|
| __device__ __forceinline__ uint32_t | cuddl::detail::load_shared_relaxed (uint32_t const *address) |
| | Relaxed CTA-scope load of a shared word that other threads update atomically.
|
| |
| template<size_t BucketCount, typename Layout , bool HasBlacklist = false, bool Naive = false> |
| __device__ __forceinline__ void | cuddl::detail::add_sequence_windows (char const *sequence, uint32_t windows, size_t first_tile, size_t tile_stride, uint32_t k, uint32_t *registers, bool packed_input=false, blacklist_view blacklist={}) |
| | Encodes raw ASCII windows into registers using shared overlapping tiles.
|
| |
| template<size_t BucketCount, typename Layout , bool HasBlacklist = false, bool Naive = false> |
| __global__ void | cuddl::detail::add_sequence_batch_kernel (sequence_batch_chunk const *chunks, size_t chunk_count, size_t block_count, uint32_t k, uint32_t *registers, blacklist_view blacklist={}) |
| | Batch kernel covering every staged chunk in one launch, including short records.
|
| |
| template<size_t BucketCount, typename Layout , bool HasBlacklist = false> |
| __global__ void | cuddl::detail::add_sequence_single_kernel (char const *sequence, uint32_t windows, uint32_t k, uint32_t *registers, blacklist_view blacklist={}) |
| | Single-sequence kernel for the public raw-ASCII API.
|
| |
| template<size_t BucketCount, typename Layout = default_register_layout> |
| __host__ Result< void > | cuddl::detail::launch_sequence_add (device_span< char const > sequence, uint32_t k, device_span< uint32_t > registers, cuda::stream_ref stream, cuda::std::optional< blacklist_view > blacklist=cuda::std::nullopt) |
| | Shared launch for one device-resident ASCII chunk.
|
| |
