ttnn.untilize

ttnn.untilize = FastOperation(python_fully_qualified_name='ttnn.untilize', function=<ttnn._ttnn.operations.data_movement.untilize_t object>, preprocess_golden_function_inputs=None, golden_function=None, postprocess_golden_function_outputs=None, is_cpp_operation=True, is_experimental=False)

Changes data layout of input tensor to ROW_MAJOR.

Input tensor must be on TT accelerator device, in TILE layout, and have BFLOAT16 data type.

Output tensor will be on TT accelerator device, in ROW_MAJOR layout, and have BFLOAT16 data type.

Args:

input_tensor (ttnn.Tensor): the input tensor.

Keyword Args:

memory_config (ttnn.MemoryConfig, optional): Memory configuration for the operation. Defaults to None. use_multicore (bool, optional): Whether to use multicore. Defaults to True. use_pack_untilize (bool, optional): Whether to use pack untilize. Defaults to True. sub_core_grids (ttnn.CoreRangeSet, optional): Sub core grids. Defaults to None. queue_id (int, optional): command queue id. Defaults to 0.

Returns:

List of ttnn.Tensor: the output tensor.