Intel MKL provides C and Fortran routines to extend the functionality of the BLAS routines. These include routines to compute vector products, matrix-vector products, and matrix-matrix products.

Intel MKL also provides routines to perform certain data manipulation, including matrix in-place and out-of-place transposition operations combined with simple matrix arithmetic operations. Transposition operations are Copy As Is, Conjugate transpose, Transpose, and Conjugate. Each routine adds the possibility of scaling during the transposition operation by giving some alpha and/or beta parameters. Each routine supports both row-major orderings and column-major orderings.

Table “BLAS-like Extensions” lists these routines.

The <?> symbol in the routine short names is a precision prefix that indicates the data type:

s

REAL

d

DOUBLE PRECISION

c

COMPLEX

z

DOUBLE COMPLEX

BLAS-like Extensions

Routine

Data Types

Description

?axpby

s, d, c, z

Scales two vectors, adds them to one another and stores result in the vector (routines).

?gem2vu

s, d

Two matrix-vector products using a general matrix, real data.

?gem2vc

c, z

Two matrix-vector products using a general matrix, complex data.

?gemmt

s, d, c, z

Computes a matrix-matrix product with general matrices but updates only the upper or lower triangular part of the result matrix.

?gemm3m

c, z

Computes a scalar-matrix-matrix product using matrix multiplications and adds the result to a scalar-matrix product.

?gemm_batch

s, d, c, z

Computes scalar-matrix-matrix products and adds the results to scalar matrix products for groups of general matrices.

?gemm3m_batch

c, z

Computes a scalar-matrix-matrix product using matrix multiplications and adds the result to a scalar-matrix product.

mkl_?imatcopy

s, d, c, z

Performs scaling and in-place transposition/copying of matrices.

mkl_?omatcopy

s, d, c, z

Performs scaling and out-of-place transposition/copying of matrices.

mkl_?omatcopy2

s, d, c, z

Performs two-strided scaling and out-of-place transposition/copying of matrices.

mkl_?omatadd

s, d, c, z

Performs scaling and sum of two matrices including their out-of-place transposition/copying.

?gemm_pack_get_size

s, d

Returns the number of bytes required to store the packed matrix.

gemm_*_pack_get_size

integer

Returns the number of bytes required to store the packed matrix.

?gemm_alloc

s, d

Allocates storage for a packed matrix.

?gemm_pack

s, d

Performs scaling and packing of the matrix into the previously allocated buffer.

gemm_*_pack

integer

Pack the matrix into the buffer allocated previously.

?gemm_compute

s, d

Computes a matrix-matrix product with general matrices where one or both input matrices are stored in a packed data structure and adds the result to a scalar-matrix product.

gemm_*_compute

integer

Computes a matrix-matrix product with general integer matrices where one or both input matrices are stored in a packed data structure and adds the result to a scalar-matrix product.

?gemm_free

s, d

Frees the storage previously allocated for the packed matrix.

gemm_*

integer

Computes a matrix-matrix product with general integer matrices.

mkl_jit_create_?gemm

s, d, c, z

Creates a handle on a jitter and generates a GEMM kernel that computes a scalar-matrix-matrix product and adds the result to a scalar-matrix product, with general matrices.

mkl_jit_get_?gemm_ptr

s, d, c, z

Returns the GEMM kernel previously generated.

mkl_jit_destroy

 

Deletes the previously created jitter and the generated GEMM kernel.

Para obter informações mais completas sobre otimizações do compilador, consulte nosso aviso de otimização.
Selecione a cor do botão adesivo: 
Orange (only for download buttons)