XSEDE, PRACE call for requests of joint support
XSEDE and PRACE, major research infrastructures, providing peer-reviewed access to high-end HPC resources and services in the United States and Europe, respectively, are now exploring options to extend collaborative efforts to other activities that effectively support research teams spanning the US and Europe. One of these options is the provisioning of interoperable services; this is a call to invite research teams that are using both infrastructures--or will be interested in doing so in the future--to express their requirements for such interoperable services.
The two research infrastructures will support research teams for setting up the required interoperability if a clear benefit is to be expected from the new facilities. Resource allocations are not part of this call, however allocations for testing purposes will be possible.
This call for requesting support complements the call of last year which was targeted at Expressions of Interest for potential joint allocation of resources. From that call it became clear that there is great interest in the enabling of the interoperable facilities of the two infrastructures. This call will give all interested research teams the opportunity to express their interest in the enhancement of interoperability and indicate interest in collaborative support opportunities with both XSEDE and PRACE.
The XSEDE Senior Management Team and the PRACE Board of Directors invite requests for support for such joint activities by XSEDE and PRACE. The request should target the enhancement of the interoperability between XSEDE and PRACE. The selected proposals will receive support both from XSEDE and PRACE-3IP project in order to improve the interoperability. For testing the implemented solutions on the XSEDE and PRACE systems time can be requested.
Requests for Support should be submitted to prace-xsede@prace-ri.eu or prace-xsede@xsede.org before January 31, 2014. They should be no longer than two pages and should address the following points.
- Identify the collaborating teams in the US and Europe.
- The technical challenges facing the collaborating teams as justification for suggested activity.
- A list of involved XSEDE/PRACE centers including the confirmation of the feasibility and acceptance of the proposed work
- The justification for access to resources in both the US and Europe, where applicable.
- What effort the collaborating teams can provide to participate in the collaborative support activity and an estimation of expected support.
- Mechanisms for monitoring progress and reviewing outcomes.
Up to three applications may be selected for a supporting period of up to six months starting on April 1, 2014. Each successful application will be supported with up to three person month's effort provided by XSEDE and/or PRACE personnel.
XSEDE and PRACE will assess the proposals based on the following criteria
- Potential impact of proposed interoperable service
- Technical feasibility
- Commitment of the proposing groups to contribute to the effort
- Required effort by XSEDE and PRACE teams
Based on this assessment and available resources, XSEDE and PRACE will select applications for support. Applicants will be informed by March 15, 2014 about the result of the assessment, including reasons for selection or rejection.
About XSEDE
The Extreme Science and Engineering Discovery Environment (XSEDE) is the most advanced, powerful, and robust collection of integrated advanced digital resources and services in the world. It is a single virtual system that scientists can use to interactively share computing resources, data, and expertise. XSEDE accelerates scientific discovery by enhancing the productivity of researchers, engineers, and scholars by deepending and extending the use of XSEDE's ecosystem of advanced digital services and by advancing and sustaining the XSEDE advanced digital infrastructure. XSEDE is a five-year, $121-million project and is supported by the National Science Foundation.
About PRACE
The Partnership for Advanced Computing in Europe (PRACE) is an international non-profit association with its seat in Brussels. The PRACE Research Infrastructure provides a persistent world-class high performance computing service for scientists and researchers from academia and industry in Europe. The computer systems and their operations accessible through PRACE are provided by 4 PRACE members (BSC representing Spain, CINECA representing Italy, GCS representing Germany and GENCI representing France). The Implementation Phase of PRACE receives funding from the EU's Seventh Framework Programme (FP7/2007-2013) under grant agreements RI-261557, RI-283493 and RI-312763. For more information, see www.prace-ri.eu
Ranger supercomputer's lifespan extended one year as part of NSF XD initiative
AUSTIN, Texas, Nov. 8, 2011 — The Texas Advanced Computing Center (TACC) today announced that operational funding for the Ranger supercomputer, which was expected to end on Feb. 4, 2012, will be extended through Feb. 4, 2013. This extension will allow Ranger to continue supporting world-class science until the next large HPC system, Stampede, is deployed as part of the National Science Foundation's (NSF) eXtreme Digital (XD) program.
Approaching its fourth anniversary, Ranger remains one of the top computing platforms in the world, ranked as No. 17 on the Top500 list (www.top500.org). The system has completed more than two million jobs with 97 percent uptime.
"Ranger was the most widely used large-scale HPC system in the TeraGrid program, and we look forward to enabling more scientific breakthroughs through early 2013 as part of the XSEDE program," said Jay Boisseau, director of TACC. "The extension will enable users to transition smoothly to using Stampede when it comes online in January 2013, and thus provide continuous productivity and progress for a large subset of the U.S. open science research community."
Ranger went into production on Feb. 4, 2008, as the most powerful and capable HPC system in the TeraGrid—with more than five times the peak performance and ten times the memory of any other TeraGrid system at that time. Ranger offered more than twice the cycles of all other TeraGrid systems combined at that time.
As a critical part of the XD program, the Extreme Science and Engineering Discovery Environment (XSEDE) consortium—comprising more than a dozen universities and two research laboratories—has now replaced the TeraGrid as the integrating fabric for the bulk of the NSF's high-end digital resources. Researchers from any U.S. open science institution can apply for a variety of novel scientific and educational activities through the XSEDE project.
"TACC is pleased to continue offering Ranger through the XSEDE program to the users and research projects currently benefitting from this powerful resource," said Chris Hempel, associate director of Resources and Services at TACC. "To date, Ranger has been used by more than 3,000 scientists in the investigation of more than 1,800 research projects."
For more than three and a half years, Ranger and its Spur visualization sub-system have supported emergency simulations of the Gulf oil spill, assisting the Coast Guard in locating and containing surface oil; helped produce the first models of the H1N1 virus, which let scientists understand the virus's potential resistance to antiviral medication; and enabled the clearest picture yet of how mantle convection operates on a global scale and how it causes earthquakes.
In addition, Ranger helped predict the storm surge from Hurricane Ike, enabled insights into biofuels and solar photovoltaic cells, and assisted in the creation of seismic hazard analysis maps used by the U.S. Geological Survey to create building codes.
While supporting new science continues as the primary focus of the Ranger project, the project team will continue contributing to the improvement of key open source technologies that are used in many other HPC systems, such as:
· MVAPICH MPI libraries
· OpenFabrics Enterprise Distribution InfiniBand software stack (OFED)
· Lustre parallel file system
The Ranger project team will continue to support the national open science community as part of the XSEDE project through Feb. 4, 2013. The project team will help users migrate to Stampede and other new systems, finally shutting Ranger down after five complete years of operations. At that point, most Ranger project staff will shift to working on Stampede and other XSEDE-related activities, continuing to bring the expertise and experiences developed from this project to the national open science community for years to come.