This page contains a Flash digital edition of a book.

Cosmology and solar research turn to HPC

The UK Computational Cosmology Consortium (COSMOS), based at the University of Cambridge, has selected SGI’s Altix UV 1000 to support its research. The announcement came at the same time as a decision by the Hansen Experimental Physics Laboratory Solar Observatories Group at Stanford University to choose SGI server and storage infrastructure to support the Solar Dynamic Observatory (SDO) group’s research into the origin of solar variability.

Professor Stephen Hawking, principal investigator, COSMOS, said: ‘Recent progress towards

a complete understanding of the universe has been impressive, but many puzzles remain. Cosmology is now a precise science, and we need supercomputers to calculate what our theories of the early universe predict and test them against observations of the present universe.’

Altix UV meets COSMOS’s requirements for high performance, scalable, big- memory supercomputing to facilitate vast amounts of data analysis. SGI is collaborating with COSMOS so that Altix UV, with its ease-of-use and rapid time-to- solution, begins contributing to

French computers maintain British atomic weapons

Bull is to provide the United Kingdom’s Atomic Weapons Establishment (AWE) with a third large-scale supercomputer system.

This system is one of the latest in the range of bullx supercomputers launched by Bull last year. Having now passed acceptance testing it is the most powerful supercomputer used by AWE. Named ‘Blackthorn’, this supercomputer will work alongside two other large scale bullx supercomputers, named ‘Willow’, supplied to AWE earlier this year.

Blackthorn is one of the first supercomputers in the world to use the latest six core Xeon ‘Westmere’ chip from Intel and comprises 2,160 (six core) processors in 1,080 blades with 750TB of storage. The system can deliver a peak performance of 145 teraflops (trillions of calculations per second). It is believed to be one of the most powerful supercomputers in the UK and will be used as part of AWE’s

ongoing work to maintain the United Kingdom’s warheads for the country’s nuclear deterrent, Trident, as well as support its position as a centre of excellence for science and technology research. Ken Atkinson, AWE’s HPC strategy manager, explained that the decision to purchase the Blackthorn supercomputer was taken due to a number of contributing factors. ‘As part of a competitive bid, Bull was able to demonstrate the superior ultra high- performance of the machine. We also took account of Bull’s reputation within this market and the fact that other customers had expressed their complete satisfaction with its supercomputers.’


l Europe under-investing in HPC according to EU Commission-funded report

research findings as quickly as possible. Collaboration efforts include: code porting to the Altix UV platform, applications knowledge transfers between SGI engineers and COSMOS users, parallel programmer support and end user training. SGI engineers will also provide dedicated support to COSMOS researchers in strategic projects, following the Altix UV installation.

At Stanford, the Solar Dynamic Observatory (SDO) is trying to understand the characteristics of the Sun’s interior and the components of its magnetic activity to help forecast space

weather. Here too researchers face a data management and analysis problem.

Every day an SDO satellite transmits 1.4 terabytes (TB) of raw data back to Earth for processing into high-definition images for study. SDO has developed and deployed a hybrid Hierarchical Storage Management (HSM) system, which selectively archives key data for future retrieval and use. This hybrid HSM greatly reduces the sets of tapes needed to mount and restore a specific event, such as a solar flare, recorded as part of this project’s research.

Neurological imaging laboratory implements new storage system

Isilon has revealed that the UCLA Laboratory of Neuro Imaging (LONI), home of the world’s largest collection of research neuroimages, has deployed Isilon scale-out storage to power its research into Alzheimer’s disease, schizophrenia and other neurological disorders. Using Isilon’s SmartPools software, LONI has unified three performance tiers of Isilon scale-out storage into a single file system, simplifying data management to drive increased efficiency, cost-savings and application performance. With SmartPools, LONI has consolidated all of its file-based operations onto a central, shared storage pool, aligning application needs with system resources to improve utilisation and reduce costs.

‘Our lab supports data- intensive research initiatives the world over, making efficient data management key to our success,’ said David Hasson, director of IT ay LONI. ‘As a result of implementing SmartPools, we’ve maintained our ability to fine-tune even the lowest level of granularity, while obviating

the need to micromanage the storage cluster. It’s an incredible boon for productivity and has allowed us to focus more time on addressing the many other technical facets of our institution, which has ultimately led to a tremendous increase in research.’

Leveraging its 5,000-plus compute-core Linux cluster and massive repository of 2D and 3D neuroimages, LONI supports an international research community with sophisticated image analysis, web-based image access and a variety of analytic tools and research best practices. LONI deployed Isilon’s SmartPools application to unify its three performance tiers into a single file system and point of management, driving increased simplicity and efficiency across its data centre. With SmartPools, LONI has eliminated manual data migration between storage tiers, reducing overall system management to less than an hour per week and improving data access for its diverse ecosystem of research groups, collaborating scientists and partner organisations.


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56
Produced with Yudu -