Parallelization openMP

A routine to compute the matrix vector product c = Ab using a hybrid multi-threading and message-passing technique. The algorithm shown combines the MPI and OpenMP parallelizations illustrated in Figures 4.4 and 4.6. Since all MPI calls are from the main thread, MPI need only support the "funneled" level of multi-threading. 

Calculations were performed on Linux-cluster using parallel MPI (MPICH2) H SMP (OpenMP) parallel paradigms. 

To use OpenMP on each node to implement the parallel work on each node. 

Hybrid OpenMP/MPI parallelization is used to compute Hv. The multithreaded OpenMP library is used for parallelization within each node, while MPI is used for communication between nodes. The subroutine fipsi that computes Hv contains two arrays of the same size the results of the portion of the calculation local to a node are stored in hps local, while the results of the portion of the calculation that requires communication are stored in hpsbujf. On each node, a dedicated (master) OpenMP thread performs all the communication, while other threads perform local parts of the work. In general, one uses as many threads as there are processors on a given node. The following scheme presents an overview of the execution of subroutine, hpsi ... 

The shared memory OpenMP library is used for parallelization within each node. The evaluation of the action of potential energy, rotational kinetic energy, and T2 kinetic energy are local to each node. These local calculations are performed with the help of a task farm. Each thread dynamically obtains a triple (/2, il, ir) of radial indices and performs evaluation of first the kinetic energy and then the potential energy contribution to hps local( , i2, il, ir) for all rotational indices. 

Quinn, M. J. Parallel Programming in C with MPI and OpenMP. New York McGraw-Hill, 2003. 

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... 

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. 

OpenMP is a set of compiler extensions to facilitate development of multithreaded programs. We describe these compiler extensions, using example source code illustrating parallel programming with OpenMP. 

L. Rohit Chandra, D. Dagum, D. Maydan, J. Kohr, and R. M. McDonald. Parallel Programming in OpenMP (Morgan Kaufmann, San Francisco, 2000). 

B. Chapman, G. dost, and R. van der Pas. Using OpenMP Portable Shared Memory Parallel Programming (The MIT Press, Cambridge, 2007). 

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... 

---