Actions and Detail Panel
Introduction to parallel programming with MPI
Thu, 24 Aug 2017, 10:00 – Fri, 25 Aug 2017, 17:00 BST
In order to take full advantage of High Performance Computing (HPC) systems, it is necessary to be able to run jobs across a large number of cores, which may be spread over many nodes of the machine. We therefore need to write our code in a way that allows data to be transferred between these processes. The de facto standard for writing the message passing used in such parallel codes is MPI. This course will cover the essentials of MPI programming and communication. This will allow the attendees to use MPI in their own codes and so take full advantage of the processing power offered by these machines.
Prerequisite: Attendees should be able to program in either Fortran, C or C++
Jon Gibson is a technical consultant at the Numerical Algorithms Group. He has 25 years’ experience in scientific programming and has worked for two national HPC services in the UK. He has taught MPI at a number of UK universities, including Imperial College, the University of Cambridge and the University of Sheffield.