[object Object]

[object Object][object Object]undefined[object Object]

• Description:

  Divides the input tensor into two tensors, x1 and x2, along the last dimension, performs Threshold computation on x1, and multiplies the result by x2.

• Formula:

  Given an input tensor input with the last dimension length of 2d, the computation proceeds as follows:

  1. Divide input into two parts:$$x_1 = \text{input}[..., :d], \quad x_2 = \text{input}[..., d:]$$
  2. Apply the Threshold activation function to x1, defined as:$$\text{Threshold}(x, \text{threshold}) = \begin{cases} 0 & \text{if } x < \text{threshold} \\ x & \text{if } x \geq \text{threshold} \end{cases}$$ Thus:$$x_1 = \text{Threshold}(x_1, \text{threshold})$$
  3. The final output is the element-wise product of x1 and x2:$$\text{out} = x_1 \times x_2$$

[object Object]

Each operator has calls. First, aclnnFatreluMulGetWorkspaceSize is called to obtain the input parameters and compute the required workspace size based on the process. Then, aclnnFatreluMul is called to perform computation.

[object Object]

• Parameters

  [object Object]

• Returns

  [object Object]: status code. For details, see .

  The first-phase API implements input parameter verification. The following errors may be thrown.

  [object Object]

[object Object]

• Parameters

  [object Object]

• Returns

  [object Object]: status code. For details, see .

[object Object]

• Deterministic computation:

  • aclnnFatreluMul defaults to a deterministic implementation.

• For typical scenarios where the last dimension is a multiple of 16, if the last dimension is not 32-byte aligned, the small-operator tiling logic is recommended.

[object Object]

The following example is for reference only. For details, see .