Cray Tackles Enterprise Big Data with New Supercomputer
Cray Inc. is tackling Big Data with a big computer that sports up to 1,728 Xeon processor cores, 22 TB of memory and 35 TB of SSD storage, along with an analytics framework and open source software, all optimized for demanding workloads.
The supercomputer specialist today announced the Urika-GX system, described as "the first agile analytics platform that fuses supercomputing technologies with an open, enterprise-ready software framework for Big Data analytics."
The unit comes with pre-integrated software such as: the Hortonworks Data Platform, which includes Hadoop and Apache Spark: the Cray Graph Engine to help solve large and complex graph analytics problems; OpenStack for management; and Apache Mesos for dynamic configuration.
The company said the Cray Graph Engine, designed for fast, complex iterative discovery, typically outperforms other graph solutions by 10 to 100 times. "The Cray Graph Engine can run in conjunction with open analytics tools such as Hadoop and Spark, enabling customers to build complete end-to-end analytics workflows and avoid unnecessary data movement," the company said in a statement today. It can reportedly scale from one to thousands of processors without a performance degradation, able to handle multi-terabyte datasets with billions of objects.
"The Urika-GX is a dynamic analytics solution that brings out the best of Cray's decades of expertise in providing our customers with world-class systems for data-intensive computing," said Peter Ungaro, president and CEO of Cray. "Customers have asked us to blend the unique features of our product lines into a single platform for data analytics. We took the Aries system interconnect from our supercomputers, the industry-standard architecture of our clusters, the scalable graph engine from the Urika-GD appliance, and the pre-integrated, open infrastructure of our Urika-XA system and combined them into one agile analytics platform. The Urika-GX gives our customers the tool they need to overcome their most advanced analytics challenges today, and the platform to bridge to tomorrow."
Cray said that sometime during the third quarter, it will provide the supercomputer in three initial enterprise-accessible configurations that feature 16, 32 or 48 nodes on an industry standard 42U 19-inch rack, with larger configurations expected to become available in the second half of the year.
David Ramel is the editor of Visual Studio Magazine.