Developer Reference for Intel® oneAPI Math Kernel Library for Fortran

ID 766686
Date 3/31/2023
Public

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents

cluster_sparse_solver_set_ptr

Internally saves a provided pointer to the data corresponding to the specified name.

Syntax

call cluster_sparse_solver_set_ptr (pt, name, ptr, comm, error)

Include Files
  • mkl_cluster_sparse_solver.f90
Description

This routine internally saves the input pointer, ptr, of the data which correspond to the provided name. The saved pointer can then be used for exporting corresponding data by means of cluster_sparse_solver_export.

NOTE:

Only call this routine after the factorization phase (phase=22) of the cluster_sparse_solver has been called. Neither pt, nor iparm should be changed after the preceding call to cluster_sparse_solver.

Input Parameters
pt

INTEGER*8 for 64-bit architectures

Array with size of 64.

Handle to internal data structure used in the prior calls to cluster_sparse_solver.

CAUTION:

Do not modify pt after the calls to cluster_sparse_solver.

name

INTEGER

Specifies the data for which the pointer is computed.

SPARSE_PTLUQT_P

Permutation P from P*A*Q=L*U.

SPARSE_PTLUQT_Q

Permutation Q from P*A*Q=L*U.

SPARSE_DPTLUQT_P

Permutation P from P* (D-1A)*Q=L*U.

SPARSE_DPTLUQT_Q

Permutation Q from P* (D-1A)*Q=L*U.

SPARSE_DPTLUQT_D

Scaling (diagonal) D from P* (D-1A)*Q=L*U.

vals

Array containing elements of the vector representation for the data which corresponds to the name. Its length should be at least local_nrows, where local_nrows is the local number of rows in a corresponding matrix (obtained from cluster_sparse_solver_get_csr_size, for example).

For permutations P and Q, it is interpreted as INTEGER.

For scaling D, it is interpreted as one of the following depending on mtype (type of the matrix A) and iparm(28) (precision) specified in the preceding call to cluster_sparse_solver.

Fortran:

 

DOUBLE PRECISION

For real types of matrices (mtype=1, 2, -2, and 11) and for double precision (iparm(28) = 0).

REAL

For real types of matrices (mtype=1, 2, -2, and 11) and for single precision (iparm(28) = 1).

DOUBLE COMPLEX

For complex types of matrices (mtype=3, 6, 13, 14, and -4) and for double precision (iparm(28) = 0).

COMPLEX

For complex types of matrices (mtype=3, 6, 13, 14, and -4) and for single precision (iparm(28) = 1).

comm

INTEGER*4

MPI communicator. The solver uses the Fortran MPI communicator internally.

Output Parameters
error

INTEGER

The error indicator:

error
Information
0

no error

-1

pt is a null pointer

-2

invalid pt

-3

invalid name

-4

unsupported name

-9

unsupported internal code path, consider switching off non-default iparm parameters for cluster_sparse_solver

-12

internal memory error

NOTE:
Refer to cl_solver_export_f90.f90 for an example using this functionality.