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 trait
TransferAtom
Describes an instruction that moves elements from memory to memory, such as a DMA submit or cp.async.bulk, without passing through the issuer's registers.
Implemented traits
AnyType,
Atom,
Copyable,
Deinitable,
ImplicitlyCopyable,
Movable,
RegisterPassable,
TrivialRegisterPassable
comptime members
dst_map
comptime dst_map
Where each index writes the destination.
DstEngine
comptime DstEngine
The engine of the memory the instruction writes.
dtype
comptime dtype
The element type the instruction moves.
src_map
comptime src_map
Where each index reads the source.
SrcEngine
comptime SrcEngine
The engine of the memory the instruction reads.
Required methods
__call__
def __call__[T: DType, LD: TensorLayout, ED: TensorEngine, LS: TensorLayout, ES: TensorEngine](self, dst: MutTileTensor[T, LD, Engine=ED, address_space=dst.address_space, linear_idx_type=dst.linear_idx_type], src: ImmTileTensor[T, LS, Engine=ES, address_space=src.address_space, linear_idx_type=src.linear_idx_type]) -> Self.Completion.Result
Issues the instruction once.
Parameters:
- T (
DType): The operands' element type. - LD (
TensorLayout): The destination view's layout. - ED (
TensorEngine): The destination view's engine. - LS (
TensorLayout): The source view's layout. - ES (
TensorEngine): The source view's engine.
Args:
- dst (
MutTileTensor[T, LD, Engine=ED, address_space=dst.address_space, linear_idx_type=dst.linear_idx_type]): The memorydst_mapdescribes. - src (
ImmTileTensor[T, LS, Engine=ES, address_space=src.address_space, linear_idx_type=src.linear_idx_type]): The memorysrc_mapdescribes.
Returns:
_Self.Completion.Result: The instruction's handle for a HandleCompletion, else
nothing.