Discovering Gold with Big Data Analytics and Data-Intensive Computing

Entries filed under “Hardware”

Massive 790 Gigabit Network Capacity Lights Up SC12

By Rich | Published November 14, 2012

The SC12 conference this week in Salt Lake City will be home to one of the fastest computer networks in the world.

Known as SCinet, the network is built each year to support the international conference for high performance computing, networking, storage and analysis. Over 100 engineers representing industry, academia and government institutions have volunteered their time over the past year to plan and build SCinet using nearly $28 million in donated equipment. The network will serve as the primary backbone supporting all 10,000+ SC conference attendees as they unveil their latest innovations in high performance computing applications.

Unlike typical Internet traffic, scientific workflows tend to demand high capacity network links for long duration large data flows,” said Linda Winkler, Senior Network Engineer at Argonne National Laboratory and chair of SCinet for SC12. “The SCinet infrastructure was architected to meet these demanding requirements.”

Read the Full Story.


Also posted in HPC, I/O, Network | Leave a comment

New DDN Hybrid Appliance Anticipates and Optimizes Big Data Movement

By Rich | Published November 11, 2012

This week DataDirect Networks (DDN) announced the SFA7700, a hybrid flash storage appliance with a unique ability to anticipate and optimize the workloads of big data-intensive applications.

DDN has extended its SFA technology to feature even greater levels of efficiency and modularity,” said Henry Baltazar, Senior Analyst, 451 Research. “With appliance-level integration into DDN’s file storage technology and new automation with DDN’s cloud collaboration tools, the SFA7700 is an ideal foundation to DDN’s Big Data portfolio and will enable organizations to ingest, process, store and distribute data with simplicity and scalability.”

According to the company, the SFA7700 hybrid storage appliance is an ideal entry-level system for organizations with big data storage needs. It can start small, supporting 60 SSDs and/or HDDs in a 4U rack for a maximum capacity of 240TBs, and can expand to support up to 396 disks in 20U rack for a maximum capacity of 960TBs. In addition, the SFA7700 also allows organizations to migrate data to a public or private cloud when integrated with DDN’s Web Object Scaler (WOS) cloud storage appliance, facilitating file sharing and collaboration. Read the Full Story.


Also posted in Flash and SSD, HPC, Storage | Leave a comment

Speed Big Data Results with the New NetApp HPS Rack Solution

By Rich | Published November 9, 2012

Today, NetApp announced the new High-Performance Storage (HPS) Rack. Prepackaged and preconfigured, the HPS Rack includes servers, management and monitoring software, and the open-source Lustre parallel file system, enabling organizations to shorten deployment time from months to days, lower risk, reduce total cost of ownership, and speed time to results.

For fast insight to action, the best software and hardware needs to be employed to achieve the highest levels of performance for our researchers,” said Scott Kornblum, managing director, Thesys Technologies, the infrastructure affiliate of Tradeworx. “Once we started running our NetApp E5400 and E2600 with Terascala’s LustreStack, it became dramatically easier for us to manage resources, helping us reduce costs. We can now monitor performance in real time and provide 5GB per second of throughput to our research group, giving them the tools they need to test and model new algorithms concurrently.”

The NetApp HPS Rack is built on the NetApp E-Series platform. Additionally, the NetApp HPS Rack can integrate Terascala LustreStack software to provide proven management and extensive analytics. With LustreStack, customers get a Lustre-based solution that deploys in minutes, is easy to manage, and is optimally tuned for applications and workflows. Administrators can get all the performance and scalability benefits of Lustre without the need for any in-house expertise, bringing rapid deployment, simplicity, and faster time to results to big data and HPC environments.

The NetApp HPS Rack will be demonstrated at next week’s SC12 Conference in Salt Lake City, Utah, from November 10–16. Come and visit NetApp at booth #4626.


Also posted in Business of Big Data, Lustre, Software, Startups | Leave a comment

ORNL to use YarcData Appliance for Healthcare Fraud Detection

By Rich | Published November 7, 2012

This week Cray’s YarcData division announced a contract to deliver a uRiKA graph-analytics appliance to the Oak Ridge National Laboratory (ORNL). Analysts at ORNL will use the uRiKA system as they conduct research in healthcare fraud and analytics for a leading healthcare payer.

Identifying healthcare fraud and abuse is challenging due to the volume of data, the various types of data, as well as the velocity at which new data is created. YarcData’s uRiKA appliance is uniquely suited to take on these challenges, and we are excited to see the results that will come from the strategic analysis of some very large and complex data sets,” said Jeff Nichols, Associate Laboratory Director for Computing and Computational Sciences at Oak Ridge National Laboratory.

In addition to the healthcare fraud detection program, researchers and scientists at ORNL will also apply the uRiKA system to other areas of research where data discovery is vital. Read the Full Story.


Also posted in Analytics, Business of Big Data, HPC | Leave a comment

IBM PureSystems in Plain English

By Rich | Published October 31, 2012

Over at the Expert Systems blog, Thiago Farah Montenegro writes that IBM PureSystems are tailor-made for applications like Big Data.

The amount of information these systems can handle is huge. The IBM BladeCenter E has been out there for 10 years. There was a time when the E chassis could not deliver the necessary I/O for the big virtualization and consolidations requirements, and then IBM launched the BladeCenter H. We have also a product for the “S” of the SMB (small, medium business), called BladeCenter S. They are all great products! Now, however, we need a new platform to handle the even bigger I/O requirements – and the IBM PureFlex System is that platform for many years to come.

Read the Full Story.


Also posted in Analytics | Leave a comment

Spectra Logic Rolls Out 10GbE Connectivity to Tape Solution

By Rich | Published October 30, 2012

Today Spectra Logic announced the introduction of support for 10 Gigabit Ethernet iSCSI connectivity as an interface option for the Spectra T-Series tape libraries. Offered in partnership with Bridgeworks, the solution enables simple integration of tape systems into 10GbE SANs.

We’re excited to continue on the path of keeping tape storage systems easy to integrate in the modern data center. By supporting the Bridgeworks solution for 10GbE iSCSI connectivity to our T-series tape libraries, our customers who are designing data center solutions based on 10GbE iSCSI no longer need to maintain a FC SAN just for their tape storage system,” said Molly Rector, executive vice president of product management and worldwide marketing, Spectra Logic.

The 10GbE iSCSI to FC bridge is available for purchase through Bridgeworks. Read the Full Story.


Also posted in Business of Big Data, Network, Storage, Tape | Leave a comment

YarcData Upgrades Big Data Appliance, Goes with Subscription-based Pricing

By Rich | Published October 23, 2012

Today Cray’s YarcData division announced a major upgrade to its uRiKA Big Data appliance for graph analytics. With the uRiKA Fall 2012 Release, the company is adding substantial new standards-based capabilities to boost functionality and performance on complex graph analytics inquiries.

Big Data graph-analytics are increasingly used to reveal unknown, unexpected or hidden relationships in a wide range of markets, including financial services, health sciences, energy, transportation, Internet commerce and others,” said Arvind Parthasarathi, president of YarcData. “Our uRiKA appliance combined with the enhanced capabilities in this release gives our current and future customers the world’s most powerful, easy-to-use platform for exploiting the power of graph analytics.”

What I find interesting here is that the uRiKA appliance is available via subscription-based pricing. The large memory of the uRiKA appliances may make the sticker price a bit too spendy for this market, so YarcData is letting you pay-as-you-go. Will this be a business model for future Cray supercomputers? We’ll have to wait and see. Read the Full Story.


Also posted in Analytics, Business of Big Data, Graph Computing | Leave a comment

Tape Technology on the Comeback Trail

By Rich | Published October 21, 2012

Over at New Scientist, Paul Marks writes that new cassette tape technology from Fujitsu can store 35 terabytes of data – or about 35 million books’ worth of information – on a cartridge that measures just 10 centimetres by 10 cm by 2 cm.

But the real debut for this technology is likely to be the Square Kilometre Array (SKA), the world’s largest radio telescope, whose thousands of antennas will be strewn across the southern hemisphere (New Scientist, 2 June, p 4). Once it’s up and running in 2024, the SKA is expected to pump out 1 petabyte (1 million gigabytes) of compressed data per day.

Read the Full Story.


Also posted in Storage, Tape | Leave a comment

Scaling Big Data Infrastructure is No Small Task

By Rich | Published October 20, 2012

Over at ZDNet, Larry Dignan writes that there’s a there’s a big jump from a Hadoop pilot to actually scaling it.

If customers have an investment in HPC that’s what they are leveraging,” said Univa CEO Gary Gary Tyreman. “The reason isn’t the hardware but operational expertise.” Companies need to figure out how to get data from storage systems from the likes of NetApp and EMC to a Hadoop framework and back again.

Read the Full Story.


Also posted in Business of Big Data, HPC, Storage | Leave a comment

Got Big Data? AWS Glacier is no Tape Killer

By Rich | Published October 18, 2012

Molly Rector from Spectra Logic writes that Amazon’s AWS Glacier cloud archival service is no “Tape Killer.”

Amazon Glacier is not practical for active archive markets with up to exabytes of data. Tape is. Bandwidth costs are too high, retrieval time is too slow and the Glacier model doesn’t meet the frequency of data access requirements. Just think about retrieval times: it would take about 40 days to move one (1) petabyte across an OC48 and 10 days to move it across 10 Gb/E. When talking about large data archive, local storage is a must.

Read the Full Story or check out the Radio Free HPC podcast on why Glacier doesn’t quite cut it.


Also posted in Business of Big Data, Storage, Tape | Leave a comment

Advertisement


View All Videos

inside-bigdata.com is a production of insideHPC, LLC. © 2011-2013 Sitemap