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): Layout describing how threads are organized over the copy.
swizzle (Optional): 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, ImplicitlyDestructible, 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`

copy[element_size: Int](self, dst: TileTensor[dst.dtype, dst.LayoutType, dst.origin, address_space=GenericToSharedTileCopier[thread_layout, swizzle=swizzle, num_threads=num_threads, thread_scope=thread_scope].dst_address_space, linear_idx_type=dst.linear_idx_type, element_size=element_size], src: TileTensor[src.dtype, src.LayoutType, src.origin, linear_idx_type=src.linear_idx_type, element_size=element_size])

Copies src in generic memory into dst in shared memory.

Masked bounds checking is not supported.

Parameters:

element_size (Int): Number of scalar elements per logical element.

Args:

dst (TileTensor): Destination tile in shared memory.
src (TileTensor): Source tile in generic memory.

Parameters​

Implemented traits​

comptime members​

dst_address_space​

src_address_space​

Methods​

copy​