Custom compute capability
Specify a custom CUDA architecture flag value
Model Configuration Pane: Simulation Target / GPU Acceleration
Description
The Custom compute capability parameter specifies the name of the NVIDIA® virtual GPU architecture for simulation acceleration.
Dependencies
This parameter requires a GPU Coder™ license.
This parameter is enabled by GPU acceleration on the Simulation Target pane.
Settings
'' (default) | argument-listSpecify the name of the NVIDIA virtual GPU architecture for which the CUDA® input files must be compiled.
For example, to specify a virtual architecture type -arch=compute_50. You
can specify a real architecture using -arch=sm_50. For more
information, see the Options for Steering GPU Code Generation topic
in the CUDA Toolkit documentation.
Recommended Settings
| Application | Setting |
|---|---|
| Debugging | No impact |
| Traceability | No impact |
| Efficiency | No impact |
| Safety precaution | No impact |
Programmatic Use
Parameter: SimGPUCustomComputeCapability |
| Type: character vector |
Value: '' or a valid user-specified virtual architecture specification |
Default: '' |
Version History
Introduced in R2020b
