For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).
Mojo function
copy_local_to_shared
def copy_local_to_shared[thread_layout: Layout[thread_layout.shape_types, thread_layout.stride_types], *, swizzle: Optional[Swizzle] = None, num_threads: Int = thread_layout.size(), thread_scope: ThreadScope = ThreadScope.BLOCK](dst: TileTensor[Storage=dst.Storage, address_space=AddressSpace.SHARED, linear_idx_type=dst.linear_idx_type], src: TileTensor[Storage=src.Storage, address_space=AddressSpace.LOCAL, linear_idx_type=src.linear_idx_type])
Synchronously copies a tile from registers (LOCAL) to SRAM (shared).
Delegates to LocalToSharedTileCopier. The AMD row_major prefetch
pattern and fp32 -> half-precision downcast of the legacy free function
are not supported here.
Parameters:
- thread_layout (
Layout[thread_layout.shape_types, thread_layout.stride_types]): Layout describing how threads are organized over the copy. - swizzle (
Optional[Swizzle]): Optional swizzle applied to the shared-memory destination; the same swizzle must be used by any subsequent reader of the tile. - num_threads (
Int): Total number of threads in the thread block. Threads beyondthread_layout.size()do not participate. - thread_scope (
ThreadScope): Scope at which thread operations are performed.
Args:
- dst (
TileTensor[Storage=dst.Storage, address_space=AddressSpace.SHARED, linear_idx_type=dst.linear_idx_type]): Destination tile in shared memory. - src (
TileTensor[Storage=src.Storage, address_space=AddressSpace.LOCAL, linear_idx_type=src.linear_idx_type]): Source tile in local memory.