Blog

Posts Tagged ‘Cray XK6’

Agenda of Course – Programming GPU Devices Using OpenACC Directives on Cray XK6

Thursday, February 9th, 2012

CSCS announced the detailed agenda of the

Programming GPU Devices using OpenACC Directives on the Cray XK6
March, 6-7  2012
CSCS in Manno

The registration fee is of CHF 150 including the coffee breaks.
Registration and agenda »

Participants will learn about the Cray XK6 hybrid multi-core and GPU architecture and its programming environment. They will learn about the OpenACC directives, which were designed to help users develop and port applications to run on heterogeneous systems.

The course syllabi and all lecture details are available here »

The deadline for registration is 29 February 2012.

First day (March 6)

09:00 – 09:15 Welcome / Introductions (Luiz DeRose, Cray)
09:15 – 09:30 Overview of the Cray XK system (Luiz DeRose, Cray)
09:30 – 10:30 Steps to create a hybrid code (Heidi Poxon, Cray)
10:30 – 11:00 Break
11:00 – 12:00 OpenACC (Alistair Hart, Cray)
- Execution and memory models
- OpenACC Directives
- CUDA Interoperability
- CCE Support status
12:00 – 13:00 Lunch
13:00 – 13:30 User experiences talks on the Cray XK6 system (Tim Ewart, University of Geneva)
13:30 – 14:30 Use case examples (Alistair Hart, Cray)
14:30 – 15:00 Break
15:00 – 15:30 How to build/run existing CUDA and OpenCL on the Cray XK6 (Alistair Hart, Cray)
15:30 – 17:30 Lab (Cray / CSCS)

Second day (March 7)

09:00 – 09:45 Performance Tools for the Cray XK (Heidi Poxon, Cray)
09:45 – 10:30 DDT debugger for the XK6 (Patrick Wohlschlegel, Allinea)
10:30 – 11:00 Break
11:00 – 11:30 Cray libsci_acc (Luiz DeRose, Cray)
11:30 – 12:00 OpenACC future (Luiz DeRose, Cray)
- New features (functionality and performance)
-  Standardization
- Support for other architectures
12:00 – 13:00 Lunch
13:00 – 14:30 User experiences talks on the Cray XK6 system (Xavier Lapillonne (Meteoswiss), Joachim Stadel (University of Zurich) and Matthias Christen (USI))
14:30 – 15:00 Break
15:00 – 17:30 Lab (Cray / CSCS / Allinea)

Course on Programming GPU Devices using OpenACC Directives on the Cray XK6

Saturday, January 21st, 2012

CSCS and HP2C are announcing the following course

Programming GPU Devices using OpenACC Directives on the Cray XK6
March, 6-7  2012
CSCS in Manno

The registration fee is of CHF 150 including the coffee breaks.

Registration and agenda »

Contents

Attendees of this HP2C training event will learn about the Cray XK6 hybrid multi-core and GPU architecture and its programming environment.

They will learn about the OpenACC directives, which were designed to help users develop and port applications to run on heterogeneous systems. They will have an understanding on how to use the Cray Performance tools to identify “hot areas” in the code to focus the use of OpenACC directives. They will have the opportunity to experiment the OpenACC directives with the Cray Compilation Environment (CCE). In addition, they will learn about the Cray scientific libraries for accelerators and will learn and experiment Allinea’s DDT and Cray’s Performance Tools for debugging and performance tuning of heterogeneous applications on the Cray XK6 systems.

Attendees are encouraged to bring in their own applications and codes for the hands-on sessions.  Experts from Cray PE, OpenACC and libsci development and performance tools and Allinea DDT debugger will be present at the meeting for discussions and feedback.  We also invite current users who have their applications running successfully on the Cray XK6 system to present brief user experience talks.

Agenda

- Welcome
- Overview of the Cray XK6 system
- Introduction to Cray XK6 Programming Environment
- Support for GPU application development and execution

  • GPU development environments (CUDA C & Fortran, OpenCL & OpenACC from Cray & PGI)
  • GPU accelerated libraries
  • Message passing communication (MPI)

- Introduction to OpenACC
- Development cycle of application porting

  • Static analysis of the application
  • Find hot loops
  • Scoping Analysis
  • Add OpenMP
  • Create OpenACC regions from OpenMP regions

- Using libsci_acc
- Debugging
- Performance tuning

  • Profile application
  • Using the accelerator hardware counters
  • Analysis of data transfers
  • Add data regions

hpc-ch Forum on GPU – Video on Cray XK6 Overview

Wednesday, November 23rd, 2011

Nicola Bianchi (CSCS) presents the last supercomputer arrival at CSCS: The Cray XK6 supercomputer which 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.

Download the slides of the presentation (PDF) »

Video: First Cray XK6 Worldwide Just Powered Up at CSCS

Sunday, October 23rd, 2011

Engineers of Cray are powering up for the first time worldwide a Cray XK6 delivered to a customer. CSCS was the first supercomputing centre signing a contract with Cray for the delivery of a Cray XK6 with 2816 cores, 176 GPU for a total of 137 TF. CSCS nicknamed the supercomputer “Tödi” after the name of a Swiss mountain.

The Cray XK6 supercomputer combines Cray´s Gemini interconnect, AMD’s multi-core scalar processors and NVIDIA´s many-core GPU processors. Shortly the Department of Energy’s (DOE) Oak Ridge National Laboratory (ORNL) signed a contract with Cray to upgrade the Cray XT5 supercomputer nicknamed “Jaguar”  to a new Cray XK6 supercomputer, which will be nicknamed “Titan.” When completed, the Titan system will have a peak performance between 10 and 20 PF.