MPI Lectures

Introduction to MPI
- Library and implementation characteristics
- MPI for python
- Error handling
Blocking point-to-point communication
- Sending and receiving with MPI_Send and MPI_Recv
- Dynamic receiving with MPI_Probe and MPI_Status
- Groups and communicators
Non-blocking communication
Collective communication
- Synchronization (Barrier)
- Data movement (Broadcast, Gather, Scatter, Allgather, Alltoall)
- Collective computation (Reduce, AllReduce, Scan, Exscan, Reduce_scatter)
- Define your own collective routine
- Non-Blocking Collective Operations
Topology mapping and neighborhood collectives
Profiling MPI applications

Code examples

Basic Codes

hello_world.py
- Basic hello world example
rank_hello.py
- Hello world for each rank
communicator_split.py
- Splitting the processes in two groups based on their ranks (keeping the order of their original ranks)
Blocking send examples
- send_dict.py - simple blocking send of a dictionary
- send_np_array.py - simple example of sending a numpy array
- send_dtype.py - example of sending a custom datatype (tuple of int32, double64)
ping_pong.py
- Simple non-blocking communication example
sendrecv.py
- Example of using the sendrecv routine
barrier.py
- Simple barrier example
custom_collective{_np}.py
- Two examples of implementing a custom reduce operation
  - Computing the product of Complex numbers (one per each MPI process) - Complex class defined in Complex.py
  - Identifying the array indexes containing odd numbers in at least one process (all processes contining a numpy array of the same size)
wtime.py
- Time measurement for mpi processes
Cartesian topology examples cart_{topology, shift}.py
- Two examples for creating a cartesian topology and identifying the neighbor processes

Other codes

Name		Name	Last commit message	Last commit date
Latest commit History 35 Commits
basic_examples		basic_examples
other_examples		other_examples
README.md		README.md
mpi_lecture.png		mpi_lecture.png