April 24, 2013
For HPC centers all over the world, supporting cutting-edge research by providing users with high-levels of compute power is job number one, but nowadays centers are also expected to be as energy-efficient as possible. Such is the case with Netherlands-based HPC center SURFsara. When the center needed to reduce its energy consumption and improve uptime, it turned to Dell Deployment Services and Dell Configuration Services.
SURFsara relies on both government and university funding to provide university groups with the computing power they need to perform ground-breaking research. In addition to this mandate, the center must ensure that government efficiency-efficiency guidelines are followed.
"We help them process large volumes of data, fast," says Jaap Dijkshoorn, Group Leader of Cluster Computing, SURFsara, The Netherlands. "[But we also] try to be as green as possible."
When SURFsara's existing cluster was reaching the end of its lifecycle, the center sought a replacement that emphasized performance-per-watt. After a European tender process, they found that Dell best met their needs based on performance, power consumption and price.
The new HPC cluster, called Lisa, consists of 624 Dell blade servers, Dell Force10 switches and Dell PowerVault direct attached storage array. It is providing researchers with a 50 percent increase in computing power – from 20 teraflops to 30 teraflops – and around-the clock-access to computing with 99 percent uptime.
The new system has also helped SURFsara meet the green IT targets set by the Dutch government. The country is aiming to reduce carbon emissions by 20 percent by 2020 and expects businesses to do their share in making this happen. Thanks to the energy-efficient Dell blades, the amount of electricity that goes into powering SURFsara has dropped by 40 percent, from 250 kilowatts to 150 kilowatts.
Observes Dijkshoorn: "Not only does that mean that as an organisation we're being as green as possible, but the fact that we're significantly reducing our electricity bills should also see us make savings that we can reinvest in developing cutting-edge technology services."
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?