Today at the GPU Technology Conference (GTC), MathWorks announced support for NVIDIA graphics processing units (GPUs) in MATLAB applications using Parallel Computing Toolbox or MATLAB Distributed Computing Server. This support enables engineers and scientists to increase the speed of many of their MATLAB computations without performing low-level programming.
Now more engineers and scientists can take advantage of NVIDIA’s CUDA-enabled GPUs, including the latest Tesla 20-series GPUs, based on the Fermi architecture, all from within MATLAB. Parallel Computing Toolbox users can access the NVIDIA CUDA library without having to learn CUDA programming or significantly modify their applications.
Originally designed for graphics rendering in the image-intensive video gaming industry, GPUs have evolved in recent years to become more general purpose. Researchers can program them to execute the computations and sophisticated graphical effects needed for data analysis, data visualization, and applications such as financial modeling and biological modeling.