OpenMP directives

The OpenMP directives shown in Table C.2 can be divided into those that specify parallel regions, work-sharing constructs, and synchronization constructs. The primary OpenMP directive is parallel, and the block of code that follows this statement is a parallel region that will be executed by multiple threads, namely a team of threads created by the thread encountering... 

Selected OpenMP directives and their effect. C/C++ directives are shown, and... 

The previous version of the BzzMath library (release 6.0) is updated until May 20, 2011 and will not undergo any further development. Moreover, the new release 7.0 has been extended quite significantly, particularly for classes dedicated to optimization and exploitation of openMP directives and to differential, differential-algebraic, and boundary value problems. 

In the BzzMath library, all the classes for the calculation of definite integrals automatically exploit the openMP directives when the compiler allows it... 

Conversely, if multiprocessor computers and openMP directives are used, the BzzFunctionRootMP class should be adopted under the same above-mentioned condition. It is worthwhile remarking that if we use objects from the BzzFunctionRootMP class, we must also use a compiler that supports openMP directives and activate them. 

If several processors are available and if the compiler is predisposed to use the openMP directives, this will speed up the calculations. 

The BzzMinimizationMultiVeryRobust class, implemented in the BzzMath library for robust multidimensional minimization, uses a number of points N > 4. If the number of processors np < 4, N = 4. If wp > 4 and the compiler exploits openMP directives, N = np so as to assign a dedicated processor to each object in the inner optimization. 

The user cannot exploit openMP directives in his/her own code portion since this would lead to a conflict with the automatic parallelization of the BzzMath classes. Before using parallel computing in the user code, it is mandatory to disable parallel computing in the library. This is very simply done by introducing the following statement into the main ... 

Algorithm robustness, using the openMP directives for shared memory parallel computing, is also investigated and implemented for function root-finding in... 

Pragmas take the form of a C preprocessor statement/ and compilers that do not recognize a pragma will ignore them. OpenMP pragmas begin with the keyword omp, which is followed by the desired directive ... 

OpenMP provides work-sharing constructs that make it unnecessary for the programmer to provide code that explicitly distributes the work among threads. A work-sharing construct binds to the thread team created by the innermost parallel directive within which the construct is nested. 

As can be seen from the above examples, a parallel directive is often followed immediately by a work-sharing directive. Therefore, OpenMP supports combined directives where the work-sharing directive is on the same line as the parallel directive, as follows ... 

During the multi-threaded parallel execution inside of an OpenMP worksharing region, it is sometimes necessary to explicitly coordinate the activity of the threads. We have already seen an example of implicit synchronization with the reduction clause of the for directive, which causes each thread to ensure that updates to the reduction variables occur in a thread-safe manner. 

---