Series of three Courses:
2014, Tuesday Sept. 23, 9:30 -17:30:
New XC40/HORNET at HLRS
2014, Wednesday Sept. 24, 9:00 - 17:30:
Efficient Parallel I/O
(This day is mostly independent
of the hardware at HLRS)
2014, Thursday-Friday, Sept. 25-26, 9:00 - 17:30:
Optimization on Cray XC40
Please book the appropriate days in the registration form!
uring August 2014 HLRS and Cray will install “HORNET” the follow-up to HERMIT. HORNET is a Cray XC40 with 3944 compute nodes. It is based on a new* processor and the Cray Aries network. The system will have some* cores, a peak performance of a few* PFLOP/s and a main memory of 493 TByte.
* for legal reasons, we currently do not announce technical details.
The first day is targeted to HERMIT users who will continue their work on HORNET. Specialists from Cray will talk about the hardware and software enhancements between the XE6 and XC40 in order to support your migration towards this new machine.
The second day is dedicated to user parallel I/O at scale. Topics are I/O hardware apects, parallel filesystems, several I/O strategies, serial I/O optimization, and I/O APIs such as MPI-IO, NetCDF, Parallel-netCDF, HDF5, SIONLib, and ADIOS. Most of the discussed topics are independent of the specific hardware at HLRS.
The third and fourth day covers a 2 day introduction workshop about porting and optimizing your application for the Cray XC40. The topics of this workshop include the Cray Programming Environment, scientific libraries and profiling tools.
HERMIT is available in Germany and Europe through this link.
2014, Tuesday Sept. 23
9:00 - 9:30: Local registration,
9:30 -17:30: New XC40/HORNET at HLRS
2014, Wednesday Sept. 24
9:00 - 17:30: Efficient Parallel I/O
2014, Thursday-Friday, Sept. 25-26
9:00 - 17:30 (Thu.), 9:00 - 16:30 (Fri.): Optimization on Cray XC40
The detailed schedule and content can be found here.
Stefan Andersson, Aniello Esposito and Michael Neff (Cray)
Academic participants (i.e., members of universities or public research institutions) from Europe or PRACE countries: Please apply through the PATC web page. After your registration, you will receive an automated "congratulation"-email about your successful registration. This email implies that you have a guaranteed seat in the course and you should organize your travel.
All other participants (not from academia, or from outside Europe), or if the PATC web page is temporarily unavailable, please apply through this online registration form.
Series of three Courses: Please book the appropriate days in the registration form!
Course number is 2014-XC30.
for registration is Sep. 14, 2014 (extended deadline).
Members of German universities and public research institutes: none.
Members of universities and public research institutes within Europe or PRACE: none.
Members of other universities and public research institutes: 120 EUR.
Others: 400 EUR.
(includes food and drink at coffee breaks, will be collected on the first day of the course, cash only)
For days 2-4 programming experience in C or Fortran, some knowledge about parallel programming.
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. The mandate for the PATCs is as follows: "The PRACE Advanced Training Centres will serve as European hubs of advanced, world-class training for researchers working in the computational sciences." (see D3.2.3)
This course is a PATC course, see also the PRACE Training Portal and Events. For participants from public research institutions in PRACE countries, the course fee is sponsored through the PRACE PATC program.
XC30 will be installed shortly before the course starts. The forerunner system is Cray XE6 (Hermit) at HLRS.
If you cannot come to the course, please send an email to the organizer as soon as possible. This would allow us to accept additional participants from the waiting-list. There is no cancelation fee.
NO-SHOW: Registered persons that do not cancel and do not show up without any reasons are blocked for the next year on any of our workshops (because it is too expensive to produce unused copies of the slides for them).
Each participant will get a paper copy of all slides.