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

• Description: Extends the permutation indices of sparse data from the table dimension to the batch dimension, applicable to scenarios where sparse features have different batch sizes across ranks.
• Formula:

$$len = outputOffset[i+1] - outputOffset[i]$$ $$outputPermuteOut[outputOffset[i]:outputOffset[i+1]] = arange(inputOffset[permute[i]],inputOffset[permute[i]]+len)$$ [object Object]

Each operator has calls. First, aclnnExpandIntoJaggedPermuteGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation flow. Then, aclnnExpandIntoJaggedPermute 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 validation. The following error codes may be returned.

  [object Object]

[object Object]

• Parameters

  [object Object]

• Return Value

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

[object Object]

• Deterministic computation:
  • aclnnExpandIntoJaggedPermute defaults to a deterministic implementation.

1. The shapes of inputOffset and outputOffset must be the same.

2. The data types of permute, inputOffset, outputOffset, and outputPermuteOut must be the same.

3. The values of outputOffset are strictly monotonically increasing, and the last value equals outputSize.

[object Object]

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