Doctoral Academy Programme Bookings

Welcome Guest
Home > Browse > IT Skills > ARC: Introduction to Parallel Programming using Message Passing (MPI) > Details
In order to register for a session, you must first log in. You will be returned to the workshop session, once logged in.
ARC: Introduction to Parallel Programming using Message Passing (MPI)
Domain: A1 Knowledge base

TACE: A - Acquisition

Format: Workshop
Suitable for: All

A modern supercomputer can be considered at its simplest to be a collection of individual computers (known as ‘nodes’), each with their own pool of memory, connected to each other via a very fast and sophisticated network. Conventional programs are limited by the fact they can only scale up to the size of a single node, whereas there may be hundreds or even thousands of nodes available. Taking full advantage of the power of modern supercomputers requires the ability to efficiently distribute work across multiple nodes via a communications protocol known as the Message Passing Interface (MPI).
This course describes the fundamentals of MPI programming, demonstrates how to break up a single piece of work into node-sized blocks, and allows the user to create and run simple MPI programs using a common set of communication functions.