The toolkit version that you need depends on the version of MATLAB you are using.
Matlab r2013a documentation code#
If you already have the corresponding PTX file, you do notįor more information about generating CUDA code in MATLAB, see Run MEX-Functions Containing CUDA Code and Run CUDA or PTX Code on GPU. * To create CUDA kernel objects in MATLAB, you must have both the CU file and the corresponding PTX file.Ĭompiling the PTX file from the CU file requires the CUDA toolkit.
Matlab r2013a documentation install#
Install the version of the CUDA Toolkit supported by your MATLAB Run MATLAB functions on a GPU or to generate CUDA enabled MEX functions.Ĭreate CUDA kernel objects from CU code.*Ĭompile CUDA compatible source code, libraries, and The CUDA Toolkit contains CUDA libraries and tools for compilation. If you want to generate CUDA kernel objects from CU code or use GPU Coder™ to compile CUDA compatible source code, libraries, and executables, you must install aĬUDA Toolkit. Information, see Forward Compatibility for GPU Devices. You might see errors and unexpected behaviour. You can enable support by enabling forward compatibilityįor GPU devices. For more information, see Forward Compatibility for GPU Devices. Support can be limited and you might seeĮrrors and unexpected behaviour. Optimized device libraries must be compiled at runtimeįrom an unoptimized version. MATLAB generates a warning the first time you use a Kepler orĬompatibility.
GPU with MATLAB will require a GPU device with compute capability 6.0 or Architectures will be removed in a future release.
0 kommentar(er)
