September 28, 2011
The Australian academic supercomputing consortium iVEC has bought another mid-sized supercomputer to help support its mission to provide HPC access to universities and industry. The 40 teraflop machine is from SGI, and, as has been recent tradition with other Aussie supers, employs GPUs for extra computational horsepower.
According to Computerworld Australia, the system will be housed the University of Western Australia (UWA) to "further the country’s ability to conduct data-intensive research." While that's a pretty broad mandate, iVEC narrows the field a bit by citing its main application areas: nanotechnology, radioastronomy, high energy physics, medical and mining training, medical research, mining and petroleum, architecture and construction, multimedia, and urban planning.
The machine itself, known as Fornax, and more formerly as iVEC@UWA, is a 96-node InfiniBand cluster, with each node equipped with two six-core Intel Xeon X5650 chips and an NVIDIA C2050 GPU. Each node also comes with with 48 GB of RAM and a hefty 7 terabytes of attached disk. The 7 TB of local storage is a feature that will allow a lot of data to be loaded onto each node, relieving the network of extra data shuffling. There is also a separate 500 TB of "fabric attached storage" available to the cluster.
The new iVEC@UWA system complements iVEC@Murdoch, a 100-teraflop machine (officially 87.2 according to the iVEC site.) That system was purchased earlier this year, and is housed, as implied by its name, at Murdoch University. The Murdoch super is one of HP's POD containerized systems and is being used for applications in radio astronomy, geoscience, nanotechnology and life science.
Other iVEC systems include a 128-CPU SGI Altix XE 1300, installed in 2008 and also located at Murdoch, and a 192-CPU SGI Altix 3700 Bx2 installed at the Australian Resources Research Center. Although these supercomputers, as well as iVEC@UWA, are relatively small machines as supercomputers go, the Aussies have some larger systems in mind.
In May, the Commonwealth Scientific and Industrial Research Organisation (CSIRO), part of the iVEC consortium, announced it is planning to begin the procurement phase of its multi-stage petascale and real-time supercomputing Pawsey Centre project. The Centre was established to host supercomputing facilities and expertise in support of the international Square Kilometre Array (SKA) project and other cutting-edge science applications.
Full story at Computerworld Australia
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?