VTDC15 - The 8th International Workshop on Virtualization Technologies in Distributed Computing
Visit HPDC'15 website

Contents

VTDC Workshop Series

The convergence of virtualization technologies and distributed computing is an exciting subject and the aim of many research projects in both academia and industry.

Since the beginning of VTDC in 2006, a number of events dealing with virtualization and cloud computing concerns have taken place. All of them have contributed to the improvement of virtualization technologies leading to more complex and larger scale systems. However, limiting the scope of Distributed Computing to Cloud platforms is not enough. For the VTDC Steering Committee, Distributed Computing is larger than just Cloud platforms and the VTDC workshop should continue to be a forum for the exchange of ideas and experiences on the use of different virtualization technologies in distributed computing, including the management of HPC, Data-Intensive or web hosting platforms as well as concerns dealing with the virtualization of network and storage facilities.

VTDC15: Convergence Between Cloud and HPC

VTDC'15 will be held in Portland, in conjunction with the 24th edition of HPDC (the International Symposium on High Performance Distributed Computing) with the support of FCRC 2015.

During the past few years, a convergence has been observed between cloud computing and High Performance Computing (HPC) at all levels, such as infrastructures, technologies, and applications. For example, cloud infrastructures are increasingly pressured to improve energy efficiency and resource utilisation, which are traditional HPC concerns, while cloud applications not only include long-running services, but also data-driven applications and number crunching jobs. On the HPC front, job elasticity (or dynamic jobs) has seen its way into batch schedulers: Instead of allocating resources for peak requirements, HPC applications can be allocated the right amount of resources for each execution phase, thus enabling a more efficient resource utilisation. Furthermore, hardware used to be either specialised for HPC or commodity for clouds, whereas now both types of infrastructure converge towards using commodity hardware with a few specialised components, in particular networking but also, e.g., accelerators. In the coming years, we expect this convergence to lead to hybrid infrastructures running hybrid applications, the infrastructures presenting characteristics both of HPC and cloud systems, whereas the applications featuring a mix of compute- and data-intensive applications, as well as user-facing services.

The VTDC workshop is open to researchers and practitioners in academia and industry who are involved in research, development, and planning activities involving the use of hybrid infrastructure and hybrid applications. Of particular interest are submissions highlighting the convergence between HPC and cloud systems at infrastructure, tools, or application level. For example, contributions showing the benefits of applying HPC techniques or technologies to clouds or the reverse are particularly interesting. Also of interests are submission highlighting the difficulty of managing hybrid infrastructures and/or hybrid applications.

More precisely, topics of interest include:

  • Cloud technologies (e.g., virtualisation, containers) applied to HPC
  • Use of HPC technologies (e.g., RDMA, low-latency communication, accelerators) inside clouds
  • Orchestrated management of hybrid applications or hybrid infrastructures
  • Unconventional HPC job scheduling (e.g., elasticity, migration)
  • Running HPC applications on cloud infrastructures
  • Programming models to support HPC application elasticity
  • HPC-as-a-Service platforms
  • Tools and programming models to support hybrid applications
  • Performance modelling for hybrid applications
  • Application deployment issues on cloud and HPC infrastructures
  • Hybrid workloads (e.g., jobs and services), analysis and modelling
  • Case studies of hybrid infrastructures and hybrid applications
  • BigData and data-driven applications running on cloud and HPC infrastructures

Submission

VTDC2015 invites authors to submit original and unpublished work. Submitted papers should be limited to 8 pages (including tables, images, and references) and formatted according to the ACM SIGS Style (http://www.acm.org/publications/gi-proceedings). Document templates can be found at http://www.acm.org/sigs/publications/proceedings-templates. Only pdf format is accepted. All papers will receive at least three reviews. Submission implies the willingness of at least one of the authors to register for the workshop and present the paper. Accepted papers will be included in the HPDC proceedings.

To submit a paper for VTDC 2015, please use the EasyChair submission site: https://easychair.org/conferences/?conf=vtdc15

Dates

  • Abstract submission: Feb 6 Feb 13, 2015 (11:59PM AOE)
  • Paper submission: Feb 13, Feb 25, 2015 (11:59PM AOE)
  • Acceptance notification: March 20, 2015
  • Final papers due: April 20, 2015 (strict deadline!)
  • Workshop: June 15, 2015


Venue

The 8th edition of VTDC is organized in conjuction with ACM FCRC and takes place in the Oregon Convention Center. For more information, please consult the ACM FCRC's website on Travel & Hotel.

Program (Room: C126, First floor)

  • 8:50 Opening Session
  • 9:00 Invited Talk: Efficient High Performance Computing in the Cloud, Dr. Abhishek Gupta, Intel, USA.

(slides)

  • 10:00 Optimizing Xen Inter-domain Communications, Sébastien Frémal (UMONS); Michel Bagein(UMONS); Pierre Manneback (UMONS).

    (slides)

  • 10:30 A2L2: an Application Aware Flexible HPC Scheduling Model for Low-Latency Allocation, Gonzalo P. Rodrigo (Umea University); Per-Olov Östberg (Umea University); Lavanya Ramakrishnan (Lawrence Berkeley National Lab) ; Erik Elmroth (Umea University).

    (slides)

  • 11:00 Coffee Break
  • 12:30 Lunch time
  • 14:00 Invited Talk: HARNESS: Bringing Real Hardware Heterogeneity to the Cloud, Dr. Guillaume Pierre, University of Rennes 1, France

(slides)

  • 15:00 Umbrella: A Portable Environment Creator for Reproducible Computing on Clusters, Clouds, and Grids, Haiyan Meng (University of Notre Dame); Douglas Thain (University of Notre Dame).

(slides)

  • 15:30 Coffee Break
  • 16:00 Integrating Containers into Workflows: A Case Study Using Makeflow, Work Queue, and Docker, Chao Zheng (University of Notre Dame); Douglas Thain (University of Notre Dame).

(slides)

  • 16:30 Invited Talk: Bridging the Divide Between HPC and Commodity System Software, Dr. John J. Lange, University of Pittsburgh, USA

    (slides)

  • 17:30 End of the workshop

Organizers

  • General Chair: Frederic Desprez, Inria - Adrien Lebre, Inria
  • Program Chair: Erik Elmroth, Umeå University and Elastisys, Sweden
  • Steering Committee Chair: Frederic Desprez, Inria, Renato Figueiredo, University of Florida, Kate Keahey, University of Chicago, Argonne National Laboratory, Adrien Lebre, Inria, Manish Parashar, Rutgers University
  • Program Committee:
    • David Breitgand, IBM Haifa, Israel
    • Dilma M Da silva, Qualcomm, USA
    • Peter Dinda, Northwestern University, IL, USA
    • Schahram Dustdar, Vienna University of Technology, Austria
    • Dick Epema, Delft University of Technology, Netherlands
    • Thomas Fahringer, University of Innsbruck, Austria
    • Renato Figueiredo, University of Florida, FL, USA
    • Liana Fong, IBM T. J. Watson Research Center, NY, USA
    • Eitan Frachtenberg, USA
    • Alfredo Goldman, University of Sao Paulo, BR
    • Kartik Gopalan, Binghamton University, NY, USA
    • Fabien Hermenier, University Nice Sophia Antipolis, France
    • Francisco Hernandez-Rodriguez, Umeå University, Sweden
    • Alexandru Iosup, Delft University of Technology, Netherlands
    • Ardalan Kangarlou, NetApp, USA
    • Cristian Klein, Umeå University, Sweden
    • Rajkumar Kettimuthu, Argonne National Laboratory, IL, USA
    • Dalibor Klusáček, Masaryk University, Czech Republic
    • Zhiling Lan, Illinois Institute of Technology, IL, USA
    • Christine Morin, INRIA, France
    • Dhabaleswar K. Panda, Ohio State University, OH, USA
    • Guillaume Pierre, Universite Rennes 1, France
    • Lavanya Ramakrishnan, Lawrence Berkeley Laboratory
    • Omer Rana, Cardiff University, UK
    • Indrajit Roy, HP Labs, CA, USA
    • Larry Rudolph, Two Sigma, USA
    • Uwe Schwiegelshohn, Technical University Dortmund, Germany
    • Xuanhua Shi, Huazhong University, China
    • Rolf Stadler, Royal Institute of Technology, Sweden
    • Mark Stillwell, Imperial College, UK
    • Murray Stokely, Google, CA, USA
    • Frederic Suter, IN2P3, France
    • Johan Tordsson, Umeå University, Sweden
    • Vladimir Vlassov, Royal Institute of Technology, Sweden
    • Wei Tang, Argonne National Laboratory, IL, USA
    • Ramin Yahyapour, GWDG - University of Göttingen, Germany
    • Ming Zhao, Florida International University, FL, USA

Previous VTDC workshops

Contact information

For more information, contact the general or program chairs at: frederic.desprez at inria.fr or adrien.lebre at inria.fr or elmroth at cs.umu.se