mesa/src/gallium/docs/source/tgsi.rst

TGSI
====

TGSI, Tungsten Graphics Shader Instructions, is an intermediate language
for describing shaders. Since Gallium is inherently shaderful, shaders are
an important part of the API. TGSI is the only intermediate representation
used by all drivers.

From GL_NV_vertex_program
-------------------------


ARL - Address Register Load

.. math::

  dst.x = \lfloor src.x\rfloor

  dst.y = \lfloor src.y\rfloor

  dst.z = \lfloor src.z\rfloor

  dst.w = \lfloor src.w\rfloor


MOV - Move

.. math::

  dst.x = src.x

  dst.y = src.y

  dst.z = src.z

  dst.w = src.w


LIT - Light Coefficients

.. math::

  dst.x = 1

  dst.y = max(src.x, 0)

  dst.z = (src.x > 0) ? max(src.y, 0)^{clamp(src.w, -128, 128))} : 0

  dst.w = 1


RCP - Reciprocal

.. math::

  dst.x = \frac{1}{src.x}

  dst.y = \frac{1}{src.x}

  dst.z = \frac{1}{src.x}

  dst.w = \frac{1}{src.x}


RSQ - Reciprocal Square Root

.. math::

  dst.x = \frac{1}{\sqrt{|src.x|}}

  dst.y = \frac{1}{\sqrt{|src.x|}}

  dst.z = \frac{1}{\sqrt{|src.x|}}

  dst.w = \frac{1}{\sqrt{|src.x|}}


EXP - Approximate Exponential Base 2

.. math::

  dst.x = 2^{\lfloor src.x\rfloor}

  dst.y = src.x - \lfloor src.x\rfloor

  dst.z = 2^{src.x}

  dst.w = 1


LOG - Approximate Logarithm Base 2

.. math::

  dst.x = \lfloor\log_2{|src.x|}\rfloor

  dst.y = \frac{|src.x|}{2^{\lfloor\log_2{|src.x|}\rfloor}}

  dst.z = \log_2{|src.x|}

  dst.w = 1


MUL - Multiply

.. math::

  dst.x = src0.x \times src1.x

  dst.y = src0.y \times src1.y

  dst.z = src0.z \times src1.z

  dst.w = src0.w \times src1.w


ADD - Add

.. math::

  dst.x = src0.x + src1.x

  dst.y = src0.y + src1.y

  dst.z = src0.z + src1.z

  dst.w = src0.w + src1.w


DP3 - 3-component Dot Product

.. math::

  dst.x = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z

  dst.y = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z

  dst.z = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z

  dst.w = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z


DP4 - 4-component Dot Product

.. math::

  dst.x = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z + src0.w \times src1.w

  dst.y = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z + src0.w \times src1.w

  dst.z = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z + src0.w \times src1.w

  dst.w = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z + src0.w \times src1.w


DST - Distance Vector

.. math::

  dst.x = 1

  dst.y = src0.y \times src1.y

  dst.z = src0.z

  dst.w = src1.w


MIN - Minimum

.. math::

  dst.x = min(src0.x, src1.x)

  dst.y = min(src0.y, src1.y)

  dst.z = min(src0.z, src1.z)

  dst.w = min(src0.w, src1.w)


MAX - Maximum

.. math::

  dst.x = max(src0.x, src1.x)

  dst.y = max(src0.y, src1.y)

  dst.z = max(src0.z, src1.z)

  dst.w = max(src0.w, src1.w)


SLT - Set On Less Than

.. math::

  dst.x = (src0.x < src1.x) ? 1 : 0

  dst.y = (src0.y < src1.y) ? 1 : 0

  dst.z = (src0.z < src1.z) ? 1 : 0

  dst.w = (src0.w < src1.w) ? 1 : 0


SGE - Set On Greater Equal Than

.. math::

  dst.x = (src0.x >= src1.x) ? 1 : 0

  dst.y = (src0.y >= src1.y) ? 1 : 0

  dst.z = (src0.z >= src1.z) ? 1 : 0

  dst.w = (src0.w >= src1.w) ? 1 : 0


MAD - Multiply And Add

.. math::

  dst.x = src0.x \times src1.x + src2.x

  dst.y = src0.y \times src1.y + src2.y

  dst.z = src0.z \times src1.z + src2.z

  dst.w = src0.w \times src1.w + src2.w


SUB - Subtract

.. math::

  dst.x = src0.x - src1.x

  dst.y = src0.y - src1.y

  dst.z = src0.z - src1.z

  dst.w = src0.w - src1.w


LRP - Linear Interpolate

.. math::

  dst.x = src0.x \times (src1.x - src2.x) + src2.x

  dst.y = src0.y \times (src1.y - src2.y) + src2.y

  dst.z = src0.z \times (src1.z - src2.z) + src2.z

  dst.w = src0.w \times (src1.w - src2.w) + src2.w


CND - Condition

.. math::

  dst.x = (src2.x > 0.5) ? src0.x : src1.x

  dst.y = (src2.y > 0.5) ? src0.y : src1.y

  dst.z = (src2.z > 0.5) ? src0.z : src1.z

  dst.w = (src2.w > 0.5) ? src0.w : src1.w


DP2A - 2-component Dot Product And Add

.. math::

  dst.x = src0.x \times src1.x + src0.y \times src1.y + src2.x

  dst.y = src0.x \times src1.x + src0.y \times src1.y + src2.x

  dst.z = src0.x \times src1.x + src0.y \times src1.y + src2.x

  dst.w = src0.x \times src1.x + src0.y \times src1.y + src2.x


FRAC - Fraction

.. math::

  dst.x = src.x - \lfloor src.x\rfloor

  dst.y = src.y - \lfloor src.y\rfloor

  dst.z = src.z - \lfloor src.z\rfloor

  dst.w = src.w - \lfloor src.w\rfloor


CLAMP - Clamp

.. math::

  dst.x = clamp(src0.x, src1.x, src2.x)

  dst.y = clamp(src0.y, src1.y, src2.y)

  dst.z = clamp(src0.z, src1.z, src2.z)

  dst.w = clamp(src0.w, src1.w, src2.w)


FLR - Floor

This is identical to ARL.

.. math::

  dst.x = \lfloor src.x\rfloor

  dst.y = \lfloor src.y\rfloor

  dst.z = \lfloor src.z\rfloor

  dst.w = \lfloor src.w\rfloor


ROUND - Round

.. math::

  dst.x = round(src.x)

  dst.y = round(src.y)

  dst.z = round(src.z)

  dst.w = round(src.w)


EX2 - Exponential Base 2

.. math::

  dst.x = 2^{src.x}

  dst.y = 2^{src.x}

  dst.z = 2^{src.x}

  dst.w = 2^{src.x}


LG2 - Logarithm Base 2

.. math::

  dst.x = \log_2{src.x}

  dst.y = \log_2{src.x}

  dst.z = \log_2{src.x}

  dst.w = \log_2{src.x}


POW - Power

.. math::

  dst.x = src0.x^{src1.x}

  dst.y = src0.x^{src1.x}

  dst.z = src0.x^{src1.x}

  dst.w = src0.x^{src1.x}

XPD - Cross Product

.. math::

  dst.x = src0.y \times src1.z - src1.y \times src0.z

  dst.y = src0.z \times src1.x - src1.z \times src0.x

  dst.z = src0.x \times src1.y - src1.x \times src0.y

  dst.w = 1


ABS - Absolute

.. math::

  dst.x = |src.x|

  dst.y = |src.y|

  dst.z = |src.z|

  dst.w = |src.w|


RCC - Reciprocal Clamped

XXX cleanup on aisle three

.. math::

  dst.x = (1 / src.x) > 0 ? clamp(1 / src.x, 5.42101e-020, 1.884467e+019) : clamp(1 / src.x, -1.884467e+019, -5.42101e-020)

  dst.y = (1 / src.x) > 0 ? clamp(1 / src.x, 5.42101e-020, 1.884467e+019) : clamp(1 / src.x, -1.884467e+019, -5.42101e-020)

  dst.z = (1 / src.x) > 0 ? clamp(1 / src.x, 5.42101e-020, 1.884467e+019) : clamp(1 / src.x, -1.884467e+019, -5.42101e-020)

  dst.w = (1 / src.x) > 0 ? clamp(1 / src.x, 5.42101e-020, 1.884467e+019) : clamp(1 / src.x, -1.884467e+019, -5.42101e-020)


DPH - Homogeneous Dot Product

.. math::

  dst.x = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z + src1.w

  dst.y = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z + src1.w

  dst.z = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z + src1.w

  dst.w = src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z + src1.w


COS - Cosine

.. math::

  dst.x = \cos{src.x}

  dst.y = \cos{src.x}

  dst.z = \cos{src.x}

  dst.w = \cos{src.w}


DDX - Derivative Relative To X

.. math::

  dst.x = partialx(src.x)

  dst.y = partialx(src.y)

  dst.z = partialx(src.z)

  dst.w = partialx(src.w)


DDY - Derivative Relative To Y

.. math::

  dst.x = partialy(src.x)

  dst.y = partialy(src.y)

  dst.z = partialy(src.z)

  dst.w = partialy(src.w)


KILP - Predicated Discard

  discard


PK2H - Pack Two 16-bit Floats

  TBD


PK2US - Pack Two Unsigned 16-bit Scalars

  TBD


PK4B - Pack Four Signed 8-bit Scalars

  TBD


PK4UB - Pack Four Unsigned 8-bit Scalars

  TBD


RFL - Reflection Vector

.. math::

  dst.x = 2 \times (src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z) / (src0.x \times src0.x + src0.y \times src0.y + src0.z \times src0.z) \times src0.x - src1.x

  dst.y = 2 \times (src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z) / (src0.x \times src0.x + src0.y \times src0.y + src0.z \times src0.z) \times src0.y - src1.y

  dst.z = 2 \times (src0.x \times src1.x + src0.y \times src1.y + src0.z \times src1.z) / (src0.x \times src0.x + src0.y \times src0.y + src0.z \times src0.z) \times src0.z - src1.z

  dst.w = 1

Considered for removal.


SEQ - Set On Equal

.. math::

  dst.x = (src0.x == src1.x) ? 1 : 0
  dst.y = (src0.y == src1.y) ? 1 : 0
  dst.z = (src0.z == src1.z) ? 1 : 0
  dst.w = (src0.w == src1.w) ? 1 : 0


SFL - Set On False

.. math::

  dst.x = 0
  dst.y = 0
  dst.z = 0
  dst.w = 0

Considered for removal.

SGT - Set On Greater Than

.. math::

  dst.x = (src0.x > src1.x) ? 1 : 0
  dst.y = (src0.y > src1.y) ? 1 : 0
  dst.z = (src0.z > src1.z) ? 1 : 0
  dst.w = (src0.w > src1.w) ? 1 : 0


SIN - Sine

.. math::

  dst.x = \sin{src.x}

  dst.y = \sin{src.x}

  dst.z = \sin{src.x}

  dst.w = \sin{src.w}


SLE - Set On Less Equal Than

.. math::

  dst.x = (src0.x <= src1.x) ? 1 : 0
  dst.y = (src0.y <= src1.y) ? 1 : 0
  dst.z = (src0.z <= src1.z) ? 1 : 0
  dst.w = (src0.w <= src1.w) ? 1 : 0


SNE - Set On Not Equal

.. math::

  dst.x = (src0.x != src1.x) ? 1 : 0
  dst.y = (src0.y != src1.y) ? 1 : 0
  dst.z = (src0.z != src1.z) ? 1 : 0
  dst.w = (src0.w != src1.w) ? 1 : 0


STR - Set On True

.. math::

  dst.x = 1
  dst.y = 1
  dst.z = 1
  dst.w = 1


TEX - Texture Lookup

  TBD


TXD - Texture Lookup with Derivatives

  TBD


TXP - Projective Texture Lookup

  TBD


UP2H - Unpack Two 16-Bit Floats

  TBD

  Considered for removal.

UP2US - Unpack Two Unsigned 16-Bit Scalars

  TBD

  Considered for removal.

UP4B - Unpack Four Signed 8-Bit Values

  TBD

  Considered for removal.

UP4UB - Unpack Four Unsigned 8-Bit Scalars

  TBD

  Considered for removal.

X2D - 2D Coordinate Transformation

.. math::

  dst.x = src0.x + src1.x \times src2.x + src1.y \times src2.y
  dst.y = src0.y + src1.x \times src2.z + src1.y \times src2.w
  dst.z = src0.x + src1.x \times src2.x + src1.y \times src2.y
  dst.w = src0.y + src1.x \times src2.z + src1.y \times src2.w

Considered for removal.


GL_NV_vertex_program2
--------------------------


ARA - Address Register Add

  TBD

  Considered for removal.

ARR - Address Register Load With Round

.. math::

  dst.x = round(src.x)

  dst.y = round(src.y)

  dst.z = round(src.z)

  dst.w = round(src.w)


BRA - Branch

  pc = target

  Considered for removal.

CAL - Subroutine Call

  push(pc)
  pc = target


RET - Subroutine Call Return

  pc = pop()

  Potential restrictions:  
  \times Only occurs at end of function.

SSG - Set Sign

.. math::

  dst.x = (src.x > 0) ? 1 : (src.x < 0) ? -1 : 0

  dst.y = (src.y > 0) ? 1 : (src.y < 0) ? -1 : 0

  dst.z = (src.z > 0) ? 1 : (src.z < 0) ? -1 : 0

  dst.w = (src.w > 0) ? 1 : (src.w < 0) ? -1 : 0


CMP - Compare

.. math::

  dst.x = (src0.x < 0) ? src1.x : src2.x

  dst.y = (src0.y < 0) ? src1.y : src2.y

  dst.z = (src0.z < 0) ? src1.z : src2.z

  dst.w = (src0.w < 0) ? src1.w : src2.w


KIL - Conditional Discard

.. math::

  if (src.x < 0 || src.y < 0 || src.z < 0 || src.w < 0)
    discard
  endif


SCS - Sine Cosine

.. math::

  dst.x = \cos{src.x}

  dst.y = \sin{src.x}

  dst.z = 0

  dst.y = 1


TXB - Texture Lookup With Bias

  TBD


NRM - 3-component Vector Normalise

.. math::

  dst.x = src.x / (src.x \times src.x + src.y \times src.y + src.z \times src.z)

  dst.y = src.y / (src.x \times src.x + src.y \times src.y + src.z \times src.z)

  dst.z = src.z / (src.x \times src.x + src.y \times src.y + src.z \times src.z)

  dst.w = 1


DIV - Divide

.. math::

  dst.x = \frac{src0.x}{src1.x}

  dst.y = \frac{src0.y}{src1.y}

  dst.z = \frac{src0.z}{src1.z}

  dst.w = \frac{src0.w}{src1.w}


DP2 - 2-component Dot Product

.. math::

  dst.x = src0.x \times src1.x + src0.y \times src1.y

  dst.y = src0.x \times src1.x + src0.y \times src1.y

  dst.z = src0.x \times src1.x + src0.y \times src1.y

  dst.w = src0.x \times src1.x + src0.y \times src1.y


TXL - Texture Lookup With LOD

  TBD


BRK - Break

  TBD


IF - If

  TBD


BGNFOR - Begin a For-Loop

  dst.x = floor(src.x)
  dst.y = floor(src.y)
  dst.z = floor(src.z)

  if (dst.y <= 0)
    pc = [matching ENDFOR] + 1
  endif

  Note: The destination must be a loop register.
        The source must be a constant register.

  Considered for cleanup / removal.


REP - Repeat

  TBD


ELSE - Else

  TBD


ENDIF - End If

  TBD


ENDFOR - End a For-Loop

  dst.x = dst.x + dst.z
  dst.y = dst.y - 1.0

  if (dst.y > 0)
    pc = [matching BGNFOR instruction] + 1
  endif

  Note: The destination must be a loop register.

  Considered for cleanup / removal.

ENDREP - End Repeat

  TBD


PUSHA - Push Address Register On Stack

  push(src.x)
  push(src.y)
  push(src.z)
  push(src.w)

  Considered for cleanup / removal.

POPA - Pop Address Register From Stack

  dst.w = pop()
  dst.z = pop()
  dst.y = pop()
  dst.x = pop()

  Considered for cleanup / removal.


GL_NV_gpu_program4
------------------------

Support for these opcodes indicated by a special pipe capability bit (TBD).

CEIL - Ceiling

.. math::

  dst.x = \lceil src.x\rceil

  dst.y = \lceil src.y\rceil

  dst.z = \lceil src.z\rceil

  dst.w = \lceil src.w\rceil


I2F - Integer To Float

.. math::

  dst.x = (float) src.x

  dst.y = (float) src.y

  dst.z = (float) src.z

  dst.w = (float) src.w


NOT - Bitwise Not

.. math::

  dst.x = ~src.x

  dst.y = ~src.y

  dst.z = ~src.z

  dst.w = ~src.w


TRUNC - Truncate

XXX how is this different from floor?

.. math::

  dst.x = trunc(src.x)

  dst.y = trunc(src.y)

  dst.z = trunc(src.z)

  dst.w = trunc(src.w)


SHL - Shift Left

.. math::

  dst.x = src0.x << src1.x

  dst.y = src0.y << src1.x

  dst.z = src0.z << src1.x

  dst.w = src0.w << src1.x


SHR - Shift Right

.. math::

  dst.x = src0.x >> src1.x

  dst.y = src0.y >> src1.x

  dst.z = src0.z >> src1.x

  dst.w = src0.w >> src1.x


AND - Bitwise And

.. math::

  dst.x = src0.x & src1.x

  dst.y = src0.y & src1.y

  dst.z = src0.z & src1.z

  dst.w = src0.w & src1.w


OR - Bitwise Or

.. math::

  dst.x = src0.x | src1.x

  dst.y = src0.y | src1.y

  dst.z = src0.z | src1.z

  dst.w = src0.w | src1.w


MOD - Modulus

.. math::

  dst.x = src0.x \bmod src1.x

  dst.y = src0.y \bmod src1.y

  dst.z = src0.z \bmod src1.z

  dst.w = src0.w \bmod src1.w


XOR - Bitwise Xor

.. math::

  dst.x = src0.x ^ src1.x

  dst.y = src0.y ^ src1.y

  dst.z = src0.z ^ src1.z

  dst.w = src0.w ^ src1.w


SAD - Sum Of Absolute Differences

.. math::

  dst.x = |src0.x - src1.x| + src2.x

  dst.y = |src0.y - src1.y| + src2.y

  dst.z = |src0.z - src1.z| + src2.z

  dst.w = |src0.w - src1.w| + src2.w


TXF - Texel Fetch

  TBD


TXQ - Texture Size Query

  TBD


CONT - Continue

  TBD


GL_NV_geometry_program4
-----------------------------


EMIT - Emit

  TBD


ENDPRIM - End Primitive

  TBD


GLSL
----------


BGNLOOP - Begin a Loop

  TBD


BGNSUB - Begin Subroutine

  TBD


ENDLOOP - End a Loop

  TBD


ENDSUB - End Subroutine

  TBD



NOP - No Operation

 Do nothing.

NRM4 - 4-component Vector Normalise

.. math::

  dst.x = \frac{src.x}{src.x \times src.x + src.y \times src.y + src.z \times src.z + src.w \times src.w}

  dst.y = \frac{src.y}{src.x \times src.x + src.y \times src.y + src.z \times src.z + src.w \times src.w}

  dst.z = \frac{src.z}{src.x \times src.x + src.y \times src.y + src.z \times src.z + src.w \times src.w}

  dst.w = \frac{src.w}{src.x \times src.x + src.y \times src.y + src.z \times src.z + src.w \times src.w}


ps_2_x
------------


CALLNZ - Subroutine Call If Not Zero

  TBD


IFC - If

  TBD


BREAKC - Break Conditional

  TBD


Explanation of symbols used
==============================


Functions
--------------


  :math:`|x|`       Absolute value of `x`.

  :math:`\lceil x \rceil` Ceiling of `x`.

  clamp(x,y,z)      Clamp x between y and z.
                    (x < y) ? y : (x > z) ? z : x

  :math:`\lfloor x\rfloor` Floor of `x`.

  :math:`\log_2{x}` Logarithm of `x`, base 2.

  max(x,y)          Maximum of x and y.
                    (x > y) ? x : y

  min(x,y)          Minimum of x and y.
                    (x < y) ? x : y

  partialx(x)       Derivative of x relative to fragment's X.

  partialy(x)       Derivative of x relative to fragment's Y.

  pop()             Pop from stack.

  :math:`x^y`       `x` to the power `y`.

  push(x)           Push x on stack.

  round(x)          Round x.

  trunc(x)          Truncate x.


Keywords
-------------


  discard           Discard fragment.

  dst               First destination register.

  dst0              First destination register.

  pc                Program counter.

  src               First source register.

  src0              First source register.

  src1              Second source register.

  src2              Third source register.

  target            Label of target instruction.


Other tokens
===============


Declaration Semantic
-------------------------


  Follows Declaration token if Semantic bit is set.

  Since its purpose is to link a shader with other stages of the pipeline,
  it is valid to follow only those Declaration tokens that declare a register
  either in INPUT or OUTPUT file.

  SemanticName field contains the semantic name of the register being declared.
  There is no default value.

  SemanticIndex is an optional subscript that can be used to distinguish
  different register declarations with the same semantic name. The default value
  is 0.

  The meanings of the individual semantic names are explained in the following
  sections.


FACE
^^^^

  Valid only in a fragment shader INPUT declaration.

  FACE.x is negative when the primitive is back facing. FACE.x is positive
  when the primitive is front facing.