Parallel Computing: Lecture 11

Learning objectives

After this class, you should be able to:

1. Explain the parallelization of Floyd's algorithm, and derive its time complexity using different decompositions.
2. Given an adjacency matrix and the number of processors, show the steps taken by the parallel Floyd's algorithm to determine the shortest distance between all pairs of processors.
3. Write parallel code using MPI_Send, MPI_Recv, MPI_Bcast, and other MPI functions that we have studied so far.

Reading assignment

1. Chapter 6, Chapter 5 section 5.5.1.
2. None.

Exercises and review questions

• Questions on current lecture's material
  1. (Programming) Exercise 6.8. Report your results on blackboard.
  2. Exercise 6.5.

• Questions on next lecture's material
  1. None.