ECMWF | Reading | 24-28 October 2016
Keynote speakers:
Jack Dongarra, University of Tennessee
Thomas Schulthess, Swiss National Supercomputing Centre (CSCS)
Workshop description
Every second year ECMWF hosts a workshop on the use of high performance computing in meteorology. High performance computer architectures are becoming ever more complex which presents significant challenges for the ongoing development of operational meteorological applications. This workshop looked at the issues surrounding the scalability of NWP codes and the steps that will be required to enable us to use future large scale heterogeneous computer systems.
Workshop aims
Our aim is to provide a venue 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 were also be presented.
Vendors of supercomputers had the opportunity to talk to managers and end users of meteorological computer centres about their current and future products. Meteorological scientists presented their achievements in the development of parallel computing techniques and algorithms, and exchanged ideas on the use of supercomputers in future research. Computer scientists gave 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 were discussed.
The workshop consisted of presentations from invited speakers, plus a series of 30 minute contributions.
Presentations
Monday 24 October
| Welcome and opening Isabella Weger (ECMWF) |
|
| Two years into ECMWF's Scalability Programme: What have we achieved? Peter Bauer (ECMWF) |
 |
| The evolving state-of-the-art in global numerical weather prediction Nils Wedi (ECMWF) |
|
| Met Office HPC update Paul Selwood (Met Office) |
|
| Fifty years of NWP at DWD - and what to expect in the future? Ulrich Schättler (DWD) |
|
| Computing at NCAR Dave Hart (NCAR) |
|
| RAPS14 benchmark on 2nd generation Intel Xeon Phi processor Mikko Byckling (Intel) |
|
| Experiences Optimizing NWP for Intel's Xeon Phi, Knights Landing John Michalakes (UCAR) |
|
| HBM code modernization Jacob Weismann-Poulsen and Per Berg (DMI) |
|
|
ECMWF's Next Generation IO for the IFS Model and Product Generation |
|
| IO Performance Evaluation on Massive Data Processing at NCI High Performance Computing Platform Rui Yang (NCI) |
|
| Emerging Cyber Infrastructure for NASA's Large-Scale Climate Data Analytics Daniel Duffy (NASA) |
|
Tuesday 25 October
|
An overview of HPC and the Changing Rules at Exascale |
|
|
A codesign effort to get ECMWF's IFS model to an extreme O(100) OpenMP threads per MPI task for the [Peta,Exa]Scale |
|
|
Determining Optimal MPI Process Placement for Large-Scale Meteorology Simulations with SGI MPIplace |
|
|
Optimizations on ARPEGE and AROME |
|
|
Hardware specific optimizations in ESCAPE |
|
|
The system design of the next generation supercomputer: Post K computer |
|
|
Preparing atmospheric modeling codes for the latest generation MIC architecture (KNL) |
|
|
Scaling Weather Climate and Environmental Science Applications, and Experiences with Intel Knights Landing |
|
|
HPC Performance Advances for Existing US Navy NWP Systems |
|
|
High-resolution results of the GEM model |
|
Wednesday 26 October
| Exascale computing: endgame or new beginning for climate modelling? Thomas Schulthess (CSCS) |
|
| Parallelization of the FV3 Dycore for GPU and MIC processors Mark Govett (NOAA) |
|
| Supercomputing Trends in Earth System Modelling Philip Brown (Cray) |
|
| Development and Testing of a Next Generation Spectral Element Model for the US Navy Alex Reinecke (NRL) |
|
|
Asynchronicity - The Challenge of Fine-Grained Parallelism |
|
| Solutions to growing intensity of climate and meteorological data Eng Lim Goh (SGI) |
N/A |
| ecProf meets High Resolution IFS forecast model at ECMWF Deborah Salmond, Sami Saarinen (ECMWF) |
|
| Investigating and Vectorizing IFS on a Cray Supercomputer Ilias Katsardis (Cray) |
|
| Towards Exascale Computing with the Atmospheric Model NUMA Andreas Müller (ECMWF) |
|
| A seven-year programme to enhance the computational and numerical prediction capabilities of the Bureau's forecast and warning services Tim Pugh (BoM) |
|
| Testing performance and scaling for NOAA's next generation global modeling system John Michalakes (UCAR) |
|
Thursday 27 October
| More accuracy with less precision: An information theoretic paradigm for weather and climate simulation Tim Palmer (University of Oxford) |
|
| NVIDIA HPC directions for Earth System Models Stan Posey (NVIDIA), Dave Norton (PGI) |
|
| Operational numerical weather prediction on a GPU-accelerated cluster supercomputer Carlos Osuna (MeteoSwiss) |
|
| The future of Data Centric Computing: OpenPOWER roadmap Cristiano Malossi (IBM Research - Zurich) |
|
| Computational Efficiency of the Aerosol Scheme in the Met Office Unified Model Mark Richardson (UKCA) |
|
| An Introduction to the LFRic Project Mike Hobson (UK Met Office) |
|
| How Bull contributes to MeteoProjects? Xavier Vigouroux (ATOS) |
|
| Scalability of MOM5, NEMO and MOM6 on NCI's Raijin supercomputer Marshall Ward (NCI) |
|
| The evolution and revolution required for exascale John Goodacre (University of Manchester) |
|
|
The Panel: What does the future look like for NWP application development? |
|
Friday 28 October
| Forecasts Applications driven by High-Performance Computing at The Weather Company Todd Hutchinson (Weather Company) |
|
| Scaling the Software and Advancing the Science of Global Modeling and Assimilation Systems at NASA William Putman (NASA) |
|
| Optimising IFS observation processing: a case study in scalability enhancement Peter Lean (ECMWF) |
|
| Advances in Time-Parallel Four-Dimensional Data-Assimilation In a Modular Software Framework Brian Etherton (NOAA) |
|
| Large scale heterogeneous applications made easy with Allinea Florent Lebeau (Allinea) |
|
| Performance Optimisation and Productivity Nick Dingle (NAG) |
|