hipblasgemmex Interface Reference

• hipfort_hipblas
• hipblasgemmex

Public Member Functions | List of all members

hipfort_hipblas::hipblasgemmex Interface Reference

BLAS EX API. More...

Public Member Functions
integer(kind(hipblas_status_success)) function	hipblasgemmex_ (handle, transa, transb, m, n, k, alpha, a, atype, lda, b, btype, ldb, beta, c, ctype, ldc, computetype, algo)

Detailed Description

BLAS EX API.

The gemmEx functions perform one of the matrix-matrix operations:

C = alpha*op( A )*op( B ) + beta*C,

where op( X ) is one of:

op( X ) = X      or
op( X ) = X**T   or
op( X ) = X**H,

alpha and beta are scalars, and A, B, and C are matrices, with op( A ) an m by k matrix, op( B ) a k by n matrix, and C an m by n matrix.

• Supported types are determined by the backend. See the cuBLAS documentation for cuBLAS backend information. For the rocBLAS backend, conversion from hipblasComputeType_t to rocblas_datatype_t happens within hipBLAS. Supported types are as follows:

aType	bType	cType	computeType
HIP_R_16F	HIP_R_16F	HIP_R_16F	HIPBLAS_COMPUTE_16F
HIP_R_16F	HIP_R_16F	HIP_R_16F	HIPBLAS_COMPUTE_32F
HIP_R_16F	HIP_R_16F	HIP_R_32F	HIPBLAS_COMPUTE_32F
HIP_R_16BF	HIP_R_16BF	HIP_R_16BF	HIPBLAS_COMPUTE_32F
HIP_R_16BF	HIP_R_16BF	HIP_R_32F	HIPBLAS_COMPUTE_32F
HIP_R_32F	HIP_R_32F	HIP_R_32F	HIPBLAS_COMPUTE_32F
HIP_R_64F	HIP_R_64F	HIP_R_64F	HIPBLAS_COMPUTE_64F
HIP_R_8I	HIP_R_8I	HIP_R_32I	HIPBLAS_COMPUTE_32I
HIP_C_32F	HIP_C_32F	HIP_C_32F	HIPBLAS_COMPUTE_32F
HIP_C_64F	HIP_C_64F	HIP_C_64F	HIPBLAS_COMPUTE_64F

hipblasGemmExWithFlags is also available. This is identical to hipblasGemmEx with the addition of a flags parameter which controls the flags used in Tensile to control gemm algorithms with the rocBLAS backend. When using a cuBLAS backend, this parameter is ignored.

Parameters

[in]	handle	- [hipblasHandle_t] handle to the hipBLAS library context queue.
[in]	transA	- [hipblasOperation_t] specifies the form of op( A ).
[in]	transB	- [hipblasOperation_t] specifies the form of op( B ).
[in]	m	- [int] matrix dimension m.
[in]	n	- [int] matrix dimension n.
[in]	k	- [int] matrix dimension k.
[in]	alpha	- [const void *] device pointer or host pointer specifying the scalar alpha. Same datatype as computeType.
[in]	A	- [void *] device pointer storing matrix A.
[in]	aType	[hipDataType] specifies the datatype of matrix A.
[in]	lda	- [int] specifies the leading dimension of A.
[in]	B	- [void *] device pointer storing matrix B.
[in]	bType	[hipDataType] specifies the datatype of matrix B.
[in]	ldb	- [int] specifies the leading dimension of B.
[in]	beta	- [const void *] device pointer or host pointer specifying the scalar beta. Same datatype as computeType.
[in]	C	- [void *] device pointer storing matrix C.
[in]	cType	[hipDataType] specifies the datatype of matrix C.
[in]	ldc	- [int] specifies the leading dimension of C.
[in]	computeType	[hipblasComputeType_t] specifies the datatype of computation.
[in]	algo	- [hipblasGemmAlgo_t] enumerant specifying the algorithm type.

Member Function/Subroutine Documentation

◆ hipblasgemmex_()

integer(kind(hipblas_status_success)) function hipfort_hipblas::hipblasgemmex::hipblasgemmex_	(	type(c_ptr), value	handle,
		integer(kind(hipblas_op_n)), value	transa,
		integer(kind(hipblas_op_n)), value	transb,
		integer(c_int), value	m,
		integer(c_int), value	n,
		integer(c_int), value	k,
		type(c_ptr), value	alpha,
		type(c_ptr), value	a,
		integer(kind(hip_r_32f)), value	atype,
		integer(c_int), value	lda,
		type(c_ptr), value	b,
		integer(kind(hip_r_32f)), value	btype,
		integer(c_int), value	ldb,
		type(c_ptr), value	beta,
		type(c_ptr), value	c,
		integer(kind(hip_r_32f)), value	ctype,
		integer(c_int), value	ldc,
		integer(kind(hipblas_compute_16f)), value	computetype,
		integer(kind(hipblas_gemm_default)), value	algo
	)

---

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

• hipfort_hipblas.F90