Direkt zum Inhalt | Direkt zur Navigation

Personal tools

You are here: Home » Community » Announcements » Events » Parallel Programming Workshop Fall 2016

Parallel Programming Workshop Fall 2016

last modified Jun 30, 2016 02:25 PM
A workshop at Höchstleistungsrechenzentrum Stuttgart
Event of interest
Oct 17, 2016 08:30 AM to Oct 21, 2016 04:30 PM (Europe/Vienna / UTC200)
Stuttgart (Germany)
Add event to calendar

Multicore CPUs are now everywhere. Within this one-week parallel programming course, Tuesday is focused on parallelization on multicore CPUs.
Monday is dedicated to an introduction to cluster programming with MPI, and Wednesday through Friday are dedicated to more advanced topics, e.g., the new MPI-3 shared memory programming model as an alternative to OpenMP.

The last three days are a also part of the curriculum of the PRACE Advanced Training Centres (PATCs).

Monday, Oct. 17:
Distributed memory parallelization with the
Message Passing Interface MPI (for beginners):

On clusters and distributed memory architectures, parallel
programming with the Message Passing Interface (MPI) is the
dominating programming model. The course gives an introduction
into MPI-1.

Tuesday, Oct. 18 :
Shared memory parallelization with OpenMP (for beginners):

The focus is on shared memory parallelization with OpenMP,
the key concept on hyper-threading, dual-core, multi-core,
shared memory, and ccNUMA platforms. This course teaches
shared memory OpenMP parallelization.

Wednesday-Friday, Oct. 19-21:
Intermediate and advanced topics in parallel programming:

Topics are advanced usage of communicators and virtual topologies, one-sided communication, derived datatypes, MPI-2 parallel file
I/O, hybrid mixed model MPI+OpenMP parallelization, parallelization of explicit and implicit solvers and of particle based applications, parallel numerics and libraries, and parallelization with PETSc. MPI-3.0 introduced a new shared memory programming interface, which can be combined with MPI message passing and remote memory access on the cluster interconnect. It can be used for direct neighbor accesses similar to OpenMP or for direct halo copies, and enables new hybrid programming models. These models are compared in the hybrid mixed model MPI+OpenMP parallelization session with various hybrid MPI+OpenMP approaches and pure MPI. Further aspects are domain decomposition, load balancing, and debugging.

Hands-on sessions are included on all days. This course provides scientific training in Computational Science, and in addition, the scientific exchange of the participants among themselves.

Registration and further information:

http://www.hlrs.de/training/2016/PAR and

Deadline for registration: Sep. 18, 2016

You can book all days together or you may select specific days. See the link to the online registration form on the web pages.

Lectures will be given by Martin Bernreuther, Uwe Woessner, Christoph Niethammer, Rainer Keller and Dr. Rolf Rabenseifner (member of the MPI Forum).

The course language is English. All slides and handouts are in English.

The last three days of the course is a PRACE Advanced Training Centre (PATC) courses at HLRS.

Further courses can be found at http://www.hlrs.de/training/ and http://www.hlrs.de/training/course-list/

Filed under: School, Event of interest