EDUCAUSE | High-Performance Computing and Contributed by or Presented at Net@EDU (State Networks)

Cyberinfrastructure and Emerging Scientific Data and Knowledge Systems

drupal — Tue, 19 Feb 2008 11:38:31 -0600

Scientific progress and discovery increasingly hinge upon analysis of a wide variety of data sources. With these datasets growing ever larger and more complex, we are increasingly challenged in the areas of management, preservation, integration, and access to high-level services that facilitate inquiry and hypothesis testing. We are also seeing an increase in geographically distributed resources. For science to advance, we must develop new knowledge-based environments that allow researchers to easily query and analyze vast holdings of diverse, distributed data. NCAR has joined a number of collaborations aimed at addressing critical science and societal challenges, ranging from the Intergovernmental Panel on Climate Change (IPCC), the International Polar Year, regional climate modeling, solar-terrestrial science, digital preservation, and more. We will survey these areas, discuss some of the challenges we face in developing effective cyberinfrastructure, and briefly touch on the important migration towards "science gateways" and knowledge-based environments.

International Perspectives on Research Computing

drupal — Fri, 09 Feb 2007 09:47:18 -0600

Research computing-how to respond to the increasing diverse demands for services and support for computing and networking-is commanding greater attention. Now that high-end desktop hardware is affordable and high-speed networking readily available, institutions face expanding resource demand and the need for more coordinated planning. U.S. universities are not alone in confronting this exponential demand-it is universal. This session will provide a look at how Canada, the EU, and Mexico are responding to the challenge.

International Scaling: Realizing the Potential of Grid and High-End Computing

drupal — Fri, 09 Feb 2007 09:47:18 -0600

Large-scale grids containing thousands of sites are being considered, developed, and deployed. Similarly, node counts for terascale systems have grown to tens of thousands, with petascale system likely to contain hundreds of thousands of nodes. In addition, a tsunami of new experimental and computational data poses equally vexing problems in analysis, transport, visualization, and collaboration. We must rethink traditional assumptions about software scaling, component integration, and hardware reliability. Our thesis is that the "two worlds" of software-grids and parallel systems-must meet, embodying ideas from each, if we are to build a usable and useful infrastructure. This talk describes approaches to scalable performance measurement, dynamic adaptation, and grid integration and their implications for large-scale science and engineering.

Networking Research: Trends and Issues

drupal — Fri, 09 Feb 2007 09:47:18 -0600

Networking research can be broadly categorized into two directions: understanding and improving current networks, and imagining future networks and related protocol/technology research and development. Significant research continually improves current features of the Internet, a prime example of a "future network" when it was envisioned over 30 years ago. External forces can also play a critical role in networking research (for example, the deployment of services that become popular overnight because current networks can support them). This phenomenon raises additional issues that can feed into either of the two broad directions. In this talk, I'll discuss a few historical examples and summarize the current trends and obstacles in networking research, addressing the need for both short- and long-term networking research directions.

Business Models for Sustainable Data Centers

drupal — Fri, 09 Feb 2007 09:47:18 -0600

How do you craft a sustainable business model that will encourage researchers to use the data center in a collaborative fashion while demonstrating to university administrators the investment was worth it? Presenters will share their experiences and initial recommendations from the Net@EDU Campus Cyberinfrastructure Working Group, as well as the consequences of not having a viable plan.

Key Needs and Requirements Driving Recent Data Center Implementations-Lessons Learned

drupal — Tue, 22 Aug 2006 10:16:41 -0500

Presented at the Campus Cyberinfrastucture (CCI) Workshop.Presentation provides a profile of how North Dakota State University set out to build a high performance computing (HPC) center, the pains the planners took to secure institutional leadership buy-in, setting up a HPC governance structure, related challenges and the lessons learned to date.