SC|05 SC|05 Gateway to Discovery
About Interactive Schedule Programs Registration Exhibits Initiatives & Challenges News & Press Hotel & Travel
technical papers
tutorials
bofs
panels
masterworks
invited speakers
awards & prizes
posters
workshops
scatter/gather
Workshops

This year, eight workshops will be held in conjunction with the SC|05 conference. Together they offer opportunities for attendees to attend related workshops of interest while at SC|05.

The SC|05 program will include a set of independently planned workshops to offer more interaction and in-depth discussion of timely topics than is possible in the shorter, more traditional technical sessions. The technical program committee will choose a set of workshops to complement the overall technical program. To suggest a workshop for consideration, please send email as soon as possible to the address below with the topic and proposed organization. Workshops may be proposed for either full-day (six hours) or a half-day (three hours) sessions.

All workshops, including date and location are available on the SC|05 interactive schedule at sc05.supercomp.org/schedule/schedule.php

The Titles and Abstract of accepted workshops are listed below:

Grid 2005 - 6th IEEE/ACM International Workshop on Grid Computing
In the last few years, the Grid community has been growing very rapidly and many new technologies and components have been proposed. This, along with the growing popularity of web-based technologies and the availability of cheap commodity components, is changing the way we do computing and business. There are now many ongoing grid projects with research and production-oriented goals.

Grid 2005 is an international meeting that brings together a community of researchers, developers, practitioners, and users involved with the Grid. The objective of Grid 2005 is to serve as a forum to present current and emerging work as well as to exchange research ideas in this field. The previous events in this series were: Grid 2000, Bangalore, India; Grid 2001, Denver; Grid 2002, Baltimore; Grid 2003, Phoenix; and Grid 2004, Pittsburgh. All of these events have been successful in attracting high quality papers and a wide international participation. Last year's event attracted about 400 registered participants.

Grid 2005 topics of interest (in no particular order) include, but are not limited to: Internet-based Computing Models • Internet-based Computing Models • Grid Applications, including eScience and eBusiness Applications • Data Grids, including Distributed Data Access and Management • Grid Middleware and Toolkits • Grid Monitoring, Management and Organization Tools • Resource Management and Scheduling • Networking • Virtual Instrumentation • Grid Object Metadata and Schemas • Creation and Management of Virtual Enterprises and Organizations • Grid Architectures and Fabrics • Grid Information Services • Grid Security Issues • Programming Models, Tools, and Environments • Grid Economy • Autonomic and Utility Computing on Global Grids • Performance Evaluation and Modeling • Cluster and Grid Integration Issues • Scientific, Industrial and Social Implications

grid

 
LaR-2005 (4th International Workshop on Language Runtimes): Validating Next Generation Multicore Programming Models
The DARPA HPCS effort has been tasked with increasing programmer productivity while enabling petascale computing. With the utilization of multicore processors by game consoles, parallel programming will finally become mainstream. Recently, there has been research targeting existing parallel programming models like OpenMP and MPI to multicore architectures. Unfortunately, opinions differ on the utility of this approach. Consequently, emerging multi-level parallel solutions like Cray's Chapel, Sun's Fortress, and IBM's X10 provide new opportunities in both scalable parallelism and high levels of programmer abstraction.

To validate the productivity of these new solutions, we need to dig deeper than their obvious syntactic differences. We will need to understand the core semantics of their respective solutions, their similarities, and differences. Additionally, metrics such as how these solutions manage complexity, ease of use, simplicity, and expressibility need to be evaluated. Furthermore, the impact of the programming environment and code reuse on the amount of new code that has to be written needs to be discussed. Finally, we will need an understanding of how all these productivity features of the proposed solutions impact their runtime performance characteristics.

To ground our discussion, and enable a meaningful comparative analysis, our workshop proposes that a single set of non-trivial algorithms be implemented multiple times in each of the HPCS languages, the DARPA PCA stream languages, and others. The goal of LaR-05 is to take a users perspective and discuss in a relaxed setting the pragmatic usability of the programming solutions being designed for scalable next generation multicore computing architectures.

 
HPCS (Workshop on High Productivity Computing Systems)
The DARPA High Productivity Computing Systems (HPCS) program is focused on providing a new generation of economically viable high productivity computing systems for national security and for the industrial user community. HPCS researchers have initiated a fundamental reassessment of how we define and measure performance, programmability, portability, robustness and ultimately, productivity in the HPC domain.

The value of a High Performance Computing (HPC) system to a user includes many factors, such as execution time on a particular problem, software development time, direct hardware costs and indirect administrative and maintenance costs. The HPCS program is developing systems that deliver increased value to users at a rate commensurate with the rate of improvement in the underlying technologies. This workshop will provide an opportunity for the broader HPC community to see the latest results from HPCS Vendors and the HPCS Productivity team and to provide feedback to the HPCS researchers.

 
HPCNano2005 (IEEE/ACM International Workshop on High Performance Computing for Nano-science and Technology)
Nanotechnology is an exciting field with many potential applications. Its impact is already being felt in materials, engineering, electronics, medicine, and other disciplines. Current research in nanotechnology requires multi-disciplinary knowledge, not only in sciences and engineering but also in high performance computing (HPC) technology. Many nano-science explorations rely on mature, efficient HPC and computational algorithms, practical and reliable numerical methods, and large-scale computing systems. This workshop offers academic researchers, developers, and practitioners an opportunity to discuss various aspects of HPC-related computational methods and problem solving techniques for nano-science and technology research.

This workshop will be conducted in conjunction with IEEE/ACM Supercomputing 2005. The workshop will be guided by the SC|05's Workshop Committee and planned and executed by a workshop program committee. We hope to attract people from diverse science and engineering disciplines, nationally and internationally, to attend the workshop, present their research results, share their experiences and ideas, and plan future collaborations.

More information is available at http://www.uiowa.edu/~nano/HPCNano05/.

 
GCE 2005 (Workshop on Grid Computing Portals)
Grid computing portals have emerged to be important components of many large-scale Grid computing projects, often serving as the primary gateway for extended and diverse communities users. Portals provide well-established mechanisms for providing familiar interfaces to secure grid resources, services, applications, tools, and collaboration services. Furthermore, portals deliver complex grid solutions to users wherever they have access to a web browser running on the Internet without the need to download or install any specialized software or worry about networks and ports, etc. As a result, the science application user is isolated from the complex details and infrastructure needed to operate an application on the grid.

The portal development community is currently undergoing a revolution as component-based architectures and services become standardized and widely adopted. Grid middleware is also changing in response to the services oriented architecture (SOA) approach to hosting services. The move towards an SOA grid maps very well to the architecture already employed by portals, further increasing their value within the grid community.

This workshop will focus on portal projects that are adopting these new technologies and services. We seek papers from all aspects of portal development including portal architecture design and standards studies, toolkits developed in support of portals, as well as high-level application portals that utilize these technologies.

 
Cluster Computing via an Application-Oriented Computational Grid
Grid technologies have been developed to address security, data transport and even job submission from desktop environments; however, installation of heavyweight approaches such as Globus on PCs and workstations are often challenging not only to set up but to maintain and use.

A more user-friendly approach is to push the heavyweight grid technologies to a server and provide a lightweight client on the desktop. The client interacts with the server, which in turn communicates with a remote HPC system running the applications. This lightweight desktop model is implemented in the Computational Chemistry Grid as a three-tier system (client/gridserver/HPC-resource) with the end user only seeing a two-tiered system (client/HPC-systems). For applications requiring simple inputs and producing minimal outputs, a web interface to the batch application server can be constructed. A web-based portal could be used to create the interface. However, with inputs and outputs requiring interactive visualization and larger amounts of data transport, it becomes necessary to provide a client application that is very responsive to object manipulation (xyz rotation/translation) and middleware services that can track and archive job output files.

The Computational Chemistry Grid uses the client-server model for a community of computational researchers to run chemistry applications at five different centers (CCS, U. Kentucky; CCT, LSU; OSC, Ohio State; NCSA, UIUC; and TACC, U. Texas, Austin). This workshop will include a description and discussion of the components of the model: the CCG infrastructure, desktop client, middleware services and scientific applications. The advantages of using this model for any batch-application need will also be examined.

The workshop also will include: • a demonstration of the GridChem client • a panel discussion with some of the developers • discussion of other/participant's tools and technology; and will seek: • input and feedback from the user community, with the goal of: • broadening the current consortium to a community of international scope.

 
State-of-the-Art Visualization Techniques for Gleaning Insights in Large Time-Varying Volume Data
The study of dynamical aspects of physical phenomena or chemical processes is critical to the advances of many sciences. Great investments have been continuously made to revolutionize high-performance computing technologies which enable high-resolution numerical modeling of complex scientific processes from diverse areas such as neuron excitation, combustion, nuclear reaction, earthquakes, long-term weather changes, and even galaxy merger.

These large-scale simulations produce data that is vast in the spatial, temporal and variable domains, creating a formidable challenge for subsequent analysis. In most cases, scientific visualization is the only plausible path to gleaning insight from these enormous data. The ability to interactively visualize and explore the complex, dynamic phenomena contained within these data is absolutely essential to ensure correct interpretation and analysis, to provoke insights, and to communicate those insights with others. Over the past few years, research innovations have been made in data reduction, rendering and interaction techniques, and system integration strategies to improve the interactivity and exploration of large-scale, time-varying data visualization, in particular, through the effort of an NSF ITR project.

The purpose of this workshop is two fold. First, the workshop attendees will be introduced to the latest and greatest research innovations in time-varying data visualization. Second, the attendees will help assess current technology and direct further research directions through an open discussion session.

More information is available at http://vis.cs.ucdavis.edu/Workshops/SC05.

 
Workshop on High Performance Compute Clustering with Windows
With growing use of Microsoft Windows technologies in cluster computing we have found that there is an increasing need in the community for opportunities for the exchange of experiences. Hosting a workshop on this topic at Supercomputer 05 will provide an excellent opportunity for users and potential users to exchange ideas, experiences, and knowledge.

Goals of this workshop are:

  • To promote the peer exchange of experiences with Windows-based Cluster Computing
  • To provide an opportunity for the community building efforts under way in the Windows-based cluster computing world.
  • To provide access to experts in the field of management of large installations of Windows clusters
To lay the groundwork for future peer-reviewed, research & experience-oriented workshops:

Agenda Directions on Windows Clusters -- 
  • Windows HPC Roadmap
  • Product Plans & Directions
  • Key Windows HPC Technologies
Developing Applications
  • Developing Environment/Debugging
  • Compilers for Windows
  • Delegations and Secure Startup
Roundtable on Managing Clusters
  • Cluster Administration
  • Deploying, Updates (Patches), Licensing
  • Dedicated Cycle scavenging, & Hybrid Strategies
  • Security Considerations for Managing Clusters
Enabling Seamless HPC
  • Using Web Services for cluster access
  • Web Service-enabled HPC
  • Custom web interfaces for Scientists 


November 12
Time
Session
Event
Chair/Speaker Location
8:30AM - 5:00PM LaR 2005 (4th International Workshop on Language Runtimes) LaR-2005 (4th International Workshop on Language Runtimes): Validating Next Generation Multicore Programming Models Yahya Mirza 602-604

November 13
Time
Session
Event
Chair/Speaker Location
2:00PM - 6:00PM Grid 2005 (6th IEEE/ACM International Workshop on Grid Computing) Grid 2005 (6th IEEE/ACM International Workshop on Grid Computing) Wolfgang Gentzsch, Daniel Katz 6A
6:00PM - 7:30PM Grid 2005 Poster Session Grid 2005 Poster Session Wolfgang Gentzsch, Daniel Katz 605, 610

November 14
Time
Session
Event
Chair/Speaker Location
8:30AM - 5:00PM Grid 2005 (Day 2) Grid 2005 (Day 2) Wolfgang Gentzsch, Daniel Katz 605, 610
8:30AM - 5:00PM Grid 2005 (Day 2) Grid 2005 (Day 2) Wolfgang Gentzsch, Daniel Katz 6A
1:30PM - 5:00PM HPCS (Workshop on High Productivity Computing Systems) HPCS (Workshop on High Productivity Computing Systems) Jeremy Kepner 619, 620

November 16
Time
Session
Event
Chair/Speaker Location
8:30AM - 5:00PM HPCNano2005 (IEEE/ACM International Workshop on High Performance Computing for Nano-science & Technology) HPCNano2005 (IEEE/ACM International Workshop on High Performance Computing for Nano-science and Technology) Jun Ni 206

November 18
Time
Session
Event
Chair/Speaker Location
8:30AM - 12:00PM GCE 2005 (Workshop on Grid Computing Portals) GCE 2005 (Workshop on Grid Computing Portals) Mary Thomas 606-607
8:30AM - 12:00PM Visualization Techniques for Gleaning Insights in Large Time-Varying Volume Data State-of-the-Art Visualization Techniques for Gleaning Insights in Large Time-Varying Volume Data Kwan-Liu Ma 302
8:30AM - 12:00PM Cluster Computing via an Application-Oriented Computational Grid Workshop on Cluster Computing via an Application-Oriented Computational Grid John W. Connolly, Chona Guiang, Rion Dooley, John Towns, Sudhakar Pamidighantam, Michael Sheetz 602-604
8:30AM - 12:00PM High Performance Compute Clustering with Windows Workshop on High Performance Compute Clustering with Windows Jack Dongarra, David Lifka 202

SC|05 Workshop Committee
John W. Cobb, Chair
Barbara Fossum, Co-Chair

More information is available at http://www.acel.sdsu.edu/mtgs/gce05/.

Questions: workshops@sc05.supercomputing.org