Cgemv

Applicable Products

Function Description

API function

• asdBlasMakeCgemvPlan: initializes the Cgemv operator configuration corresponding to the handle.
• asdBlasCgemv: matrix-vector multiplication, which is used to compute the product of complex matrix A and complex vector x. The result is stored in complex vector y.

Formula:

• asdBlasCgemv formula: ,

  where . alpha and beta are scalars, x and y are vectors, and A is an m*n matrix.

• Example:
  Input A:

  [   [ 1+i,1+2i ],
      [ 1+2i,1+3i ]  ]

  Input x:

  [ 2+i,2+2i ]

  Input y:

  [ 1+i,1+2i ]

  The input m is 2, the input n is 2, the input trans is 'N':2, the input alpha is 1+i, and the input beta is 2+2i.

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

  asdBlasMakeCgemvPlan is called to generate a plan.

  After the asdBlasCgemv API is called, the output y is as follows:

  [ -10 + 12i,-19 + 15i]

Function Prototype

• AspbStatus asdBlasMakeCgemvPlan(asdBlasHandle handle, asdBlasOperation_t trans, const int64_t m, const int64_t n,aclTensor *y, const int64_t incy)
• AspbStatus asdBlasCgemv(asdBlasHandle handle, asdBlasOperation_t trans, const int64_t m, const int64_t n,const std::complex<float> *alpha, aclTensor *A, const int64_t lda, aclTensor *x,const int64_t incx, const std::complex<float> *beta, aclTensor *y, const int64_t incy)

Parameter Description

• asdBlasMakeCgemvPlan

  Parameter	Input/Output	Type	Description
  handle	Input	asdBlasHandle	cgemv operator handle.
  trans	Input	asdBlasOperation_t	Whether matrix A should be transposed. ASDBLAS_OP_N // Not transposed ASDBLAS_OP_T // Transposed ASDBLAS_OP_C // Conjugately transposed
  m	Input	const int64_t	Number of rows of matrix A, and number of elements in vector y.
  n	Input	const int64_t	Number of columns of matrix A, and number of elements in vector x.
  y	Input	aclTensor *	Vector y.
  incy	Input	const int64_t	Stride of vector y.

• asdBlasCgemv

  Parameter	Input/Output	Type	Description
  handle	Input	asdBlasHandle	cgemv operator handle.
  trans	Input	asdBlasOperation_t	Whether matrix A should be transposed. ASDBLAS_OP_N // Not transposed ASDBLAS_OP_T // Transposed ASDBLAS_OP_C // Conjugately transposed
  m	Input	const int64_t	Number of rows of matrix A, and number of elements in vector y.
  n	Input	const int64_t	Number of columns of matrix A, and number of elements in vector x.
  alpha	Input	const std::complex<float> *	alpha in the formula is a complex scalar, and is used to multiply the result of the matrix and vector multiplication.
  A	Input	aclTensor *	Matrix A in the formula, which is in column-major order and is a tensor on the device. The data type is COMPLEX64, the data format is ND, and the shape is [m, n].
  lda	Input	const int64_t	Memory address increment between consecutive elements of A (currently restricted to m).
  x	Input	aclTensor *	Vector 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 std::complex<float>	Stride of vector x (currently restricted to 1).
  beta	Input	const std::complex<float> *	beta in the formula is a complex scalar, and is used to multiply vector y.
  y	Input/Output	aclTensor *	Vector y 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 [m].
  incy	Input	const int64_t	Stride of vector y (currently restricted to 1).

Return Value Description

For details about the return values, see Return Value.

Constraints

• asdBlasMakeCgemvPlan: none.
• asdBlasCgemv
  • The input element count (m, n) currently supports the range [1, 8193].
  • The input matrix A of the operator is in column-major order. The input shape is [m, n], [m], or [n], and the output shape is [m].
  • The operator does not support the calculation for three or more dimensions.

Calling Example

For details about the operator calling example, see Cgemv.