CUDA in Action

Today tens of thousands of developers, scientists, students, game creators, and researchers are writing applications that take advantage of GPU computing in areas as diverse as physics-based game play, equity risk analysis, seismic data analysis, and weather prediction.

General Mills employed a CUDA-based system to answer this question: What’s the optimal way to cook a frozen pizza in the microwave? Rather than physically experiment with thousands of combinations, General Mills created virtual pizza models to discover the effects of microwave radiation on various permutations of mozzarella cheese, tomato paste, and crust. They found it less expensive and time consuming to model the pizzas using a sophisticated computer, and only cook up the best candidates.
SeismicCity uses CUDA to improve the chance of finding oil. The cost of drilling deep oil exploration wells can reach hundreds of millions of dollars. In many cases, there is only one chance to drill a successful well. SeismicCity’s CUDA-based depth imaging technology interprets seismic data that leads to the selection of new drilling locations much faster than they could do with previous systems.
OptiTex Ltd. has taken the design industry to a new level with its 3D CAD/CAM technology. Traditionally, fashion designers have had to physically create cloth samples for prototyping, a time-consuming and expensive process. OptiTex 3D modernizes this process by enabling designers to simulate the look and movement of clothing on virtual models, allowing them to review, refine, and measure samples before the first piece of fabric is ever cut. Product development time for a seasonal collection is typically 190 days, but with the OptiTex’s CUDA-based solution, the time to market is reduced to as little as 35 days.

These are just a few examples of how parallel GPU computing is revolutionizing computationally-intensive problems across multiple industries.

In addition, the academic world has recognized the incredible potential of this computing architecture. CUDA-based GPU Computing is now part of the curriculum at more than 200 universities, including MIT, Harvard, Cambridge, Oxford, the Indian Institutes of Technology, National Taiwan University, and the Chinese Academy of Sciences.

Click here to see world map of educational institutions where CUDA and GPU Computing are taught.

Click here to see a list of GPU computing clusters built with CUDA-based Tesla systems.

Click here to see a list of organizations offering consulting and training services.