SALT LAKE CITY, Feb. 13 /PRNewswire/ -- Linux Networx, the Linux
Supercomputing Company, announced today that the Department of Defense (DoD)
High Performance Computing Modernization Program (HPCMP), has placed the
largest single order for Linux Supercomputers in the company's history. The
DoD purchased five supercomputers from Linux Networx including three Advanced
Technology Clusters (ATC's) and one LS-1 for the Army Research Laboratory
(ARL) Major Shared Resource Center (MSRC), and an additional LS-1 for Dugway
Proving Ground. The procurement increases ARL MSRC's computing capability to
over 80 trillion floating-point operations (TFLOPS), making it one of the
largest computing centers in the DoD. In addition, the procurement enhances
ARL MSRC's visualization capabilities. Linux Networx was selected due to its
recognized expertise in designing, building and delivering next generation
Linux supercomputers that leverage the price/performance value of open
software and hardware platforms.
The Linux Supercomputers are part of the Technology Insertion 2006 (TI-06)
program, an initiative to modernize the Department of Defense high performance
computing (HPC) capabilities. The HPCMP provides the supercomputer services,
high-speed network communications, and computational science expertise that
enable the U.S. Defense laboratories, such as ARL, to conduct a wide range of
focused research, development, and test activities. Linux Networx is a key
partner in the drive to put advanced technology in the hands of U.S. armed
forces more quickly, less expensively, and with greater certainty of success.
"We are honored to partner with the DoD on this key technology project,"
said Robert (Bo) H. Ewald, CEO of Linux Networx. "This procurement features
our Linux Supercomputers powering a broad set of applications to solve a
number of complex challenges -- leveraging a variety of visualization
capabilities within the DoD and within the defense community special programs.
This wide ranging application of Linux Networx supercomputing technology
confirms our position as the leading Linux supercomputing company in the
"We've observed tremendous scalability for some of our applications on our
current commodity clusters," said Charles J. Nietubicz, director of the ARL
MSRC and director of the High Performance Computing Division in the
Computational and Information Sciences Directorate (CISD). "The TI-06
increase in computing capability will give DoD scientists and engineers the
additional ability to solve more complex, three-dimensional, time-dependent,
physics-based problems in a timeframe that can provide the data necessary to
assist with weapon development and procurement decisions."
ATCs are especially well suited for organizations that wish to pioneer new
technologies, new programming models or new levels of supercomputing scale.
Linux Networx works with customers and technology partners to identify and
integrate emerging and proven technologies into a production-ready system.
The three Linux Networx ATC's will be installed at the ARL MSRC this
summer. The most powerful of the new systems is expected to be ranked in the
top twenty of the world's most powerful computer systems. It is a
1122-compute node supercomputer with 4488 mid-voltage 3.2 GHz Intel Dempsey
cores for computation. This system will increase the ARL MSRC's computational
capability by more than 28.7 TFLOPs. The system will also have 112 3.46 GHz
cores (28 nodes) for login, storage, and administration with 9.4 TB of memory
and 260 TB (raw) of disk. All nodes will communicate via a 4X DDR (20 Gbps)
Infiniband network with 10 GigE uplink capability. The 3.2 GHz mid voltage
chips were selected for the compute nodes due to their thermal efficiency.
A second system is also expected to be ranked in the top twenty of world's
most powerful computer systems. An 842-compute node Advanced Technology
Cluster, it will be comprised of 3368 mid voltage 3.2 GHz Intel Dempsey cores
for computation. The system will increase the ARL MSRC's computational
capability by more than 21.5 TFLOPS. The system will also have 96 3.46 GHz
cores (24 nodes) for login, storage, and administration and will have 7.1 TB
of memory and 196 TB (raw) of disk. All nodes will communicate via a 4X DDR
Infiniband network with 10 GigE uplink capability.
Tom Kendall, Chief Engineer of the ARL MSRC, said: "The combination of
dual core processors with dual memory busses, DDR 4X Infiniband and fully
buffered memory into a power optimized system will provide DoD researchers
with an unprecedented level of high performance computing capability and
The third system is a 68 core test and development system with 7 TB of
disks to be delivered in advance of the other two systems. The Linux Networx
and ARL MSRC teams will work closely utilizing this machine to integrate the
DoD software environment.
"Interconnects and file systems are critical to what we do, the
availability of a smaller advanced development system will ensure our users a
positive first experience when they get onto the larger production machines,"
said Tom Kendall.
LS-1 Supersystems blend application-optimized performance with a
standardized systems experience to deliver ultimate supercomputing value,
thereby delivering significantly reduced total cost of operations (TCO). LS-1
Supersystems arrive ready for production-at-power-up, pre-tuned and optimized
to match the specific needs of the customer application environment --
dramatically reducing initial operations cost while accelerating time to
productivity. As a result, customers can immediately focus on delivering
computational solutions to their computational research and design challenges
-- not on supercomputing cluster setup and operations.
The first LS-1 system will also be deployed at the ARL MSRC this summer.
A 64 node scientific visualization supercomputing cluster, the LS features
dual Nvidia Quadro FX 4500 cards per node and an Infiniband network. This
will be the first scientific visualization supercomputer in the HPCMP.
The visualization supercomputing cluster will allow for interactive
visualization of enormous datasets. By performing both the visualization
algorithms and rendering in parallel, a scalable solution for analyzing
calculations consisting of billions of computational cells will be achieved.
"The complexity and fidelity of current production DoD calculations
consume terabytes of memory and tens of CPU years for a single simulation,"
said Jerry Clarke, Scientific Visualization Team Leader. "When you're dealing
with that much data, every aspect of visualization must be parallel. This
system will allow for the interactive analysis of important calculations
currently impossible on available resources."
Details of the LS-1 system for the Dugway Proving Ground will be released
later this year.
About Linux Networx
Linux Networx, The Linux Supercomputing Company, delivers Linux
Supersystems that combine the price/performance advantage of Linux clusters
with real-world supercomputing expertise and technology innovation. The
company has delivered over 450 supercomputing clusters to more than
165 supercomputing customers around the world. In 2005 the company achieved
record orders, finishing the year with three consecutive quarters of record
growth. The company's customer list represents a "who's who" of
supercomputing users, including Los Alamos National Laboratories, Sandia
National Laboratories, Boeing, BMW, Daimler Chrysler, Audi, Caterpillar, John
Deere, Total, Schlumberger and Shell Oil in the Oil and Gas industry. For
more information about Linux Networx, visit www.linuxnetworx.com.
About the Army Research Laboratory Major Shared Resource Center (ARL
The ARL MSRC is one of four DoD Major Shared Source Centers serving the
Defense community. Created in 1996 under the High Performance Computing
Modernization Program, the ARL MSRC is one of the world's most powerful
computing sites. The ARL MSRC delivers the latest in computational tools and
innovative technologies. The Center's full spectrum of computational
capabilities help DoD scientists and engineers develop, test, and field weapon
systems faster and more efficiently -- shortening the entire acquisition
process from research to production. For more information about the ARL MSRC,
SOURCE Linux Networx