Agenda of hpc-ch Forum on the Use of GPU and Accelerators for HPC

More than 30 members of the hpc-ch will participate to the next forum on «the Use of GPU and Accelerators for HPC» Thursday 27th October 2011 hosted by University of Basel. We are looking forward meeting you all in Basel.

Agenda

The hpc-ch meeting will already start on Wednesday, October 26th with a common dinner starting at 19:00 at the restaurant Löwenzorn Gemsberg 2/4 4051 Basel (http://www.loewenzorn.ch).

The agenda for the October 27th is the following:

9:45 -10:00 Coffee and registration

10:00 -10:10 Greeting and introduction, Michael Brüwer (URZ) and Michele De Lorenzi (CSCS)

10:10 – 11:45 Presentations

  • GPU Use at the University of BaselImplementation and usage of GPU on our cluster; Martin Jacquot (Universitiy of Basel)
  • “Enhancing” commercial softwareIn this presentation we will share our experience with Nvidia CUDA, AMD FireStream and Platform LSF; Adrian Ulrich (ETH Zurich)
  • Multi-resolution flow simulations on multi/many-core architecturesWhile the peak performance and energy efficiency of computing hardware are constantly growing, the development of fast scientific software is experiencing an important paradigm shift. Efficient algorithm implementations face rigid constraints about memory layouts, access patterns and FLOP/Byte ratios. We discuss the design of wavelet-based adaptive solvers for compressible flow simulations that run effectively on multi- and many-core architectures; Diego Rossinelli (ETH Zurich)

11:45 – 12:15 Community Development (Michele De Lorenzi)

  • Overview of hpc-ch activities
  • Planing of activities for 2012

12:15 – 13:00 Lunch in the gallery on the right side of the room 106

13:00 -14:30 Guided tour through the Biozentrum

  • Guided tour through the BC2 Cluster room
  • 3D Application “Drug the bug”
  • Material analysis and imaging with Scanning Electron Microscope

14:30 – 17:00 Presentations

  • Installation and Operational Needs of Multi-purpose GPU ClustersCSCS has experience of operating multi-purpose GPU clusters for a diverse project and service portfolio.  We present details on system installation and operation for two clusters: a production and experimental testbed that serves as HP2C prototype system and a multi-purpose visualization and GPU development cluster; Vincenzo Annaloro (CSCS)
  • Scheduling GRES resources With SLURM; Stephen Trofinoff (CSCS)
  • Cray XK6 OverviewThe Cray XK6 supercomputer is a trifecta of scalar, network and many-core innovation. It combines Cray’s proven Gemini interconnect, AMD’s leading multi-core scalar processors and NVIDIA’s powerful many-core GPU processors to create a true, productive hybrid supercomputer; Kris Howard (CSCS)

17:00 Farewell and end of the meeting