This is the first of two presentations on MPI Collective Communication routines. If you've studied our presentations on Point-to-Point Communications you've learned about routines that allow you to take a single process in your parallel code and send a message from that process and pick up that message on a single other process within the parallel program. With the collective communication routines, you're going to see how you can use one subroutine call to communicate amongst a whole group of processes within your parallel code. In this presentation, we're going to talk about the specific subroutines within the collective communication suite of routines and how you use them. At the end of the presentation we'll talk a little bit about performance issues. There is a second talk, Collective Communications II, in which you'll learn more about some of the advanced routines.