coopVecMatMul

Description

Multiply a matrix with a cooperative vector. Given a M-row by K-col matrix, and a K-element column vector input, computes matrix*input, and returns a M-element vector.

Signature

/// Requires Capability Set 1:
CoopVec<T, M> coopVecMatMul<T, int M, int K, U>(
    CoopVec<U, K> input,
    CoopVecComponentType inputInterpretation,
    RWByteAddressBuffer matrix,
    int matrixOffset,
    CoopVecComponentType matrixInterpretation,
    CoopVecMatrixLayout memoryLayout,
    bool transpose,
    uint matrixStride)
    where T : __BuiltinArithmeticType
    where U : __BuiltinArithmeticType;

/// Requires Capability Set 1:
CoopVec<T, M> coopVecMatMul<T, int M, int K, U>(
    CoopVec<U, K> input,
    CoopVecComponentType inputInterpretation,
    ByteAddressBuffer matrix,
    int matrixOffset,
    CoopVecComponentType matrixInterpretation,
    CoopVecMatrixLayout memoryLayout,
    bool transpose,
    uint matrixStride)
    where T : __BuiltinArithmeticType
    where U : __BuiltinArithmeticType;

/// Requires Capability Set 2:
CoopVec<T, M> coopVecMatMul<T, int M, int K, U, IgnoredBufferElementType>(
    CoopVec<U, K> input,
    CoopVecComponentType inputInterpretation,
    RWStructuredBuffer<IgnoredBufferElementType, DefaultDataLayout> matrix,
    int matrixOffset,
    CoopVecComponentType matrixInterpretation,
    CoopVecMatrixLayout memoryLayout,
    bool transpose,
    uint matrixStride)
    where T : __BuiltinArithmeticType
    where U : __BuiltinArithmeticType;

/// Requires Capability Set 2:
CoopVec<T, M> coopVecMatMul<T, int M, int K, U, IgnoredBufferElementType>(
    CoopVec<U, K> input,
    CoopVecComponentType inputInterpretation,
    StructuredBuffer<IgnoredBufferElementType, DefaultDataLayout> matrix,
    int matrixOffset,
    CoopVecComponentType matrixInterpretation,
    CoopVecMatrixLayout memoryLayout,
    bool transpose,
    uint matrixStride)
    where T : __BuiltinArithmeticType
    where U : __BuiltinArithmeticType;

/// Requires Capability Set 3:
CoopVec<T, M> coopVecMatMul<T, int M, int K, U>(
    CoopVec<U, K> input,
    CoopVecComponentType inputInterpretation,
    Ptr<void, Access.ReadWrite, AddressSpace.Device, DefaultDataLayout> matrix,
    CoopVecComponentType matrixInterpretation,
    CoopVecMatrixLayout memoryLayout,
    bool transpose,
    uint matrixStride)
    where T : __BuiltinArithmeticType
    where U : __BuiltinArithmeticType;

Generic Parameters

T: __BuiltinArithmeticType

M : int

K : int

U: __BuiltinArithmeticType

IgnoredBufferElementType

Parameters

input : CoopVec<U, K>

The K-element input cooperative vector to multiply with the matrix.

inputInterpretation : CoopVecComponentType

Specifies how to interpret the values in the input vector (e.g. as 8-bit integers, 16-bit floats, etc).

matrix : RWByteAddressBuffer

The M-by-K matrix to multiply with the input vector.

matrixOffset : int

Byte offset into the matrix buffer.

matrixInterpretation : CoopVecComponentType

Specifies how to interpret the values in the matrix (e.g. as 8-bit integers, 16-bit floats, etc).

memoryLayout : CoopVecMatrixLayout

Specifies the memory layout of the matrix (row-major or column-major).

transpose : bool

Whether to transpose the matrix before multiplication.

matrixStride : uint

The stride in bytes between rows/columns of the matrix.

matrix : ByteAddressBuffer

The M-by-K matrix to multiply with the input vector.

matrix : RWStructuredBuffer<IgnoredBufferElementType, DefaultDataLayout>

The M-by-K matrix to multiply with the input vector.

matrix : StructuredBuffer<IgnoredBufferElementType, DefaultDataLayout>

The M-by-K matrix to multiply with the input vector.

matrix : Ptr<void, Access.ReadWrite, AddressSpace.Device, DefaultDataLayout>

The M-by-K matrix to multiply with the input vector.

Return value

A new cooperative vector containing the result of the matrix multiplication.

Remarks

Depending on target hardware, some combinations of inputInterpretation, matrixInterpretation and memoryLayout may not be supported. For example, CoopVecComponentType.Float32 is not widely supported. Developers should query device properties through the host graphics API to find out which interpretations are supported.

Transposing is not supported when memoryLayout is RowMajor or ColumnMajor, and transpose must be false. Not all component types support transposing. When memoryLayout is InferencingOptimal or TrainingOptimal, matrixStride is ignored.

Availability and Requirements

Capability Set 1

Defined for the following targets:

hlsl

Available in all stages.

glsl

Available in all stages.

cpp

Available in all stages.

cuda

Available in all stages.

Requires capability: optix_coopvec.

spirv

Available in all stages.

Requires capability: spvCooperativeVectorNV.

Capability Set 2

Defined for the following targets:

spirv

Available in all stages.

Requires capability: spvCooperativeVectorNV.

cuda

Available in all stages.

Requires capability: optix_coopvec.

Capability Set 3

Defined for the following targets:

spirv

Available in all stages.

Requires capability: spvCooperativeVectorNV.