Back to Table of contents

Primeur weekly 2018-10-08

Special

Where did the first 500 million euro invested by the European Horizon 2020 programme go? ...

Focus

World's first ARM-based supercomputer Isambard is ready for science ...

Exascale supercomputing

New European project ESCAPE-2 on exascale computing for numerical weather prediction gets under way ...

Berkeley Lab, Oak Ridge, and NVIDIA team breaks exaop barrier with deep learning application ...

Coming soon to exascale computing: Software for chemistry of catalysis ...

Quantum computing

ORNL researchers advance quantum computing, science through six DOE awards ...

Berkeley Lab to build an advanced quantum computing testbed ...

Berkeley Lab to push quantum information frontiers with new programmes in computing, physics, materials, and chemistry ...

Berkeley Quantum to accelerate innovation in quantum information science ...

Quantum software company Zapata Computing adds Clark Golestani to Board ...

Defects promise quantum communication through standard optical fiber ...

Focus on Europe

Atos and the University of Reims launch ROMEO, one of the most powerful supercomputers in the world, under the sponsorship of Cedric Villani ...

Special Edition of Open e-IRG Workshop under the Austrian EU Presidency will focus on relationship between Open Science, FAIR data and EOSC ...

Goethe University to develop green supercomputer for science ...

Calling on HPC experts and enthusiasts to propose tutorials and workshops for ISC 2019 ...

ISC 2019 calls for research paper submission by December 12, 2018 ...

Middleware

USC ISI to pilot Cyberinfrastructure Center of Excellence for National Science Foundation ...

Hardware

Tintri co-founder Mark Gritter joins Tintri by DDN as CTO to lead analytics and server virtualization vision ...

DDN simplifies the AI data centre with NVIDIA ...

New research could lead to more energy-efficient computing ...

Applications

New simulation sheds light on spiraling supermassive black holes ...

DNA unzipped, turned around, and rezipped ...

Dark Energy Survey releases first year value-added data products ...

A quantum leap toward expanding the search for dark matter ...

HP-CONCORD paves the way for scalable machine learning in HPC ...

In disaster's wake, novel computing techniques support emergency responders ...

Transition metal dichalcogenides could increase computer speed, memory by a million times ...

A new brain-inspired architecture could improve how computers handle data and advance AI ...

Rochester Institute of Technology leads multi-university collaboration to simulate neutron star mergers ...

The Cloud

Oracle rolls out Autonomous NoSQL Database service ...

Quanta Cloud Technology showcases AI portfolio options at GTC Europe ...

ZeroStack delivers GPU-as-a-Service via NVIDIA hardware ...

New European project ESCAPE-2 on exascale computing for numerical weather prediction gets under way

The participants in ESCAPE-2 will aim to build on the success of the ESCAPE project.5 Oct 2018 Reading - The ESCAPE-2 kick-off meeting brought together 30 experts on computing, numerical weather prediction (NWP) and climate. The ESCAPE-2 project on energy-efficient scalable algorithms for weather and climate prediction at the exascale was formally launched with a kick-off meeting at the European Centre for Medium-Range Weather Forecasts (ECMWF) from 2 to 4 October 2018.

It will build on the success of the ESCAPE project, which has achieved remarkable gains in computing efficiency by developing the concept of "weather and climate dwarfs".

Like its predecessor, ESCAPE-2 is a three-year project coordinated by ECMWF and funded by the European Commission's Horizon 2020 Future and Emerging Technologies for High-Performance Computing (FET-HPC) programme.

It brings together 12 partners, including national meteorological and hydrological services, HPC centres, hardware vendors and universities.

The ESCAPE project aimed to prepare NWP and climate models for new computing architectures towards exascale computing, with a focus on energy efficiency.

The project developed the concept of fundamental building blocks called dwarfs. Dwarfs represent functional units in the forecasting model, such as an advection or a physics parametrization scheme, which also come with specific computational patterns for processor memory access and data communication.

Assessing numerical methods and algorithms for dwarfs rather than entire models reduces the complexity of the code. It enables HPC centres, research groups and hardware vendors to focus on specific aspects of performance for which code restructuring and adaptation to novel processor architectures is more straightforward.

The codes were optimised for different types of Intel CPU and NVIDIA GPU processors and a new technique particularly suited for performing Fourier transformations with an optical device.

For spectral transforms on CPUs, efficiency gains of up to 40% were achieved. Code optimization for GPU delivered speed-up factors of about 10 to 50 on a single node, and again by a factor of 2 to 3 when deployed on multiple GPUs connected by NVSwitch.

However, using accelerators only for a small part of the code destroys a lot of the benefit in terms of the overall cost if the CPUs are idle while the accelerators perform their computations.

Ideally, a large part of the code is moved to the accelerator, or computations on the host-CPUs are overlapped with computations on the accelerator. Fully implementing either option will require further work.

So-called domain specific languages (DSL) were another focus of the ESCAPE project. They are a very promising tool to enable good performance on multiple architectures while still having a single, portable code base.

Designing a DSL that is user-friendly whilst delivering good performance on each architecture is still a challenge.

Tests with a dwarf calculating the advection of air showed a speed improvement by a factor of 2 compared to the manually adapted version on GPUs.

Beyond code adaptation and optimisation, a range of numerical methods exploiting multi-grid solvers and different types of spatial discretisation and time stepping have been investigated.

This work will support ECMWF's development of the finite-volume module, FVM, that presents an alternative option to the currently operational spectral-transform dynamical core of the Integrated Forecasting System (IFS).

It also supports strategies of ECMWF's Member and Co-operating States for their limited-area applications.

ESCAPE-2 will extend the work on dwarfs to other models, such as the German national meteorological service's ICON model and the community ocean model NEMO.

It will ultimately develop benchmarks that represent the computing and data handling patterns of weather and climate models more realistically, and are thus more suitable for assessing the performance of future HPC systems.

This is relevant for future procurements but also for guiding the performance assessment of future HPC systems of the EuroHPC Joint Undertaking.

ESCAPE-2 will also combine cross-disciplinary uncertainty quantification tools (URANIE) for HPC, originating from the energy sector, with ensemble-based weather and climate models to quantify the effect of model- and data-related uncertainties on forecasting in a cost-effective way.

The mathematical and algorithmic research in ESCAPE-2 will focus on implementing data structures and tools supporting parallel computation of dynamics and physics on multiple scales and multiple levels.

Highly-scalable spatial discretisation will be combined with proven large time-stepping techniques to optimise both time-to-solution and energy-to-solution.

Connecting multi-grid tools, iterative solvers, and overlapping computations with flexible-order spatial discretisation will strengthen algorithm resilience against soft or hard failure.

In addition, machine learning techniques will be applied to accelerate complex sub-components.

The intended outcome is a solution which combines performance, resilience and accuracy with portability.

The ESCAPE project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No. 671627.

The ESCAPE-2 project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 800897.
Source: European Centre for Medium-Range Weather Forecasts - ECMWF

Back to Table of contents

Primeur weekly 2018-10-08

Special

Where did the first 500 million euro invested by the European Horizon 2020 programme go? ...

Focus

World's first ARM-based supercomputer Isambard is ready for science ...

Exascale supercomputing

New European project ESCAPE-2 on exascale computing for numerical weather prediction gets under way ...

Berkeley Lab, Oak Ridge, and NVIDIA team breaks exaop barrier with deep learning application ...

Coming soon to exascale computing: Software for chemistry of catalysis ...

Quantum computing

ORNL researchers advance quantum computing, science through six DOE awards ...

Berkeley Lab to build an advanced quantum computing testbed ...

Berkeley Lab to push quantum information frontiers with new programmes in computing, physics, materials, and chemistry ...

Berkeley Quantum to accelerate innovation in quantum information science ...

Quantum software company Zapata Computing adds Clark Golestani to Board ...

Defects promise quantum communication through standard optical fiber ...

Focus on Europe

Atos and the University of Reims launch ROMEO, one of the most powerful supercomputers in the world, under the sponsorship of Cedric Villani ...

Special Edition of Open e-IRG Workshop under the Austrian EU Presidency will focus on relationship between Open Science, FAIR data and EOSC ...

Goethe University to develop green supercomputer for science ...

Calling on HPC experts and enthusiasts to propose tutorials and workshops for ISC 2019 ...

ISC 2019 calls for research paper submission by December 12, 2018 ...

Middleware

USC ISI to pilot Cyberinfrastructure Center of Excellence for National Science Foundation ...

Hardware

Tintri co-founder Mark Gritter joins Tintri by DDN as CTO to lead analytics and server virtualization vision ...

DDN simplifies the AI data centre with NVIDIA ...

New research could lead to more energy-efficient computing ...

Applications

New simulation sheds light on spiraling supermassive black holes ...

DNA unzipped, turned around, and rezipped ...

Dark Energy Survey releases first year value-added data products ...

A quantum leap toward expanding the search for dark matter ...

HP-CONCORD paves the way for scalable machine learning in HPC ...

In disaster's wake, novel computing techniques support emergency responders ...

Transition metal dichalcogenides could increase computer speed, memory by a million times ...

A new brain-inspired architecture could improve how computers handle data and advance AI ...

Rochester Institute of Technology leads multi-university collaboration to simulate neutron star mergers ...

The Cloud

Oracle rolls out Autonomous NoSQL Database service ...

Quanta Cloud Technology showcases AI portfolio options at GTC Europe ...

ZeroStack delivers GPU-as-a-Service via NVIDIA hardware ...