ttnn.div

ttnn.div(input_tensor_a: ttnn.Tensor, input_tensor_b: ttnn.Tensor or Number, *, memory_config: ttnn.MemoryConfig = None, accurate_mode: bool = false, round_mode: string = None, output_tensor: ttnn.Tensor = None) → ttnn.Tensor

Computes div for input_tensor_a and input_tensor_b and returns the tensor with the same layout as input_tensor_a

\[\begin{split}\mathrm{output}_i = \begin{cases} \mathrm{\left(\frac{\mathrm{input\_tensor\_a}_i}{\mathrm{input\_tensor\_b}_i}\right)}, & \text{if } \mathrm{round\_mode} = \mathrm{None} \\ \mathrm{\text{floor}\left(\frac{\mathrm{input\_tensor\_a}_i}{\mathrm{input\_tensor\_b}_i}\right)}, & \text{if } \mathrm{round\_mode} = \mathrm{floor} \\ \mathrm{\text{trunc}\left(\frac{\mathrm{input\_tensor\_a}_i}{\mathrm{input\_tensor\_b}_i}\right)}, & \text{if } \mathrm{round\_mode} = \mathrm{trunc} \end{cases}\end{split}\]
Parameters:

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

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

Keyword Arguments:

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

  • accurate_mode (bool, optional) – false if input_tensor_b is non-zero, else true (Only if the input tensor is not ComplexTensor). Defaults to false.

  • round_mode (string, optional) – can be None, floor and trunc (only if the input tensor is not ComplexTensor). Defaults to None.

  • output_tensor (ttnn.Tensor, optional) – preallocated output tensor. Defaults to None.

Returns:

ttnn.Tensor – the output tensor.

Binary elementwise operations, C=op(A,B), support input tensors A and B in row major and tile layout, in interleaved or sharded format (height, width or block sharded), in DRAM or L1. A and B are completely independent, and can have different tensor specs.

Broadcast of A and B operands is supported up to dimension 5 (DNCHW). Any dimensions of size 1 in either A or B will be expanded to match the other input, and data will be duplicated along that dimension. For example, if the shape of A is [2,1,1,32] and B is [1,16,8,1], the output shape will be [2,16,8,32]. The size of dimensions higher than 5 must match between A and B.

The output C also supports row major and tile layout, interleaved or sharded format (height, width or block sharded), in DRAM or L1. The tensor spec of C is independent of A and B, and can be explicitly set using the optional output tensor input; if not provided, the operation will attempt a best decision at an appropriate tensor spec. The dimensions of C, or equivalently the optional output tensor, must match the broadcast-matched size of A and B.

Performance considerations: Elementwise operations operate natively in tile format, tiled tensors are preferred as an input, and row-major tensors are tilized and untilized during the operation. L1 sharded layout is preferred, with no broadcast and matching tensor specs for A, B and C.

Note

Supported dtypes, layouts, and ranks:

Dtypes

Layouts

Ranks

BFLOAT16

TILE

2, 3, 4

Example

# Create two tensors for division
tensor1 = ttnn.from_torch(
    torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16), layout=ttnn.TILE_LAYOUT, device=device
)
tensor2 = ttnn.from_torch(
    torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16), layout=ttnn.TILE_LAYOUT, device=device
)

output = ttnn.div(tensor1, tensor2, accurate_mode=False, round_mode=None)
logger.info(f"Division result: {output}")

# Create tensor and scalar for division
tensor = ttnn.from_torch(
    torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16), layout=ttnn.TILE_LAYOUT, device=device
)
scalar = 3
output = ttnn.div(tensor, scalar, round_mode="floor")
logger.info(f"Division (tensor-scalar) result: {output}")