[hpc-announce] CFP: DLMCS Workshop on Data Locality, Granada, Spain

[Karl Fuerlinger]

==============================================================================
                                CALL FOR PAPERS

        First International Workshop on Data Locality in Modern Computing
                        Systems (DLMCS) Granada, Spain

         Held in Conjunction with ICA3PP 2016, The 16th International
                Conference on Algorithms and Architectures for
                       Parallel Processing (ICA3PP 2016)

                   Granada, Spain, December 14-16, 2016

                            http://www.dlmcs.org

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

SCOPE

The cost of moving data is becoming a dominant factor for performance
and energy efficiency in high performance computing systems. To
minimize data movement, applications have to consider initial data
placement and optimize both vertical data movement in the memory
hierarchy and horizontal data transfer between processing units.

While trends in computer architecture suggest that the number of
computing cores on a node is continuing to increase, it is likely that
some long-held programmability assumptions such as cache coherence
across a whole compute node will no longer be valid on future
systems. At the same time, the inclusion of high-bandwidth memory and
non-volatile storage will further complicate the programming of HPC
systems. To address this situation, application developers need to be
equipped with new techniques, tools, libraries, and programming
abstractions to deal with data locality as a first class concern.


KEY DATES

Submission Deadline:               July 17, 2016
Notification of Acceptance:   September 15, 2016
Final Papers Due:               October 15, 2016
Workshop Date:              December 14-16, 2016


TOPICS

Topics of interest include, but are not limited to

*  Programming abstractions for data locality
*  Approaches for multi-level locality
*  Support for data locality in task-based programming models
*  Global address space approaches and data locality
*  Language extensions and domain-specific libraries for locality
*  On-chip networks and data locality
*  Hardware mechanisms for exploiting locality
*  Locality in large-scale HPC interconnect networks
*  Advances in cache coherence protocols
*  Data locality and communication avoidance
*  Data locality and multi-tier memory systems
*  Approaches for processing in memory
*  Dataflow approaches


PAPER SUBMISSION

Submissions must be formatted according to the Springer LNCS format
and should not exceed 14 pages. All submissions must be in PDF format
and represent substantial original research results not published or
under review elsewhere. At least one author of every accepted paper is
required to attend the conference in order for the paper to be
included in the final proceedings.

For paper submissions please use

   https://www.easychair.org/conferences/?conf=dlmcs2016


For more details please see the DLMCS website at

   http://www.dlmcs.org/dlmcs/2016


WORKSHOP ORGANIZERS

Karl Fuerlinger, Ludwig-Maximilians-Universitaet Muenchen, Germany
Josef Weidendorfer, TU Muenchen, Germany
Jose Gracia, HLRS Stuttgart, Germany

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

-- 
Dr. Karl Fürlinger

Ludwig-Maximilians-Universität München (LMU)
Munich Network Management Team (MNM)
Institut für Informatik / Dept. of Informatics
Oettingenstr. 67, Room E U106
D-80538 München, Germany