[hpc-announce] CFP: 3rd workshop data locality ( In conjunction with Euro-Par 2019 Gottingen)

Thu Apr 11 06:50:21 CDT 2019

Submission deadline : May 10, 2019

A well-known handicap for HPC applications running on modern highly parallelized
and heterogeneous HPC platforms is that an increasing amount of time is spent in
communication and data transfers; thus, it is necessary to design, implement and
validate new approaches to optimize process placement and data locality

Website: https://project.inria.fr/coloc

Program chairs
	- Emmanuel Jeannot, Inria France 

Program Committee
	- George Bosilca, UTK, USA
	- Florina Ciorba, University of Basel, Switzerland
	- Matthias Diener, University of Illinois at Urbana-Champaign, USA
	- Anshu Dubey, Argonne Natl Lab, USA
	- Karl Fuerlinger, Ludwig-Maximilians-University, Munchen, Germany
	- Brice Goglin, Inria, France
	- Aleksandar Ilic, INESC-ID/IST, Universidade de Lisboa, Portugal
	- Vitus Leung, Sandia National Laboratories, USA
	- Hatem Ltaief, KAUST, Saudi Arabia
	- Allen Malony, Institution: University of Oregon, USA
	- Naoya Maruyama, LLNL, USA
	- Lawrence, Mitchell, Durham University, UK
	- Hartmut Mix, Technische Universitat Dresden, Germany
	- Marc Perache, CEA, France
	- Eric Petit, Intel, France
	- Didem Unat, Koc University, Turkey

Call for Paper

The COLOC workshop seeks contribution targeting (i) developing methods and tools
enabling to model all resources of a computing platform using a hierarchical
topology that describes the characteristics of these resources (ii) enhancing
upper software layers (resource manager; data communication libraries;
performance analysis tools) to better manage data placement, thereby maximize
application performance, and (iii) validating data-locality optimization, using
applications from different domains. The aim of this workshop is to present the
main recent results in the domain of parallel computing where locality and
topology is used to enhance performance. Concerning, application domain, we will
seek contributions from several fields. First, we will target high-performance
computing. However, we also look at contributions on data locality and energy
efficiency, data locality in the context of BigData or deep learning


Areas or research interest include, but are not limited to: 
	  Modeling node topology
	  Modeling network and communication
	  Performance analysis of applications to understand affinity
	  Affinity metrics
	  Runtime support for extracting affinity from application
	  Code analysis in order to understand communication pattern
	  Algorithm to improve locality
	  Language, abstraction and compiler support for data locality 
	  Data structure and library support to better manage memory access
	  Runtime-system and dynamic locality management
	  System-scale locality optimization
	  Validating locality optimization at thread or process level
	  Memory management
	  Locality management in large-scale application

Targeted audience:
	  HPC application developers interested in exploring new ways to optimize their code.
	  HPC centers and clusters managers to enhance cluster usage and application efficiency.
	  Academics and researchers in scientific computing.

Important date:
	  Workshop papers due: May 10, 2019
	  Workshop author notification: June 28, 2019
	  Informal Camera-ready version : July 22, 2019
	  Workshop date: Monday August 26 or 27, 2019

What and how to submit a paper

Paper, in PDF format, should be submitted to the workshop easychair. Papers
should be formatted according to the LNCS style that can be downloaded from the
springer website. Page limit is 12. It includes everything (text, figures,
references) and will be strictly enforced by the submission system. Complete
LaTeX sources must be provided for accepted papers. Papers should be typeset
using the single column format. All submitted research papers will be
peer-reviewed. Only contributions that are not submitted elsewhere or currently
under review will be considered. Authors of accepted papers will have to sign a
Springer copyright form. Short papers (2-4 pages) are also accepted
submission. However, only paper which camera-ready version will be longer than
10 pages will be included in the proceedings published by Springer in the
ARCoSS/LNCS series.

Submission link: 

https://easychair.org/my/conference.cgi?conf=europar2019workshops (choose COLOC   Workshop on Data Locality).

More information about the hpc-announce mailing list