2019-03-18 PRACE Course: Advanced Topics in High Performance Computing

In this add-on course to the parallel programming course special topics are treated in more depth, in particular performance analysis, I/O and PGAS concepts. It is provided in collaboration of Erlangen Regional Computing Centre (RRZE) and LRZ within KONWIHR.

The course is a PRACE Training event.

Each day is comprised of approximately 5 hours of lectures and 2 hours of hands-on sessions.

Tentative schedule:

Day 1 (09:00-17:00)

• Processor-Specific Optimization

Day 2 (09:00-17:00)

• 09:00-12:30 Parallel I/O with MPI IO
• 13:30-17:00 Tuning I/O on LRZ's HPC systems / I/O Profiling: Darshan tool

Day 3 (09:00-17:00)

• 09:00-12:30 Scientific Data Libraries: HDF5 / Scalable I/O library: SIONlib
• 13:30-15:30 Special Public Lecture by Intel: Intel Xeon Scalable (Skylake) processor architecture (Hörsaal, H.E.009), Lecture Flyer, Slides
  
• 15:30-17:00 SuperMUC Tour

Day 4 (09:00-17:00)

• PGAS programming with coarray Fortran and Unified Parallel C

We are happy to announce that during the course Andrey Semin (Intel) will give a special public lecture about the Intel Xeon Scalable (Skylake) processor architecture (no registration necessary).

This lecture will be devoted to the Intel Xeon Scalable (codenamed Skylake) processor that powers the brand new LRZ supercomputer: SuperMUC-NG. The presentation will cover details about Skylake core microarchitecture and Xeon uncore design. Additionally, the talk will provide details about SuperMUC-NG compute node design and the fabric system architecture.