NSC is happy to announce a three-day course in shared memory
programming using OpenMP open to all PhD students, postdocs etc.
affiliated with a Swedish research institute, as well as NSC partners
SMHI and SAAB. The course will be held at NSC between May 27 and May
29.
OpenMP provides an efficient method to write parallel programs in C, C++
and Fortran. OpenMP programs are suitable for execution on shared memory
architectures such as modern multi core systems or a single compute node
of the SNIC HPC clusters.
This course will introduce participants to the shared-memory model for
parallel programming and the OpenMP application-programming interface.
In many cases OpenMP allows an existing serial program to be upgraded
incrementally, starting with the parallelization of the most
time-consuming parts of the code. Typically OpenMP programs are easily
ported from one shared memory multi processor system to another one.
The course consists of lectures alternating with practical sessions. The
teaching language will be English. No prior experience in parallel
computing is required. Participants are however expected to be able to
write serial programs in C, C++ or Fortran. The course contents
includes:
* Shared memory programming concepts
* Syntax of the OpenMP API
* Parallel and serial regions
* Shared and private data
* Workshare constructs and scheduling
* Reductions
* Avoiding data access conflicts and race conditions
* Performance considerations for non-uniform memory access hardware
(e.g. nodes of SNIC HPC clusters)
At the end of the course participants should have the ability to
parallelize many of the computational kernels used in scientific codes.
Pre-requisites: Participants should be able to program in either of C,
C++ or Fortran at an intermediate level. For the practical sessions,
participants are required to bring their own laptop computers.
The lecturer Joachim Hein is the SNIC parallel programming expert based
at Lunarc, the Center for Scientific and Technical Computing at Lund
University. He is also a researcher at the Centre of Mathematical
Sciences at Lund University and a computing architect at EPCC at The
University of Edinburgh in Scotland. He has more than 18 years
experience in parallel computing.
The course is open to all PhD students, postdocs etc. affiliated with a
Swedish research institute, as well as NSC partners SMHI and SAAB, but
the number of seats are limited and will be reserved on a first come,
first served basis. Registration is open until Friday May 10. The course
will be held at NSC, Campus Valla, Linköping University. Course
registration and other details can be found at URL
http://www.nsc.liu.se/openmp-course.
