13th Workshop on the Use of High Performance Computing in Meteorology

Every second year the European Centre for Medium-Range Weather Forecasts (ECMWF) hosts a workshop on the use of high performance computing in meteorology. The 13th Workshop on High Performance Computing in Meteorology took place from 3-7 November 2008.


The emphasis of this workshop was on running meteorological applications at sustained teraflops performance in a production environment. Particular emphasis was placed on the future scalability of NWP codes and the tools and development environments to facilitate this.

This workshop aims to provide a situation where:

  • Users from our Member States and around the world can report on their experience and achievements in the field of high performance computing during the last two years; plans for the future and requirements for computing power will also be presented.
  • Vendors of supercomputers will have the opportunity to talk to managers and end users of meteorological computer centres about their current and future products.
  • Meteorological scientists can present their achievements in the development of parallel computing techniques and algorithms, and can exchange ideas on the use of supercomputers in future research.
  • Computer scientists can give an update on their efforts in providing tools which will help users to exploit the power of supercomputers in the field of meteorology.
  • The challenges of creating a computer centre infrastructure for HPC can be discussed.


PDF iconProgramme


Session 1

Development of the ECMWF forecasting system

Jean-Noël Thépaut (ECMWF)

PDF icon

IFS performance on the new IBM Power6 systems at ECMWF

Deborah Salmond (ECMWF)

PDF icon
Session 2

Preparing for future HPC systems - scalability of the ECMWF data assimilation system

Mats Hamrud (ECMWF)

PDF icon

From climate to weather coupled modelling, challenges for ACCESS

Tim Pugh (Australian Bureau of Meteorology)

PDF icon

High performance computing at the Canadian Meteorological Centres (CMC)

Michel Desgagné (Environment Canada)

PDF icon
Session 3

The new HPC facility at DKRZ: Computing and data handling

Joachim Biercamp (Deutsches Klimarechenzentrum GmbH)

PDF icon

Seamless simulations with Multi-Scale Simulator for the Geoenvironment (MSSG)

Ryo Onishi (Earth Simulator Center)

PDF icon
Session 4

Mass conserving positive definite semi-Lagrangian advection in NCEP GFS: decomposition of massively parallel computing without halo

Hann-Ming Henry Juang (NOAA/NWS/NCEP/EMC)

PDF icon

Sequential data assimilation on high-performance computers with the parallel data assimilation framework

Lars Nerger (Alfred Wegener Institute)

PDF icon
Session 5

Multicore meets Petascale: Opportunities and challenges

Kathy Yelick (EECS/NERSC)

PDF icon

Cell and climate modeling

Don Grice (IBM Corporation)

PDF icon
Session 6

Update on Cray Activities in the Earth Sciences

Per Nyberg (Cray Inc)

PDF icon

The NEC SX-9: The next step forward in computational meteorology

Thomas Schoenemeyer (NEC Deutschland GmbH)

PDF icon
Session 7

HPC technologies for weather and climate simulations

David Barkai (Intel Corp)

PDF icon

Profiling and optimization of climate, ocean and weather codes on large clusters

Hans Joraandstad (Sun Microsystems)

PDF icon

Scalability of weather and climate codes: managing computational overheads in the many-core era

Eng Lim Goh (Silicon Graphics)

PDF icon
Session 8

The Portland Group - Premier services success stories

Dave Norton (The Portland Group)

PDF icon

IFS in the DEISA benchmark

Peter Towers (ECMWF)

Session 9

RAPS workshop: Progress report

George Mozdzynski (ECMWF)

PDF icon

Parallel programming in Fortran with Coarrays

John Reid (JKR Associates)

PDF icon

Combining object-oriented techniques with co-arrays in Fortran 2008

Robert Numrich (University of Minnesota)

PDF icon
Session 10

IFS scaling

George Mozdzynski (ECMWF)

PDF icon

Exploring extreme scalability in scientific applications

Mike Ashworth (STFC Daresbury Laboratory)

PDF icon

Switch jitter

John Hague (IBM)

PDF icon
Session 11

Further COSMO-model development or: Is it dangerous to buy a vector computer

Ulrich Schättler (Deutscher Wetterdienst)

PDF icon

Results from the UK Met Office HPC procurement

Paul Selwood (Met Office)

PDF icon

Porting and optimizing the cosmos coupled model on Power 6

Luis Kornblueh (Max Planck Institute for Meteorology)

PDF icon
Session 12

Simplifying complex software development environments at scale with Allinea tools

Jacques Philouze on behalf of David Lecomber (Allinea Software)

PDF icon

Improved SW troubleshooting with TotalView and ReplayEngine

Brian Bonenfant and Jim Pioche (TotalView Technologies)

Session 13

The petaflops challenge for NWP and climate research

Geerd-Ruediger Hoffmann (Deutscher Wetterdienst) & Ulrich Trottenberg (Fraunhofer-Institut SCAI)

PDF icon

An update of activities at NCAR's Computational and Information Systems laboratory

Al Kellie (NCAR)

PDF icon
Session 14

NOAA Modeling Portal

Jeff Smith (Earth System Research Lab/NOAA)

PDF icon

Running operational weather models on FNMOC's Linux Networx Custom Supersystem

Roger Stocker (FNMOC)

PDF icon

Mass storage and archive challenges at NCEP

George VandenBerghe (NOAA/NCEP)

PDF icon
Session 15

Performance of the JMA NWP models on the PC cluster TSUBAME  

Hara Tabito (Japan Meteorological Agency)

PDF icon

Variational ensemble Kalman filtering on parallel computers

Tuomo Kauranne(Lappeenranta University of Technology)

PDF icon

What can a small country do? The MeteoSwiss implementation of the COSMO suite on the Cray XT4

Petra Baumann(Federal Office of Meteorology and Climatology MeteoSwiss)

PDF icon