- Who We Are
- What We Do
- Get Help Now
Introduction to the TeraGrid
What is the TeraGrid?
Started in 2001, the National Science Foundation's (NSF) TeraGrid has evolved into the “World’s largest infrastructure for open scientific discovery.”
TeraGrid is an open scientific discovery infrastructure combining leadership class resources at eleven partner sites to create an integrated, persistent computational resource. Using high-performance network connections, TeraGrid integrates high-performance computers, data resources and tools, and high-end experimental facilities around the country. Currently, TeraGrid resources include more than 2 petaflops of computing capability and more than 50 petabytes of online and archival data storage, with rapid access and retrieval over high-performance networks. Researchers can also access more than 100 discipline-specific databases. With this combination of resources, the TeraGrid is the world's largest, most comprehensive distributed cyberinfrastructure for open scientific research. (Teragrid website)
According to the NSF, Cyberinfrastructure (also called eScience) is a technological solution to the problem of efficiently connecting data, computers, and people with the goal of enabling derivation of novel scientific theories and knowledge. The term was used by the NSF Blue Ribbon committee in 2003 in response to the question: “How can the NSF… remove existing barriers to the rapid evolution of high performance computing, making it truly usable by all the nation's scientists, engineers, scholars, and citizens?” The answer - NSF decided it was cost-effective to create national institutes of supercomputing. Eventually these separate institutes were merged to produce the TeraGrid as a single administrative unit with a single procedure for allocating resources, signing-on, administrating resources, etc.
Some highlights of the TeraGrid include:
- High-performance networks
- High-performance computers (>1.5 PFlops)
- Visualization systems
- Data resources and tools (>30 PB, >100 discipline-specific databases)
- Science Gateways
- User portal
- User services - Help desk, training, advanced app support
- Allocated through national peer-review process
- It’s free!
The TeraGrid began in 2001 when NSF awarded $45 million to NCSA, SDSC, Argonne National Laboratory, and the Center for Advanced Computing Research (CACR) at California Institute of Technology, to establish a Distributed Terascale Facility (DTF). The DTF became known to users as the TeraGrid, a multi-year effort to build and deploy the world's largest, fastest, most comprehensive, distributed infrastructure for general scientific research. The initial TeraGrid specifications included computers capable of performing 11.6 teraflops, disk-storage systems with capacities of more than 450 terabytes of data, visualization systems, data collections, integrated via grid middleware and linked through a 40-gigabits-per-second optical network. In August 2005, NSF's newly created Office of Cyberinfrastructure extended support for the TeraGrid with a $150 million set of awards for operation, user support and enhancement of the TeraGrid facility over the next five years. Using high-performance network connections, the TeraGrid integrates high-performance computers, data resources and tools, and high-end experimental facilities around the country. The five-year award, originally scheduled to end in July, 2010, was extended until July 2011. As of July, 2010, TeraGrid integrated resources include more than 2 petaflops of computing capability and more than 50 petabytes (quadrillions of bytes) of online and archival data storage with rapid access and retrieval over high-performance networks. " In applying to the TeraGrid, you have more power available to you as a researcher than any other administrative unit for HPC in the world.” (Teragrid website)
- High Performance Computers –Over 3PFs available now and growing.
- High Performance Networks (40 GB/sec)
- The TeraGrid currently delivers an average of 420,000 cpu-hours per day
Who Uses the TeraGrid
Researchers, engineers, and other scholars with a need for free access to high performance computing.
How does the Teragrid benefit you as a researcher?
It's free computing! The Teragrid offers an alternative to buying and maintaining an expensive HPC cluster onsite. The people that benefit the most immediately are the people who are starting to use or already know how to use clusters. The Teragrid might be least accommodative to those who need on-demand computing or have specific, proprietary software needs.
A Science Gateway is a community-developed set of tools, applications, and data that is integrated via a portal or a suite of applications, usually in a graphical user interface, that is further customized to meet the needs of a targeted community. In a traditional computing model, each researcher obtains his or her own allocation on a computing resource, connecting from the command line of each supercomputer or storage resource and setting up individual codes and environments. Researchers have to do most of the work, bringing together the tools and finding the best resources to accomplish their research goals. Gateways, on the other hand, enable entire communities of users associated with a common scientific discipline to use national resources through a common interface that is already configured for optimal use. While talented gateway developers are required to enable this use, the benefits of their work can extend to many more end users, allowing researchers to focus on their research and fostering collaborations. (TeraGrid website)
Examples of TeraGrid Research
The TeraGrid has enabled research on a variety of topics including:
- Storm Prediction (Tornadoes, Hurricanes)
- Gravitational Waves
- Cosmology (Galaxy Formation and Evolution)
- Biology (3-d Virus Reconstruction)
How Does it Work?
Submitting a Proposal
Computing on the Teragrid is free but you still need to submit a proposal outlining your research for an initial allocation. From the time the proposal is submitted to the time you can log-on and use the Teragrid is usually about 6 months so the first step is to plan ahead. The proposal for an initial allocation of 200,000 core hours is short (2-3 paragraphs) and takes 2-3 weeks to approve. For more information on writing and submitting a proposal, see the Guide to the Proposal Process.
Getting Started with the TeraGrid
The best thing to do if you are interested in using the TeraGrid is to talk to your local TeraGrid “Campus Champion” For the UW, that's jeffpg [at] uw [dot] edu (Jeff Gardner.)
Campus Champions can:
- Direct you to the most appropriate TeraGrid platforms
- Give you an experimental TeraGrid account
- Help you write proposals to acquire TeraGrid time
The Future of the TeraGrid - eXtreme Digital (XD)
The TeraGrid is still evolving. In April 2011, the National Science Foundation Office of Cyberinfrastructure (NSF-OCI) will embark on the next step in providing the scientific community with significantly enhanced high-performance computing resources and data services. The first impact to users will be a phased transition to a suite of resources and services that exceed the current aggregate computational power on TeraGrid.
Researchers looking for access to HPC for computation and storage can gain free access through the Teragrid with a straigtforward proposal outlining their research and allocation needs. Check out the TeraGrid website which includes courses and online tutorials for potential new users.
help [at] TeraGrid [dot] org
Also in... Get Help Now
Frequently Asked Questions.
Learn about particular technology options and how they can support your research goals.
Find step-by-step instructions on how to perform specific technology tasks.
Read stories of innovation about researchers who are using the techniques and technologies of eScience in creative and effective ways.
Latest eScience News
Community Data Science Workshops (Spring 2015) 6 days 20 hours ago
AWS Scientific Computing FAQ on AWS HIPAA Compliance 2 weeks 4 days ago
MathAcrossCampus Lecture: Computational Thinking 5 weeks 1 hour ago
Classification, Inference and Modeling of Dynamic Networks from Data 5 weeks 1 hour ago
Please help us support your research by including the following acknowledgment in publications to which we have contributed:
Supported in part by the University of Washington eScience Institute.