[hpc-announce] Call for Papers - ExaMPI-2019 - Workshop on Exascale MPI 2019
puri at uab.edu
Thu Jun 20 08:28:15 CDT 2019
Call for Papers
ExaMPI-19 - Workshop on Exascale MPI 2019
Sunday, November 10th, 2019
Denver, CO, USA
Held in conjunction with SC19: The International Conference for High
Performance Computing, Networking, Storage and Analysis
In cooperation with the IEEE Computer Society Technical Consortium on
High Performance Computing (TCHPC)
The MPI standard and its implementations have proved surprisingly
scalable. Issues that hampered scalability have been addressed in the
MPI 2.1 – 2.2 definition process, and continued into MPI 3.0 and
3.1. Thus, MPI has been robust and has been able to evolve, without
fundamentally changing the model or specification. For this and many
other reasons, MPI is currently the de-facto standard for HPC systems
and applications. However, there is a need for re-examination of the
message-passing model for extreme-scale systems characterized by
asymptotically decreasing local memory and highly localized
communication networks. Likewise, there is a need for exploring new
innovative and potentially disruptive concepts and algorithms
partially to explore other roads than those taken by the recently
released MPI 2018 Draft Specification. The aim of this workshop is to
bring together developers and researchers to present and discuss
innovative algorithms, protocols, operations, and concepts in Message
Passing programming models, in particular related to MPI or MPI+X.
Topics of interest include (but are not limited to):
- Design and development of scalable Message Passing collective operations.
- Communication and architecture topology mapping interfaces and algorithms.
- Innovative algorithms for scheduling/routing to avoid network congestion.
- Integrated use of structured data layout descriptors.
- One-sided communication models and RDMA-based MPI.
- Support for heterogenous compute devices and heterogeneous memory systems.
- MPI multi-threading and threading requirements from OSes.
- Interoperability of Message Passing and PGAS models.
- Integration of task-parallel models into Message Passing models.
- Fault tolerance in MPI.
- MPI I/O.
Paper submission and publication
There are two submission categories:
(1) Regular research paper: submission of full paper. Regular paper
submissions are limited to 10 single-space pages (including figures,
tables and references) using a 10-point on 8.5x11-inch pages (US
Templates can be found at:
Instructions for preparing regular papers for the proceedings will
be emailed to authors of accepted papers. Accepted regular papers will
be published in the TCHPC proceedings. Selected regular papers will be
invited for submission to a special issue of a journal (more details
to follow soon).
(2) Hot topic abstract: submission of an extended abstract. These
submissions target work-in-progress research on potentially
controversial topics in Message-Passing. Hot topic extended abstracts
are limited to 3 single-space pages. Templates can be found at:
Accepted hot topic extended abstracts will be published only on the
Regular Papers and extended abstracts should be submitted
electronically through Linklings at: https://submissions.supercomputing.org.
Paper Submissions Deadline: August 31, 2019
Paper Notification: October 4, 2019
Final Camera Ready Version: October 14, 2019
More information about the hpc-announce