Computer Systems Lab
Collaboration and Distance Learning Ideas 2003
MPI - Parallel Programming Part 1

1. MPI Program Lab00, "HelloCluster.c"
   MPI_Init(), MPI_Comm_size() , MPI_Comm_rank(), MPI_Finalize() MPI_COMM_WORLD (scroll down to "Communicators")
2. MPI Program Lab01, share.c
   --Input a number with scanf, broadcast this value to other nodes in the "lamhosts" file
   uses MPI_Bcast(), also see MPI Data types
   NOTE: Place the call to MPI_Bcast outside of the "if (rank == 0)" block:

            if (rank == 0) {
   	      scanf( ... );
   	  }
   	  MPI_Bcast( ... );  //MPI_Bcast is like a combination send/receive,
   	                     //so each process needs it
   	

3. MPI Program Lab02, DinnerParty.c
   Use MPI_Send(), and MPI_Recv(), INSTEAD OF MPI_Bcast()
   Sample Output:
   mpirun N lab02
   Process 0, Sending out random int 406999 to process 1
   Process 2 received: 1252750, mysalary=380245, sending out 1632995 to process 3
   Process 3 received: 1632995, mysalary=600007, sending out 2233002 to process 4
   Process 1 received: 406999, mysalary=845751, sending out 1252750 to process 2
   Process 0 received 3014004, mySalary=157838, average salary=$460807.17
   Process 4 received: 2233002, mysalary=618007, sending out 2851009 to process 5
   Process 5 received: 2851009, mysalary=162995, sending out 3014004 to process 0
4. MPI Program Lab03, IntervalSlicing.c - Calculate Pi,
   --parallelize the program "gregory.c"
   Use MPI_Reduce() to sum data that is local to each process
5. Program LabOriginal - Your OWN MPI Parallel Programming application.
   Use these elements:
   • MPI_Init(), MPI_Comm_Rank(), MPI_Comm_Size(), MPI_Finalize()
   • MPI_Send() & MPI_Recv() OR MPI_Bcast()
   • MPI_Reduce() (Optional)
   • Think about an application using an array or a matrix
   • Example ideas:
     • CalculateFactorial (Erik Hansen),
     • ParallelMandelbrot/Julia,
     • SortArray (each process sorts part of the array),
     • SumArray (each process sums part of the array),
     • TrapezoidAreaUnderCurve (each process calculates a portion of the area)
     • Choose a "topology: Do you want processes in a "ring", "tree", or "root --> each process"
6. Show copies/screenshots of:
   • __ Program output
   • __ Link to commented code
7. SYNTAX for MPI Functions