rocblas_stpsv_strided_batched Interface Reference

rocblas_stpsv_strided_batched Interface Reference#

hipFORT API Reference: hipfort_rocblas::rocblas_stpsv_strided_batched Interface Reference
hipfort_rocblas::rocblas_stpsv_strided_batched Interface Reference

BLAS Level 2 API. More...

Public Member Functions

integer(c_int) function rocblas_stpsv_strided_batched_ (handle, uplo, transa, diag, n, ap, stride_a, x, incx, stride_x, batch_count)
 
integer(kind(rocblas_status_success)) function rocblas_stpsv_strided_batched_rank_0 (handle, uplo, transa, diag, n, ap, stride_a, x, incx, stride_x, batch_count)
 
integer(kind(rocblas_status_success)) function rocblas_stpsv_strided_batched_rank_1 (handle, uplo, transa, diag, n, ap, stride_a, x, incx, stride_x, batch_count)
 

Detailed Description

BLAS Level 2 API.

The tpsv_strided_batched functions solve:

 A_i*x_i = b_i or
 A_i**T*x_i = b_i or
 A_i**H*x_i = b_i

where x_i and b_i are vectors and A_i is a triangular matrix stored in the packed format, for i in [1, batch_count].

The input vectors b_i are overwritten by the output vectors x_i.

Parameters
[in]handle- [rocblas_handle] handle to the rocBLAS library context queue.
[in]uplo- [rocblas_fill]
  • rocblas_fill_upper: each A_i is an upper triangular matrix.
  • rocblas_fill_lower: each A_i is a lower triangular matrix.
[in]transA- [rocblas_operation]
  • rocblas_operation_none: Solves A*x = b.
  • rocblas_operation_transpose: Solves A**T*x = b.
  • rocblas_operation_conjugate_transpose: Solves A**H*x = b.
[in]diag- [rocblas_diagonal]
  • rocblas_diagonal_unit: each A_i is assumed to be unit triangular (the diagonal elements of each A_i are not used in computations).
  • rocblas_diagonal_non_unit: each A_i is not assumed to be unit triangular.
[in]n- [rocblas_int] n specifies the number of rows of each b_i. n >= 0.
[in]AP- device pointer pointing to the first packed matrix A_1, of dimension >= (n * (n + 1) / 2).
[in]stride_A- [rocblas_stride] stride from the beginning of one packed matrix (AP_i) to the next (AP_i+1).
[in,out]x- device pointer pointing to the first input vector b_1. Overwritten by each x_i on output.
[in]incx- [rocblas_int] specifies the increment for the elements of each x_i.
[in]stride_x- [rocblas_stride] stride from the beginning of one vector (x_i) to the next (x_i+1).
[in]batch_count- [rocblas_int] specifies the number of instances in the batch.

Member Function/Subroutine Documentation

◆ rocblas_stpsv_strided_batched_()

integer(c_int) function hipfort_rocblas::rocblas_stpsv_strided_batched::rocblas_stpsv_strided_batched_ ( type(c_ptr), value  handle,
integer(c_int), value  uplo,
integer(c_int), value  transa,
integer(c_int), value  diag,
integer(c_int), value  n,
type(c_ptr), value  ap,
integer(c_int64_t), value  stride_a,
type(c_ptr), value  x,
integer(c_int), value  incx,
integer(c_int64_t), value  stride_x,
integer(c_int), value  batch_count 
)

◆ rocblas_stpsv_strided_batched_rank_0()

integer(kind(rocblas_status_success)) function hipfort_rocblas::rocblas_stpsv_strided_batched::rocblas_stpsv_strided_batched_rank_0 ( type(c_ptr), value  handle,
integer(kind(rocblas_fill_upper))  uplo,
integer(kind(rocblas_operation_none))  transa,
integer(kind(rocblas_diagonal_non_unit))  diag,
integer(c_int)  n,
real(c_float), target  ap,
integer(c_int64_t)  stride_a,
real(c_float), target  x,
integer(c_int)  incx,
integer(c_int64_t)  stride_x,
integer(c_int)  batch_count 
)

◆ rocblas_stpsv_strided_batched_rank_1()

integer(kind(rocblas_status_success)) function hipfort_rocblas::rocblas_stpsv_strided_batched::rocblas_stpsv_strided_batched_rank_1 ( type(c_ptr), value  handle,
integer(kind(rocblas_fill_upper))  uplo,
integer(kind(rocblas_operation_none))  transa,
integer(kind(rocblas_diagonal_non_unit))  diag,
integer(c_int)  n,
real(c_float), dimension(:), target  ap,
integer(c_int64_t)  stride_a,
real(c_float), dimension(:), target  x,
integer(c_int)  incx,
integer(c_int64_t)  stride_x,
integer(c_int)  batch_count 
)

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