HPC NEWS
Contents
HPC News
The latest news in
high-performance computing
HPC Products
A brief update of the latest HPC software and hardware
Digging for black gold
Stephen Mounsey on the use of HPC in oil and gas exploration
23 20
18
Medical researchers at King’s College London cut analysis time with HPC
Speed merchants
Paul Schreier on the challenges of multicore programming
29 The sky’s the limit 35
Stephen Mounsey defines and explores cloud computing
Medical researchers at the National Institute for Health Research (NIHR) Comprehensive Biomedical Research Centre at Guy’s and St Thomas’ NHS Foundation Trust and King’s College London are for the first time using a high performance computer (HPC) system. The system is being used by researchers to analyse, store and archive vast quantities of data generated through work on understanding the role of genetics in a range of common health issues, such as the development of cancer. The two sequencing machines in use in the King’s College London and NIHR Biomedical Research Centre’s genomics facility collectively generate up to 50 billion base pairs of usable DNA sequence data every 10 days. The HPC system can reduce the time necessary to analyse this data 20-fold or more, reducing the time scales for analysis from days to hours.
‘The sequence of the human genome has been known for 10 years now, so we are using new sequencing technologies to sequence specific regions of the genome
HPC Director
Dr Oz Parchment, IT
infrastructure services manager, University of Southampton
44
in large numbers of people in order to help understand the contributory factors to a variety of common complex disorders and developmental defects,’ said Dr Rebecca Oakey, reader in epigenetics, Department of Medical and Molecular Genetics, School of Medicine, King’s College London. ‘These include skin diseases such as psoriasis, inflammatory bowel disease and the step by step development of vascular disorders, psychiatric disorders, diabetes, infection and immune disease as well as genetic components in cancer development.’
The HPC system’s bespoke design, implementation, configuration, ongoing support and user training is handled by OCF, and includes: IBM’s iDataplex server hardware, which includes ultra-low latency, 10Gb Ethernet switching modules from Blade Network Technologies; Panasas plug-and-play ActiveStor Series 8 clustered storage with capacity of up to 180TB of raw data; and an IBM TS3310 Tape Library Unit with Tivoli Storage Manager to enable long-term, secure, off-site data back-up.
Louisiana Optical Network partners with SC10 for SCinet
The Louisiana Optical Network Initiative (LONI) is partnering with SC10 to provide high- speed network resources for SCinet, the conference’s ultra- high bandwidth network. From 13-19 November, New Orleans’ Ernest N Morial Convention Center will be home to one of the most powerful networks in the world – SCinet. Built each year for the annual SC conference, SCinet will deliver more than 300 gigabits per second (Gbps) in bandwidth, which would allow the entire collection of books at the Library of Congress to be transferred in under 27 seconds. SCinet provides the platform SC exhibitors and attendees require to showcase the revolutionary high performance computing (HPC) applications and networking experiments that have become the trademark of the conference. Key leaders from LONI, along with high-performance computing staff at Louisiana State University, will work with the conference on planning and logistics throughout the year to ensure adequate networking operations and support, and will begin building the network on-site in September.
Sandia National Laboratories wins Federal Laboratory Consortium award
Cover montage: Dean Farrow
18
Sandia National Laboratories has won a Federal Laboratory Consortium award for its efforts to transfer technology to supercomputer manufacturer Cray. Sandia and Cray joined forces in 2001 to build the Red Storm supercomputer, the predecessor of the Seattle, Washington-
SCIENTIFIC COMPUTING WORLD JUNE/JULY 2010
based company’s line of Cray XT supercomputers. When the partnership started, there were no commercial supercomputers that targeted complex simulations, said Sudip Dosanjh, senior manager of Computer and Software Systems at Sandia. Peter Ungaro, Cray’s chief
executive and president, credits Sandia for the speed of the development. ‘We would have gotten there, but we definitely wouldn’t have done it in the timeframe that we got there with Sandia, and we wouldn’t have built as good a product, if we had done it ourselves,’ he said.
www.scientific-computing.com
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 |
Page 57 |
Page 58 |
Page 59 |
Page 60