First-ever full observable universe simulation

Alimi, Jean‐Michel; Bouillot, Vincent; Reverdy, Vincent; Corasaniti, Pier-Stefano; Balmès, Irène; Requena, Stéphane; Delaruelle, Xavier; Richet, Jean-Noel

doi:10.1109/sc.2012.58

Cited by 15 publications

(16 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pFoF code also proved to be a highly efficient analysis tool, for instance, it has been used to analyse the DEUS-FUR (Alimi et al 2012) simulations (8192 3 particles) using 32 768 processes, showing good scalability and low memory use during the "Grand Challenge" test phase of the C supercomputer. Finally as seen in the following, the I/O step is efficient but could probably be optimized.…”

Section: Numerical Resultsmentioning

confidence: 99%

“…Results of the DEUS-FUR simulations show that the I/O bandwidth of the C supercomputer is saturated by 4096 processes writing at the same time (Alimi et al 2012). This supercomputer-dependent feature explains the low speed-up for high number of processes.…”

Section: Strong Scalingmentioning

confidence: 99%

“…LSST, EUCLID or SKA), the need for larger and larger cosmological N-body simulations is greater than ever. With the ever-increasing memory and computing power of supercomputers, recent simulations are able to handle as many as one trillion particles or resolution elements (Alimi et al 2012;Habib et al 2012). While this provides access to new scientific questions, a drawback lies in the generation of petabytes of data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

pFoF: a highly scalable halo-finder for large cosmological data sets

Roy¹,

Bouillot²,

Rasera³

2014

A&A

Self Cite

View full text Add to dashboard Cite

We present a parallel implementation of the friends-of-friends algorithm and an innovative technique for reducing complex-shaped data to a user-friendly format. This code, named pFoF, contains an optimized post-processing workflow that reduces the input data coming from gravitational codes, arranges them in a user-friendly format and detects groups of particles using percolation and merging methods. The pFoF code also allows for detecting structures in sub-or non-cubic volumes of the comoving box. In addition, the code offers the possibility of performing new halo-findings with a lower percolation factor, useful for more complex analysis. In this paper, we give standard test results and show performance diagnostics to stress the robustness of pFoF. This code has been extensively tested up to 32768 MPI processes and has proved to be highly scalable with an efficiency of more than 75%. It has been used for analysing the Dark Energy Universe Simulation: Full Universe Runs (DEUS-FUR) project, the first cosmological simulations of the entire observable Universe, modelled with more than half a trillion dark matter particles.

show abstract

Section: Numerical Resultsmentioning

confidence: 99%

Section: Strong Scalingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

pFoF: a highly scalable halo-finder for large cosmological data sets

Roy¹,

Bouillot²,

Rasera³

2014

A&A

Self Cite

View full text Add to dashboard Cite

show abstract

“…This model complements the cosmo-OWLS simulations by modelling a smaller volume at higher resolution with an independent numerical method and independent treatment of subgrid physics. In addition, lightcone catalogues of halos with mass >10 13 h −1 M computed for various DE models are available from the DEUS project (Alimi et al 2012;Rasera et al 2014).…”

Section: Associated Cosmological Simulationsmentioning

confidence: 99%

The XXL Survey

Pierre

Pacaud

Adami

et al. 2016

A&A

247

View full text Add to dashboard Cite

Context. The quest for the cosmological parameters that describe our universe continues to motivate the scientific community to undertake very large survey initiatives across the electromagnetic spectrum. Over the past two decades, the Chandra and XMM-Newton observatories have supported numerous studies of X-ray-selected clusters of galaxies, active galactic nuclei (AGNs), and the X-ray background. The present paper is the first in a series reporting results of the XXL-XMM survey; it comes at a time when the Planck mission results are being finalised. Aims. We present the XXL Survey, the largest XMM programme totaling some 6.9 Ms to date and involving an international consortium of roughly 100 members. The XXL Survey covers two extragalactic areas of 25 deg 2 each at a point-source sensitivity of ∼5 × 10 −15 erg s −1 cm −2 in the [0.5−2] keV band (completeness limit). The survey's main goals are to provide constraints on the dark energy equation of state from the spacetime distribution of clusters of galaxies and to serve as a pathfinder for future, wide-area X-ray missions. We review science objectives, including cluster studies, AGN evolution, and large-scale structure, that are being conducted with the support of approximately 30 follow-up programmes. Methods. We describe the 542 XMM observations along with the associated multi-λ and numerical simulation programmes. We give a detailed account of the X-ray processing steps and describe innovative tools being developed for the cosmological analysis. Results. The paper provides a thorough evaluation of the X-ray data, including quality controls, photon statistics, exposure and background maps, and sky coverage. Source catalogue construction and multi-λ associations are briefly described. This material will be the basis for the calculation of the cluster and AGN selection functions, critical elements of the cosmological and science analyses. Conclusions. The XXL multi-λ data set will have a unique lasting legacy value for cosmological and extragalactic studies and will serve as a calibration resource for future dark energy studies with clusters and other X-ray selected sources. With the present article, we release the XMM XXL photon and smoothed images along with the corresponding exposure maps.

show abstract

“…Examples of such time-stepped applications include behavioral simulations [1], [2], [3], [4], and n-body problem [5], [6], [7], [8] and also are pervasive in graph algorithms [9], [10], [11], [12], scientific computing [13], [14] and so on. Recently, these applications have again attracted much attentions because they are becoming instrumental in characterizing physical, ecological, and societal systems.…”

Section: Introductionmentioning

confidence: 99%

Resisting Skew-Accumulation for Time-Stepped Applications in the Cloud via Exploiting Parallelism

Liao

Jin

Min

2015

IEEE Trans. Cloud Comput.

View full text Add to dashboard Cite

Abstract-Time-stepped applications are pervasive in scientific computing domain but perform poorly in the cloud because these applications execute in discrete time-step or tick and use logical synchronization barriers at tick boundaries to ensure correctness. As a result, the accumulated computational skew and communication skew that were unsolved in each tick can slow down time-stepped applications significantly. However, the existing solutions have focused only on the skew in each tick and thus cannot resist the accumulation of skew. To fill in this gap, an efficient approach to resisting the accumulation of skew is proposed in this paper via fully exploiting parallelism among ticks. This new approach allows the user to decompose much computational part (also called asynchronous part) of the processing for an object, into several asynchronous sub-processes which are dependent on one data object. Each sub-process from different ticks can then proceed in advance using the idle time whenever the needed data object is available, redressing the negative effects caused by accumulated unsolved computational and communication skew. To efficiently support such an approach, a data-centric programming model and also a runtime system, namely AsyTick, coupled with an ad hoc scheduler are developed. Experimental results show that the proposed approach can improve the performance of time-stepped applications over a state-of-the-art computational skew-resistant approach up to 2.53 times.

show abstract

First-ever full observable universe simulation

Cited by 15 publications

References 23 publications

pFoF: a highly scalable halo-finder for large cosmological data sets

pFoF: a highly scalable halo-finder for large cosmological data sets

The XXL Survey

Resisting Skew-Accumulation for Time-Stepped Applications in the Cloud via Exploiting Parallelism

Contact Info

Product

Resources

About