The Code Generation > GPU Code category includes parameters for configuring GPU-specific settings of the generated code.
These parameters require a GPU Coder™ license.
On the Configuration Parameters dialog box, the following configuration parameters are on the Code Generation > GPU Code pane.
| Parameter | Description |
|---|---|
Kernel name prefix (Simulink Coder) | Specify custom kernel name prefixes. |
GPU device index (Simulink Coder) | Specify the CUDA® device to target. |
Memory allocation mode (Simulink Coder) | Specify the Memory allocation ( |
Dynamic memory allocation threshold (Simulink Coder) | Specify the size above which the private variables are allocated on the heap instead of the stack. |
Stack size per GPU thread (Simulink Coder) | Specify the maximum stack limit per GPU thread. |
cuBLAS (Simulink Coder) | Replacement of math function calls with NVIDIA®
|
cuSOLVER (Simulink Coder) | Replacement of math function calls with NVIDIA
|
cuFFT (Simulink Coder) | Replacement of math function calls with NVIDIA
|
Include error checks in generated code (Simulink Coder) | Add run-time error-checking functionality to the generated CUDA code. |
Compute capability (Simulink Coder) | Specify the minimum compute capability for which CUDA code is generated. |
Custom compute capability (Simulink Coder) | Specify the name of the NVIDIA virtual GPU architecture for code generation. |
Additional compiler flags (Simulink Coder) | Specify additional flags to the |