General-purpose Graphics Processing Units (GPGPUs) potentially offer exceptionally high memory bandwidth and performance for a wide range of applications. The challenge in utilizing such accelerators has been the difficulty in programming them. The OpenACC Directives for Accelerators offers straightforward pragma extensions to C++ and Fortran to address this programming hurdle.
The goal of EuroHack is for current or prospective users groups of large hybrid CPU-GPU systems to send teams of 3-6 developers along with either (1) a (potentially) scalable application that needs to be ported to GPU accelerators, or (2) an application running on accelerators which needs optimization. There will be intensive mentoring during this 5-day hands-on workshop, with the goal that the teams leave with applications running on GPUs, or at least with a clear roadmap of how to get there. Our mentors come from national laboratories, universities and vendors, and besides having extensive experience in programming with OpenACC, many of them develop the OpenACC-capable compilers and help define the OpenACC standard.
Target Audience and Format
We are looking for teams of 3-6 developers with a scalable** application to port to or optimize on a GPU accelerator. Collectively the team should know the application intimately. (** by scalable we really mean node-to-node communication implemented, but don’t be discouraged to apply if your application is less than scalable. We are also looking for breadth of application areas.)
Ok, so how can we attend?
The application period is now open. Prior GPU experience is not required! The team coordinator needs to fill out the OpenACC_Eurohack_Application and send it to William Sawyer (wsawyer(at)cscs.ch) by Friday, March 27, 2015. Space will be limited to 8 teams, with 2 mentors for each team. Groups will be notified about acceptance or rejection of their application by Friday, April 17, 2015.
Those groups whose application successfully passes the selection process will receive further information regarding registration.
What applications is EuroHack targeting?
No application specifically — we would like a wide spectrum of applications, including those outside of traditional High-Performance Computing. The preference would be to have open-source community codes in need of porting (or optimizing) individual modules. This is a great opportunity for graduate students and post-docs.
So what is in it for the participants?
Besides your code running lightening fast on a hybrid CPU-GPU machine like the CSCS_Piz_Daint platform? During the workshop, we will enable your amazing transformation to OpenACC expert and present your team with a certificate in front of your admiring fans. There will also be a workshop outing in scenic Lugano one afternoon during the height of the Ticino summer and the opportunity to visit the CSCS_Computing_Facility. Finally, ISC 2015 (July 12-16) attendees may find it easier to justify travel by putting down two trip objectives.
But we don’t even know how to use OpenACC…
Programming experience with OpenACC is not a requirement — you will learn quickly in the intense 5-day schedule, working on your code 95% of the time with the mentors. But for those who desire some preparation, CSCS will hold a course in May or June in GPU programming. Please consult the CSCS Events Page.
But what if we want to use something other than OpenACC?
CSCS organizes courses on various hybrid CPU-GPU programming techniques on a regular basis. Please keep an eye on the CSCS_Events_Page.
The First OpenACC EuroHack will be hosted at Hotel de la Paix located in Lugano, Italian area of Switzerland. The hotel will allow 24h access to the meeting rooms so that the selected teams can work on their project at their convenience.
Participation in the workshop is free of charge. The meeting room and lunches, as well as access to the supercomputers throughout the event are offered by the Swiss National Supercomputing Centre (CSCS). Mentors and learning materials introduced by the instructors are sponsored by CSCS and the following partner organizations: Cray, NVIDIA, Oak Ridge National Laboratory, PGI, Tokyo Institute of Technology, and Technische Universität Dresden.
Participants are responsible for their travels to the meeting venue, accommodation, meals not included in the program, and personal expenses.