Skip to main content

Mojo function

pad_shape

pad_shape[input_type: DType, paddings_type: DType, single_thread_blocking_override: Bool](input_buf: TileTensor[input_type, LayoutType, origin, address_space=address_space, linear_idx_type=linear_idx_type, element_shape_types=element_shape_types], paddings_buf: TileTensor[paddings_type, LayoutType, origin, address_space=address_space, linear_idx_type=linear_idx_type, element_shape_types=element_shape_types]) -> IndexList[TileTensor[input_type, LayoutType, origin, address_space=address_space, linear_idx_type=linear_idx_type, element_shape_types=element_shape_types].rank]

Compute the output shape of a pad operation, and assert the inputs are compatible.

Parameters:

  • input_type (DType): Type of the input tensor.
  • paddings_type (DType): Type of the padding tensor.
  • single_thread_blocking_override (Bool): If True, then the operation is run synchronously using a single thread.

Args:

  • input_buf (TileTensor): The tensor to pad.
  • paddings_buf (TileTensor): The paddings tensor, of shape (input_rank, 2).

Returns:

IndexList: The output shape.

Was this page helpful?