Introduction to Parallelization with OpenMP

Course material:

• Primary course material
• Alternative course material

This course covers code parallelization on shared memory systems using the OpenMP standard. The course covers relevant architectural features for the systems involved and then proceeds with basic ideas of parallelism, threads, OpenMP directives, compiler options, performance issues, and common problems. To a good extent the presentation of the material is example driven. The Introduction to Unix and Scalar Code Optimization courses provide essential background material for this course. You are strongly encouraged to attend these courses prior to attending this parallelization short course.

The schedule of topics for this course as follows:

• Day 1
  • Architectural overview
  • Shared memory parallelization concepts
  • Compiling and running OMP programs
• Day 2
  • OpenMP directives
  • OpenMP run-time library
• Day 3
  • Performance monitoring and tuning
  • Common problems