7.26. CUDA_KERNEL_NODE_PARAMS_v2 Struct Reference

[Data types used by CUDA driver]

GPU kernel node parameters

Public Variables

unsigned int  blockDimX
unsigned int  blockDimY
unsigned int  blockDimZ
CUcontext ctx
* extra
CUfunction func
unsigned int  gridDimX
unsigned int  gridDimY
unsigned int  gridDimZ
CUkernel kern
* kernelParams
unsigned int  sharedMemBytes

Variables

unsigned int CUDA_KERNEL_NODE_PARAMS_v2::blockDimX [inherited]

X dimension of each thread block

unsigned int CUDA_KERNEL_NODE_PARAMS_v2::blockDimY [inherited]

Y dimension of each thread block

unsigned int CUDA_KERNEL_NODE_PARAMS_v2::blockDimZ [inherited]

Z dimension of each thread block

CUcontextCUDA_KERNEL_NODE_PARAMS_v2::ctx [inherited]

Context for the kernel task to run in. The value NULL will indicate the current context should be used by the api. This field is ignored if func is set.

* CUDA_KERNEL_NODE_PARAMS_v2::extra [inherited]

Extra options

CUfunctionCUDA_KERNEL_NODE_PARAMS_v2::func [inherited]

Kernel to launch

unsigned int CUDA_KERNEL_NODE_PARAMS_v2::gridDimX [inherited]

Width of grid in blocks

unsigned int CUDA_KERNEL_NODE_PARAMS_v2::gridDimY [inherited]

Height of grid in blocks

unsigned int CUDA_KERNEL_NODE_PARAMS_v2::gridDimZ [inherited]

Depth of grid in blocks

CUkernelCUDA_KERNEL_NODE_PARAMS_v2::kern [inherited]

Kernel to launch, will only be referenced if func is NULL

* CUDA_KERNEL_NODE_PARAMS_v2::kernelParams [inherited]

Array of pointers to kernel parameters

unsigned int CUDA_KERNEL_NODE_PARAMS_v2::sharedMemBytes [inherited]

Dynamic shared-memory size per thread block in bytes