cuda_dot_conj_kernel_impl()

void syten::Cuda::cuda_dot_conj_kernel_impl	(	std::size_t	sz,
		const std::complex< double > *	to_be_conj_a,
		const std::complex< double > *	b,
		std::complex< double > *	result,
		void *	cuda_stream
	)

Calculates the scalar product of two CUDA arrays.

Parameters

sz	the number of elements in the arrays
to_be_conj_a	the first array, whose elements will be complex-conjugated on-the-fly, in device memory
b	the second array, elements not conjugated, in device memory
result	pointer to result, must be zero-initialised, in device memory.
cuda_stream	CUDA stream inside which this computation will be performed

Remarks

This function requires 64-bit float atomic add instructions available only on CUDA Compute Capabilities 6.0 and over.

Referenced by dot().

Here is the caller graph for this function: