Collective communication using broadcast

During the development of a parallel code, we often find ourselves in the situation where we have to share between multiple processes the value of a certain variable at runtime or certain operations on variables that each process provides (presumably with different values).

To resolve this type of situations, the communication trees are used (for example the process 0 sends data to the processes 1 and 2, which respectively will take care of sending them to the processes 3, 4, 5, and 6, and so on).

Instead, MPI libraries provide functions ideal for the exchange of information or the use of multiple processes that are clearly optimized for the machine in which they are performed.

Broadcasting data from process 0 to processes 1, 2, 3, and 4

A communication method that involves all the processes belonging to a communicator is called a collective communication. Consequently, a collective communication generally involves more than two processes. However, instead...