! Date changed to April 4-7, 2017 ! (last modified Dec 05, 2016)
In August 2015, the Cray XC40 supercomputer Hornet at HLRS was upgraded to a new system named "Hazel Hen", featuring 7712 compute nodes, each equipped with two 12 core Intel Haswell processors running at 2.5 GHz. Each node is equipped with 128 GB DDR4 memory and connected to the other nodes through the Cray Aries network. The peak performance amounts to 7.4 PFlops.
In order to help users running efficiently on this new large system, HLRS and Cray offer an optimization workshop. The intent of this workshop is to enhance the node-level performance as well as scaling of user applications by detecting, locating and eliminate bottlenecks.
By doing so, users can raise the volume as well as quality of their scientific findings while the costs (in terms of core hours) stay constant.
Target audience: Code owners of applications already running on Hazel Hen.
With support from CRAY and HLRS specialists, participants will enhance the efficiency of their application. In order to gain knowledge of and improve the application's behavior, profiling tools as well as optimization methods are discussed and exercised, both on simple examples and the actual user application. All categories of potential bottlenecks (CPU, memory subsystem, communication and I/O) will be addressed. Besides intensive hands-on sessions, there will be lectures and discussions on:
9:00 - 9:30 Local registration
9:30 - 17:30 Course
2nd and 3rd day
9:00 - 17:30 Course
9:00 - 16:30 Course
In order to attend the workshop, you will have to bring your own code including a dataset that can be used at the scale of your current and maybe future production runs. You will be required to do some work on your application before the workshop (details will follow). In order to do so, you should already have an account on Hazel Hen and your application should already be able to run on the system. Information on access to Hazel Hen from Germany and Europe is available through this link.
German (in English, if required)
Stefan Andersson and Mandes Schönherr (Cray)
Handouts will be available to participants in printed as well as digital form.
Members of German universities and public research institutes: none
Members of universities and public research institutes within EU or PRACE-member countries: none
Members of other universities and public research institutes: 120 EUR
Others: 400 EUR
(includes coffee breaks)
see our How to find us page.
HLRS is part of the Gauss Centre for Supercomputing (GCS), which is one of the six PRACE Advanced Training Centres (PATCs) that started in Feb. 2012.
HLRS is also member of the Baden-Württemberg initiative bwHPC-C5.
This course is provided within the framework of the bwHPC-C5 user Support. This course is not part of the PATC curriculum and is not sponsored by the PATC program.