% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Asch:862062,
author = {Asch, M. and Moore, T. and Badia, R. and Beck, M. and
Beckman, P. and Bidot, T. and Bodin, F. and Cappello, F. and
Choudhary, A. and de Supinski, B. and Deelman, E. and
Dongarra, J. and Dubey, A. and Fox, G. and Fu, H. and
Girona, S. and Gropp, W. and Heroux, M. and Ishikawa, Y. and
Keahey, K. and Keyes, D. and Kramer, W. and Lavignon, J-F
and Lu, Y. and Matsuoka, S. and Mohr, B. and Reed, D. and
Requena, S. and Saltz, J. and Schulthess, T. and Stevens, R.
and Swany, M. and Szalay, A. and Tang, W. and Varoquaux, G.
and Vilotte, J-P and Wisniewski, R. and Xu, Z. and Zacharov,
I.},
title = {{B}ig data and extreme-scale computing: {P}athways to
{C}onvergence-{T}oward ashaping strategy for a future
software and data ecosystem for scientific inquiry},
journal = {The international journal of high performance computing
applications},
volume = {32},
number = {4},
issn = {1741-2846},
address = {Thousand Oaks, Calif.},
publisher = {Sage Science Press},
reportid = {FZJ-2019-02426},
pages = {435 - 479},
year = {2018},
abstract = {Over the past four years, the Big Data and Exascale
Computing (BDEC) project organized a series of five
international workshops that aimed to explore the ways in
which the new forms of data-centric discovery introduced by
the ongoing revolution in high-end data analysis (HDA) might
be integrated with the established, simulation-centric
paradigm of the high-performance computing (HPC) community.
Based on those meetings, we argue that the rapid
proliferation of digital data generators, the unprecedented
growth in the volume and diversity of the data they
generate, and the intense evolution of the methods for
analyzing and using that data are radically reshaping the
landscape of scientific computing. The most critical
problems involve the logistics of wide-area, multistage
workflows that will move back and forth acrossthe computing
continuum, between the multitude of distributed sensors,
instruments and other devices at the networks edge, and the
centralized resources of commercial clouds and HPC centers.
We suggest that the prospects for the future integration of
technological infrastructures and research ecosystems need
to be considered at three different levels. First, we
discuss the convergence of research applications and
workflows that establish a research paradigm that combines
both HPC and HDA, where ongoing progress is already
motivating efforts at the other two levels. Second, we offer
an accountof some of the problems involved with creating a
converged infrastructure for peripheral environments, that
is, a shared infrastructure that can be deployed throughout
the network in a scalable manner to meet the highly diverse
requirements for processing, communication, and
buffering/storage of massive data workflows of many
different scientific domains. Third, we focus on some
opportunities for software ecosystem convergence in big,
logically centralized facilities that execute large-scale
simulations and models and/or perform large-scale data
analytics. We close by offering some conclusions and
recommendations for future investment and policy review.},
cin = {JSC},
ddc = {004},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {511 - Computational Science and Mathematical Methods
(POF3-511)},
pid = {G:(DE-HGF)POF3-511},
typ = {PUB:(DE-HGF)16},
UT = {WOS:000438959200001},
doi = {10.1177/1094342018778123},
url = {https://juser.fz-juelich.de/record/862062},
}