Application Centric Energy-Efficiency Study of Distributed Multi-Core and Hybrid CPU-GPU Systems

Cumming, Ben; Fourestey, Gilles; Fuhrer, Oliver; Gysi, Tobias; Fatica, Massimiliano; Schulthess, T. C.

doi:10.1109/sc.2014.72

Cited by 11 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In future years as on-chip energy metering matures and is standardized, we can imagine adding an "actual Joules per SY (AJPSY)" measure, which takes into account the actual energy used by the model and its workflow across the simulation lifecycle, including computation, data movement, and storage. These measures are similar in spirit to some prior measures of "energy to solution" (Bekas and Curioni, 2010;Cumming et al, 2014;Charles et al, 2015). The FTTSE metric of Bekas and Curioni (2010) is very similar to the AJPSY metric proposed here, and which we believe will replace JPSY in due course, when direct metering becomes routinely available.…”

Section: Balaji Et Al: Measurements Of Earth System Models In Cmip6supporting

confidence: 52%

“…As the energy cost of computing (Cumming et al, 2014;Charles et al, 2015) is increasingly becoming the limiting factor in large-scale computing, we expect that our machineaverage measure of model energy consumption JPSY will need to be replaced by a more accurate measure of energy consumption AJPSY, using fine-grained hardware energy Table 4. Details of platforms used in this study.…”

Section: Summary and Future Workmentioning

confidence: 99%

See 1 more Smart Citation

CPMIP: measurements of real computational performance of Earth system models in CMIP6

et al. 2017

View full text Add to dashboard Cite

Abstract. A climate model represents a multitude of processes on a variety of timescales and space scales: a canonical example of multi-physics multi-scale modeling. The underlying climate system is physically characterized by sensitive dependence on initial conditions, and natural stochastic variability, so very long integrations are needed to extract signals of climate change. Algorithms generally possess weak scaling and can be I/O and/or memory-bound. Such weakscaling, I/O, and memory-bound multi-physics codes present particular challenges to computational performance.Traditional metrics of computational efficiency such as performance counters and scaling curves do not tell us enough about real sustained performance from climate models on different machines. They also do not provide a satisfactory basis for comparative information across models.We introduce a set of metrics that can be used for the study of computational performance of climate (and Earth system) models. These measures do not require specialized software or specific hardware counters, and should be accessible to anyone. They are independent of platform and underlying parallel programming models. We show how these metrics can be used to measure actually attained performance of Earth system models on different machines, and identify the most fruitful areas of research and development for performance engineering.We present results for these measures for a diverse suite of models from several modeling centers, and propose to use these measures as a basis for a CPMIP, a computational performance model intercomparison project (MIP).

show abstract

Section: Balaji Et Al: Measurements Of Earth System Models In Cmip6supporting

confidence: 52%

Section: Summary and Future Workmentioning

confidence: 99%

CPMIP: measurements of real computational performance of Earth system models in CMIP6

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Cumming et al [10] present a simple and practical methodology looking at energy minimization that can be applied to various applications.…”

Section: Related Workmentioning

confidence: 99%

Evaluating the performance and energy efficiency of the COSMO-ART model system

et al. 2014

View full text Add to dashboard Cite

Registro de acceso restringido Este recurso no está disponible en acceso abierto por política de la editorial. No obstante, se puede acceder al texto completo desde la Universitat Jaume I o si el usuario cuenta con suscripción. Registre d'accés restringit Aquest recurs no està disponible en accés obert per política de l'editorial. No obstant això, es pot accedir al text complet des de la Universitat Jaume I o si l'usuari compta amb subscripció. Restricted access item This item isn't open access because of publisher's policy. The full--text version is only available from Jaume I University or if the user has a running suscription to the publisher's contents.

show abstract

“…Current computing technologies are based on increased concurrency of arithmetic and logic, while the speed of computation and memory access itself has stalled. This is driven by many technological constraints, not least of which is the energy budget of computing (Cumming et al, 2014;Charles et al, 2015;Kogge et al, 2008). These massive increases in concurrency pose challenges for HPC applications: an era where existing applications would run faster with little or no effort, simply by upgrading to newer hardware, has ended.…”

Section: Balaji Et Al: Coarse-grained Component Concurrencymentioning

confidence: 99%

Coarse-grained component concurrency in Earth System modeling

Balaji

Benson

Wyman

et al. 2016

Preprint

View full text Add to dashboard Cite

Abstract. Climate models represent a large variety of processes on a variety of time and space scales, a canonical example of multi-physics multi-scale modeling. Current hardware trends, such as GPUs and MICs, are based on marginal increases in clock speed, coupled with vast increases in concurrency, particularly at the fine grain. Multi-physics codes face particular challenges in achieving fine-grained concurrency, as different physics and dynamics components have different computational profiles, and universal solutions are hard to come by. We propose here one approach for multi-physics codes. These codes are typically structured as components interacting via software frameworks. The component structure of a typical Earth system model consists of a hierarchical and recursive tree of components, each representing a different climate process or dynamical system. This recursive structure generally encompasses a modest level of concurrency at the highest level (e.g atmosphere and ocean on different processor sets) with serial organization underneath. We propose to extend concurrency much further by running more and more lower- and higher-level components in parallel with each other. Each component can further be parallelized on the fine grain, potentially offering a major increase in scalability of Earth system models. We present here first results from this approach, called Coarse-grained Component Concurrency. Within the GFDL Flexible Modeling System, the atmospheric radiative transfer component has been configured to run in parallel with the atmospheric dynamics and all other atmospheric physics components. We will explore the algorithmic challenges involved in such an approach, and present results from such simulations. Plans to achieve even greater levels of coarse-grained concurrency by extending this approach within other components such as the ocean, will be discussed.

show abstract

Application Centric Energy-Efficiency Study of Distributed Multi-Core and Hybrid CPU-GPU Systems

Cited by 11 publications

References 18 publications

CPMIP: measurements of real computational performance of Earth system models in CMIP6

CPMIP: measurements of real computational performance of Earth system models in CMIP6

Evaluating the performance and energy efficiency of the COSMO-ART model system

Coarse-grained component concurrency in Earth System modeling

Contact Info

Product

Resources

About