OpenMP at SC15

In my previous blog post I stated that OpenMP 4.5 is on it’s way and scheduled for a release during SC15. If you are interested in learning about OpenMP, SC15 can be a great opportunity. This blog post points out all the related activities that I have been made aware of.

Tutorials on Sunday and Monday

On Sunday the full-day tutorial A Hands-On Introduction to OpenMP will take place, covering the core features of OpenMP 4.0. On Monday, there will be the full-day tutorial Advanced OpenMP: Performance and 4.1 Features (we did not expect the name change at the time of the submission) which basically continues from the introductory tutorial and concentrates on getting performance from OpenMP codes as well as it discusses language features introduced with OpenMP 3.x and 4.x in-depth. In addition to those two tutorials with a focus on programming, the half-day tutorial Debugging & Performance Tools for MPI and OpenMP 4.0 APIs provides exploration of parallel debugging and optimization focused on techniques that can be used with accelerators and coprocessors.

The OpenMP BoF

This year’s BoF is titled OpenMP: Where Are We, and What’s Next?. I think that is a reasonable question to ask at this point. The BoF will take place on Tuesday 5:30 – 7:00 pm in room 291. From the description: Experts will give short presentations on key OpenMP 4.1 features and answer your technical questions. OpenMP CEO Michael Wong will present our vision for OpenMP 5.0 and we’ll finish with an audience-led discussion with a panel including members of the OpenMP ARB.

The OpenMP Booth and Booth Talks

As in previous years the OpenMP organization has its own booth, which is number #2036. Most important, every day from 4 pm to 6 pm there will be free beer (while supply lasts), and with that the opportunity to talk to OpenMP folks in person. There are also a couple of talks scheduled to take place right at the OpenMP booth, which will be recorded and published online:

  • Power Optimization Strategies in OpenMP, on Tuesday 11:15 – 11:40 am, by A. Malik (University of Houston),
  • OpenMP and the Multicore Association (MCA), on Tuesday 2:15 to 2:40 pm, by S. Chandrasekaran (University of Delaware),
  • Getting OpenMP up to Speed, on Wednesday 11:15 – 11:40 pm, by R. van der Pas (Oracle),
  • OpenMP Tasking, on Wednesday 2:15 to 2:40 pm, by M. Klemm (Intel) and C. Terboven (RWTH Aachen University),
  • Parallelware and OpenMP, on Thursday 11:15 – 11:40 pm, by M. Arenaz (Appentra).

PPCES Video Lectures on OpenMP, MPI and Xeon Phi release

Since 2001 already, the IT Center (formerly: Center for Computing and Communication) of RWTH Aachen University offers a one week HPC workshop on Parallel Programming during spring time. This course is not restricted to scientists and engineers from our university, in fact we have about 30% of external attendees each time. This year we were very happy about a record attendance of up to 85 persons for the OpenMP lectures on Wednesday. As usual we publish all course materials online, but this year we also created screencasts from all presentations. That means you see the slides and the live demos and you hear the presenter talk. This blog post contains links to both the screencasts as well as the other course material, sorted by topic.

OpenMP

We have three talks as an introduction to OpenMP from Wednesday and two talks on selected topics from Thursday, which were vectorization and tools.

Introduction to OpenMP Programming (part 1), by Christian Terboven:

 

Getting OpenMP up to Speed, by Ruud van der Pas:

 

Introduction to OpenMP Programming (part 2), by Christian Terboven:

 

Vectorization with OpenMP, by Dirk Schmidl:

 

Tools for OpenMP Programming, by Dirk Schmidl:

 

MPI

We have two talks as an introduction to MPI and one on using the Vampir toolchain, all from Tuesday.

Introduction to MPI Programming (part 1), by Hristo Iliev:

 

Introduction to MPI Programming (part 2), by Hristo Iliev:

 

Introduction to VampirTrace and Vampir by Hristo Iliev:

 

Intel Xeon Phi

We put a special focus on presenting this architecture and we have one overview talk and one talk on using OpenMP 4.0 constructs for this architecture.

Programming the Intel Xeon Phi Coprocessor Overview, by Tim Cramer:

 

OpenMP 4.0 for Accelerators, by Christian Terboven:

 

Other talks

Some more talks, for instance on using our cluster or basics of parallel computer architectures, can be found in the youtube channel: https://www.youtube.com/channel/UCtdrEoe46tD2IvJJRs_JH1A.