MATLAB GPU Computing Support for NVIDIA CUDA-Enabled GPUs

Perform MATLAB Computations on CUDA GPUs

Using MATLAB for GPU computing lets you accelerate your applications with GPUs more easily than by using C or Fortran. With the familiar MATLAB language you can take advantage of the CUDA GPU computing technology without having to learn the intricacies of GPU architectures or low-level GPU computing libraries.

You can use GPUs with MATLAB through Parallel Computing Toolbox, which supports:

• NVIDIA CUDA GPUs with compute capability version 1.3 or higher, including Tesla GPUs. These GPUs support double-precision computations.
• GPU use directly from MATLAB
  • GPU-enabled MATLAB functions such as fft, filter, and several linear algebra operations
  • CUDA kernel integration in MATLAB applications, using only a single line of MATLAB code
• Multiple GPUs on the desktop and computer clusters using MATLAB workers in Parallel Computing Toolbox and MATLAB Distributed Computing Server

Examples and How To

• GPU Computing with MATLAB (Webinar)
• MATLAB GPU Computing (Video)
• Parallel Computing with MATLAB on Multicore Desktops and GPU (Webinar)
• Benchmarking a MATLAB GPU-Enabled Operation on an NVIDIA CUDA GPU (Example)
• Accelerating Computation of Mandelbrot Set Using MATLAB GPU Computing Capabilities (Example)
• Speeding Up a MATLAB Application Using an NVIDIA CUDA GPU (Example)
• GPU Programming in MATLAB (Article)
• Cornell Collaboration Explores GPU Computing Using MATLAB (News Release)

Reference

• MATLAB GPU Computing: Requirements
• MATLAB GPU Computing: Documentation
• Find the Compute Capability for Your NVIDIA CUDA GPU (NVIDIA resource)
• MATLAB Acceleration on CUDA GPUs (NVIDIA resource)
• What is GPU Computing? (NVIDIA resource)
• What is CUDA? (NVIDIA resource)

See also: parallel computing