cudaError_t cudaMemsetAsync ( void *  devPtr,
int  value,
size_t  count,
cudaStream_t  stream = 0 
)

Fills the first count bytes of the memory area pointed to by devPtr with the constant byte value value.

cudaMemsetAsync() is asynchronous with respect to the host, so the call may return before the memset is complete. The operation can optionally be associated to a stream by passing a non-zero stream argument. If stream is non-zero, the operation may overlap with operations in other streams.

Parameters:
devPtr - Pointer to device memory
value - Value to set for each byte of specified memory
count - Size in bytes to set
stream - Stream identifier
Returns:
cudaSuccess, cudaErrorInvalidValue, cudaErrorInvalidDevicePointer
Note:
Note that this function may also return error codes from previous, asynchronous launches.
See also:
cudaMemset, cudaMemset2D, cudaMemset3D, cudaMemset2DAsync, cudaMemset3DAsync


Generated by Doxygen for NVIDIA CUDA Library  NVIDIA