[hpc-announce] CFP: SC17 workshop, Computational Reproducibility at Exascale 2017 (CRE-2017)

[Keyrouz, Walid (Fed)]

                        CALL FOR PAPERS

======================================================================

     Computational Reproducibility at Exascale Workshop (CRE2017)
     ------------------------------------------------------------


    Where:          In cooperation with SC17, Denver, Colorado
    When:           Sunday afternoon, November 12, 2017
    Web:            http://www.cs.fsu.edu/~cre
    Submit:         https://easychair.org/conferences/?conf=cre2017
    Deadline:       Monday, August 28, 2017
    Notifications:  Monday, September 18, 2017
    Full Papers:    Monday, October 02, 2017
    Organized by:   Walid Keyrouz (NIST), Miriam Leeser (NEU), and
                    Michael Mascagni (FSU & NIST)

======================================================================

This workshop will address the problems of reproducibility in HPC in
general and those anticipated as we scale to Exascale machines in the
next decade.  We seek contributions of extended abstracts (two pages)
in the areas of computational reproducibility in HPC from academic,
government, and industry stakeholders.  Areas of interest include, but
are not limited to:

- Case studies of reproducibility or the lack of thereof
- Reproducibility issues in current HPC
- System-level solutions
- Algorithmic solutions
- Software solutions
- Uncertainty quantification in computational reproducibility
- Fundamental numerical analysis of reproducibility
- Future prospects


Papers submitted to the workshop will be reviewed and the top papers
will be selected to be presented at the workshop. In addition, a group
of papers will be published in a special issue of the International
Journal of High-Performance Computing and Applications (IJHPCA)
devoted to Computational Reproducibility.  Please note that papers
submitted to the IJHPCA for the CRE2017 special issue must fall within
the IJHPCA's editorial scope.  This primarily means that all papers
for the special issue must have relevance to high-performance
computing.

Overview and Background
=======================

Experimental reproducibility is a cornerstone of the scientific
method.  As computing has grown into a powerful tool for scientific
inquiry, computational reproducibility has been one of the core
assumptions underlying scientific computing.  With "traditional"
single-core CPUs, documenting a numerical result was relatively
straightforward.  However, hardware developments over the past several
decades have made it almost impossible to ensure computational
reproducibility or to even fully document a computation without
incurring a severe loss of performance.  This loss of reproducibility
started when systems combined parallelism (e.g., clusters) with
non-determinism (e.g., single-core CPUs with out-of-order execution).
It has accelerated with recent architectural trends towards platforms
with increasingly large numbers of processing elements, namely
multicore CPUs and compute accelerators (GPUs, Intel Xeon Phi, FPGAs).

Programmers targeting these platforms rely on tools and libraries to
produce codes or execute them efficiently.  As a result, codes can run
efficiently, but have execution details that can be impossible to
predict and are often very difficult to understand after execution.
Furthermore, parallel implementations often result in code with
varying execution orders between runs, leading to non-reproducible
computations.  The underlying reasons are that (1) the hardware and
system software allocate parallel work in ways that are not always
specifiable at compile time and (2) the execution often proceeds in an
opportunistic manner with the execution order changing between runs.
As such, floating-point computations, which are not commutative and
associative, can have different execution orders and execute on
different processing elements between runs, leading to runs with
varying results as a matter of fact.  The predictability of systems is
further complicated by two issues that are becoming more critical as
systems grow in scale: (1) interconnect systems with latencies that
are often outside the control of programmers and (2) reliability as
the mean time between failure (MTBF) is now measured in hours on large
systems.  This situation seriously affects the ability to rely on
scientific computations as a metrological substitute for
experimentation.


This workshop extends the Numerical Reproducibility at Exascale
Workshops (conducted in 2015 and 2016 at SC) to address the broader
range of issues in reproducibility that arise when computing at
Exascale.  The first edition, NRE2015 was held at SC15, its webpage
can be found here: http://www.nist.gov/itl/ssd/is/numreprod2015.cfm.
The second edition, NRE2016, was at SC16 and its webpage can be found
here: http://www.cs.fsu.edu/~cre/nre-2016.html.


Submissions
===========

Submissions of two page extended abstracts are sought.  The format for
the abstracts should follow the IEEE Conference Proceedings format.
Templates are available at "IEEE - Manuscript Templates for Conference
Proceedings"
(https://www.ieee.org/conferences_events/conferences/publishing/templates.html).
The full papers must be in the format of the International Journal of
High-Performance Computing and Applications (IJHPCA)
(https://us.sagepub.com/en-us/nam/manuscript-submission-guidelines).

The abstracts are to submitted as a PDF document using Easychair at
https://easychair.org/conferences/?conf=cre2017

Important Dates (all are Mondays)
=================================

Aug. 28, 2017: submission deadline for two page abstracts via
               https://easychair.org/conferences/?conf=cre2017

Sep. 18, 2017: notification of authors about their submissions based
               on rejection, acceptance as a paper, acceptance as a
               paper and presentation

Oct. 02, 2017: submission deadline for full papers for refereeing via
               the IJHPCA site, the papers must be in IJHPCA format

Organizers and Co-Editors of the IJHPCA Special Issue
=====================================================

- Walid Keyrouz, National Institute of Standards and Technology (NIST), USA
- Miriam Leeser, Northeastern University, USA
- Michael Mascagni, National Institute of Standards and Technology
  (NIST) and Florida State University, USA

Steering Committee
==================

- Dong H. Ahn, Lawrence Livermore National Lab, USA
- David Bailey, UC Davis, USA
- Mike Heroux, Sandia National Laboratory, USA
- Torsten Hoefler, ETH-Zurich, Switzerland
- Walid Keyrouz (co-organizer), NIST, USA
- Miriam Leeser (co-organizer), Northeastern University, USA
- Xiaoye Sherry Li, Lawrence Berkeley National Laboratory, USA
- Yaohang Li, Old Dominion University, USA
- Michael Mascagni (co-organizer), FSU/NIST, USA
- Junji Nagano, Institute of Statistical Mathematics, Japan
- Nathalie Revol, INRIA/ENS-Lyon, France
- Siegfried Rump, University of Hamburg, Germany
- Michela Taufer, University of Delaware

Contact
=======

E-mail: numerical.reproducibility.at.nist.gov (replace ".at." by "@")


	-Walid

------ 


Walid Keyrouz, PhD
Research Scientist
NIST | ITL | SSD
+1 (301) 975-4031