SHPCloud 2014 - International Workshop on Extreme Scale Data Cloud Computing Architectures

Extreme scale computing needs architectures that do not have scalability limits .Following the trajectory of existing architecture trends, however, these seem highly unlikely .The current architectures have reached an inflection point signified by a gridlock of well-known impossibilities, such as limitations of circuit packaging technologies in hardware and CAP Theorem in software .The most telling evidence is the commonly accepted notion that it is impossible to gain application performance and reliability at the same time as we up scale the processing architectures .Therefore, "SHPC" means "sustainable high performance computing" .The proposed workshop solicits paradigm shifting architecture proposals, preliminary results, concepts and ideas towards the building of next generation extreme scale data cloud computing architectures that can handle compute intensive and data intensive applications .This workshop will provide a platform for academic architecture researchers, industry practitioners and government agencies to exchange evolving requirements, ideas and current results .Relevance
One distinct feature of the Big Data processing applications from the traditional transaction data processing is the increased computation and data requirements .It also differs from typical HPC (high performance computing) applications in its heavy data traffic .Thus, the architecture challenges must also include data storage architecture since it is integral part of the processing infrastructure .The emergence of auction-based computing clouds makes the architecture challenge even more interesting: How can future applications gain the ability to harness increasingly more volatile resources for increasingly larger datasets? In this context, extreme scale and cloud computing share the same characteristics that falls under the processing architecture matter for Big Data Science 2014 .Workshop Format
The proposed workshop will start with a short introduction session by Justin Shi (shi-AT-temple.edu) discussing the detrimental effects of relying on “virtual circuits” in application programming interfaces (APIs) and a blueprint of statistic multiplexed computing (SMC) architecture .A panel session will be included in the mid-day discussing the typically data center or cloud operation difficulties, wish lists and potential solutions .A half-day demonstration session is also planned for the authors with prototype implementations to perform onsite demos .Topics of Interest
We invite submissions on the theoretical foundation of programming for volatile resources .We will also encourage submissions of practical experiences using compute and data intensive cloud resources .These include but not limited to the following areas:
Theoretical foundation of programming volatile resources .Application scalability analysis using volatile resources .Investigative reports on delivered performance for computation intensive and data intensive applications with or without failure and recovery
Investigative results on delivered cloud performances for computation intensive and data intensive applications
Experiences in non-conventional HPC programming paradigms
Experiences in using auction-based cloud resources
Experiences in virtualized GPU for HPC applications
Experiences in virtualized network for HPC applications
Innovative failure prevention and recovery methods
HPC security considerations using cloud resources
Communication infrastructure virtualization experiences
Private cloud implementation experiences
Innovative cloud auction pricing models
Paper Submission:
Regular papers should be 6-8 pages .Please refer to the main conference site for format and style instructions: http://www.scienceengineering.org/ase/conference/2...
Regular papers are to be selected by the blind peer review process .Position papers can be up to 5 pages, single column with minimal 11 point font .Position papers are to be selected by the Program Committee .At least one author of the accepted paper is expected to present their work at the Workshop .For all paper submissions, please click Here
Workshop Organizers
Justin Y .Shi, CIS, Temple University (Workshop Chair )
Boleslaw Szymanski, CS, Rensselaer Polytechnic Institute (Vice Workshop Chair)
Chiu Tan, CIS, Temple University
Kreishah Abdallah, ECE, New Jersey Institute of Technology
Pavan Balaji, Argon National Laboratory
Moussa Taifi, Cloudamize.com
Chunming Rong, CIPSI, University of Stavanger, Norway,
Dave Yuen, Earth Sciences, University of Minnesota
Eagles Song, Parallel Computers Technology Inc .Wang Gang, Nankai University, China
Xiaoguang Liu, Nankai University, China
Ningfang Mi, Northeastern University, USA (Position Paper Chair)
Christo Kartsakalis, Oak Ridge National Laboratory, USA
Weiwei Chen, University of Southern California, USA
Wei Wei, Xi'an University of Technology, China
Important Dates:
? Submission Deadline: May 15, 2014
? Author Notification: June 1, 2014
? Final Paper Due: June 15, 2014
? Workshop Date: August 4, 2014
Contact: Justin Y .Shi, shi-AT-temple.edu, http://spartan.cis.temple.edu/shi