Issue link: http://osercommunicationsgroup.uberflip.com/i/265924
S u p e r C o m p u te r S h o w D a i l y W e d n e s d a y, N o ve m b e r 2 0 , 2 0 1 3 1 2 and SCinet are also providing terabit- scale layer two switching within the local area conference network. Momentum is quickly building towards 400G and beyond, and SCinet is demonstrating that the technology is Ciena ( Cont'd. from p. 4) (nearly) ready for primetime. The team at CERN can expect the next 75 petabytes to move much quicker than the previous 75. During SC13, visit Ciena at booth 1924. For more information, go to www.ciena.com, call 800-207-3714 or +44 20 7012 5555 or email pr@ciena.com. ister. The canister slides into the enclo- sure and plugs into the backplane at the rear of the enclosure. An internal system monitor provides system operation data, including fan operation, voltages and temperature at several points in the enclosure. A remote interface is provided through the Ethernet port on the rear of the enclosure. An optional IPMI module is available for operators who wish to collect system data through the IPMI bus. One Stop Systems pioneered stan- dards-based PCIe expansion products starting in 2005. OSS continues its pio- neering tradition by producing high per- formance computing appliances target- ing advanced technologies in any mar- ket with high-performance, high-densi- ty requirements. OSS provides flexible One Stop Systems ( Cont'd. from p. 4) platforms for high-density next genera- tion storage, GP-accelerated computing and professional audio and video appli- cations. OSS also customizes its prod- ucts to make them fit its customers' pre- cise requirements. Custom and semi- custom products have long been OSS' core capability. OSS has a proven record of producing the highest quality products through superior engineering, ISO9001-2008 quality-driven produc- tion, and responsive pre- and post-sales support. For more information, contact the sales department toll free at 877- 438-2724 and visit online at www.onestopsystems.com. During SC13, visit One Stop Systems at booth 1137. For more information, visit www.onestopsystems.com, call 760-745-9883 or e-mail rru- ple@onestopsystems.com. ASROCK RACK PROVIDES INNOVATIVE SERVER BAREBONE DESIGN At CeBIT 2013, ASRock Rack intro- duced the first Server Barebone 2U12L6S-2T2OS6/D16. In the front, it supports up to 12 x 3.5 inch SAS 6G/SATA 6G drives in a tailor-made chassis, featuring dual sided hybrid stor- age to also connect 4 x 2.5 inch SAS6G/SATA6G +2X SATA 6G drives for the SSD and OS acceleration in the rear. With the 12 LFF (12 x 3.5 inch HDDs) for data storage and the 6 SFF (6 x 2.5 inch SSDs) for the operating system and cache, it can dramatically accelerate the speed of the storage. Another pro is the non-shading design with the dual Xeon 2600 series proces- sors and 16 DIMMs. There is absolute- ly no trade off between heat dissipation and computing power. "Expecting merely high storage capacity on a server system is just so out of date. We want our users to own more than enough capacity, stability and responsiveness all at the same time," said LL Shiu, Chief Executive Officer of ASRock Rack Inc. Taking a deeper look into the bare- bone system, the server board ASRock EP2C602-2T2OS6/D16 placed inside the system benefits from dual Intel E5-2690 CPUs situated conveniently near the fans for maximum heat dissi- pation. Both Intel 82599ES and X540 10G LAN solutions are applied for blistering fast internet connections and quicker inter-rack nodes commu- nications. As for the memory, there are a total of 16 quad channel DDR3 slots that ultimately promise over- whelming performance especially for virtualization. With LSI SAS 2308 IO controller on the server motherboard and LSI SAS 2x20 expander IC on the HDD's backplane, it guarantees the industry's maximum performance and bandwidth. Another interesting server barebone ASRock Rack presents is a cold storage. With the growing Big Data demand, more and more data are stored on the server side instead of personal storage. However, 80 percent of the data is not often accessed but still need to retain at lowest cost. This triggered the demand for cold storage server. Taking benefit of Intel's latest Avoton SoC, ASRock Rack offered a 1U 12x 3.5 inch HDDs system to the market. The motherboard in this system is an innovative embedded Mini-ITX board, 8core Avoton Intel SoC designed for cold storage data center solutions. "ASRock Rack is among the leading manufacturers of motherboards to have this platform design," said Wei-Shi Sa, President of ASRock Rack. "The server and workstation services of the manufac- turer with the designation ASRock Rack demonstrated with the current Mini-ITX board the right feel for current trends in the data center environment." The compact board in Mini-ITX for- mat offers exceptional facilities for power-efficient modern storage require- ments in green data centers. The new Intel Server SoC Avoton C2750 offers amazing performance with low heat out- put and low power consumption. Despite the compact design, ASRock Rack has also managed to make four memory sockets for a maximum memory size up to 64GB. The number of SATA ports is also outstanding compared to the market. Two on-board controllers allow the direct connection of up to 12 hard drives. The ASRock Rack Mini-ITX board is ideal for cold storage as well as data center solutions with high-performance NAS and storage server solutions with low power consumption in spite of high per- formance. During SC13, visit ASRock at booth 4322. For more information, visit www.asrock.com, call +886-2-55599600 or email ASRockRack_sales@ asrockrack.com. LOOKING TO THE FUTURE OF COMPUTING IN A BIG DATA ENVIRONMENT By Jill King, Vice President, Adaptive Computing As industries across the spectrum stand at the intersection of the collision of cloud computing, high-performance computing and Big Data, organizations need to do larger compute jobs, faster, with better results – all while staying within budget. Take an oil and gas company simu- lating subterranean modeling to aid their oil exploration efforts, a hospital con- ducting research for childhood ailments such as cancer or autism, a satellite imag- ing company assisting first responders to keep people out of harm's way, a weath- er organization chartered with warning us of dangerous environmental conditions or an aircraft manufacturer putting its lat- est design through a flight simulation. All of them need to perform these jobs in minutes or hours, not days, weeks or even months like the current logjam in the datacenter. However, these data sets demand intensive processes and analytics before one can achieve that "eureka" moment, which historically has been a very manual, time-consuming process. As this collision intensifies, compa- nies must tackle Big Data with a whole datacenter approach rather than siloed, specialized environments that may overutilize one area of your datacenter while others remain underutilized. Using all available resources within the data- center, including virtual machines, bare metal, hybrid cloud, Big Data and HPC environments, allows IT to streamline the simulation and analysis process, creating a solid foundation to leverage Big Data for game-changing results. A strategy that does not incorporate these technologies is similar to building a skyscraper without doing a soil study first; you might make some initial progress, but sooner or later you'll discover that you need to understand and thoroughly adapt to an inadequate foundation. To perform simulations and analyze the accompanying Big Data, it is key to manage and optimize all available data- center resources and operate them as one, turning the logjam into an orderly work- flow that greatly increases throughput and productivity. This enables companies to solve Big Data challenges faster, more accurately and most cost-effectively, allowing them to go to market with new products rapidly and remain competitive in the marketplace. At Adaptive Computing, we have deployed our solutions on some of the most complex cloud and HPC environ- ments in the world, with some of the most interesting and large Big Data assets. We are constantly pursuing the invaluable insights the enterprise needs to make game-changing decisions and the world a better place. The industry is entering a new age where Big Data will transform cloud, datacenters and supercomputing into a hub for creative uses. Not all compelling tech problems live at this nexus, but an amazing number do – and the collision will only continue to intensify. During SC13, visit Adaptive Computing at booth 3113. For more information, visit www.adaptivecomputing.com, call 801-717-3700 or email solutions@ adaptivecomputing.com. MARC SNIR TO RECEIVE SEYMOUR CRAY AWARD AT SC13 Dr. Marc Snir, a parallel computing pioneer whose innovative work has advanced the elite supercomputing systems that drive scientific discovery, will receive this year's IEEE Computer Society Seymour Cray Computer Engineering Award at SC13. Director of the Mathematics and Computer Science Division at Argonne National Laboratory, Snir is also the Michael Faiman and Saburo Muroga Professor in the Department of Computer Science at the University of Illinois, Urbana-Champaign (UIUC), a department he led from 2001-2007. Since 2007, he has also served as the lead software architect for the Blue Waters supercomputing system at the National Center for Supercomputing Applications (NCSA) at UIUC. "Marc has contributed to the development of some of the most suc- cessful high performance computing architectures developed to date and spearheaded innovations that have led to broad use parallel programming by the HPC community," said Bill Gropp, SC13 chair and Thomas M. Siebel chair in Computer Science at UIUC. "He is one of those rare scientists today who is shaping both supercomputing and the widespread adoption of parallel programming it makes possible."