Introduction to parallel programming with MPI and OpenMP @ JSC

The course provides an introduction to parallel programming of supercomputers in technical and scientific environments. It focuses on the use of the Message Passing Interface (MPI), the most common programming model for distributed memory systems. It also covers OpenMP, which is used on shared memory systems.

The first four days of the course consist of lectures and short exercises. On the fifth day, much of the course content will be revisited and applied in the context of a larger example. For this purpose, starting from a simple but representative serial algorithm, a parallel version will be designed and implemented using the technologies learned.

Agenda:

Day 1:

Introduction
MPI Basics
MPI point-to-point communication

Day 2:

MPI Collective Communication
MPI Data types

Day 3:

MPI I/O
MPI Communicators
MPI Thread compliance

Day 4:

OpenMP Parallel construct
OpenMP Data sharing
OpenMP Loop work sharing
OpenMP Task work sharing

Day 5:

Tutorial from serial to parallel program

Official language

The official language  is English.

Prerequisites

Experience in C, C++ or Fortran, Basic knowledge in UNIX/Linux

Application

This course will take place as an online event. The link to the streaming platform will be provided to the accepted registrants only.

Registrations are only considered until 20 July 2022,

Register here