[hpc-announce] CFP: Job Scheduling Strategies for Parallel Processors (JSSPP 2014)

Narayan Desai desai at mcs.anl.gov
Tue Dec 24 14:32:13 CST 2013

18th Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP)

In Conjunction with IPDPS 2014
Phoenix, Arizona, USA
23 May 2014

The JSSPP workshop addresses all scheduling aspects of parallel processing.

Large parallel systems have been in production for about 20 years, creating the need of scheduling for such systems. This workshop was created in 1995 to provide a forum for the research and engineering community working in the area. Initially, parallel systems were very static. Machines were built in fixed configurations, which would be wholesale replaced every few years. Much of the workload consisted of parallel scientific jobs. These jobs were static, running on a fixed number of nodes. Systems were primarily managed via batch queues. The user experience was far from interactive; jobs could wait in queues for days or even weeks.

A little over 10 years ago, the emergence of large scale, interactive, web applications began to drive the development of a new class of systems and schedulers. These systems would run “services”, which would essentially never terminate (unlike scientific jobs). This created systems and schedulers with vastly different properties. Moreover, this created an enormous demand for computing resources, resulting in a commercial market of competing providers. At the same time, the increasing demands for more power and interactivity have driven scientific platforms in a similar direction, causing the lines between these platforms to blur.

Nowadays, parallel processing is much more dynamic and connected. Many workloads are interactive and make use of variable resources over time. Complex parallel infrastructures can now be built on the fly, using resources from different sources, provided with different prices and quality of services. Capacity planning became more proactive, where resources are acquired continuously, with the goal of staying ahead of demand. The interaction model between job and resource manager is shifting to one of negotiation, where they agree on resources, price, and quality of service. These are just a few examples of the open issues facing our field.

JSSPP solicits papers that address any of the challenges in parallel scheduling, including:

Design and evaluation of new scheduling approaches.
Performance evaluation of scheduling approaches, including methodology, benchmarks, and metrics.
Workloads, including characterization, classification, and modeling.
Consideration of additional constraints in scheduling systems, like job priorities, price, accounting, load estimation, and quality of service guarantees.
Impact of scheduling strategies on application performance, user friendliness, cost efficiency, and energy efficiency.
Scaling and composition of very large scheduling systems.
Cloud provider issues: capacity planning, service level assurance, reliability.
Interaction between schedulers on different levels, like processor level as well as whole single- or even multi-owner systems.
Experience reports from production systems.
Experience reports from large scale compute campaigns.
From its very beginning, JSSPP has strived to balance practice and theory in its program. This combination provides a rich environment for technical debate about scheduling approaches including both academic researchers as well as participants from industry. JSSPP is a high-visibility workshop, which has been ranking repeatedly in the top 10% of Citeseer’s venue impact list.
Submission Dates and Guidelines

DEADLINE:	19 January 2014
NOTIFICATION:	4 March 2014
Papers should be no longer than 20 single-spaced pages, 10pt font, including figures and references. All papers in scope will be reviewed by at least three members of the program committee. All submissions must follow the LNCS format, see the instructions at Springer's web site.

Files must be submitted electronically in PDF format and must be formatted for 8.5x11 inch paper. Papers must be submitted via EDAS; To submit a paper, click here.


Registration will be part of the IPDPS process and is handled by the IEEE. For details, see the IPDPS web site.

Interim proceedings containing a collection of the papers presented will be distributed at the workshop in electronic form. It is planned to also publish a post-workshop proceedings in the Springer Lecture Notes on Computer Science series, as was done in previous years (pending approval from Springer).
Workshop organizers

Walfredo Cirne, Google
Narayan Desai, Argonne National Laboratory
Program Committee

Henri Casanova, University of Hawaii at Manoa
Julita Corbalan, Technical University of Catalonia
Dick Epema, Delft University of Technology
Gilles Fedak,	 INRIA
Dror Feitelson, The Hebrew University
Liana Fong,	 IBM T. J. Watson Research Center
Eitan Frachtenberg, Facebook
Ali Ghodsi, UC Berkeley
Alfredo Goldman, University of Sao Paulo
Allan Gottlieb, New York University
Alexandru Iosup, Delft University of Technology
Morris Jette, SchedMD LLC
Rajkumar Kettimuthu, Argonne National Laboratory
Dalibor Klusáček, Masaryk University
Zhiling Lan,	 Illinois Institute of Technology
Bill Nitzberg, Altair Engineering
Larry Rudolph, MIT
Uwe Schwiegelshohn, Technical University Dortmund
Mark Squillante, IBM T. J. Watson Research Center
Murray Stokely, Google
Wei Tang,	 Argonne National Laboratory
Dan Tsafrir, Technion - Israel Institute of Technology
Ramin Yahyapour, GWDG - University of Göttingen

More information about the hpc-announce mailing list