Crossing the Chasm: How to develop weather and climate models for next generation computers?

Abstract

Abstract.Weather and climate models are complex pieces of software which include many individual components, each of which is evolving under the pressure to exploit advances in computing to enhance some combination of a range of possible improvements (higher spatio/temporal resolution, increased fidelity in terms of resolved processes, more quantification of uncertainty etc). However, after many years of a relatively stable computing environment with little choice in processing architecture or 5 programming paradigm (basically X86 processors using MPI for parallelism), the existing menu of processor choices includes significant diversity, and more is on the horizon. This computational diversity, coupled with ever increasing software complexity, leads to the very real possibility that weather and climate modelling will arrive at a chasm which will separate scientific aspiration from our ability to develop and/or rapidly adapt codes to the available hardware.In this paper we review the hardware and software trends which are leading us towards this chasm, before describing current 10 progress in addressing some of the tools which we may be able to use to bridge the chasm. This brief introduction to current tools and plans is followed by a discussion outlining the scientific requirements for quality model codes which have satisfactory performance and portability, while simultaneously supporting productive scientific evolution. We assert that the existing method of incremental model improvements employing small steps which adjust to the changing hardware environment is likely to be inadequate for crossing the chasm between aspiration and hardware at a satisfactory pace, in part because insti-15 tutions cannot have all the relevant expertise in house. Instead, we outline a methodology based on large community efforts in engineering and standardisation, one which will depend on identifying a taxonomy of key activities -perhaps based on 1 Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2017-186 Manuscript under review for journal Geosci. Model Dev. Discussion started: 5 September 2017 c Author(s) 2017. CC BY 4.0 License. existing efforts to develop domain specific languages, identify common patterns in weather and climate codes, and develop community approaches to commonly needed tools, libraries etc -and then collaboratively building up those key components. Such a collaborative approach will depend on institutions, projects and individuals adopting new interdependencies and ways of working.

A mixed finite‐element, finite‐volume, semi‐implicit discretization for atmospheric dynamics: Cartesian geometry

“…The current trend of supercomputer architectures is towards a greatly increasing number of processors, together with an increasingly complex hierarchy of heterogeneous processors and memories. In terms of the efficiency of a dynamical core, this trend shifts interest from optimizing the number of calculations towards optimizing the management of memory and communications between processors (Lawrence et al, 2017). This has led to a renewed interest in the choice of mesh used and in particular to a desire, for those still using it, to move away from a latitude-longitude mesh, (Staniforth and Thuburn, 2012).…”

Accelerating High-Resolution Weather Models with Deep-Learning Hardware

“…High-performance computing architectures are currently undergoing a paradigm shift, prompting a reconsideration of how we design scientific computing applications [9]. Future supercomputers will be heterogeneous, employing a variety of computing hardware, and will place more emphasis on data transfer between individual computing units, including memory-to-processor and nodeto-node communication, compared with the traditional focus on raw floating-point computation.…”

Optimizing the HOMME dynamical core for multicore platforms

“…The continued evolution of the underlying hardware complicates the development of efficient software to support the advancement of scientific objectives. A good description of the myriad of software challenges that face earth system modeling is provided in the study by Lawrence et al (2018). Our approach to addressing these challenges is based on the premise that we need to coevolve our software to address the evolving hardware.…”