From supercomputing applications to financial modeling, graphics chips are being deployed for a number of research and development activities.
Graphics chips are great when it comes to crunching repetitive computational tasks, which is a reason why they are making it to diverse applications beyond gaming. This is in comparison to desktop processors, which are made to perform general applications.
The larger number of cores in graphics chips makes them ideal candidates for research focused on obtaining results for various permutations of data for the same models.
Few excerpts from the article at BBC:
Professor Susan Hagness from the Department of Electrical and Computer Engineering at the University of Wisconsin-Madison has turned to graphics cards to quickly analyse breast scans to spot cancer in its early stages.
The financial models that Prof Giles is running test the same algorithm on each core but each one gets different random numbers as input.
PhD student Tobias Brandvik and Dr Graham Pullan in the Whittle Laboratory at the University of Cambridge engineering department and sped up simulations of turbine blade designs by 40 times by using a few graphics cards.
Perhaps it is with this developing segment in mind that AMD has its focus settled on delivering graphics solutions tightly integrated with its platforms. Don’t forget that it also owns ATI, a leading graphics chipset maker.