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 struct

GenericToSharedTileCopier

struct GenericToSharedTileCopier[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]

A TileCopier that moves a tile from generic memory into shared memory.

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 for bank-conflict mitigation. None produces a straight copy.
• ​num_threads (Int): Total number of threads in the thread block. Threads beyond thread_layout.size() do not participate.
• ​thread_scope (ThreadScope): Scope at which thread operations are performed (BLOCK or WARP). Defaults to ThreadScope.BLOCK.

Implemented traits

AnyType, Copyable, ImplicitlyCopyable, ImplicitlyDeletable, Movable, TileCopier

comptime members

dst_address_space

comptime dst_address_space = AddressSpace.SHARED

Destination AddressSpace this copier writes to.

src_address_space

comptime src_address_space = AddressSpace.GENERIC

Source AddressSpace this copier reads from.

Methods

copy

def copy(self, dst: TileTensor[Storage=dst.Storage, address_space=Self.dst_address_space, linear_idx_type=dst.linear_idx_type], src: TileTensor[Storage=src.Storage, linear_idx_type=src.linear_idx_type])

Copies src in generic memory into dst in shared memory.

Masked bounds checking is not supported.

Args:

• ​dst (TileTensor[Storage=dst.Storage, address_space=Self.dst_address_space, linear_idx_type=dst.linear_idx_type]): Destination tile in shared memory.
• ​src (TileTensor[Storage=src.Storage, linear_idx_type=src.linear_idx_type]): Source tile in generic memory.