cuda_transpose_kernel_impl() [4/4]

void syten::CudaDenseTensorImpl::cuda_transpose_kernel_impl	(	std::uint32_t	rank,
		std::size_t	sz,
		const std::complex< float > *	inp,
		std::complex< float > *	out,
		cukrn_transpose_array const &	old_dim,
		cukrn_transpose_array const &	new_dim,
		cukrn_transpose_array const &	ar_perm,
		void *	str,
		bool	do_conj
	)

Launcher for the CUDA tensor transposition kernel, std::complex<float> version.

Parameters

rank	number of tensor indices
sz	number of elements in the tensor
inp	input tensor array, pointer to device memory
out	output tensor array, pointer to device memory
old_dim	dimensions of the input tensor as a simple POD
new_dim	dimensions of the output tensor as a simple POD
ar_perm	permutation, perm[i] = j puts the old leg j at position i+1
str	CUDA stream in which the computation will take place
do_conj	whether to conjugate every entry