hipblasztrsmbatched Interface Reference

• hipfort_hipblas
• hipblasztrsmbatched

Public Member Functions | List of all members

hipfort_hipblas::hipblasztrsmbatched Interface Reference

BLAS Level 3 API. More...

Public Member Functions
integer(kind(hipblas_status_success)) function	hipblasztrsmbatched_ (handle, side, uplo, transA, diag, m, n, alpha, A, lda, B, ldb, batchCount)
integer(kind(hipblas_status_success)) function	hipblasztrsmbatched_full_rank (handle, side, uplo, transA, diag, m, n, alpha, A, lda, B, ldb, batchCount)
integer(kind(hipblas_status_success)) function	hipblasztrsmbatched_rank_0 (handle, side, uplo, transA, diag, m, n, alpha, A, lda, B, ldb, batchCount)
integer(kind(hipblas_status_success)) function	hipblasztrsmbatched_rank_1 (handle, side, uplo, transA, diag, m, n, alpha, A, lda, B, ldb, batchCount)

Detailed Description

BLAS Level 3 API.

trsmBatched performs the following batched operation:

op(A_i)*X_i = alpha*B_i or  X_i*op(A_i) = alpha*B_i, for i = 1, ..., batchCount.

where alpha is a scalar, X and B are batched m by n matrices, A is triangular batched matrix and op(A) is one of

op( A ) = A   or   op( A ) = A^T   or   op( A ) = A^H.

Each matrix X_i is overwritten on B_i for i = 1, ..., batchCount.

Note about memory allocation: When trsm is launched with a k evenly divisible by the internal block size of 128, and is no larger than 10 of these blocks, the API takes advantage of utilizing pre-allocated memory found in the handle to increase overall performance. This memory can be managed by using the environment variable WORKBUF_TRSM_B_CHNK. When this variable is not set the device memory used for temporary storage will default to 1 MB and may result in chunking, which in turn may reduce performance. Under these circumstances it is recommended that WORKBUF_TRSM_B_CHNK be set to the desired chunk of right hand sides to be used at a time. (where k is m when HIPBLAS_SIDE_LEFT and is n when HIPBLAS_SIDE_RIGHT)

Parameters

[in]	handle	[hipblasHandle_t] handle to the hipblas library context queue.
[in]	side	[hipblasSideMode_t] HIPBLAS_SIDE_LEFT: op(A)*X = alpha*B. HIPBLAS_SIDE_RIGHT: X*op(A) = alpha*B.
[in]	uplo	[hipblasFillMode_t] HIPBLAS_FILL_MODE_UPPER: each A_i is an upper triangular matrix. HIPBLAS_FILL_MODE_LOWER: each A_i is a lower triangular matrix.
[in]	transA	[hipblasOperation_t] HIPBLAS_OP_N: op(A) = A. HIPBLAS_OP_T: op(A) = A^T. HIPBLAS_OP_C: op(A) = A^H.
[in]	diag	[hipblasDiagType_t] HIPBLAS_DIAG_UNIT: each A_i is assumed to be unit triangular. HIPBLAS_DIAG_NON_UNIT: each A_i is not assumed to be unit triangular.
[in]	m	[int] m specifies the number of rows of each B_i. m >= 0.
[in]	n	[int] n specifies the number of columns of each B_i. n >= 0.
[in]	alpha	device pointer or host pointer specifying the scalar alpha. When alpha is &zero then A is not referenced and B need not be set before entry.
[in]	A	device array of device pointers storing each matrix A_i on the GPU. Matricies are of dimension ( lda, k ), where k is m when HIPBLAS_SIDE_LEFT and is n when HIPBLAS_SIDE_RIGHT only the upper/lower triangular part is accessed.
[in]	lda	[int] lda specifies the first dimension of each A_i. if side = HIPBLAS_SIDE_LEFT, lda >= max( 1, m ), if side = HIPBLAS_SIDE_RIGHT, lda >= max( 1, n ).
[in,out]	B	device array of device pointers storing each matrix B_i on the GPU.
[in]	ldb	[int] ldb specifies the first dimension of each B_i. ldb >= max( 1, m ).
[in]	batchCount	[int] number of trsm operatons in the batch.

Member Function/Subroutine Documentation

◆ hipblasztrsmbatched_()

integer(kind(hipblas_status_success)) function hipfort_hipblas::hipblasztrsmbatched::hipblasztrsmbatched_	(	type(c_ptr), value	handle,
		integer(kind(hipblas_side_left)), value	side,
		integer(kind(hipblas_fill_mode_upper)), value	uplo,
		integer(kind(hipblas_op_n)), value	transA,
		integer(kind(hipblas_diag_non_unit)), value	diag,
		integer(c_int), value	m,
		integer(c_int), value	n,
		complex(c_double_complex)	alpha,
		type(c_ptr)	A,
		integer(c_int), value	lda,
		type(c_ptr)	B,
		integer(c_int), value	ldb,
		integer(c_int), value	batchCount
	)

◆ hipblasztrsmbatched_full_rank()

integer(kind(hipblas_status_success)) function hipfort_hipblas::hipblasztrsmbatched::hipblasztrsmbatched_full_rank	(	type(c_ptr)	handle,
		integer(kind(hipblas_side_left))	side,
		integer(kind(hipblas_fill_mode_upper))	uplo,
		integer(kind(hipblas_op_n))	transA,
		integer(kind(hipblas_diag_non_unit))	diag,
		integer(c_int)	m,
		integer(c_int)	n,
		complex(c_double_complex)	alpha,
		complex(c_double_complex), dimension(:,:,:), target	A,
		integer(c_int)	lda,
		complex(c_double_complex), dimension(:,:,:), target	B,
		integer(c_int)	ldb,
		integer(c_int)	batchCount
	)

◆ hipblasztrsmbatched_rank_0()

integer(kind(hipblas_status_success)) function hipfort_hipblas::hipblasztrsmbatched::hipblasztrsmbatched_rank_0	(	type(c_ptr)	handle,
		integer(kind(hipblas_side_left))	side,
		integer(kind(hipblas_fill_mode_upper))	uplo,
		integer(kind(hipblas_op_n))	transA,
		integer(kind(hipblas_diag_non_unit))	diag,
		integer(c_int)	m,
		integer(c_int)	n,
		complex(c_double_complex)	alpha,
		complex(c_double_complex), target	A,
		integer(c_int)	lda,
		complex(c_double_complex), target	B,
		integer(c_int)	ldb,
		integer(c_int)	batchCount
	)

◆ hipblasztrsmbatched_rank_1()

integer(kind(hipblas_status_success)) function hipfort_hipblas::hipblasztrsmbatched::hipblasztrsmbatched_rank_1	(	type(c_ptr)	handle,
		integer(kind(hipblas_side_left))	side,
		integer(kind(hipblas_fill_mode_upper))	uplo,
		integer(kind(hipblas_op_n))	transA,
		integer(kind(hipblas_diag_non_unit))	diag,
		integer(c_int)	m,
		integer(c_int)	n,
		complex(c_double_complex)	alpha,
		complex(c_double_complex), dimension(:), target	A,
		integer(c_int)	lda,
		complex(c_double_complex), dimension(:), target	B,
		integer(c_int)	ldb,
		integer(c_int)	batchCount
	)

---

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

• hipfort_hipblas.f