applyMatrixMultiplication(inputA:transposed:inputB:transposed:output:alpha:workspace:filterParameters:)

Declaration

static func applyMatrixMultiplication(inputA: BNNSNDArrayDescriptor, transposed transposeA: Bool, inputB: BNNSNDArrayDescriptor, transposed transposeB: Bool, output: BNNSNDArrayDescriptor, alpha: Float, workspace: UnsafeMutableRawBufferPointer?, filterParameters: BNNSFilterParameters? = nil) throws

Parameters

• inputA:

  The descriptor of matrix A.

• transposeA:

  A Boolean value that indicates whether the function transposes the last two dimensions of matrix A.

• inputB:

  The descriptor of matrix B.

• transposeB:

  A Boolean value that indicates whether the function transposes the last two dimensions of matrix B.

• output:

  The descriptor of the output.

• alpha:

  A scalar value that scales the result.

• workspace:

  A pointer to a memory region that the function uses as scratch space. This must have a size no less than the value that Matrixmultiplicationworkspacesize(inputa:transposed:inputb:transposed:output:alpha:filterparameters:) returns.

• filterParameters:

  The filter runtime parameters.

See Also

Matrix multiplication

• BNNSDirectApplyBroadcastMatMul(_:_:_:_:_:_:_:)
• BNNS.BroadcastMatrixMultiplyLayer
• BNNSLayerParametersBroadcastMatMul
• BNNSFilterCreateLayerBroadcastMatMul(_:_:)
• BNNSMatMulWorkspaceSize(_:_:_:_:_:_:_:)
• BNNSMatMul(_:_:_:_:_:_:_:_:)
• matrixMultiplicationWorkspaceSize(inputA:transposed:inputB:transposed:output:alpha:filterParameters:)