Custom compute capability
Virtual GPU architecture
Description
App Configuration Pane: GPU Code
Configuration Objects: coder.GpuCodeConfig
The Custom compute capability parameter specifies the name of the NVIDIA® virtual GPU architecture for which to compile the CUDA® input files.
For example, to specify a virtual architecture, enter
-arch=compute_50. To specify a real architecture, enter
-arch=sm_50. For more information, see the "Options for
Steering GPU Code Generation" topic in the CUDA Toolkit documentation.
Settings
- no default
Enter the virtual GPU architecture to use.
Programmatic Use
Property:
CustomComputeCapability |
Values: '' | character
vector | string scalar |
Default: '' |
Version History
Introduced in R2018a
