From: Rolf Rabenseifner <rabenseifner@hlrs.de>
Reply-To: Rolf Rabenseifner <rabenseifner@hlrs.de>,
 Lucienne Dettki <dettki@hlrs.de>
To: contact@ins.uni-bonn.de
Subject: OpenMP GPU directives, an alternative to CUDA - Mar 12-13, 2018
Message-Id: <20180115144801.6AFAE89C2E@awsrr.hlrs.de>
Date: Mon, 15 Jan 2018 15:48:01 +0100 (CET)

Dear Madam or Sir/ Sehr geehrte Damen und Herren,

In previous years, we taught CUDA to several hundred course participants.
The accelerator directives within the OpenMP standard and its
predecessor OpenACC are a serious, efficient and also simple 
alternative to CUDA programming. 
Please, can you pass this GPU course announcement also to 
interested colleagues.  / Es waere schoen, wenn Sie diese Ankuendigung 
auch an interessierte Kollegen weitergeben koennten.

http://www.hlrs.de/training/2018/GPU - further details see below.

Kind regards / Mit freundlichen Gruessen
Rolf Rabenseifner and Lucienne Dettki


======================================================================
                      Call for Participation
======================================================================
Dear HPC-user,

OpenMP and OpenACC GPU directives are open standards, as simple 
as OpenMP for parallelization, but with a performance opportunity 
similar to CUDA, and also available on other hardware systems.

I hope to awaken your interest in this emerging technology
in the area of High Performance Computing (HPC).
Specialists from Cray and HLRS (Stefan Andersson and Nils Urmersbach)
will teach this course and assist you in the hands-on sessions.


               OpenMP GPU Directives for
           Parallel Accelerated Supercomputers -- 
       an alternative to CUDA from Cray perspective. 
                   March 12-13, 2018
      at HLRS, Nobelstr. 19, Stuttgart, Ruehle-Saal.


Abstract:
This workshop will cover the directive-based programming 
model based on OpenMP v4.5 whose multi-vendor support 
allows users to portably develop applications for 
parallel accelerated supercomputers. 
It also includes the predecessor interface OpenACC v2. 
The workshop will also demonstrate how to use the Cray 
Programming Environment tools to identify application 
bottlenecks, facilitate the porting, provide accelerated 
performance feedback and to tune the ported applications. 
The Cray scientific libraries for accelerators will be 
presented, and interoperability of the directives 
approach with these and with CUDA will be demonstrated. 
Through application case studies and tutorials, users 
will gain direct experience of using both OpenMP and 
OpenACC directives in realistic applications. 
Users may also bring their own codes to discuss with Cray 
specialists or begin porting. 
 
Further information on this course and registration,
please see 
        http://www.hlrs.de/training/2018/GPU
 
(You may have to accept an unofficial certificate before you can 
 view the course page - my apologies for this)

We will provide a system with test accounts for the participants.

Deadline for registration is already Feb. 11, 2018.

This course is a PRACE Advanced Training Centre (PATC) course at HLRS.
The course language is English. 

I hope, we can see you in Stuttgart,
best regards
Rolf Rabenseifner

PS: 
  Information on further courses:
  - by HLRS: 
  http://www.hlrs.de/training  and
  http://www.hlrs.de/training/course-list
  - by the Gauss Centre of Supercomputing (GCS):
  http://www.gauss-centre.eu/training
  - by the PRACE Advanced Training Centres (PATCs)
  http://www.training.prace-ri.eu/


---------------------------------------------------------------------
HLRS Online Courses:   http://www.hlrs.de/training/par-prog-ws/

As a member of the HLRS course mailing list, you should have received
the password with an email titled "Get your access to HLRS online courses".
---------------------------------------------------------------------


---------------------------------------------------------------------
We would appreciate if you could forward this email (without the
following personal subscription-paragraph) to interested colleagues.
---------------------------------------------------------------------

---------------------------------------------------------------------
Based on an upcoming law change, as mentioned in my prior email
from Dec. 04, 2017, we kindly ask you to follow this link
http://java.hlrs.de/subscription/elist?addr=contact@ins.uni-bonn.de&chk=208&a=YES
to acknowledge your interest in continuing to receive mailings from HLRS.

Please also note that if you do not acknowledge your agreement, it will no
longer be possible for you to access our online course recordings.

If you receive double postings or you want to stop my postings,
then please unsubscribe at any time through visiting
http://java.hlrs.de/subscription/elist?addr=contact@ins.uni-bonn.de&chk=208&a=UNSUBSCRIBE
---------------------------------------------------------------------


---------------------------------------------------------------------
Dr. Rolf Rabenseifner .. . . . . . . . . . email rabenseifner@hlrs.de
Lucienne Dettki . . . .. . . . . . . . . . . . . . . . dettki@hlrs.de
High Performance Computing Center (HLRS) . phone ++49(0)711/685-65530
University of Stuttgart .. . . . . . . . . and : ++49(0)711/685-63894
Nobelstr. 19, D-70569 Stuttgart, Germany
---------------------------------------------------------------------