mkl_?csrgemv

Computes matrix - vector product of a sparse general matrix stored in the CSR format (3-array variation) with one-based indexing.

Syntax

Fortran:

call mkl_scsrgemv(transa, m, a, ia, ja, x, y)

call mkl_dcsrgemv(transa, m, a, ia, ja, x, y)

call mkl_ccsrgemv(transa, m, a, ia, ja, x, y)

call mkl_zcsrgemv(transa, m, a, ia, ja, x, y)

C:

void mkl_scsrgemv (char *transa, MKL_INT *m, float *a, MKL_INT *ia, MKL_INT *ja, float *x, float *y);

void mkl_dcsrgemv (char *transa, MKL_INT *m, double *a, MKL_INT *ia, MKL_INT *ja, double *x, double *y);

void mkl_ccsrgemv (char *transa, MKL_INT *m, MKL_Complex8 *a, MKL_INT *ia, MKL_INT *ja, MKL_Complex8 *x, MKL_Complex8 *y);

void mkl_zcsrgemv (char *transa, MKL_INT *m, MKL_Complex16 *a, MKL_INT *ia, MKL_INT *ja, MKL_Complex16 *x, MKL_Complex16 *y);

Include Files

  • Fortran: mkl.fi
  • C: mkl.h

Description

The mkl_?csrgemv routine performs a matrix-vector operation defined as

y := A*x

or

y := A'*x,

where:

x and y are vectors,

A is an m-by-m sparse square matrix in the CSR format (3-array variation), A' is the transpose of A.

Note

This routine supports only one-based indexing of the input arrays.

Input Parameters

Parameter descriptions are common for all implemented interfaces with the exception of data types that refer here to the FORTRAN 77 standard types. Data types specific to the different interfaces are described in the section "Interfaces" below.

transa

CHARACTER*1. Specifies the operation.

If transa = 'N' or 'n', then as y := A*x

If transa = 'T' or 't' or 'C' or 'c', then y := A'*x,

m

INTEGER. Number of rows of the matrix A.

a

REAL for mkl_scsrgemv.

DOUBLE PRECISION for mkl_dcsrgemv.

COMPLEX for mkl_ccsrgemv.

DOUBLE COMPLEX for mkl_zcsrgemv.

Array containing non-zero elements of the matrix A. Its length is equal to the number of non-zero elements in the matrix A. Refer to values array description in Sparse Matrix Storage Formats for more details.

ia

INTEGER. Array of length m + 1, containing indices of elements in the array a, such that ia(i) is the index in the array a of the first non-zero element from the row i. The value of the last element ia(m + 1) is equal to the number of non-zeros plus one. Refer to rowIndex array description in Sparse Matrix Storage Formats for more details.

ja

INTEGER. Array containing the column indices for each non-zero element of the matrix A.

Its length is equal to the length of the array a. Refer to columns array description in Sparse Matrix Storage Formats for more details.

x

REAL for mkl_scsrgemv.

DOUBLE PRECISION for mkl_dcsrgemv.

COMPLEX for mkl_ccsrgemv.

DOUBLE COMPLEX for mkl_zcsrgemv.

Array, size is m.

On entry, the array x must contain the vector x.

Output Parameters

y

REAL for mkl_scsrgemv.

DOUBLE PRECISION for mkl_dcsrgemv.

COMPLEX for mkl_ccsrgemv.

DOUBLE COMPLEX for mkl_zcsrgemv.

Array, size at least m.

On exit, the array y must contain the vector y.

Interfaces

FORTRAN 77:

SUBROUTINE mkl_scsrgemv(transa, m, a, ia, ja, x, y)
   CHARACTER*1  transa
   INTEGER      m
   INTEGER      ia(*), ja(*)
   REAL       a(*), x(*), y(*)

SUBROUTINE mkl_dcsrgemv(transa, m, a, ia, ja, x, y)
   CHARACTER*1  transa
   INTEGER      m
   INTEGER      ia(*), ja(*)
   DOUBLE PRECISION       a(*), x(*), y(*)

SUBROUTINE mkl_ccsrgemv(transa, m, a, ia, ja, x, y)
   CHARACTER*1  transa
   INTEGER      m
   INTEGER      ia(*), ja(*)
   COMPLEX       a(*), x(*), y(*)

SUBROUTINE mkl_zcsrgemv(transa, m, a, ia, ja, x, y)
   CHARACTER*1  transa
   INTEGER           m
   INTEGER           ia(*), ja(*)
   DOUBLE COMPLEX    a(*), x(*), y(*)

C:

void mkl_scsrgemv(char *transa, int *m, float *a,
int *ia, int *ja, float *x, float *y);

void mkl_dcsrgemv(char *transa, int *m, double *a,
int *ia, int *ja, double *x, double *y);

void mkl_ccsrgemv(char *transa, int *m, MKL_Complex8 *a,
int *ia, int *ja, MKL_Complex8 *x, MKL_Complex8 *y);

void mkl_zcsrgemv(char *transa, int *m, MKL_Complex16 *a,
int *ia, int *ja, MKL_Complex16 *x, MKL_Complex16 *y);
Para obtener más información sobre las optimizaciones del compilador, consulte el aviso sobre la optimización.