OpenMP* Fortran Compiler Directives

Intel® Fortran provides OpenMP* Fortran compiler directives that comply with OpenMP Fortran Application Program Interface (API) specification Version 1.1 and most of Version 2.0.

To use these directives, you must specify compiler option -openmp (Linux and Mac OS X) or /Qopenmp (Windows).

Options that use OpenMP* are available for both Intel® microprocessors and non-Intel microprocessors, but these options may perform additional optimizations on Intel® microprocessors than they perform on non-Intel microprocessors. The list of major, user-visible OpenMP constructs and features that may perform differently on Intel® microprocessors vs. non-Intel microprocessors includes: locks (internal and user visible), the SINGLE construct, barriers (explicit and implicit), parallel loop scheduling, reductions, memory allocation, thread affinity, and binding.

This section discusses data scope attribute clauses, conditional compilation rules, nesting and binding rules, and the following directives:

• ATOMIC directive

  Specifies that a specific memory location is to be updated dynamically.

• BARRIER directive

  Synchronizes all the threads in a team.

• CRITICAL directive

  Restricts access for a block of code to only one thread at a time.

• DO directive

  Specifies that the iterations of the immediately following DO loop must be executed in parallel.

• FLUSH directive

  Specifies synchronization points where the implementation must have a consistent view of memory.

• MASTER directive

  Specifies a block of code to be executed by the master thread of the team.

• ORDERED directive

  Specifies a block of code to be executed sequentially.

• PARALLEL directive

  Defines a parallel region.

• PARALLEL DO directive

  Defines a parallel region that contains a single DO directive.

• PARALLEL SECTIONS directive

  Defines a parallel region that contains SECTIONS directives.

• PARALLEL WORKSHARE directive

  Defines a parallel region that contains a single WORKSHARE directive.

• SECTIONS directive

  Specifies a block of code to be divided among threads in a team (a worksharing area).

• SINGLE directive

  Specifies a block of code to be executed by only one thread in a team.

• TASK directive

  Defines a task region.

• TASKWAIT directive

  Specifies a wait on the completion of child tasks generated since the beginning of the current task.

• TASKYIELD directive

  Specifies that the current task can be suspended in favor of execution of a different task.

• THREADPRIVATE directive

  Makes named common blocks private to a thread but global within the thread.

• WORKSHARE directive

  Divides the work of executing a block of statements or constructs into separate units.

The OpenMP parallel directives can be grouped into the categories shown in the following table:

Note that certain general directives and rules can affect DO loops. For more information, see Rules for General Directives that Affect DO Loops.

Copyright © 1996-2011, Intel Corporation. All rights reserved.