In this presentation Adrian Ulrich (ETH Zurich) shares his experience with Nvidia CUDA, AMD FireStream and Platform LSF.
Blog
Posts Tagged ‘Community’
hpc-ch Forum on GPU – Video on “Enhancing” commercial software
Monday, November 21st, 2011hpc-ch Forum on GPU – Video on GPU Use at the University of Basel
Monday, November 21st, 2011In October hpc-ch organized together with the University of Basel a Forum on the Use of GPU and Accelerators for HPC. In a series of articles we publish the videos of the presentations.
Martin Jacquot (Universitiy of Basel) was hosting the event and presented the implementation and usage of GPU at the University of Basel.
Agenda of hpc-ch Forum on the Use of GPU and Accelerators for HPC
Thursday, October 20th, 2011More 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 Basel – Implementation and usage of GPU on our cluster; Martin Jacquot (Universitiy of Basel)
- “Enhancing” commercial software – In 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 architectures – While 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 Clusters – CSCS 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 Overview – The 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
Call for presentations and participants: Forum on the Use of GPU and Accelerators for HPC
Tuesday, September 27th, 2011Thursday 27 October 2011, 10:00 – 17:00, hosted by Universität Basel
Setting the Scope
In the last years the interest in using Graphics Processing Units (GPU) for HPC computing has been growing. Modern GPUs are designed to support computer games in the real time calculation of their visual effects. Therefore modern GPUs are highly parallel multi core systems optimised for floating point operations and high throughput. They pack more computing power in the same space than a traditional CPU with reduced power consumption and cost. While those characteristics are perfectly fitted for HPC computing others impose problems. The more problematic features of GPU arise since in its classic use neither precision is a top priority nor is there much need for access control to the GPU.
With the introduction of CUDA, OpenCL and similar products a larger number of programmers were enabled to use GPUs. This is leading to an increasing number of programs making use of GPU capabilities and leads to an increased demand of GPUs in HPC computing.
The use of GPU in HPC clusters pose new challenges like the integration in the queuing system and the programming languages to use. The goal of this forum is to exchange the information about the usage of the GPU in a HPC environment.
Key Questions
- Are GPUs a current hype or the technology of the future?
- How can we make use of this new technology?
- How to integrate the GPUs in the queuing systems?
- Which system tools are you deploying to monitor and report the HW status of the GPGPUs accelerators integrated into your HPC Cluster? How do you handle GPU drivers failure detection and recovery, also from a batch queuing system point of view?
- How to gain usage metrics per user?
- What are your experiences in the integration of GPU in the HPC clusters?
- What could be the possible metric in order to measure the usage and the performance of the GPU?
- What are the limitations of this technology (benefit versus overhead)?
- Development tool CUDA versus OpenCL: experience, advantage, disadvantage?
- Are your GPGPU cluster customers adopting GPU-Direct technology ? If yes, in which application field ? In which particular application ? Did they measure any interesting application performance improvement ?
Location / Hosting
The Topic Forum will take place at the Biozentrum at the University of Basel in the room 106.
Please refer to this link to get information about how to reach Biozentrum and a map of the site: http://www.biozentrum.unibas.ch/directions/
Chairmanship
- Martin Jacquot, URZ, tel 061 267 22 66
- Michele De Lorenzi, CSCS, tel 091 610 82 08
Registration
This event is only open to hpc-ch community members and guests. To register contact your representative listed here.
Fotogallery and Movie hpc-ch Booth at ISC11
Thursday, August 18th, 2011hpc-ch participated to ISC11 in Hamburg with an own booth. If you were not able to participate to the conference you can now see some photos of the booth and a short movie edited by UZH (thank you Alexander and Reini).
Follow the construction of the booth:
