HPC Initiative Opens September 16th at Arizona State University
HPC Initiative Opens September 16th at Arizona State University
New super computer at Arizona State will have enormous potential for researchers
New super computer at Arizona State will have enormous potential for researchers
As gasoline prices soar, alternative fuel research grows in popularity
As gasoline prices soar, alternative fuel research grows in popularity
July 12, 2005: HPCI Main Lab Nears completion
HPCI Facility Construction
The primary machine room for the HPCI will be in room 167 of the
Goldwater Center. This facility will provide a state of the art home
for the most sophisticated computing clusters on the ASU campus. The
facility will employ some of the most advanced cooling technology on
the market to support systems at densities far beyond the capability of
normal computer rooms. This facility will feature an uninterruptible
power supply with more than 750,000 watts of capacity, 6" chilled water
lines, under floor and in-rack cooling systems, raised floors, and
ceiling mount cable trays. Building this facility required major
renovations to the power and cooling distribution systems throughout
the Goldwater center, in addition to rebuilding the three existing
rooms combined into room 167. Major construction began May 19th, 2005,
after months of planning, bids, design, and procurement. Follow some of
the progress in the snapshots below.
Mike the foreman looks over the early chaos:
High-Performance Computing with FPGAS: Towards an Open Source FPGA Accelerator for BLAST
Assistant Research Professor
ITTC
University of Kansas
From manufacturing to entertainment to computational science,innovations in High-Performance Computing (HPC) are providing our Nation with a competitive advantage in the worldwide marketplace. One recent trend is the introduction of Field-Programmable Gate Arrays (FPGAs) into high-performance systems, as evidenced by recent offerings from several ``big iron'' supercomputing companies. Machines, such as Cray's XD-1, allow users to implement part of their application as customized hardware realized in the machine's reconfigurable FPGAs.
ASU’s Decision Theater ushers in new age of public policy
 |
|
The Decision Theater at ASU gives a three-dimensional view of real-life public policy issues. The science-based computer models allow policy makers to test the outcomes of decisions made on such topics as urban growth and water usage, public health and a myriad of environmental and social challenges. The Future of Parallel File Systems in Computational ScienceDate: 04/08/2005 - 3:00pm
As parallel machines for computational science have grown in number of nodes and applications have grown in complexity, the I/O system software used to provide services have likewise grown from simple file systems to layered I/O stacks relying on multiple software components. The parallel file system resides at the bottom of this stack, organizing many hardware devices into a single logical space and providing an interface to this space. Gaining Knowledge from Large Datasets using Parallel and Distributed ComputingDate: 03/25/2005 - 2:00pm
Dan Katz, Supervisor
Parallel Applications Technologies Group Jet Propulsion Lab
Brickyard Room 628 JPL's Parallel Applications Technologies Group has been exploring the issues of data access and visualization of very large datasets over the past 10 or so years. This work has used a number of types of parallel and distributed computers. This talk will highlight some of the applications and tools we have developed, including how they use computing resources. Our applications focus on NASA's needs; thus our datasets are usually related to Earth and Space Science, including data delivered from instruments in space, and data produced by telescopes on the ground. Collins Joins High Performance Computing InitiativeDate: 03/12/2005 - 12:00pm
March 2005: Charles Collins has joined the High Performance Computing Initiative as a system administrator, with special emphasis on the cluster and visualization systems available in Decision Theater. Charles brings over 20 years of IT experience to the HPCI, including previous system administration, as well as consulting, teaching and CS curriculum design experience. Charles previously managed the high performance computing lab at UT-San Antonio. Parallel Programming on Linux Beowulf ClustersDate: 01/13/2005 - 9:00am - 01/14/2005 - 5:00pm (Due to popular demand, this will be repeated Jan. 17th and 18th) The Fulton High Performance Computing Initiative would like to announce the first in a series of short courses to provide hands-on training in the use of Beowulf cluster parallel computers in an intensive 2 day format. This course is open to all students, staff, postdocs and faculty in the Fulton School on a first-come, first-serve basis, and will be repeated periodically as needed. The format of the course is 4 ~90 minute lectures (as described below) interspersed with 4 brief hands-on lab sessions; each of the 4 sections can be taken independently, for those with time constraints. The lecture/lab sessions will run 9-12 and 1:30-4:30 each day. Examples will be presented in both FORTRAN and C. If you plan to attend, please contact Dan Stanzione at dstanzi@asu.edu 
|