cuda_transpose_recursive()

template<Rank rank, typename Scalar >

void syten::CudaDenseTensorImpl::cuda_transpose_recursive	(	CudaConstSpan< Scalar >	inp,
		CudaMutSpan< Scalar >	out,
		ConstSpan< IndexNumber >	in_perm,
		ConstSpan< Index >	in_dim,
		Conj	do_conj = Conj::n()
	)

Entry point for the CUDA recursive tensor transposition implementation, to be called only from cuda_transpose_impl().

References syten::Cuda::CudaDynArray< Type >::begin(), syten::Cuda::conj_copy(), syten::Cuda::host_device(), syten::rank(), syten::SpanImpl::ConstSpan< T >::size(), and SYTEN_ASSERT.

Here is the call graph for this function: