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_dram_to_local
def copy_dram_to_local[thread_layout: Layout[thread_layout.shape_types, thread_layout.stride_types], *, num_threads: Int = thread_layout.size(), thread_scope: ThreadScope = ThreadScope.BLOCK](dst: TileTensor[Storage=dst.Storage, address_space=AddressSpace.LOCAL, linear_idx_type=dst.linear_idx_type], src: TileTensor[Storage=src.Storage, linear_idx_type=src.linear_idx_type])
Synchronously copies a tile from DRAM (generic memory) to registers.
Delegates to GenericToLocalTileCopier. The AMD buffer_load path of the
legacy free function is not supported here.
Parameters:
- thread_layout (
Layout[thread_layout.shape_types, thread_layout.stride_types]): Layout describing how threads are organized over the copy. - 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.LOCAL, linear_idx_type=dst.linear_idx_type]): Destination tile in local memory. - src (
TileTensor[Storage=src.Storage, linear_idx_type=src.linear_idx_type]): Source tile in generic memory.