GPU index (GPU Coder)

Specify the CUDA^® device to target.

Compute capability (GPU Coder)

Specify the minimum compute capability for which CUDA code is generated.

Custom compute capability (GPU Coder)

Specify the name of the NVIDIA^® virtual GPU architecture for code generation.

Memory mode (GPU Coder)

Specify the Memory allocation (malloc) mode to be used in the generated CUDA code.

Maximum blocks per kernel (GPU Coder)

Specify the maximum number of CUDA blocks created during a kernel launch.

Dynamic memory allocation threshold (GPU Coder)

Specify the size above which the private variables are allocated on the heap instead of the stack.

Memory Manager (GPU Coder)

Select the GPU memory manager for efficient memory allocation, management, and improving run-time performance.

Stack size per GPU thread (GPU Coder)

Specify the maximum stack limit per GPU thread.

Include error checks in generated code (GPU Coder)

Add run-time error-checking functionality to the generated CUDA code.

Kernel name prefix (GPU Coder)

Specify custom kernel name prefixes.

Additional compiler flags (GPU Coder)

Specify additional flags to the nvcc compiler.

cuBLAS (GPU Coder)

Replacement of math function calls with NVIDIA cuBLAS library calls.

cuSOLVER (GPU Coder)

Replacement of math function calls with NVIDIA cuSOLVER library calls.

cuFFT (GPU Coder)

Replacement of math function calls with NVIDIA cuFFT library calls.