helpers.cuh File Reference

#include <cuda_runtime.h>
#include <cuda/std/bit>
#include <cuda/std/concepts>
#include <cstddef>
#include <cstdint>
#include <cuddl/cuda_error.hpp>

Go to the source code of this file.

Namespaces
namespace	cuddl
	Batch operations over contiguous device rows.
namespace	cuddl::detail

Functions
__host__ __device__ constexpr uint32_t	cuddl::detail::load_256_alignment () noexcept
	Byte alignment load_256_global_nc requires on the compiled architecture.
template<typename QueryScore , typename ReferenceScore >
__host__ __device__ bool	cuddl::detail::wide_rows_aligned (QueryScore const *query, ReferenceScore const *reference) noexcept
	True when both row bases meet load_256_alignment on the compiled architecture.
template<typename T >
__device__ __forceinline__ void	cuddl::detail::load_256_global_nc (const T *ptr, T *out)
	Loads 256 bits from global memory using the non-coherent cache path.