taken if no other
1756 .. opcode:: ENDSWITCH - End of switch
1758 Ends a switch expression.
1764 The interpolation instructions allow an input to be interpolated in a
1765 different way than its declaration. This corresponds to the GLSL 4.00
1766 interpolateAt* functions. The first argument of each of these must come from
1767 ``TGSI_FILE_INPUT``.
1769 .. opcode:: INTERP_CENTROID - Interpolate at the centroid
1771 Interpolates the varying specified by src0 at the centroid
1773 .. opcode:: INTERP_SAMPLE - Interpolate at the specified sample
1775 Interpolates the varying specified by src0 at the sample id specified by
1776 src1.x (interpreted as an integer)
1778 .. opcode:: INTERP_OFFSET - Interpolate at the specified offset
1780 Interpolates the varying specified by src0 at the offset src1.xy from the
1781 pixel center (interpreted as floats)
1789 The double-precision opcodes reinterpret four-component vectors into
1790 two-component vectors with doubled precision in each component.
1792 .. opcode:: DABS - Absolute
1800 .. opcode:: DADD - Add
1804 dst.xy = src0.xy + src1.xy
1806 dst.zw = src0.zw + src1.zw
1808 .. opcode:: DSEQ - Set on Equal
1812 dst.x = src0.xy == src1.xy ? \sim 0 : 0
1814 dst.z = src0.zw == src1.zw ? \sim 0 : 0
1816 .. opcode:: DSNE - Set on Not Equal
1820 dst.x = src0.xy != src1.xy ? \sim 0 : 0
1822 dst.z = src0.zw != src1.zw ? \sim 0 : 0
1824 .. opcode:: DSLT - Set on Less than
1828 dst.x = src0.xy < src1.xy ? \sim 0 : 0
1830 dst.z = src0.zw < src1.zw ? \sim 0 : 0
1832 .. opcode:: DSGE - Set on Greater equal
1836 dst.x = src0.xy >= src1.xy ? \sim 0 : 0
1838 dst.z = src0.zw >= src1.zw ? \sim 0 : 0
1840 .. opcode:: DFRAC - Fraction
1844 dst.xy = src.xy - \lfloor src.xy\rfloor
1846 dst.zw = src.zw - \lfloor src.zw\rfloor
1848 .. opcode:: DTRUNC - Truncate
1852 dst.xy = trunc(src.xy)
1854 dst.zw = trunc(src.zw)
1856 .. opcode:: DCEIL - Ceiling
1860 dst.xy = \lceil src.xy\rceil
1862 dst.zw = \lceil src.zw\rceil
1864 .. opcode:: DFLR - Floor
1868 dst.xy = \lfloor src.xy\rfloor
1870 dst.zw = \lfloor src.zw\rfloor
1872 .. opcode:: DROUND - Fraction
1876 dst.xy = round(src.xy)
1878 dst.zw = round(src.zw)
1880 .. opcode:: DSSG - Set Sign
1884 dst.xy = (src.xy > 0) ? 1.0 : (src.xy < 0) ? -1.0 : 0.0
1886 dst.zw = (src.zw > 0) ? 1.0 : (src.zw < 0) ? -1.0 : 0.0
1888 .. opcode:: DFRACEXP - Convert Number to Fractional and Integral Components
1890 Like the ``frexp()`` routine in many math libraries, this opcode stores the
1891 exponent of its source to ``dst0``, and the significand to ``dst1``, such that
1892 :math:`dst1 \times 2^{dst0} = src` . The results are replicated across
1897 dst0.xy = dst.zw = frac(src.xy)
1902 .. opcode:: DLDEXP - Multiply Number by Integral Power of 2
1904 This opcode is the inverse of :opcode:`DFRACEXP`. The second
1905 source is an integer.
1909 dst.xy = src0.xy \times 2^{src1.x}
1911 dst.zw = src0.zw \times 2^{src1.z}
1913 .. opcode:: DMIN - Minimum
1917 dst.xy = min(src0.xy, src1.xy)
1919 dst.zw = min(src0.zw, src1.zw)
1921 .. opcode:: DMAX - Maximum
1925 dst.xy = max(src0.xy, src1.xy)
1927 dst.zw = max(src0.zw, src1.zw)
1929 .. opcode:: DMUL - Multiply
1933 dst.xy = src0.xy \times src1.xy
1935 dst.zw = src0.zw \times src1.zw
1938 .. opcode:: DMAD - Multiply And Add
1942 dst.xy = src0.xy \times src1.xy + src2.xy
1944 dst.zw = src0.zw \times src1.zw + src2.zw
1947 .. opcode:: DFMA - Fused Multiply-Add
1949 Perform a * b + c with no intermediate rounding step.
1953 dst.xy = src0.xy \times src1.xy + src2.xy
1955 dst.zw = src0.zw \times src1.zw + src2.zw
1958 .. opcode:: DDIV - Divide
1962 dst.xy = \frac{src0.xy}{src1.xy}
1964 dst.zw = \frac{src0.zw}{src1.zw}
1967 .. opcode:: DRCP - Reciprocal
1971 dst.xy = \frac{1}{src.xy}
1973 dst.zw = \frac{1}{src.zw}
1975 .. opcode:: DSQRT - Square Root
1979 dst.xy = \sqrt{src.xy}
1981 dst.zw = \sqrt{src.zw}
1983 .. opcode:: DRSQ - Reciprocal Square Root
1987 dst.xy = \frac{1}{\sqrt{src.xy}}
1989 dst.zw = \frac{1}{\sqrt{src.zw}}
1991 .. opcode:: F2D - Float to Double
1995 dst.xy = double(src0.x)
1997 dst.zw = double(src0.y)
1999 .. opcode:: D2F - Double to Float
2003 dst.x = float(src0.xy)
2005 dst.y = float(src0.zw)
2007 .. opcode:: I2D - Int to Double
2011 dst.xy = double(src0.x)
2013 dst.zw = double(src0.y)
2015 .. opcode:: D2I - Double to Int
2019 dst.x = int(src0.xy)
2021 dst.y = int(src0.zw)
2023 .. opcode:: U2D - Unsigned Int to Double
2027 dst.xy = double(src0.x)
2029 dst.zw = double(src0.y)
2031 .. opcode:: D2U - Double to Unsigned Int
2035 dst.x = unsigned(src0.xy)
2037 dst.y = unsigned(src0.zw)
2042 The 64-bit integer opcodes reinterpret four-component vectors into
2043 two-component vectors with 64-bits in each component.
2045 .. opcode:: I64ABS - 64-bit Integer Absolute Value
2053 .. opcode:: I64NEG - 64-bit Integer Negate
2063 .. opcode:: I64SSG - 64-bit Integer Set Sign
2067 dst.xy = (src0.xy < 0) ? -1 : (src0.xy > 0) ? 1 : 0
2069 dst.zw = (src0.zw < 0) ? -1 : (src0.zw > 0) ? 1 : 0
2071 .. opcode:: U64ADD - 64-bit Integer Add
2075 dst.xy = src0.xy + src1.xy
2077 dst.zw = src0.zw + src1.zw
2079 .. opcode:: U64MUL - 64-bit Integer Multiply
2083 dst.xy = src0.xy * src1.xy
2085 dst.zw = src0.zw * src1.zw
2087 .. opcode:: U64SEQ - 64-bit Integer Set on Equal
2091 dst.x = src0.xy == src1.xy ? \sim 0 : 0
2093 dst.z = src0.zw == src1.zw ? \sim 0 : 0
2095 .. opcode:: U64SNE - 64-bit Integer Set on Not Equal
2099 dst.x = src0.xy != src1.xy ? \sim 0 : 0
2101 dst.z = src0.zw != src1.zw ? \sim 0 : 0
2103 .. opcode:: U64SLT - 64-bit Unsigned Integer Set on Less Than
2107 dst.x = src0.xy < src1.xy ? \sim 0 : 0
2109 dst.z = src0.zw < src1.zw ? \sim 0 : 0
2111 .. opcode:: U64SGE - 64-bit Unsigned Integer Set on Greater Equal
2115 dst.x = src0.xy >= src1.xy ? \sim 0 : 0
2117 dst.z = src0.zw >= src1.zw ? \sim 0 : 0
2119 .. opcode:: I64SLT - 64-bit Signed Integer Set on Less Than
2123 dst.x = src0.xy < src1.xy ? \sim 0 : 0
2125 dst.z = src0.zw < src1.zw ? \sim 0 : 0
2127 .. opcode:: I64SGE - 64-bit Signed Integer Set on Greater Equal
2131 dst.x = src0.xy >= src1.xy ? \sim 0 : 0
2133 dst.z = src0.zw >= src1.zw ? \sim 0 : 0
2135 .. opcode:: I64MIN - Minimum of 64-bit Signed Integers
2139 dst.xy = min(src0.xy, src1.xy)
2141 dst.zw = min(src0.zw, src1.zw)
2143 .. opcode:: U64MIN - Minimum of 64-bit Unsigned Integers
2147 dst.xy = min(src0.xy, src1.xy)
2149 dst.zw = min(src0.zw, src1.zw)
2151 .. opcode:: I64MAX - Maximum of 64-bit Signed Integers
2155 dst.xy = max(src0.xy, src1.xy)
2157 dst.zw = max(src0.zw, src1.zw)
2159 .. opcode:: U64MAX - Maximum of 64-bit Unsigned Integers
2163 dst.xy = max(src0.xy, src1.xy)
2165 dst.zw = max(src0.zw, src1.zw)
2167 .. opcode:: U64SHL - Shift Left 64-bit Unsigned Integer
2169 The shift count is masked with 0x3f before the shift is applied.
2173 dst.xy = src0.xy << (0x3f \& src1.x)
2175 dst.zw = src0.zw << (0x3f \& src1.y)
2177 .. opcode:: I64SHR - Arithmetic Shift Right (of 64-bit Signed Integer)
2179 The shift count is masked with 0x3f before the shift is applied.
2183 dst.xy = src0.xy >> (0x3f \& src1.x)
2185 dst.zw = src0.zw >> (0x3f \& src1.y)
2187 .. opcode:: U64SHR - Logical Shift Right (of 64-bit Unsigned Integer)
2189 The shift count is masked with 0x3f before the shift is applied.
2193 dst.xy = src0.xy >> (unsigned) (0x3f \& src1.x)
2195 dst.zw = src0.zw >> (unsigned) (0x3f \& src1.y)
2197 .. opcode:: I64DIV - 64-bit Signed Integer Division
2201 dst.xy = \frac{src0.xy}{src1.xy}
2203 dst.zw = \frac{src0.zw}{src1.zw}
2205 .. opcode:: U64DIV - 64-bit Unsigned Integer Division
2209 dst.xy = \frac{src0.xy}{src1.xy}
2211 dst.zw = \frac{src0.zw}{src1.zw}
2213 .. opcode:: U64MOD - 64-bit Unsigned Integer Remainder
2217 dst.xy = src0.xy \bmod src1.xy
2219 dst.zw = src0.zw \bmod src1.zw
2221 .. opcode:: I64MOD - 64-bit Signed Integer Remainder
2225 dst.xy = src0.xy \bmod src1.xy
2227 dst.zw = src0.zw \bmod src1.zw
2229 .. opcode:: F2U64 - Float to 64-bit Unsigned Int
2233 dst.xy = (uint64_t) src0.x
2235 dst.zw = (uint64_t) src0.y
2237 .. opcode:: F2I64 - Float to 64-bit Int
2241 dst.xy = (int64_t) src0.x
2243 dst.zw = (int64_t) src0.y
2245 .. opcode:: U2I64 - Unsigned Integer to 64-bit Integer
2247 This is a zero extension.
2251 dst.xy = (int64_t) src0.x
2253 dst.zw = (int64_t) src0.y
2255 .. opcode:: I2I64 - Signed Integer to 64-bit Integer
2257 This is a sign extension.
2261 dst.xy = (int64_t) src0.x
2263 dst.zw = (int64_t) src0.y
2265 .. opcode:: D2U64 - Double to 64-bit Unsigned Int
2269 dst.xy = (uint64_t) src0.xy
2271 dst.zw = (uint64_t) src0.zw
2273 .. opcode:: D2I64 - Double to 64-bit Int
2277 dst.xy = (int64_t) src0.xy
2279 dst.zw = (int64_t) src0.zw
2281 .. opcode:: U642F - 64-bit unsigned integer to float
2285 dst.x = (float) src0.xy
2287 dst.y = (float) src0.zw
2289 .. opcode:: I642F - 64-bit Int to Float
2293 dst.x = (float) src0.xy
2295 dst.y = (float) src0.zw
2297 .. opcode:: U642D - 64-bit unsigned integer to double
2301 dst.xy = (double) src0.xy
2303 dst.zw = (double) src0.zw
2305 .. opcode:: I642D - 64-bit Int to double
2309 dst.xy = (double) src0.xy
2311 dst.zw = (double) src0.zw
2313 .. _samplingopcodes:
2315 Resource Sampling Opcodes
2316 ^^^^^^^^^^^^^^^^^^^^^^^^^
2318 Those opcodes follow very closely semantics of the respective Direct3D
2319 instructions. If in doubt double check Direct3D documentation.
2320 Note that the swizzle on SVIEW (src1) determines texel swizzling
2325 Using provided address, sample data from the specified texture using the
2326 filtering mode identified by the given sampler. The source data may come from
2327 any resource type other than buffers.
2329 Syntax: ``SAMPLE dst, address, sampler_view, sampler``
2331 Example: ``SAMPLE TEMP[0], TEMP[1], SVIEW[0], SAMP[0]``
2333 .. opcode:: SAMPLE_I
2335 Simplified alternative to the SAMPLE instruction. Using the provided
2336 integer address, SAMPLE_I fetches data from the specified sampler view
2337 without any filtering. The source data may come from any resource type
2340 Syntax: ``SAMPLE_I dst, address, sampler_view``
2342 Example: ``SAMPLE_I TEMP[0], TEMP[1], SVIEW[0]``
2344 The 'address' is specified as unsigned integers. If the 'address' is out of
2345 range [0...(# texels - 1)] the result of the fetch is always 0 in all
2346 components. As such the instruction doesn't honor address wrap modes, in
2347 cases where that behavior is desirable 'SAMPLE' instruction should be used.
2348 address.w always provides an unsigned integer mipmap level. If the value is
2349 out of the range then the instruction always returns 0 in all components.
2350 address.yz are ignored for buffers and 1d textures. address.z is ignored
2351 for 1d texture arrays and 2d textures.
2353 For 1D texture arrays address.y provides the array index (also as unsigned
2354 integer). If the value is out of the range of available array indices
2355 [0... (array size - 1)] then the opcode always returns 0 in all components.
2356 For 2D texture arrays address.z provides the array index, otherwise it
2357 exhibits the same behavior as in the case for 1D texture arrays. The exact
2358 semantics of the source address are presented in the table below:
2360 +---------------------------+----+-----+-----+---------+
2361 | resource type | X | Y | Z | W |
2362 +===========================+====+=====+=====+=========+
2363 | ``PIPE_BUFFER`` | x | | | ignored |
2364 +---------------------------+----+-----+-----+---------+
2365 | ``PIPE_TEXTURE_1D`` | x | | | mpl |
2366 +---------------------------+----+-----+-----+---------+
2367 | ``PIPE_TEXTURE_2D`` | x | y | | mpl |
2368 +---------------------------+----+-----+-----+---------+
2369 | ``PIPE_TEXTURE_3D`` | x | y | z | mpl |
2370 +---------------------------+----+-----+-----+---------+
2371 | ``PIPE_TEXTURE_RECT`` | x | y | | mpl |
2372 +---------------------------+----+-----+-----+---------+
2373 | ``PIPE_TEXTURE_CUBE`` | not allowed as source |
2374 +---------------------------+----+-----+-----+---------+
2375 | ``PIPE_TEXTURE_1D_ARRAY`` | x | idx | | mpl |
2376 +---------------------------+----+-----+-----+---------+
2377 | ``PIPE_TEXTURE_2D_ARRAY`` | x | y | idx | mpl |
2378 +---------------------------+----+-----+-----+---------+
2380 Where 'mpl' is a mipmap level and 'idx' is the array index.
2382 .. opcode:: SAMPLE_I_MS
2384 Just like SAMPLE_I but allows fetch data from multi-sampled surfaces.
2386 Syntax: ``SAMPLE_I_MS dst, address, sampler_view, sample``
2388 .. opcode:: SAMPLE_B
2390 Just like the SAMPLE instruction with the exception that an additional bias
2391 is applied to the level of detail computed as part of the instruction
2394 Syntax: ``SAMPLE_B dst, address, sampler_view, sampler, lod_bias``
2396 Example: ``SAMPLE_B TEMP[0], TEMP[1], SVIEW[0], SAMP[0], TEMP[2].x``
2398 .. opcode:: SAMPLE_C
2400 Similar to the SAMPLE instruction but it performs a comparison filter. The
2401 operands to SAMPLE_C are identical to SAMPLE, except that there is an
2402 additional float32 operand, reference value, which must be a register with
2403 single-component, or a scalar literal. SAMPLE_C makes the hardware use the
2404 current samplers compare_func (in pipe_sampler_state) to compare reference
2405 value against the red component value for the surce resource at each texel
2406 that the currently configured texture filter covers based on the provided
2409 Syntax: ``SAMPLE_C dst, address, sampler_view.r, sampler, ref_value``
2411 Example: ``SAMPLE_C TEMP[0], TEMP[1], SVIEW[0].r, SAMP[0], TEMP[2].x``
2413 .. opcode:: SAMPLE_C_LZ
2415 Same as SAMPLE_C, but LOD is 0 and derivatives are ignored. The LZ stands
2418 Syntax: ``SAMPLE_C_LZ dst, address, sampler_view.r, sampler, ref_value``
2420 Example: ``SAMPLE_C_LZ TEMP[0], TEMP[1], SVIEW[0].r, SAMP[0], TEMP[2].x``
2423 .. opcode:: SAMPLE_D
2425 SAMPLE_D is identical to the SAMPLE opcode except that the derivatives for
2426 the source address in the x direction and the y direction are provided by
2429 Syntax: ``SAMPLE_D dst, address, sampler_view, sampler, der_x, der_y``
2431 Example: ``SAMPLE_D TEMP[0], TEMP[1], SVIEW[0], SAMP[0], TEMP[2], TEMP[3]``
2433 .. opcode:: SAMPLE_L
2435 SAMPLE_L is identical to the SAMPLE opcode except that the LOD is provided
2436 directly as a scalar value, representing no anisotropy.
2438 Syntax: ``SAMPLE_L dst, address, sampler_view, sampler, explicit_lod``
2440 Example: ``SAMPLE_L TEMP[0], TEMP[1], SVIEW[0], SAMP[0], TEMP[2].x``
2444 Gathers the four texels to be used in a bi-linear filtering operation and
2445 packs them into a single register. Only works with 2D, 2D array, cubemaps,
2446 and cubemaps arrays. For 2D textures, only the addressing modes of the
2447 sampler and the top level of any mip pyramid are used. Set W to zero. It
2448 behaves like the SAMPLE instruction, but a filtered sample is not
2449 generated. The four samples that contribute to filtering are placed into
2450 xyzw in counter-clockwise order, starting with the (u,v) texture coordinate
2451 delta at the following locations (-, +), (+, +), (+, -), (-, -), where the
2452 magnitude of the deltas are half a texel.
2455 .. opcode:: SVIEWINFO
2457 Query the dimensions of a given sampler view. dst receives width, height,
2458 depth or array size and number of mipmap levels as int4. The dst can have a
2459 writemask which will specify what info is the caller interested in.
2461 Syntax: ``SVIEWINFO dst, src_mip_level, sampler_view``
2463 Example: ``SVIEWINFO TEMP[0], TEMP[1].x, SVIEW[0]``
2465 src_mip_level is an unsigned integer scalar. If it's out of range then
2466 returns 0 for width, height and depth/array size but the total number of
2467 mipmap is still returned correctly for the given sampler view. The returned
2468 width, height and depth values are for the mipmap level selected by the
2469 src_mip_level and are in the number of texels. For 1d texture array width
2470 is in dst.x, array size is in dst.y and dst.z is 0. The number of mipmaps is
2471 still in dst.w. In contrast to d3d10 resinfo, there's no way in the tgsi
2472 instruction encoding to specify the return type (float/rcpfloat/uint), hence
2473 always using uint. Also, unlike the SAMPLE instructions, the swizzle on src1
2474 resinfo allowing swizzling dst values is ignored (due to the interaction
2475 with rcpfloat modifier which requires some swizzle handling in the state
2478 .. opcode:: SAMPLE_POS
2480 Query the position of a sample in the given resource or render target
2481 when per-sample fragment shading is in effect.
2483 Syntax: ``SAMPLE_POS dst, source, sample_index``
2485 dst receives float4 (x, y, undef, undef) indicated where the sample is
2486 located. Sample locations are in the range [0, 1] where 0.5 is the center
2489 source is either a sampler view (to indicate a shader resource) or temp
2490 register (to indicate the render target). The source register may have
2491 an optional swizzle to apply to the returned result
2493 sample_index is an integer scalar indicating which sample position is to
2496 If per-sample shading is not in effect or the source resource or render
2497 target is not multisampled, the result is (0.5, 0.5, undef, undef).
2499 NOTE: no driver has implemented this opcode yet (and no state tracker
2500 emits it). This information is subject to change.
2502 .. opcode:: SAMPLE_INFO
2504 Query the number of samples in a multisampled resource or render target.
2506 Syntax: ``SAMPLE_INFO dst, source``
2508 dst receives int4 (n, 0, 0, 0) where n is the number of samples in a
2509 resource or the render target.
2511 source is either a sampler view (to indicate a shader resource) or temp
2512 register (to indicate the render target). The source register may have
2513 an optional swizzle to apply to the returned result
2515 If per-sample shading is not in effect or the source resource or render
2516 target is not multisampled, the result is (1, 0, 0, 0).
2518 NOTE: no driver has implemented this opcode yet (and no state tracker
2519 emits it). This information is subject to change.
2521 .. opcode:: LOD - level of detail
2523 Same syntax as the SAMPLE opcode but instead of performing an actual
2524 texture lookup/filter, return the computed LOD information that the
2525 texture pipe would use to access the texture. The Y component contains
2526 the computed LOD lambda_prime. The X component contains the LOD that will
2527 be accessed, based on min/max lod's and mipmap filters.
2528 The Z and W components are set to 0.
2530 Syntax: ``LOD dst, address, sampler_view, sampler``
2533 .. _resourceopcodes:
2535 Resource Access Opcodes
2536 ^^^^^^^^^^^^^^^^^^^^^^^
2538 For these opcodes, the resource can be a BUFFER, IMAGE, or MEMORY.
2540 .. opcode:: LOAD - Fetch data from a shader buffer or image
2542 Syntax: ``LOAD dst, resource, address``
2544 Example: ``LOAD TEMP[0], BUFFER[0], TEMP[1]``
2546 Using the provided integer address, LOAD fetches data
2547 from the specified buffer or texture without any
2550 The 'address' is specified as a vector of unsigned
2551 integers. If the 'address' is out of range the result
2554 Only the first mipmap level of a resource can be read
2555 from using this instruction.
2557 For 1D or 2D texture arrays, the array index is
2558 provided as an unsigned integer in address.y or
2559 address.z, respectively. address.yz are ignored for
2560 buffers and 1D textures. address.z is ignored for 1D
2561 texture arrays and 2D textures. address.w is always
2564 A swizzle suffix may be added to the resource argument
2565 this will cause the resource data to be swizzled accordingly.
2567 .. opcode:: STORE - Write data to a shader resource
2569 Syntax: ``STORE resource, address, src``
2571 Example: ``STORE BUFFER[0], TEMP[0], TEMP[1]``
2573 Using the provided integer address, STORE writes data
2574 to the specified buffer or texture.
2576 The 'address' is specified as a vector of unsigned
2577 integers. If the 'address' is out of range the result
2580 Only the first mipmap level of a resource can be
2581 written to using this instruction.
2583 For 1D or 2D texture arrays, the array index is
2584 provided as an unsigned integer in address.y or
2585 address.z, respectively. address.yz are ignored for
2586 buffers and 1D textures. address.z is ignored for 1D
2587 texture arrays and 2D textures. address.w is always
2590 .. opcode:: RESQ - Query information about a resource
2592 Syntax: ``RESQ dst, resource``
2594 Example: ``RESQ TEMP[0], BUFFER[0]``
2596 Returns information about the buffer or image resource. For buffer
2597 resources, the size (in bytes) is returned in the x component. For
2598 image resources, .xyz will contain the width/height/layers of the
2599 image, while .w will contain the number of samples for multi-sampled
2602 .. opcode:: FBFETCH - Load data from framebuffer
2604 Syntax: ``FBFETCH dst, output``
2606 Example: ``FBFETCH TEMP[0], OUT[0]``
2608 This is only valid on ``COLOR`` semantic outputs. Returns the color
2609 of the current position in the framebuffer from before this fragment
2610 shader invocation. May return the same value from multiple calls for
2611 a particular output within a single invocation. Note that result may
2612 be undefined if a fragment is drawn multiple times without a blend
2616 .. _bindlessopcodes:
2621 These opcodes are for working with bindless sampler or image handles and
2622 require PIPE_CAP_BINDLESS_TEXTURE.
2624 .. opcode:: IMG2HND - Get a bindless handle for a image
2626 Syntax: ``IMG2HND dst, image``
2628 Example: ``IMG2HND TEMP[0], IMAGE[0]``
2630 Sets 'dst' to a bindless handle for 'image'.
2632 .. opcode:: SAMP2HND - Get a bindless handle for a sampler
2634 Syntax: ``SAMP2HND dst, sampler``
2636 Example: ``SAMP2HND TEMP[0], SAMP[0]``
2638 Sets 'dst' to a bindless handle for 'sampler'.
2641 .. _threadsyncopcodes:
2643 Inter-thread synchronization opcodes
2644 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2646 These opcodes are intended for communication between threads running
2647 within the same compute grid. For now they're only valid in compute
2650 .. opcode:: BARRIER - Thread group barrier
2654 This opcode suspends the execution of the current thread until all
2655 the remaining threads in the working group reach the same point of
2656 the program. Results are unspecified if any of the remaining
2657 threads terminates or never reaches an executed BARRIER instruction.
2659 .. opcode:: MEMBAR - Memory barrier
2663 This opcode waits for the completion of all memory accesses based on
2664 the type passed in. The type is an immediate bitfield with the following
2667 Bit 0: Shader storage buffers
2668 Bit 1: Atomic buffers
2670 Bit 3: Shared memory
2673 These may be passed in in any combination. An implementation is free to not
2674 distinguish between these as it sees fit. However these map to all the
2675 possibilities made available by GLSL.
2682 These opcodes provide atomic variants of some common arithmetic and
2683 logical operations. In this context atomicity means that another
2684 concurrent memory access operation that affects the same memory
2685 location is guaranteed to be performed strictly before or after the
2686 entire execution of the atomic operation. The resource may be a BUFFER,
2687 IMAGE, HWATOMIC, or MEMORY. In the case of an image, the offset works
2688 the same as for ``LOAD`` and ``STORE``, specified above. For atomic
2689 counters, the offset is an immediate index to the base hw atomic
2690 counter for this operation.
2691 These atomic operations may only be used with 32-bit integer image formats.
2693 .. opcode:: ATOMUADD - Atomic integer addition
2695 Syntax: ``ATOMUADD dst, resource, offset, src``
2697 Example: ``ATOMUADD TEMP[0], BUFFER[0], TEMP[1], TEMP[2]``
2699 The following operation is performed atomically:
2703 dst_x = resource[offset]
2705 resource[offset] = dst_x + src_x
2708 .. opcode:: ATOMFADD - Atomic floating point addition
2710 Syntax: ``ATOMFADD dst, resource, offset, src``
2712 Example: ``ATOMFADD TEMP[0], BUFFER[0], TEMP[1], TEMP[2]``
2714 The following operation is performed atomically:
2718 dst_x = resource[offset]
2720 resource[offset] = dst_x + src_x
2723 .. opcode:: ATOMXCHG - Atomic exchange
2725 Syntax: ``ATOMXCHG dst, resource, offset, src``
2727 Example: ``ATOMXCHG TEMP[0], BUFFER[0], TEMP[1], TEMP[2]``
2729 The following operation is performed atomically:
2733 dst_x = resource[offset]
2735 resource[offset] = src_x
2738 .. opcode:: ATOMCAS - Atomic compare-and-exchange
2740 Syntax: ``ATOMCAS dst, resource, offset, cmp, src``
2742 Example: ``ATOMCAS TEMP[0], BUFFER[0], TEMP[1], TEMP[2], TEMP[3]``
2744 The following operation is performed atomically:
2748 dst_x = resource[offset]
2750 resource[offset] = (dst_x == cmp_x ? src_x : dst_x)
2753 .. opcode:: ATOMAND - Atomic bitwise And
2755 Syntax: ``ATOMAND dst, resource, offset, src``
2757 Example: ``ATOMAND TEMP[0], BUFFER[0], TEMP[1], TEMP[2]``
2759 The following operation is performed atomically:
2763 dst_x = resource[offset]
2765 resource[offset] = dst_x \& src_x
2768 .. opcode:: ATOMOR - Atomic bitwise Or
2770 Syntax: ``ATOMOR dst, resource, offset, src``
2772 Example: ``ATOMOR TEMP[0], BUFFER[0], TEMP[1], TEMP[2]``
2774 The following operation is performed atomically:
2778 dst_x = resource[offset]
2780 resource[offset] = dst_x | src_x
2783 .. opcode:: ATOMXOR - Atomic bitwise Xor
2785 Syntax: ``ATOMXOR dst, resource, offset, src``
2787 Example: ``ATOMXOR TEMP[0], BUFFER[0], TEMP[1], TEMP[2]``
2789 The following operation is performed atomically:
2793 dst_x = resource[offset]
2795 resource[offset] = dst_x \oplus src_x
2798 .. opcode:: ATOMUMIN - Atomic unsigned minimum
2800 Syntax: ``ATOMUMIN dst, resource, offset, src``
2802 Example: ``ATOMUMIN TEMP[0], BUFFER[0], TEMP[1], TEMP[2]``
2804 The following operation is performed atomically:
2808 dst_x = resource[offset]
2810 resource[offset] = (dst_x < src_x ? dst_x : src_x)
2813 .. opcode:: ATOMUMAX - Atomic unsigned maximum
2815 Syntax: ``ATOMUMAX dst, resource, offset, src``
2817 Example: ``ATOMUMAX TEMP[0], BUFFER[0], TEMP[1], TEMP[2]``
2819 The following operation is performed atomically:
2823 dst_x = resource[offset]
2825 resource[offset] = (dst_x > src_x ? dst_x : src_x)
2828 .. opcode:: ATOMIMIN - Atomic signed minimum
2830 Syntax: ``ATOMIMIN dst, resource, offset, src``
2832 Example: ``ATOMIMIN TEMP[0], BUFFER[0], TEMP[1], TEMP[2]``
2834 The following operation is performed atomically:
2838 dst_x = resource[offset]
2840 resource[offset] = (dst_x < src_x ? dst_x : src_x)
2843 .. opcode:: ATOMIMAX - Atomic signed maximum
2845 Syntax: ``ATOMIMAX dst, resource, offset, src``
2847 Example: ``ATOMIMAX TEMP[0], BUFFER[0], TEMP[1], TEMP[2]``
2849 The following operation is performed atomically:
2853 dst_x = resource[offset]
2855 resource[offset] = (dst_x > src_x ? dst_x : src_x)
2858 .. opcode:: ATOMINC_WRAP - Atomic increment + wrap around
2860 Syntax: ``ATOMINC_WRAP dst, resource, offset, src``
2862 Example: ``ATOMINC_WRAP TEMP[0], BUFFER[0], TEMP[1], TEMP[2]``
2864 The following operation is performed atomically:
2868 dst_x = resource[offset] + 1
2870 resource[offset] = dst_x <= src_x ? dst_x : 0
2873 .. opcode:: ATOMDEC_WRAP - Atomic decrement + wrap around
2875 Syntax: ``ATOMDEC_WRAP dst, resource, offset, src``
2877 Example: ``ATOMDEC_WRAP TEMP[0], BUFFER[0], TEMP[1], TEMP[2]``
2879 The following operation is performed atomically:
2883 dst_x = resource[offset]
2885 resource[offset] = (dst_x > 0 && dst_x < src_x) ? dst_x - 1 : 0
2888 .. _interlaneopcodes:
2893 These opcodes reduce the given value across the shader invocations
2894 running in the current SIMD group. Every thread in the subgroup will receive
2895 the same result. The BALLOT operations accept a single-channel argument that
2896 is treated as a boolean and produce a 64-bit value.
2898 .. opcode:: VOTE_ANY - Value is set in any of the active invocations
2900 Syntax: ``VOTE_ANY dst, value``
2902 Example: ``VOTE_ANY TEMP[0].x, TEMP[1].x``
2905 .. opcode:: VOTE_ALL - Value is set in all of the active invocations
2907 Syntax: ``VOTE_ALL dst, value``
2909 Example: ``VOTE_ALL TEMP[0].x, TEMP[1].x``
2912 .. opcode:: VOTE_EQ - Value is the same in all of the active invocations
2914 Syntax: ``VOTE_EQ dst, value``
2916 Example: ``VOTE_EQ TEMP[0].x, TEMP[1].x``
2919 .. opcode:: BALLOT - Lanemask of whether the value is set in each active
2922 Syntax: ``BALLOT dst, value``
2924 Example: ``BALLOT TEMP[0].xy, TEMP[1].x``
2926 When the argument is a constant true, this produces a bitmask of active
2927 invocations. In fragment shaders, this can include helper invocations
2928 (invocations whose outputs and writes to memory are discarded, but which
2929 are used to compute derivatives).
2932 .. opcode:: READ_FIRST - Broadcast the value from the first active
2933 invocation to all active lanes
2935 Syntax: ``READ_FIRST dst, value``
2937 Example: ``READ_FIRST TEMP[0], TEMP[1]``
2940 .. opcode:: READ_INVOC - Retrieve the value from the given invocation
2941 (need not be uniform)
2943 Syntax: ``READ_INVOC dst, value, invocation``
2945 Example: ``READ_INVOC TEMP[0].xy, TEMP[1].xy, TEMP[2].x``
2947 invocation.x controls the invocation number to read from for all channels.
2948 The invocation number must be the same across all active invocations in a
2949 sub-group; otherwise, the results are undefined.
2952 Explanation of symbols used
2953 ------------------------------
2960 :math:`|x|` Absolute value of `x`.
2962 :math:`\lceil x \rceil` Ceiling of `x`.
2964 clamp(x,y,z) Clamp x between y and z.
2965 (x < y) ? y : (x > z) ? z : x
2967 :math:`\lfloor x\rfloor` Floor of `x`.
2969 :math:`\log_2{x}` Logarithm of `x`, base 2.
2971 max(x,y) Maximum of x and y.
2974 min(x,y) Minimum of x and y.
2977 partialx(x) Derivative of x relative to fragment's X.
2979 partialy(x) Derivative of x relative to fragment's Y.
2981 pop() Pop from stack.
2983 :math:`x^y` `x` to the power `y`.
2985 push(x) Push x on stack.
2989 trunc(x) Truncate x, i.e. drop the fraction bits.
2996 discard Discard fragment.
3000 target Label of target instruction.
3011 Declares a register that is will be referenced as an operand in Instruction
3014 File field contains register file that is being declared and is one
3017 UsageMask field specifies which of the register components can be accessed
3018 and is one of TGSI_WRITEMASK.
3020 The Local flag specifies that a given value isn't intended for
3021 subroutine parameter passing and, as a result, the implementation
3022 isn't required to give any guarantees of it being preserved across
3023 subroutine boundaries. As it's merely a compiler hint, the
3024 implementation is free to ignore it.
3026 If Dimension flag is set to 1, a Declaration Dimension token follows.
3028 If Semantic flag is set to 1, a Declaration Semantic token follows.
3030 If Interpolate flag is set to 1, a Declaration Interpolate token follows.
3032 If file is TGSI_FILE_RESOURCE, a Declaration Resource token follows.
3034 If Array flag is set to 1, a Declaration Array token follows.
3037 ^^^^^^^^^^^^^^^^^^^^^^^^
3039 Declarations can optional have an ArrayID attribute which can be referred by
3040 indirect addressing operands. An ArrayID of zero is reserved and treated as
3041 if no ArrayID is specified.
3043 If an indirect addressing operand refers to a specific declaration by using
3044 an ArrayID only the registers in this declaration are guaranteed to be
3045 accessed, accessing any register outside this declaration results in undefined
3046 behavior. Note that for compatibility the effective index is zero-based and
3047 not relative to the specified declaration
3049 If no ArrayID is specified with an indirect addressing operand the whole
3050 register file might be accessed by this operand. This is strongly discouraged
3051 and will prevent packing of scalar/vec2 arrays and effective alias analysis.
3052 This is only legal for TEMP and CONST register files.
3054 Declaration Semantic
3055 ^^^^^^^^^^^^^^^^^^^^^^^^
3057 Vertex and fragment shader input and output registers may be labeled
3058 with semantic information consisting of a name and index.
3060 Follows Declaration token if Semantic bit is set.
3062 Since its purpose is to link a shader with other stages of the pipeline,
3063 it is valid to follow only those Declaration tokens that declare a register
3064 either in INPUT or OUTPUT file.
3066 SemanticName field contains the semantic name of the register being declared.
3067 There is no default value.
3069 SemanticIndex is an optional subscript that can be used to distinguish
3070 different register declarations with the same semantic name. The default value
3073 The meanings of the individual semantic names are explained in the following
3076 TGSI_SEMANTIC_POSITION
3077 """"""""""""""""""""""
3079 For vertex shaders, TGSI_SEMANTIC_POSITION indicates the vertex shader
3080 output register which contains the homogeneous vertex position in the clip
3081 space coordinate system. After clipping, the X, Y and Z components of the
3082 vertex will be divided by the W value to get normalized device coordinates.
3084 For fragment shaders, TGSI_SEMANTIC_POSITION is used to indicate that
3085 fragment shader input (or system value, depending on which one is
3086 supported by the driver) contains the fragment's window position. The X
3087 component starts at zero and always increases from left to right.
3088 The Y component starts at zero and always increases but Y=0 may either
3089 indicate the top of the window or the bottom depending on the fragment
3090 coordinate origin convention (see TGSI_PROPERTY_FS_COORD_ORIGIN).
3091 The Z coordinate ranges from 0 to 1 to represent depth from the front
3092 to the back of the Z buffer. The W component contains the interpolated
3093 reciprocal of the vertex position W component (corresponding to gl_Fragcoord,
3094 but unlike d3d10 which interpolates the same 1/w but then gives back
3095 the reciprocal of the interpolated value).
3097 Fragment shaders may also declare an output register with
3098 TGSI_SEMANTIC_POSITION. Only the Z component is writable. This allows
3099 the fragment shader to change the fragment's Z position.
3106 For vertex shader outputs or fragment shader inputs/outputs, this
3107 label indicates that the register contains an R,G,B,A color.
3109 Several shader inputs/outputs may contain colors so the semantic index
3110 is used to distinguish them. For example, color[0] may be the diffuse
3111 color while color[1] may be the specular color.
3113 This label is needed so that the flat/smooth shading can be applied
3114 to the right interpolants during rasterization.
3118 TGSI_SEMANTIC_BCOLOR
3119 """"""""""""""""""""
3121 Back-facing colors are only used for back-facing polygons, and are only valid
3122 in vertex shader outputs. After rasterization, all polygons are front-facing
3123 and COLOR and BCOLOR end up occupying the same slots in the fragment shader,
3124 so all BCOLORs effectively become regular COLORs in the fragment shader.
3130 Vertex shader inputs and outputs and fragment shader inputs may be
3131 labeled with TGSI_SEMANTIC_FOG to indicate that the register contains
3132 a fog coordinate. Typically, the fragment shader will use the fog coordinate
3133 to compute a fog blend factor which is used to blend the normal fragment color
3134 with a constant fog color. But fog coord really is just an ordinary vec4
3135 register like regular semantics.
3141 Vertex shader input and output registers may be labeled with
3142 TGIS_SEMANTIC_PSIZE to indicate that the register contains a point size
3143 in the form (S, 0, 0, 1). The point size controls the width or diameter
3144 of points for rasterization. This label cannot be used in fragment
3147 When using this semantic, be sure to set the appropriate state in the
3148 :ref:`rasterizer` first.
3151 TGSI_SEMANTIC_TEXCOORD
3152 """"""""""""""""""""""
3154 Only available if PIPE_CAP_TGSI_TEXCOORD is exposed !
3156 Vertex shader outputs and fragment shader inputs may be labeled with
3157 this semantic to make them replaceable by sprite coordinates via the
3158 sprite_coord_enable state in the :ref:`rasterizer`.
3159 The semantic index permitted with this semantic is limited to <= 7.
3161 If the driver does not support TEXCOORD, sprite coordinate replacement
3162 applies to inputs with the GENERIC semantic instead.
3164 The intended use case for this semantic is gl_TexCoord.
3167 TGSI_SEMANTIC_PCOORD
3168 """"""""""""""""""""
3170 Only available if PIPE_CAP_TGSI_TEXCOORD is exposed !
3172 Fragment shader inputs may be labeled with TGSI_SEMANTIC_PCOORD to indicate
3173 that the register contains sprite coordinates in the form (x, y, 0, 1), if
3174 the current primitive is a point and point sprites are enabled. Otherwise,
3175 the contents of the register are undefined.
3177 The intended use case for this semantic is gl_PointCoord.
3180 TGSI_SEMANTIC_GENERIC
3181 """""""""""""""""""""
3183 All vertex/fragment shader inputs/outputs not labeled with any other
3184 semantic label can be considered to be generic attributes. Typical
3185 uses of generic inputs/outputs are texcoords and user-defined values.
3188 TGSI_SEMANTIC_NORMAL
3189 """"""""""""""""""""
3191 Indicates that a vertex shader input is a normal vector. This is
3192 typically only used for legacy graphics APIs.
3198 This label applies to fragment shader inputs (or system values,
3199 depending on which one is supported by the driver) and indicates that
3200 the register contains front/back-face information.
3202 If it is an input, it will be a floating-point vector in the form (F, 0, 0, 1),
3203 where F will be positive when the fragment belongs to a front-facing polygon,
3204 and negative when the fragment belongs to a back-facing polygon.
3206 If it is a system value, it will be an integer vector in the form (F, 0, 0, 1),
3207 where F is 0xffffffff when the fragment belongs to a front-facing polygon and
3208 0 when the fragment belongs to a back-facing polygon.
3211 TGSI_SEMANTIC_EDGEFLAG
3212 """"""""""""""""""""""
3214 For vertex shaders, this sematic label indicates that an input or
3215 output is a boolean edge flag. The register layout is [F, x, x, x]
3216 where F is 0.0 or 1.0 and x = don't care. Normally, the vertex shader
3217 simply copies the edge flag input to the edgeflag output.
3219 Edge flags are used to control which lines or points are actually
3220 drawn when the polygon mode converts triangles/quads/polygons into
3224 TGSI_SEMANTIC_STENCIL
3225 """""""""""""""""""""
3227 For fragment shaders, this semantic label indicates that an output
3228 is a writable stencil reference value. Only the Y component is writable.
3229 This allows the fragment shader to change the fragments stencilref value.
3232 TGSI_SEMANTIC_VIEWPORT_INDEX
3233 """"""""""""""""""""""""""""
3235 For geometry shaders, this semantic label indicates that an output
3236 contains the index of the viewport (and scissor) to use.
3237 This is an integer value, and only the X component is used.
3239 If PIPE_CAP_TGSI_VS_LAYER_VIEWPORT or PIPE_CAP_TGSI_TES_LAYER_VIEWPORT is
3240 supported, then this semantic label can also be used in vertex or
3241 tessellation evaluation shaders, respectively. Only the value written in the
3242 last vertex processing stage is used.
3248 For geometry shaders, this semantic label indicates that an output
3249 contains the layer value to use for the color and depth/stencil surfaces.
3250 This is an integer value, and only the X component is used.
3251 (Also known as rendertarget array index.)
3253 If PIPE_CAP_TGSI_VS_LAYER_VIEWPORT or PIPE_CAP_TGSI_TES_LAYER_VIEWPORT is
3254 supported, then this semantic label can also be used in vertex or
3255 tessellation evaluation shaders, respectively. Only the value written in the
3256 last vertex processing stage is used.
3259 TGSI_SEMANTIC_CLIPDIST
3260 """"""""""""""""""""""
3262 Note this covers clipping and culling distances.
3264 When components of vertex elements are identified this way, these
3265 values are each assumed to be a float32 signed distance to a plane.
3268 Primitive setup only invokes rasterization on pixels for which
3269 the interpolated plane distances are >= 0.
3272 Primitives will be completely discarded if the plane distance
3273 for all of the vertices in the primitive are < 0.
3274 If a vertex has a cull distance of NaN, that vertex counts as "out"
3277 Multiple clip/cull planes can be implemented simultaneously, by
3278 annotating multiple components of one or more vertex elements with
3279 the above specified semantic.
3280 The limits on both clip and cull distances are bound
3281 by the PIPE_MAX_CLIP_OR_CULL_DISTANCE_COUNT define which defines
3282 the maximum number of components that can be used to hold the
3283 distances and by the PIPE_MAX_CLIP_OR_CULL_DISTANCE_ELEMENT_COUNT
3284 which specifies the maximum number of registers which can be
3285 annotated with those semantics.
3286 The properties NUM_CLIPDIST_ENABLED and NUM_CULLDIST_ENABLED
3287 are used to divide up the 2 x vec4 space between clipping and culling.
3289 TGSI_SEMANTIC_SAMPLEID
3290 """"""""""""""""""""""
3292 For fragment shaders, this semantic label indicates that a system value
3293 contains the current sample id (i.e. gl_SampleID) as an unsigned int.
3294 Only the X component is used. If per-sample shading is not enabled,
3295 the result is (0, undef, undef, undef).
3297 Note that if the fragment shader uses this system value, the fragment
3298 shader is automatically executed at per sample frequency.
3300 TGSI_SEMANTIC_SAMPLEPOS
3301 """""""""""""""""""""""
3303 For fragment shaders, this semantic label indicates that a system
3304 value contains the current sample's position as float4(x, y, undef, undef)
3305 in the render target (i.e. gl_SamplePosition) when per-fragment shading
3306 is in effect. Position values are in the range [0, 1] where 0.5 is
3307 the center of the fragment.
3309 Note that if the fragment shader uses this system value, the fragment
3310 shader is automatically executed at per sample frequency.
3312 TGSI_SEMANTIC_SAMPLEMASK
3313 """"""""""""""""""""""""
3315 For fragment shaders, this semantic label can be applied to either a
3316 shader system value input or output.
3318 For a system value, the sample mask indicates the set of samples covered by
3319 the current primitive. If MSAA is not enabled, the value is (1, 0, 0, 0).
3321 For an output, the sample mask is used to disable further sample processing.
3323 For both, the register type is uint[4] but only the X component is used
3324 (i.e. gl_SampleMask[0]). Each bit corresponds to one sample position (up
3325 to 32x MSAA is supported).
3327 TGSI_SEMANTIC_INVOCATIONID
3328 """"""""""""""""""""""""""
3330 For geometry shaders, this semantic label indicates that a system value
3331 contains the current invocation id (i.e. gl_InvocationID).
3332 This is an integer value, and only the X component is used.
3334 TGSI_SEMANTIC_INSTANCEID
3335 """"""""""""""""""""""""
3337 For vertex shaders, this semantic label indicates that a system value contains
3338 the current instance id (i.e. gl_InstanceID). It does not include the base
3339 instance. This is an integer value, and only the X component is used.
3341 TGSI_SEMANTIC_VERTEXID
3342 """"""""""""""""""""""
3344 For vertex shaders, this semantic label indicates that a system value contains
3345 the current vertex id (i.e. gl_VertexID). It does (unlike in d3d10) include the
3346 base vertex. This is an integer value, and only the X component is used.
3348 TGSI_SEMANTIC_VERTEXID_NOBASE
3349 """""""""""""""""""""""""""""""
3351 For vertex shaders, this semantic label indicates that a system value contains
3352 the current vertex id without including the base vertex (this corresponds to
3353 d3d10 vertex id, so TGSI_SEMANTIC_VERTEXID_NOBASE + TGSI_SEMANTIC_BASEVERTEX
3354 == TGSI_SEMANTIC_VERTEXID). This is an integer value, and only the X component
3357 TGSI_SEMANTIC_BASEVERTEX
3358 """"""""""""""""""""""""
3360 For vertex shaders, this semantic label indicates that a system value contains
3361 the base vertex (i.e. gl_BaseVertex). Note that for non-indexed draw calls,
3362 this contains the first (or start) value instead.
3363 This is an integer value, and only the X component is used.
3365 TGSI_SEMANTIC_PRIMID
3366 """"""""""""""""""""
3368 For geometry and fragment shaders, this semantic label indicates the value
3369 contains the primitive id (i.e. gl_PrimitiveID). This is an integer value,
3370 and only the X component is used.
3371 FIXME: This right now can be either a ordinary input or a system value...
3377 For tessellation evaluation/control shaders, this semantic label indicates a
3378 generic per-patch attribute. Such semantics will not implicitly be per-vertex
3381 TGSI_SEMANTIC_TESSCOORD
3382 """""""""""""""""""""""
3384 For tessellation evaluation shaders, this semantic label indicates the
3385 coordinates of the vertex being processed. This is available in XYZ; W is
3388 TGSI_SEMANTIC_TESSOUTER
3389 """""""""""""""""""""""
3391 For tessellation evaluation/control shaders, this semantic label indicates the
3392 outer tessellation levels of the patch. Isoline tessellation will only have XY
3393 defined, triangle will have XYZ and quads will have XYZW defined. This
3394 corresponds to gl_TessLevelOuter.
3396 TGSI_SEMANTIC_TESSINNER
3397 """""""""""""""""""""""
3399 For tessellation evaluation/control shaders, this semantic label indicates the
3400 inner tessellation levels of the patch. The X value is only defined for
3401 triangle tessellation, while quads will have XY defined. This is entirely
3402 undefined for isoline tessellation.
3404 TGSI_SEMANTIC_VERTICESIN
3405 """"""""""""""""""""""""
3407 For tessellation evaluation/control shaders, this semantic label indicates the
3408 number of vertices provided in the input patch. Only the X value is defined.
3410 TGSI_SEMANTIC_HELPER_INVOCATION
3411 """""""""""""""""""""""""""""""
3413 For fragment shaders, this semantic indicates whether the current
3414 invocation is covered or not. Helper invocations are created in order
3415 to properly compute derivatives, however it may be desirable to skip
3416 some of the logic in those cases. See ``gl_HelperInvocation`` documentation.
3418 TGSI_SEMANTIC_BASEINSTANCE
3419 """"""""""""""""""""""""""
3421 For vertex shaders, the base instance argument supplied for this
3422 draw. This is an integer value, and only the X component is used.
3424 TGSI_SEMANTIC_DRAWID
3425 """"""""""""""""""""
3427 For vertex shaders, the zero-based index of the current draw in a
3428 ``glMultiDraw*`` invocation. This is an integer value, and only the X
3432 TGSI_SEMANTIC_WORK_DIM
3433 """"""""""""""""""""""
3435 For compute shaders started via opencl this retrieves the work_dim
3436 parameter to the clEnqueueNDRangeKernel call with which the shader
3440 TGSI_SEMANTIC_GRID_SIZE
3441 """""""""""""""""""""""
3443 For compute shaders, this semantic indicates the maximum (x, y, z) dimensions
3444 of a grid of thread blocks.
3447 TGSI_SEMANTIC_BLOCK_ID
3448 """"""""""""""""""""""
3450 For compute shaders, this semantic indicates the (x, y, z) coordinates of the
3451 current block inside of the grid.
3454 TGSI_SEMANTIC_BLOCK_SIZE
3455 """"""""""""""""""""""""
3457 For compute shaders, this semantic indicates the maximum (x, y, z) dimensions
3458 of a block in threads.
3461 TGSI_SEMANTIC_THREAD_ID
3462 """""""""""""""""""""""
3464 For compute shaders, this semantic indicates the (x, y, z) coordinates of the
3465 current thread inside of the block.
3468 TGSI_SEMANTIC_SUBGROUP_SIZE
3469 """""""""""""""""""""""""""
3471 This semantic indicates the subgroup size for the current invocation. This is
3472 an integer of at most 64, as it indicates the width of lanemasks. It does not
3473 depend on the number of invocations that are active.
3476 TGSI_SEMANTIC_SUBGROUP_INVOCATION
3477 """""""""""""""""""""""""""""""""
3479 The index of the current invocation within its subgroup.
3482 TGSI_SEMANTIC_SUBGROUP_EQ_MASK
3483 """"""""""""""""""""""""""""""
3485 A bit mask of ``bit index == TGSI_SEMANTIC_SUBGROUP_INVOCATION``, i.e.
3486 ``1 << subgroup_invocation`` in arbitrary precision arithmetic.
3489 TGSI_SEMANTIC_SUBGROUP_GE_MASK
3490 """"""""""""""""""""""""""""""
3492 A bit mask of ``bit index >= TGSI_SEMANTIC_SUBGROUP_INVOCATION``, i.e.
3493 ``((1 << (subgroup_size - subgroup_invocation)) - 1) << subgroup_invocation``
3494 in arbitrary precision arithmetic.
3497 TGSI_SEMANTIC_SUBGROUP_GT_MASK
3498 """"""""""""""""""""""""""""""
3500 A bit mask of ``bit index > TGSI_SEMANTIC_SUBGROUP_INVOCATION``, i.e.
3501 ``((1 << (subgroup_size - subgroup_invocation - 1)) - 1) << (subgroup_invocation + 1)``
3502 in arbitrary precision arithmetic.
3505 TGSI_SEMANTIC_SUBGROUP_LE_MASK
3506 """"""""""""""""""""""""""""""
3508 A bit mask of ``bit index <= TGSI_SEMANTIC_SUBGROUP_INVOCATION``, i.e.
3509 ``(1 << (subgroup_invocation + 1)) - 1`` in arbitrary precision arithmetic.
3512 TGSI_SEMANTIC_SUBGROUP_LT_MASK
3513 """"""""""""""""""""""""""""""
3515 A bit mask of ``bit index < TGSI_SEMANTIC_SUBGROUP_INVOCATION``, i.e.
3516 ``(1 << subgroup_invocation) - 1`` in arbitrary precision arithmetic.
3519 TGSI_SEMANTIC_TESS_DEFAULT_OUTER_LEVEL
3520 """"""""""""""""""""""""""""""""""""""
3522 A system value equal to the default_outer_level array set via set_tess_level.
3525 TGSI_SEMANTIC_TESS_DEFAULT_INNER_LEVEL
3526 """"""""""""""""""""""""""""""""""""""
3528 A system value equal to the default_inner_level array set via set_tess_level.
3531 Declaration Interpolate
3532 ^^^^^^^^^^^^^^^^^^^^^^^
3534 This token is only valid for fragment shader INPUT declarations.
3536 The Interpolate field specifes the way input is being interpolated by
3537 the rasteriser and is one of TGSI_INTERPOLATE_*.
3539 The Location field specifies the location inside the pixel that the
3540 interpolation should be done at, one of ``TGSI_INTERPOLATE_LOC_*``. Note that
3541 when per-sample shading is enabled, the implementation may choose to
3542 interpolate at the sample irrespective of the Location field.
3544 The CylindricalWrap bitfield specifies which register components
3545 should be subject to cylindrical wrapping when interpolating by the
3546 rasteriser. If TGSI_CYLINDRICAL_WRAP_X is set to 1, the X component
3547 should be interpolated according to cylindrical wrapping rules.
3550 Declaration Sampler View
3551 ^^^^^^^^^^^^^^^^^^^^^^^^
3553 Follows Declaration token if file is TGSI_FILE_SAMPLER_VIEW.
3555 DCL SVIEW[#], resource, type(s)
3557 Declares a shader input sampler view and assigns it to a SVIEW[#]
3560 resource can be one of BUFFER, 1D, 2D, 3D, 1DArray and 2DArray.
3562 type must be 1 or 4 entries (if specifying on a per-component
3563 level) out of UNORM, SNORM, SINT, UINT and FLOAT.
3565 For TEX\* style texture sample opcodes (as opposed to SAMPLE\* opcodes
3566 which take an explicit SVIEW[#] source register), there may be optionally
3567 SVIEW[#] declarations. In this case, the SVIEW index is implied by the
3568 SAMP index, and there must be a corresponding SVIEW[#] declaration for
3569 each SAMP[#] declaration. Drivers are free to ignore this if they wish.
3570 But note in particular that some drivers need to know the sampler type
3571 (float/int/unsigned) in order to generate the correct code, so cases
3572 where integer textures are sampled, SVIEW[#] declarations should be
3575 NOTE: It is NOT legal to mix SAMPLE\* style opcodes and TEX\* opcodes
3578 Declaration Resource
3579 ^^^^^^^^^^^^^^^^^^^^
3581 Follows Declaration token if file is TGSI_FILE_RESOURCE.
3583 DCL RES[#], resource [, WR] [, RAW]
3585 Declares a shader input resource and assigns it to a RES[#]
3588 resource can be one of BUFFER, 1D, 2D, 3D, CUBE, 1DArray and
3591 If the RAW keyword is not specified, the texture data will be
3592 subject to conversion, swizzling and scaling as required to yield
3593 the specified data type from the physical data format of the bound
3596 If the RAW keyword is specified, no channel conversion will be
3597 performed: the values read for each of the channels (X,Y,Z,W) will
3598 correspond to consecutive words in the same order and format
3599 they're found in memory. No element-to-address conversion will be
3600 performed either: the value of the provided X coordinate will be
3601 interpreted in byte units instead of texel units. The result of
3602 accessing a misaligned address is undefined.
3604 Usage of the STORE opcode is only allowed if the WR (writable) flag
3607 Hardware Atomic Register File
3608 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
3610 Hardware atomics are declared as a 2D array with an optional array id.
3612 The first member of the dimension is the buffer resource the atomic
3614 The second member is a range into the buffer resource, either for
3615 one or multiple counters. If this is an array, the declaration will have
3618 Each counter is 4 bytes in size, and index and ranges are in counters not bytes.
3622 This declares two atomics, one at the start of the buffer and one in the
3627 DCL HWATOMIC[1][1..3], ARRAY(1)
3629 This declares 5 atomics, one in buffer 0 at 0,
3630 one in buffer 1 at 0, and an array of 3 atomics in
3631 the buffer 1, starting at 1.
3634 ^^^^^^^^^^^^^^^^^^^^^^^^
3636 Properties are general directives that apply to the whole TGSI program.
3641 Specifies the fragment shader TGSI_SEMANTIC_POSITION coordinate origin.
3642 The default value is UPPER_LEFT.
3644 If UPPER_LEFT, the position will be (0,0) at the upper left corner and
3645 increase downward and rightward.
3646 If LOWER_LEFT, the position will be (0,0) at the lower left corner and
3647 increase upward and rightward.
3649 OpenGL defaults to LOWER_LEFT, and is configurable with the
3650 GL_ARB_fragment_coord_conventions extension.
3652 DirectX 9/10 use UPPER_LEFT.
3654 FS_COORD_PIXEL_CENTER
3655 """""""""""""""""""""
3657 Specifies the fragment shader TGSI_SEMANTIC_POSITION pixel center convention.
3658 The default value is HALF_INTEGER.
3660 If HALF_INTEGER, the fractionary part of the position will be 0.5
3661 If INTEGER, the fractionary part of the position will be 0.0
3663 Note that this does not affect the set of fragments generated by
3664 rasterization, which is instead controlled by half_pixel_center in the
3667 OpenGL defaults to HALF_INTEGER, and is configurable with the
3668 GL_ARB_fragment_coord_conventions extension.
3670 DirectX 9 uses INTEGER.
3671 DirectX 10 uses HALF_INTEGER.
3673 FS_COLOR0_WRITES_ALL_CBUFS
3674 """"""""""""""""""""""""""
3675 Specifies that writes to the fragment shader color 0 are replicated to all
3676 bound cbufs. This facilitates OpenGL's fragColor output vs fragData[0] where
3677 fragData is directed to a single color buffer, but fragColor is broadcast.
3680 """"""""""""""""""""""""""
3681 If this property is set on the program bound to the shader stage before the
3682 fragment shader, user clip planes should have no effect (be disabled) even if
3683 that shader does not write to any clip distance outputs and the rasterizer's
3684 clip_plane_enable is non-zero.
3685 This property is only supported by drivers that also support shader clip
3687 This is useful for APIs that don't have UCPs and where clip distances written
3688 by a shader cannot be disabled.
3693 Specifies the number of times a geometry shader should be executed for each
3694 input primitive. Each invocation will have a different
3695 TGSI_SEMANTIC_INVOCATIONID system value set. If not specified, assumed to
3698 VS_WINDOW_SPACE_POSITION
3699 """"""""""""""""""""""""""
3700 If this property is set on the vertex shader, the TGSI_SEMANTIC_POSITION output
3701 is assumed to contain window space coordinates.
3702 Division of X,Y,Z by W and the viewport transformation are disabled, and 1/W is
3703 directly taken from the 4-th component of the shader output.
3704 Naturally, clipping is not performed on window coordinates either.
3705 The effect of this property is undefined if a geometry or tessellation shader
3711 The number of vertices written by the tessellation control shader. This
3712 effectively defines the patch input size of the tessellation evaluation shader
3718 This sets the tessellation primitive mode, one of ``PIPE_PRIM_TRIANGLES``,
3719 ``PIPE_PRIM_QUADS``, or ``PIPE_PRIM_LINES``. (Unlike in GL, there is no
3720 separate isolines settings, the regular lines is assumed to mean isolines.)
3725 This sets the spacing mode of the tessellation generator, one of
3726 ``PIPE_TESS_SPACING_*``.
3731 This sets the vertex order to be clockwise if the value is 1, or
3732 counter-clockwise if set to 0.
3737 If set to a non-zero value, this turns on point mode for the tessellator,
3738 which means that points will be generated instead of primitives.
3740 NUM_CLIPDIST_ENABLED
3741 """"""""""""""""""""
3743 How many clip distance scalar outputs are enabled.
3745 NUM_CULLDIST_ENABLED
3746 """"""""""""""""""""
3748 How many cull distance scalar outputs are enabled.
3750 FS_EARLY_DEPTH_STENCIL
3751 """"""""""""""""""""""
3753 Whether depth test, stencil test, and occlusion query should run before
3754 the fragment shader (regardless of fragment shader side effects). Corresponds
3755 to GLSL early_fragment_tests.
3760 Which shader stage will MOST LIKELY follow after this shader when the shader
3761 is bound. This is only a hint to the driver and doesn't have to be precise.
3762 Only set for VS and TES.
3764 CS_FIXED_BLOCK_WIDTH / HEIGHT / DEPTH
3765 """""""""""""""""""""""""""""""""""""
3767 Threads per block in each dimension, if known at compile time. If the block size
3768 is known all three should be at least 1. If it is unknown they should all be set
3774 The MUL TGSI operation (FP32 multiplication) will return 0 if either
3775 of the operands are equal to 0. That means that 0 * Inf = 0. This
3776 should be set the same way for an entire pipeline. Note that this
3777 applies not only to the literal MUL TGSI opcode, but all FP32
3778 multiplications implied by other operations, such as MAD, FMA, DP2,
3779 DP3, DP4, DST, LOG, LRP, and possibly others. If there is a
3780 mismatch between shaders, then it is unspecified whether this behavior
3783 FS_POST_DEPTH_COVERAGE
3784 """"""""""""""""""""""
3786 When enabled, the input for TGSI_SEMANTIC_SAMPLEMASK will exclude samples
3787 that have failed the depth/stencil tests. This is only valid when
3788 FS_EARLY_DEPTH_STENCIL is also specified.
3791 Texture Sampling and Texture Formats
3792 ------------------------------------
3794 This table shows how texture image components are returned as (x,y,z,w) tuples
3795 by TGSI texture instructions, such as :opcode:`TEX`, :opcode:`TXD`, and
3796 :opcode:`TXP`. For reference, OpenGL and Direct3D conventions are shown as
3799 +--------------------+--------------+--------------------+--------------+
3800 | Texture Components | Gallium | OpenGL | Direct3D 9 |
3801 +====================+==============+====================+==============+
3802 | R | (r, 0, 0, 1) | (r, 0, 0, 1) | (r, 1, 1, 1) |
3803 +--------------------+--------------+--------------------+--------------+
3804 | RG | (r, g, 0, 1) | (r, g, 0, 1) | (r, g, 1, 1) |
3805 +--------------------+--------------+--------------------+--------------+
3806 | RGB | (r, g, b, 1) | (r, g, b, 1) | (r, g, b, 1) |
3807 +--------------------+--------------+--------------------+--------------+
3808 | RGBA | (r, g, b, a) | (r, g, b, a) | (r, g, b, a) |
3809 +--------------------+--------------+--------------------+--------------+
3810 | A | (0, 0, 0, a) | (0, 0, 0, a) | (0, 0, 0, a) |
3811 +--------------------+--------------+--------------------+--------------+
3812 | L | (l, l, l, 1) | (l, l, l, 1) | (l, l, l, 1) |
3813 +--------------------+--------------+--------------------+--------------+
3814 | LA | (l, l, l, a) | (l, l, l, a) | (l, l, l, a) |
3815 +--------------------+--------------+--------------------+--------------+
3816 | I | (i, i, i, i) | (i, i, i, i) | N/A |
3817 +--------------------+--------------+--------------------+--------------+
3818 | UV | XXX TBD | (0, 0, 0, 1) | (u, v, 1, 1) |
3819 | | | [#envmap-bumpmap]_ | |
3820 +--------------------+--------------+--------------------+--------------+
3821 | Z | XXX TBD | (z, z, z, 1) | (0, z, 0, 1) |
3822 | | | [#depth-tex-mode]_ | |
3823 +--------------------+--------------+--------------------+--------------+
3824 | S | (s, s, s, s) | unknown | unknown |
3825 +--------------------+--------------+--------------------+--------------+
3827 .. [#envmap-bumpmap] http://www.opengl.org/registry/specs/ATI/envmap_bumpmap.txt
3828 .. [#depth-tex-mode] the default is (z, z, z, 1) but may also be (0, 0, 0, z)
3829 or (z, z, z, z) depending on the value of GL_DEPTH_TEXTURE_MODE.