Research IT

Code Optimisation on ARCHER

Would you like to improve the performance of your applications on ARCHER?

This course on “Single Node Performance Optimisation” will cover the main features of modern HPC nodes, including multiple cores, vector floating point units, deep cache hierarchies, and NUMA memory systems.

It will also cover techniques for efficient programming of these features, using batch processing options and compiler options as well as hand tuning of code. There will also be an introduction to the use of Cray performance analysis tools.

The course will be held on the 28th – 29th November at the University of Manchester and it is free to attend due to PRACE funding. For more information and to register for the event please visit the event website.