Lecture 10

Lecture 10: MPI Examples
Date: Monday, October 7, 2024

Agenda

Announcements
- Schedule update: Midterm exam delayed until after October break: Friday, October 25
- Create your accounts on ACCESS CI so I can set up Stampede3 access (see email from last week)
- Submission/grading updates
- Lab 6: Collective Communication Practice [HTML] [PDF] should be done
- Programming Project 4: Collective Communication [HTML] [PDF] due tomorrow
Example: MPI implementation of Conway's Game of Life
- Uses a distributed data structure: Each process maintains its own subset of the computational domain, in this case just some of the rows of the grid. Other processes do not know about the data on a given process. Only the data that is needed to compute the next generation, a one-cell overlap (sometimes called ghost cells or a halo), is exchanged between neighbors before each iteration.
- When we need to get a global count of some statistic, such as the count of live cells at the start, we use a reduction.
- The communication of cell data between iterations is done with two pairs of sends and receives. Here, we use nonblocking calls, then wait for their completion with the MPI_Waitall call.
- This example also shows a technique for writing a file when the intended contents are distributed among a set of processes.
Programming Project 5: Parallelizing Jacobi Iteration [HTML] [PDF] introduction
More MPI Examples: parallelizations of matrix-matrix multiplication (see topic notes)

Terminology

Examples