Ctrmv

Applicable Products

Function Description

API function

• asdBlasMakeCtrmvPlan: initializes the Ctrmv operator configuration corresponding to the handle.
• asdBlasCtrmv: single-precision complex matrix-vector multiplication operator, which is used to compute the product of a complex triangular matrix and a complex vector.

Formula:

• asdBlasCtrmv formula:

  Matrix-vector product:

  Transposed matrix-vector product:

  Conjugately transposed matrix-vector product:

• Example:

  Input A:

      [  [ 1+2i, 1+2i ],
        [ 1+2i, 1+2i ]  ]

  Input x:

      [  [ 0+0i, 1+i ]  ]

  The input uplo is L, the input trans is N, and the input diag is N.

  The input n is 2, the input lda is 2, and the input incx is 1.

  After the Ctrmv operator is called, the output x is as follows:

      [  [ 0+0i, -1+3i ]  ]

Function Prototype

• AspbStatus asdBlasMakeCtrmvPlan(asdBlasHandle handle, asdBlasFillMode_t uplo, int64_t n)
• AspbStatus asdBlasCtrmv(asdBlasHandle handle, asdBlasFillMode_t uplo, asdBlasOperation_t trans, asdBlasDiagType_t diag,const int64_t n, aclTensor *A, const int64_t lda, aclTensor *x, const int64_t incx)

Parameter Description

• asdBlasMakeCtrmvPlan

  Parameter	Input/Output	Type	Description
  handle	Input	asdBlasHandle	ctrmv operator handle.
  uplo	Input	asdBlasFillMode_t	Storage format of matrix A. ASDBLAS_FILL_MODE_LOWER // Lower triangle ASDBLAS_FILL_MODE_UPPER // Upper triangle
  n	Input	int64_t	Order of matrix A, and dimension of vector x.

• asdBlasCtrmv

  Parameter	Input/Output	Type	Description
  handle	Input	asdBlasHandle	ctrmv operator handle.
  uplo	Input	asdBlasFillMode_t	Storage format of matrix A. ASDBLAS_FILL_MODE_LOWER // Lower triangle ASDBLAS_FILL_MODE_UPPER // Upper triangle
  trans	Input	asdBlasDiagType_t	Whether matrix A should be transposed. ASDBLAS_OP_N // Not transposed ASDBLAS_OP_T // Transposed ASDBLAS_OP_C // Conjugately transposed
  diag	Input	asdBlasDiagType_t	Diagonal element handling mode of matrix A. ASDBLAS_DIAG_NON_UNIT // General matrix ASDBLAS_DIAG_UNIT // Unit matrix
  n	Input	const int64_t	Order of matrix A, and dimension of vector x.
  A	Input	aclTensor *	A in the formula, which is a tensor on the device. The data type can only be COMPLEX64, the data format can be ND, and the shape is [n, n].
  lda	Input	const int64_t	Leading dimension of matrix A
  x	Input/Output	aclTensor *	x in the formula, which is a tensor on the device. The data type can only be COMPLEX64, the data format can be ND, and the shape is [n].
  incx	Input	const int64_t	Stride of elements in vector x

Return Value Description

For details about the return values, see Return Value.

Constraints

• asdBlasMakeCtrmvPlan: none.
• asdBlasCtrmv
  • The input element count n currently supports the range [1, 8192].
  • The input shape of the operator is [n, n] and [n], and the output shape is [n].
  • The operator does not support the calculation for three or more dimensions.

Calling Example

For details about the operator calling example, see Ctrmv.