applications
connect. Te back end is the visualisation; the front end is how you make changes. We have lots of ways to modify the design; we even have a way for you to modify the mesh that you have created as part of your simulation. You can even bring in scan data; there are a number of ways that to get access to geometry that you may want to evaluate for different alternatives. As we allow people to do that, the visualisation becomes increasingly important because people start to see what happens,’ Christenson said. ‘Te visualisation becomes important because it allows you to see how the modifications affect the design process.’ For visualisation to be effective at driving
innovation, however, it must be integrated into the design cycle as early as possible. Normand explains: ‘Embedding them, or making them associative with the major CAD systems around the world, is really opening the doors for engineers to experiment with the “what if?”. What if we switch materials to something lighter, cheaper or that can be more easily manufactured? What happens if we want to take our product into a new market that requires higher thermal loads or higher power density? It really gives engineers the chance to do what they do best, while at the same time lowering the risk for the company to explore those options.’ Visualisation is unlikely ever to be the sole
method of data analysis. But, as complex models get larger, the sheer amount of data increases dramatically, graphical visualisations can be used to represent large data sets. According to Christenson: ‘Te amount of
data that you are going to generate – whether you are going to visualise it or not – depends on the driver. For instance, fluid metrics used to be hundreds of thousands of cells that went to millions of cells, and now we are able to solve a billion fluid cells. Te same can be said for structural analysis – we have just solved a problem with a billion degrees of freedom. Te amount of data that you generate has gone from megabytes to gigabytes to now hundreds of gigabytes of files to generate those very large models. So what becomes important is your technology strategy, along with HPC – how you are able to develop both from a customer and a vendor standpoint.’ Although Normand believes that a technical
background is needed properly to interpret visualisations, he also highlighted how the visualisation of models can be used to inform people with a less technical background. ‘Visualisation obviously helps people to make sense of the information that is coming back. You know if you are just presented with reams and reams of stress figures, or temperature data, or pressure plots, or something like that, then,
The amount of data generated in modelling has increased massively
for some people especially towards the design end of the spectrum, it can be difficult to process that and understand that information.’ Normand said that Autodesk’s soſtware can
be used to present only the critical data within the visualisation. He gave an example of the new generation of Xbox design where the engineers were only really concerned with temperature around the new processor. Te soſtware has ‘decision centres’ that help bring forward the pressure data, or the temperature data, or whatever that critical data, is for the designer. Normand concludes: ‘It brings that to the forefront, so that they can make those kinds of decisions without having to spend days and days going through a model to analyse the results.’
Making the World’s Fastest Computers Even Faster.
NVIDIA and PGI. Together we create the world’s fastest HPC Accelerators and the world’s best HPC Compilers. Accelerate your Science. Accelerate your Discoveries.
Learn more about NVIDIA Accelerated Computing Solutions at
www.nvidia.com/tesla Test Drive PGI Compilers with OpenACC at
www.pgroup.com/accelerate
®
Ansys
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