Issue 89, 27 May 2010

Featuring


NAG Numerical Routines for GPUs Expanded


We have recently announced the inclusion of additional routines in the NAG Numerical Routines for GPUs. This prototype library is being collaboratively developed to deliver first class algorithmic capability to those working with GPUs. At its second release the set of routines includes pseudo and quasi-random number generators, providing uniform, Normal and exponential distributions and a Brownian Bridge Constructor.

monte carlo simulation using nag

Speed up: Monte Carlo Simulation using NAG RNG on GPU versus CPU


NAG Prize 2010 Awarded at SIAM Student Chapter Conference


With great pleasure NAG awarded the 2010 Winners of the NAG Prize at the first Manchester SIAM Student Chapter Conference earlier this month.

The awards were established in 2006 to recognize the highest achiever in the Mathematics and Computational Science and Mathematical Finance MSc courses at the University of Manchester. This years prizes were awarded to Xiaolu Han and Michael Crabb by Mike Dewar, Chief Technology Officer at NAG.

Fundamental to NAG's longevity in the numerical software arena is the fostering of young and upcoming mathematical talent from the world of academia. The company was founded on academic collaborations and still has very strong links with universities and learning institutions all over the world. NAG offers support to students and post graduates in many ways, whether by way of the NAG Prize or by recruiting students on yearly work placements.

nag prize winners 2010

NAG Prize Winners 2010 with Mike Dewar


Interfacing the NAG C Library and Python on Windows


At one of his talks, Mike Croucher, Science and Engineering Applications Specialist at the University of Manchester, was asked "Does your Python-NAG interface work on Windows machines?"

His answer at the time was "No", however after a bit of research he discovered that "thanks to the portability of Python and the consistency of the NAG Library across platforms" it could be easily achieved.

To read the full story visit http://www.walkingrandomly.com/?p=2188


Wilkinson Prize Announcement


In honour of the outstanding contributions of James Hardy Wilkinson to the field of numerical software, Argonne National Laboratory, the National Physical Laboratory, and the Numerical Algorithms Group award a numerical software prize of US $3000.

The next Wilkinson Prize will be awarded at ICIAM 2011 in Vancouver, July 18-22, 2011. To learn more about the prize including the rules of submission and selection criteria visit [site:url]other/wilkinsonprize.asp.


Supercomputing: From Scripting to Scaling


Multicore is challenging even the most battle-scared programmer

Over the past year or so, whenever I talk to anyone involved in the support of researchers who use HPC facilities and the subject of programming comes up, there seems to be a growing consensus. The next generation of scientific programmer is not using Fortran or C/C++. An increasing number of researchers can fulfil their computational needs using Python or MATLAB, or some other packages/high level languages. Recently, someone came to HECToR, the UK's Supercomputing Service, with a MATLAB script wanting to run much larger simulations than their desktop allowed. So, what do we tell researchers like this?

I am sure many would be tempted to raise an eyebrow and say you should have learned a more, shall we say, traditional scientific computing language when you were an undergraduate! That debate rages on and on as this recent contribution shows (http://www.walkingrandomly.com/?p=1397), so we will avoid that here. However, I did recently teach Fortran to some graduate students who had only used MATLAB thus far and had Fortran 77 thrust upon them by their supervisor. The sheer panic in their faces only went to reinforce the simplicity of prototyping that some people find in scripting languages like MATLAB, that they don't in lower-level languages.

I also am not going to debate why people use Python, MATLAB, et al. The packages advantages in terms of usability, flexibility, easy graphics, fast prototyping capability, post processing features, interactivity, ease-of-data generation, clean syntax and the whole range of modules/toolboxes available are well documented. It is therefore easy to see why such packages are so attractive.

Read the full story recently published in Scientific Computing, by Craig Lucas, Senior Technical Consultant at NAG.


David W Martin


We are sorry to report that David Warwick Martin died on 28th April 2010.

David played a large part in the early years of NAG, representing NPL in on the NAG governing body until May 1983.

I remember David very fondly as a person of great integrity, who acted as a generous host at our regular linear algebra meetings with Jim Wilkinson, Gwen Peters and other NPL colleagues. We owe David a huge debt of gratitude for tempting Sven Hammarling to NPL to take the three year position of Principal Research Fellow. David was head of the group at that time. From there of course Sven joined NAG.

Circumstances placed David in a difficult situation when government cut-backs forced economies upon NPL and NPL were unable to continue to support the NAG project in the same manner. Eventually this led to his retirement from the NAG governing body and ultimately to retirement from NPL.

Ever a gentleman, and considerate of others, David left his body for medical research.

David Sayers, NAG Principal Technical Consultant


Recent Blog Posts


Reflecting on 40 Years of Software Development
NAG's 40th Anniversary
Congratulations NAG Prize 2010 Winners
Waiting for software and School children
Plotting Lambert's W Function
New product launch = busy, but happy marketing department!


Out & About with NAG


For more information on any of the above events visit NAG's ‘Out & About’ webpage


New NAG product implementations


The NAG Library for SMP & Multicore, Mark 22 is now available for the following platforms:

  • Fujitsu HX600 using the Fujitsu Fortran Compiler
  • AMD-64 Windows64 using the Intel Fortran v11.1 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 [site:url]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: [site:url]NAGNews/index.asp.


NAGNews - Past Issues


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