The Complete Magazine on Open Source

Cray develops a supercomputer based on open source solutions

, / 168 0

Cray Urika GX system

Cray today unveiled its latest supercomputer model with some open source solutions. Called the Cray Urika-GX system, the new supercomputer runs on OpenStack platform and comes preloaded with the Hortonworks Data Platform to provide Hadoop and Apache Spark in addition to the proprietary Cray Graph Engine.

The Cray Urika-GX supercomputer is aimed to offer an “unprecedented versatility” to its users to run multiple analytics workloads concurrently on a single platform. It eliminates some major challenges of big data analytics using the pre-installed open source framework.

“Customers have asked us to blend the unique features of our product lines into a single platform for data analytics,” says Peter Ungaro, president and CEO, Cray, in a statement. “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.”

Cray has provided Intel Xeon Broadwell cores alongside 22 terabytes of memory and 35 terabytes of local SSD storage. The system comes in three enterprise-accessible configurations in the initial stage, including 16, 32 and 48 nodes.

“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,” Ungaro adds.

The Cray Urika-GX system with an industry standard 42U 19-inch rack will be available starting the third quarter of this year. Its larger configurations will also hit the market in the second half.