CUresult cuLaunchGridAsync ( CUfunction  f,
int  grid_width,
int  grid_height,
CUstream  hStream 
)

Invokes the kernel f on a grid_width x grid_height grid of blocks. Each block contains the number of threads specified by a previous call to cuFuncSetBlockShape().

cuLaunchGridAsync() can optionally be associated to a stream by passing a non-zero hStream argument.

Parameters:
f - Kernel to launch
grid_width - Width of grid in blocks
grid_height - Height of grid in blocks
hStream - Stream identifier
Returns:
CUDA_SUCCESS, CUDA_ERROR_DEINITIALIZED, CUDA_ERROR_NOT_INITIALIZED, CUDA_ERROR_INVALID_CONTEXT, CUDA_ERROR_INVALID_VALUE, CUDA_ERROR_LAUNCH_FAILED, CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES, CUDA_ERROR_LAUNCH_TIMEOUT, CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING, CUDA_ERROR_SHARED_OBJECT_INIT_FAILED
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cuFuncSetBlockShape, cuFuncSetSharedSize, cuFuncGetAttribute, cuParamSetSize, cuParamSetf, cuParamSeti, cuParamSetv, cuLaunch, cuLaunchGrid


Generated by Doxygen for NVIDIA CUDA Library  NVIDIA