Issue 80, 14 May 2009

Featuring


Key materials science code enhanced on HECToR


The UK's newest national supercomputing facility, HECToR, has been heavily used, since its official launch in October 2007, by scientists needing supercomputing resources. A substantial part of the Research Councils' six-year funding for this facility is devoted to the Computational Science and Engineering (CSE) support provided by NAG. An important part of the CSE Service is the distributed CSE (dCSE) programme which, through a lightweight peer review process, delivers dedicated multi-month performance and scalability development projects in response to proposals from the user community. The first dCSE project to complete has proven to be an excellent example of what can be achieved, with dramatic improvements in code performance and scalability which could potentially save millions of pounds and allow significant new science to be undertaken for the UK Car-Parrinello Consortium (UKCP). Read more http://www.nag.co.uk/market/articles/CASTEP_on_HECToR1.asp

Learn more about NAG's specialist HPC service and HECToR.


NAG Library for .NET Beta Test invitation


The NAG Library for .NET, currently at Beta release, has been developed to serve the growing number of application developers and users of Microsoft .NET requiring mathematical and statistical routines. The numerical routines in the NAG Library for .NET are fast and efficient in execution which can enhance application capabilities and reduce crucial development time. The NAG Library for .NET prototype currently contains NAG's popular optimization routines, however later releases will contain the extensive functionality found in the NAG Library.

The NAG Library for .NET is the first prototype, but is available to Microsoft .NET users as part of NAG's Beta Test Program. Beta testing is vital to help drive the prototype forward to future releases. NAG provides expert support service as part of the program to help guide users through technical queries or difficulties.

If you utilize .NET and would like to be part of the NAG Library for .NET Beta Test Program please click here to the product's home page where a link to an online request form is available.


NAG and Python continued'


The numerical routines included in the NAG Library are inherently flexible making their use from many different programming environments, languages and packages quick, easy and efficient. Python is one such evolving language that can call NAG routines. Last year NAG published a paper showing how to call NAG Fortran routines from Python using the F2PY tool http://www.nag.co.uk/doc/techrep/index.asp#np3665. More recently, NAG enthusiast, Dr Mike Croucher, University of Manchester, set to work investigating how to call NAG's C Library from Python using the standard Python ctypes module.

Mike has written up his investigations as an ongoing series of tutorials and examples on his blog http://www.walkingrandomly.com/?p=830. Examples are drawn from several chapters of the NAG C library including special functions, numerical quadrature and optimization.

We are keen to receive feedback on this work and hear what other NAG functionality from Python might be useful. If you'd like to contact us please do by reply to nagnews@nag.co.uk


Supercomputing: Are supercomputers just better liars?


Supercomputers might be better at providing the right answers ' or they could just be providing the wrong answers in far greater detail. Supercomputers enable simulations to use much higher resolutions, more detailed physics, and a greater amount of input data. Yet does all that extra simulation power ensure their predictions are more accurate ' or more likely to be right than a simpler model? In other words, how do you know your supercomputer is telling the truth?

It is a fact of modern life that many things we deal with daily are influenced in some way by computer modelling. Phones, soft-drink cans, vehicles, computers, food containers, healthcare products ' all are designed with input from computer modelling. Those products are shipped to us with logistics supported by computer modelling. Everyday life is powered by energy found or generated by computer modelling.

Increasingly, computer simulations are replacing physical testing for most design work ' jet-engine failures are now tested in computer simulations many times before a single final physical test is conducted. That testing saves huge amounts of time and money for designers of jet engines.

Read the full article by Andrew Jones, Vice-President HPC Business at NAG


NAG in Financial Mathematics Day


Readers of NAGNews are now able to access a further presentation given at the “NAG in Mathematical Finance Day” held recently at Manchester Business School. Nick Higham, School of Mathematics, University of Manchester presented “Structured Nearest Correlation Matrix Problems” which utilizes NAG's nearest correlation matrix routine which was introduced into the NAG Library at Mark 22 http://www.nag.co.uk/numeric/FL/nagdoc_fl22/pdf/G02/g02aaf.pdf.


New Search Routines in the NAG Fortran Library explained


NAG announced the release of the latest mark of the NAG Fortran Library in the last NAGNews. Included at Mark 22 are new search routines. The three search routines differ from conventional search tools which return true if the sought-after item is found or false otherwise. They were developed with statistical problems in mind. They examine a vector and return the index of the first value equal to the sought-after item. If this value cannot be found, the index of the closest value lower than the sought-after value is returned and if there is no lower value, 0 is returned. In statistics this type of searching utility proves useful when categorizing data into particular groups, for example when creating a frequency table from raw data or generating series of random numbers from a general discrete distribution. The new search routines search a vector of double precision numbers, integers and character data, respectively. Read more. To learn more about the new functionality at Mark 22 follow this link.


Ask the Expert!


Question: “How do I fit an ARIMA model using the NAG C Library”

Answer: One commonly used family of time series models are seasonal autoregressive integrated moving average (ARIMA) models. In the linked paper, Senior Technical Consultant (Statistician) at NAG, Martyn Byng, gives a brief description of how to fit a seasonal ARIMA model using a NAG C Library routine and also shows how to forecast from such a model using another C Library routine.


Out & About with NAG


Risk Europe, 2009
4-5 June 2009, Frankfurt
We are exhibiting at Risk magazine's annual flagship conference, providing an invaluable perspective into how leading financial institutions are implementing cutting-edge strategies to mitigate risk, manage portfolios and investments and tackle key industry challenges. Attendees will be updated on developments shaping the financial derivatives market, practical solutions and best practices.

HPCS 2009
14-17 June 2009, Kingston, Ontario
HPCS (High Performance Computing Symposium) is a multidisciplinary conference that focuses on research involving High Performance Computing and its application. Attended by Canadian and international experts and renowned researchers in the sciences, all areas of engineering, the applied sciences, medicine and life sciences, mathematics, the humanities and social sciences, it is Canada's pre-eminent forum for HPC. Jeremy Walton, one of NAG's Senior Technical Consultants, will be speaking at the conference; he will be presenting a workshop on Using the NAG Numerical Libraries on Multicore Systems which describes the functionality of the NAG library and the way in which it has been optimised for multicore systems and other shared memory architectures.

23rd Biennial Conference on Numerical Analysis
23-26 June 2009, University of Strathclyde
The Mathematics Department at the University of Strathclyde is hosting a biennial conference covering all areas of numerical analysis. The conference is open to all researchers in the field, who are invited to contribute a talk on current projects. NAG Senior Technical Consultant, Lawrence Mulholland and colleagues will be presenting a mini-symposium on Algorithms for Multi-Core Systems, and will also be available at NAG's exhibition stand.

International Supercomputer Conference 2009
23-26 June 2009, Hamburg
Come and see us at stand 603 at Europe's leading conference and exhibition on high performance computing. The conference and exhibition will provide delegates the forum to learn, network and do business, all under one roof. NAG will be available to talk about its numerical routines for HPC and our specialist HPC services.

World Congress on Engineering 2009
1-3 July 2009, Imperial College London
NAG will be exhibiting at the congress, organized by the International Association of Engineers (IAENG), a non-profit international association for engineers and computer scientists. The conference will focus on topics in theoretical and applied engineering and computer science.

Quant USA
14-16 July 2009, New York
NAG will be exhibiting at Quant USA. Attendees will gain invaluable insight into quantitative strategies adopted by leading financial institutions. NAG experts will be available to talk about how NAG's routines can enhance finance applications.

HECToR (High End Computing Terascale Resource) Training Courses
Presented by the NAG HECToR Team
A full list of forthcoming HECToR Training Courses can be viewed on the official HECToR website here.


New NAG product implementations


NAG is committed to offering new implementations of its broad range of numerical and statistical software components and compilers and tools.'The following implementations for NAG products have become available since the last issue of our newsletter:

The NAG Fortran Library, Mark 22 is now available for the following platforms:

  • x86-64 Linux64 using the GNU gfortran 4.3.2 compiler
  • x86-32 Linux using the gfortran 4.3.2 compiler
  • x86-64 Linux64 using the Intel Fortran v10.1 compiler
  • Linux x86-32 Linux using the Intel Fortran v10.1 compiler

The NAG Parallel Library, Release 3 is now also available for the following platform:

  • x86-64 Linux64 using the Intel Fortran v11.0 compiler

For full details of these and all other available implementations, visit the NAG site. Comprehensive technical details of each implementation are given in the relevant Installation and User Notes at http://www.nag.co.uk/doc/inun.asp


Managing your subscription


Please feel free to forward this newsletter to colleagues or to post it to your company's Intranet sites.

To subscribe, unsubscribe or learn more about managing your subscription, please see: http://www.nag.co.uk/NAGNews/index.asp.


NAGNews - Past Issues


We provide an online archive of past issues of NAGNews. For editions prior to these, please contact us.

Website Feedback

If you would like a response from NAG please provide your e-mail address below.

(If you're a human, don't change the following field)
Your first name.
CAPTCHA
This question is for testing whether you are a human visitor and to prevent automated spam submissions.
Image CAPTCHA
Enter the characters shown in the image.