OpenMP

Content

With the increasing prevalence of multicore processors, shared-memory programming models are essential. OpenMP is a popular, portable, widely supported, and easy-to-use shared-memory model.

Over the more than two decades of its existence, OpenMP has tracked the evolution of hardware and the complexities of software to ensure that it stays as relevant to today’s high performance computing community as it was in 1997.

This workshop will cover a range of topics, reaching from the basics of OpenMP programming, over the Tasking concept, to some important performance optimization topics, such as programming NUMA machines. The lecture will be mixed with hands-on sessions.

Agenda

• 09:00 - 10:30 Introduction: Parallel Region - Worksharing - Scoping
• 10:30 - 10:45 Break
• 10:45 - 12:15 Tasking: Tasks - Taskloop - Cut-off
• 12:15 - 13:30 Lunch Break
• 13:30 - 14:30 Hands-on
• 14:30 - 15:00 Vectorization
• 15:15 - 16:00 NUMA
• 16:00 - 17:00 Hands-on

Trainer(s)

• Dr. Christian Terboven (RWTH Aachen)

Requirements

• Programming knowledge in C/C++ or Fortran to be able to use OpenMP