Introduction to HPC

Course overview

The Introduction to High Performance Computing (HPC) course introduces fundamental HPC principles and techniques that can be used to address problems in computational science and engineering domains.

After motivating the use of HPC as a complement to theory and experiment and introducing the basic concepts of parallel computing, we outline the hardware design of modern HPC platforms and the parallel programming models that they support. The principal methods of measuring and characterising serial and parallel performance are then covered.

This course is taught using a variety of methods including formal lectures, practical exercises, programming examples and informal tutorial discussions. The practical session covers, logging into the ICHEC systems, code compilation, makefiles, batch job submission, speed-up measurement and the use of a taskfarm, optimization flags, libraries and debuggers. The supporting of the lecture material by the tutored practical sessions helps to reinforce the key concepts.

Learning Outcomes

After the practical session, users should be able to

• Login to the ICHEC Stokes cluster
• Compile code on Walton and create a Makefile
• Utilize the available libraries and optimization flags
• Submit a PBS batch job to the queue
• Calculate speed-up using a sequential and MPI code
• Debug code using DDT

Pre-requisites

• Some basic Linux/Unix knowledge and an interest in High Performance Computing.

Course Timetable

Slides

The course slides are currently unavailable.

Further Information

For further information please contact us at training@ichec.ie