Thanks for visiting Scientific Computing World.

You're trying to access an editorial feature that is only available to logged in, registered users of Scientific Computing World. Registering is completely free, so why not sign up with us?

By registering, as well as being able to browse all content on the site without further interruption, you'll also have the option to receive our magazine (multiple times a year) and our email newsletters.

A model Centre

Share this on social media:

This article is brought to you by: 

CFMS invites you to participate in its latest Modelling and Simulation Research Survey. This short and confidential survey consists of 12 questions, including contact details, and will take approximately 5 minutes to complete. The survey is available here.

Much has changed in the modelling and simulation arena during the past 10 years. In the early 2000s, multi-core processors were still in their infancy, while novel technologies such as Sony PlayStations and very early graphics cards began to emerge from the gaming industry to be applied within high-performance computing. At the time, consumers of large engineering simulation tools like computational fluid dynamics grew concerned that the level of power performance they enjoyed would not continue with the new chips, and so the Southwest Regional development Agency funded a programme dedicated to exploring novel hardware. 

Led by Airbus UK, the programme’s results were made available to a consortium of organisations including BAE, Rolls-Royce, Williams, MBDA, and Frazer-Nash Consultancy, and those results demonstrated the potential for speeding up certain elements of simulation tasks that would often run for weeks, or even months, on supercomputers. These long-duration, expensive calculations could be accelerated by a factor of 100 or more, reducing what might take a year down to a matter of days, significantly impacting on the engineering design process. 

The project that followed widened the scope of research while continuing the focus on testing a vast amount of hardware. In addition to the original consortium participants, process-orientated IT companies, such as Microsoft and Streamline Computing, joined the programme to not only explore how to boost power to simulation tools, but to answer the question of how best to access and make use of the data these tools produce. Sponsored by the Technology Strategy Board – now known as Innovate UK – this £17.5 million project lasted three and a half years and led to the development of many exciting prototype solutions and technologies, including the raw acceleration of computational fluid dynamics processes by a factor of 1,000. Named the Core Programme, this landmark collaborative project ultimately led to the incorporation of the Centre for Modelling and Simulation (CFMS).  

Based at the Bristol & Bath Science Park, CFMS is an independent, not-for-profit provider of modelling and simulation services. ‘At CFMS we’re continuing to promote advanced modelling and simulation by pushing the boundaries of what’s currently possible, and by enabling companies to take full advantage of these tools in their design processes,’ commented David Standingford, one of the lead technologists at CFMS. ‘Our aim is to support all those original Core Programme objectives through a combination of providing HPC services, by continuing to explore the use of emerging and novel hardware, and by participating in and leading collaborative research projects. These projects involve organisations that are experienced in the area of mathematical modelling and simulation, as well as those who are new to it.’  

While one of CFMS’ goals is to maintain a fairly broad footprint, the organisation’s key pedigree is rooted in aerospace. It has also been increasing its focus on additional sectors that it has identified as being most able to assimilate and benefit from new design technologies. ‘We’re always keen to add value where we can, but the four main sectors we focus on all stand to benefit greatly from improved, higher fidelity simulation tools,’ said Standingford. ‘Each of those industries is being pressed to produce more complex products in ever reducing timescales. While this puts an enormous amount of pressure on the use of physical prototypes, it does motivate companies to investigate how they can take advantage of computer simulation. By going down that road, they not only stand to benefit from accelerated turnaround times, they will have a wider range of options available for consideration early in the design cycle.’ 

Standingford added that he believes there has been a general global trend towards more commodity manufacturing being done in the East, and that this in turn has driven many UK companies towards the higher value end of the design and manufacture industries. A key enabler of this move is computer simulation, and as a not-for-profit organisation, CFMS is keen to stress that it does not seek to compete with the commodity services that other businesses aim to provide. ‘Our role is to partner with those businesses, leverage them and add value to what they’re doing,’ Standingford explained. ‘CFMS fills a gap in technology readiness levels, but more than that we bridge communities. A lot of innovation is happening in the hardware space, and there’s a large amount of academic work being done to drive things forward, but many organisations are often far too busy focusing on their products to be able to dedicate enough time to research elements. 

‘There’s a lag between taking that academic work, making it available and then proving its inherent value to industry,’ Standingford continued. ‘CFMS sits in that space by bringing different communities together to be able to add value that can then be made available for industrial consumption.’ 

One notable Innovate UK project recently undertaken by CFMS involved the Global Register for Energy Efficient Numerical Simulation (GREENS). As part of the project, CFMS, along with a number of other partners, looked beyond the traditional focus of energy efficient computing – namely the power supply and hardware – to the algorithms being used and how they leveraged the hardware. By looking across different cases, and by using a variety of commercially available or open source solvers, the project participants identified the benefits that came with making adjustments to the algorithms and how those related to the hardware in question. The intention being to ensure simulations of specific types could run efficiently. Nathan Harper, head of IT systems at CFMS, explained that rather than relying on manufacturers’ stated power performances, the team metered the equipment to know precisely the effect the adjustments were having across the different platforms. That project was completed in 2014, and since that time CFMS has invested heavily in its data centre hardware in order to monitor the power usage of its technology. 

‘With every new piece of equipment we bring in, there is a focus on energy efficiency and what techniques we can use to improve both performance and energy consumption. And from a systems’ perspective, some of the potential tweaks can have an incredible impact,’ Harper commented. ‘For example, we looked at CPU schedulers and the power saving modes in modern CPUs because when building HPC systems, many people will immediately turn off all power saving functions and instead run everything in performance mode. 

‘While this is the easiest way to ensure consistent performance, it means that even when simulations that aren’t doing any heavy compute are being run, all of the cores across that entire job run are in performance mode, drawing energy.’ Harper added that the change made in the CPU scheduler was originally designed to improve the battery life in laptops, but as it filtered through the sectors it was found to improve the efficiency of servers and compute nodes. 

‘With some work you can still get the consistency and performance you would expect from performance mode while still being able to use the energy saving features that companies like Intel have spent quite lot of effort putting into CPUs,’ Harper continued. ‘We’re now looking at whether there are more novel and exotic pieces of technology we can look at from this perspective as the trend is definitely moving towards energy to solution, rather than time to solution.’ Ultimately, the message here is that it may take slightly longer to optimise and then run the simulation jobs, but potentially they will use half the energy. 

David Standingford added that a further motivation within the project was that, for most businesses, the cost of individual components, such as the infrastructure in which the computing is housed, the computing system itself, the software being used, and the staff, usually comes from different budgets: ‘The total cost of offering up a complete compute solution for a modelling and simulation task isn’t aggregated until it reaches the finance director of the company. In fact, very few businesses put conscious effort into optimising that combination of elements and so one of our project aims was to demonstrate that for a number of workflows in common use, there is a variation of a factor of 10 in the energy consumed across the different approaches.’

Within its own fully equipped lab facility, CFMS can appraise a system by instrumenting up a surrogate, evaluating it and then offering an estimate of whether or not there may be an opportunity to optimise it in terms of both performance and power consumption. ‘If you work out the power budget associated with a consolidated approach and apply it to even a moderate user of simulation, you see that it could equate to power savings of several £100,000 per year,’ Standingford continued. ‘These potential savings are not generally known by organisations – even those who are themselves experts in the application of modelling and simulation – and that’s the real value that CFMS provides.’

For more information on CFMS or to discuss opportunities for collaboration, please call +44 (0)117 906 1100 or email info@cfms.org.uk

CFMS invites you to participate in its latest Modelling and Simulation Research Survey. This short and confidential survey consists of 12 questions, including contact details, and will take approximately 5 minutes to complete. The survey is available here.