Intel® MKL v.10.2 provides auxiliary routines called as matrix converter routines that convert sparse matrix from one storage format to another. These routines are declared in mkl_spblas.fi for FORTRAN 77 interface and in mkl_spblas.h for C interface.

See below the list of the Matrix Converter Routines available:

mkl_ddnscsr:
Stores a sparse matrix in the CSR format (3-array variation).

mkl_dcsrcoo:
Converts a sparse matrix in the CSR format (3-array variation) to the coordinate format and vice versa.

mkl_dcsrbsr:
Converts a sparse matrix in the CSR format to the BSR format (3-array variations) and vice versa.

mkl_dcsrcsc:
Converts a sparse matrix in the CSR format to the CSC and vice versa (3-array variations).

mkl_dcsrdia:
Converts a sparse matrix in the CSR format (3-array variation) to the diagonal format and vice versa.

 mkl_dcsrsky:
Converts a sparse matrix in the CSR format (3-array variation) to the sky line format and vice versa.

User can also refer to the MKL Manual ( mklman.pdf ) document, Chapter 2: "BLAS and Sparce BLAS Routines" for further information.

Comment 1:
There are 2 examples program for using MKL Sparse format converters. You can find these files into directory: MKLROOT\examples\spblas\source\ and you can find there two "C" and "Fortran" based examples: converters_c.c and converters_f.f

Comment 2:
know restriction for this topic: the current implementation supports only double precision data types for such functionality
by another words single complex, double complex and single precition data types are not supported currently

Comment 3:
if somebody are interested in supporting another data types (mentioned into comment 2), we are encourage you submit the issue against MKL to Premier support (https://premier.intel.com/ )