FORTRAN INTERFACE

use elpa
class(elpa_t), pointer :: elpa

call elpa%eigenvalues_float_complex (a, ev, error)

With the definitions of the input and output variables:

class(elpa_t) :: elpa ! returns an instance of the ELPA object

datatype :: a

The matrix a for which the eigenvalues should be computed. The dimensions of matrix a must be set BEFORE with the methods elpa_set(3) and elpa_setup(3). The datatype of the matrix must be complex(kind=c_float_complex). The matrix has to be hermitian this is not checked by the routine. In case of a GPU build a can be a device pointer of type "type(c_ptr) to a matrix a on the device memory.

datatype :: ev

The vector ev where the eigenvalues will be stored in ascending order. The datatype of the vector ev must be "real(kind=c_float)". In case of a GPU build ev can be a device pointer of type "type(c_ptr) to the vector of eigenvalues in the device memory

integer, optional :: error

The return error code of the function. Should be "ELPA_OK". The error code can be querried with the function elpa_strerr(3)

C INTERFACE

#include <elpa/elpa.h>
elpa_t handle;

void elpa_eigenvalues_float_compplex(elpa_t handle, datatype *a, datatype *ev, int *error);

With the definitions of the input and output variables:

elpa_t handle;

The handle to the ELPA object

datatype *a;

The matrix a for which the eigenvalues should be computed. The dimensions of the matrix must be set BEFORE with the methods elpa_set(3) and elpa_setup(3). The datatype must be "float complex". The matrix has to be symmetric, this is not checked by the routine. In case of a GPU build a can be a device pointer to a matrix a on the device memory.

datatype *ev;

The storage for the computed eigenvalues. Eigenvalues will be stored in ascendig order. The datatype must be "float". In case of a GPU build ev can be a device pointer to the vectors of eigenvalues in the device memory.

int *error;

The error code of the function. Should be "ELPA_OK". The error codes can be querried with elpa_strerr(3)