rocblas_syrk_ex Interface Reference#
hipfort_rocblas::rocblas_syrk_ex Interface Reference
BLAS EX API. More...
Public Member Functions | |
| integer(kind(rocblas_status_success)) function | rocblas_syrk_ex_ (handle, uplo, transa, n, k, alpha, a, a_type, lda, beta, c, c_type, ldc, execution_type) |
Detailed Description
BLAS EX API.
The syrk_ex functions perform one of the matrix-matrix operations for a symmetric rank-k update:
C := alpha*op( A )*op( A )^T + beta*C,
where alpha and beta are scalars, op(A) is an n by k matrix, and C is a symmetric n x n matrix stored as either upper or lower.
op( A ) = A, and A is n by k if transA == rocblas_operation_none op( A ) = A^T and A is k by n if transA == rocblas_operation_transpose
Currently supported datatypes are as follows:
| a_type | c_type | execution_type |
|---|---|---|
| bf16_r | bf16_r | f32_r |
| bf16_r | f32_r | f32_r |
| f16_r | f16_r | f32_r |
| f16_r | f32_r | f32_r |
| f32_r | f32_r | f64_r |
| f32_r | f64_r | f64_r |
- Parameters
-
[in] handle - [rocblas_handle] handle to the rocBLAS library context queue. [in] uplo - [rocblas_fill] - rocblas_fill_upper: C is an upper triangular matrix.
- rocblas_fill_lower: C is a lower triangular matrix.
[in] transA - [rocblas_operation] - rocblas_operation_transpose: op(A) = A^T
- rocblas_operation_none: op(A) = A
- rocblas_operation_conjugate_transpose: op(A) = A^T
- rocblas_operation_conjugate_transpose is not supported for complex types. See cherk and zherk.
[in] n - [rocblas_int] n specifies the number of rows and columns of C. n >= 0. [in] k - [rocblas_int] k specifies the number of columns of op(A). k >= 0. [in] alpha - [const void *] device pointer or host pointer specifying the scalar alpha. When alpha is zero, then A is not referenced and A need not be set before entry. Same datatype as compute_type. [in] A - pointer storing matrix A on the GPU. Matrix dimension is ( lda, k ) when transA = rocblas_operation_none. Otherwise, (lda, n). [in] a_type - [rocblas_datatype] specifies the datatype of matrix A. [in] lda - [rocblas_int] lda specifies the first dimension of A. - If transA = rocblas_operation_none, lda >= max( 1, n ).
- Otherwise, lda >= max( 1, k ).
[in] beta - [const void *] device pointer or host pointer specifying the scalar beta. When beta is zero, then C need not be set before entry. Same datatype as compute_type. [in] C - pointer storing matrix C on the GPU. Only the upper/lower triangular part is accessed. [in] c_type - [rocblas_datatype] specifies the datatype of matrix C. [in] ldc - [rocblas_int] ldc specifies the first dimension of C. ldc >= max( 1, n ). [in] execution_type - [rocblas_datatype] specifies the datatype of computation.
Member Function/Subroutine Documentation
◆ rocblas_syrk_ex_()
| integer(kind(rocblas_status_success)) function hipfort_rocblas::rocblas_syrk_ex::rocblas_syrk_ex_ | ( | type(c_ptr), value | handle, |
| integer(kind(rocblas_fill_upper)), value | uplo, | ||
| integer(kind(rocblas_operation_none)), value | transa, | ||
| integer(c_int), value | n, | ||
| integer(c_int), value | k, | ||
| type(c_ptr), value | alpha, | ||
| type(c_ptr), value | a, | ||
| integer(kind(rocblas_datatype_f16_r)), value | a_type, | ||
| integer(c_int), value | lda, | ||
| type(c_ptr), value | beta, | ||
| type(c_ptr), value | c, | ||
| integer(kind(rocblas_datatype_f16_r)), value | c_type, | ||
| integer(c_int), value | ldc, | ||
| integer(kind(rocblas_datatype_f16_r)), value | execution_type | ||
| ) |
The documentation for this interface was generated from the following file: