ttnn.lcm

ttnn.lcm(input_tensor_a: ttnn.Tensor, input_tensor_b: ttnn.Tensor, *, memory_config: ttnn.MemoryConfig | None = None) → ttnn.Tensor

Computes Least common multiple of input_tensor_a and input_tensor_b and returns the tensor with the same layout as input_tensor_a. [supported range -1024 to 1024].

$${\mathrm{output}\mathrm{\_}\mathrm{tensor}}_i=\mathtt{\text{lcm}}({\mathrm{input}\mathrm{\_}\mathrm{tensor}\mathrm{\_}\mathrm{a}}_i,{\mathrm{input}\mathrm{\_}\mathrm{tensor}\mathrm{\_}\mathrm{b}}_i)$$

Parameters:

• input_tensor_a (ttnn.Tensor) – the input tensor.

• input_tensor_b (ttnn.Tensor) – the input tensor.

Keyword Arguments:

memory_config (ttnn.MemoryConfig, optional) – memory configuration for the operation. Defaults to None.

Returns:

ttnn.Tensor – the output tensor.

Note

Supported dtypes, layouts, and ranks:

Dtypes	Layouts	Ranks
INT32	TILE	2, 3, 4

Example

>>> tensor1 = ttnn.from_torch(torch.tensor([[1, 2], [3, 4]], dtype=torch.int32), dtype=ttnn.float32, layout=ttnn.TILE_LAYOUT, device=device)
>>> tensor2 = ttnn.from_torch(torch.tensor([[1, 2], [3, 4]], dtype=torch.int32), dtype=ttnn.float32, layout=ttnn.TILE_LAYOUT, device=device)
>>> output = ttnn.lcm(tensor1, tensor2)