Workshop: Next Generation HPC architectures for studying climate variability

20th - 22nd March 2017, Exeter

 

This is a ReCoVER meeting being co-organised by Beth Wingate (University of Exeter), Lawrence Mitchell (Imperial College, London) and Chris Budd, (University of Bath).

The purpose of this meeting is to imagine and build a roadmap for taking advantage of next-generation HPC computer architectures for studying climate variability.  This is thought to be a serious issue since most parallelisation strategies used in state-of-the-art climate models have the following issues:

  1. the number of cores is nearly optimal for today’s grid resolutions – adding more compute cores no longer decreases the time-to-solution and
  2. increases in grid resolution require longer simulation times due to the CFL criteria.

Therefore, current climate models will have to be retooled to improve both numerical methods and compute/software infrastructure to make use of more parallelism.

At present, most climate models will scale well on machines thought to be suitable contenders for ARCHER 2, but beyond that less is known both about the possible architectures and strategies for ‘going beyond the strong scaling limit’. Some areas of discussion will include:

  • What sort of novel numerical algorithms might be developed (and applied to environmental modelling) that fully exploit emerging architectures, and what are the challenges to numerical analysts from these algorithms?
  • While the longer-term processes of item 1 are ongoing throughout the next decade, what can we do to make best use of these architectures? For example, should we concentrate on more ensemble runs, more statistics/machine learning, or diverse model runs at the same time? Are there new science questions that can be asked that can have an impact on UK and international science?

The programme includes a small number of keynote speakers who will speak about the future of computer architectures and what is currently planned; several shorter presentations setting the scene in different organisations; and in addition, lightening talks will highlight relevant ongoing research.  This will be followed by a workshop-style meeting where participants will be encouraged to engage across disciplinary boundaries to devise a strategic path forward for research that will make best use of the new architectures. 

 

Programme

 

Monday 20th March 2017

 

Time

 

12:00

Lunch

13:20

Welcome and introduction

13:30

Lecture: Lawrence Mitchell (Imperial College, London) –

From here to there: challenges for exascale transient simulation

14:15

Lecture: Katherine Evans (US Department of Energy) –

Look aloft: Using next generation HPC to advance our understanding of climate change at multiple scales

15:00

Tea/Coffee

15:30

Lecture: Matthew Chantry (Oxford) - Precision reduction: the route to more accurate weather and climate modelling?

15:50

Lecture: Chris Maynard (Met Office) -

Domains specific languages: Why one size no longer fits all

16:10

Lecture: Willem Deconinck (ECMWF)

ESCAPE project (H2020) status and strategy

16:30

Lecture: Hans Vandierendonck (Queen's University Belfast)

Dataflow programming models in HPC

17:00

Close

 

Evening: self-organized meal in Exeter

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Tuesday 21st March 2017

 

Time

 

8.30

Tea/Coffee available

9:15

HPC challenges: Beth Wingate (Exeter)

9:30

Lightning talks (7 minutes each):

  • Richard Everson
  • Jemma Shipton (Imperial College, London) - Scalable numerics for numerical weather prediction using compatible finite element methods’
  • Eike Mueller (University of Bath) – Matrix-free block smoothers for higher-order DG methods
    • Paul Dellar (University of Oxford) – Experiences with CUDA Fortran for spectral GFD codes
    • Dejice Jacob (University of Glasgow) – Tools for AnyScale computing
    • Serge Guillas (UCL) – Dimension reduction for Gaussian process emulation: an application to emulation for fields of input boundary conditions
    • Peter Challenor (University of Exeter) – Uncertainty quantification

10.45

Tea/Coffee

11:10

Agenda-setting activities

12.:30

Lunch

13:30

Walk (could be muddy and wet so please wear suitable footwear and bring a coat)

15:30

Discussions, with tea, coffee and cake available

17:30

Close

19:00

Workshop dinner, Samuel Jones’ www.samueljonesexeter.co.uk

 

Wednesday 22nd March 2017

 

Time

 

8.30

Tea/Coffee available

9:00

Discussions

10.30

Tea/Coffee

11:00

Reporting back

12:30

Lunch and finish

13.30

Close

 

ReCoVER Funding

 

This is a workshop organised by the EPSRC network ReCoVER.  The network will offer participants the opportunity to apply for a feasibility funding project of up to £25k to follow up ideas from the workshop.  .  Please see the ReCoVER website () for the application form and the terms and conditions.  Please send your completed application form to Emily Paremain by the deadline of 23:59 on Monday 27th March 2017.