ttnn.polyval

ttnn.polyval(input_tensor: ttnn.Tensor, Coeffs: Vector of floats, *, memory_config: ttnn.MemoryConfig | None = None) → ttnn.Tensor

Computes polyval of all elements of input_tensor_a with coefficients coeffs and returns the tensor with the same layout as input_tensor_a

\[\mathrm{output\_tensor} = \sum_{i=0}^{n} (\mathrm{coeffs}_i) (\mathrm{input\_tensor}^i)\]

Parameters:

input_tensor (ttnn.Tensor) – the input tensor.
Coeffs (Vector of floats) – coefficients of the polynomial.

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
BFLOAT16, BFLOAT8_B	TILE	2, 3, 4

Example

>>> tensor = ttnn.from_torch(torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16), layout=ttnn.TILE_LAYOUT, device=device)
>>> coeffs = [1, 2, 3, 4]
>>> output = ttnn.polyval(tensor, coeffs)