Alan Turing Institute gets a Cray
- Autor:Ella Cai
- Zwolnij na:2017-07-14
Cray is providing an Urika-GX system to the Alan Turing Institute through a collaboration between Cray, Intel, and the Institute.
Five founding universities: Cambridge, Edinburgh, Oxford, UCL and Warwick; plus the UK Engineering and Physical Sciences Research Council founded it 2015.
The computer will be hosted at the University of Edinburgh in the Edinburgh Parallel Computing Centre (EPCC) – and will be used for engineering and technology, defence, security, smart cities, financial services and life sciences, said Cray.
Urika-GX is based around Xeon E5 v4 processors with up to 22Tbyte of DRAM, and up to 176Tbyte of local Intel P3700 SSD (solid-state drives).
They come in 16, 32, and 48 node configurations, and the system at the Alan Turing Institute is a 16 node system.
“A feature of the Urika-GX system is the Graph Engine,” said Cray, “which leverages the high-speed Aries network interconnect, to provide unprecedented, large-scale graph pattern matching and discovery operations across complex collections of data. Also supported is the Apache Spark cluster engine and the Apache Hadoop software library. When combined, the Spark, Hadoop and Graph Engine – enable customers to build analytics work-flows and avoid unnecessary data movement.”
“The Cray system, based in the University of Edinburgh, one of our founding university partners, will be an important addition to the Turing’s data science toolkit.” said Institute CEO Sir Alan Wilson.
Based at the British Library in London, the Alan Turing Institute is the UK’s national institute for data science, and brings together researchers from a range of disciplines to tackle core challenges in data science theory and application.
Five founding universities: Cambridge, Edinburgh, Oxford, UCL and Warwick; plus the UK Engineering and Physical Sciences Research Council founded it 2015.
The computer will be hosted at the University of Edinburgh in the Edinburgh Parallel Computing Centre (EPCC) – and will be used for engineering and technology, defence, security, smart cities, financial services and life sciences, said Cray.
Urika-GX is based around Xeon E5 v4 processors with up to 22Tbyte of DRAM, and up to 176Tbyte of local Intel P3700 SSD (solid-state drives).
They come in 16, 32, and 48 node configurations, and the system at the Alan Turing Institute is a 16 node system.
“A feature of the Urika-GX system is the Graph Engine,” said Cray, “which leverages the high-speed Aries network interconnect, to provide unprecedented, large-scale graph pattern matching and discovery operations across complex collections of data. Also supported is the Apache Spark cluster engine and the Apache Hadoop software library. When combined, the Spark, Hadoop and Graph Engine – enable customers to build analytics work-flows and avoid unnecessary data movement.”
“The Cray system, based in the University of Edinburgh, one of our founding university partners, will be an important addition to the Turing’s data science toolkit.” said Institute CEO Sir Alan Wilson.
