This immediates are accessible in (almost) any instruction, provided the immediate mode is kept to the default. They optimize for the most common immediate values; any immediate listed here may be used without taking up a uniform slot or a register. Most integer instructions can access separate half-words and individual bytes via swizzles on the source. 0x00000000 0xFFFFFFFF 0x7FFFFFFF 0xFAFCFDFE 0x01000000 0x80002000 0x70605030 0xC0B0A090 0x03020100 0x07060504 0x0B0A0908 0x0F0E0D0C 0x13121110 0x17161514 0x1B1A1918 0x1F1E1D1C 0x3F800000 0x3DCCCCCD 0x3EA2F983 0x3F317218 0x40490FDB 0x00000000 0x477FFF00 0x5C005BF8 0x2E660000 0x34000000 0x38000000 0x3C000000 0x40000000 0x44000000 0x48000000 0x42480000 Every Valhall instruction can wait on dependency slots. A few special flows are available, specified in the instruction metadata from this enum. The `wait0126` flow is required to wait on dependency slot #6 and should be set on the instruction immediately preceding `ATEST`. The `wait` flow should be set for barriers. The `discard` flow only applies to fragment shaders and is used to terminate helper invocations, it should be set as early as possible after helper invocations are no longer needed as determined by data flow analysis. The `end` flow is used to terminate the shader, although it may be overloaded by the `BLEND` instruction. The `reconverge` flow is required on any instruction immediately preceding a possible change to the mask of active threads in a subgroup. This includes all divergent branches, but it also includes the final instruction at the end of any basic block where the immediate successor (fallthrough) is the target of a divergent branch. none wait0 wait1 wait01 wait2 wait02 wait12 wait012 wait0126 wait reconverge discard end Situated between the immediates hard-coded in the hardware and the uniforms defined purely in software, Valhall has a some special "constants" passing through data structures. These are encoded like the table of immediates, as if special constant $i$ were lookup table entry $32 + i$. warp_id framebuffer_size atest_datum sample blend_descriptor_0 blend_descriptor_1 blend_descriptor_2 blend_descriptor_3 blend_descriptor_4 blend_descriptor_5 blend_descriptor_6 blend_descriptor_7 Situated between the immediates hard-coded in the hardware and the uniforms defined purely in software, Valhall has a some special "constants" passing through data structures. These are encoded like the table of immediates, as if special constant $i$ were lookup table entry $32 + i$. thread_local_pointer workgroup_local_pointer resource_table_pointer Situated between the immediates hard-coded in the hardware and the uniforms defined purely in software, Valhall has a some special "constants" passing through data structures. These are encoded like the table of immediates, as if special constant $i$ were lookup table entry $32 + i$. lane_id core_id program_counter b0123 b3210 b0101 b2323 b0000 b1111 b2222 b3333 b2301 b1032 b0011 b2233 Used to select the 2 bytes for shifts of 16-bit vectors b02 b00 b11 b22 b33 b01 b23 Used to select the 2 bytes to convert for conversions from 8-bit vectors to 16-bit vectors b00 b10 b20 b30 b01 b11 b21 b31 b02 b12 b22 b32 b03 b13 b23 b33 h00 h10 h01 h11 b00 b20 b02 b22 b11 b31 b13 b33 b01 b23 none h0 h1 b0 b1 b2 b3 none h0 h1 b0 b1 b2 b3 w0 b0 b1 b2 b3 Used for the lane select of `BRANCHZ`. To use an 8-bit condition, a separate `ICMP` is required to cast to 16-bit. none h0 h1 and lowbits h0 h1 b0 b1 b2 b3 h0 h1 w0 d0 h0 h1 w0 d0 identity w0 d0 identity identity identity identity Corresponds to IEEE 754 rounding modes rte rtp rtn rtz Comparison instructions like `FCMP` return a boolean but may encode this boolean in a variety of ways. `i1` gives a OpenGL style `0/1` boolean. `m1` gives a Direct3D style `0/~0` boolean. `f1` gives a floating-point `0.0f / 1.0f` boolean. Switching between these modes is useful to fold a boolean type convert into a comparison. `u1` is used internally to implement 64-bit comparisons. i1 f1 m1 u1 none h0 h1 Clamp applied to the destination of a floating-point instruction. Note the clamps may be decomposed as two independent bits for `clamp_0_inf` and `clamp_m1_1`, with `clamp_0_1` arising as the composition of `clamp_0_inf` and `clamp_m1_1` in either order. Clamps are implemented per the SPIR-V specification: $$\text{clamp} \; (x, \ell, h) = \min( \max( x, \ell ), h)$$ The min/max functions return the other operand if one operand is NaN, and compare $-0 < +0$. That means the following identities hold for Valhall clamps: \begin{align*} \text{clamp}(-0.0, 0.0, 1.0) & = +0.0 \\ \text{clamp}(-\text{NaN}, 0.0, 1.0) & = +0.0 \\ \text{clamp}(\text{NaN}, 0.0, 1.0) & = +0.0 \\ & \\ \text{clamp}(-0.0, -1.0, 1.0) & = -0.0 \\ \text{clamp}(\text{NaN}, -1.0, 1.0) & = -1.0 \\ \text{clamp}(-\text{NaN}, -1.0, 1.0) & = -1.0 \\ & \\ \max(\text{NaN}, 0.0) & = +0.0 \\ \max(-\text{NaN}, 0.0) & = +0.0 \\ \max(-0.0, 0.0) & = +0.0 \\ \end{align*} This behaviour is consistent with the FMin/FMax/FClamp and NMin/NMax/NClamp rules prescribed by SPIR-V and governed by IEEE-754. As a consequence, substituting these clamps for equivalent minimum/maximum exprssions is legal even with strict floating point rules. none clamp_0_inf clamp_m1_1 clamp_0_1 Condition code. Type must be inferred from the instruction. IEEE 754 total ordering only applies to floating point compares. "Not equal" and "greater than or less than" are distinguished by NaN behaviour conforming to the IEEE 754 specification. eq gt ge ne lt le gtlt total Texture dimension. 1d 2d 3d cube Level-of-detail selection mode in a texture instruction. zero computed explicit computed_bias grdesc Format of data loaded to / stored from registers for general memory access. auto f32 f16 s32 s16 u32 u16 sr0 sr1 sr2 sr3 sr4 sr5 sr6 sr7 write1 write2 write3 write4 write5 write6 write7 write8 r g rg b rb gb rgb a ra ga rga ba rba gba rgba gather4_r gather4_g gather4_b gather4_a Unsized type, part of a register format. f u s Untyped size, part of a register format. 16 32 Size of results for varying texture instructions. For dual 16-bit results use "16-bit". 16 32 16.32 32.32 Number of channels loaded/stored for general memory access. none v2 v3 v4 Dependency slot set on a message-passing instruction that writes to registers. Before reading the destination, a future instruction must wait on the specified slot. Slot #7 is for `BARRIER` instructions only. slot0 slot1 slot2 slot7 Memory access hint for a `LOAD` or `STORE` instruction. none istream estream force Selects the effective subgroup size from subgroup operations. The hardware warps are sixteen threads on Valhall, but subdividing a warp may be useful for API requirements. In particular, derivatives may be calculated with quads (four threads). subgroup2 subgroup4 subgroup8 subgroup16 Acts as a modifier on the lane specificier for a `CLPER` instruction. The `accumulate` mode is required for efficient subgroup reductions. none xor accumulate shift Accesses to inactive lanes (due to divergence) in a subgroup is generally undefined in APIs. However, the results of permuting with an inactive lane with `CLPER.i32` are well-defined in Valhall: they return one of the following values, as specified in the `CLPER.i32` instructions. Sometimes certain values enable small optimizations. zero umax i1 v2i1 smin smax v2smin v2smax v4smin v4smax f1 v2f1 infn inf v2infn v2inf Condition to use for a `MUX` instruction. `neg` checks the sign bit, `int_zero` compares to `0x00000000`, `fp_zero` compares to $\pm 0.0$ as an IEEE 754 float, and `bit` checks each bit separately. The `bit` mode acts like an imaginary `CSEL.v32u1` instruction, and implements `bitselect()` in OpenCL. neg int_zero fp_zero bit Varying interpolation mode, for choosing the correct sample to interpolate at, allowing the `sample` and `centroid` qualifiers to be implemented, as well as the `interpolateAt*` functions. center centroid sample explicit The Valhall GPU maintains hidden state when interpolating varyings, to allow reusing sample location calculations. The update mode of a varying load controls this hidden state. store retrieve clobber For fused varying/texture instructions, only the following specific combinations of sample and update modes are permitted. center_store centroid_store sample_store explicit_store center_clobber sample_clobber retrieve In-memory format of varyings. Note: src_flat32 is only valid with 32-bit varying instructions and src_flat16 is only valid with 16-bit varying instructions. src_flat32 src_flat16 src_f32 src_f16 Operation performed in a general computational atomic instruction. aadd asmin asmax aumin aumax aand aor axor axchg Operation performed in a computational atomic-with-1 instruction. ainc adec aumax1 asmax1 aor1 Do nothing. Useful at the start of a block for waiting on slots required by the first actual instruction of the block, to reconcile dependencies after a branch. Also useful as the sole instruction of an empty shader. Branches to a specified relative offset if its source is nonzero (default) or if its source is zero (if `.eq` is set). The offset is 27-bits and sign-extended, giving an effective range of ±26-bits. The offset is specified in units of instructions, relative to the *next* instruction. Positive offsets may be interpreted as "number of instructions to skip". Since Valhall instructions are 8 bytes, this operates as: $$PC := \begin{cases} PC + 8 \cdot (\text{offset} \; + 1) & \text{if} \; \text{src} \stackrel{?}{=} 0 \\ PC + 8 & \text{otherwise} \end{cases}$$ Used with comparison instructions to implement control flow. Tie the source to a nonzero constant to implement a jump. May introduce divergence, so generally requires `.reconverge` flow control. Value to compare against zero Evaluates the given condition, and if it passes, discards the current fragment and terminates the thread. Only valid in a **fragment** shader. Left value to compare Right value to compare Jump to an indirectly specified (absolute or relative) address. Used to jump to blend shaders at the end of a fragment shader. Value to compare against zero Branch target General-purpose barrier. Must use slot #7. Must be paired with a `.wait` flow on the instruction. Evaluates the given condition and outputs either the true source or the false source. Left value to compare Right value to compare Return value if true Return value if false Evaluates the given condition and outputs either the true source or the false source. Valhall lacks integer minimum/maximum instructions. `CSEL` instructions with tied operands form the canonical implementations of these instructions. Similarly, the integer $\text{sign}$ function is canonically implemented with a pair of `CSEL` instructions. Left value to compare Right value to compare Return value if true Return value if false Interpolates a given varying from hardware buffer Interpolates a given varying from hardware buffer Interpolates a given varying from a software buffer Varying index and table Interpolates a given varying from a software buffer Fetches a given varying from a software buffer Varying index and table Fetches a given varying from a software buffer Load `vecsize` components from the attribute descriptor at entry `index` of resource table `table` at index (vertex ID, instance ID), converting to the specified register format. Vertex ID Instance ID Load `vecsize` components from the attribute descriptor at the specified location at index (vertex ID, instance ID), converting to the specified register format. The index must not diverge within a warp. Vertex ID Instance ID Index and table Load `vecsize` components from the texture descriptor at entry `index` of resource table `table`, converting to the specified register format. X/Y coordinates (16:16) Z/W coordinates (16:16) Load `vecsize` components from the texture descriptor at the specified location at index, converting to the specified register format. X/Y coordinates (16:16) Z/W coordinates (16:16) Index and table Load the effective address of an attribute specified with the given immediate index. Returns three staging register: the low/high 32-bits of the address and the internal conversion descriptor. Vertex index Instance index Load the effective address of an attribute specified with the given index. Returns three staging register: the low/high 32-bits of the address and the internal conversion descriptor. Vertex index Instance index Attribute index and table Load the effective address of a texel from the image specified with the given immediate index. Returns three staging registers: the low/high 32-bits of the address and the internal conversion descriptor. The format of the internal conversion descriptor is compatible with Bifrost but omits the register format, as this is specified with the ST_CVT instruction on Valhall. Coordinates are specified as 16-bit integers, packed into 32-bit sources. X/Y coordinates (16:16) Z/W coordinates (16:16) Load the effective address of a texel from the image specified with the given index. Returns three staging register: the low/high 32-bits of the address and the internal conversion descriptor. The format of the internal conversion descriptor is compatible with Bifrost but omits the register format, as this is specified with the ST_CVT instruction on Valhall. Coordinates are specified as 16-bit integers, packed into 32-bit sources. X/Y coordinates (16:16) Z/W coordinates (16:16) Index and table Loads a buffer descriptor. If bits 25...31 of the mode descriptor are all-ones, load from the buffer descriptors in the table indexed by the bottom byte of the mode descriptor. If they are all zeroes, load the contents of the buffer in the first table indexed by the bottom byte of the mode descriptor. Address to load from after adding offset Mode descriptor Loads a buffer descriptor. If bits 25...31 of the mode descriptor are all-ones, load from the buffer descriptors in the table indexed by the bottom byte of the mode descriptor. If they are all zeroes, load the contents of the buffer in the first table indexed by the bottom byte of the mode descriptor. Byte offset Mode descriptor Loads a buffer descriptor. If bits 25...31 of the mode descriptor are all-ones, load from the buffer descriptors in the table indexed by the bottom byte of the mode descriptor. If they are all zeroes, load the contents of the buffer in the first table indexed by the bottom byte of the mode descriptor. Byte offset Mode descriptor Loads a buffer descriptor. If bits 25...31 of the mode descriptor are all-ones, load from the buffer descriptors in the table indexed by the bottom byte of the mode descriptor. If they are all zeroes, load the contents of the buffer in the first table indexed by the bottom byte of the mode descriptor. Byte offset Mode descriptor Loads a buffer descriptor. If bits 25...31 of the mode descriptor are all-ones, load from the buffer descriptors in the table indexed by the bottom byte of the mode descriptor. If they are all zeroes, load the contents of the buffer in the first table indexed by the bottom byte of the mode descriptor. Byte offset Mode descriptor Loads a buffer descriptor. If bits 25...31 of the mode descriptor are all-ones, load from the buffer descriptors in the table indexed by the bottom byte of the mode descriptor. If they are all zeroes, load the contents of the buffer in the first table indexed by the bottom byte of the mode descriptor. Byte offset Mode descriptor Loads a buffer descriptor. If bits 25...31 of the mode descriptor are all-ones, load from the buffer descriptors in the table indexed by the bottom byte of the mode descriptor. If they are all zeroes, load the contents of the buffer in the first table indexed by the bottom byte of the mode descriptor. Byte offset Mode descriptor Loads a buffer descriptor. If bits 25...31 of the mode descriptor are all-ones, load from the buffer descriptors in the table indexed by the bottom byte of the mode descriptor. If they are all zeroes, load the contents of the buffer in the first table indexed by the bottom byte of the mode descriptor. Byte offset Mode descriptor Load effective address of a buffer with an immediate offset added. Linear ID Loads from main memory Address to load from after adding offset Loads from main memory Address to load from after adding offset Loads from main memory Address to load from after adding offset Loads from main memory Address to load from after adding offset Loads from main memory Address to load from after adding offset Loads from main memory Address to load from after adding offset Loads from main memory Address to load from after adding offset Loads from main memory Address to load from after adding offset Stores to main memory Address to store to after adding offset Store to memory with data conversion. The address to store to is given in the first source, which must be a 64-bit register (a pair of 32-bit registers). The other source is the conversion descriptor used for the store. Used with LEA_TEX_IMM to implement image stores. 64-bit address to store to Internal conversion descriptor Loads a given render target, specified in the pixel indices descriptor, at a given location and sample, and convert to the format specified in the internal conversion descriptor. Used to implement EXT_framebuffer_fetch and internally in blend shaders. Pixel indices descriptor Coverage mask Conversion descriptor Store to given render target, specified in the pixel indices descriptor, at a given location and sample, and convert to the format specified in the internal conversion descriptor. Used internally in blend shaders. Pixel indices descriptor Coverage mask Conversion descriptor Blends a given render target. This loads the API-specified blend state for the render target from the first source. Blend descriptors are available as special immediates. It then reads the colour to be blended from the first staging register, with the specified vector size and register format as desired. The resulting coverage mask is stored to the second set of staging registers. In the fixed-function path, `BLEND` sends the colour to the blender to be written to the tilebuffer. Then, if the instruction's flow control specifies termination, the fragment program is ended. If it does not specify termination, `BLEND` acts as a relative branch, branching with the offset specified as `target`. This allows the subsequent instructions to be skipped when fixed-function blending is used. Note this implicit branch can never introduce divergence, so `.reconverge` is not required. In the blend shader path, `BLEND` ignores the specified flow control and does not branch to the specified offset. Instead, execution continues normally with the next instruction. The compiler should insert code for calling a blend shader after the `BLEND` instruction unless it is known that a blend shader will never be required. The indirection is required to support both fixed-function and blend shaders efficiently and without shader variants. Blend descriptor Sample coverage Does alpha-to-coverage testing, updating the sample coverage mask. ATEST does not do an implicit discard. It should be executed before the first ZS_EMIT or BLEND instruction. Updated coverage mask Input coverage mask Alpha value (render target 0) Programatically writes out depth, stencil, or both, depending on which modifiers are set. Used to implement gl_FragDepth and gl_FragStencil. Updated coverage mask Depth value Stencil value Input coverage mask Performs the given data conversion. Note that floating-point rounding is handled via the same hardware and therefore shares an encoding. Round mode is specified where it makes sense. Value to convert Performs the given data conversion. Value to convert Performs the given data conversion. Value to convert Performs the given data conversion. Value to convert Converts up with the specified round mode. Value to convert Performs the given data conversion. Value to convert Performs the given data conversion. Value to convert Performs the given rounding, using the convert unit. Value to convert Canonical register-to-register move. Used as a primitive for various bitwise operations. Used as a primitive for various bitwise operations. Used as a primitive for various bitwise operations. 64-bit abs may be constructed in 4 instructions (5 clocks) by checking the sign with `ICMP.s32.lt.m1 hi, 0` and negating based on the result with `IADD.s64` and `LSHIFT_XOR.i32` on each half. Only available as 32-bit. Smaller bitsizes require explicit conversions. 64-bit popcount may be constructed in 3 clocks by separate 32-bit popcounts of each half and a 32-bit add, which is guaranteed not to overflow. Only available as 32-bit. Other bitsizes may be derived with swizzles. For fully featured bitwise operation, see the shift opcodes. For fully featured bitwise operation, see the shift opcodes. Returns the mask of lanes ever active within the warp (subgroup), such that the source is nonzero. The number of work-items in a subgroup is given as the popcount of this value with a nonzero input. An `all()` subgroup operation may be constructed as `WMASK` of the input compared for equality with `WMASK` of an nonzero value. An `any()` subgroup operation may be constructed as `WMASK` of the input compared against zero. Breaks up the floating-point input into its fractional (mantissa) and exponent parts. By default, this is compatible with the `frexp()` function in APIs. With the log/sqrt modifiers, the floating point format is adjusted to be compatible with Valhall's argument reduction for logarithm and square root computation respectively. Performs a given special function. The floating-point reciprocal (`FRCP`) and reciprocal square root (`FRSQ`) instructions may be freely used as-is. The logarithm instruction (`FLOGD.f32`) requires an argument reduction. See the transcendentals section for more information. Like the Bifrost op, `FRSQ_APPROX.f32` does an implicit `FREXPM.f32.sqrt` on the source. Performs a given special function. The trigonometric tables (`FSIN_TABLE.u6` and `FCOS_TABLE.u6`) are crude, requiring both an argument reduction and postprocessing. $A + B$ A B $\min \{ A, B \}$ A B $\max \{ A, B \}$ A B Given a pair of 32-bit floats, output a pair of 16-bit floats packed into a 32-bit destination. A B Computes $A \cdot 2^B$ by adding B to the exponent of A. Used to calculate various special functions, particularly base-2 exponents. Special case handling differs from an actual floating-point multiply, so this should not be used outside fixed instruction sequences. A Calculates the base-2 exponent of an argument specified as a 8:24 fixed-point. The original argument is passed as well for correct handling of special cases. Input as 8:24 fixed-point Input as 32-bit float Performs a floating-point addition specialized for logarithm computation. A B Used for `atan2()` implementation. Destination is two 16-bit values (int and float) for the first form, and a single 32-bit float when `.second` is set (indicating the FATAN_TABLE.f32 instruction). A B $A + B$ with optional saturation. As Valhall lacks swizzle instructions, `IADD.v2i16` with zero is the canonical lowering for swizzles. A B Calculates $A | (B \ll 16)$. Used to implement `(ushort2)(A, B)` A B $A - B$ with optional saturation A B Similar to SHADDX, but especially used for loading offsets into WLS. Usually this is only required for atomic operations, which cannot directly use wls_pointer as an address. .neg indicates SEG_SUB instead. A B Sign or zero extend B to 64-bits, left-shift by `shift`, and add the 64-bit value A. These instructions accelerate address arithmetic, but may be used in full generality for 64-bit integer arithmetic. A B $A \cdot B$ with optional saturation. Note the multipliers can only handle up to 32-bit by 32-bit multiplies. The 64-bit "multiply" acts like IMUL.u32 but additionally writes the high half of the product to the high half of the 64-bit destination. Along with IADD.u32 and IADD.u64, this allows the construction of a 64-bit multiply in 5 instructions (6 clocks). A B A B $(A + B) \gg 1$ without intermediate overflow, corresponding to `hadd()` in OpenCL. With the `.rhadd` modifier set, it instead calculates $(A + B + 1) \gg 1$ corresponding to `rhadd()` in OpenCL. Selects the value of A in the subgroup lane given by B. This implements subgroup broadcasts. It may be used as a primitive for screen space derivatives in fragment shaders. A B $A \cdot B + C$ A B C Left shifts its first source by a specified amount and bitwise ANDs it with the second source, optionally inverting the second source or the result. A shift B Right shifts its first source by a specified amount and bitwise ANDs it with the second source, optionally inverting the second source or the result. If `signed` is set, the hardware performs an arithmetic right shift; otherwise, it performs an unsigned right shift. A shift B Left shifts its first source by a specified amount and bitwise ORs it with the second source, optionally inverting the second source or the result. A shift B Right shifts its first source by a specified amount and bitwise ORs it with the second source, optionally inverting the second source or the result. If `signed` is set, the hardware performs an arithmetic right shift; otherwise, it performs an unsigned right shift. A shift B Left shifts its first source by a specified amount and bitwise XORs it with the second source, optionally inverting the second source or the result. A shift B Right shifts its first source by a specified amount and bitwise XORs it with the second source, optionally inverting the second source or the result. If `signed` is set, the hardware performs an arithmetic right shift; otherwise, it performs an unsigned right shift. A shift B Mux between A and B based on the provided mask. The condition specified as the `mux` modifier is evaluated on the mask. If true, `A` is chosen, else `B` is chosen. The `bit` modifier acts bitwise, equivalent to `bitselect()` in OpenCL, so `MUX.i32.bit A, B, mask` calculates `(A & mask) | (A & ~mask)`. A B Mask Mux between A and B based on the provided mask. The condition specified as the `mux` modifier is evaluated on the mask. If true, `A` is chosen, else `B` is chosen. The `bit` modifier acts bitwise, equivalent to `bitselect()` in OpenCL, so `MUX.i32.bit A, B, mask` calculates `(A & mask) | (A & ~mask)`. A B Mask Mux between A and B based on the provided mask. The condition specified as the `mux` modifier is evaluated on the mask. If true, `A` is chosen, else `B` is chosen. The `bit` modifier acts bitwise, equivalent to `bitselect()` in OpenCL, so `MUX.i32.bit A, B, mask` calculates `(A & mask) | (A & ~mask)`. A B Mask During a cube map transform, select the S coordinate given a selected face. Z coordinate as 32-bit floating point X coordinate as 32-bit floating point Cube face index During a cube map transform, select the T coordinate given a selected face. Y coordinate as 32-bit floating point Z coordinate as 32-bit floating point Cube face index Calculates $A | (B \ll 8) | (CD \ll 16)$ for 8-bit A and B and 16-bit CD. To implement `(uchar4) (A, B, C, D)` in full generality, use the sequence `MKVEC.v2i8 CD, C, D, #0; MKVEC.v2i8 out, A, B, CD` `MKVEC.v2i8` also allows zero extending arbitrary 8-bit lanes. For example, to extend `r0.b3` to `r1`, use `MKVEC.v2i8 r1, r0.b3, 0x0.b0, 0x0`. A B CD Select the maximum absolute value of its arguments. X coordinate as 32-bit floating point Y coordinate as 32-bit floating point Z coordinate as 32-bit floating point Select the cube face index corresponding to the arguments. X coordinate as 32-bit floating point Y coordinate as 32-bit floating point Z coordinate as 32-bit floating point 8-bit integer dot product between 4 channel vectors, intended for machine learning. Available in both unsigned and signed variants, controlling sign-extension/zero-extension behaviour to the final 32-bit destination. Saturation is available. Corresponds to the `cl_arm_integer_dot_product_*` family of OpenCL extensions. Not for actual use, just for completeness. Instead, use your platform's neural accelerator. For $A, B \in \{ 0, \ldots, 255 \}^4$ and $\text{Accumulator} \in \mathbb{Z}$, calculates $(A \cdot B) + \text{Accumulator}$ and optionally saturates. A B Accumulator Evaluates the given condition, do a logical and/or with the condition in the result source, and return in the given result type (integer one, integer minus one, or floating-point one). The third source is useful for chaining together conditions without intermediate bitwise arithmetic; when this is not desired, tie it to zero and use the OR combine mode (do not set the `.and` modifier). The sequence modifier `.seq` is used to construct 64-bit compares in 2 `ICMP.u32` instructions, in conjunction with the `u1` result type on the low half, the `m1` result type on the high half, and the result of the low half comparison passed as the third source. For comparisons other than 64-bit, do not set the `.seq` modifier and do not use the `u1` result type. A B C Evaluates the given condition, do a logical and/or with the condition in the result source, and return in the given result type (integer one, integer minus one, or floating-point one). The third source is useful for chaining together conditions without intermediate bitwise arithmetic; when this is not desired, tie it to zero and use the OR combine mode (do not set the `.and` modifier). A B C Evaluates the given condition, do a logical and/or with the condition in the result source, and return in the given result type (integer one, integer minus one, or floating-point one). The third source is useful for chaining together conditions without intermediate bitwise arithmetic; when this is not desired, tie it to zero and use the OR combine mode (do not set the `.and` modifier). The sequence modifier `.seq` is used to construct signed 64-bit compares in 1 `ICMP.u32` and 1 `ICMP.s32` instruction, in conjunction with the `u1` result type on the low half, the `m1` result type on the high half, and the result of the low half comparison passed as the third source. For comparisons other than 64-bit, do not set the `.seq` modifier and do not use the `u1` result type. A B C Adds an arbitrary 32-bit immediate embedded within the instruction stream. If no modifiers are required, this is preferred to `IADD.i32` with a constant accessed as a uniform. However, if the constant is available inline, `IADD.f32` is preferred. `IADD_IMM.i32` with the source tied to zero is the canonical immediate move. A Adds an arbitrary pair of 16-bit immediates embedded within the instruction stream. If no modifiers are required, this is preferred to `IADD.v2i16` with a constant accessed as a uniform. However, if the constant is available inline, `IADD.v2i16` is preferred. Adding only a single 16-bit constant requires replication of the constant. A Adds an arbitrary quad of 8-bit immediates embedded within the instruction stream. If no modifiers are required, this is preferred to `IADD.v4i8` with a constant accessed as a uniform. However, if the constant is available inline, `IADD.v4i8` is preferred. Adding only a single 8-bit constant requires replication of the constant. A Adds an arbitrary 32-bit immediate embedded within the instruction stream. If no modifiers are required, this is preferred to `FADD.f32` with a constant accessed as a uniform. However, if the constant is available inline, `FADD.f32` is preferred. A Adds an arbitrary pair of 16-bit immediates embedded within the instruction stream. If no modifiers are required, this is preferred to `FADD.v2f16` with a constant accessed as a uniform. However, if the constant is available inline, `FADD.v2f16` is preferred. Adding only a single 16-bit constant requires replication of the constant. A 64-bit address to operate on 64-bit address to operate on 64-bit address to operate on 64-bit address to operate on 64-bit address to operate on 64-bit address to operate on Unfiltered textured instruction. Image to read from Ordinary texturing instruction using a sampler. Image to read from Texture gather instruction. Image to read from Pair of texture instructions. Image to read from Only works for FP32 varyings. Performance characteristics are similar to LD_VAR_BUF_IMM_F32.v2.f32 followed by TEX, using both V and T units. Image to read from Varying offset Only works for FP32 varyings. Performance characteristics are similar to LD_VAR_BUF_IMM_F32.v2.f32 followed by TEX, using both V and T units. Image to read from Varying offset Only works for FP32 varyings. Performance characteristics are similar to LD_VAR_BUF_IMM_F32.v2.f32 followed by TEX, using both V and T units. Image to read from Varying offset Only works for FP32 varyings. Performance characteristics are similar to LD_VAR_BUF_IMM_F32.v2.f32 followed by TEX_DUAL, using both V and T units. Image to read from Varying offset Only works for FP32 varyings. Performance characteristics are similar to LD_VAR_IMM_F32.v2.f32 followed by TEX, using both V and T units. Image to read from Varying offset Only works for FP32 varyings. Performance characteristics are similar to LD_VAR_IMM_F32.v2.f32 followed by TEX, using both V and T units. Image to read from Varying offset Only works for FP32 varyings. Performance characteristics are similar to LD_VAR_IMM_F32.v2.f32 followed by TEX, using both V and T units. Image to read from Varying offset Only works for FP32 varyings. Performance characteristics are similar to LD_VAR_IMM_F32.v2.f32 followed by TEX_DUAL, using both V and T units. Image to read from Varying offset First calculates $A \cdot B + C$ and then biases the exponent by D. Used in special transcendental function sequences. It should not be used for general code as its special case handling differs from two back-to-back `FMA.f32` operations. Equivalent to `FMA.f32` back-to-back with `LDEXP.f32` A B C D First calculates $A \cdot B + C$ and then biases the exponent by D. If $A = 0$ or $B = 0$, the multiply $A \cdot B$ is treated as zero even if an ordinary multiply would return NaN. Used in special transcendental function sequences. It should not be used for general code as its special case handling differs from two back-to-back `FMA.f32` operations. Equivalent to `FMA.f32` back-to-back with `LDEXP.f32` A B C D First calculates $A \cdot B + C$ and then biases the exponent by D. If $A = 0$ or $B = 0$, the multiply is treated as $A$ even if an ordinary multiply would return NaN. Used in special transcendental function sequences. It should not be used for general code as its special case handling differs from two back-to-back `FMA.f32` operations. Equivalent to `FMA.f32` back-to-back with `LDEXP.f32` A B C D First calculates $A \cdot B + C$ and then biases the exponent by D, interpreted as a 16-bit value. Used in special transcendental function sequences. It should not be used for general code as its special case handling differs from two back-to-back `FMA.f32` operations. Equivalent to `FMA.f32` back-to-back with `LDEXP.f32` A B C D