This page contains proposed changes for a future release of ROCm. Read the latest Linux release of ROCm documentation for your production environments.

rocblas_zdgmm_batched Interface Reference

rocblas_zdgmm_batched Interface Reference#

HIPFORT API Reference: hipfort_rocblas::rocblas_zdgmm_batched Interface Reference
hipfort_rocblas::rocblas_zdgmm_batched Interface Reference

BLAS Level 3 API. More...

Public Member Functions

integer(kind(rocblas_status_success)) function rocblas_zdgmm_batched_ (handle, side, m, n, A, lda, x, incx, C, ldc, batch_count)
 
integer(kind(rocblas_status_success)) function rocblas_zdgmm_batched_full_rank (handle, side, m, n, A, lda, x, incx, C, ldc, batch_count)
 
integer(kind(rocblas_status_success)) function rocblas_zdgmm_batched_rank_0 (handle, side, m, n, A, lda, x, incx, C, ldc, batch_count)
 
integer(kind(rocblas_status_success)) function rocblas_zdgmm_batched_rank_1 (handle, side, m, n, A, lda, x, incx, C, ldc, batch_count)
 

Detailed Description

BLAS Level 3 API.

dgmm_batched performs one of the batched matrix-matrix operations

C_i = A_i * diag(x_i) for i = 0, 1, ... batch_count-1 if side == rocblas_side_right
C_i = diag(x_i) * A_i for i = 0, 1, ... batch_count-1 if side == rocblas_side_left

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

Parameters
[in]handle[rocblas_handle] handle to the rocblas library context queue.
[in]side[rocblas_side] specifies the side of diag(x)
[in]m[rocblas_int] matrix dimension m.
[in]n[rocblas_int] matrix dimension n.
[in]Adevice array of device pointers storing each matrix A_i on the GPU. Each A_i is of dimension ( lda, n )
[in]lda[rocblas_int] specifies the leading dimension of A_i.
[in]xdevice array of device pointers storing each vector x_i on the GPU. Each x_i is of dimension n if side == rocblas_side_right and dimension m if side == rocblas_side_left
[in]incx[rocblas_int] specifies the increment between values of x_i
[in,out]Cdevice array of device pointers storing each matrix C_i on the GPU. Each C_i is of dimension ( ldc, n ).
[in]ldc[rocblas_int] specifies the leading dimension of C_i.
[in]batch_count[rocblas_int] number of instances in the batch.

Member Function/Subroutine Documentation

◆ rocblas_zdgmm_batched_()

integer(kind(rocblas_status_success)) function hipfort_rocblas::rocblas_zdgmm_batched::rocblas_zdgmm_batched_ ( type(c_ptr), value  handle,
integer(kind(rocblas_side_left)), value  side,
integer(c_int), value  m,
integer(c_int), value  n,
type(c_ptr)  A,
integer(c_int), value  lda,
type(c_ptr)  x,
integer(c_int), value  incx,
type(c_ptr)  C,
integer(c_int), value  ldc,
integer(c_int), value  batch_count 
)

◆ rocblas_zdgmm_batched_full_rank()

integer(kind(rocblas_status_success)) function hipfort_rocblas::rocblas_zdgmm_batched::rocblas_zdgmm_batched_full_rank ( type(c_ptr)  handle,
integer(kind(rocblas_side_left))  side,
integer(c_int)  m,
integer(c_int)  n,
complex(c_double_complex), dimension(:,:,:), target  A,
integer(c_int)  lda,
complex(c_double_complex), dimension(:,:), target  x,
integer(c_int)  incx,
complex(c_double_complex), dimension(:,:,:), target  C,
integer(c_int)  ldc,
integer(c_int)  batch_count 
)

◆ rocblas_zdgmm_batched_rank_0()

integer(kind(rocblas_status_success)) function hipfort_rocblas::rocblas_zdgmm_batched::rocblas_zdgmm_batched_rank_0 ( type(c_ptr)  handle,
integer(kind(rocblas_side_left))  side,
integer(c_int)  m,
integer(c_int)  n,
complex(c_double_complex), target  A,
integer(c_int)  lda,
complex(c_double_complex), target  x,
integer(c_int)  incx,
complex(c_double_complex), target  C,
integer(c_int)  ldc,
integer(c_int)  batch_count 
)

◆ rocblas_zdgmm_batched_rank_1()

integer(kind(rocblas_status_success)) function hipfort_rocblas::rocblas_zdgmm_batched::rocblas_zdgmm_batched_rank_1 ( type(c_ptr)  handle,
integer(kind(rocblas_side_left))  side,
integer(c_int)  m,
integer(c_int)  n,
complex(c_double_complex), dimension(:), target  A,
integer(c_int)  lda,
complex(c_double_complex), dimension(:), target  x,
integer(c_int)  incx,
complex(c_double_complex), dimension(:), target  C,
integer(c_int)  ldc,
integer(c_int)  batch_count 
)

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