Intel® oneAPI Math Kernel Library
Ask questions and share information with other developers who use Intel® Math Kernel Library.

C++ wrapper for CBLAS available on github

tdoris
Beginner
880 Views
I have written a C++ wrapper for CBLAS which some people may find useful, details are here:

http://wiki.github.com/tdoris/cppmkl

Main ideas are:
1. Provide wrapper functions that accept any conforming matrix type as an argument. In the wrapper figure out what the appropriate values for the various matrix shape parameters to the raw MKL function; i.e., it is possible to use any matrix type with these functions.
2. The wrapper functions figure out what underlying MKL function to call based on the type of data (float, double, MKL_Complex8/16) contained in the matrix.
3. Provide some generic functionality like an STL allocator so that STL-container-managed-storage can be used with MKL without loss of precision or performance.
4. Provide a simple matrix class that serves as a container for the raw matrix elements.


0 Kudos
3 Replies
Ilya_B_Intel
Employee
880 Views
Interesting project. C++ users might be welcoming it when it is done.

It seems that there is some space for improvments in your current codes. For example, I would add some includes here and there (cppmklcppmkl_allocator.h isin lack of #include and #include ).

Best wishes in your start.
0 Kudos
tdoris
Beginner
880 Views
llya, well spotted, omitting these headers does not cause an error on my compiler but you are correct, they should be there, this is fixed.

The API now also supports using the boost matrix class with the cppmkl functions. I have also added wrapper functions for the VML API.
0 Kudos
Umutgokdg
Beginner
523 Views

ı can not see your repository, can you update your link please, thank you

0 Kudos
Reply