hipblassdgmmstridedbatched Interface Reference

hipblassdgmmstridedbatched Interface Reference#

HIPFORT API Reference: hipfort_hipblas::hipblassdgmmstridedbatched Interface Reference
hipfort_hipblas::hipblassdgmmstridedbatched Interface Reference

BLAS Level 3 API. More...

Public Member Functions

integer(kind(hipblas_status_success)) function hipblassdgmmstridedbatched_ (handle, side, m, n, ap, lda, stridea, x, incx, stridex, cp, ldc, stridec, batchcount)
 
integer(kind(hipblas_status_success)) function hipblassdgmmstridedbatched_rank_0 (handle, side, m, n, ap, lda, stridea, x, incx, stridex, cp, ldc, stridec, batchcount)
 
integer(kind(hipblas_status_success)) function hipblassdgmmstridedbatched_rank_1 (handle, side, m, n, ap, lda, stridea, x, incx, stridex, cp, ldc, stridec, batchcount)
 
integer(kind(hipblas_status_success)) function hipblassdgmmstridedbatched_full_rank (handle, side, m, n, ap, lda, stridea, x, incx, stridex, cp, ldc, stridec, batchcount)
 

Detailed Description

BLAS Level 3 API.

The dgmmStridedBatched functions perform one of the batched matrix-matrix operations:

C_i = A_i * diag(x_i)   if side == HIPBLAS_SIDE_RIGHT   for i = 0, 1, ... batchCount-1
C_i = diag(x_i) * A_i   if side == HIPBLAS_SIDE_LEFT    for i = 0, 1, ... batchCount-1

where C_i and A_i are m by n dimensional matrices, diag(x_i) is a diagonal matrix, and x_i is a vector of dimension n if side == HIPBLAS_SIDE_RIGHT and dimension m if side == HIPBLAS_SIDE_LEFT.

  • Supported precisions in rocBLAS : s, d, c, and z.
  • Supported precisions in cuBLAS : No support.
Parameters
[in]handle- [hipblasHandle_t] handle to the hipBLAS library context queue.
[in]side- [hipblasSideMode_t] specifies the side of diag(x).
[in]m- [int] matrix dimension m.
[in]n- [int] matrix dimension n.
[in]AP- device pointer to the first matrix A_0 on the GPU. Each A_i is of dimension ( lda, n ).
[in]lda- [int] specifies the leading dimension of A.
[in]strideA- [hipblasStride] stride from the start of one matrix (A_i) to the next one (A_i+1).
[in]x- pointer to the first vector x_0 on the GPU. Each x_i is of dimension n if side == HIPBLAS_SIDE_RIGHT and dimension m if side == HIPBLAS_SIDE_LEFT.
[in]incx- [int] specifies the increment between values of x.
[in]stridex- [hipblasStride] stride from the start of one vector(x_i) to the next one (x_i+1).
[in,out]CP- device pointer to the first matrix C_0 on the GPU. Each C_i is of dimension ( ldc, n ).
[in]ldc- [int] specifies the leading dimension of C.
[in]strideC- [hipblasStride] stride from the start of one matrix (C_i) to the next one (C_i+1).
[in]batchCount- [int] number of instances i in the batch.

Member Function/Subroutine Documentation

◆ hipblassdgmmstridedbatched_()

integer(kind(hipblas_status_success)) function hipfort_hipblas::hipblassdgmmstridedbatched::hipblassdgmmstridedbatched_ ( type(c_ptr), value  handle,
integer(kind(hipblas_side_left)), value  side,
integer(c_int), value  m,
integer(c_int), value  n,
type(c_ptr), value  ap,
integer(c_int), value  lda,
integer(c_int64_t), value  stridea,
type(c_ptr), value  x,
integer(c_int), value  incx,
integer(c_int64_t), value  stridex,
type(c_ptr), value  cp,
integer(c_int), value  ldc,
integer(c_int64_t), value  stridec,
integer(c_int), value  batchcount 
)

◆ hipblassdgmmstridedbatched_full_rank()

integer(kind(hipblas_status_success)) function hipfort_hipblas::hipblassdgmmstridedbatched::hipblassdgmmstridedbatched_full_rank ( type(c_ptr)  handle,
integer(kind(hipblas_side_left))  side,
integer(c_int)  m,
integer(c_int)  n,
real(c_float), dimension(:,:), target  ap,
integer(c_int)  lda,
integer(c_int64_t)  stridea,
real(c_float), dimension(:), target  x,
integer(c_int)  incx,
integer(c_int64_t)  stridex,
real(c_float), dimension(:,:), target  cp,
integer(c_int)  ldc,
integer(c_int64_t)  stridec,
integer(c_int)  batchcount 
)

◆ hipblassdgmmstridedbatched_rank_0()

integer(kind(hipblas_status_success)) function hipfort_hipblas::hipblassdgmmstridedbatched::hipblassdgmmstridedbatched_rank_0 ( type(c_ptr)  handle,
integer(kind(hipblas_side_left))  side,
integer(c_int)  m,
integer(c_int)  n,
real(c_float), target  ap,
integer(c_int)  lda,
integer(c_int64_t)  stridea,
real(c_float), target  x,
integer(c_int)  incx,
integer(c_int64_t)  stridex,
real(c_float), target  cp,
integer(c_int)  ldc,
integer(c_int64_t)  stridec,
integer(c_int)  batchcount 
)

◆ hipblassdgmmstridedbatched_rank_1()

integer(kind(hipblas_status_success)) function hipfort_hipblas::hipblassdgmmstridedbatched::hipblassdgmmstridedbatched_rank_1 ( type(c_ptr)  handle,
integer(kind(hipblas_side_left))  side,
integer(c_int)  m,
integer(c_int)  n,
real(c_float), dimension(:), target  ap,
integer(c_int)  lda,
integer(c_int64_t)  stridea,
real(c_float), dimension(:), target  x,
integer(c_int)  incx,
integer(c_int64_t)  stridex,
real(c_float), dimension(:), target  cp,
integer(c_int)  ldc,
integer(c_int64_t)  stridec,
integer(c_int)  batchcount 
)

The documentation for this interface was generated from the following file: