Mojo function

lt_to_tt

lt_to_tt[dtype: DType, lt_layout: Layout, //, ResultLayout: TensorLayout = Layout[#kgen.variadic.reduce(DimList(VariadicParamList(#kgen.variadic.tabulate(len[IntTuple](lt_layout.shape), [idx: __mlir_type.index] _int_to_dim(lt_layout.shape[idx].value())))).value.value, base=, reducer=[PrevV: Variadic[CoordLike], VA: Variadic[Dim], idx: __mlir_type.index] #kgen.variadic.concat(PrevV, ComptimeInt[VA[idx]._value_or_missing] if (VA[idx] != -31337) else RuntimeInt[DType.int64])), #kgen.variadic.reduce(DimList(VariadicParamList(#kgen.variadic.tabulate(len[IntTuple](lt_layout.stride), [idx: __mlir_type.index] _int_to_dim(lt_layout.stride[idx].value())))).value.value, base=, reducer=[PrevV: Variadic[CoordLike], VA: Variadic[Dim], idx: __mlir_type.index] #kgen.variadic.concat(PrevV, ComptimeInt[VA[idx]._value_or_missing] if (VA[idx] != -31337) else RuntimeInt[DType.int64]))]](lt: LayoutTensor[dtype, lt_layout, lt.origin, address_space=lt.address_space, element_layout=lt.element_layout, layout_int_type=lt.layout_int_type, linear_idx_type=lt.linear_idx_type, masked=lt.masked, alignment=lt.alignment]) -> TileTensor[dtype, Layout[ResultLayout._shape_types, ResultLayout._stride_types], lt.origin]

Convert a LayoutTensor to a TileTensor.

Static dimensions (known at compile time) are preserved as ComptimeInt. Dynamic dimensions (UNKNOWN_VALUE) become RuntimeInt, filled from the LayoutTensor's runtime layout. Works for any flat rank.

By default the TileTensor layout is derived automatically from the LayoutTensor's legacy layout. Pass an explicit ResultLayout to override which dimensions are static vs runtime.

Parameters:

dtype (DType): Element type of the tensor.
lt_layout (Layout): The legacy Layout of the LayoutTensor.
ResultLayout (TensorLayout): The target TileTensor layout type. Defaults to LTToTTLayout[lt_layout].

Args:

lt (LayoutTensor): The LayoutTensor to convert.

Returns:

TileTensor: A TileTensor with the same data and equivalent layout.