OpenMP* is a parallel programming framework for C, C++, or Fortran code. Using OpenMP requires few source changes and is supported by multiple compilers. Because OpenMP is supported by OpenMP libraries, you modify your source code with compiler directives rather than using types, variables, and calls. An OpenMP program can often be changed from parallel execution to serial execution by omitting a compiler option so the compiler ignores the OpenMP directives.
OpenMP 2 is very good at using several cores on loops that process arrays, but does not support irregular parallelism through general tasking. It is supported by the Microsoft, the Intel, and the GNU* C, C++ and Fortran compilers. It is difficult to use OpenMP version 2 for situations other than simple divisions of statement sequences or complete loop bodies.
The OpenMP 3.0 specification adds TASK support. The TASK directives enable performing arbitrary pieces of an algorithm in parallel. The Intel compilers support OpenMP 3.0 and some parts of OpenMP 4.0. For Intel, Microsoft, and GNU* compilers, consult your compiler documentation for the level of OpenMP support.
If your application is written in Fortran, OpenMP is the only high-level parallel framework available.