Skip to main content


Introduction

Collective communication involves all the processes in a communicator. (Communicators were introduced in Basics of MPI Programming.) The purpose of collective communication is to manipulate a shared piece or set of information. The collective communication routines have been built upon point-to-point communication routines. You could build your own collective communication routines in this way, but it might involve a lot of tedious work and might not be as efficient.

Although other message-passing libraries provide some collective communication calls, none of them provides a set that is as complete and robust as the one provided by MPI. In this module, we introduce these routines in three categories: synchronization, data movement, and global computation. MPI-3 introduced nonblocking variants of all its collective communication calls, which are also discussed after the the other categories of routines.

Cornell Center for Advanced Computing

Revised and updated by Brandon Barker
October 2014