Intel® Moderncode for Parallel Architectures
Support for developing parallel programming applications on Intel® Architecture.

MKL: What to buy?


Hello I am quite disorientated about your MKL library.
I mean, I have developed a calculation software in C# that involves linear system resolution, with dense matrix (complex numbers). My resolution system is very slow, so I was very interested in your library but what to try?
What is Parallel Studio XE? and Which is the difference between Cluster, Professional and Composer Edition?
There are also dll for 64 and 32 bit?

Thank you for any help



0 Kudos
1 Reply
Black Belt

I suppose the Intel web pages seem unnecessarily confusing.   We've learned not to expect logic from marketing.  In case you want MKL by itself, did you try out ?  No doubt, part of the aim in making MKL available for use such as you mention would be to induce you to consider purchasing a more complete Intel Software Tools package.

By contrast, the announcement page about Parallel Studio (possibly on account of it being a paid product) seems relatively straightforward, aside from the extra marketing jargon.  Each of the packages includes both 32- and 64-bit compilers and libraries, with the option to install either or both.  Separate packages are available for Windows, linux, or Mac OSX.

Composer means simply a Fortran or C++ compiler, plus the MKL and other libraries (with 1 year of support).  The compilers include a more complete combination of optimization and listing reports than the competition, perhaps justifying the term "composer."  The installer tools attempt to be aware of the full Parallel Studio framework; for example, if you buy both Fortran and C++, they integrate into a package.

Professional adds the VTune Amplifier profiler and Advisor tools to help with performance optimization, and Inspector to check correctness of C/C++ or Fortran parallelization.

Cluster includes everything, both C++ and Fortran and the Professional tools, plus Intel MPI and MPI performance analysis tools (primarily for programming distributed memory parallel applications).  This one isn't available for Mac.

0 Kudos