Transfer.Copy.h File Reference

#include <cuda_runtime.h>
#include <cstddef>

Go to the source code of this file.

Namespaces
namespace	Mila
	Mila main API namespace.
namespace	Mila::Dnn
namespace	Mila::Dnn::Compute
namespace	Mila::Dnn::Compute::Cuda

Functions
template<typename SrcT, typename DstT>
void	Mila::Dnn::Compute::Cuda::launch_convert_copy_kernel (const SrcT *d_src, DstT *d_or_h_dst, size_t n, cudaStream_t stream)
	Launch type-converting copy kernel between tensors.
template<typename T>
void	Mila::Dnn::Compute::Cuda::launch_fast_copy_kernel (const T *d_src, T *d_dst, size_t n, cudaStream_t stream)
	Launch optimized same-type copy kernel.