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 a specialist in modelling and simulation that support the development of engineering design capability. ‘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 there are a number of additional sectors that 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.’