This page contains a Flash digital edition of a book.
News Networks v2 11/12/08 12:31 Page 16
Supercomputer successes
Sandia National Laboratories, a US network. The NetIron MLX-32 offers us
science-based systems engineering incredible performance, the ability to
laboratory, has selected multiple bond up to 32 ports of 10GbE for
Foundry NetIron MLX-32 MPLS routers maximum interconnect density, an
for their industry-leading 10 gigabit exceptional feature set, as well as
Ethernet (10GbE) density, performance excellent total cost of ownership. The
and computing power while NetIron MLX-32 provides us major
significantly reducing its costly energy savings in regards to lower power
consumption overhead. Sandia consumption, cooling requirements,
installed the NetIron MLX-32 to expand maintenance, and space efficiency.”
and extend the capabilities of its
supercomputer, Red Storm. By Meanwhile, Force10 Networks’
installing the world’s most dense and TeraScale E-Series family of
efficient routers within Red Storm’s switch/routers is powering the world’s distributing the incredible amount of
high-performance input/output system, first petaflop supercomputer and compute power harnessed by this
Sandia is able to maximize research world’s fastest cluster supercomputer machine that will further the country’s
and development cycles through its as listed by Top500.org. national security initiatives and aid in
geographically distributed external new scientific discoveries.”
Sandia and tri-lab networks and data The “Roadrunner” supercomputer at
centre. Los Alamos National Laboratory ‘Unmatched’ line-rate density and
(LANL) in New Mexico also ranks as scalability on the E-Series
Currently ranked in the top 12 on the the third “greenest” worldwide, based switch/routers enables the devices to
global TOP500 list of the world’s fastest on its efficient footprint, cooling, and provide network services for
supercomputers, Red Storm is a power usage. With the ability to move Roadrunner’s 1.5 Petabyte cluster that
massive parallel processing up to 1 billion packets over each of its includes more than 10,000 CPUs. To
supercomputer at Sandia and one of 1.6875 Tbps non-blocking switch accommodate the computing cluster’s
the Advanced Simulation & Computing fabrics, the 15 Force10 E1200 rapidly growing mix of smaller
supercomputers dominating world switch/routers played a pivotal role in transactions and enormous files, the
computing records. With the sheer the IBM-based system reaching 1.026 E1200 scales up to 1,260 Gigabit
amount of data that Red Storm is able petaflop per second, becoming the first Ethernet (GbE) and 224 10 GbE ports
to process, it was imperative that supercomputer ever to reach this per chassis with access control lists
Sandia selected the highest performing milestone. (ACLs) on all ports. LANL is leveraging
networking router available. The the computing power and the mission-
NetIron MLX-32, which is capable of “The Force10 E-Series switch/routers critical data for researching a broad
forwarding up to 7.68 terabits per have efficiently and reliably provided range of initiatives ranging from
second per chassis, exceeded the extremely high performance and alternate energy sources to weapons
requirements to manage, switch and reliability needed to support the systems.
route the traffic to and from the thousands of I/O operations of storage
supercomputers. in our clustered environment,” said Dr. “The Force10 solution allows us to do
Andy White, Deputy Associate storage at high bandwidth rates
“Foundry routers have been the Laboratory Director for Theory, without network down time or data
integral high-performance routing Simulation and Computation, Los corruption,” says Dr. White. “The
platform of our Red Storm Alamos National Laboratory. cluster depends on storage and we
supercomputing network from the very “Architecting and deploying a new scale depend on Force10 for maximum up
start,” said John Naegle, senior of supercomputer is a tremendous time and high throughput to our global
engineer for Sandia. “We require the accomplishment and one of the parallel files system. With a cluster as
highest performance, density, pleasant surprises was the system’s large as Roadrunner, it’s essential to
reliability and efficiency from the stability as it scaled up in size. Force10 supply it with data and be able to do
switches and routers in our demanding architecture plays a pivotal role in large checkpoints.”
16 | DATA CENTRE SOLUTIONS | www.datacentresols.com Winter 2008
Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71  |  Page 72  |  Page 73  |  Page 74  |  Page 75  |  Page 76
Produced with Yudu - www.yudu.com