Dec. 18 — Clusters have become the workhorse for computational science and engineering research, powering innovation and discovery that advance science and society. They are the base for building today’s rapidly evolving cloud and HPC infrastructures, and are used to solve some of the most complex problems. The challenge to make them scalable, efficient, and more functional requires the joint effort of the cluster community in the areas of cluster system design, management and monitoring, at hardware, system, middleware, and application level.
2014 Highlight: Cluster Support for Big Data
The evolution of cluster technologies is expected to substantially impact emerging research areas, such as the increasingly important Data Science field. Therefore, we have chosen this year to highlight research topics expected to bring substantial progress in the way clusters can help in addressing Big Data challenges. Specific topics are dedicated to this direction within all conference tracks alongside more traditional topics. In addition, special tutorials and workshops will focus on cluster technologies for Big Data storage and processing.
New this year: Student Mentoring Track
Today’s Master and PhD students are our future colleagues. The future development of cluster, grid and could computing falls on their shoulders. The Cluster conference is proud to contribute to their education through a specific mentoring program all along the week. This program will include a Poster Master Class delivered by renowned researchers, to improve their poster making and presentation skills. It will also include specific VIP scientific sessions, delivered by first-class lecturers introducing them to their vision of the field, and private question quarters, to give them a chance to ask their questions to plenary speakers after their keynotes. Also, a special “Looking to my future” session will be organized with cluster-oriented company VIPs to tell students the latest opportunities for positions in this area, and how to earn them. Last by not least, special student socializing events will be organized, and various Best-*-Awards offered.
Cluster 2014 is hosted in Madrid, Spain. Attendees will have access to the latest developments in cluster computing technologies and practices. Join the cluster computing community, and discuss new directions, opportunities and ideas that will influence its future. Cluster 2014 welcomes paper submissions on innovative work from researchers and practitioners in academia, government, and industry that describe original research and development efforts in cluster computing.
All papers will be evaluated for their originality, technical depth and correctness, potential impact, relevance to the conference, and quality of presentation. Research papers must clearly demonstrate research contributions and novelty, while experience reports must clearly describe lessons learned and demonstrate impact.
Major topics of interest include, but are not limited to:
Track 1: Cluster Design, Configuration and Administration
- Cluster Architecture for Big Data storage and processing
- Energy-efficient cluster architectures
- Node and system architecture
- Packaging, power and cooling
- Visualization clusters and tiled displays
- GPU and hybrid CPU/GPU clusters
- Interconnect/memory architectures
- Single system image clusters
- Administration and maintenance tools
Track 2: Cluster Software, Middleware, Tools
- Middleware for Big Data management
- Big Data visualization tools
- Performance modeling for Big Data processing
- Performance evaluation, analysis and optimization
- Cloud-enabling cluster technologies and virtualization
- Energy-efficient middleware
- Protocols, libraries, and interfaces
- Lightweight communication protocols
- Resource and job management
- Scheduling and load balancing
- Reliability and high-availability architecture
- Fault tolerance, checkpointing and recovery
- Cost and performance implications of reliability
- Software environments and tools
Track 3: Cluster Storage and File Systems
- Cluster support for Big Data processing
- Cloud storage for Big Data
- Storage support for Data-intensive computing
- Storage cluster architectures
- File systems and I/O libraries
Track 4: Cluster Applications
- Programming models for Big Data processing
- Big Data Application studies on cluster architectures
- HPC Applications on GPUs
- Programming languages and environments
- Hybrid programming techniques (MPI+OpenMP, MPI+OpenCL, etc.)
- Benchmarking & profiling tools
- Performance prediction & modeling
Paper Format: Since the camera-ready version of accepted papers must be compliant with the IEEE Xplore format for publication, submitted papers must conform to the following Xplore layout, page limit, and font size.
- PDF files only are accepted.
- Maximum 9 pages for Technical Papers, maximum 5 pages for Student Papers submitted to the Student Mentoring Track.
- Single-spaced, 2-column numbered pages in IEEE Xplore format (8.5×11-inch paper, margins in inches– top: 0.75, bottom: 1.0, sides:0.625, and between columns:0.25, main text: 10pt ).
- LaTeX and Word Templates are available here: http://www.ieee.org/conferences_events/conferences/publishing/templates.html.
- Only web-based submission is accepted: https://www.easychair.org/conferences/?conf=ieeecluster2014
- Abstracts (required) due: April 24, 2014
- Full Papers Due: May 2, 2014
- Paper Acceptance Notification: June 30, 2014
María S. Pérez, UPM, Madrid, General Chair
Call for Workshops
Workshops will be held Friday 26 September 2014.
The conference is particularly interested in workshops related to:
- Current and future directions in cluster technology, including hardware, software, networks, data, and storage
- Clusters driving innovation in industrial and academic research
- Clusters in education and outreach (both formal education and outreach efforts, as well as how the community can help educate and train a twenty-first century workforce)
- Clusters and clouds in cyberinfrastructure (eScience/eResearch) strategy
- Clusters in distributed visualization
Workshop submissions should be a small number of pages, including the following content:
- Names and affiliations of organizers
- If held previously, when and in which venues? How many people attended? How many submissions/papers?
- How workshop is to be advertised
- How papers/workshop will be published
- Proposed agenda
- Proposed speakers or from where speakers will be drawn
- Proposed program committee, if applicable
The expected workshop schedule is:
- Workshop proposals due: 3 March 2014
- Workshop decisions announced: 24 March 2014
- Camera-ready workshop papers due, if published in conference proceedings: TBD
Questions and submissions:
Daniel S. Katz, University of Chicago & Argonne National Laboratory firstname.lastname@example.org Cluster 2014 Workshops Chair
Call for Tutorials
Experts in cluster computing are invited to share their expertise with the community by submitting proposals for tutorials to be presented at the Cluster 2014 conference that will be held on September 22-26, 2014 in Madrid, Spain. The Cluster 2014 tutorials program will give attendees the opportunity to explore in depth a broad range of topics on the design of clusters and related technologies and on effectively managing or using cluster resources and services. Cluster 2014 invites proposals for tutorials, either full day (six hours) or half-day (three hours). All tutorials will be presented on September 22, 2014.
Topics of interest include but are not limited to cluster node and system architecture, GPU clusters, cluster management tools, cluster distributed operating systems, single system image systems, memory management, data management, storage systems, distributed and parallel file systems, I/O libraries, high performance networks, communication systems, resource and job management systems, scheduling and load balancing, virtualization, IaaS and PaaS cloud software, parallel programming models and runtimes, programming language and environments, security, fault-tolerance, checkpointing and high availability, power management and cooling, performance evaluation, analysis and optimization, benchmarking, gateways, visualization, web service hosting, data analytics frameworks, computational science, Grids…
Cluster 2014 technical program highlights cluster support for Big Data problems. Tutorials related to this topic are particularly welcome.
Proposals should contain the following material
A 3-page description including:
- Unordered List Item
- A title, an abstract (400 words maximum) & a syllabus
- Discussion of the topic’s relevance
- Goals and any demos and exercises
- A description of the target audience
- Prerequisite background and content level
- An indication of half-day or full-day duration
- A listing of equipment needs. For example, proposals might list a projector for just a presentation, or a projector and workstations with minimum specifications for a hands-on tutorial.
- A slide deck from a recent tutorial (if one exists) or a draft slide deck
- If applicable, details on when/where the tutorial has been presented before, including attendance numbers.
- A brief bio-sketch (2 pages per presenter).
Please note that the number of presenters is limited to 2 for a half-day tutorial and to 3 for full day tutorial.
A single pdf file with all the material described above should be submitted to the Cluster 2014 conference on-line submission system under the tutorial track: https://www.easychair.org/conferences/?conf=ieeecluster2014
Submission: May 19, 2014
Notification of acceptance: June 13, 2014
Cluster 2014 Tutorial Chair
Christine Morin, Inria, France
Stephen Scott, ORNL, USA
Florin Isaila, University Carlos III, Spain