ttnn.heaviside

ttnn.heaviside(input_tensor: ttnn.Tensor, value: float, *, memory_config: ttnn.MemoryConfig = None, output_tensor: ttnn.Tensor = None) → ttnn.Tensor

Applies heaviside to input_tensor element-wise with value.

\[\mathrm{output\_tensor}_i = \verb|heaviside|(\mathrm{input\_tensor}_i, \verb|value|)\]

Parameters:

input_tensor (ttnn.Tensor) – the input tensor.
value (float) – The value parameter for the Heaviside function.

Keyword Arguments:

memory_config (ttnn.MemoryConfig, optional) – Memory configuration for the operation. Defaults to None.
output_tensor (ttnn.Tensor, optional) – preallocated output tensor. 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

# Create a tensor with specific values
tensor = ttnn.from_torch(
    torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16),
    dtype=ttnn.bfloat16,
    layout=ttnn.TILE_LAYOUT,
    device=device,
)
value = 3

# Apply Heaviside step function
output = ttnn.heaviside(tensor, value)
logger.info(f"Heaviside: {output}")