AUSTIN, Texas — The National Science Foundation (NSF) today announced "Jetstream," a new self-service cloud to increase participation in advanced computing for researchers who need flexible, reproducible, powerful and easy-to-use computing.

"Jetstream will serve as a cloud computing facility for scientists and engineers across the whole portfolio of disciplines supported by the National Science Foundation," said Craig Stewart, Indiana University Pervasive Technology Institute executive director and associate dean for research technologies at Indiana University. "It will allow researchers to create a customized virtual machine environment or select from an existing one, while also ensuring the reproducibility of the results supercomputers produce."

Jetstream will be part of the eXtreme Digital (XD) program, currently the most advanced, comprehensive, and robust collection of integrated digital resources and services enabling open science research in the world. Jetstream will empower thousands of currently underserved users whose software and workflows do not conform to the existing resources available — researchers in communities such as biology, atmospheric sciences, geosciences, social sciences, and the humanities.

Matthew Vaughn, Director of Life Sciences Computing at TACC and responsible for Jetstream's software environment

"Bridges and Jetstream will expand the capabilities of the NSF-supported computational infrastructure, pushing the frontiers of science forward in biology, the social sciences and other emerging computational fields by exploiting interactive and cloud-based computing paradigms," said Irene Qualters, division director for advanced cyberinfrastructure at NSF.

These two systems offer a mix of new capabilities and usage modalities, from large memory nodes enabling big data efforts, to virtual machines running in the cloud, which will let a broader swath of researchers use advancing computing. These technologies are expected to make new kinds of scientific inquiry possible.

Researchers will be able to create virtual machines (VMs) on Jetstream as a remote resource, setting up individual environments that look and feel like their lab workstation or home machine, but able to harness thousands of times the computing power.

"Virtualization has emerged as a solution to many of today's problems in scientific computing, one of which is how to share complex software setups," said Matthew Vaughn, director of Life Sciences Computing at TACC and responsible for Jetstream's software environment. "Jetstream will allow a researcher to work in an analysis environment shared with his or her colleagues. It's a way of creating a collaborative computing laboratory."

Jetstream will feature a rich catalog of project- and user-contributed VM "appliances" configured to support varied uses such as 3D image reconstruction, natural language processing, basic software development, and biostatistics. Furthermore, VM images will be sharable outside of Jetstream and can be associated with citable Digital Object Identifiers (DOIs). Thus, all the computational requirements to do an analysis – data, software code, and scripts – can be packaged up in and published to a digital library.

"Your research isn't locked away on a single computer," Vaughn said.

Snapshot of Jetstream user interface

"The Atmosphere team has done a fantastic job on user experience," Vaughn said. "One literally can log on, click an appropriate VM image, and have a fully functional environment ready in a couple of minutes. People love Atmosphere and use it in ways we didn't expect. We're constantly shocked by the inventiveness of how end users and developers alike take advantage of an accessible user-provisioned cloud. So, we decided to bring Atmosphere to other research communities."

With the Jetstream project, our goal is to expand and diversify the NSF XSEDE user base, add much needed capacity to users with intermediate computing needs, and provide a reliable, easy-to-use, self-provisioned platform with low total cost of ownership, according to Vaughn.

"We expect Jetstream to be of particular interest to researchers analyzing ‘born digital' data with research needs that are more suited to cloud computing than the traditional supercomputers that have been the mainstay of NSF-funded cyberinfrastructure in the past," Stewart said.

Jetstream compliments the existing hardware, software, networking and community development that together constitute the nation's cyberinfrastructure ecosystem. Since 2009, NSF has invested nearly $1 billion in cyberinfrastructure in support of the nation's researchers.

"As high performance computing has evolved over the years, its importance to science and engineering has only grown," Qualters said. "Bridges and Jetstream will help researchers today, but also point to the future of computational science. With these systems, we continue to push the boundaries of computing so that researchers in all fields can solve critical, and previously intractable, problems."

The Jetstream partners are Indiana University's Pervasive Technology Institute (IU); the Texas Advanced Computing Center (TACC) at The University of Texas at Austin; the University of Chicago; the University of Arizona; University of Texas at San Antonio; Johns Hopkins University; Pennsylvania State University; Cornell University; University of Arkansas at Pine Bluff; University of Hawaii; the National Snow and Ice Data Center; the Odum Institute at the University of North Carolina; the University of Hawaii; and the National Center for Genome Analysis Support.

For more information about Jetstream, please visit: http://youtu.be/6Jf1AJqnuJA.

For more information, please see the NSF version of the press release, click here.