[hpc-announce] CFP HiPINEB'19 - Washington D.C., USA - 5th IEEE International Workshop on High-Performance Interconnection Networks in the Exascale and Big-Data Era (co-located with IEEE HPCA 2019)

Fri Nov 30 12:55:54 CST 2018

[Apologies if you receive this CFP from multiple sources]

==================================================================
HiPINEB 2019

The 5th IEEE International Workshop on High-Performance Interconnection 
Networks in the Exascale and Big-Data Era

February 16-20 2019, Washington D.C., USA
http://hipineb.i3a.info/hipineb2019/

To be held in conjunction with the HPCA Conference 2019
==================================================================

ABSTRACT

By the year 2023, High-Performance Computing (HPC) Systems are expected 
to break the performance barrier of the Exaflop (10^18 FLOPS) while 
their power consumption is kept at current levels (or increases 
marginally), what is known as the Exascale challenge. In addition, more 
storage capacity and data-access speed is demanded to HPC clusters and 
datacenters to manage and store huge amounts of data produced by 
software applications, what is known as the Big-Data challenge. Indeed, 
both the Exascale and Big-Data challenges are driving the technological 
revolution of this decade, motivating big research and development 
efforts from industry and academia. In this context, the interconnection 
network plays an essential role in the architecture of HPC systems and 
datacenters, as the number of processing or storage nodes to be 
interconnected in these systems is very likely to grow significantly to 
meet the higher computing and storage demands. Besides, the capacity of 
the network links is expected to grow, as the roadmaps of several 
interconnect standards forecast. Therefore, the interconnection network 
should provide a high communication bandwidth and low latency, otherwise 
the network would become the bottleneck of the entire system. In that 
regard, many design aspects are considered when it comes to improving 
the interconnection network performance, such as topology, routing 
algorithm, power consumption, reliability and fault tolerance, 
congestion control, programming models, control software, etc.

The main goal of the fifth edition of HiPINEB is to gather and discuss 
in a full-day event the latest and most prominent efforts and advances, 
from both industry and academia, in the design and development of 
scalable high-performance interconnection networks, especially those 
oriented to meet the Exascale challenge and Big-data demands.

All researchers and professionals, from both industry and academia, 
working in the area of interconnection networks for scalable HPC systems 
and Datacenters are encouraged to submit an original paper to the 
workshop and to attend this event.

TOPICS OF INTEREST

The list of topics covered by this workshop includes, but is not limited 
to, the following:

* Interconnect architectures and network technologies for high-speed, 
low-latency interconnects.
* Scalable network topologies, suitable for interconnecting a huge 
number of nodes.
* Power saving policies in the interconnect devices and network 
infrastructure, both at software and hardware level.
* Good practices in the configuration of the network control software.
* Network communication protocols: MPI, RDMA, MapReduce, etc.
* APIs and support for programming models.
* Routing algorithms.
* Quality of Service (QoS).
* Reliability and Fault Tolerance.
* Load balancing and traffic scheduling.
* Network Virtualization.
* Congestion Management.
* Applications and Traffic characterization.
* Modeling and simulation tools.
* Performance Evaluation.
* Interfacing accelerators through the interconnect (GPUs, Xeon Phi, etc).
* Network infrastructure in distributed storage, distributed databases, 
and Big-Data.

Furthermore, short papers in the above topics will be also taken into 
consideration, as long as they are based on emerging ideas, 
work-in-progress and early, high-impact achievements.

Note, however, that papers focused on topics that are too far from the 
design, development, and configuration of high-performance interconnects 
for HPC systems and Datacenters (e.g., mobile networks, intrusion 
detection, peer-to-peer networks or grid/cloud computing) will be 
automatically considered as out of scope and rejected without review.

PAPER SUBMISSIONS

Regular and short papers must be in PDF format and should include title, 
authors and affiliations as well as the e-mail address of the contact 
author. Submitted regular manuscripts may not exceed 8 single-spaced 
double-column pages using 10-point size font on 8.5x11 inch pages, 
including figures, tables, and references. Short papers may not exceed 4 
single-spaced double-column pages using 10-point size font on 8.5x11 
inch pages. At least one author of the paper must be registered for the 
conference workshop. The conference style is based on IEEE (available 
at http://www.ieee.org/conferences_events/conferences/publishing/templates.html).

HiPINEB manuscript submissions are managed by easyChair. To submit a 
paper, go to https://easychair.org/conferences/?conf=hipineb2019 and 
follow the instructions.

REVIEW PROCESS

Authors are entitled to submit original papers of high technical 
quality, according to the list of topics described above. Papers will be 
reviewed based on originality, novelty, technical strength, presentation 
quality, correctness and relevance to the conference scope.

WORKSHOP PROCEEDINGS

Papers will be published in the HiPINEB proceedings. Further details 
will be provided soon.

SPECIAL ISSUE

Best papers among those selected for HiPINEB 2019 will be invited to 
submit an extended version to a journal indexed in the JCR index. 
Further details will be provided soon.

IMPORTANT DATES

* Submission Opens: November 28, 2018
* Paper submission due: January 20, 2019 (Hard deadline)
* Notification of acceptance: January 30, 2019
* Early Registration due: TBA (http://hpca2019.seas.gwu.edu/)
* Camera-ready papers due: February 2, 2019
* Workshop date: February 16-17, 2019

All deadlines are set at 11:59 p.m. anywhere on Earth
(Cf. http://wirelessman.org/aoe.html).

WORKSHOP ORGANIZATION

Organizers:

* Pedro Javier Garcia, University of Castilla-La Mancha, Spain
* Jesus Escudero-Sahuquillo, University of Castilla-La Mancha, Spain

Steering Committee:

* Jose Duato, Technical University of Valencia, Spain
* Ada Gavrilovska, Georgia Tech, USA
* Maria Engracia Gómez, Technical University of Valencia, Spain
* Torsten Hoefler, ETH Zurich, Switzerland
* Timothy M. Pinkston, University of Southern California, USA
* Francisco Jose Quiles, University of Castilla-La Mancha, Spain
* Eitan Zahavi, Mellanox, Israel

Program Committee:

* TBA

ADDITIONAL INFORMATION

For more information on HiPINEB 2019 check the website at: 
http://hipineb.i3a.info/hipineb2019 or, if you have any question, please 
contact the workshop organizers at hipineb at dsi.uclm.es