ttnn.rdiv

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

Performs the element-wise division of a scalar value by a tensor input and rounds the result using rounding_mode.

Input tensor must have BFLOAT16 data type.

Output tensor will have BFLOAT16 data type.

Parameters:

input_tensor (ttnn.Tensor) – the input tensor.
value (float) – denominator that is considered as numerator, which should be a non-zero float value.

Keyword Arguments:

rounding_mode (string) – rounding_mode value. Can be None, “trunc”, “floor”. Defaults to None.
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	TILE	2, 3, 4

System memory is not supported.

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 = 2

# Compute reverse division (value / tensor)
output = ttnn.rdiv(tensor, value, rounding_mode=None)
logger.info(f"Reverse division: {output}")